Did You Hear of Such an AM Receiver? For DSB-Suppressed Carrier.

[KerimF]

Note1: The academic purpose of this thread could be read on reply #72
Note2: More details on replies #9 (LTspice), #14 (AM-FM equation), #40 (DSBSC vs SSBSC), #44 (to gurus in electronics)

The receiver of interest demodulates a special double sideband suppressed carrier (DSB-SC) signal.

The modulating signal is of speech (narrow baseband) or music (wide baseband).
The frequency of the suppressed carrier is 455 kHz (IF, Intermediate Frequency in AM receivers).
The carrier is also frequency modulated by 300 Hz sinewave with a frequency deviation +/- 30 KHz. (It may be called, therefore, FM-DSB-SC.)

To my knowledge, a graduate engineer from any faculty of RF communications wasn’t taught how it could be done, though a hobbyist can build it.
It doesn’t need I-Q signals (Costas Loop) or LC selective filter (Squaring method).
Its reliable simple topology could be integrated as a low-cost IC. This IC doesn’t exist because even an IEEE professional in AM communications has no idea how to do it.

But I suspect a few members here may have heard of it, right?

Happy NEW YEAR 2025

Kerim Fahme

Hint: It is based on conventional PLL.

[pardo-bsso]

We had the same conversation some months ago but I can't find the link right now

[KerimF]

Sorry for the delay, the battery of my old lap (15 years) decided to die now (right after I started this thread).
I couldn't replace it (or buy a new lap), once every few years, because of the sad events in my region since year 2011.
To avoid a crash now, I have to keep the lap in state of charging all the time. The problem is that we have at best 4/24 mains AC only, so we depend on external inverters/batteries during the rest of the day.

https://www.eevblog.com/forum/rf-microwave/a-simple-reliable-double-sideband-suppressed-carrier-(dsb-sc)-demodulator/

As you see, the previous thread was in the RF forum (around July 2023). I didn't continue it there after I realized that discussing of this DSB-SC demodulator (still unknown universally, though I had the chance to discover its basic topology since fall 1979 as an MS thesis) is related more to electronics than today's RF.

The irony is that the local people (even so-called professors in communications) still tell me that it is impossible for a local engineer (in an underdeveloped country) to know a technical practical idea not known in the developed ones. This doesn't surprise me because, on the internet, even the engineers in the developed countries find really hard to believe a non-familiar topology (or be interested to verify it for their own knowledge in the least) as long it is not approved first by certain top representatives of today's Science.

Naturally, if no one here likes (or is capable) to discuss it (this non-familiar topology of AM demodulation) in depth, electronically (formulas, parameters... for various applications), I agree with you that there is no need to keep this thread alive in this forum too.

[radiolistener]

Let's use matlab/octave.

Usual AM can be written as:

Code: [Select]

Fs = 384000;     % sample rate
N = Fs*3;       % sample length 3 seconds

A = 1;          % Carrier amplitude
M = 0.8;        % Message amplitude
m = M / A;      % Modulation index m = M / A

carrier = A * cos(7000 * 2*pi*(0:N-1)/Fs);
message =     cos(1    * 2*pi*(0:N-1)/Fs);      % Normalized

signal_am = (1 + m*message) .* carrier;

Could you write formula for your modulation, so we can test it?

[SteveThackery]

@KerimF: could you explain more clearly what is the purpose of this thread? I think then you would get more engagement.

The thread title is "Did you hear of...", to which the only answer is "Yes" or "No" - hardly the basis for an interesting discussion. Or is it supposed to be a test for forum members, to see if they can design a circuit that will receive such a signal? Or are you hoping to discuss the benefits of double sideband suppressed carrier? Please explain clearly what you want to discuss.

I learned about various modulation systems several decades ago, and I seem to recall that DSSC was a standard AM signal with the carrier not transmitted. Even more economical for transmitter power is single sideband suppressed carrier.  My understanding is that both carriers contain the same information, so there is no benefit in transmitting both.

So there you go: the sum total of my "knowledge". 

My question is this: what is the purpose of frequency modulating the carrier at 300Hz?  And don't forget to tell us what you want from this thread.

[KerimF]

Let's use matlab/octave.

Usual AM can be written as:

Code: [Select]

Fs = 384000;     % sample rate
N = Fs*3;       % sample length 3 seconds

A = 1;          % Carrier amplitude
M = 0.8;        % Message amplitude
m = M / A;      % Modulation index m = M / A

carrier = A * cos(7000 * 2*pi*(0:N-1)/Fs);
message =     cos(1    * 2*pi*(0:N-1)/Fs);      % Normalized

signal_am = (1 + m*message) .* carrier;

Could you write formula for your modulation, so we can test it?

Hi,

As you said, the above formulas are for the usual AM signal when the carrier is not suppressed, that is 0<m<1. In this case, the polarity of the carrier doesn't reverse.

If m>1, the carrier polarity reverses at zero crossing of the modulating signal.

I don't have Matlab (or the like). I guess you know that, in case the carrier is suppressed, A=0 and m=infinity. And let us assume you will write a code for this case (A=0), will Matlab tell us how to recover the missing carrier (frequency and phase) to recover the modulating signal?

For instance, do you have LTspice?

[CaptDon]

An I.C. to demodulate such a signal is not a product of high value since there is no practical purpose or commercial usage of such a signal. There is a signal which uses two forms of modulation at the same time. It is the modulation scheme used for the VHF Omni Range or the VOR device common in 99.9% of aircraft. As far as demodulating your 'example' is the 300Hz with 30KHz of deviation steady or does it vary? Are you wanting to recover both the 300Hz signal and the DSB modulation or just the DSB riding on a carrier of useless complexity? Is your 30KHz deviation actually + and - 30KHz for a total of 60KHz bandwidth? That is over 10% of the 455KHz bandwidth and would probably lead to some residual AM component due to bandwidth rolloff of the receiver I.F. strip. Can it be designed, yes, by an amateur radio technical hobbyist, probably yes. Can a college student design it and build it as a graduate thesis, I would say yes. Is there any point to building it, any use for it, probably NO.

[KerimF]

@KerimF: could you explain more clearly what is the purpose of this thread? I think then you would get more engagement.

The thread title is "Did you hear of...", to which the only answer is "Yes" or "No" - hardly the basis for an interesting discussion. Or is it supposed to be a test for forum members, to see if they can design a circuit that will receive such a signal? Or are you hoping to discuss the benefits of double sideband suppressed carrier? Please explain clearly what you want to discuss.

I learned about various modulation systems several decades ago, and I seem to recall that DSSC was a standard AM signal with the carrier not transmitted. Even more economical for transmitter power is single sideband suppressed carrier.  My understanding is that both carriers contain the same information, so there is no benefit in transmitting both.

So there you go: the sum total of my "knowledge". 

My question is this: what is the purpose of frequency modulating the carrier at 300Hz?  And don't forget to tell us what you want from this thread.

Hi Steve,

The two purposes of this thread are:
[1] To hear a "Yes" or "No".
[2] In case someone is curious about it, and he is good in math and electronics, I can start with him a technical discussion after providing all what I did, since no one is perfect, to see how it could be updated and be applied for certain applications.

You are right, the advantages of SSB-SC are narrower bandwidth and lower power (half).

On the other hand, the advantage of DSB-SC, in case the simple reliable DSB-SC demodulator is used (not of Costas Loop or Squaring method), is that the proper reception is not sensitive to the carrier frequency variation, at the transmitter and receiver sides.
I gave an exaggerated example by modulating the carrier frequency at 300Hz with a relatively wide bandwidth +/- 30 KHz (covering 6 channels on MW band).
For instance, I used this added frequency modulation, though at 6Hz only, as a scrambling way in my private RF voice links in the 80's. Listeners on conventional AM receivers (on MW band) used to hear sort of noisy interference every time a voice signal was transmitted. (I also took advantage of this demodulator on FM band since it doesn't need a pilot. But this has another story).

By the way, in 1979 at the university, the idea of my MS thesis was to prove that receiving more information (two symmetrical sidebands) should let the recovery of the modulating signal simpler and more reliable/practical than receiving less information (one single band). This was the main idea behind this novel DSB-SC demodulator.
After 3 months of consecutive failures at the university lab, I built, during the last 3 days and as the last design I thought of, the first prototype of this demodulator. To my big surprise, it worked very well though it shouldn't work at all, in theory. Then, I had to return home for financial reason where I rebuilt it and was able to find out the 'minor' imperfection in the prototype that let the PLL be locked to the suppressed carrier.
Of course, after 45 years, I had enough time to analyze almost everything about its topology.

In brief, the big image of the DSB-SC system is completed, its transmitter and receiver are simple to build (relative to other systems) besides the frequency lock function (one example, for controlled toys, in case the low-cost DSB-SC demodulator IC is made).

Kerim

[KerimF]

An I.C. to demodulate such a signal is not a product of high value since there is no practical purpose or commercial usage of such a signal.

You are totally right since FCC doesn't give licenses for DSB in general.

As far as demodulating your 'example' is the 300Hz with 30KHz of deviation steady or does it vary? Are you wanting to recover both the 300Hz signal and the DSB modulation or just the DSB riding on a carrier of useless complexity? Is your 30KHz deviation actually + and - 30KHz for a total of 60KHz bandwidth? That is over 10% of the 455KHz bandwidth and would probably lead to some residual AM component due to bandwidth rolloff of the receiver I.F. strip.

