Data-driven lithium-ion battery capacity estimation from voltage relaxation

Abstract

Accurate capacity estimation is critical for reliable and safe operation of lithium-ion batteries. A proposed approach exploiting features from the relaxation voltage curve enables battery capacity estimation without requiring previous cycling information. Machine learning methods are used in the approach. A dataset including 27,330 data units are collected from batteries with LiNi0.86Co0.11Al0.03O2 cathode (NCA battery) cycled at different temperatures and currents until reaching about 71% of their nominal capacity. One data unit comprises three statistical features (variance, skewness, and maxima) derived from the relaxation voltage curve after fully charging and the following discharge capacity for verification. Models adopting machine learning methods, i.e., ElasticNet, XGBoost, Support Vector Regression (SVR), and Deep Neural Network (DNN), are compared to estimate the battery capacity. Both XGBoost and SVR methods show good predictive ability with 1.1 % root-mean-square error (RMSE). The DNN method presents a 1.5% RMSE higher than that obtained using ElasticNet and SVR. 30,312 data units are extracted from batteries with LiNi0.83Co0.11Mn0.07O2 cathode (NCM battery). The model trained by the NCA battery dataset is verified on the NCM battery dataset without changing model weights. The test RMSE is 3.1% for the XGBoost method and 1.8% RMSE for the DNN method, indicating the generalizability of the capacity estimation approach utilizing battery voltage relaxation.

Deep‐Learning‐Enabled Crack Detection and Analysis in Commercial Lithium‐Ion Battery Cathodes

“…There have been a few machine‐learning based methods developed in the literature including the automatic capacity estimation of lithium‐ion batteries. [ 31 ] To systematically predict the performance degradation behavior of battery material it requires enough dataset collected under different operational conditions. Scientifically, it is conceivable that the side reactions and bulk phase crack generation are correlated and mutually modulated.…”

A novel multiple training-scale dynamic adaptive cuckoo search optimized long short-term memory neural network and multi-dimensional health indicators acquisition strategy for whole life cycle health evaluation of lithium-ion batteries

“…Step 3. 2 Step size dynamic adjustment strategy. According to the fitness of all nests obtained, the maximum fitness f m , the mean value f q of all fitness, and the mean value f v of all fitness exceeding f q are determined.…”

“…The development of new energy vehicle technology is a strategic measure to alleviate the world energy crisis and achieve the goal of carbon neutrality [1][2][3].…”

Calendar ageing modelling using machine learning: an experimental investigation on lithium ion battery chemistries

“…XGBoost is a decision tree based machine learning algorithm, while the ANN is an artificial adaptive system that uses its base elements, called neurons and connections, to transform its global inputs into a predicted output 14 . The motivation behind the selection of these algorithms is that both methods are known for their ability to yield reliable results 6 , 15 , 16 as well as, by employing these algorithms, there would be a means of comparing the prediction performances of machine learning algorithms on different chemistries.…”