1. Attachments are working again! Check out this thread for more details and to report any other bugs.

I'm scared. Post-reconditioning the HVB overcharged and warbled.

Discussion in 'Gen 3 Prius Technical Discussion' started by articulite, Feb 2, 2023.

  1. articulite

    articulite Junior Member

    Joined:
    Jul 5, 2020
    33
    5
    4
    Location:
    Honolulu
    Vehicle:
    Other Electric Vehicle
    Model:
    N/A
    Good catch RE: outliers.

    I do have bad modules and weak modules.

    To be clear, I'm only pack charging and module discharging, as of now.

    If the recommendation is to test the discharger (it only discharges) on bad or weak modules first, I can do that.

    Though it would be ideal if there is a recommended max discharge rate for a module in a pack down to 6V. Or even 6.3V.

    My goal is to measure capacity, even if it's not entirely accurate, in a safe but fast way. I'm looking for data to inform pairing modules.

    I'll keep digging through the forum and online for consensus.

    If it helps to make this less confusing, let's separate the capacity testing process of 1 prolong charge & 1 (2A/3A/5A/8A/10A) discharge per module from a 3 cycle reconditioning process.

    If this new process for capacity testing works (for the purpose of pairing modules in an otherwise healthy pack), and is fast, and is safe, it could be valuable information for future readers and I'll make a new thread documenting it clearly.

    Edit: PriusCamper discharges with a 50w 12V halogen, down to what appears as low as 1V. That's ~4.2A. Sometimes they add a 20w bulb to the mix for a total of 5.84A. "which is super fast when modules are at full charge but potentially damaging below 5v"

    I'm just going down to 6V or 6.3V if I want to be extra safe. Yes, I know that the capacity measurement going down to 6.3V will be less than actual. My thinking is that I'll still get a good enough idea of which modules to pair. Better than having no data at all and pairing them haphazardly. Some modules, I would think, even then, would show higher capacities, with some showing lower.
     
    #21 articulite, Feb 7, 2023
    Last edited: Feb 7, 2023
  2. Grit

    Grit Senior Member

    Joined:
    Aug 22, 2017
    6,103
    4,032
    1
    Location:
    Wilkes Land
    Vehicle:
    2012 Prius
    Model:
    Four
    This is one hell of a big boss before the wack o mole stage.
     
  3. vvillovv

    vvillovv Senior Member

    Joined:
    Mar 19, 2013
    3,493
    1,231
    1
    Location:
    NY
    Vehicle:
    2017 Prius Prime
    Model:
    Prime Plus
    with only one module of a pair showing bad I agree, but whats described in a thread is not always the whole story.

    The pack looks good in the screen shot. Is good good enough or does it need to be better? I gave my opinion, if for nothing else, to get a baseline in the car and another screenshot. One attachment does not the whole story tell even with essential supporting data, of when DrPrius screenshot(s) were taken, car was, at idle, under load, how much load, etc etc etc....
     
    #23 vvillovv, Feb 7, 2023
    Last edited: Feb 8, 2023
  4. articulite

    articulite Junior Member

    Joined:
    Jul 5, 2020
    33
    5
    4
    Location:
    Honolulu
    Vehicle:
    Other Electric Vehicle
    Model:
    N/A
    Half the pack is ebay modules at this point. I have no insight into the capacity of any of the modules as I bought the car used with a dead pack. I have 11 spares in condition ranging from poor to weak but potentially ok after reconditioning.

    So I know (or at lease think I know) this much: the blocks aren't paired and failures are likely happening from poor pairing. I'm trying to address this and gather data. Most people are fine chucking a module in, and I could do that too as I've done before, but where's the challenge in that? :D

    Do I have a few 3400mAh modules in there? Are they all 3xxxmAh? I'd like to know ballpark where I stand, because no amount of ebay modules will help the situation if I just keep making bad pairs.

    Ideally, I can target 5500mAh across all the blocks. Identify which modules need more attention, more cycles, deeper cycles individually on the side to get them into parity.

