Parallel connecting of big capacitors with smaller capacitors for optimising the sound??

[john12ax7]

In which position (PSU, cathode, filter or coupling) did Ken Fischer do this? A quick web search revealed that he sometimes connected a film coupling capacitor in parallel with a ceramic capacitor of the same size. So to speak, the 100% version compared to the 10% or 1% version.
He must have had his reasons for doing so.

In a guitar amp for coupling an Orange Drop will sound different than a Mallory which will sound different than a ceramic. It's a way to blend sonic characteristics of different parts, a blend of non-linearities .

For pro audio you might want this, you might not. When you see a smaller cap next to a bigger one, it is usually an attempt to make a more ideal capacitor that works over a wider bandwidth.

 

[Gus]

you can hear class 3 ceramics in certain places and voltages so if the .001uF is a class 3 in the trainweck it could make a difference.
It has dielectric stress caused by the plate to grid voltage difference.

Some people also like a class 3 cap at treble spot in a Fender or Marshall tone stack.

 

[abbey road d enfer]

you can hear class 3 ceramics in certain places and voltages so if the .001uF is a class 3 in the trainweck it could make a difference.
It has dielectric stress caused by the plate to grid voltage difference.

Some people also like a class 3 cap at treble spot in a Fender or Marshall tone stack.

Guitar amps are unabashed dirtifyers.

 

[CJ]

some fender treble caps, 250 pf, put a little spike on top of the wave, some don't, can be seen with the scope,

 

[abbey road d enfer]

What do you think, does it make sense at this point to complement a bigger capacitor (like c9) with a smaller film capacitor (let's say a MKP 0.22uF)?

I would first replace this capacitor with a recent one. The difference in performance of capacitors in the last 20 years is phenomenal.
I bet it would produce more difference than adding 1% to the existing cap.
Now you may not like this difference.

 

[Philbo King]

I used to do this routinely for the RF/microwave circuits I designed. Sometimes 3 or 4 cap values. Because a lot of caps are not intrinsically wideband (talking in MHz/GHz here).

 

[abbey road d enfer]

I used to do this routinely for the RF/microwave circuits I designed. Sometimes 3 or 4 cap values. Because a lot of caps are not intrinsically wideband (talking in MHz/GHz here).

It sure makes sense for RF circuits, where the parasitic inductance make the capacitors appear as isolated tuned circuits.
How relevant for audio circuits implies analyzing the consequences in terms of response and stability of active circuits.
I believe there is no doubt about the benefits of paralleling capacitors for rail decoupling purposes. For signal coupling, the debate is still open.
I have never met a case where paralleling a small film or ceramic to a signal-coupling electrolytic made a significant difference, except for circuits with very low impedance, such as the capacitor that goes to ground in NFB (such as JR mentioned in his phono preamp) or the capacitor in series with the gain pot in a Cohen preamp.
Analyzing this type of concern always implies modelling the parasitics and accepting the fact that a wire is a resistor in swith an inductor and that "ground" is a fiction.

 

[Philbo King]

It sure makes sense for RF circuits, where the parasitic inductance make the capacitors appear as isolated tuned circuits.
How relevant for audio circuits implies analyzing the consequences in terms of response and stability of active circuits.
I believe there is no doubt about the benefits of paralleling capacitors for rail decoupling purposes. For signal coupling, the debate is still open.
I have never met a case where paralleling a small film or ceramic to a signal-coupling electrolytic made a significant difference, except for circuits with very low impedance, such as the capacitor that goes to ground in NFB (such as JR mentioned in his phono preamp) or the capacitor in series with the gain pot in a Cohen preamp.
Analyzing this type of concern always implies modelling the parasitics and accepting the fact that a wire is a resistor in swith an inductor and that "ground" is a fiction.

Precisely so. Audio is easy-peasey compared to RF.

 

[MicUlli]

Different capacitor types and values in parallel make sense for DC blocking and RF stuff. Sometimes i have seen this principle in passive speaker crossovers where the load (tweeter) has quite a low impedance...

 

[Wavelength]

Like 3 years ago we had access to one of those $$$$ network analyzers so we did a number of tests like the typical bypass an electrolytic with a film or smaller ceramic and so forth.
The conclusion was really interesting and simple. Unless you are paralleling the same type and value it's actually working against you.
But considering what you are doing the sonic results and listening may lead you another way. Just like the amount of capacitance. Unless you have a real nice super low noise FFT analyzer then choosing the value might be guess work or calculated. Sims to me never get the bypass stuff right, maybe close.

 

[Script]

Thought I'd try.
Here's what ChatGPT says:

You
In electronic circuits, sometimes electrolytic capacitors are bypassed by smaller film caps. Why? What is the merit here?


ChatGPT
Bypassing electrolytic capacitors with smaller film capacitors is often done to improve high-frequency response and reduce the equivalent series resistance (ESR) of the circuit. Film capacitors have lower ESR and better high-frequency characteristics compared to electrolytic capacitors, making them more effective in filtering out noise and improving signal integrity. This combination helps to enhance the overall performance of the circuit, especially in applications where high-frequency signals are critical.

You
How is the value for ratio determined? Is there a rule of thumb?


