Be interesting to put a switch on that feedback capacitor to see how it affects the sound of the amp. Merry Christmas to you as well, I always enjoy your videos.
I considered putting in a 4 or 5 position rotor switch so I could switch in different values of C across the NFB resistor. I am trying to appreciate and enjoy the amplifier rather than turn it into a never-ending project. I am not sure I can resist... Seems I hit the "sweet spot" with this one. I have not had the same success with the 300B - but I don't give up easily... 🙂
Cracks me up! You are like a kid in a candy store with all the tweaking and testing you are doing on you SE amp. I can relate too! We are never satisfied or happy with the results... ALWAYS modifying and testing and testing! Have a GREAT Holiday and stay safe.
Even though most of this theory is way over my head I always enjoy your explanations and learn a little more. Know you’re working on a stereo version if I read correctly, oh boy. I’d love to pay for that schematic of that when it’s ready I have a few 807’s matched and a variant 6B something pair as well I believe
I’m glad to see you’re experimenting with some lovely single ended amps. For a long time, I would go for performance and I would geek over push pull amps. Until I decided to build a simple Single ended amp. The difference was night and day. They sound so much better and natural. After over 20 years of experimenting with tube amps, I guess I finally found the amp for me. An ultra linear single ended el34 amp. I’m using a 4800 / 8 ohm opt I wound myself using the Delatsch Calculator app for iPhone and it’s great. I drive the el34 with half a 5670 and I’m getting 5w rms per ch from 18-19.000Hz at less than 1%thd using a tube regulated power supply (low impedance is critical for bass performance and régulation helps with hum reduction in SE amps) . If I bump b+ all the way up to 285V, I can squeeze an extra watt and a half per ch below 1% thd. But it sounds like a million bucks and I compared it to stuff like the Dynaco ST70 and even some great solid state amps. The transformers have to be oversized or you won’t be able to get down to 18Hz at -3dB. Right now I’m using a 250v power supply and a 250 ohm cathode resistor.
I used the same schematic you used for a long time and got great results but I found that the el34 is a lot easier to drive and that allows me to use only half a triode per ch at the front end. With no cathode bypass and just a tiny bit of global NFB
I think you’d love the way el34’s sound when they’re used in SE, especially when triode connected or in UL mode. In triode mode with a 100 ohm resistor between the screen and the plate, the plate resistance goes down to 910 ohms, which makes it sound a lot like a 300B
Something you might find interesting from ChatGPT on SE amplifiers. ___________________________________________________________________ You said: I tested a high-end single-ended (SE) amplifier last night and with an ultra low distortion signal generator (Tektronix SG505) I only got even order harmonics out of the amplifier. I was running the output at 3W into an 8 ohm load. The OPT was rated at 10W, 5K primary to 8 ohm secondary. The secondary across non-inductive load resistors. I can't explain no odd order harmonics or is how it performed a characteristic of a SE amplifier? ChatGPT said: ChatGPT The performance of your single-ended (SE) amplifier showing only even order harmonics is indeed characteristic of this type of amplifier, especially under the conditions you've described. Here’s a breakdown of why this happens: Even Order Harmonics Dominance: SE amplifiers, particularly those that use triode vacuum tubes, typically generate predominantly even order harmonics (such as 2nd and 4th harmonics). This characteristic stems from the inherent asymmetry in the amplification process of SE designs, where the waveform's positive and negative halves are not amplified equally. The even harmonics often provide a type of distortion perceived as more musically pleasant or "warmer" compared to odd harmonics. Lack of Odd Order Harmonics: The absence of odd order harmonics (like the 3rd or 5th) that you observed can be influenced by several factors: Tube Selection and Biasing: The specific tube used and its bias point significantly affect harmonic content. Some tubes, when biased correctly, can suppress certain harmonics due to their smooth clipping characteristics. Output Transformer and Load Characteristics: The interaction between the output transformer and the load can also influence the harmonic distortion profile. Transformers can, to some extent, affect which harmonics are more pronounced based on their design and how they handle saturation. Circuit Design: SE amplifiers typically do not have negative feedback (or very minimal), which allows the natural characteristics of the tube and transformer to dominate the sound, including the harmonic content. Negative feedback, when used, can help reduce distortion but also tends to make the output more linear and suppresses harmonics, both even and odd. Given that you were using a high-quality signal generator and a non-inductive load, your measurements are likely accurate, reflecting the natural behavior of your SE amplifier under the conditions tested. If odd harmonics were completely absent, it's a testament to the linearity and quality of your setup at the tested power level, particularly the effectiveness of the output transformer in maintaining waveform integrity. For further exploration, you might consider varying the load or adjusting the bias of the tube to see how the harmonic content shifts. These types of experiments can help confirm the behavior and characteristics of different components within the amplifier circuit.
