Refined lithium-ion battery state of health estimation with charging segment adjustment

Accurately monitoring the state of health (SOH) of lithium-ion batteries (LIBs) is crucial for battery management systems (BMS), yet there lack of the possibility to fully use the random charging segments with any length. To this end, a residual convolution and transformer network (R-TNet) is proposed to enable an accurate LIB SOH estimation with the sparse dimension of feature in random segments, where the start and end voltage, the Ampere-hour (Ah) throughput, temperature, and current rate of a charging segment are required for the estimation task. Through the cross-attention mechanism of R-TNet, the operation condition and the position of the partial voltage can be integrated to enable the LIBs SOH estimation within a charging segment. To extend the flexibility with arbitrary charging behaviors, an ElasticNet-based feature transfer strategy is designed to use any charging length. 121 cells with different chemistries and cycling conditions are used to validate the performance of the proposed method. The results of the proposed method show that the root mean square error (RMSE) of SOH estimation can reach 1.6% even for a 50 mV voltage segment.