nicknorman
Patron
-
Posts
21,880 -
Joined
-
Last visited
-
Days Won
119
Content Type
Profiles
Forums
Events
Gallery
Blogs
Store
Posts posted by nicknorman
-
-
12 minutes ago, magnetman said:
The main problem is alternators. In reality that is the only issue facing anyone. If you don't use an altenator to charge then drop in replacement means just that and the solar or mains chargers can be installed to suit the batteries.
Add an alternator, which is what a lot of people have as their primary charging device and all hell breaks loose.
True. However most boaters charge their batteries via an alternator at some point. And for many, it provides most or all of the charge.
-
10 hours ago, BoatinglifeupNorth said:
On the other hand it also has to be said that IanD has no experience with fitting out a boat with lithiums. He paid someone else a lot of money to do it for him. Although I can see why you might think otherwise.
-
1 hour ago, dmr said:
Thats a bit tenuous (hope I'm not starting another argument here). An equivalent circuit of a resistor could be a pure resistor in parallel with a voltage source, or sources (or in series with a current source) and these sources generate the noise, so the resistive part itself will still be truly ohmic.
Well yes but your “pure resistor” is an imaginary concept that doesn’t exist in reality. So ohms law is very good at predicting the behaviour of an imaginary construct that doesn’t exist in the universe. Very useful (not)! -
1 hour ago, dmr said:
Yes, this thread (argument) has got better, I think maybe 7/10 for you 😀
Can you say a bit more about the errors in Ohms Law? (or probably best not).
Yes. Apply some voltage to a resistor, what is the instantaneous current? You can’t work it out using ohms law because it varies. Shot noise. And thermal noise. So yes ohms law kind of works in an imprecise way at a cursory glance, but in a detailed way it doesn’t work.
Then there is quantum tunnelling.
-
I blame DMR. I was going to let it drop because there is no point in arguing with a narcissist, but then Dave came along and drew some parallel with Gibbo, so I felt morally obliged to continue.
-
11 minutes ago, IanD said:
Maybe that explains why you don't seem able to work out simple voltage drops and currents in connections and wires then... 😉
Here are two quotes; I'll leave it up to the (extremely bored by now...) reader to decide which is correct.
"Certainly the difference in cable sections (and hence resistance) between the battery 0v line (70mm^2) and the BMV data line (very thin) means that the dc current flowing through that thin wire, and thence through another thin wire between BMS and cell 0v, wont be much. But then again “not much” of 200A can still be a fair bit. But if you introduce some slightly corroded or bad connection in the 70mm^2 wire, you could end up with large currents flowing through the thin wires and much smoke and melting ensuing."
"BTW I went and looked up some actual numbers for you -- shielded data cables are recommended to be grounded at both ends so long as the voltage difference between the grounds is less than 1V rms (this is aimed at mains systems, to prevent ground loops), so they'll be perfectly happy with that and certainly not smoke or melt. If you have a 1V drop in a poor ground connection carrying 200A (5mohms -- your number not mine) then it might well burst into flames since it will dissipate 200W, but the shielded data cable (and the PCB it connects to) will still be perfectly happy, it might carry an amp or two of current down the shield -- and an unshielded one won't even notice. Numbers matter... 😉"
I expect this will trigger more insults/character assassination/diversion from you rather than doing what you accused me of *never* doing, which is admitting you were wrong... 😞
Have you ever thought of going into politics? You certainly have the prerequisite of a selective memory.
As I explained before, if the thin wire is uniform they you are correct. But it isn't. As I explained, the "thin wire" circuit is from the shunt to the BMV, from the BMV to the BMS, and from the BMS to the cell 0v. All of which are reasonably similar and adequate cables that won't melt. However within the BMS there would be (if I hadn't designed it out) a PCB track connecting the BMV and cell 0v wires. A thin PCB track which at first glance would not be required to carry any more current than the sub-mA current arising from the TTL level 232 data lines. So likely very thin and thus concentrating nearly all the circuit resistance, and hence nearly all the heat, in a very small area with virtually zero thermal mass or ability to disspate heat. And even if the fat connection did get very hot and melt a bit, that is easily fixed. Whereas internal damage to the BMS pcb would require a new BMS.