The generation of even harmonics in a square wave is dependent on the duty cycle, 50 percent duty cycle produces no even harmonics. As to the inductive ring in the waveform, most of that is being produced by the inductive loop of the leads to RC substitution box. Bigger the loop, more the ringing.
The anomaly around 16 KHz is not part of the amplifier - it is some sort of loop, as you mention, in the breakout box - dummy load - multiple coax jumpers to all the test equipment - ??? I will see if I can find it tonight by disconnecting one thing at a time.
@@EJP286CRSKWHi Esmond, From a monitor.. hmmmm... I don't know but it is just below 16 KHz. I just, a few minutes ago, went to my shop and turned everything on. I did not see it immediately but will let everything warm up for a while. Thanks for the suggestion. I know you and I have had real conversations about clean push-pull amplifiers and this crazy SE stuff but I am here to tell you, it is very pleasing to the ear to listen to. I have build other SE amplifiers, just maybe three years ago got into SE amplifiers, and have seen "normal" harmonic profiles, the second being the largest harmonic but in this case, maybe the 807 ?, maybe a good SE OPT ? maybe because I have it biased to a sweet spot - I don't know. I can't fight the measurements but they do amaze and even confuse me. Look at the comment I posted on my last video from ChatGPT. Hope you are doing well and have a safe and happy Christmas and New Year. 🙂
You know what I found when I have been tweaking my amplifiers is that if we try to perfect the square wave that they produce, playing with the feedback and getting rid of that little bit of ringing makes them sound lifeless and sterile if that’s the word… like in my head I picture an all white room, white speakers just plain and colourless. I actually prefer a bit of overshoot and ringing personally and have left most of mine like that. I would say I play around and tune out maybe 60-76% of it and it sounds great to me!
I understand and agree with what you are saying. We can tweak the sound out of it - in a real sense... 🙂I am so pleased with the sound, even though I may keep taking it to the bench for testing, I have, so far, not changed it. I spent last night preparing my 300B stereo SET for the two transformers I order from Marko in Poland. In the 6SN7 driving the 300B I ended up changing the 22K cathode resistor to 18K and the 75K to 82K to truly tweak it to the best I can get it. I have learned that when using a scope on the 6SN7 stages up to the grid of the 300B (or whatever output tube) if either the top or bottom of the sine wave is "fatter" than the other, that indicates mostly 2nd order harmonic. That is one thing I focus on and work to get the sine wave at the grid of the 300B as perfect as possible. I think of that as "worthwhile" tweaking... Anyway, I should get my transformers in a couple of weeks and I will have a stereo version with high-end OPT transformers. The 300B will do 6.5 very nice watts and it will be interesting to see if it actually sounds better, or as good, as the 807. We will see...
@@ElPasoTubeAmps Thats intersting about the sine wave Im going to have to look at that, I have all the parts to finish my 300B amplifier minus the tubes themselves I have been meaning to order some but just get so busy doing other stuff I forget. It will be really interested to hear the 300B and the 807 side by side because the 807 is a really good sounding tube, the 300B has a cult following as the gold standard fro SET. talking about 6SN7 tubes they are probably my favourite as a driver I try and use them on most of my amps. And speaking of Marko I purchased his transformer calculator package from his website because I may or may not try winding my own.....one day haha. I think I will purchase some transformers from him for whatever I build next. Thanks for sharing another video with us all and I hope to see you again soon. If I don't talk to you before Christmas I hope you have a great Christmas and all the best to you!
If I remember correctly you have over 100uf cap directly connected to rectifier tube no current limit resistance.isnt that going to hard on the rectifier and hv winding of the transformer? Otherwise an interesting circuit.
That has been mention by another gentleman. It may have been just too much for the transformer. I left it on (forgot about it) for a couple of days and when I went to use it, it had blown the fuse. Checked it quickly and put in another 2A fuse - blown - you can tell if the failure is catastrophic when the inside of the glass if blackened by the melting of the fuse element. I knew something was serious wrong - fast forward - the secondary was shorted. I have never worried about the value of the input capacitor - I am cautious not to make it outrageous large but I think 100 uF should be OK. In any case I was lucky enough to have a better replacement. I am thinking the Hammond rating of 100 mA was not a 24/7 rating. I don't know for sure.
Very interesting. I've testing quite a few valve amps both SE & PP & have never seen a FFT result that hasn't had any 3H content. It shouldn't be a test gear anomaly. I'd be interested in seeing the result with a 100hz or lower signal. Also interested in seeing the OP prior to the OP valve. Thanks, a very thought provoking video. Edit: Re sq wave test @ 1khz, looks like there's some LF rolloff. I usually set my NFB capacitor with a 10khz sq wave, then sw too 100hz sq wave & dial in the C. I usually have an LC/Zobel across the speaker OP teminals & from anode to ground set to the same F 3dB point. The increased instability/ringing at 2khz from 1khz isn't good though, could it be down to the OPT? Have you done any no load & capacitive load testing? A 100n is a good value, it show up any instability issue's - no load LF instability, cap - HT instability. Lastly, had a thought about the no 3H, the amps I've tested have been stereo amps with a common power supply, I've had issues with Xtalk, I wonder how much of the 3H content I saw was a consequence of Xtalk & or IM? Lastly I I agree, don't matter what it tests like, if it sounds good, leave it be.