    But it could also be as simple of an optimization as knowing which modules to pair from the current pack, swapping only the bad module in block 5. No more reconditioning, for now, because I can get a smaller spread on the blocks with proper pairing.
     
    #24 articulite, Feb 7, 2023
    Last edited: Feb 7, 2023
    vvillovv likes this.
  5. articulite

    articulite Junior Member

    Joined:
    Jul 5, 2020
    33
    5
    4
    Location:
    Honolulu
    Vehicle:
    Other Electric Vehicle
    Model:
    N/A
    Are you inferring that there is no benefit to having blocks with the same capacity in a pack? I was under the impression that this could extend the time between whack a mole events. And that a large part of why whack a mole events happen is because this intelligent pairing isn't taking place.
     
  6. vvillovv

    vvillovv Senior Member

    Joined:
    Mar 19, 2013
    3,493
    1,231
    1
    Location:
    NY
    Vehicle:
    2017 Prius Prime
    Model:
    Prime Plus
    If you're looking for a challenge, you sure found one, no joke.
    DrPrius (subscription) pack tests, can give a general (and simple ) idea of pack Capacity. Which many of us did not have when we started down our own wack a mole holes.
    Knowing Pack Capacity of new cells is really to only way of understanding what a weak pack looks like.
    Unfortunately, that data is not easy to find and or interpret, cause people that buy new packs don't typically run capacity tests on them.
    One way to get a ballpark capacity of a pack is to time the discharge after a prolong topping charge (where voltage stays constant for several hours) . But you need something to compare the discharge time with. ie: If you've been grid charging with prolong for a few years, and it normally took 4 hours to discharge to your discharge voltage stop point, and now your discharge takes 3 hours, you know your pack has capacity loss, even if you don't know exactly how much loss. Everyone tries to make estimates of how much, which is only one reason why it's so difficult to figure out where your pack is on the capacity front lines.
    The only way to know what the capacity in the car is going be, from cycling modules and the readings the data the charger spits out at you is from ( experience, like what you read from @TMR-JWAP ).
     
  7. articulite

    articulite Junior Member

    Joined:
    Jul 5, 2020
    33
    5
    4
    Location:
    Honolulu
    Vehicle:
    Other Electric Vehicle
    Model:
    N/A
    Noted.

    I think what I'm going to try first is compare "usable" capacity of the pack modules going from 8.4V to 7.1V. (after a prolong topping charge, cool down, and trickle charging/discharging individual modules to 8.4V before the test)

    Before doing that however, I'll see if the bad module in block 5 will even reach 8.4V on an individual trickle and establish baseline bad with the measurements for it. Then I'll see what the questionable other module in block 5 does. Then I'll see what a probably good module does.

    Edit: DrPrius tested at 33.74%. I've gone up from 30% to 60% before, but that's still pretty bad.
     
    vvillovv likes this.
  8. articulite

    articulite Junior Member

    Joined:
    Jul 5, 2020
    33
    5
    4
    Location:
    Honolulu
    Vehicle:
    Other Electric Vehicle
    Model:
    N/A
    Wouldn't DrPrius only show the capacity of the weakest block?
     
  9. vvillovv

    vvillovv Senior Member

    Joined:
    Mar 19, 2013
    3,493
    1,231
    1
    Location:
    NY
    Vehicle:
    2017 Prius Prime
    Model:
    Prime Plus
    You'd have to ask Jack how his app would show you the capacity. priusapp.com
     
  10. articulite

    articulite Junior Member

    Joined:
    Jul 5, 2020
    33
    5
    4
    Location:
    Honolulu
    Vehicle:
    Other Electric Vehicle
    Model:
    N/A
    From what I understand, it pulse charges at high amps (up to more than 60A!, but mostly 30A) (hit the gas, wait, hit the gas, wait, etc) until the car won't let you do that anymore. Typically 75%-80% SoC, but less than that if the pack is in poor condition. It'll stop letting you pulse charge when the pack hits its maximum SoC. This is determined by when the first module (or maybe block) hits it's max SoC.

