10kWh LifePO4 DIY Battery Addition..... Here is my write up.

@S' - if you're not using a BMS than you are the BMS

You can set top and bottom voltages in the inverter, but the inverter doesn't know if one or more cells are too high or too low. You will need to keep an eye on it. I ran my first 16 CALBS for 15 months without a BMS (or balancer) and all was fine. Because I am a half decent BMS 😁

LiFePO4 shouldn't be charged over 3.65V. But what many people don't know is that the max you can charge LiFePO4 to without doing damage is 4.2V. But you went way above that and your cells are now damaged and likely have reduced capacity. The only way to tell how bad capacity has got is by doing a capacity test. LiFePO4 are relatively very safe, but I'm not sure if I would want a cell in my home that has been overcharged that badly and is now swollen.

If they're swollen, they went significantly higher than 4.2V. If it were my system, I'd order 2 new cells and not use the battery of 16 cells as is. Or only use it in controlled / safe circumstances like only when you are physically there right next to them, or if you have them in an outbuilding / shed where they can do no harm

I finally got my battery connected together after many months. I bought 32 CALB cells from PWOD store and top balanced them months ago, but only got them connected to the inverter though he Seplos BMS and the inverter wired to the consumer unit last week. It's a Sofar ME3000SP inverter. and I've wired the cells as 16s2p.

When I tried to discharge it, the seplos seemed to reboot, and it didn't discharge anything. The Seplos had been reporting around 35% full, which seemed a bit low, but I figured it wouldn't be accurate till a few charge discharge cycles anyay.

I noticed it was reporting around 100mv difference between the top and bottom cells, so I put the Sofar into charge mode to charge the battery at 400W. It didn't take long to report 100%, buy still with a 120mv voltage difference between the top and bottom cells, unsurprisingly, since there's not much real balancing going on.

The Sofar won't discharge now, as it's reporting battery low voltage, this is the data exported from the seplos:

I'll top balance again I guess, but is here possibly a bad cell or 2?

Thanks, I top balanced them months ago, and they've been reconfigured as 16s2p for a long time waiting to get wired up, so they must have drifted over time and I'll just reconfigure them in parallel and top balance again before trying again.

Must get myself a capacity tester, I think there was an AliExpress link earlier in the thread

Has anyone purchased REPT cells before? I got an offer from Docan Power for some 280Ah versions which they say are closer to 300Ah in reality.

I purchased 280Ah EVE cells from them before which they said would be closer to 290Ah and they were actually slightly above this.

About €1,720 for 16 cells DDP from China.

I tried to discharge as part of the commissioning test, even though I wat the Seplos was reporting differing cell voltages and it thought it was only around 35% full, I thought it would discharge a bit until the lower voltage cells brought total voltage to the equivalent of 15% battery capacity (which should be around 3.2V*16=51.2V), then it should have stopped discharging.

I expected to be able to charge then until the highest cells reached the configured monomer high voltage level (from the file champoinc uploaded) of 3.6V.

But the first attempt to discharge resulted in the Seplos resetting and nothing being discharged. So I decided to force charge it using he inverter to 400W. It did start to charge, but very shortly afterwards it reported 100% full so it stopped charging. The Seplos reported the voltages I pasted above. I assume the max voltage got to 3.6V during charging and returned to 3.45 at rest, representing 100% for those cells).

So, I put the Inverter back into auto mode and with import from the grid it should have started dischagring, but it didn't and the event log showed an ID85 Battery Low error which is described in the manual as:

"

ID85

SOC <= 1 -DOD or Battery voltage is low

For example, if you set DOD to 30%, when SOC is less than 70%, you will see ID85 in the event list. ME3000SP won’t discharge the battery when ID85 is present. Or This is an indication of low battery voltage. ME3000SP won’t discharge battery in this case to ensure long battery cycle life.

"

The DOD is set at 85% in the inverter I think, so it shouldn't reach a battery low voltage until the battery pack voltage reaches (16X3.2v=) 51.2V, but it's still reporting 54.63V in the Seplos output above, so that's at rest. I'm wondering if the voltage drops below 51.2V when under load, but that would be a big voltage drop, and could indicate some faulty cells?

I'm a bit confused TBH, and trying to understand how this all should be working.

Is the Seplos definitely integrated into the Sofar (i.e. is it setup as General Lithium) ?

And don't go back into configuration to check settings. You should go into the information menu screen 5 onwards

Yep, it's configured as general lithium and is communicating correctly to the Seplos

I'll try another discharge test later if I can, and monitor the battery voltage with the multimeter throughout

Those are EVE type cells. The CALB type cells that most of us are using (as per the OP) are far sturdier.

Updates for those interested in my battery mishap:

Photo before I switched on the meter:

Next

Next

Looks like it's nearly there, current has dropped way down so how do I know or what would people say the actual capacity is?

I think it shows low while draining. Maybe? I’ll check the voltage when it’s fully drained see what it says.