You have some really good thought provoking suggestions. 10 KHz square wave is very rounded - too rounded for a NFB bypass capacitor to have much if any effect. I posted a ChatGPT response to the question about only even harmonics in an SE amplifier in the comment section you might find interesting. The only other SE amplifier I have built, before this one, is one that I posted maybe three years ago using 300B and using PS chokes as plate load and a James 8K primary OPT to match to 8 ohms. Worked OK but did not have the sustained charm this one has. Somehow the 300B and choke load design/build tired me after a while. This one does not... This "Little Jewel" uses a genuine SE transformer so maybe I am just discovering something - I am still in awe of the harmonic profile. In the 300B just mentioned, it had a harmonic profile that was expected - huge 2H and small 3H. I will be doing some more testing tonight but as you say, don't mess it up... 🙂
@@ElPasoTubeAmps Hello David, I no longer have the amps in question & it was a few years ago when I tested them, so, can't be certain that I didn't assume them to be 2H, 3H etc. However the spacing between a 2H & 3H is quite noticeably different to 2H 4H etc. I'll see if I have any footage stashed but I don't often bother with an FFT test. You did say in your first comment that the 300B did have 3H content though, still, memory can be in error, mine often is. I have had test setup fault's EG odd readings from mains earth loops between scope & stereo dummy load too which I have to watch out for. Whichever, I think your onto something that needs more investigation. My intuition is that the OPT's are playing a big part in this, hence why I suggested a look at the OP of V1 & V2, maybe V3 too - open loop at LF. Could be wrong though. I've found that tweaking R & C value's, balancing PP stages etc might change THD by 0.01% or more, but your OPT & load has far more effect, especially load. Simple R dummy load testing only shows us so much, but we know a speaker is far more complex. Keep up the good work, am finding this really instructive as I always do your work.
@@diabolicalartificer It just dawned on me what is going on - I was driving the amplifier with a 2 KHz pure sine wave. Harmonics are integer multiples of the fundamental so they are going to be harmonics of 4, 6, 8, 10, etc. - all even. Holy Cow... the thing about it however, is the driving signal is a very pure sine wave so the amplifier is indeed creating all these even harmonics as artifacts. I kept shaking my head last night thinking I surely must be confused - and I was - when I put in the 1 KHz square wave which is naturally the fundamental and all odd harmonics - that is what I got out. This has been banging around in my head and just did not seem right - and it wasn't. Sorry for the confusion.
@@ElPasoTubeAmps Of coarse, 6khz is the 3H, the numbers themselves fooled us both, being that they are even numbers, our brains equated them to even harmonics. Therefore your amp IS producing odd harmonics but it's the amplitude or level of these harmonics that is the important thing, not the number. EG usually we see the F at 0dB say, the 2H at - 6dB, the 3H at - 5dB, or vice versa. your harmonics ARE unusual because they are all at the same level, instead of diminishing as they proceed. Electronics eh : ) Have to keep your wits about you ; )
You applied injected a 2Khz square waveform but why would an amplifier has to be 10X times the fundamental? 2Khz X 10 = 20khz , I'm don't understand what makes the guitar amplifiers circuit design is 10X times the fundamental. The NFB does what to the Squarewave testing measurement?
I didn't know that. I looked it up and see he has a, Grommes LJ7 guitar amplifier. I named my amplifier after my latest kitten who I named, Jewel. I will have to study his schematic. 🙂
@@ElPasoTubeAmpsGrommes Little Jewel was a hifi originally , nowadays lots of folks ( including me)are tasking them with guitar chores. Great amps either way
@@billfog393 Thank you - I looked up Grommes and found his equipment. Interesting we both chose the name, "Little Jewel" for our amplifiers. I assume he does not have a patent on the name... 🙂
It just dawned on me what is going on - I was driving the amplifier with a 2 KHz pure sine wave. Harmonics are integer multiples of the fundamental so they are going to be harmonics of 4, 6, 8, 10, etc. - all even. What I failed to realize is 6 and 10 ,for example, is the 3rd harmonic and 5th (odd) harmonic of 2 KHz. I was described as a kid in a candy store, and I have had too much candy... Holy Cow... the thing about it however, is the driving signal is a very pure sine wave so the amplifier is indeed creating all these even harmonics as artifacts. I kept shaking my head last night thinking I surely must be confused - and I was - when I put in the 1 KHz square wave which is the fundamental and all odd harmonics - that is what I got out. This has been banging around in my head and just did not seem right - and it wasn't. Sorry for the confusion.
