Voltage-stress-based state of charge estimation of pouch lithium-ion batteries using a long short-term memory network

In this work, a novel SOC estimation method of a battery based on voltage and stress measurements is proposed with the utilization of machine learning techniques. To evaluate the necessity of stress measurements for SOC estimation, a series of stress characteristic experiments are designed to probe the relationship between mechanical responses and the SOC. On this basis, the stress is taken as an auxiliary for the SOC estimation. Then, a typical (long short-term memory) LSTM network is introduced to map battery measurement signals directly to the battery SOC. The proposed method is evaluated under constant current (CC), dynamic stress test (DST), and urban dynamometer driving schedule (UDDS) conditions. Experimental results show that the voltage-stress-based method can achieve good accuracy. In general, the proposed method provides a new insight into the SOC estimation of pouch lithium-ion batteries.

September 2022