Whats on your amp workbench?

[Jay]

Are you measuring bias on the 6L6 grid?

The above measurements were taken on the wiper of the pot. Actual measurements on the valve grid pins are about 3vdc different. Ie, -49 on wiper, -46 on valve pin.

Edit. Which means there is a 0.018 micro amp flowing through the 220kohm grid leak resistors

[MikeC]

Are you measuring bias on the 6L6 grid?

The above measurements were taken on the wiper of the pot. Actual measurements on the valve grid pins are about 3vdc different. Ie, -49 on wiper, -46 on valve pin.

Edit. Which means there is a 0.018 micro amp flowing through the 220kohm grid leak resistors

-46 on grid sounds reasonable but what % of MPD is it actually biased at?
I added a few more questions to my previous post.

[Jay]

Are you measuring bias on the 6L6 grid?
Also, EH 6L6 specs state 500V max on plates? It's not 6V6 is it?
Is it just biased too hot to deal with the lowered bias voltage that occurs with the trem settings as described.
Have you calculated the % of MPD at idle - can you lower this?

I don't know the brand of the 6L6, it is a repackaged Teonex one so no idea from what era it is and hence what spec to use. The lettering has gone from the valve.

Yes, leaving the trem depth pot at any setting leaves the bias voltage as per that setting even when you turn the trem switch off. In other words... the trem depth pot operates like a bias pot ( to the valves' detriment).

Yes, at idle with bias set to -49vdc, the 10 ohm cathode resistors provide a voltage measuremt of about 0.31v and 0.34v on the other. With plate voltage at 485v that equates to about 15w which is well under the 19w max.

Of course the bias can be set colder (not ideal) but I want to find out if what i experience is due to a bad design (ie, happens in all Jansen 6/20 & 6/30 etc) or is there a fault in this particular amp.

[MikeC]

If your MPD specs for those 6L6s & your plate dissipation calc is correct, then those 6L6s are biased quite hot at 79%.
Can you re-bias them to reduce the plate dissipation to around 60% of max and test trem again?
Or do you have another set of "known" 6L6s to install & bias to around 60% of mpd & test with trem?

[Jay]

Have you got another set of "known" 6L6s to try?

No I don't, but they behave perfectly okay when the trem depth pot is fully turned counterclock wise. In fact it sounds great with and without tremolo. It's just that when you turn OFF tremolo, you MUST turn depth down else it will start red plating.

[Jay]

So this is what Claude says after a few drill down questions... which is entirely what I said but I cannot believe that it is truly a design issue as valves would have blown up all the time... Jansen amps would have been finished a long time ago...

My last Claude Question:

with the tremolo ON and the tremolo depth potentiometer set halfway, it works fine. Then, when leaving the depth pot the same but turning the tremolo OFF with the pot switch, the output valves see a much hotter bias and start red plating

Claude's Answer:

Ah, that explains the issue! What you're describing is a classic case of bias modulation tremolo interacting with the bypass switch in a way that creates unexpected behavior.

When you turn the tremolo OFF using the switch while the depth is set halfway, the circuit is essentially "freezing" at whatever point in the modulation cycle it was at when switched off. If this happens to be at the "hot" part of the tremolo cycle (where bias is less negative), the tubes will suddenly be constantly biased at this hotter point rather than cycling between hot and cold.

This is definitely a design oversight in those Jansen models. Here's what's happening:

The tremolo circuit in these amps modulates the bias voltage to the power tubes
When operating normally, it swings between cooler and hotter bias points
The tremolo bypass switch apparently doesn't return the bias to its normal "no tremolo" setting
Instead, it locks the bias at whatever point in the cycle it was when switched off
Red plating is a serious concern that indicates the tubes are being pushed beyond their safe operating parameters. This can significantly reduce tube life or even damage the amp.

Solutions to consider:

Always turn the tremolo depth to zero before switching the tremolo off
Have a technician modify the bypass switch circuit to properly reset the bias when tremolo is turned off
Make sure to power down the amp if you notice red plating to prevent damage
This is definitely a circuit design issue rather than normal behavior. A proper tremolo bypass should return the bias to the standard operating point when disengaged.

[MikeC]

Have you got another set of "known" 6L6s to try?

No I don't, but they behave perfectly okay when the trem depth pot is fully turned counter clock wise. In fact it sounds great with and without tremolo. It's just that when you turn OFF tremolo, you MUST turn depth down else it will start red plating.

I'd drop the plate dissipation down to about 60% of max then see if red plating still occurs. The results of this will help.