I deliberately exaggerated the FM modulation to show its very low sensitivity to the variation of the carrier frequency.
And yes, by adding a LPF at VCO_in, the demodulator recovers two modulating signals simultaneously (from AM and FM).

Can it be designed, yes, by an amateur radio technical hobbyist, probably yes. Can a college student design it and build it as a graduate thesis, I would say yes. Is there any point to building it, any use for it, or any point to this conversation, NO.

I agree with what you said.

For instance, to make money from a novel idea, there will be a need to think of novel applications for it as well.
Unfortunately, I am not rich to start novel commercial projects that take advantage of this simple low-cost topology.

[KerimF]

Those who are still enthusiastic in electronics basics may like to comment technically on the uploaded example. Its Vcc=10V so that CD4046 can be used at 2*fc [910 kHz +/- 155 kHz].

I also uploaded screen shots to those who don’t have LTspice, to run the files in 'FM_DSB-SC_455K_10V_v1.zip'.



Any question is welcomed.
Please read my few previous posts to avoid repeating things.

[geggi1]

If you want to simulate the modulation and demodulation you can look into GNU-radio that is a freeware. Together with a SDR tv dongle you can demodulate almost anything.
As a replacement for Matlab have a look into Scilab that is a freeware equivalant.

[KerimF]

FCC licences are given for 4kHz bandwidth in general. This is good to transmit voice by SSB.

It may be possible to transmit voice by using DSB-SC in 4 kHz bandwidth if we apply the technique of 'Narrow Band Voice Transmission'.
But I am not sure if the added complexity at the baseband side is compensated by simplifying other parts in the transmitter and receiver in order to take advantage of the frequency lock.

[KerimF]

If you want to simulate the modulation and demodulation you can look into GNU-radio that is a freeware. Together with a SDR tv dongle you can demodulate almost anything.
As a replacement for Matlab have a look into Scilab that is a freeware equivalant.

Thank you for your valuable suggestions. Unfortunately, from where I live, I can't access anymore (since around 15 years ago) any technical tool offered, for free or not, on the internet... due to the world's sanctions applied on the people among whom I was born and live.

Would you please notify me if any of these tools can help you design the receiver on post #1 (just its DSB-SC demodulator, when the suppressed carrier is frequency modulated)?


 

[radiolistener]

Thank you for your valuable suggestions. Unfortunately, from where I live, I can't access anymore (since around 15 years ago) any technical tool offered, for free or not, on the internet... due to the world's sanctions applied on the people among whom I was born and live.

I'm using GNU Octave which is a free alternative for Matlab. It uses the same syntax and libraries with the same functions, so you can share your code with Matlab (with some limitations). This is complete free and open tool and is not limited by any kind of "sanctions". You can get its source code and use it for free, the only limitation is to keep all derivative products also free and open with providing its source code.

If you want to analyze your modulation scheme, you first need to express it mathematically. This will allow you to analyze and validate your ideas in a mathematical form, as is customary in modern science. Matlab/Octave simply provides a way to formalize and test your ideas in mathematical form.

For instance, do you have LTspice?

Before doing it in LTspice, we're needs to analyze it in math form, it allows to check if LTSpice circuit is implemented correctly.

As you said, the above formulas are for the usual AM signal when the carrier is not suppressed, that is 0<m<1. In this case, the polarity of the carrier doesn't reverse.

If m>1, the carrier polarity reverses at zero crossing of the modulating signal.

I don't have Matlab (or the like). I guess you know that, in case the carrier is suppressed, A=0 and m=infinity. And let us assume you will write a code for this case (A=0), will Matlab tell us how to recover the missing carrier (frequency and phase) to recover the modulating signal?

DSB signal can be expressed in math with just removing "1 +" field from expression.

Here is example for both AM and DSB modulation for 7000 Hz carrier and 1 Hz message:

Code: [Select]

Fs = 384000;
N = 2^16;

A = 1;       % Carrier amplitude
M = 0.8;     % Message amplitude
m = M / A;   % AM Modulation index m = M / A

carrier = A * cos(7000 * 2*pi*(0:N-1)/Fs);
message = M * sin(1    * 2*pi*(0:N-1)/Fs);
   
% AM modulation:
signal_am = (1 + message/A) .* carrier;

% DSB modulation:
signal_dsb = message .* carrier;

As you can see this "1+" field in AM modulation is multiplied by carrier and so adding carrier to AM modulation output, but it is missing from DSB output. This explains why carrier is missing from DSB modulation in math form.

Here is spectrum of AM modulated signal from example above:


And here is spectrum of DSB modulated signal from example above:


Can you explain your modulation in math form, so we can analyze and test it before implementation?

[KerimF]

@radiolistener
Sorry, I don’t know your syntax. I use Excel only for my calculations.

The time domain equation of the received signal v(t) is:

v(t) = Ac*sin(W1*t)*cos[Wc*t + (dF/F2)*sin(W2*t)]

where:
Ac = 1.8 V
W1 = 2*pi*4000 rad/sec [in case the AM modulating signal is 4 kHz]
W2 = 2*pi*300 rad/sec [in case the FM modulating signal is 300 Hz]
Wc = 2*pi*455000 rad/sec [in case the carrier frequency is IF]
dF = 30000 Hz [the maximum frequency deviation, 30 kHz]
F2 = 300 Hz [see W2 above]

I hope this helps.

[KerimF]

If a carrier (say 100 kHz) is amplitude modulated by a sinewave (say 10 kHz), its spectrum bandwidth is...
If a carrier (say 100 kHz) is frequency modulated by a sinewave (say 10 kHz) with a small deviation (say 100 Hz), its spectrum bandwidth is...
If the 100 kHz carrier is amplitude modulated by a 10 kHz and frequency modulated by a 10 kHz sinewave with a 100 Hz deviation, its spectrum bandwidth is...

[mawyatt]

v(t) = Ac*sin(W1*t)*cos[Wc*t + (dF/F2)*sin(W2*t)]

where:
Ac = 1.8 V
W1 = 2*pi*4000 rad/sec [in case the AM modulating signal is 4 kHz]
W2 = 2*pi*300 rad/sec [in case the FM modulating signal is 300 Hz]
Wc = 2*pi*455000 rad/sec [in case the carrier frequency is IF]
dF = 30000 Hz [the maximum frequency deviation, 30 kHz]
F2 = 300 Hz [see W2 above]

I hope this helps.

The term "(dF/F2)*sin(W2*t)" apparently is not in radians per your definitions? The maximum absolute value of such is +-dF/F2 or +-100, not sure if this is what was intended?

Best

[KerimF]

@mawyatt

Let us assume that B (beta) is the maximum deviation of the carrier phase:

v(t) = Ac*cos[Wc*t + B*sin(Wa*t)]

We get the instantaneous frequency by the derivative of [Wc*t + B*sin(Wa*t)]:

F = Wc/(2*pi) + B*Wa/(2*pi)*cos(Wa*t)
F= Fc + B*Fa*cos(Wa*t)

Therefore :
dF = B*Fa [dF=the maximum frequency deviation and Fa=the frequency of the FM modulating signal]]
B = dF / Fa

The above equation becomes:
v(t) = Ac*cos[Wc*t + dF/Fa*sin(Wa*t)] [corrected]

[mawyatt]

@mawyatt

Let us assume that B (beta) is the maximum deviation of the carrier phase:

v(t) = Ac*cos[Wc*t + B*sin(Wa*t)]

We get the instantaneous frequency by the derivative of [Wc*t + B*sin(Wa*t)]:

F = Wc/(2*pi) + B*Wa/(2*pi)*cos(Wa*t)
F= Fc + B*Fa*cos(Wa*t)

Therefore :
dF = B*Fa [dF=the maximum frequency deviation and Fa=the frequency of the FM modulating signal]]
B = dF / Fa

The above equation becomes:
v(t) = Ac*cos[Wc*t + dF / Fa (Wa*t)]

Those 2 equations are not the same tho!!

Example at T=1 the 1st equations cos argument is {Wc + Sin(Wa)}, while the second equations cos argument is {Wc + (dF/Fa)Wa}!!

Best

[KerimF]

@mawyatt
So, I wonder what your right equation of FM modulation is... v(t)=...

I see... I missed the 'sin', sorry

[mawyatt]

Well all we know is that mathematically in reference to above the max argument for the cos is Wc + B and the 2nd equation cos argument is Wc + (dF/Fa)*Wa. These cos arguments aren't equal @ T=1 unless B = (dF/Fa)*Wa and Sin(Wa) =1!!

Best

[KerimF]

It seems you didn't notice yet that I corrected the second (final) equation on my post #17, thanks to you:

v(t) = Ac*cos[Wc*t + dF/Fa*sin(Wa*t)] [corrected]

Best

[mawyatt]

Didn't note your correction, thanks!!

Best

[KerimF]

I'm using GNU Octave which is a free alternative for Matlab. It uses the same syntax and libraries with the same functions, so you can share your code with Matlab (with some limitations). This is complete free and open tool and is not limited by any kind of "sanctions". You can get its source code and use it for free, the only limitation is to keep all derivative products also free and open with providing its source code.

