An Online SOH Estimation Method Based on the Fusion of Improved ICA and LSTM

State of health (SOH) estimation is one of the basic functions of a battery management system. Accordingly, the SOH estimation method becomes particularly important. This paper proposes a SOH estimation method based on the fusion of improved incremental capacity analysis (ICA) and long short term memory (LSTM) neural network. And the SOH is estimated based on data from the constant-current and constant-voltage charging stage. In order to make full use of the charging process, the entire charging SOC is spaced. The corresponding models are established in the different SOC intervals. The specific model is selected based on the data collected in real time, and the estimated SOH is obtained. Among all models, the maximum error does not exceed 4%.