ChatGPT
The choice of the ratio between electrolytic capacitors and film capacitors in bypassing is often based on the specific requirements of the circuit and the frequencies involved. While there isn't a strict rule of thumb applicable to all cases, some general guidelines exist.
A common approach is to use a film capacitor with a value in the range of 0.01 μF to 0.1 μF for bypassing electrolytic capacitors. The exact value depends on factors such as the frequency range of interest, the capacitance of the electrolytic capacitor being bypassed, and the specific application requirements.
It's essential to consider the impedance characteristics of both capacitors at the frequencies of interest. The goal is to create a combination that effectively filters out noise and provides a low-impedance path for high-frequency signals.
Experimentation and simulation can be valuable tools in determining the optimal ratio for a given circuit, as the ideal values can vary based on the specific design and performance goals.

You
Does this apply to an audio path too, cos human hearing is not particularly high frequency.


ChatGPT
Yes, the concept of bypassing electrolytic capacitors with film capacitors can also apply to audio circuits. While human hearing is not particularly sensitive to extremely high frequencies, the audio signal path can still benefit from effective filtering and improved impedance characteristics.
In audio applications, the focus may be on enhancing the mid-range frequencies and addressing any potential distortion or noise that could affect the overall audio quality. Choosing appropriate values for film capacitors in parallel with electrolytic capacitors can help achieve better high-frequency response, reduce distortion, and improve the clarity of the audio signal.
Again, the specific values and ratios may depend on the characteristics of the audio circuit, the components used, and the desired audio performance. Experimentation and careful consideration of the frequency response requirements in the audible range can guide the selection of capacitor values for optimal results in audio applications.


ChatGPT can make mistakes. Consider checking important information.

 

[abbey road d enfer]

Here's what ChatGPT says:

A collection of hearsays, with a lot of conditionals. You could have the same answer from a lawyer, but it would cost more.

 

[JohnRoberts]

Thought I'd try.
Here's what ChatGPT says:

You
In electronic circuits, sometimes electrolytic capacitors are bypassed by smaller film caps. Why? What is the merit here?


ChatGPT
Bypassing electrolytic capacitors with smaller film capacitors is often done to improve high-frequency response and reduce the equivalent series resistance (ESR) of the circuit. Film capacitors have lower ESR and better high-frequency characteristics compared to electrolytic capacitors, making them more effective in filtering out noise and improving signal integrity. This combination helps to enhance the overall performance of the circuit, especially in applications where high-frequency signals are critical.

You
How is the value for ratio determined? Is there a rule of thumb?


ChatGPT
The choice of the ratio between electrolytic capacitors and film capacitors in bypassing is often based on the specific requirements of the circuit and the frequencies involved. While there isn't a strict rule of thumb applicable to all cases, some general guidelines exist.
A common approach is to use a film capacitor with a value in the range of 0.01 μF to 0.1 μF for bypassing electrolytic capacitors. The exact value depends on factors such as the frequency range of interest, the capacitance of the electrolytic capacitor being bypassed, and the specific application requirements.
It's essential to consider the impedance characteristics of both capacitors at the frequencies of interest. The goal is to create a combination that effectively filters out noise and provides a low-impedance path for high-frequency signals.
Experimentation and simulation can be valuable tools in determining the optimal ratio for a given circuit, as the ideal values can vary based on the specific design and performance goals.

You
Does this apply to an audio path too, cos human hearing is not particularly high frequency.


ChatGPT
Yes, the concept of bypassing electrolytic capacitors with film capacitors can also apply to audio circuits. While human hearing is not particularly sensitive to extremely high frequencies, the audio signal path can still benefit from effective filtering and improved impedance characteristics.
In audio applications, the focus may be on enhancing the mid-range frequencies and addressing any potential distortion or noise that could affect the overall audio quality. Choosing appropriate values for film capacitors in parallel with electrolytic capacitors can help achieve better high-frequency response, reduce distortion, and improve the clarity of the audio signal.
Again, the specific values and ratios may depend on the characteristics of the audio circuit, the components used, and the desired audio performance. Experimentation and careful consideration of the frequency response requirements in the audible range can guide the selection of capacitor values for optimal results in audio applications.


ChatGPT can make mistakes. Consider checking important information.

I feel dumber after reading that....

JR

 

[Script]

LOL Yes. Not overly informative.

I tried the opposite argumentation with chatgpt, implying that paralleling caps in an audio path (other than for tuning cutoff fq in a filter) is urban electronic myth.

Seems that chatty has read this thread (good info above) It dropped ESR and ESL as parameters in RF. scenarios and rail decoupling, adding that paralleling caps in audio path is pursued rather by musicians and audiophiles.

Other than that not much wiser

 

[ruffrecords]

ChatGPT sounds more like a clueless politician every day.

Cheers

Ian

 

[rock soderstrom]

ChatGPT sounds more like a clueless politician every day.

It reminds me more of some of my former students in exams. Somehow they learned the subject matter but didn't really understand it and to cover it up they say way too much.

How would you grade this answer?

(Marks 1 to 6, where 1 is very good and 6 is really bad).

 

[abbey road d enfer]

How would you grade this answer?

Grades are sooo 20th century...

 

[rock soderstrom]

Grades are sooo 20th century...

So true. You can grade without restraint, ChatGPT won't take you to court for traumatization. (I hope)

 

[moamps]

1

 

[Newmarket]

Precisely so. Audio is easy-peasey compared to RF.

That seems a rather sweeping statement tbh. RF obviously had its particular challenges, techniques and solutions. But audio has some amazing specs compared to other fields eg SNR, Dynamic Range, THD, clock jitter etc.