Would it be possible for you to upload the schematic with some voltages written on it? I seen the schematic in an earlier post but it has no voltages written on it. For those of us who would like to try this Amp.
Apparently, the reason why we like even harmonics is because the harmonics are octaves of the fundamental, so they tend to sound more harmonious and musical to the human ear, octaves tend to sound consonant, whereas odd harmonics sound dissonant.
Something similar was mentioned in another post and the sum and differences of mixing fundamental with odd and even harmonics (may?) cause dissonant cords in the upper freqencies as I understant it - but I am no musician.
It is true, musically even harmonics can't even be called distortion. Musically even harmonics are not distortion at all, it is simply a musical octave. In Western civilization music, the music we all know, octaves are simply a doubling of frequency, and in music playing a note in any octave is always "still in tune". Therefore even harmonics can't be considered as distortion at all. When a musician doubles octaves, it thickens and warms the timbre, it is never dissonant. Odd harmonics however always generate additional notes in the music that are never anywhere near being "in tune". I would love to build this Amp now, oh boy just what I need, another project.
@@ElPasoTubeAmps Dissonance in higher instruments is always more offensive. Imagine two piccolos playing the same melody a semitone or less apart! Versus two double basses doing the same, the lower frequency is "slower" in exposing the "beat note" when tuning two instruments to each other, so not as noticeable. Chords containing all sorts of intervals minor/major thirds, seconds, 4ths, 5ths, 9ths, etc. mixes using the same 12 note intervals our brains recognize. The well-tempered musical scale is an amazing invention since it was actually established at a time when frequency measurement itself was impossible. All done by ear, the intervals Do Re Me, sharps and flats, and most importantly, octaves occurring at each doubling, which coincides with second harmonic "distortion" perfectly.
The reason, according to Floyd Toole and researchers at Harman and elsewhere is Even Harmonics are what occur in nature. Whether a church bell, or banging on a pipe with a hammer, or a trumpet or violin, sounds in nature just naturally amplify Even Harmonics. Maybe there is something in nature that evolutionarily led to a dislike Odd Order Harmonics. For example, I wonder what something like a Big Cat's growl looks like on a frequency spectrum? We have evolved for that sound to really catch our attention. And probably have a visceral negative reaction to it. Now, in the modern day, when we hear brakes screeching, it is not much different than a Big Cat's growl, with the same reaction. So my suspicion is that this preference for Even Harmonics is an Evolutionary trait, and that is something that could be easily researched. But in the meantime, thank Satan for Tube Electronics. They don't just reproduce natural harmonics beautifully. Also, when done well, they create incredible Soundstage, Imaging, a sense of Air and Spaciousness that I have yet to hear equalled by Solid State when comparing at the highest levels. I started in high and HiFi back in the 80s. Only recently have I heard the jaw-dropping, just astounding performance of some of the pure Class A high-powered Transmitter Tube amplifiers. Some of the ones that you have made are a great example. The 805s, 845s, and even some of the massive tubes used by NAT Audio that are as hot and bright as the Sun - you could get a tan - they are utterly amazing. They put the performers in the room, and recreate the room that they're in, like no other amps. I've also started to fall into the rabbit hole of some of the Preamps employing the big signal tubes, and again, there is Soundstage and Imaging, as well as inner detail and resolution, without any harshness or fatigue, that's on a whole other level. So the incredible ability of tubes seems to be never ending. And I'm totally down for that. Bring it on!
This is simply untrue. It is easy to construct natural resonators that produce 3HD: for example, a clarinet. The truth of this is that it isn’t the even harmonics that are pleasing: it is the ones that are powers of two, because they are octaves and don’t disturb the harmonic structure. There isn’t much pleasing about a sixth or tenth harmonic. Bizarre that people are still researching this. It was known to organ builders before Bach was born.
For years, I have enjoyed the technical detail of your videos. Well done again and great explanation. Keep up the 'audio' projects and videos.
Be interesting to put a switch on that feedback capacitor to see how it affects the sound of the amp. Merry Christmas to you as well, I always enjoy your videos.
I considered putting in a 4 or 5 position rotor switch so I could switch in different values of C across the NFB resistor. I am trying to appreciate and enjoy the amplifier
rather than turn it into a never-ending project. I am not sure I can resist... Seems I hit the "sweet spot" with this one. I have not had the same success
with the 300B - but I don't give up easily... 🙂
Every video you do is educational Dave. That is great
Great video, as always. 73s and hope you have a very blessed Christmas!
Cracks me up! You are like a kid in a candy store with all the tweaking and testing you are doing on you SE amp.