And then we have the problems that you are choosing to forget - a disconnection or near disconnection of the battery -ve which would keep services live but pass all the current through the alternative route and vapourise it. And the fact that the mV accuracy of the 0v BMS line would be compromised by even relatively small currents following the alternative path.
All of which comes back to my point that it is bad practice to design systems that have alternative and "unintended" current paths.
Also important to bear in mind that FMEA is only as good as the failure modes you think of. Building in weak points/bad design even though you can't immediately think of a scenario where it might cause a problem, is still bad design. If you are a good engineer, that is.
-
42 minutes ago, IanD said:
If you can't take sarcasm, don't dish it out.
I didn't invent Morse code, but unlike some I do at least seem able to apply Ohm's and Kirchoff's laws... 😉
Shock horror you didn't invent it? I am amazed. Anyway as we both know Ohm's and Kirchoff's laws have long been discredited for being inaccurate.
-
21 minutes ago, IanD said:
Two can play that game -- what's Morse code for "Melted any good CANbus cables recently"? 🙂
There is no morse code for inverted commas. Or a question mark. Or a slightly smiley emoji. Nor is there any distinguishment between lower case and upper case. In fact do you know ANYTHING about morse code?
Apart from the fact that you invented it, obviously.
-
1
-
-
9 minutes ago, peterboat said:
Actually lots of modern diesels have throttles now, quite why I have not bothered to find out, but I did a 3 litre cambelt last week and the butterfly was there. Perhaps its something to do with EGR or DPF regeneration, or performance? Who knows
Lots of NOx from diesels which is why they have EGRs
Yes this is true, and not just modern diesels. But not the sort of diesels found on narrowboats.
I just asked an AI chatbot why. This is the answer:
- Modern diesel engines may still feature throttle bodies, primarily for emissions control and Exhaust Gas Recirculation (EGR).
- The throttle body’s butterfly valve can be controlled by the ECU (Electronic Control Unit) or a solenoid-controlled vacuum line.
- Under low engine load conditions, the ECU restricts the amount of fresh air (from the turbocharger) entering the intake manifold. This creates a pressure differential, aiding the EGR system by allowing more exhaust gas to be recirculated.
- During engine shutdown, the throttle body acts as an Anti-Shudder Valve (ASV), ensuring a smoother shutdown.
I also asked it why some BMW petrol engines don't have a throttle valve. This was the answer (quite useful these AI things!)
Certainly! Some BMW petrol engines are designed without a traditional throttle valve, and here’s why:
-
Valvetronic Technology:
- BMW employs an innovative system called Valvetronic in certain petrol engines.
- Unlike conventional throttle bodies, Valvetronic eliminates the need for a butterfly throttle valve.
- Instead, it electronically adjusts both the lift and timing of the intake valves.
-
How Valvetronic Works:
- When you press the gas pedal in a Valvetronic-equipped BMW, you’re altering how much the intake valves open.
- The Valvetronic system varies valve lift instantly, allowing precise control over engine breathing.
- By eliminating the traditional throttle valve, BMW reduces pumping losses.
- Pumping losses occur when the throttle restricts airflow during partial load conditions, wasting energy.
-
Benefits of Valvetronic:
- Improved fuel efficiency: Valvetronic optimizes air intake without relying on a throttle plate.
- Enhanced power delivery: The system adjusts valve lift dynamically based on driver demand.
- Drive-by-wire throttle action: Valvetronic operates electronically, providing a seamless response.
-
Production and Impact:
- Valvetronic-equipped engines are manufactured at BMW’s Hams Hall plant in England.
- These engines enhance performance, reduce emissions, and contribute to BMW’s reputation for innovation.
-
1 minute ago, cheesegas said:
Also worth noting that because of this, there's a lot more carbon monoxide in petrol exhaust compared to diesels - at low throttle/low load, I seem to remember reading it's something like 50-100% more. All the more reason to run a petrol genny off the boat and downwind!
Yes. Certainly at idle I would have thought a diesel produced virtually no CO. Although 100% more is only twice as much, I would have thought it was much more.
