Importance of replacing the electrolytic capacitors in any vintage gears

[nanook]

Zero - current - check:
There's no trim-pot for the bias current nor for output offset voltage; the output stage obviously lives with a fixed value and all you can do is check the bias current as described.
The resistor defining the bias current seems not to be determined in production (NAD did this) but they fitted a 68 Ohm resistor according to the service manual that is attached.

Capacitors:
There are a lot of electrolytic caps in the signal path, some of them even as low as 0.47uF. Since the circuit is quite "high-ohmic" in many places, you will not notice a dried out cap until it reaches the nF regime, but you might notice a "fat bass" because the HP-filter formed by the dry cap and the DC-return-path will generate some harmonics. I'm speculating
If you want to really use this amplifier, my take would be to change all except for the reservoir caps. The 0.47uF, 1uF and 3.3uF even suggest for a replacement with film caps (polyester, so MKT or MKS are definitely good enough).
But I have already outed myself as the member of the "replace-all crowd".
If you have an ESR meter - or can borrow one - this is the first step.

Volume Potentiometer:
Those were not bad so I'd only replace it when it's really bad or if it's not possible to eliminate the scratching with Teslanol T6.
You can apply a sinewave with a frequency that your multimeter can measure correctly (many multimeters are specified up to 400 Hz only, but in the end you just compare the values for L and R, so the absolute value is not important)
Loudness: off
Tone control: flat
Then start with volume fully cw and check the ac voltages L and R. The signal source should be set such that the amplifier is not clipping. Just dial the level such that you measure e.g. 10V ac at the outputs. Then reduce the volume by e.g. 5dB and compare again, then 10dB....
Note: Most potentiometers do have significant L/R deviation for attenuation of 40dB and higher.

Have fun!

 

[nanook]

This talk about replacing op amps that keeps popping up here on ASR. Not something I planned to do, just thought I'd mention it in passing. As a curiosity.

If you really want to replace the Opamp (it's just one dual one for the phono preamp as far as the schematic tells), you might want to try the venerable NE5532. It's cheap, it has gotten fairly low voltage noise and it has comparably low current noise.
But I'm pretty sure that you will not notice a difference.

 

[KSTR]

My question:
Which parameters of an aluminium electrolyitic capacitor change when it wears out / dries out?

This is the KI answer:

When an aluminium electrolytic capacitor wears out or dries out, several of its electrical parameters degrade. The most critical changes are:

---

1. Capacitance (C)​

• Decreases as the electrolyte dries out.
• The dielectric layer (aluminium oxide) remains, but the reduction in effective surface area and increased spacing from electrolyte loss reduces capacitance.

---

2. Equivalent Series Resistance (ESR)​

• Increases significantly with aging.
• Dried-out electrolyte increases internal resistance, leading to higher ESR.
• This is one of the most noticeable and damaging effects.

---

3. Leakage Current​

• Can increase or decrease depending on how the dielectric is affected.
• Often, in dried-out caps, leakage current decreases, but if the oxide layer is damaged, leakage may increase.

---

4. Dissipation Factor (tan δ)​

• Increases with ESR and dielectric degradation.
• Higher dissipation factor indicates more energy loss as heat.

---

5. Impedance​

• Increases, especially at higher frequencies.
• Due to increased ESR and decreased capacitance.

---

6. Ripple Current Handling​

• Decreases, making the capacitor more prone to overheating and failure under normal conditions.

---

Summary Table:​

Parameter	Change when drying out
Capacitance	↓ Decreases
ESR	↑ Increases significantly
Leakage Current	↑ or ↓ (varies)
Dissipation Factor	↑ Increases
Impedance	↑ Increases
Ripple Current Rating	↓ Decreases

---

Diagnostic Tip:​

An ESR meter is often the most effective tool to detect worn-out aluminium electrolytics in-circuit, as ESR is the parameter most sensitive to electrolyte degradation.
Let me know if you want to know how this affects circuits like power supplies or audio paths.

My question: How about dielectric absorption?

KI answer:

Great question!