I can relate too!
We are never satisfied or happy with the results... ALWAYS modifying and testing and testing!
Have a GREAT Holiday and stay safe.
Even though most of this theory is way over my head I always enjoy your explanations and learn a little more. Know you’re working on a stereo version if I read correctly, oh boy. I’d love to pay for that schematic of that when it’s ready I have a few 807’s matched and a variant 6B something pair as well I believe
I’m glad to see you’re experimenting with some lovely single ended amps. For a long time, I would go for performance and I would geek over push pull amps. Until I decided to build a simple Single ended amp. The difference was night and day. They sound so much better and natural. After over 20 years of experimenting with tube amps, I guess I finally found the amp for me. An ultra linear single ended el34 amp. I’m using a 4800 / 8 ohm opt I wound myself using the Delatsch Calculator app for iPhone and it’s great. I drive the el34 with half a 5670 and I’m getting 5w rms per ch from 18-19.000Hz at less than 1%thd using a tube regulated power supply (low impedance is critical for bass performance and régulation helps with hum reduction in SE amps) . If I bump b+ all the way up to 285V, I can squeeze an extra watt and a half per ch below 1% thd. But it sounds like a million bucks and I compared it to stuff like the Dynaco ST70 and even some great solid state amps. The transformers have to be oversized or you won’t be able to get down to 18Hz at -3dB. Right now I’m using a 250v power supply and a 250 ohm cathode resistor.
I used the same schematic you used for a long time and got great results but I found that the el34 is a lot easier to drive and that allows me to use only half a triode per ch at the front end. With no cathode bypass and just a tiny bit of global NFB
I think you’d love the way el34’s sound when they’re used in SE, especially when triode connected or in UL mode. In triode mode with a 100 ohm resistor between the screen and the plate, the plate resistance goes down to 910 ohms, which makes it sound a lot like a 300B
hi i agree with you i got single end 6sl7 and kt66 and its sound very good
@@kubockferre5532 before this amp, I had built a 6sl7/5881 that sounded pretty good too and I imagine the kt66 would sound d even better
Something you might find interesting from ChatGPT on SE amplifiers.
___________________________________________________________________
You said:
I tested a high-end single-ended (SE) amplifier last night and with an ultra low distortion signal generator (Tektronix SG505) I only got even order harmonics out of the amplifier. I was running the output at 3W into an 8 ohm load. The OPT was rated at 10W, 5K primary to 8 ohm secondary. The secondary across non-inductive load resistors. I can't explain no odd order harmonics or is how it performed a characteristic of a SE amplifier?
ChatGPT said:
ChatGPT
The performance of your single-ended (SE) amplifier showing only even order harmonics is indeed characteristic of this type of amplifier, especially under the conditions you've described. Here’s a breakdown of why this happens:
Even Order Harmonics Dominance: SE amplifiers, particularly those that use triode vacuum tubes, typically generate predominantly even order harmonics (such as 2nd and 4th harmonics). This characteristic stems from the inherent asymmetry in the amplification process of SE designs, where the waveform's positive and negative halves are not amplified equally. The even harmonics often provide a type of distortion perceived as more musically pleasant or "warmer" compared to odd harmonics.
Lack of Odd Order Harmonics: The absence of odd order harmonics (like the 3rd or 5th) that you observed can be influenced by several factors:
Tube Selection and Biasing: The specific tube used and its bias point significantly affect harmonic content. Some tubes, when biased correctly, can suppress certain harmonics due to their smooth clipping characteristics.
Output Transformer and Load Characteristics: The interaction between the output transformer and the load can also influence the harmonic distortion profile. Transformers can, to some extent, affect which harmonics are more pronounced based on their design and how they handle saturation.
Circuit Design: SE amplifiers typically do not have negative feedback (or very minimal), which allows the natural characteristics of the tube and transformer to dominate the sound, including the harmonic content. Negative feedback, when used, can help reduce distortion but also tends to make the output more linear and suppresses harmonics, both even and odd.
Given that you were using a high-quality signal generator and a non-inductive load, your measurements are likely accurate, reflecting the natural behavior of your SE amplifier under the conditions tested. If odd harmonics were completely absent, it's a testament to the linearity and quality of your setup at the tested power level, particularly the effectiveness of the output transformer in maintaining waveform integrity.
For further exploration, you might consider varying the load or adjusting the bias of the tube to see how the harmonic content shifts. These types of experiments can help confirm the behavior and characteristics of different components within the amplifier circuit.
Thanks for another great video, it’s so inspiring. Keep up the great work you’ve been doing since the first video.
thank you for the videos and happy hollidays
The generation of even harmonics in a square wave is dependent on the duty cycle, 50 percent duty cycle produces no even harmonics. As to the inductive ring in the waveform, most of that is being produced by the inductive loop of the leads to RC substitution box. Bigger the loop, more the ringing.