-
21 minutes ago, magnetman said:
I would have thought a petrol engine of the same displacement would shift more air as it will tend to have a higher rpm.
No, massive difference between a petrol and diesel engine at low power/idle. The petrol engine has the throttle closed, this severely restricts both airflow and fuel - the throttle is typically a butterfly valve that is closed at idle. Very little airflow. This is because the mixture must remain within very close tolerances, so small fuel flow = small air flow.
The diesel engine “throttle” only controls fuel flow. There is no restriction on the air inlet. A diesel doesn’t need or want a stochiometric mixture. So a 2 litre diesel shifts 2 litres of air every 2 revolutions at idle (roughly).
A 2 litre petrol engine at idle shifts a tiny fraction of 2 litres of air every 2 rotations.
-
1
-
-
13 minutes ago, dmr said:
The engine room can get surprisingly hot in summer, especially if working the engine hard on a river. I think we have hit 40 degrees once or twice though this will be on rainy days when we can't open the sides. This can be quite an issue with proper engine rooms as we sleep in the back cabin and if we boat late into the evening its just too hot for sleeping, though lovely in winter. A couple of fans aimed at the engine is effective (once the engine has stopped). How hot does it get in "an under the deck" engine 'oil?
This is another reason to get the Zeus with temperature control, better than setting a current limit and assuming the temperature.
A long while ago Iskra said a winding temperature of 120 degrees was ok but I would not be too happy with that. I suspect that our alternator is just a smaller version of yours, but in our case dog hairs blocking up the airways is a significant issue.
It doesn’t seem to get that hot in the under deck (actually very small under boards compartment of the “modern trad” stern. I think because there are large areas of uninsulated steel in contact with the cut, and when the engine sucks air into the inlet, new air comes in from outside. Being a diesel there is a lot of air going through the engine even at low power. So there is a kind of “forced ventilation”. Still, I suspect it gets to 40C in summer. -
1 hour ago, dmr said:
Without major engineering (machine shop stuff) I am stuck with a single V belt and am running a bigger pulley than is ideal in order to control belt slip.
Once I have the option to limit current/field drive I can hopefully go to a smaller pulley to get a bit more cooling, and then do a temperature limit. I am hoping to get a continuous output of about 70 amps. Setting the maximum temperature will be a seat of the pants sort of thing.
In a previous post you did question whether Bluetooth real time monitoring and control was really essential and this is a case where it will be very useful.
Another topic for another day is the option of using external rectifier diodes to get a bitmore ouput without overheating.
I think 70% of maximum is a reasonable target. My Iskra is dual fan (one at each end) and I can run it at around 125A/175A ie 71%, that with a limiting cooling air exit temperature of 90C which is fairly conservative bearing in mind the alternator spec says max AMBIENT temperature of 110C
23 minutes ago, IanD said:Have you also considered an external cooling fan/ducting to blow cold air into the alternator?
He has a "proper" engine room so alternator inlet temperature will be close to ambient with the doors open. Just a moment whilst I convert that to morse code...
-
19 minutes ago, dmr said:
Anyway phase 1 of this project is to get a Zeus working with the current 12 volt Trojan bank and see how many amps I can squeeze out of the 100 amp alternator.
This will depend entirely on how hot you want to run the alternator!
-
14 minutes ago, dmr said:
I disabled the regulator in my 100amp Iskra recently and it was a right pain, quite thick pins and not enough clearance to get in with any of my snips so a slow and fiddly dremmel job.
My comment on open sourcing your design was a bit light hearted. There are several electronic engineers on this forum so we could have done a good job, but the Arco Zeus is close enough to what is needed so much less justification for a DIY alternative (and if we value our time even at half minimum wage it would still cost more than £850).
Something like an alternative to the Victron Gerbo/GX might be a good open source project as it would be good to have a bit more flexibility than Victron provide.
Current plan is to get the Zeus, maybe later this week, get it going with the Trojans then get a Lithium. The battery box does not fit any off the shelf lithiums too well so its either a lot of wasted space or making my own from cells.