As far as I can tell there are a number of possible scenarios.
1. The installed 6L6s are biased too hot (and they're unidentified so their specs are not actually known).
2. The installed 6L6 are bad.
3. There's a fault in the bias/trem circuit.
4. There isn't a fault in the bias/trem circuit bias/trem circuit but it causes a reduction in the bias voltage at the described settings which cause your current 6L6s at their current (potentially too hot) bias point to red plate.

[Jay]

Have you got another set of "known" 6L6s to try?

No I don't, but they behave perfectly okay when the trem depth pot is fully turned counter clock wise. In fact it sounds great with and without tremolo. It's just that when you turn OFF tremolo, you MUST turn depth down else it will start red plating.

I'd drop the plate dissipation down to about 60% of max then see if red plating still occurs. The results of this will help.

As far as I can tell there are a number of possible scenarios.
1. The installed 6L6s are biased too hot (and they're unidentified so their specs are not actually known).
2. The installed 6L6 are bad.
3. There's a fault in the bias/trem circuit.
4. There isn't a fault in the bias/trem circuit bias/trem circuit but it causes a reduction in the bias voltage at the described settings which cause your current 6L6s at their current (potentially too hot) bias point to red plate.

I had hoped RectifiedAmps would chime in but after spending much time on the web reading all sorts of stuff on fixed biased amps with tremolo bias wiggle, I have come to the conclusion that the Jansen 6/20 and 6/30 amps have an inherent design flaw which allows the tremolo circuit to interfere in a destructive way with the power valves' bias. In other words, biasing the power valves should be done in such a way that when the tremolo depth (or intensity) knob is on max, the plate currents must be within safe range... even when the tremolo is switched off.

For this particular amp I am fixing it means I need to modify the negative bias circuit so it can provide a higher negative voltage that what is currently available or I modify the tremolo circuit to allow for a reduced bias voltage swing.

TBC

[RectifiedAmps]

No I don't, but they behave perfectly okay when the trem depth pot is fully turned counter clock wise. In fact it sounds great with and without tremolo. It's just that when you turn OFF tremolo, you MUST turn depth down else it will start red plating.

I'd drop the plate dissipation down to about 60% of max then see if red plating still occurs. The results of this will help.

As far as I can tell there are a number of possible scenarios.
1. The installed 6L6s are biased too hot (and they're unidentified so their specs are not actually known).
2. The installed 6L6 are bad.
3. There's a fault in the bias/trem circuit.
4. There isn't a fault in the bias/trem circuit bias/trem circuit but it causes a reduction in the bias voltage at the described settings which cause your current 6L6s at their current (potentially too hot) bias point to red plate.

I had hoped RectifiedAmps would chime in but after spending much time on the web reading all sorts of stuff on fixed biased amps with tremolo bias wiggle, I have come to the conclusion that the Jansen 6/20 and 6/30 amps have an inherent design flaw which allows the tremolo circuit to interfere in a destructive way with the power valves' bias. In other words, biasing the power valves should be done in such a way that when the tremolo depth (or intensity) knob is on max, the plate currents must be within safe range... even when the tremolo is switched off.

For this particular amp I am fixing it means I need to modify the negative bias circuit so it can provide a higher negative voltage that what is currently available or I modify the tremolo circuit to allow for a reduced bias voltage swing.

TBC

Hi! Yes, this is a design issue and I’ve seen it on other bias-wiggle trem Jansens, although it often manifests while the trem is actually running if it runs long enough. I can’t remember what amp you’re talking about here but I’m guessing it has 6L6s. The max grid resistance rating for them in fixed bias mode specifies something like 100k. The grid resistors on Jansens are often 220k or 270k even, then that runs through the 500k trem depth control to ground, so the total resistance between the grid and ground can reach >700k, which is way higher than the rating. I guess grid current ‘builds up’ and the bias gets pulled down, causing over dissipation.

The solution is tricky but setting a colder bias (50%) should help to begin with. Then you can try 100k grid leak resistors. Then a 250k trem depth pot but that might weaken the trem oscillations too much, so it’s a last resort.

[Slowy]

Working on the principle that ignorance makes all things appear simple, this seems like a reason to disconnect the trem circuit entirely and use a Flint.

[crowbgood1]

Getting there - 1963
I need to put the speakers in. I have 4x8ohm speakers of about 25w, and from what I've read I will need to wire 2 pairs in series, then parallel the 2 pairs together to achieve 100w at 8ohms. Am I close?

Jansen cab.jpg (1.04 MiB) Viewed 492 times

[MikeC]

"I need to put the speakers in. I have 4x8ohm speakers of about 25w, and from what I've read I will need to wire 2 pairs in series, then parallel the 2 pairs together to achieve 100w at 8ohms. Am I close?"

Bullseye. You could also wire each pair in parallel then wire the two pairs in series. Potato/potarto but there may be a good reason to choose one method over the other.