I wish you are right. But facts are facts.
On our dear planet, Earth, humans have been forced, since always in human history, to live in different, if not divided, worlds (after all, this is how the world is designed, and no one can change it).

[RoGeorge]

Octave is like Matlab, just that Octave is free.  If you can't download Octave from where you are, try using Tor Browser (not torrents, though a torrent client might work too), and visit the Octave download page using the Tor Browser instead of whatever browser you may be using now.  Tor behaves like a VPN, it accesses the Internet as if you were from somewhere else.

https://www.torproject.org/download/
https://octave.org/download

[coppice]

Octave is like Matlab, just that Octave is free.  If you can't download Octave from where you are, try using Tor Browser (not torrents, though a torrent client might work too), and visit the Octave download page using the Tor Browser instead of whatever browser you may be using now.  Tor behaves like a VPN, it accesses the Internet as if you were from somewhere else.

Note where the OP is. People in Syria, Iran, and North Korea are restricted in various ways the rest of the planet are not.

[KerimF]

Octave is like Matlab, just that Octave is free.  If you can't download Octave from where you are, try using Tor Browser (not torrents, though a torrent client might work too), and visit the Octave download page using the Tor Browser instead of whatever browser you may be using now.  Tor behaves like a VPN, it accesses the Internet as if you were from somewhere else.

https://www.torproject.org/download/
https://octave.org/download

I was able to open the page of https://octave.org/download , thank you. It directed me to other sites since my OS is W7, 32 bits.

I bought my today/old laptop a few months before March 2011 after which we had no mains AC, fuel and water for many years (we had just daily missiles over the streets and buildings at random). Now, we have 4/24 mains AC at best, and enough fuel to warm one room for a couple of hours (fortunately we are allowed to have fresh water) while almost all private businesses in the city (including mine) are paralyzed.

I am 75, so I think it is a bit late for me now to learn how to use professionally a versatile tool as Octave (which likely needs other resources) while I live in the actual living conditions.

Anyway, thank you again for your care.

[KerimF]

The simple trick that lets PLL be locked despite the polarity reversal of the carrier is the frequency doubler (see U2 and U4, XOR gates).

[KerimF]

In every PLL circuit, its crucial part to be designed properly is its LPF (R9, R10 and C6 in the uploaded example) to have a stable and fast response.

[KerimF]

R7 and C5 forms a delay circuit to let the e-switch of CD4066 (U7) in phase with the suppressed carrier when its frequency equals to half of the VCO mid-frequency.
Although it will be out of phase at higher and lower frequencies, the phase difference is relatively small (this reduces the gain of the synchronous detector) even when the carrier is at the limits +/- 30 kHz.
 

[RoGeorge]

Note where the OP is. People in Syria, Iran, and North Korea are restricted in various ways the rest of the planet are not.

You must be kidding when saying the rest of the planet is not under censorship/restriction.  It is, just that maybe not that severe restriction, but the restrictions are increasing fast, haven't anybody else noticed?  In fact the UK levels of censorship increased at alarming rates in the recent years.  Similar for where I live, EU/Romania.  I can't visit certain websites.

Don't want to go into politics, but FIY, the level of censorship and propaganda in the western world right now is bigger than the one I've seen under Ceausescu dictatorship here in Romania, about 35+ years ago.  I'm not a nostalgic for communists regimes, or for dictators long gone, just that 30 years ago I would have never thought the western world would catch up with those dystopian levels of propaganda and censorship we used to have during the Ceausescu's regime.

I was very happy when Romania escaped the soviet influence, and joined to EU and to the western world, except now it turned into a clown world, lying in your face, all day long.  To give an example, last month our supreme court canceled the presidential elections in the middle of the process, because allegedly Tik-Toc influences.  No evidence, just that they canceled peoples votes.  Everybody here in Romania is outraged.  Same like everybody else in EU is outraged for being invaded and displaced by illegal immigrants with 10 times the birth rates of EU nations.  Same as people in UK is outraged for being arrested over misgendering people on twitter and such.

The censorship in the west is higher than ever, and increasing.  In this rhythm, won't be long till we catch up with North Korea.  We've already reached the levels I know from the former Communism/Socialism during Ceausescu. 

Sorry for the offtopic slip, but pretending everything is fine at this point is suicidal for the west.

As for the Tor Browser (Onion network) don't know if it can be used from where the OP is, might work, or might not work, worth a try.  Same for the torrent network, might work or might not, worth a try to install qBittorent, or alike torrent client with a search plugin included.

[KerimF]

By adding a LPF after VCO_in, the FM modulating signal can also be received.
In theory, this FM modulating frequency can be made high. So, one may think that the AM and FM modulating signals could be of a stereo system, left and right (having 9 kHz bandwidth each, for example). In this case, the FM-AM bandwidth of the transmitted signal would be... who can guess it

[radiolistener]

On our dear planet, Earth, humans have been forced, since always in human history, to live in different, if not divided, worlds (after all, this is how the world is designed, and no one can change it).

Just FYI, I'm living in the country where currently is one of the most bloody war of century with more than 1 millions deaths, I survived military assault on my city with everyday shelling and bombing for about 6 months long, and living in this hell for almost 3 years. Because there is no way to leave it for civilians, it is unofficially prohibited (in violation of the requirements of the constitution and laws). So if you know what I'm talking about, you should know that I'm living in one of the restricted place of the world at the moment. But I don't see the reason why you cannot use GNU Octave, especially if you have access to the internet.

This is even more confusing, since you're using LTSpice.


Here is example of AM, DSB and FM modulation written in Octave:

Code: [Select]

Fs = 384000;    % Sample rate
N = 2^24;       % Sample length

A = 1;          % Carrier amplitude
M = 0.8;        % Message amplitude
%m = M / A;      % AM modulation index m = M / A

wc = 7000 * 2*pi;   % Carrier frequency in radians
wm = 1    * 2*pi;   % Message frequency in radians
wd = 1000 * 2*pi;   % FM deviation in radians

message = M * sin(wm * (0:N-1)/Fs);
carrier = A * cos(wc * (0:N-1)/Fs);
   
% AM modulated signal
signal_am = (1 + message/A) .* carrier;   

% DSB modulated signal
signal_dsb = message .* carrier;

% FM modulated signal
phase_fm = cumsum((message * wd + wc) / Fs);
signal_fm = cos(phase_fm);

and here is the spectrum of this FM signal:


Do I understand correctly that your modulation scheme is a usual DSB modulation where you trying to use a special signal instead of carrier which is represented as FM modulation of 455 kHz carrier with 300 Hz message with 30 kHz deviation?

If so, I'm not sure what is the reason to use such complicated signal as a carrier? Is it some kind of attempt to encrypt the message?

[KerimF]

But I don't see the reason why you cannot use GNU Octave, especially if you have access to the internet.

Please note that I answered it in my reply #26.

This is even more confusing, since you're using LTSpice.

I am using its rather very old version LTspiceIV. I couldn't download any of its newer versions after LT was acquired by Analog Devices (which, unlike LT, has to obey the rules of its system). To my big surprise I was able to join its forum (of AD) to talk about this demodulator. A few days later, I got an email with an apology that AD had to ban me to avoid breaking the rules. It was in Holidays season, so I wish the sender a Merry Christmas and Happy New Year Eve).   

Here is example of AM, DSB and FM modulation written in Octave:

Code: [Select]

Fs = 384000;    % Sample rate
N = 2^24;       % Sample length

A = 1;          % Carrier amplitude
M = 0.8;        % Message amplitude
%m = M / A;      % AM modulation index m = M / A

wc = 7000 * 2*pi;   % Carrier frequency in radians
wm = 1    * 2*pi;   % Message frequency in radians
wd = 1000 * 2*pi;   % FM deviation in radians

message = M * sin(wm * (0:N-1)/Fs);
carrier = A * cos(wc * (0:N-1)/Fs);
   
% AM modulated signal
signal_am = (1 + message/A) .* carrier;   

% DSB modulated signal
signal_dsb = message .* carrier;

% FM modulated signal
phase_fm = cumsum((message * wd + wc) / Fs);
signal_fm = cos(phase_fm);

Do I understand correctly that your modulation scheme is a usual DSB modulation where you trying to use a special signal instead of carrier which is represented as FM modulation of 455 kHz carrier with 300 Hz message with 30 kHz deviation?

If so, I'm not sure what is the reason to use such complicated signal as a carrier? Is it some kind of attempt to encrypt the message?

I also cannot understand why you insist to use Octave other than finding the effective FM-AM signal bandwidth which could be deduced from the separate study of AM and FM modulations.

[KerimF]

If so, I'm not sure what is the reason to use such complicated signal as a carrier? Is it some kind of attempt to encrypt the message?

I guess you likely missed reading my reply #7.
 

[radiolistener]

Please note that I answered it in my reply #26.

I bought my today/old laptop a few months before March 2011 after which we had no mains AC, fuel and water for many years (we had just daily missiles over the streets and buildings at random). Now, we have 4/24 mains AC at best, and enough fuel to warm one room for a couple of hours (fortunately we are allowed to have fresh water) while almost all private businesses in the city (including mine) are paralyzed.