    The test then discharges from that point at ~6.5A and times how long it takes to drop pack SoC to 40% (but really 39.4-39.9%).

    Then the time is converted into a rough estimate of capacity by comparing to the measurement taken on a new pack.

    So, if measuring usable capacity is good enough a metric for DrPrius on a pack level, I think it's good enough a metric to measure myself on a module level. Though, yes, as has been stated, I don't have a comparative new module measurement using my method to infer a true capacity %. But I will have relative measurements from the other modules which should be sufficient for pairing.

    Actually, Jack would have that number and I should ask him what it is. :)
     
    #30 articulite, Feb 8, 2023
    Last edited: Feb 8, 2023
  11. articulite

    articulite Junior Member

    Joined:
    Jul 5, 2020
    33
    5
    4
    Location:
    Honolulu
    Vehicle:
    Other Electric Vehicle
    Model:
    N/A
    I emailed Jack, but I also asked ChatGPT (AI) to calculate usable capacity with the knowledge that the DrPrius discharge test ideally pulls 6.5A for 900 seconds on a new pack to reach a 100% capacity result.

    The AI says...

    The usable capacity between 80% and 40% on a new Prius NiMH battery discharging at 6.5A can be calculated as follows:

    First, we need to find the discharge rate in Ampere-hours (Ah). The discharge rate can be found using the formula:

    Discharge rate (Ah) = Current (A) x Time (h)

    In this case, the current is 6.5A, and the time is 0.25 hours (15 minutes), so the discharge rate is:

    Discharge rate = 6.5A x 0.25h = 1.625 Ah

    Next, we need to find the total capacity of the battery. For this calculation, the total capacity of the battery is 6.5Ah.

    Finally, we can calculate the usable capacity between 80% and 40% as follows:

    Usable capacity = Total capacity x (80% - 40%) = 6.5Ah x (80% - 40%) = 6.5Ah x 40% = 2.6Ah

    So, in this scenario, the usable capacity between 80% and 40% on a new Prius NiMH battery discharging at 6.5A is 2.6Ah.
     
  12. articulite

    articulite Junior Member

    Joined:
    Jul 5, 2020
    33
    5
    4
    Location:
    Honolulu
    Vehicle:
    Other Electric Vehicle
    Model:
    N/A
    I'll need to think about why DrPrius doesn't discharge 2.6Ah but rather 1.625Ah for the life expectancy test. I'll also look around for a DrPrius video where a new pack is tested. I have seen a few where packs test >110%, exceeding the 900 second timer.
     
  13. articulite

    articulite Junior Member

    Joined:
    Jul 5, 2020
    33
    5
    4
    Location:
    Honolulu
    Vehicle:
    Other Electric Vehicle
    Model:
    N/A
    Ok I tried again but asked the AI to factor in the operating range of voltages. This feels more directionally correct.

    The usable capacity between 80% and 40% on a new Prius NiMH battery can be calculated as follows:

    First, we need to find the energy that has been taken out of the battery in 15 minutes, given a discharge current of 6.5A. The energy in watt-hours (Wh) can be found using the formula:

    Energy (Wh) = Voltage (V) x Current (A) x Time (h)

    We can assume an average voltage between 8.4V and 7.2V, which is 7.8V, during the discharge period. Therefore, the energy taken out of the battery in 15 minutes is:

    Energy = 7.8V x 6.5A x 0.25h = 12.57 Wh

    Next, we can calculate the usable capacity between 80% and 40% as follows:

    Usable capacity = Energy / Total capacity = 12.57Wh / 6.5Ah = 1.9Ah

    So, in this scenario, the usable capacity between 80% and 40% on a new Prius NiMH battery discharging at 6.5A is 1.9Ah.

    Well, dividing watt hours by amp hours to get amp hours seems kind of weird, and wrong. Disregard this. It's NOT directionally correct.

    1.625Ah is the closest answer to being right thus far.

    Update: Jack said "40% usable", but I'm following up to clarify if it's 1625mAh or 2600mAh.
     