Dielectric Absorption (a.k.a. “soakage”)​

Dielectric absorption is the phenomenon where a capacitor, after being discharged, slowly regains some voltage due to charge retention in the dielectric material.

---

What happens to dielectric absorption in a worn-out aluminium electrolytic capacitor?​

Short answer:
Dielectric absorption may slightly change, but it is not a dominant failure mode in dried-out aluminium electrolytics.

---

Details:​

1. Electrolytic capacitors use an oxide layer (Al₂O₃) as the dielectric, which is formed electrochemically.
2. The electrolyte's role is to maintain this oxide and serve as part of the anode system.
3. As the electrolyte dries out, the oxide may degrade, and the internal structure changes.
4. This might cause minor changesin dielectric absorption, but:
   • ESR, capacitance, and leakage current degrade much more significantly.
   • Dielectric absorption is not usually measured or used as a diagnostic indicator of aging in electrolytic caps.

---

In practice:​

• For precision applications (like sample-and-hold circuits), dielectric absorption is a concern — but aluminium electrolytics are already poor choices for such applications, even when new.
• Other capacitor types (e.g., film, ceramic, tantalum) are evaluated more closely for dielectric absorption.

---

Summary:​

Parameter	Changes with aging	Diagnostic relevance
Dielectric Absorption	Slight, unclear	Low
Capacitance	Decreases	High
ESR	Increases	Very high
Leakage Current	Can increase	Medium

---

If you're troubleshooting a circuit, dielectric absorption is not worth testing in electrolytics. Focus on ESR and capacitance instead.
Want a quick guide on testing electrolytics in-circuit?

Never ever trust AI answers on technical questions. In this case, it doesn't understand the failure mechanism and missed the reference I'm giving below (found the paper, see attachment):

Key line:
"During early Z METER tests, Sencore Application Engineers found that the D/A level is a very good indicator of electrolytic aging. The D/A often gets worse before any other measurable changes appear, such as value, leakage, or ESR."

 

[DanielT]

Zero - current - check:
There's no trim-pot for the bias current nor for output offset voltage; the output stage obviously lives with a fixed value and all you can do is check the bias current as described.
The resistor defining the bias current seems not to be determined in production (NAD did this) but they fitted a 68 Ohm resistor according to the service manual that is attached.

Capacitors:
There are a lot of electrolytic caps in the signal path, some of them even as low as 0.47uF. Since the circuit is quite "high-ohmic" in many places, you will not notice a dried out cap until it reaches the nF regime, but you might notice a "fat bass" because the HP-filter formed by the dry cap and the DC-return-path will generate some harmonics. I'm speculating
If you want to really use this amplifier, my take would be to change all except for the reservoir caps. The 0.47uF, 1uF and 3.3uF even suggest for a replacement with film caps (polyester, so MKT or MKS are definitely good enough).
But I have already outed myself as the member of the "replace-all crowd".
If you have an ESR meter - or can borrow one - this is the first step.

Volume Potentiometer:
Those were not bad so I'd only replace it when it's really bad or if it's not possible to eliminate the scratching with Teslanol T6.
You can apply a sinewave with a frequency that your multimeter can measure correctly (many multimeters are specified up to 400 Hz only, but in the end you just compare the values for L and R, so the absolute value is not important)
Loudness: off
Tone control: flat
Then start with volume fully cw and check the ac voltages L and R. The signal source should be set such that the amplifier is not clipping. Just dial the level such that you measure e.g. 10V ac at the outputs. Then reduce the volume by e.g. 5dB and compare again, then 10dB....
Note: Most potentiometers do have significant L/R deviation for attenuation of 40dB and higher.

Have fun!

I thank you for the tips and advice.

I'll check what kind of measuring equipment my friend has. I'm almost certain that he has an ESR meter because his hobby is fixing amplifiers/receivers.
IF my friend starts a more extensive replacement operation like you suggest, I want him to measure and check the condition of the capacitors before he does it. If they measure ok, I see no reason to change. Or maybe as a preventative measure....or not. Which what this thread is about. To change or not and when and why if so. Pros and cons.
Regarding relay contacts. About the same thing there as the capacitors.