We also had a period when AC mains was delivered very rarely - several hours per several days or something like that, but it don't prevent to use computer from batteries. Usually it happened after next big bomb blast. I have 222 Wh battery for this case, which allows to run a tablet for about 24 hours or my small desktop for 7 hours. Usually internet is going offline after 3-4 hours of AC outage, but you can do some programming or development offline.

Missiles and drones still flying over my city and I hear air strike alarm and/or blasts sounds every hour, now it happens more rare, but still happens and everyone here is already used to it and doesn't pay attention. Of course there is a risk that it can hit some civilian building, and many building was damaged in that way (for example yesterday we have civilian building damage with bomb), but you cannot do anything with this.

I also cannot understand why you insist to use Octave other than finding the effective FM-AM signal bandwidth which could be deduced from the separate study of AM and FM modulations.

Octave allows to generate signal, estimate its parameters and quality and generate test signals which can be used in simulator for testing. You can do all things in the math first and then implement it in circuit and can test it in simulator. In other words you can make sure that all things works as expected and estimate it's quality even with no need to build a real circuit.

I am using its rather very old version LTspiceIV. I couldn't download any of its newer versions after LT was acquired by Analog Devices (which, unlike LT, has to obey the rules of its system). To my big surprise I was able to join its forum (of AD) to talk about this demodulator. A few days later, I got an email with an apology that AD had to ban me to avoid breaking the rules. It was in Holidays season, so I wish the sender a Merry Christmas and Happy New Year Eve).   

You can try simulator in KiCad. It also has circuit simulator, it is similar to LTSplice, but a little bit different. It is open source and I think it is probably available with no issue for you.

[KerimF]

Octave allows to generate signal, estimate its parameters and quality and generate test signals which can be used in simulator for testing. You can do all things in the math first and then implement it in circuit and can test it in simulator. In other words you can make sure that all things works as expected and estimate it's quality even with no need to build a real circuit.

What could I add?
I am fortunate that my old laptop has a genuine Excel (2007) by which I was (still am) able to solve all my design problems which are no more related to communications. Since year 1975, I used to produce various controllers which were needed by the local consumers in every period of time.

I just did this modulator as an MS thesis. Then, I used it for many years in the 80's to scramble my short-range RF voice links between home and workplace (3 km) till I got a phone line at home.

It happens that LTspice and Excel complement each other. For example, LTspice has FFT function (and THD) and Excel solves non-linear equations.

[KerimF]

I forgot to add that I do have Kicad though a very old version. I got it before the Kicad doors started to close too. This old version is good enough for the local old PCB services I print the PCB layout as PDF and send it to the PCB maker.

For instance, before year 2011, I used to send the designed schematic only to China where the Chinese engineers drew its layout, made its PCB, assembled its components and test the final ordered boards before exporting them to my place. This sort of easy life is now a thing of the past.
 

[dustooff]

Been following this thread as best I can, (not radio engineer).

By some coincidence this article came to life a few days ago,
https://www.allaboutcircuits.com/technical-articles/understanding-the-square-law-modulator-for-generating-am-signals

Initially I was curious as to the benefit of DSB-SC, it was not clear to me that the suppressed carrier was due to zero signal.
So it may be the main benefit is keeping a transmission path going without continuous carrier, thus making it hidden most of the time. (if necessary)

[radiolistener]

is this is what did you mean?

Code: [Select]

Fs = 1000000;   % Sample rate
N = 2^24;       % Sample length

A = 1;          % Carrier amplitude
M = 0.8;        % Message amplitude

wc = 455000 * 2*pi;   % Carrier for FM-modulated sub-carrier [frequency in radians]
ws = 300    * 2*pi;   % Message for FM-modulated sub-carrier [frequency in radians]
wd = 30000  * 2*pi;   % FM deviation for FM-modulated sub-carrier [frequency in radians]
wm = 1000   * 2*pi;   % Message frequency [frequency in radians]

subMessage = cos(ws * (0:N-1)/Fs);                      % 300 Hz sine
subCarrier = cos(cumsum((subMessage * wd + wc) / Fs));  % 455kHz FM modulated with 300 Hz

message = M * sin(wm * (0:N-1)/Fs);  % message 1 kHz sine

signal = message .* subCarrier;      % sub-carrier DSB modulated with message

%audiowrite("test.wav", [signal], Fs, "BitsPerSample", 32);



I tried to receive it with DSB, AM and FM demodulators, but it sounds like buzz. You can listen flac file in attachment on how it sounds on a usual receiver (it split on a three parts with different demodulators - DSB, AM and FM).

The main issue is that it requires 60-80 kHz bandwidth to transmit 1 kHz sine and it is unclear for me on how to reconstruct the carrier frequency and phase

[KerimF]

Been following this thread as best I can, (not radio engineer).

By some coincidence this article came to life a few days ago,
https://www.allaboutcircuits.com/technical-articles/understanding-the-square-law-modulator-for-generating-am-signals

Initially I was curious as to the benefit of DSB-SC, it was not clear to me that the suppressed carrier was due to zero signal.
So it may be the main benefit is keeping a transmission path going without continuous carrier, thus making it hidden most of the time. (if necessary)

Hi,

You got it. During silence periods there is no RF signal. This also applies on single sideband suppressed carrier system, SSB-SC.
The benefit of SSB is its reduced bandwidth (half of DSB), so the number of RF channels is doubled in a specific RF spectrum. But this has a price. The suppressed carrier cannot be restored from one side, it has to be generated in the receiver. This solves partially the recovery of the modulated signal since the generated carrier cannot be made in phase with the transmitted suppressed carrier. For this reason, the conventional envelop detector (with its limitation about the signal strength) has to be used to recover the modulating signal (also not in phase, but our ears are not sensitive to the phase variation of the audio signal).

The DSB-SC system was not recommended for two reasons. It needs twice the bandwidth of SSB (this is the main disadvantage of DSB). And it needs more power for the same receiver RF sensitivity. But this gives two extra bonuses. The carrier can be restored, frequency and phase, from the two symmetrical sidebands. So, the recovery of hi-fi audio signal can be achieved by using synchronous detection. The second benefit is that a relatively low strength of the RF signal doesn't distort the recovered signal as in the case of envelop detector.

There was (I say, there was, not there is) a third reason for which the DSB-SC wasn't recommended. Its known demodulators were more complex and less reliable than of the SSB-SC demodulators. The known topologies for DSB-SC demodulation were two. The first one is of Costas Loop which needs I-Q signals (in quadrature), not simple to build. And the second one is presented in your article (your URL above) which needs an LC selective filter which is somehow bulky.

In this thread, I presented a third topology (I knew and used it in real since the 80's, as explained earlier) which combines the previous two known topologies while being simpler and more reliable. It is simple because it doesn't need I-Q signals or an LC selective filter. It is more reliable because it locks to the suppressed carrier in a relatively wide spectrum (in my example here, Fc varies between 455-30 kHz and 455+30 kHz). Naturally, it can also recover the FM modulating signal (that is it could be seen as a double detector that recovers two signals at the same time).

But... there is always a BUT... the believers of 'Science' cannot add this third topology (which could be called 'Harmonic Loop', since 'Kerim Loop' is out of question, mainly in these days ), into their set of knowledge, before the today's representatives of 'Science' approve it officially.

[KerimF]

I tried to receive it with DSB, AM and FM demodulators, but it sounds like buzz. You can listen flac file in attachment on how it sounds on a usual receiver (it split on a three parts with different demodulators - DSB, AM and FM).

The main issue is that it requires 60-80 kHz bandwidth to transmit 1 kHz sine and it is unclear for me on how to reconstruct the carrier frequency and phase

Sorry, but I have to say it clearly to all readers here. Any AI robot has also no idea, at all, on how the presented FM-AM DSB-SC demodulator here could be made. I am afraid it is a novel solution that the world didn't recognize it universally yet.

Yes, a conventional AM detector, not my novel DSB-SC demodulator (discussed in this thread), detects the FM-AM signal of post #1 (an exaggerated example) as of a noisy interference.

[coppice]

Note where the OP is. People in Syria, Iran, and North Korea are restricted in various ways the rest of the planet are not.

You must be kidding when saying the rest of the planet is not under censorship/restriction.  It is, just that maybe not that severe restriction, but the restrictions are increasing fast, haven't anybody else noticed?  In fact the UK levels of censorship increased at alarming rates in the recent years.  Similar for where I live, EU/Romania.  I can't visit certain websites.

Where did I say the rest of the world was a paradise of freedom? I said those three countries have specific restrictions placed on them, which nowhere else does.  Lot of things are restricted for export to lots of places, but those three countries have a total ban on anything being supplied to them that has not been given explicit permission by an appropriate government. For example, see https://www.state.gov/iran-north-korea-and-syria-nonproliferation-act-sanctions-inksna/

[KerimF]

Fortunately, we all are allowed to talk together here as friends who care of each other, despite all sort of divisions in the world created (for money and power) by the powerful rich ruling systems.

[KerimF]

To those who have time to study the ‘Harmonic Loop’ demodulator, uploaded on reply #9, I repeat here its important points I mentioned ealier:

[1] There is a simple trick added to its conventional PLL that lets the PLL be locked to the suppressed carrier, frequency and phase, despite its polarity reversal at the zero crossings of the modulating signal. It is the frequency doubler (see U2 and U4, XOR gates). It could be used in other applications, for example, to double the frequency of a crystal.

