State-of-Health Estimation and Anomaly Detection in Li-Ion Batteries Based on a Novel Architecture with Machine Learning

Abstract

Variations across cells, modules, packs, and vehicles can cause significant errors in the state estimation of LIBs using machine learning algorithms, especially when trained with small datasets. Training with large datasets that account for all variations is often impractical due to resource and time constraints at initial product release. To address this issue, we proposed a novel architecture that leverages electronic control units, edge computers, and the cloud to detect unrevealed variations and abnormal degradations in LIBs. The architecture comprised a generalized deep neural network (DNN) for generalizability, a personalized DNN for accuracy within a vehicle, and a detector. We emphasized that a generalized DNN trained with small datasets must show reasonable estimation accuracy during cross validation, which is critical for real applications before online training. We demonstrated the feasibility of the architecture by conducting experiments on 65 DNN models, where we found distinct hyperparameter configurations. The results showed that the personalized DNN achieves a root mean square error (RMSE) of 0.33%, while the generalized DNN achieves an RMSE of 4.6%. Finally, the Mahalanobis distance was used to consider the SOH differences between the generalized DNN and personalized DNN to detect abnormal degradations.

A machine learning framework for remaining useful lifetime prediction of li-ion batteries using diverse neural networks

“…Model capability [1] GRNN Type 1 [2] Residual network with attention mechanism Type 2 [3] TCN Type 2 [4] CNN-LSTM Type 2 [5], [6] LSTM Type 3 [7] Bi-directional GRU Type 3 [8] Bi-directional LSTM Type 3 [9] LSTM with attention Type 3 [10] Bi-directional LSTM with attention Type 3 [11] Transformer Type 3 [12] FFNN Type 3…”

“…Finally, Lee et al [12] put forth an innovative system designed to esti-mate the SOH and detect anomalies in Li-ion batteries. This system is unique in its software architecture, which enables a synergistic interaction between battery management systems (BMSs), domain control units (DCUs), and the cloud.…”