Work

A hybrid data-driven method for voltage state prediction and fault warning of Li-ion batteries

Year: 2024

Type: article

Abstract: As the extensive application of Electrochemical Energy Storage (EES), Li-ion battery fault is a key factor reference to the reliable operation and system security, influencing by the environment temperature and battery voltage. The Li-ion battery fault may result in the thermal runaway, even fire and explosion accidents, which is a crucial bottleneck hindering of EES as their volume and quantity increase. In this paper, a novel 1DCNN-Bi-LSTM network has been proposed to predict the Li-ion battery fault, which contains an 1DCNN module to extract various parameter features and a Bi-LSTM module with self-attention mechanism to realize fault prediction process precisely. To further verify the algorithm effectiveness, a new 18650 battery dataset has been set up under various conditions between day and night. The experimental results show that our model has high accuracy and exemplary performance in various environmental temperatures, the MAPE indicator is around 1% in multiple temperatures. Compared with state-of-the-art methods, the proposed model has smaller difference between predicted and true values, performs better at peaks and valleys, and has higher computational efficiency. Considering the temperature factor and voltage variation, our developed method can be effectively applied to battery management systems.

Source: Case Studies in Thermal Engineering

DOI: 10.1016/j.csite.2024.105420

Authors: Yufeng Huang, Xuejian Gong, Zhiyu Lin, Lei Xu

Institutions: Shenyang Aerospace University, Shenyang Fire Research Institute

Language: English

Topic: Advanced Battery Technologies Research

Subfield: Automotive Engineering

Field: Engineering

Domain: Physical Sciences

SDGs: Affordable and clean energy, Industry, innovation and infrastructure

Open Access status: gold

Estimated APC paid: $1,210