Making up for the lost weight of the Trojans will be an issue. 😀
Phase two will be to replace the Travel Power with a big inverter and second alternator with its own battery bank but can't decide between 24 or 48 volts. I suspect things might change quite a bit in the next year or two so will delay on this unless the TravelPower fails.
I will be really interesting to hear how you get on with the Zeus. It certainly looks a good product, although possibly a somewhat immature one. One of those products that has been taken to the market before all the intended features are actually functional. Seems to be the way of things these days!
Definitely an issue with the weight lost, we had to get a couple of 28lb weights to replace the Trojans, even though we went up from 450Ah to 600Ah
You could of course just get cells like I did, and add a cots BMS. At least that allows you to locate the cells in the existing space (and in our case, the 600 Ah Li had a smaller footprint than the 450 Ah Trojans, although they were taller). I used https://blslifepo4battery.com/ without any issues, pleased with the product and price although that was a couple of years ago. And has the advantage that you have direct access to the BMS and its configuration.
-
23 minutes ago, dmr said:
A good idea but that "just" is a bit of an over-simplification. You will have to mess about with the innards of the alternator to break the field circuit and bring wires from both sides of the break out of the alternator, so a fair bit more difficult than the usual Adverc type mod (difficulty depends on design of alternator/regulator).
Maybe its time for you to update and open-source your regulator design to compete with the Zeus? 😀
Many years ago a mate of mine moved the power transistors from his hifi out of the enclosure on longish wires and had each one sat in a saucer of water.
The "just" also applies to the expensive Wakespeed, Zeus, Alpha Pro etc in that you need to disconnect the existing regulator and access the brushes directly. Much the same amount of work, and although I would agree it is not an entirely trivial thing, someone with reasonable mechanical and electrical competence should be able to do it. I did! The advantage over the above alternator controllers is that it is a massively cheaper solution! You could of course also add a switch into the field circuit to "disable" the alternator gracefully once the Li was charged.
I am always happy to share my alternator controller design but one problem is that it was designed to be integral to a system, not stand alone. It currenly looks at individual cell voltages and battery temperature (which it gets from the custom BMS), and battery current and SoC (from BMV712) to control charging, as well as being aware if the BMS is about to emergency disconnect the battery. The software could be re-written to be blind to all that but then there is the risk that a drop-in BMS would decide to disconnect the battery with the alternator controller being unaware until it detects a rapid rise in system voltage.
-
1
-
-
34 minutes ago, magnetman said:
LTO batteries are interesting
I am also intrigued about the suggestion of using resistors and heatsinks to alter the voltage and current out of the alternator. It seems that if done nice and tidy this could be a better solution than the iece of wire .
Putting the resistor in a water heating system seems interesting even if it is not going to be much power .
Yes just add a resistor into the field circuit. Around 4.25A maximum current at 14v seems fairly typical for a boat alternator field current, ie a field resistance of 3.3ohms. To limit the current to 2.5A (alternator limited to 60% of maximum output) you would need to increase the resistance to 5.6 ohm, ie add 2.2 ohm resistor. 2.2 ohms at 2.5A will dissipate ~14 watts. You could use a 25w resistor but I would choose a 50w wirewound chassis mount one, and it would need to be on a heatsink/metal plate because it would get extremely hot even at 14watts if not so mounted. I've been saying this for years, but I don't think anyone has ever tried it.
-
2
-
-
10 hours ago, IanD said:
<sigh> exactly the response I predicted... 😞
Apart from personal abuse and insults, do you have anything useful to contribute to the subject of the thread?
I suppose I could continue to repeat myself, but what would be the point? Your interpreter algorithm is malfunctioning. Maybe you should stick this into your OS, being binary your parser might understand it more easily:01000001 01110110 01101111 01101001 01100100 01101001 01101110 01100111 00100000 01100001 01101100 01110100 01100101 01110010 01101110 01100001 01110100 01101001 01110110 01100101 00100000 01100111 01110010 01101111 01110101 01101110 01100100 00100000 01110000 01100001 01110100 01101000 01110011 00100000 01101001 01110011 00100000 01100001 00100000 01100111 01101111 01101111 01100100 00100000 01110100 01101000 01101001 01101110 01100111 00101110
-
1 minute ago, magnetman said:
What happens if there is a large unexpectedly large loaf on the battery and the switch gets welded closed by high currents?