    #33 articulite, Feb 9, 2023
    Last edited: Feb 9, 2023
  14. TMR-JWAP

    TMR-JWAP Senior Member

    Joined:
    Aug 12, 2016
    6,058
    5,783
    0
    Location:
    Columbia, SC
    Vehicle:
    2007 Prius
    Model:
    Touring
    Are you an engineer by trade?
     
  15. articulite

    articulite Junior Member

    Joined:
    Jul 5, 2020
    33
    5
    4
    Location:
    Honolulu
    Vehicle:
    Other Electric Vehicle
    Model:
    N/A
    I'm an extremely persistent startup founder with a tech generalist skillset. If I don't know how to do something, I learn how to do it. I take things from concept to functional product in the market, sometimes by myself if I don't have venture capital to hire others to work with me.

    I wouldn't say I'm an engineer by trade, mechanical or software, but I think like an engineer.

    When a relative breaks a fridge and mentions they are going to throw it out, I fix it for them so they don't. I very much like fixing things as well as data analysis. Systems optimization.
     
    #35 articulite, Feb 9, 2023
    Last edited: Feb 9, 2023
  16. Peter1234

    Peter1234 New Member

    Joined:
    Feb 15, 2022
    1
    0
    0
    Location:
    China
    Vehicle:
    2021 Prius
    Model:
    Technology
    It's really dangerous, it is recommended to stay away from this place
     
  17. articulite

    articulite Junior Member

    Joined:
    Jul 5, 2020
    33
    5
    4
    Location:
    Honolulu
    Vehicle:
    Other Electric Vehicle
    Model:
    N/A
    upload_2023-2-9_1-35-9.png

    This is from a new cylindrical pack. DrPrius went past the 15 minute discharge timer by another 5 minutes. Complicating the measurement slightly is the fact that the amperage wasn't maintained at 6.5A near the end of the test.
     
  18. TMR-JWAP

    TMR-JWAP Senior Member

    Joined:
    Aug 12, 2016
    6,058
    5,783
    0
    Location:
    Columbia, SC
    Vehicle:
    2007 Prius
    Model:
    Touring
    Close enough.
    How do you make a project 10x more complicated and 10x expensive? Get an engineer involved.......too few (of us?) stick to KISS.
     
    vvillovv likes this.
  19. articulite

    articulite Junior Member

    Joined:
    Jul 5, 2020
    33
    5
    4
    Location:
    Honolulu
    Vehicle:
    Other Electric Vehicle
    Model:
    N/A
    Hehe.

    My situation is that I bought the car for 1/2 Kelley Blue Book and 1/6th of MSRP. 8 years old and with 139k miles plus a dead pack at the time. The used car place sold it to me at cost without taking a profit because they didn't think anyone else would walk in wanting to buy a dead hybrid vehicle.

    I've had good fun reconditioning the pack with prolong charger and discharger, both of which I bought used on ebay.

    I've had good luck with the modules from ebay.

    I bought some tools I didn't need to, like an impact wrench.

    Altogether and including my most recent purchases of a hobby charger and a discharger with cables, I've still spent far less than the cost of a new pack. (To say nothing of the cost of the car, which I love. It's a CT200h.)

    KISS in this case would be buying a new pack. Which is great if you can afford it. I develop free and open source software that might make money eventually from complimentary products. So Keep It Complicated Korey is what I must practice until then. ;)

    ...And then I'm upgrading to the NexCells muahahaha.
     
    #39 articulite, Feb 9, 2023
    Last edited: Feb 9, 2023
  20. vvillovv

    vvillovv Senior Member

    Joined:
    Mar 19, 2013
    3,493
    1,231
    1
    Location:
    NY
    Vehicle:
    2017 Prius Prime
    Model:
    Prime Plus
    I was also wonderin how long this was gonna take to get a semi compete picture more in focus.

    I had a clue from the reference to a post from S Keith, there I said it.

    welcome to priuschatpta
     
    #40 vvillovv, Feb 9, 2023
    Last edited: Feb 9, 2023