The anomaly around 16 KHz is not part of the amplifier - it is some sort of loop, as you mention, in the breakout box - dummy load - multiple coax jumpers to all the test equipment - ???
I will see if I can find it tonight by disconnecting one thing at a time.
@@ElPasoTubeAmps Could it be a 15.65kHz spike from a monitor?
@@EJP286CRSKWHi Esmond,
From a monitor.. hmmmm... I don't know but it is just below 16 KHz. I just, a few minutes ago, went to my shop and turned everything on. I did not see it immediately but will let everything warm up for a while. Thanks for the suggestion. I know you and I have had real conversations about clean push-pull amplifiers and this crazy SE stuff but I am here to tell you, it is very pleasing to the ear to listen to. I have build other SE amplifiers, just maybe three years ago got into SE amplifiers, and have seen "normal" harmonic profiles, the second being the largest harmonic but in this case, maybe the 807 ?, maybe a good SE OPT ? maybe because I have it biased to a sweet spot - I don't know. I can't fight the measurements but they do amaze and even confuse me. Look at the comment I posted on my last video from ChatGPT. Hope you are doing well and have a safe and happy Christmas and New Year. 🙂
@@ElPasoTubeAmps Thanjs David, you too. I am emailing you about a related matter I am dealing with at the moment, too much to put here. EJP
You know what I found when I have been tweaking my amplifiers is that if we try to perfect the square wave that they produce, playing with the feedback and getting rid of that little bit of ringing makes them sound lifeless and sterile if that’s the word… like in my head I picture an all white room, white speakers just plain and colourless. I actually prefer a bit of overshoot and ringing personally and have left most of mine like that. I would say I play around and tune out maybe 60-76% of it and it sounds great to me!
I understand and agree with what you are saying. We can tweak the sound out of it - in a real sense... 🙂I am so pleased with the sound, even though I may keep taking it to the bench for testing, I have, so far, not changed it. I spent last night preparing my 300B stereo SET for the two transformers I order from Marko in Poland. In the 6SN7 driving the 300B I ended up changing the 22K cathode resistor to 18K and the 75K to 82K to truly tweak it to the best I can get it. I have learned that when using a scope on the 6SN7 stages up to the grid of the 300B (or whatever output tube) if either the top or bottom of the sine wave is "fatter" than the other, that indicates mostly 2nd order harmonic. That is one thing I focus on and work to get the sine wave at the grid of the 300B as perfect as possible. I think of that as "worthwhile" tweaking... Anyway, I should get my transformers in a couple of weeks and I will have a stereo version with high-end OPT transformers. The 300B will do 6.5 very nice watts and it will be interesting to see if it actually sounds better, or as good, as the 807. We will see...
@@ElPasoTubeAmps Thats intersting about the sine wave Im going to have to look at that, I have all the parts to finish my 300B amplifier minus the tubes themselves I have been meaning to order some but just get so busy doing other stuff I forget. It will be really interested to hear the 300B and the 807 side by side because the 807 is a really good sounding tube, the 300B has a cult following as the gold standard fro SET. talking about 6SN7 tubes they are probably my favourite as a driver I try and use them on most of my amps. And speaking of Marko I purchased his transformer calculator package from his website because I may or may not try winding my own.....one day haha. I think I will purchase some transformers from him for whatever I build next. Thanks for sharing another video with us all and I hope to see you again soon. If I don't talk to you before Christmas I hope you have a great Christmas and all the best to you!
If I remember correctly you have over 100uf cap directly connected to rectifier tube no current limit resistance.isnt that going to hard on the rectifier and hv winding of the transformer? Otherwise an interesting circuit.
That has been mention by another gentleman. It may have been just too much for the transformer. I left it on (forgot about it) for a couple of days and when I went to use it, it had blown the fuse. Checked it quickly and put in another 2A fuse - blown - you can tell if the failure is catastrophic when the inside of the glass if blackened by the melting of the fuse element. I knew something was serious wrong - fast forward - the secondary was shorted. I have never worried about the value of the input capacitor - I am cautious not to make it outrageous large but I think 100 uF should be OK. In any case I was lucky enough to have a better replacement. I am thinking the Hammond rating of 100 mA was not a 24/7 rating. I don't know for sure.
Very interesting. I've testing quite a few valve amps both SE & PP & have never seen a FFT result that hasn't had any 3H content. It shouldn't be a test gear anomaly. I'd be interested in seeing the result with a 100hz or lower signal. Also interested in seeing the OP prior to the OP valve. Thanks, a very thought provoking video.
Edit: Re sq wave test @ 1khz, looks like there's some LF rolloff. I usually set my NFB capacitor with a 10khz sq wave, then sw too 100hz sq wave & dial in the C. I usually have an LC/Zobel across the speaker OP teminals & from anode to ground set to the same F 3dB point.