[2] In every PLL circuit, the crucial part to be designed properly is its LPF (see R9, R10 and C6 in the uploaded example) in order to have a stable and fast response. On request, more details on how to calculate their values could be given, in case someone has no PC program (tool) made for such study/calculations.

[3] R7 and C5 are added between CD4013, U3, and CD4066, U7 (e-switch), to delay the phase of the recovered carrier and let it be in phase with the suppressed one when its frequency equals half of the VCO mid-frequency.
Although the two will be out of phase at higher and lower frequencies, their maximum phase difference is relatively small when the carrier is at the limits +/- 30 kHz. Please note that the phase difference reduces the gain of the synchronous detector.

[4] By adding a low pass filter at VCO_in, also the FM modulating signal can be recovered.
In theory, this FM modulating frequency can be made high (much higher than 300 Hz). So, one may think that the AM and FM modulating signals could be of a stereo system, left and right (having 9 kHz bandwidth each, for example).

This leads us to a question which was never asked at schools and universities
What is the effective bandwidth of an RF channel that uses an FM-AM signal (the carrier is AM and FM modulated at the same time)?
I can't access any AI robot. May someone ask one about it? Thank you.

[KerimF]

If this simple reliable DSB-SC demodulator was known in the early 80’s (soon after I knew it) and the new FM receivers, at that time, started using it, adding the pilot 19 kHz (for FM stereo) would be no more needed. This removal increases the power efficiency of the FM transmitters. Anyway, most transmissions are now made digital.

When I was in need, I took advantage of it (being unknown by the world) in the 80’s by transmitting the voice signal on 32768 Hz suppressed carrier (instead of 38 kHz of FM stereo) on the FM baseband. The conventional FM receivers detect just a silent channel during a conversation. And the lack of a pilot made impossible for an RF hacker (local or foreigner) to recover the voice signal properly. I used this technique for many years without being noticed

[KerimF]

If you want to simulate the modulation and demodulation you can look into GNU-radio that is a freeware. Together with a SDR tv dongle you can demodulate almost anything.

If someday you will find a tool, hardware or software, which can demodulate the FM-DSB-SC signal (described on post #1), I hope you will let me hear of it too because, to my knowledge, it doesn't exist yet to the world (other than the topology which I described in this thread). Thank you in advance.

[KerimF]

For instance, among the designs I rejected while I was looking, in 1979 as an MS thesis project, to build a simple reliable DSB-SC demodulator, it was the topology which was 'patented' for someone many years later (United States Patent 4430620). Its idea could be summarized:
“A DSB-SC signal could be demodulated without reinsertion of the carrier at the receiver. The received DSB-SC wave is amplified, demodulated by a full-wave rectifier. The rectifier output reversed in polarity at instants of successive zero crossings of the recovered signal.”

I couldn't accept it after I noticed that when the modulating signal becomes very close to zero before going up again (fake zero crossing), the output rectifier is fooled, and the output is reversed. In this case, the AC and DC voltages of the recovered signal are distorted.
And to determine when the reversing is needed or not, to avoid this sort of distortion, cannot be achieved by a simple circuit (the main purpose of the project).

I wonder who will be able to patent the topology of the DSB-SC 'Harmonic Loop' demodulator which we are discussing here. I will be glad to hear that someone will also take advantage of it, as I did in the 80's. Or it will be patented after I die

[KerimF]

Although no one here seems to be interested, for one reason or another, in my simple DSB-SC demodulator (non-existent yet to the world), we will see, in my next thread, how its topology could also be updated to receive/demodulate two signals in quadrature (yes, AM stereo).

Cheers

Note: Useful technical posts about my DSB-SC demodulator are at #1, #9, #14, #15, #40, #44,

[SteveThackery]

Although no one here seems to be interested, for one reason or another, in my simple DSB-SC demodulator (non-existent yet to the world).....

I don't think people are uninterested, it's just that what you are discussing might be seen as a "curiosity" of limited relevance in the real world. Yes, it is interesting and intriguing, but if you are hoping to see the world of broadcast radio adopt this technology en masse, you will surely be disappointed. Another way to express it is that it looks a bit like a solution looking for a problem.

Personally I do find it interesting although I can't follow the theory and mathematics so I cannot make any kind of useful contribution to this thread. For example, earlier on I asked why the carrier is frequency modulated, but I simply didn’t understand the answer. 

[KerimF]

I don't think people are uninterested, it's just that what you are discussing might be seen as a "curiosity" of limited relevance in the real world.

Yes, what you say here is indeed true.
In fact, in the real world, if a person who never served certain powerful rich families (owners of a big company or corporation for example), his work would have no relevance in the real world.
But my personal observation may be wrong if you can help me know a famous inventor who wasn't working under the direction of certain big heads (unless his family is rich and famous already).

Yes, it is interesting and intriguing, but if you are hoping to see the world of broadcast radio adopt this technology en masse, you will surely be disappointed. Another way to express it is that it looks a bit like a solution looking for a problem.

It happens that, since I was in schools then universities, I studied hard while respecting always my teachers, good and evil, to get enough knowledge that helps me gain my living in the least while being really independent. To me, my independence is worth more than all treasures of the world. So, I was never tried to be rich (hired for a high-salary job for example) and lose it (naturally, this disappointed all my relatives who use to run after money). In my private business (since 1975 till now) I try my best that my various designs and products please my local customers, not the world.

So, I have the impression that I did a big mistake to share my work here. Should this thread be removed? The moderators have the answer.

...earlier on I asked why the carrier is frequency modulated, but I simply didn’t understand the answer. 

You didn't... because you likely didn't also hear of the two known topologies for the DSB-SC demodulators, Costas Loop and the Squaring method. Both cannot track the frequency of the suppressed carrier if it varies in a relatively wide spectrum. This is why I deliberately modulated, with exaggeration, the frequency of the carrier to show, clearly, to the academic professionals in RF communications around the world that their two known topologies are things of the past if they are rational and realistic, are they?

In a real application, the frequency of the carrier doesn't need to be modulated, unless there is a need to also send a low-rate data (as FM) while the AM transmission is active.

[KerimF]

A few times earlier I raised the following question, following the French style (no options):
What is the effective bandwidth of an RF channel that uses an FM-AM signal (the carrier is AM and FM modulated at the same time)?

I repeated it here by following the American style. Now you can select the right answer:

[1] BW_am + BW_fm
[2] BW_am
[3] BW_fm
[4] BW_am + BW_fm/2
[5] BW_am/2 + BW_fm
[6] (BW_am + BW_fm)/2

Cheers

Added: We can assume that BW_fm < BW_am

[radiolistener]

but if you are hoping to see the world of broadcast radio adopt this technology en masse

It is not allowed, since transmission with 80 kHz bandwidth on short wave is not allowed, such transmission just occupies the entire broadcast band, no worse than a jammer, since FM modulation provides constant power in entire operating bandwidth. Thus, one such station will jam dozens of other broadcasting stations. With no any kind of benefit. It will need 8x times more power for transmission and complicated demodulator to receive it.

And I suspect it will be much more sensitive to a multipath propagation issues on short wave than a usual FM modulation with much less bandwidth. It will be also very sensitive to a moving transmitter/receiver due to Doppler effect.

I see it this way: this type of modulation has all the disadvantages of both AM and FM modulation, but does not add any advantages. On the contrary, it takes up too much bandwidth.

[mawyatt]

Almost all communications systems today are digital, wether wired, optical or wireless. Over the past half century considerable effort has gone into pushing as many bits as fast as possible thru these communication channel limits utilizing all sorts of modulation schemes employing AM, FM, PM and various combinations of such.

Unless one can improve the through-put/spectral efficiency of modern digital comms and stay within the regulations, any "new" ideas are likely to fall on deaf ears!!

Best

[KerimF]

but if you are hoping to see the world of broadcast radio adopt this technology en masse

It is not allowed, since transmission with 80 kHz bandwidth on short wave is not allowed, such transmission just occupies the entire broadcast band, no worse than a jammer, since FM modulation provides constant power in entire operating bandwidth. Thus, one such station will jam dozens of other broadcasting stations. With no any kind of benefit. It will need 8x times more power for transmission and complicated demodulator to receive it.

And I suspect it will be much more sensitive to a multipath propagation issues on short wave than a usual FM modulation with much less bandwidth.

What could I add? when someone doesn't have time to read all my replies like the one in the recent post #50 in which I answered the same question and ended it with:

In a real application, the frequency of the carrier doesn't need to be modulated, unless there is a need to also send a low-rate data (as FM) while the AM transmission is active.

[coppice]

Almost all communications systems today are digital, wether wired, optical or wireless. Over the past half century considerable effort has gone into pushing as many bits as fast as possible thru these communication channel limits utilizing all sorts of modulation schemes employing AM, FM, PM and various combinations of such.

Unless one can improve the through-put/spectral efficiency of modern digital comms and stay within the regulations, any "new" ideas are likely to fall on deaf ears!!

Best

Yep. For pretty much any comms idea right now you have to ask the question "is this competitive with OFDM, or so astonishingly low power it can carve out a niche?".

[radiolistener]

Added: We can assume that BW_fm < BW_am

No, FM modulation requires much more bandwidth for the same message signal dynamic range than AM modulation.
AM modulation just use double bandwidth of the message signal. This is why FM is not used on short wave, where bandwidth is very limited.