Well at least you will be able to have a nice luncheon. Or several in fact. -
Generally the advice from here for disconnecting a battery, is to disconnect the negative first. This is because if you touch the hull with the spanner, it doesn't matter. If you disconnect the positive first and touch the hull, you have a molten spanner. Once the negative is disconnected you can remove the postive connection and if the spanner touches the hull, nothing happens.
5 hours ago, IanD said:I do get it, because it's obvious -- in spite of your repeated sniping to assert your superiority, you're not the only one who understands basic electrical principles -- or even advanced ones. If you want a ground noise/shielding/screening/current loop challenge you should try dealing with having to get 1000A from an SMPS into a massive switch/router chip with a few millivolts of voltage drop, all sitting right next to sensitive analogue circuits with 100fs of jitter and 50GHz bandwidth.
[now I expect you'll come back and accuse me of bragging -- trust me, if I wanted to do that there's a load more stuff I could chuck out, but you're the one who started the "I know better than you" p*ssing-up-the-wall contest]
You really should write a book. After all, you have designed almost everything from the entire Apollo moon landing software (which lets face it was pretty simple!) to the latest AI systems that can recognise a face from orbit. And everything in between. It would be fascinating, although rather long.
Although I do curse you when I find that on my iPhone the ringer volume and the alarm volume are inseparable. What were you thinking of when you designed that bit?
5 hours ago, IanD said:But all this is not what you said earlier, is it? With no ground connection through any data cables, there's no risk of them or the PCB tracks they connect to smoking and melting, is there? And even if there was a ground connection, a poor high-resistance high-current connection is extremely unlikely to result in enough voltage drop or current to damage the "thin wire", isn't it? All of which is what you said, and all of which is wrong, as Georg Ohm and Gustav Kirchoff would be well aware 🙂
This is exactly what I said earlier. To paraphrase "just as well I decided not to have any ground connections through any data cables as there would be a risk of harm to them or the PCB tracks (or the BMS accuracy) if I had done."
Having a ground connection would be the default, not having a ground connection was the result of considering the alternative current paths issue. This is the incredibly basic point of logic that you don't seem to get. Perhaps you are a badly trained AI after all?
By your logic, I avoided a problem with alternative ground paths by not having an alternative ground connection, therefore the potential issue of alternative ground connections doesn't exist. Ever. At all.
Does not compute. Back to the training data for you! Oh and forget the ad hominem attack thing, that only applies to humans.
-
26 minutes ago, IanD said:
I'm not getting excited, just tired of you evading questions you don't want to answer, misrepresenting what you said, and pretending things can happen when they can't... 🙂
I'm not ignoring what you're saying, the numbers simply don't add up given the likely maximum voltage drop across a poor high-current ground connection (a few hundred mV) without it destroying itself -- this is the maximum voltage driving ground currents in any other cable or connection. Due to series resistance (thin wires, remember) the current this would cause down any CANbus or similar cable with a ground connection will be small, certainly not enough to damage it. And then you tell me that these cables don't have a shield/ground connection anyway, which means that no current will flow at all -- the data lines are high impedance at DC so there will be no current in any PCB tracks.
If you disconnect a battery negative and try and power the entire boat through a thin wire -- in effect, putting 12V across it -- then undoubtedly something will go phut. Though how this can happen in a CANbus cable without a ground connection beats me -- so please do explain... 🙂
You haven't been following the topic very well, have you. I started the issue talking about the VE.Direct connection. Maybe you don't know what that is? It is a 3.3v TTL level RS232 duplex connection between the BMV 712 battery monitor and something else, in this case my BMS. That cable, being single ended data, quite long and fairly low voltages, is screened with the screen acting as the 0v line. So there would be a direct ground connection to the BMS had I not decided to go for an optoisolator at the interface with the BMS.
Then I went on to mention the CANBUS and how I had decided not to connect the ground at all because it wasn't necessary and would again create an alternative ground current path.