If you really want to replace the Opamp (it's just one dual one for the phono preamp as far as the schematic tells), you might want to try the venerable NE5532. It's cheap, it has gotten fairly low voltage noise and it has comparably low current noise.
But I'm pretty sure that you will not notice a difference.

Well. Nop. I'm not changing it. IF I don't need to change capacitors, if they're not up to spec, so you can access the existing op amp, when the amplifier is disassembled. Then we do it. Mostly because I happen to have one:

...at home. Which I don't use for anything anyway.

By the way, op amp rolling is not really my thing:

'Replace OP amps. Completely pointless, or not?'

Oct 2, 2021

Why do so many OPs change amps in, for example, the amplifier AIYIMA A07 TPA3255?

What's the point of that? Does not modern OPs amps amplify the signal completely linear straight(if the construction they sit in is well constructed,
and made to fit OP amp X)? Do not modern OP amps have a distortion level far, I mean really FAR below the audible? What the hell is the difference in sound that those who change claim to hear? Is it just imagination or have I missed something now?

Tips for those who have a friend who can help. Just to test. OP amps are not expensive. Ask your friend to...

• DanielT
• Replies: 651
• Forum: Audio Newbie/Beginner Technical Forum

• 

 

[Dimitri]

Apart from the caps I would follow @MAB's recommendations. Replace or clean relay contacts, treat pots and switches with "Oszillin Teslanol T6" contact spray (it's been renamed a couple of years ago and is called "Contact spray" on the can but is advertised as Teslanol T6 in many cases to avoid confusion).

Relays are sneaky. I recently repaired / replaced capacitors on a marantz. Out of all the capacitors replaced only three had slightly high ESR, the rest I would consider "good". The relay story is more interesting.
The relay was replaced "just because i was in there anyway", ( I did all the work on the PA without disconnecting any of the wire-wrapped wires ) and I didn't want to have to go back and do it again;
The old relay did have a measurably "high" resistance between the contacts in the low single digit ohms.

 

[rdenney]

If you really want to replace the Opamp (it's just one dual one for the phono preamp as far as the schematic tells), you might want to try the venerable NE5532. It's cheap, it has gotten fairly low voltage noise and it has comparably low current noise.
But I'm pretty sure that you will not notice a difference.

Those are the opamps used in my Yamaha YP2006 digital parametric equalizer. That unit is quite clean.

Rick “but never had any issue with TL072’s and 82’s, either” Denney

 

[nanook]

Never ever trust AI answers on technical questions. In this case, it doesn't understand the failure mechanism and missed the reference I'm giving below (found the paper, see attachment):

Key line:
"During early Z METER tests, Sencore Application Engineers found that the D/A level is a very good indicator of electrolytic aging. The D/A often gets worse before any other measurable changes appear, such as value, leakage, or ESR."

Well, never trust a company that has commercial interests either . This is not a scientific paper being peer-reviewed in the end.

The explanation of the suggested mechanism (crystallization at the electrode) makes plausible, that an ESR measurement would only show a slight increase (max. +10% if ca. 10% of the total area are "decoupled" by series resistance).
But shouldn't the capacitance measured at e.g. 100 Hz reveal that areas having an RC time constant >63ms?
Measuring capacitance with a sinewave of relatively low frequency (low due to the high capacitance of electrolytic caps), you do include the contributions of areas having shorter time constants (i.e. they do contribute) and they thus do not show up as reduced capacitance. Measuring caps with higher capacitance might be done sourcing a constant DC current and measuring the voltage; this will probably take fractions of a second or even longer, so only fairly slow time constants will show up as reduced capacitance.
The example they give in fig. 11 however suggests a time constant of 10^4 s and thus would have shown up in a capacitance measurement.

Thanks for looking up the paper, this is an interesting idea. When the next suitable dried out capacitor crosses my way I will try to do a measurement of |Z| vs. frequency.