The increased instability/ringing at 2khz from 1khz isn't good though, could it be down to the OPT? Have you done any no load & capacitive load testing? A 100n is a good value, it show up any instability issue's - no load LF instability, cap - HT instability.
Lastly, had a thought about the no 3H, the amps I've tested have been stereo amps with a common power supply, I've had issues with Xtalk, I wonder how much of the 3H content I saw was a consequence of Xtalk & or IM?
Lastly I I agree, don't matter what it tests like, if it sounds good, leave it be.
You have some really good thought provoking suggestions. 10 KHz square wave is very rounded - too rounded for a NFB bypass capacitor to have much if any effect. I posted a ChatGPT response to the question about only even harmonics in an SE amplifier in the comment section you might find interesting. The only other SE amplifier I have built, before this one, is one that I posted maybe three years ago using 300B and using PS chokes as plate load and a James 8K primary OPT to match to 8 ohms. Worked OK but did not have the sustained charm this one has. Somehow the 300B and choke load design/build tired me after a while. This one does not... This "Little Jewel" uses a genuine SE transformer so maybe I am just discovering something - I am still in awe of the harmonic profile. In the 300B just mentioned, it had a harmonic profile that was expected - huge 2H and small 3H. I will be doing some more testing tonight but as you say, don't mess it up... 🙂
@@ElPasoTubeAmps Hello David, I no longer have the amps in question & it was a few years ago when I tested them, so, can't be certain that I didn't assume them to be 2H, 3H etc. However the spacing between a 2H & 3H is quite noticeably different to 2H 4H etc.
I'll see if I have any footage stashed but I don't often bother with an FFT test.
You did say in your first comment that the 300B did have 3H content though, still, memory can be in error, mine often is. I have had test setup fault's EG odd readings from mains earth loops between scope & stereo dummy load too which I have to watch out for.
Whichever, I think your onto something that needs more investigation. My intuition is that the OPT's are playing a big part in this, hence why I suggested a look at the OP of V1 & V2, maybe V3 too - open loop at LF. Could be wrong though.
I've found that tweaking R & C value's, balancing PP stages etc might change THD by 0.01% or more, but your OPT & load has far more effect, especially load. Simple R dummy load testing only shows us so much, but we know a speaker is far more complex.
Keep up the good work, am finding this really instructive as I always do your work.
@@diabolicalartificer It just dawned on me what is going on - I was driving the amplifier with a 2 KHz pure sine wave. Harmonics are integer multiples of the fundamental so they are going to be harmonics of 4, 6, 8, 10, etc. - all even. Holy Cow... the thing about it however, is the driving signal is a very pure sine wave so the amplifier is indeed creating all these even harmonics as artifacts. I kept shaking my head last night thinking I surely must be confused - and I was - when I put in the 1 KHz square wave which is naturally the fundamental and all odd harmonics - that is what I got out. This has been banging around in my head and just did not seem right - and it wasn't. Sorry for the confusion.
@@ElPasoTubeAmps Of coarse, 6khz is the 3H, the numbers themselves fooled us both, being that they are even numbers, our brains equated them to even harmonics. Therefore your amp IS producing odd harmonics but it's the amplitude or level of these harmonics that is the important thing, not the number.
EG usually we see the F at 0dB say, the 2H at - 6dB, the 3H at - 5dB, or vice versa. your harmonics ARE unusual because they are all at the same level, instead of diminishing as they proceed.
Electronics eh : ) Have to keep your wits about you ; )
@@diabolicalartificer I like to think of this overlook as excitement rather than cognitive decline... 🙂 lol...
You applied injected a 2Khz square waveform but why would an amplifier has to be 10X times the fundamental? 2Khz X 10 = 20khz , I'm don't understand what makes the guitar amplifiers circuit design is 10X times the fundamental. The NFB does what to the Squarewave testing measurement?
Because you need at least so many harmonics to get a plausible square wave before the higher terms become negligiblez
At first, I thought this was in reference to a Grommes Little Jewel. I'm not sure which I like better now, haha.
I didn't know that. I looked it up and see he has a, Grommes LJ7 guitar amplifier. I named my amplifier after my latest kitten who I named, Jewel. I will have to study his schematic. 🙂
@ElPasoTubeAmps there were earlier models, too. The LJ-6 is what I have. They are very easily converted for guitar without permanent modifications.
