Long-short term memory neural network based life prediction of lithium-ion battery considering internal parameters

Effective state of health (SOH) estimation is of great significance for the maintenance and management of lithium-ion battery. A method for life prediction of lithium-ion batteries based on long short-term memory (LSTM) neural network is presented in this paper. To simulate the actual scene of the electric vehicle (EV), the dynamic aging experiment is carried out. In order to enhance the accuracy of parameter identification, the RLS algorithm is improved using fuzzy logic, the forgetting factor is adaptive according to the voltage error. Further, the internal parameters strongly related to SOH are extracted, and the SOH prediction model with LSTM neural network is established. The performance of the proposed algorithm is verified by comparing different algorithms with training sets of different scales. (C) 2022 The Author(s). Published by Elsevier Ltd.

Automated summary

This paper presents a method for life prediction of lithium-ion batteries based on LSTM neural network. The SOH prediction model is established through dynamic aging experiment and parameter identification improvement, and the effectiveness of the proposed method is verified through experiments.