 

[SSS]

Never ever trust AI answers on technical questions. In this case, it doesn't understand the failure mechanism and missed the reference I'm giving below (found the paper, see attachment):

Key line:
"During early Z METER tests, Sencore Application Engineers found that the D/A level is a very good indicator of electrolytic aging. The D/A often gets worse before any other measurable changes appear, such as value, leakage, or ESR."

Measuring dielectric absorbtion is not easy and not feasible in-circuit. So you had to solder the suspect out, instead of measuring then you may direct replace it with a new cap. Whether the D/A is really an indicator for an ageing electrolytic cap, I am not sure because you hardly will find the spec for a new and an used cap.

 

[KSTR]

Measuring ESR is also not always feasible in-circuit. But of course it's true that measuring D/A is problematic because there is usually no reference data for new capacitors.

The above does not make the observed phenomenon invalid, peer-reviewed or not. D/A tends to rise before other entities show relevant changes and one could use that as an early indicator. I see no reason why we should doubt that, rather we should think about how to exploit it.

 

[nanook]

I'm cautious because this is so far the only source of this information and stating it as fact isn't making it a fact, at least not in general.

Manufacturers of caps provide no information on this for aluminum electrolytic caps as far as I searched the literature.

I came across a reliability paper on capacitors in general. It's from 1999, so quite a bit old, but that's in line with the age of equipment we're talking about:

https://restservice.epri.com/publicdownload/TR-112175/0/Product

Although quite extensive, it doesn't say much about dielectric absorption.

2.3.2.5 Dielectric Absorption
"The apparent capacitance of a capacitor can be strongly affected by absorption effects. A capacitor measured at low frequencies might appear to have a much greater capacitance than at high frequencies."

3.2 Off-Line Monitoring for Components
"For example, the allowable dielectric
absorption is 15% for aluminum and tantalum electrolytic capacitors."

Excerpt from another white paper from Cornell-Dubilier:

https://www.rellpower.com/wp/wp-content/uploads/2018/09/AEappGUIDE1.pdf

"DIELECTRIC ABSORPTION
Dielectric absorption may be observed as the reappearance of a voltage across a capacitor after the terminals have been shorted for a brief period and the short removed. This characteristic is important in RC timing circuits, triggering systems and phase shift networks. For aluminum electrolytic capacitors dielectric absorption will allow up to 10% recovery of the charging voltage between 100 s and 1000 s at 25 °C, and is more pronounced at higher temperatures. Maximum dielectric absorption can be obtained by charging capacitors for 1 hour at rated voltage and discharging through a dead short for 1 minute. Subsequent measurements over time can be made with a high impedance micrometer."

This sounds like the time constants involved are fairly long (and thus should get visible with a capacitance measurement at 100Hz), but maybe much smaller time constants exist, so I'd be really curious to see a |Z| vs. frequency plot for a fresh, a stored and a worn out capacitor of similar value, rating and size.
-> If someone owns a Z-meter that can measure vs. frequency, I'd really appreciate if you could give it a try.

Regarding "in circuit" measurement of ESR:
This is possible in most cases. My "blue" ESR meter applies a step of a few hundred millivolts only, such that silicon diodes (ESD protection of ICs, etc.) will "not" conduct. You will be fooled if several caps are connected in parallel (usually power supply in so called "high-end" gear) or in C-L-C PI-filters (output section in SMPS). So in case you measure an almost identical ESR for some caps, I'd recommend to check with an Ohms-meter if they are connected (with or without L between them) in parallel.

 

[nanook]

Measuring Z of a polarized aluminum electrolytic cap: would you measure it with DC bias voltage applied or at 0V?

Sure, if measuring with 0V, the AC voltage across the cap has to be fairly low, e.g. <1Vpk (1.5V reverse DC bias are considered safe for this type of capacitor).

 

[SSS]

I measure electrolytic caps without DC bias since my ESR meter uses only around 100 mV at high frequency. So there is no long time for backward biasing the cap.
Since the ESR values are not needed to measure with 1 % tolerance I think a possible slight error can be tolerated. But it is right to measure the capacitance and other parameters with the cap biased since this is the normal usage in operation. Exception is non-polarized electrolytic caps like used in passive crossovers for loudspeakers.

