Open Access
ARTICLE
A Power Battery Fault Diagnosis Method Based on Long-Short Term Memory-Back Propagation
School of Automation, Harbin University of Science and Technology, Harbin, 150080, China
* Corresponding Author: Jiahao Song. Email:
(This article belongs to the Special Issue: Advanced Modelling, Operation, Management and Diagnosis of Lithium Batteries)
Energy Engineering 2025, 122(2), 709-731. https://doi.org/10.32604/ee.2024.059021
Received 26 September 2024; Accepted 07 November 2024; Issue published 31 January 2025
Abstract
The lithium battery is an essential component of electric cars; prompt and accurate problem detection is vital in guaranteeing electric cars’ safe and dependable functioning and addressing the limitations of Back Propagation (BP) neural networks in terms of vanishing gradients and inability to effectively capture dependencies in time series, and the limitations of Long-Short Term Memory (LSTM) neural network models in terms of risk of overfitting. A method based on LSTM-BP is put forward for power battery fault diagnosis to improve the accuracy of lithium battery fault diagnosis. First, a lithium battery model is constructed based on the second-order RC equivalent circuit and the electro-thermal coupling model, and various lithium battery failures are simulated to examine the fault characteristics. Then, the lithium battery charging and discharging experiments collect, clean, and process the battery data. By constructing a neural network LSTM-BP model, we verified the superiority and accuracy of the LSTM-BP neural network model by comparing the LSTM model and BP model vertically and by comparing the Recurrent Neural Network (RNN) model, the Gated Recurrent Unit (GRU) model, and the Residual Neural Network (ResNet) model of a more advanced architecture horizontally. Finally, the lithium battery fault diagnosis process is summarized through the threshold quantitative criteria, and different faults are diagnosed and analyzed. The results show that the LSTM-BP neural network not only overcomes the limitations of the LSTM neural network and BP neural network but also improves the ability to process sequence data and reduces the risk of overfitting.Keywords
Cite This Article

This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.