FM modulation is very complicated for math analysis due to it's non-linear properties, but as I know it requires about 10x times more bandwidth than message signal in order to keep dynamic range and bandwidth of the message signal at good quality with low distortions.

The most effective analog modulation is SSB (LSB or USB). Its bandwidth is equal to a message bandwidth. And it also very efficient from power point of view, since it don't need to transmit something when there is DC on message signal input.

[KerimF]

Almost all communications systems today are digital, wether wired, optical or wireless. Over the past half century considerable effort has gone into pushing as many bits as fast as possible thru these communication channel limits utilizing all sorts of modulation schemes employing AM, FM, PM and various combinations of such.

Unless one can improve the through-put/spectral efficiency of modern digital comms and stay within the regulations, any "new" ideas are likely to fall on deaf ears!!

Best

Sorry, aren't you suggesting that almost all analogue solutions in RF communications need to be removed now from the university's textbooks?
Or just the new ones are not supposed to be added to the old obsolete solutions (like of Costas and Squaring method) that the undergraduate students have to hear of, despite they are no more useful in today's digital world.

Sorry, if I couldn't understand you well.

[KerimF]

Added: We can assume that BW_fm < BW_am

No, FM modulation requires much more bandwidth for the same message signal dynamic range than AM modulation.
AM modulation just use double bandwidth of the message signal. This is why FM is not used on short wave, where bandwidth is very limited.

The most effective analog modulation is SSB (LSB or USB). Its bandwidth is equal to a message bandwidth. And it also very efficient from power point of view, since it don't need to transmit something when there is DC on message signal input.

It looks here as if we live on the famous Babylon Tower on which no one understand what another says

I agree with you, but it seems to me that you didn't notice it was just an academic question. You don't need to know its right answer.

[radiolistener]

What could I add? when someone doesn't have time to read all my replies like the one in the recent post #50 in which I answered the same question and ended it with:

In a real application, the frequency of the carrier doesn't need to be modulated, unless there is a need to also send a low-rate data (as FM) while the AM transmission is active.

Sorry, but I don't see any explanation of advantage of such DSB modulation with FM modulated carrier in the post #50.

If you remove FM modulation for the carrier your modulation turns into a usual DSB, isn't it?

[mawyatt]

Sorry, aren't you suggesting that almost all analogue solutions in RF communications need to be removed now from the university's textbooks?
Or just the new ones are not supposed to be added to the old obsolete solutions (like of Costas and Squaring method) that the undergraduate students have to hear of, despite they are no more useful in today's digital world.

Sorry, if I couldn't understand you well.

Seems you are the one suggesting, example your new revolutionary DSB-SC modulation scheme. We are certainly not suggesting remove anything in the Electronics 101 Texts as one needs to understand the modulation fundamentals of AM, FM and PM before venturing into the more complex and spectral efficient modulation schemes in use today.

Best

[SteveThackery]

So, I have the impression that I did a big mistake to share my work here. Should this thread be removed? The moderators have the answer.

This is the third time you've said something that gives me the impression that there might be a chip on your shoulder, which is motivating you to try to prove that you are smarter than most of the established "experts" in the field over the past 70-odd years.

This is why I deliberately modulated, with exaggeration, the frequency of the carrier to show, clearly, to the academic professionals in RF communications around the world that their two known topologies are things of the past if they are rational and realistic, are they?

Yes, there you go again - a perfect example of what I've just said. Three things: firstly, the "academic professionals in RF communications around the world" aren't listening, and they won't listen unless you can come up with something compelling that delivers some major step forward.

Secondly, I think you are seriously underestimating these academic professionals.

Thirdly, and the showstopper: these professionals would be the first to agree that the "two known topologies" are indeed a thing of the past! Of course they are! Radio communications are digital almost everywhere APART from the legacy stuff that is a continuation of services that have been running since decades past. Nobody cares about AM, FM, SSB, DSB, suppressed carriers - they are mid-20th century technology and the world has moved on.  21st century broadcast television is digital; 21st century broadcast radio is digital.

If you really want to demonstrate how smart you are, invent something better than OFDM and the associated protocols in the stack. Arguing the toss over something that is 40 years obsolete isn't going to impress anyone.

[KerimF]

So, I have the impression that I did a big mistake to share my work here. Should this thread be removed? The moderators have the answer.

This is the third time you've said something that gives me the impression that there might be a chip on your shoulder, which is motivating you to try to prove that you are smarter than most of the established "experts" in the field over the past 70-odd years.

Sorry, you remind me when I faced to be sent to jail when, in the 80's, I presented my work in real (both my FM-AM DSB-SC transmitter around 1Mhz on MW band, and my receiver) to the local authorities at the National Military headquarters in the capital. My crime, as you said, was my claim to know something not known in the West. They refused to verify my claim in any way and insisted that I was an ignorant dreamer. Yes, they used to believe (still do) that the West has gods, and I was seen, therefore, as a blasphemer towards those gods and deserve to be punished. Fortunately, my mind recalled what happened to Galileo (I hope you heard what happened to him). So, in a hurry, I apologized and asked their forgiveness for wasting their time with an ignorant dreamer and this was the Happy End. They were glad and proud for being right and they allowed me to return home, sane and safe.
Soon later, I installed the proper antennas, at home and workplace, and established a two-way scrambled RF link between the two. My links were heard just as an intermittent noisy interference for many months (as I explained earlier) when I decided to stop it and use instead the FM band (also as I explained earlier). The trick on FM band was better and it wasn't noticed for many years till I got a phone line at home which was located in a poor neighborhood.
 
In brief, since you also cannot verify what I say (it is not your field of interest), just tell me what you like me to tell you that lets you feel fine towards me, unless you have no choice but to insist, I am an ignorant blasphemer.

[KerimF]

Sorry, aren't you suggesting that almost all analogue solutions in RF communications need to be removed now from the university's textbooks?
Or just the new ones are not supposed to be added to the old obsolete solutions (like of Costas and Squaring method) that the undergraduate students have to hear of, despite they are no more useful in today's digital world.

Sorry, if I couldn't understand you well.

Seems you are the one suggesting, example your new revolutionary DSB-SC modulation scheme. We are certainly not suggesting remove anything in the Electronics 101 Texts as one needs to understand the modulation fundamentals of AM, FM and PM before venturing into the more complex and spectral efficient modulation schemes in use today.

Best

Anyway, I guess I am guilty, in the eyes of some members here, for saying that my analog solution is better, simpler and more reliable, than the two known ones by the world.

But I will have no reason not to believe someone who will test it, in real, and say it is not better than the ones he used to know.

[KerimF]

What could I add? when someone doesn't have time to read all my replies like the one in the recent post #50 in which I answered the same question and ended it with:

In a real application, the frequency of the carrier doesn't need to be modulated, unless there is a need to also send a low-rate data (as FM) while the AM transmission is active.

Sorry, but I don't see any explanation of advantage of such DSB modulation with FM modulated carrier in the post #50.

If you remove FM modulation for the carrier your modulation turns into a usual DSB, isn't it?

No, it will be always a DSB-SC signal which the world offers only two topologies to demodulate it (Costas Loop and the Squaring method) which are more complex and less reliable/practical than the one I liked to share in this forum
(I started to believe that presenting a new unfamiliar solution here was another silly decision I made in my life)

[SteveThackery]

 
In brief, since you also cannot verify what I say (it is not your field of interest), just tell me what you like me to tell you that lets you feel fine towards me, unless you have no choice but to insist, I am an ignorant blasphemer.

"An ignorant blasphemer"? I'm sorry, I have no idea what you mean. There is no blasphemy here.

I think you are aiming your efforts in the wrong direction. You seem to be trying to convince "the West" (via this forum) that you (and probably other people from your country) are just as smart as western academic experts by showing them a new modulation system that they haven't thought of. The thing is, nobody in the West thinks you're less smart than them. The vast majority of educational institutions are packed with academics from all over the world. When I was lecturing at university, I was the only English person in my office. The others were Italian, Japanese, Pakistani and Chinese. Only our qualifications and experience mattered.  Oh, and a good command of English.

Basically, the West is mostly about about making profits, and if someone can help make a company more profitable then issues around their country of origin are irrelevant. Here in the UK we have loads of Chinese people in academia, IT, telecommunications, and other high tech industries, despite China not being in the West and China being a dictatorship with appalling human rights. If you are smart enough you get the job.

You might be disappointed by the reactions of the people in this forum to your invention, but this is not because they are judging you and deciding you are less smart than them. It is only that your invention doesn't seem to bring any substantive benefit, bearing in mind that analogue radio has been obsolescent for forty years, now.

I think you should be directing your efforts in the opposite direction. I was horrified when you wrote this:

My crime, as you said, was my claim to know something not known in the West. They refused to verify my claim in any way and insisted that I was an ignorant dreamer. Yes, they used to believe (still do) that the West has gods, and I was seen, therefore, as a blasphemer towards those gods and deserve to be punished.

I could hardly believe my eyes when I read your story. Your treatment was appalling and outrageous. Plus it misrepresents the West. Yes, the West has a brilliant track record in science and technology, but definitely no "gods" (except money), and questioning and challenging the current scientific knowledge is not only allowed, it is encouraged. That is how science works.