 

[nanook]

I will try to measure Z without bias as a first step. I can still add a quality cap in series and apply a bias via a e.g. 1 kOhm resistor.

Wil take a bit - I'm traveling at the moment

 

[AnalogSteph]

Since I've been playing with capacitors a fair bit lately (owing to my new ESR meter and lab power supply), I noticed that leakage may be a more sensitive indicator than ESR - I had two caps of the same type and similar age, and one measured about 50% higher ESR but leakage current at rated voltage remained a factor of 10 higher (settling at ~3 µA where the other Elna 1000µ/25 settled below 0.3µA, ESR being 0.04-0.05 ohms vs. 0.03 ohms; the better one is virtually like new and went in the parts bin). ESR is the more practical one since it can be measured in-circuit, obviously.

I would consider doubled ESR "tired but still serviceable" and tripled ESR grounds for replacement. The tricky part is having a good frame of reference for ESR depending on capacitance, voltage rating, size, proportions and type.

Risk factors for electrolytics of a certain level of quality seem to be being of medium capacitance (33-100 µF) at low to medium voltage ratings (10-16 V in particular, but up to 35 V at times), and being located near heat sources like regulator heatsinks or zener diodes. Physical size plays in here, I guess. Also, types of 10 or 16 V rating seem more prone to failing short if the device has been left unused for a long time. (Case in point, the two 470µ/10V and one 47µ/16V I pulled out of a Kenwood KT-880L. Funnily enough, not the ones seeing the highest voltages relative to their ratings in use. Perhaps being run near the edge keeps caps on their toes so to speak? Leakage does go down dramatically with applied voltage after all, and that's associated with regeneration, so in a hot environment degradation might eventually outrun it. Just a theory.)

I have measured ESR for various types new and NOS, so here you go:
Aishi 1µ/100V - ESR 5.3 ohms (#1), 5.4 ohms (#2).
Jamicon SS 2.2µ/50V - ESR 5.6 ohms.
Elite 4.7µ/25V - ESR 0.9 ohms (#1 and #2).
Jamicon TK 4.7µ/63V - #1 1.5 ohms, #2 2.0 ohms.
NOS blue Philips axial 4.7µ/100V - 2.5 / 1.9 ohms, leaky junk
CapXon GL 10µ/63V - 0.93 / 0.83 / 0.82 / 0.88 ohms
Jamicon TK 22µ/63V (NOS from 20+years ago) - 0.80 / 0.80 / 0.87 / 0.83 ohms.
Elite 33µ/63V - #1 0.49 ohms, #2 0.52 ohms
Samwha RD 47µ/35V - #1 0.19 ohms, #2 0.17 ohms.
Jamicon SS 100µ/16V - 0.45 ohms
Jamicon TK 100µ/35V - #1 0.18 ohms, #2 0.21 ohms
CapXon 100µ/63V (parts jar) - 0.08 ohms
Samwhat WL 100µ/63V - 0.07 ohms
Matsushita ED 100µ/160V - #1 0.14 ohms, #2 0.15 ohms. (High voltage tax right there.)
Jamicon TK 220µ/35V - 0.09 ohms (#1, #2 and #3).
Elite 220µ/63V - 0.10 ohms
CapXon 220µ/63V (parts jar) - 0.05 ohms
Samwha RD 330µ/63V - 0.10 ohms
Jamicon TK 470µ/25V - 0.07 ohms (#1 and #2).
Jamicon TK 1000µ/63 - 0.03 ohms
Nichicon UPW 1200µ/35V (16x20mm) - 0.03 ohms, leakage eventually settling a bit under 0.1µA overnight
Nichicon PL 2200µ/16 (parts jar) - 0.02 ohms

In terms of used caps, I found 3.5-3.6 ohms in '80s 1µ/50V Elnas, most 10µ/35s a bit above 1 ohm, and 47µ/16V at 0.23 ohms. While a near 45-year-old orange Elna low-leakage 0.47µ/50V is too small for ESR to be measured accurately with my meter, leakage settled at under 0.01 µA at its rated 50 V.