@@ElPasoTubeAmpsGrommes Little Jewel was a hifi originally , nowadays lots of folks ( including me)are tasking them with guitar chores. Great amps either way
@@billfog393 Thank you - I looked up Grommes and found his equipment. Interesting we both chose the name, "Little Jewel" for our amplifiers. I assume he does not have a patent on the name... 🙂
It just dawned on me what is going on - I was driving the amplifier with a 2 KHz pure sine wave. Harmonics are integer multiples of the fundamental so they are going to be harmonics of 4, 6, 8, 10, etc. - all even. What I failed to realize is 6 and 10 ,for example, is the 3rd harmonic and 5th (odd) harmonic of 2 KHz. I was described as a kid in a candy store, and I have had too much candy... Holy Cow... the thing about it however, is the driving signal is a very pure sine wave so the amplifier is indeed creating all these even harmonics as artifacts. I kept shaking my head last night thinking I surely must be confused - and I was - when I put in the 1 KHz square wave which is the fundamental and all odd harmonics - that is what I got out. This has been banging around in my head and just did not seem right - and it wasn't. Sorry for the confusion.
Would it be possible for you to upload the schematic with some voltages written on it? I seen the schematic in an earlier post but it has no voltages written on it. For those of us who would like to try this Amp.
I can do that with a link to an unlisted video and no advertisements. We can't add to a posted video. Let me plan for it.
Apparently, the reason why we like even harmonics is because the harmonics are octaves of the fundamental, so they tend to sound more harmonious and musical to the human ear, octaves tend to sound consonant, whereas odd harmonics sound dissonant.
Something similar was mentioned in another post and the sum and differences of mixing fundamental with odd and even harmonics (may?) cause dissonant cords in the upper freqencies as I understant it - but I am no musician.
It is true, musically even harmonics can't even be called distortion. Musically even harmonics are not distortion at all, it is simply a musical octave. In Western civilization music, the music we all know, octaves are simply a doubling of frequency, and in music playing a note in any octave is always "still in tune". Therefore even harmonics can't be considered as distortion at all. When a musician doubles octaves, it thickens and warms the timbre, it is never dissonant. Odd harmonics however always generate additional notes in the music that are never anywhere near being "in tune". I would love to build this Amp now, oh boy just what I need, another project.
Another project - go for it... 🙂 Are not there fundamental/harmonic mixing conditions that create dissonant tones in the higher frequency region?
@@ElPasoTubeAmps Dissonance in higher instruments is always more offensive. Imagine two piccolos playing the same melody a semitone or less apart! Versus two double basses doing the same, the lower frequency is "slower" in exposing the "beat note" when tuning two instruments to each other, so not as noticeable. Chords containing all sorts of intervals minor/major thirds, seconds, 4ths, 5ths, 9ths, etc. mixes using the same 12 note intervals our brains recognize. The well-tempered musical scale is an amazing invention since it was actually established at a time when frequency measurement itself was impossible. All done by ear, the intervals Do Re Me, sharps and flats, and most importantly, octaves occurring at each doubling, which coincides with second harmonic "distortion" perfectly.
The reason, according to Floyd Toole and researchers at Harman and elsewhere is Even Harmonics are what occur in nature.
Whether a church bell, or banging on a pipe with a hammer, or a trumpet or violin, sounds in nature just naturally amplify Even Harmonics.
Maybe there is something in nature that evolutionarily led to a dislike Odd Order Harmonics. For example, I wonder what something like a Big Cat's growl looks like on a frequency spectrum?
We have evolved for that sound to really catch our attention. And probably have a visceral negative reaction to it. Now, in the modern day, when we hear brakes screeching, it is not much different than a Big Cat's growl, with the same reaction.
So my suspicion is that this preference for Even Harmonics is an Evolutionary trait, and that is something that could be easily researched.
But in the meantime, thank Satan for Tube Electronics. They don't just reproduce natural harmonics beautifully.
Also, when done well, they create incredible Soundstage, Imaging, a sense of Air and Spaciousness that I have yet to hear equalled by Solid State when comparing at the highest levels.
I started in high and HiFi back in the 80s. Only recently have I heard the jaw-dropping, just astounding performance of some of the pure Class A high-powered Transmitter Tube amplifiers.
Some of the ones that you have made are a great example. The 805s, 845s, and even some of the massive tubes used by NAT Audio that are as hot and bright as the Sun - you could get a tan - they are utterly amazing.
They put the performers in the room, and recreate the room that they're in, like no other amps.
I've also started to fall into the rabbit hole of some of the Preamps employing the big signal tubes, and again, there is Soundstage and Imaging, as well as inner detail and resolution, without any harshness or fatigue, that's on a whole other level.
So the incredible ability of tubes seems to be never ending. And I'm totally down for that. Bring it on!
This is simply untrue. It is easy to construct natural resonators that produce 3HD: for example, a clarinet.
The truth of this is that it isn’t the even harmonics that are pleasing: it is the ones that are powers of two, because they are octaves and don’t disturb the harmonic structure. There isn’t much pleasing about a sixth or tenth harmonic.
Bizarre that people are still researching this. It was known to organ builders before Bach was born.