So it seems to me that the people you need to convince are the people in your story, not the people in the West. As far as the West is concerned you are pushing at an open door.

[mawyatt]

Here is the West science rules, it rules over Politics, Religion, Race, Gender, and Money (mostly, explained later).

We taught (retired adjunct creating and teaching graduate level EE courses) and were taught science rules are to be broken, unless they can't, then they are called Laws!!

This is mostly true with exception to the semiconductor physics areas which have proven if enough market exist and enough $ are available certain perceived Physic Laws can be broken (Moores's Law).
 
We were taught long ago that semiconductor chip processing would stall at @ 10um, then 1um, and then later for sure nothing could ever be processed below 100nm except Direct Write E-Beam which wasn't a batch process so much too expensive for conventional chip processing.

We were also taught and experienced that it took almost a decade for the most advanced semiconductor technology to leave the Labs to end up in general purpose commercial products. That started to change when CMOS semiconductors took hold in the 80s, quickly bypassing any Government Labs attempts to "keep up", then started out pacing any financial means for the government to "keep up" with the "bleeding CMOS edge".

Soon folks started talking about the end of Moore's Law and backed up with physics limitations, however the semiconductor folks didn't listen and kept pushing the CMOS envelope soon passing what any sane physicist would even say is possible much less even doable at these nanometer levels, when the complexity of these chips boasting 30+ Billion nanometer transistors, costing $1B just to develop in a $30B fab!!

Oh yeah, and this impossible semiconductor IC technology ends up in our iPhones, iPads and Laptops anyone can get a few months after the formal announcements of the impossible chip developments, and for under $1000!!

These "Semiconductor Gods" are not only in the West, as TSMC and Samsung are leading the fabrication charge into the nanometer regions supporting these 30+ Billion chips designed at Nvidia, Apple, Intel, AMD and so on which have design centers scattered throughout the world.

Soon, very soon in fact ( ) we'll experience a chip with ~100 Billion transistors in 2nm CMOS!!

Well we all know that's totally impossible

Best 

[radiolistener]

No, it will be always a DSB-SC signal which the world offers only two topologies to demodulate it (Costas Loop and the Squaring method) which are more complex and less reliable/practical than the one I liked to share in this forum

Just to be clear, DSB-SC (also known simply as DSB) refers to AM modulation without a carrier.
However, your modulation also incorporates FM modulation for the carrier.

When you add FM modulation, it no longer makes sense to discuss suppressed carriers, because the output bandwidth of FM is much wider than the narrow and stable carrier of AM.

In other words, by introducing FM modulation in your modulation scheme, you negate the advantages of SSB, DSB, and AM modulation:

- SSB: Bandwidth and power efficiency.
- DSB: Power efficiency.
- AM: Frequency tolerance.

As you know FM modulation is a non-linear operation, so adding it you also add all disadvantages of FM modulation.

What, then, is the benefit of your approach? I fail to see any advantage. Could you please clarify this point?


You also mentioned that using FM modulation is not mandatory for your modulation scheme. But if you remove FM modulation from the carrier, your "new" modulation scheme essentially becomes classic DSB (DSB-SC). So, I am struggling to understand what exactly you are referring to.

Do I understand correctly that you are describing a specific approach to demodulate DSB signals? If so, can you please explain it in math? Or at least with some text description step-by-step on how to process the signal. Because it's hard to understand from the analog schematic.

Additionally, you mentioned issues with demodulating wideband DSB signals using classic methods. I am particularly interested in different kind of modulation from a digital processing perspective, and I don't see any problem with demodulating a DSB signal with a 100 kHz bandwidth (or more) using DSP techniques.

Could you please clarify what specific issue you mean regarding the demodulation of wideband DSB signals using classic approaches?

[KerimF]

No, it will be always a DSB-SC signal which the world offers only two topologies to demodulate it (Costas Loop and the Squaring method) which are more complex and less reliable/practical than the one I liked to share in this forum

Just to be clear, DSB-SC (also known simply as DSB) refers to AM modulation without a carrier.
However, your modulation also incorporates FM modulation for the carrier.

Oh my God, how many times I still need to repeat that I added deliberately the FM modulation JUST to prove the higher performance of My DSB-SC Demodulator over the World's Known Ones.
Sorry I see you as someone needs $100 to start a project. One of his generous friends offered him $200. The former refused the offer and said: your $200 don't help me because I need $100 only.

My DSB-SC demodulator can recover two signals ($200). One doesn't have to send two signals just because my demodulator, unlike the two old ones, can recover them both at the same time. He can use my demodulator to receive one signal only ($100) without the need to add FM modulation.

If you still cannot get the reason for which I added the FM modulation, my English is surely very bad, sorry.

Note:
A simple/conventional diode detector can demodulate an AM DSB signal with low distortion, only if the modulation index is not close to 1. It cannot demodulate a DSB-SC.
This is why our dear Costas had to present to the world his famous solution (that needs I-Q signals) which was given the name of Costas Loop.
Also, those who are professional in RF communications took advantage of the non-linear characteristic of active elements to generate a signal which has twice the frequency of the suppressed carrier one (after proper filtering at 2fc) and solved the problem (by dividing 2fc by 2).

[KerimF]

Do I understand correctly that you are describing a specific approach to demodulate DSB signals? If so, can you please explain it in math? Or at least with some text description step-by-step on how to process the signal. Because it's hard to understand from the analog schematic.

You request is reasonable.

Unfortunately, I use math just to solve (find out) the values of the elements which are used in a design that seems (logically) to work/function as expected if the right (optimum) values are found.

In our case here, I am afraid that having a basic knowledge on how a PLL circuit works is a prerequisite to understand the updated one here.
If you didn't have the chance and time to study a simple conventional PLL, I don't think I can help you, unless you ask me very specific questions (not general ones).

[radiolistener]

Unfortunately, I use math just to solve (find out) the values of the elements which are used in a design that seems (logically) to work/function as expected if the right (optimum) values are found.

In our case here, I am afraid that having a basic knowledge on how a PLL circuit works is a prerequisite to understand the updated one here.
If you didn't have the chance and time to study a simple conventional PLL, I don't think I can help you, unless you ask me very specific questions (not general ones).

I did not ask what a PLL is, nor did I suggest that I don’t understand how it works. My question was specific and technical: I asked for a description of your approach to demodulating a DSB signal, either mathematically or at least verbally.

Instead of addressing the question, you consistently shift to unrelated topics like politics or make assumptions about others understanding. Bringing up political issues in the context of this technical discussion is entirely inappropriate. Please focus on the math and provide a clear and concise explanation of your method without unnecessary digressions.

[mawyatt]

Could this new modulation scheme be related to BPSK?

Best

[KerimF]

Could this new modulation scheme be related to BPSK?

Best

I am not sure why it is so hard for me to explain, using English, that the title of this thread is simply to attract attention to a third topology (not known universally yet) to demodulate DSB-SC signals.

So, I added here a rather weird FM modulation, 455 Khz +/- 30 kHz (though I used it to scramble my short-range RF voice links. in the 80's) because no other known topology can recover the AM modulating signal from this FM-AM DSB-SC, unless the frequency of its suppressed carrier is made somehow invariant (fixed).

What I presented on post #9 is just about a new DSB-SC demodulator, nothing else. And if someone has LTspice he can set the parameter:
FM_pk = 0 instead of 0.5
By doing this, he removes the FM modulation completely while the recovered AM audio signal stays the same. For instance, in this case, the DSB-SC demodulators of Costas Loop and Squaring method (which are more complex to build than mine) can also recover it.

In brief, what we got here is a DSB-SC demodulator (actually, it works for any AM index, from m=0, no audio modulating signal, to infinity, no carrier). But it is simpler to build and more reliable/practical than the known ones. (It happens it can also act simultaneously as an FM demodulator in case the carrier frequency is modulated, besides its amplitude).

Kerim

[KerimF]

As you know AI bots are made by humans. So, if a programmer has no idea about something, his AI bot cannot know it too.

I guess for example, this is one of the questions that an AI bot cannot answer properly:

BW_am is the bandwidth of an RF channel when the amplitude of its carrier is modulated.

BW_fm is the bandwidth of the same RF channel but when the frequency of its carrier is modulated.

The question is:
What is the bandwidth, BW_am_fm (in function of BW_am and BW_fm), of this channel when both the amplitude and frequency of its carrier are modulated at the same time?

I wish to know how an AI bot will answer this question. Unfortunately, unlike most readers here, I can’t access one.

But, what about who have a Natural Intelligence? Hmmm... now I am doomed

[KerimF]

Since this thread is almost locked, speaking practically, here is the answer of post #73:

BW_am_fm = BW_am + BW_fm

I guess proving it is easy to most of you.

See you on another thread.

Cheers
Kerim

[radiolistener]

What I presented on post #9 is just about a new DSB-SC demodulator, nothing else. And if someone has LTspice he can set the parameter:
FM_pk = 0 instead of 0.5
By doing this, he removes the FM modulation completely while the recovered AM audio signal stays the same. For instance, in this case, the DSB-SC demodulators of Costas Loop and Squaring method (which are more complex to build than mine) can also recover it.

