I've seen testing where oil caps did marvelously well in terms of passing a signal with minimal degradation. Don't ask me what brands they were, as the brands weren't mentioned. Having said that, many find oil caps to be soft, warm and musical sounding. It is possible that they sound less "accurate" because many folks that grew up listening to lower grade SS gear were used to listening to non-linear distortions, which resulted in high end emphasis or "false detail".
As to why SS gear is typically rated for higher power levels than tube based designs, it has to do with current capacity. SS gear can typically pass a LOT more current. Since wattage equals voltage multiplied by the current in the circuit, greater current capacity with the same voltage will result in more total power output. Too much current will typically "blow" a tube faster than it will a transistor. Whereas tubes "open up" and fail, a transistor can blow a few junctions and still keep operating. It might not work as well as it used to under extreme conditions, but it is still working. As such, tubes are typically more fragile and either "work" or "don't work" acceptably. This is especially true of power output tubes in amplifiers. Sean
> |
Sean is correct, but remember that many speakers produce their best sound by way of voltage, not wattage. Soundlab is a perfect example.
The ultra high rail voltages of tube amps will typically drive this load better than transistors.
For example, some SET Tube amps rated as low as 20 watts run 1,000 volt (or higher) rail voltage and therefore can swing enough drive the big Soundlabs to near 90 DB SPL.
No 20 watt transistor amp I am aware of would work on big Soundlabs. In addition, transistors hate big impedances in bass, reducing power to a fraction of it's textbook rating. Some tube amps actually produce MORE power at 30 ohms than 8 ohms.
In other words, the answer is not always easy to determine by numbers or text. As always, listening is the most important test you can make. |
Albert, I'm not sure whether you were being facetious or not? You actually gave a pretty good argument for using the numbers or text. |
Point I was making was, published specifications don't tell us the whole story. Many people assume that the quality, power and sound of an amplifier may be determined by what the manufacturer puts into print.
I admit that some statistics are laughable, but that is not what I was referring to.
I encourage people to think about the variables effecting end results. Even specifications not discussed in literature. That's why a personal audition of the gear is so important. |
I don't really agree with the assumption that SS amps are 'typically' rated for higher output power (wattage) than tube amps. Yes, transistors are physically smaller than tubes, and SS amps don't require output transformers, so SS amps can often carry higher output power ratings for a given chassis size or weight. But even this construct breaks down when considering many of the top SS amps, which because they generally require more power supply capacitance and of course heat-sinking than comparably-powerful tube amps (especially as the operational bias class creeps upward), tend to feature some pretty behemoth dimensions and masses for their rated power.
Both SS and tubed amps rated for hundreds of watts of output power can be bought. Maybe the question could be better phrased, Why are there seemingly fewer lower-powered SS designs than lower-powered tube designs? Tube fans may answer, because SS amps don't approach clipping as gracefully and therefore require higher power margins to avoid unpleasantness. Hence the nostrum that tube amps can seem to 'play' about doubly powerful compared to similarly-rated SS amps. I personally don't think that this is literally true, and that power supply robustness for rated output power ultimately has more to do with the subjective sonic result - as far as rated power levels go - than does the type of output devices employed (but also that although gross tube clipping is really no more pleasant in this context than is transistor clipping, it is usually less potentially damaging to speakers when it happens).
Mostly, it just seems that in the present market manufacturers have simply moved away from lower-powered SS amps, which many did used to make, but which now apparently fail to sell well enough (with the possible exception of integrateds) to continue justifying their production. (Some of this could have a lot to do with the HT boom.) Modestly-powered tube amps, on the other hand, apparently do still sell well (and not just single-digit SET's either). Anyway, it would usually be a mistake to focus too much on rated output power when comparing amps of different types (provided none are truly underpowered for the given speakers, room, and listener). In my own experience, I have owned a tube amp rated at less than half the output power (and twice the price, to be fair) of a SS amp it replaced and vastly preferred the former, even at higher volumes (in a smallish room).
Sean: Are you implying that some PIO or FIO caps might measure better than some audiophile-grade plastic-film types? Do you have any modding or listening experience yourself that makes you tend to lean toward one or the other for certain applications? |
Oil caps are one of the original types of capacitors - usually using paper wound with foil, bathed in an oil dielectric. Often in a rectangular, oval, or round can with two terminals on one end. There are modern day equivalents, Jensen makes some nice ones (copper foil in oil, etc.), as does others (for even more money, e.g. Audio Note silver foil in oil....). Usually vintage caps are referred to as PIO. (paper in oil or sometimes poly in oil). They work great and are often used as filter caps in a tube amp power supply (probably their best application). Also good in crossovers, and sometimes as coupling caps between (tube) amp stages. Fairly easy to find the old ones, commonly they are available from 200v - 1000v ratings, sometimes higher. Usually values range from 1uf to 20uf but sometimes as high as 40 or 100uf for more modern ones. Modern applications include motor run caps (for DC electric motors).