It goes without saying that a circuit's sensitivity to bad caps can vary widely. Anything switch-mode is likely to be relatively fussy, linear circuitry less so.
The cap that kept my 1992 Kenwood KT-3050L from working was a 4.7µ/50V used as a mains filter in power-down detection that measured ESR = 10.3 ohms and capacitance = 1.66 µF out of circuit - very much toast. I also replaced a 10µ/35V on the output of the 5.6V regulator that measured 2.38 ohms with almost all capacitance remaining. In the power supply section of a 1987 KT-1100D that showed no outward signs of trouble, I found one 33µ/35V at 1.03 ohms, one 47µ/10V at 1.27 ohms, one 100µ/10V at 1.12 ohms (all 3 of which have now been replaced) and one 100µ/35V at 0.36V struck me as dubious at least. Of the big guys, only one 1000µ/35V seems a bit tired at 0.04 ohms, the others basically measure like new (330µ/35V - 0.10 ohms, 330µ/50V - 0.09 ohms, 2200µ/35V - 0.02 ohms).
In an Onkyo T-422 which I suspect of being high hours (on account of standby being almost the same as on and a very dark top case inside), the 1000µ/25V measured 0.05 ohms (which might account for a bit of low-level hum), a 47µ/100V with adjacent resistive heating (should be in the negative voltage supply for the display) measured 2.5 ohms = toast and has since been replaced by a new 100µ/63V, and surprisingly a 100µ/16V at the frontend was up to 0.55 ohms (though given the results for the one new Jamicon I measured, this may not even be too far out of line - I might stuff a 220µ/35V in there if I can make it fit).
All of the caps in question were quality types from Elna (Kenwood) or Nichicon (Onkyo), respectively.

Whenever I see coupling capacitors of a decent voltage rating that have only seen a few millivolts in decades, I tend to seriously consider reforming them externally. The quality of replacements I can get locally is all over the map. I still have to look at the leakage I can get on such pulls more closely.

 

[Winner]

I just replaced all the caps on my KEF103/4 crossovers (30+ years old) and the bass is sharper and tighter and the highs are crystal clear, almost too bright listening to black pink (girly squeaky voices for the purpose of testing highs) anyway my point is that all my old caps are within capacitor spec and ESR values are well within spec. I bought a Zoyi DQ02 LCR bridge specifically for testing and it's accurate. So frens what gives? How come the caps are completely fine but the new ones "sound" better? Ran sweeps with UMIK-1 & REW and they're is no real difference but it's 'clearly' different.
Explain yourselves ASR bros.

 

[DanielT]

I just replaced all the caps on my KEF103/4 crossovers (30+ years old) and the bass is sharper and tighter and the highs are crystal clear, almost too bright listening to black pink (girly squeaky voices for the purpose of testing highs) anyway my point is that all my old caps are within capacitor spec and ESR values are well within spec. I bought a Zoyi DQ02 LCR bridge specifically for testing and it's accurate. So frens what gives? How come the caps are completely fine but the new ones "sound" better? Ran sweeps with UMIK-1 & REW and they're is no real difference but it's 'clearly' different.
Explain yourselves ASR bros.

IF you measured FR , distortion and so on found no difference: Imagination?

I imagine this and that. So do others. Sometimes with self-awareness we realize it was just imagination. In other cases, well... if we look at it from the positive side then...Ignorance is bliss?

IF you change the values of the components in the crossover, you get a different crossover. Of course, this can absolutely lead to audible differences before vs. after that, but that wasn't the case with you, was it? And you measured and saw no difference. Then it ends up in a different light.

Edit:
Incidentally, Danny at GR-Research is good at explaining how an upgrade of a crossover ( which does not show measurable differences before and after it is done) leads to a big differences in sound. How a crossover upgrade opens up the soundstage, more clarity, hear micro details and so on. Imagination? At least in his case, it is not imagination when the money in his wallet rattles after he sells his crossover upgrade.