The problem here is that I'm using Linux OS on aarch64 platform, while LTspice is for Windows/Apple OS with x86/x64 platform. So, I have no way to test it, because I cannot run LTspice. And it's hard to see the root of your idea from schematic.

This is why I asked to write it in math for matlab/octave, so that it can run on any OS/platform. Or at least describe it using math with usual text description.

As you know AI bots are made by humans. So, if a programmer has no idea about something, his AI bot cannot know it too.

That's not technically correct.
Here is response from AI bot on your statement:

Your statement is partially true, but it simplifies how AI works. AI bots are trained on vast amounts of data, including information that the individual programmers may not personally know. While programmers build the systems and define their structure, the knowledge embedded in AI models comes from the data they're trained on, not solely from the programmers' understanding.

So, an AI bot might "know" things that its creators are unaware of, as long as that knowledge exists in the training data. However, if the data lacks certain information, the AI won’t have it either, regardless of the programmers’ expertise.

In other words, AI's knowledge is practically independent of the programmer's knowledge, just as the information written on a piece of paper does not depend on the knowledge of the person who made the paper.

[radiolistener]

I guess for example, this is one of the questions that an AI bot cannot answer properly:

BW_am is the bandwidth of an RF channel when the amplitude of its carrier is modulated.

BW_fm is the bandwidth of the same RF channel but when the frequency of its carrier is modulated.

The question is:
What is the bandwidth, BW_am_fm (in function of BW_am and BW_fm), of this channel when both the amplitude and frequency of its carrier are modulated at the same time?

I wish to know how an AI bot will answer this question. Unfortunately, unlike most readers here, I can’t access one.

Here is the answer on your question from Chat-GPT:

When both amplitude modulation (AM) and frequency modulation (FM) are applied to the same carrier, the resulting bandwidth BW_{am_fm} will generally be the sum of the bandwidths required for each modulation independently, as both forms of modulation add spectral components to the signal.

Thus, the bandwidth for the combined modulation can be expressed as:

BW_{am_fm} = BW_am + BW_fm

Explanation:
- BW_am​: This represents the bandwidth required for the AM signal. For a standard AM signal, this bandwidth is twice the highest frequency present in the modulating signal.
- BW_fm​: This represents the bandwidth required for the FM signal. It depends on both the frequency deviation and the highest frequency of the modulating signal, typically calculated using Carson's rule.

When both modulations are applied simultaneously, the spectral content of the signal includes components from both types of modulation, leading to the combined bandwidth.

[radiolistener]

I also asked Chat-GPT to analyze your schematic from picture in this post: https://www.eevblog.com/forum/projects/did-you-hear-of-such-an-am-receiver/msg5770781/#msg5770781

And here is Chat-GPT result:

> Analyze schematic for DSB signal demodulation from picture in attachment

The circuit represents a combined demodulator for DSB-SC (Double Sideband Suppressed Carrier) and FM (Frequency Modulation) signals using a Phase-Locked Loop (PLL). Here's an analysis of the key components:

1. Input Signal:
    The input signal is modulated in both amplitude (AM) and frequency (FM).
    Variables V_AM and V_FM​ simulate the AM and FM modulated signals, respectively.

2. DSB-SC Section:
    The DSB-SC signal is introduced into the circuit via the DSB - SC + component.
    Logic gates (74HC86) are used to process and recover the original DSB-SC signal.

3. FM Section:
    The FM signal is generated using the SINE() function for frequency modulation.
    A PLL, implemented with CD4046 and 74HC86, is employed to extract the frequency-modulated information.

4. Signal Processing:
    Limiters and logic gates (74HC86) prepare the signal before it enters the PLL for demodulation.
    The "Optional" section includes additional circuitry for muting (Mute) using the CD4066 component.

5. Demodulation:
    The CD4046 component is used for phase detection and retrieval of the FM-modulated signal.
    The DSB-SC signal is processed separately through its own signal path.

6. Output Signal:
    The outputs, R_{AF_FM}​ and R_{AF_AM}​, correspond to the recovered FM and AM signals, respectively.
    These outputs can be connected to an analyzer or an amplifier for further processing.

Remarks:
- This circuit effectively demonstrates the integration of AM and FM signal processing in a single design.
- The PLL (CD4046) is utilized efficiently for FM demodulation.
- However, the accuracy of demodulation depends on proper tuning of parameters such as F_lock​, F_PLL​, and the input signal characteristics (amplitude, frequency).

Let me know if you have any specific questions or need further clarification!

Then I asked to analyze DSB-SC demodulation signal path. Here is result:

> Analyze DSB-SC demodulation signal path

The DSB-SC (Double Sideband Suppressed Carrier) demodulation signal path in the provided circuit can be analyzed as follows:

1. Input Signal (DSB-SC):
    The DSB-SC signal is introduced into the circuit via node DSB-SC+.
    The signal is represented as V=V(Fc)⋅V(AF), where Fc​ is the carrier frequency and V(AF) is the amplitude-modulated information.

2. Signal Limiting:
    Limiter (U1):
        The input DSB-SC signal passes through a limiter (constructed using a 74HC86 XOR gate) to clip the signal and remove amplitude variations.
        This step ensures the signal is prepared for zero-crossing detection and phase processing, emphasizing the frequency and phase information.
        Resistors R3, R8, and capacitor C1 set the operating conditions for the limiter stage.

3. Signal Delay and Phase Adjustment:
    Delay Circuit (U2):
        The output of the first limiter is passed through another XOR gate (74HC86) with a delay introduced by R2, C2, and R11, C7.
        The delay helps align the signal for proper phase detection and demodulation.
        This block ensures synchronization of the DSB-SC signal for downstream processing.

4. Phase Detection:
    The delayed and limited signal is processed through another XOR gate (U2) for phase detection.
    The result of the XOR operation helps distinguish the suppressed carrier and the amplitude-modulated components.

5. PLL Demodulation (Optional Path):
    PLL (CD4046):
        While primarily used for FM demodulation, the PLL can also lock onto the carrier frequency of the DSB-SC signal.
        The recovered carrier frequency can assist in reconstructing the original amplitude-modulated signal.

6. Output Signal Recovery:
    After phase detection and XOR processing, the demodulated DSB-SC signal is passed through a low-pass filter (outside the XOR logic path).
    The low-pass filter removes high-frequency components, isolating the baseband signal V(AF), which contains the original modulating information.
    The final output is available at R_{AF_AM}​, representing the recovered AM signal.

Key Observations:
1.    The demodulation relies heavily on logic gates and limiters for phase detection.
2.    The XOR gates (74HC86) are critical for detecting phase differences and reconstructing the suppressed carrier.
3.    The low-pass filter ensures only the baseband signal is retrieved at the output.
4.    For accurate demodulation, the system depends on proper synchronization and delay adjustments.

Let me know if you need a deeper analysis or specific parameter details!

As you can see, it just extract basic information

[KerimF]

As you can see, it just extract basic information

First, thank you for your time to ask Chat-GPT because I can't do it.
It is sad that you cannot test the circuit. Those who can run LTspice they may be able to update it too.

So, I will try to explain it verbally.
The reason that a conventional PLL topology cannot lock in case of DSB-SC (and if m>1), is that the carrier phase shifts 180 degrees every time the modulating signal cross 0V. So, if the two inputs of its comparator are of the same frequency fc, the polarity of the comparator output will change at every zero crossing too and this prevents the PLL to lock.

To avoid this situation, I simply doubled the frequencies at the comparator inputs.

[1] On the schematic, R2/C2 and R11/C7 delayed the XOR output U1, V(LMT). Their total delay is 90 degrees, that is equal to Tc/4 [550 ns, in case fc=455 kHz). At the output of XOR U4, V(DBL), we get a square wave whose frequency is 2*fc.
[2] The mid-frequency of the VCO is also set to 2*fc.

Now, the polarity of the comparator output doesn't change because at zero crossings V(DBL) stays/looks the same despite the reversal phase of the suppressed carrier.

Naturally, the VCO output (2fc) has to be divided by 2 (see U3).
And the total delay of the XOR U5 (90 degrees of fc) and the R7/C5 is added and adjusted to let CD4066 be in phase with the suppressed carrier.

Hope this helps.

[KerimF]

I think the readers who had the time to analyze and understand the demodulator presented here (which could be called ‘Kerim Loop’ or ‘Harmonic Loop’) are shy to add two negative comments/remarks about it:

[1] You said it can recover, at the same time, two independent signals which modulated the amplitude and the frequency of the suppressed carrier, respectively. But when the AM modulating signal is off (silence periods during a conversation), the FM recovered signal will be lost (the two sidebands are off, no RF signal).   

[2] You said R7/C5 (delay circuit) is added and adjusted to let the synchronous detection (by CD4066) be in phase with the suppressed carrier. This works if the frequency of the suppressed carrier is fixed. In case its frequency varies, its phase varies too, forwards and backwards. The gain of the synchronous detector decreases in both directions which results to a gain distortion.

For case [1], in a real application, this is can be solved in a way that suits the purpose of adding a second signal as FM.
For case [2], the fixed delay needs to be controlled by the average voltage of VCO_in (LPF output) in order to follow the phase variation. In a real application, the gain distortion (when FM is also used, as in the example on reply #9) is relatively small and not noticed during a conversation. But I am working on it to make it a voltage-controlled delay circuit (VCD).

Cheers,
Kerim