-Ed |
>>Whereas tubes "open up" and fail, a transistor can blow a >>few junctions and still keep operating. It might not work >>as well as it used to under extreme conditions, but it is >>still working.
This is TOTALLY wrong!! A transistor will never work even if A junction is blown!! In fact, many times transistors do not work even when a junction is not blown owing to materials impurities or if they are not thermally annealed correctly. This is TREMENDOUS amount of misinformation! Please do not do this dis-service to other members of this forum by plying them with wrong info! You have answered many, many other threads with very good info but this content in your post is far from the truth & you appear to be quite mis-informed.
Au contrare, a vacuum tube has a higher possiblity of working if it fails vs. a silicon transistor. It is a well-known fact that tubes "die" gracefully whereas silicon transistors are a 0/1 deal. In Engineering school we are taught this in Electronics 101.
>>As such, tubes are typically more fragile and >>either "work" or "don't work" acceptably.
This again a MYTH! Totally incorrect. Vacuum tubes are very hardy devices & can withstand very high voltages (as clearly mentioned by Albert Porter in his post). For eg. I was listening to an ASL 50W/ch mono block @ a dealer's store & this amp used an 845 tube. This is a radio broadcasting type tube & the grid is biased at 1500V! There is no transistor I know used in audio applications that gets biasesd this way. Tubes can take quite a beating & still reproduce sound thru them. They might not perform to their best ability (highs rolled off &/or wooly bass) but they will pass sound thru them. A silicon transistor would be long dead (smoked!) by this time. Only a catastrophic failure in the tube such as a disconnected terminal or blown grids/cathode/anode would cause a tube to fail completely.
We audiophiles are so nit-picky about our tubed gear that we have assumed that the vacuum tube is a fragile component. The vacuum tube pins are delicate & care needs to be taken while inserting the tube in its socket & yes, you can break it if you drop it on a hard surface & you could squish it if you apply too much pressure while inserting it but that does not make a vacuum tube fragile! These days not much is taught about tubes in Engineering school & so I think a lot of people are ignorant about it & assume it to be fragile.
Sorry to be so hard on you but I hope that you'll see my point & take it in the right spirit.
I agree with the oil caps explanation & why ss power amp gear is usually rated @ higher wattage for the same size chassis & relative cost. To expand this pt. further: miniaturization of silicon devices (better silicon process created by the fabs) has allowed us to put higher wattage BJTs & MOSFETs into smaller & smaller packages. Also, packaging of silicon devices has come a long, long way in the last 20 yrs thus these packages are very good at dissipating heat generated in the ss output stages. Thus, we can pack it in i.e. insert more & more of these high current carrying devices into reasonably sized chassis. The result is very high wattage ss power amps.
As hinted by Albert Porter, vacuum tubes are voltage output devices i.e. they are very good at providing a voltage swing but provide a very poor amount of current. Also, to get a vacuum tube to work with low impedances (such as a loudspeaker) one needs an impedance transformation i.e. an output transformer. You'll notice that the output xformer is huge. This is not only to provide an impedance xlation from but also to ensure that the current flow is un-impeded. There is a physical limitation of how large this xformer can become. Thus, output wattage of vacuum tube power amps gets limited. There is 1 practical way around this - the OTL amp. However, to get reasonable Watts out of it, one needs a large # of tubes (eg. Atma-sphere OTL amps) & they become space heaters (as a 2ndary function).
Hope that this helps some. |
Although Sean's post raised my eyebrows too, I think it's pretty academic to focus on how a device might theoretically continue to operate to some degree when it's damaged or broken, when obviously if it doesn't sound right we're going to want to repair or replace it ASAP.
Though I'm certainly no engineer, I think many of us realize that yes, vacuum tubes can be more robust than transistors under certain unusual conditions having little-to-nothing to do with home audio (some kinds of radiation exposure, thermal stress, higher voltages), and yes, they can be made to last a pretty long time under relatively harsh conditions where transistors are at a disadvantage (in radio transmitters, microwave magnetrons).
But when it comes to home audio, I think all we tube lovers can admit that our vacuum devices will be much more likely to fail, and anyway need a hell of a lot sooner replacement, than silicon semiconductors. In fact, tubes will audibly degrade over their useful lifetime to a much greater degree than transistors. And the ways they usually fail prematurely, such as losing their vacuum, blowing like an incandescent light bulb, or getting intolerably noisy in one way or another, are going to cause us to replace them, not marvel at how they might still be able to function a little bit. (But I would think the same goes for a failing transistor - I've just never had one go bad yet). In addition, tubes are generally more sensitive to some stuff that does find its way into the audio environment, like vibration and accidental impact.
Anyway, I've never thought "graceful" when one of my tubes died, except to the extent that it didn't take out anything around it, knock on wood (and once it did). But regardless, this whole debate is irrelevent to the question asked, and I'm not quite sure why Sean brought it up in the first place, unless he meant to imply that amps using large numbers of output tubes to develop higher powers would entail discouragingly high retubing costs... |
Bombaywalla: I have pulled apart dozens of high current RF transistors and found blown junctions in them. All of these were still working albeit at reduced output due to the loss of internal conductors.