[murky]

"I need to put the speakers in. I have 4x8ohm speakers of about 25w, and from what I've read I will need to wire 2 pairs in series, then parallel the 2 pairs together to achieve 100w at 8ohms. Am I close?"

Bullseye. You could also wire each pair in parallel then wire the two pairs in series. Potato/potarto but there may be a good reason to choose one method over the other.

The different wirings sound different (I know…..). Series-parallel also leaves 3 speakers working if one blows (as opposed to 2), and keeps the omage a little closer to pre blow.

[Jay]

I'd drop the plate dissipation down to about 60% of max then see if red plating still occurs. The results of this will help.

As far as I can tell there are a number of possible scenarios.
1. The installed 6L6s are biased too hot (and they're unidentified so their specs are not actually known).
2. The installed 6L6 are bad.
3. There's a fault in the bias/trem circuit.
4. There isn't a fault in the bias/trem circuit bias/trem circuit but it causes a reduction in the bias voltage at the described settings which cause your current 6L6s at their current (potentially too hot) bias point to red plate.

I had hoped RectifiedAmps would chime in but after spending much time on the web reading all sorts of stuff on fixed biased amps with tremolo bias wiggle, I have come to the conclusion that the Jansen 6/20 and 6/30 amps have an inherent design flaw which allows the tremolo circuit to interfere in a destructive way with the power valves' bias. In other words, biasing the power valves should be done in such a way that when the tremolo depth (or intensity) knob is on max, the plate currents must be within safe range... even when the tremolo is switched off.

For this particular amp I am fixing it means I need to modify the negative bias circuit so it can provide a higher negative voltage that what is currently available or I modify the tremolo circuit to allow for a reduced bias voltage swing.

TBC

Hi! Yes, this is a design issue and I’ve seen it on other bias-wiggle trem Jansens, although it often manifests while the trem is actually running if it runs long enough. I can’t remember what amp you’re talking about here but I’m guessing it has 6L6s. The max grid resistance rating for them in fixed bias mode specifies something like 100k. The grid resistors on Jansens are often 220k or 270k even, then that runs through the 500k trem depth control to ground, so the total resistance between the grid and ground can reach >700k, which is way higher than the rating. I guess grid current ‘builds up’ and the bias gets pulled down, causing over dissipation.

The solution is tricky but setting a colder bias (50%) should help to begin with. Then you can try 100k grid leak resistors. Then a 250k trem depth pot but that might weaken the trem oscillations too much, so it’s a last resort.

Thanks for that RA. Yes, this Jansen 6/20 has 6L6 power valves.

Looking at the 6V6 datasheets, it also specifically states that the grid leak resistor should not exceed 100kOhm for fixed biasing. A very popular vintage amp, let's call it Princeton Reverb, uses 6V6 power valves with 220 kOhm grid leak resistors too. Tremolo circuit very similar and injecting into fixed grid bias circuit. So this design flaw issue wouldn't be limited to Jansen only. (Some would say that Jansen just copied the Fender designs)
I guess these circuits/amps were factory biased relatively cold and very forgiving valves must have been used

This makes me wonder how many 'fixed grid bias wiggle amps' are out there running way too hot

For this amp, I am going to lower the plate voltage a bit first and then try 150 kOhm grid leak resistors. Then set the fixed bias to 50% MPD and hopefully that will still provide a good tremolo function without the latter causing it to go into red plate territory.

[RectifiedAmps]

Thanks for that RA. Yes, this Jansen 6/20 has 6L6 power valves.

Looking at the 6V6 datasheets, it also specifically states that the grid leak resistor should not exceed 100kOhm for fixed biasing. A very popular vintage amp, let's call it Princeton Reverb, uses 6V6 power valves with 220 kOhm grid leak resistors too. Tremolo circuit very similar and injecting into fixed grid bias circuit. So this design flaw issue wouldn't be limited to Jansen only. (Some would say that Jansen just copied the Fender designs)
I guess these circuits/amps were factory biased relatively cold and very forgiving valves must have been used

This makes me wonder how many 'fixed grid bias wiggle amps' are out there running way too hot

For this amp, I am going to lower the plate voltage a bit first and then try 150 kOhm grid leak resistors. Then set the fixed bias to 50% MPD and hopefully that will still provide a good tremolo function without the latter causing it to go into red plate territory.

6V6s (and EL84s) probably don’t suffer this issue as much since they draw less grid current than a 6L6 (or EL34). I’d be curious to see if Fender used bias wiggle on any of their 6L6 amps and, if they did, how they implemented it… will check some schematics.

Why are you lowering the plate voltage? The max plate voltage is 500v for a 6L6GC so I doubt it’d be contributing to the redplating. It might not be worth the effort.