 

[Audiofire]

Psychoacoustics.

Psychoacoustics is the scientific study of how humans perceive sound, combining aspects of psychology and acoustics to understand how we interpret different sounds and their emotional impacts. It explores how our auditory system processes sound waves and how various factors influence our listening experience.

Auto-generated based on listed sources by DuckDuckGo.

Understanding Psychoacoustics: Definition and Applications

Psychoacoustics combines the physiology of sound - how our bodies receive sound - with the psychology of sound, or how our brains interpret sound.

www.ansys.com

Psychoacoustics 101: How To Manipulate Emotions With Sound

Psychoacoustics, the fusion of psychology and acoustics that explores how we perceive and interpret sound, can help you make emotionally-packed music!

unison.audio

 

[Winner]

Psychoacoustics.


Auto-generated based on listed sources by DuckDuckGo.

Understanding Psychoacoustics: Definition and Applications

Psychoacoustics combines the physiology of sound - how our bodies receive sound - with the psychology of sound, or how our brains interpret sound.

www.ansys.com

Psychoacoustics 101: How To Manipulate Emotions With Sound

Psychoacoustics, the fusion of psychology and acoustics that explores how we perceive and interpret sound, can help you make emotionally-packed music!

unison.audio

IF you measured FR , distortion and so on found no difference: Imagination?

I imagine this and that. So do others. Sometimes with self-awareness we realize it was just imagination. In other cases, well... if we look at it from the positive side then...Ignorance is bliss?

IF you change the values of the components in the crossover, you get a different crossover. Of course, this can absolutely lead to audible differences before vs. after that, but that wasn't the case with you, was it? And you measured and saw no difference. Then it ends up in a different light.

Edit:
Incidentally, Danny at GR-Research is good at explaining how an upgrade of a crossover ( which does not show measurable differences before and after it is done) leads to a big differences in sound. How a crossover upgrade opens up the soundstage, more clarity, hear micro details and so on. Imagination? At least in his case, it is not imagination when the money in his wallet rattles after he sells his crossover upgrade.

Yeah dude, your right is all in my head. Won't bother contributing any more, I'm clearly a psycho. Good luck chaps. Psycho out.

 

[rdenney]

Yeah dude, your right is all in my head. Won't bother contributing any more, I'm clearly a psycho. Good luck chaps. Psycho out.

With all due respect, you are butt-hurt but you have not tested your own ability to perceive differences with rigorous, controlled testing. You invested in testing the cap and also the sound, but you did not test your own perceptions for reliability and repeatability.

Most of us have conducted those tests in various contexts, and we have learned that our hearing and perceptions play tricks on us. For example, I replaced the old electrolytic caps in my Advents with audiophile-grade film capacitors. Those old caps did not show any degradation either. During that process, I compared one speaker before the change with the other speaker after the change and could detect no discernable difference at all. I was actually a bit surprised that the old caps were still effective--I bought those speakers new in 1976.

Rick "we were all butt-hurt at first" Denney

 

[DanielT]

Yeah dude, your right is all in my head. Won't bother contributing any more, I'm clearly a psycho. Good luck chaps. Psycho out.

Don't take it personally. It's just a hypothesis. If there are no measurable differences, there shouldn't be any audible differences.

By the way, a few days ago I measured FR with a pair of crappy 8 inch bass drivers in a pair of sealed speaker boxes vs the same bass drivers in a pair of TQWP/ Voigt pipes. I experienced, thought it sounded like a better and lower bass in the TQWP. But after some measurements it turns out that there was no difference in FR between the different boxes/constructions. Imagination on my part? It could be the case or there is something else - that can be measured, just that I haven't done that type of measurement - that explains my perceived difference. Distortion, difference in SPL plus then in reaction to SPL- distortion for example, different resonances resulting in and so on.
It could be the same for you with your crossover and your measurements

Another explanation is that I made a mistake when I took my measurements and got the same results. I believe that hypothesis less, but I'll throw it in too.