Many transistors use several junctions in parallel to handle the current levels needed, so blowing a few simply reduces the gain and max current potential. In effect, they have compacted several transistors into one case and they are all working together to share the load. Blowing one of the internal junctions inside of a transistor is no different than running a dozen external transistors in parallel. One, two or three might fail, but the rest of the circuit will continue to work at reduced capacity. That is, so long as the transistors that failed blew open and not shorted. If the transistors are running in matched push-pull pairs, noticeable distortion may occur, but the circuit can be made to work again by simply deleting the the mate to the transistors that went south. Once again, it will not be as powerful, but it will work and should maintain a reasonable semblance of linearity.
As far as tubes go, they are in a continual state of decline once they are fired up. While most experience a very slow and gradual death, it is more likely for a tube to "pop" at random than for a transistor just to up and let loose. On top of this, it is not uncommon for a piece of equipment to experience major damage when a tube lets go. If you doubt this, try searching the archives here pertaining to tube failure and start reading about the fires that have resulted.
Other than that, i agree with everything that Albert had to say. High rail voltages are a must if you want realism. Then again, you have to have enough current to maintain that level of voltage when under load or the rails will sag. As such, unless you have a speaker that is of noticeably higher than average impedance across the band, at least a reasonable amount of current will be required from the output section in order to maintain linearity, dynamic headroom and a solid soundstage. As the voltage sags under load, so does the impact and spatial characteristics. Sean
> |
Both solid state and tube amps produce a voltage. Current is what results when voltage is applied to a load, such as a loudspeaker. An amplifier might be capable of high voltage output under no load condition, but if it has little current delivery capability this voltage cannot be maintained into a load. Your preamp typically can output a signal of several volts, enough to play a speaker quite loudly, however if you hook it up to a speaker I doubt you would hear anything. The preamp can only deliver enough current to maintain the voltage into a load of several tens of thousands of ohms, not 4 or 8 ohms.
Tube amps have high "rail" voltage (plus and minus 400 volts or more) so that the output tubes can apply a high voltage to the primary winding of the output transformer. The output tubes cannot deliver a great deal of current. However, the output transformer is wound with a step-down turns ratio, so that the secondary output voltage is down to a handfull of volts, as appropriate for the speaker, but the necessary current capability is there. You might think of the output transformer as similar to the gearbox of a sports car, which permits a small engine reved up to 7000rpm, to accelerate the car from a standing start. |
Correction in order here bomby:
"845 tube. This is a radio broadcasting type tube & the grid is biased at 1500V! "
No, sorry - not correct. max PLATE voltage on 845 is 1250v, and ASL doesnt' run them that hard. They would not bias the grid higher than the plate(!) and infact the grid is going to have about 70-80v of negative voltage applied, to run them in class A1.
And let's stop talking about 'rail' voltage w.r.t. tube amps - it's called B+. Rails apply to sand amps.
Eldartford makes a good point I was going to mention - B+ on tube amp is somewhat irrelavent in any case, since it's almost always going to go out through an OT, which has a massive step down ratio. (5000 : 8 or more)
The only situation which B+ would be used to drive speakers directly would be a high voltage transmitting tube output connected directly to the panel of an electrostatic loudspeaker. There were a few commercial attempts at this I think, none sold today that I know of. It's an idea which has a lot of merit but unfortunately is rather difficult to implement well, or at all. There are some more worthwhile and successful attempts being made by the DIY tube crowd, but that doesnt' apply to commercially available designs. Most of the time you would need a bigger tube that even 845 to do it as a SET amp (the only way it would be worth doing), meaning either a tube like a 212 or 849 or maybe 250/450TL, or else a more modern planar triode ala Eimac or Svet ceramic types possibly. (talking 1500-3500+v on the plate of those tubes)
-Ed |
Thanks for all the wonderful response. It was a pleasure to read them all. This will definitely help me understand my new Cary tube preamp and also help me when deciding on a new amp and weather to go SS or Tube when the time comes. |
Thanks for the correction Ed_sawyer. My bad for quoting the dealer without double-checking the info he gave me. |
Bombaywalla, how did the ASL sound? |
Brooks1, The sound was exemplary, if I may say so! The sound was very transparent, plenty of high freq. & low freq extension & since I was listening to single-driver speakers (Cain & Cain Single BEN & Carolina Audio JTM) the sound was so very coherent i.e. music had very good timing! With the ASL SETs, the midrange was additionally magical. If you have the inclination, I did write a lengthy report on my ASL/single-driver experience. It's long, so have been warned! :-) http://forum.audiogon.com/cgi-bin/fr.pl?cspkr&1072830036&read&keyw&zzsingle=driver=speakers |
They smooth out the sound (more refined sound). Given more details and seperation, music notes have more decay and body. |
I will look up your report Bombawalla. Thanks Nguyenchiro. |