You have focussed on the CANBUS not having a ground path because I decided not to connect it. Congratulations, you remembered that bit! But I don't think you see the point. Neither does the VE.Direct have a ground connection, thanks to the way it is designed. Otherwise known as having an isolated ground in each case. Which was why I mentioned it by way of illustration - sometimes having an isolated ground is necessary even on a narrowboat. Do you get it now? (probably not).
-
3 hours ago, IanD said:
No, it's perfectly rational -- I can be wrong about one thing (e.g. CANbus shielding), you can be wrong about another (e.g. CANbus melting).
Still playing the ad hominem card, I see?
I notice you're carefully avoiding mentioning your scaremongering posts about melting thin comms cable wires with massive currents through them due to huge ground voltage differences, perhaps because you've now realised they were just plain wrong -- the differences can't be bigger than a few hundred millivolts without melting the high-current connection, even if this happened the currents through the CANbus ground connection would be small and non-damaging -- and since you say that they don't have a ground connection anyway, no current would flow at all 🙂
Care to own up to being wrong on this? If not, your accusations of me refusing to admit I'm wrong (and ad hominem snipes) are exposed for what they are -- projection of your own behaviour.
Which in case you don't know, is what Donald Trump does -- accuses other people of doing things (e.g. lying, namecalling, cheating) that he does himself, because he can't believe that other people wouldn't be as mendacious as he is.
P.S. As pointed out by another poster, you seem determined to turn this into a personal vendetta about irrelevancies rather than return to the subject -- which was how to charge a 12V LFP from a12V LA/alternator, in case you've forgotten...
You are getting quite excited! Maybe a lie down in a dark room?
As I have repeatedly said and you repeatedly ignored (so I really have no idea why I’m bothering) when there are alternative ground paths this can lead to problems. In the case of current divided between two alternative paths, one beefy, one weedy, the current is of course divided in proportion to the resistances of the two paths. So if the resistance of the beefy path increases, the current in the weedy part increases. The beefy part generates heat, the weedy part generates heat. The excess temperature reached depends on the ability to dissipate that heat and the rate of temperature change depends on the thermal mass. When there are varying resistances along the weedy path, the generation of heat will vary accordingly. So if you consider let’s say a 1mm^2 conductor from the BMV to the BMS, and a 1mm^2 conductor from BMS to battery negative you might think there is even heat dissipation along the route. But somewhere inside the BMS linking the two conductors there is a short and very thin PCB track - after all, the designer consider it a “signal wire” and knows that the return current from the data lines is miniscule. So now we have most of the circuit resistance (most of the generated heat) confined to a very small pcb track with very poor ability to dissipate heat.
But as I also said, the main issue is when there is a disconnect in the beefy battery negative line. Maybe someone decided to change the batteries - “disconnect the negative first” someone once told them. They would expect this to de-power the domestic electrics, but instead all the current is now routing through the thin wire. Disaster waiting to happen.
Anyway, I’ve got to go now, I am just putting together my bid for President of USA.
-
43 minutes ago, dmr said:
I think you both need to look back at some old threads and study the Gibbo arguments, they were really good, facts and insults are fine but where is the entertainment factor? 😀
I had to isolate between my laptop and the speakers as they run on different 12 volt circuits and so have slightly different and noisy ground levels. I started off with an audio transformer but now do it with an optical cable. I could use Bluetooth but I like wires.
The thing with Gibbo was that he was actually wrong about quite a lot of stuff, but he said what he said with such dogmatism, repetitiveness and conviction (DRC) that the forumerati believed it all as gospel and he created a whole new post-truth. IanD still has some way to go in the DRC stakes, although it has to be said he is trying hard. Or maybe just trying?
1 hour ago, IanD said:As always I've even offered straight out to own up to being wrong if you do, which kind of blows a hole in your argument, doesn't it?
That is irrational as we can't both be wrong.
-
Bored with pointless arguing with someone who is not capable of ever being even slightly wrong.
-
2
-
Lithium Batteries installation
in Boat Equipment
Posted
Groundhog day.