Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Development of a free Capacity Predicition, need your help
#11
Isn't manufacture date also supposed to be relevant to cell capacity over time?
I suspect too many things will influence change in capacity from when it was new to easily predict capacity of a cell taken out of a pack.
Reply
#12
(05-08-2019, 02:42 AM)Oz18650 Wrote: Isn't manufacture date also supposed to be relevant to cell capacity over time?
I suspect too many things will influence change in capacity from when it was new to easily predict capacity of a cell taken out of a pack.

Not really. Number of cycles is probably the biggest factor. Degradation over time is minimal by comparison. Other variables include storage conditions - what sate of charge was the cell stored at, and what temperature was it stored at.

Measuring internal resistance is indeed the only valid method for predicting capacity.
Reply
#13
I meant that you won't know things that have gone on previously, such as number of cycles.
I do believe that IR will be a good indicator, but you will need a good sample size of each type of cell to get meaningful data - as wolf has done.
I am hoping to do similar predicting as my cells are all the same type, so I will have a good sample size.
I also know manufacture date of the cell packs, so I am hoping to see how that affects performance of the cells.
I was planning to have started testing already, but I got more cells so I have continued extracting instead.
Reply
#14
I like the new ideas that started in this thread. 
But using some kind of Metamodel and put some data in it and hope that it will create good results doesn't work in reallife.
The development of such models is my dayly work and the models I show here are also complete developed by myself over years.
So you will not get that special kind of models in scipy or numpy etc..

And sample size is not everything. If you think so, you don't understand that kind of models and maybe you don't understand data modelling itself.

So next data, looks really promising in my opinion:
Reply
#15
Please explain the picture for us?
I think I get it, but want to make sure.
Reply
#16
Oz18650 Wrote:Please explain the picture for us?
I think I get it, but want to make sure.

(05-07-2019, 09:14 AM)drbacke Wrote: Ok here are the first results. 
The X-Axis shows the measured results and the Y-Axis the predicted results with the predicted uncertainty as error bars.
The blue line marks the ideal line, if the model wouöd be perfect, all values would lie on this line.
.....

This diagram shows rather what we are interested in:
On the X-Axis is the measured Capacity and on the Y-Axis the predicted probability that the cell will have more than 2000mAh. So this looks quite good, most of the cells which have a probability>50% are actually over 2000mAh. 
Of course you can use any capacity instead of 2000mAh, it's just an example.



 

Reply
#17
(05-07-2019, 07:11 PM)Wolf Wrote:
(05-07-2019, 04:12 PM)Satiriasis Wrote: When we have enough data, I can build the model and say for sure if it works. But as I say, my initial measurements say it is possible...
@Satiriasis

That is interesting combining these 3 parameters into a ML for prediction. I will watch to see how it progresses.
I am more of trying to get the probability of a cell being good and within 80% of rated capacity rather than the prediction of capacity which I tried with several different methods. None with any AI, NN or ML though. I was not successful. Hopefully some of you are.

I look forward to your results and may the IR be with you.

Wolf
Hi Wolf, 

thanks for your reply, yes I also do not have much time, currently I have just one Opus where I have setup the environment, my way is to record the video for the complete charging/discharging process and than manually extract the data. So it will take ages, I need hundreds of batteries + different chemistry and vendors. 

Currently, I am building the model that is able to predict it from complete discharge, later I believe, I can build the model also from completely charged batteries and watch characteristic while discharging them (again about 30min from the fully charged state). The final HW will have ability to decide - if you harvested fully charged battery, it will start from fully charged one, if almost discharged, it will discharge it and start testing for 30min.

The problem you have mentioned with the noise of the temperature is not a problem. I am not interested in the overall accurate temperature, rather than changes within the time (deltas), but I will not be saying more at the moment...
Reply
#18
@drbacke

Quite interesting to view your Capacity Prediction Test sheet on google drive and look at your capacity results using IR as a guide and they match my own results pretty close. Pretty much within a 5% deviation. Not bad.

Wolf
If 18 X 650 = 2200+mAh then we have power! 
May all your Cells have an IR of 75mΩ or less Smile
Last count as of 5/23/2019
Total Number of Cells                          5354
Cells  >80% of Capacity                      3801
Cells <80% of Capacity                       1553
Cells ≥2200mAh & ≥ 80% & ≤75mΩ    2645 (155) to go
For Info Google Drive
Not your average Wolf       
            Cool



Reply
#19
(05-08-2019, 11:13 AM)Wolf Wrote: @drbacke

Quite interesting to view your Capacity Prediction Test sheet on google drive and look at your capacity results using IR as a guide and they match my own results pretty close. Pretty much within a 5% deviation. Not bad.

Wolf
Which results do you exactly mean? 






Next results: 
There are now some cells with low capacity and it seems to work quite well also.
But there is one cell, which was predicted quite bad in my opinion (in the probability plot ~30% prob and 2500mAh).  It's a Sanyo UR18650NSX with 12.5 mOhm.
Maybe in this case its really a problem of lacking data, because the predicted standard deviation is at maximum, which means there is no data in this place.
But also you can see, that the deviation is quite high, what tells you: "I don't know anything here"



 
Reply
#20
(05-09-2019, 05:00 AM)drbacke Wrote: Which results do you exactly mean?



Your tested capacity results in your sheet.
I just sort my data by cell Part number and then sort by IR selecting the IR you recorded as close as possible and eliminating the rest.

Certainly there is some deviation but most of them match up pretty close.
    

Quote:Next results: 
There are now some cells with low capacity and it seems to work quite well also.
But there is one cell, which was predicted quite bad in my opinion (in the probability plot ~30% prob and 2500mAh).  It's a Sanyo UR18650NSX with 12.5 mOhm.
Maybe in this case its really a problem of lacking data, because the predicted standard deviation is at maximum, which means there is no data in this place.
But also you can see, that the deviation is quite high, what tells you: "I don't know anything here"


The Sanyo UR18650NSX is a high drain manganese based cell which will have a very low IR compared to a cobalt based low drain cell.
You really can't put those cell into the same category as it will throw your model way off.

Wolf
If 18 X 650 = 2200+mAh then we have power! 
May all your Cells have an IR of 75mΩ or less Smile
Last count as of 5/23/2019
Total Number of Cells                          5354
Cells  >80% of Capacity                      3801
Cells <80% of Capacity                       1553
Cells ≥2200mAh & ≥ 80% & ≤75mΩ    2645 (155) to go
For Info Google Drive
Not your average Wolf       
            Cool



Reply


Who read this thread?
55 User(s) read this thread:
hbpowerwall, daromer, Sean, Korishan, PAF, wim, watts-on, jesusangel, Stefaan De Ridder, Geek, floydR, emerca, ChrisD5710, Oz18650, djuro, BaronVonChickenPants, dwarflundgren, drchips, gpn, Chablis_m, thanar, Crimp Daddy, Redpacket, completelycharged, Ibiza, Bubba, Cherry67, Riplash, Jim Jr., Katarn_89, w0067814, HikingGuy42, chuckp, emuland-metroman, Truth, Shawndoe, Wolf, Bastler_Ro, Solardad, kevinjaye, mart1nn, OffGridInTheCity, Satiriasis, fannel, Overmind, ma3006he, winny, 100kwh-hunter, JBonesaw, juanjo57, drbacke, gigaz, ben teker, Marrcin, fsalinas

Forum Jump:


Users browsing this thread: 1 Guest(s)