Fast and Accurate Health Assessment of Lithium-Ion Batteries Based on Typical Voltage Segments

Abstract

Lithium-ion batteries are widely employed in industries and daily life. Research on the state of health (SOH) of batteries is essential for grasping the performance of batteries, better guiding battery health management, and avoiding safety mishaps caused by battery aging. Nowadays, most research adopts a data-driven artificial intelligence approach to assess SOH. However, the majority of approaches are based on entire voltage, current, or temperature curves. In reality, voltage, current, and temperature are frequently presented in segments, leading to the limited flexibility and slow analysis speed of the traditional techniques. This study solves the problem by dividing the whole voltage curve into many typical kinds of segments with equal timescales based on different typical voltage beginning points. On this foundation, the temporal convolution network (TCN) is used to create a sub-model of SOH estimation for several typical kinds of segments. In addition, the sub-models are fused using the bootstrap aggregating (Bagging) approach to boost accuracy. Finally, this research uses a publicly available dataset from Oxford to demonstrate the effectiveness of the suggested strategy.