Article: A health prediction method for new energy vehicle power batteries based on AACNN-LSTM neural network Journal: International Journal of Information and Communication Technology (IJICT) 2024 Vol.24 No.5 pp.74 - 94 Abstract: Battery pack is an important part of the energy system of electric vehicles, and ensuring its safety is of great significance to the intelligent development of electric vehicles and human life and property. Detecting and ensuring the safety of battery pack in the energy system has become a research hotspot in the field of power batteries. This paper proposes a new composite deep neural network attention after CNN-LSTM (AACNN-LSTM) based on the characteristics and limitations of long- and short-term memory (LSTM) neural network, one-dimensional convolution neural network (1D-CNN) and other methods. We have carried out comparative experiments such as data division of different life stages, ablation experiments of multiple architecture combinations, and comparison with different types of algorithms. The results show that compared with other methods, the precision is significantly improved and the operation efficiency is maintained. Finally, the proposed health state estimation method is verified by three different battery accelerated aging test datasets. The experimental results show that the proposed method shows excellent battery health state estimation performance and good robustness under different working conditions and different number of training cycles. Inderscience Publishers - linking academia, business and industry through research

Title: A health prediction method for new energy vehicle power batteries based on AACNN-LSTM neural network

Authors: Jijun Zhang; Wenjian Feng; Yisong Tan; Hanping Pan

Addresses: College of Automotive and Information Engineering, Guangxi Eco-Engineering Vocational & Technical College, Liuzhou 545004, Guangxi, China ' College of Automotive and Information Engineering, Guangxi Eco-Engineering Vocational & Technical College, Liuzhou 545004, Guangxi, China ' College of Automotive and Information Engineering, Guangxi Eco-Engineering Vocational & Technical College, Liuzhou 545004, Guangxi, China ' College of Automotive and Information Engineering, Guangxi Eco-Engineering Vocational & Technical College, Liuzhou 545004, Guangxi, China

Abstract: Battery pack is an important part of the energy system of electric vehicles, and ensuring its safety is of great significance to the intelligent development of electric vehicles and human life and property. Detecting and ensuring the safety of battery pack in the energy system has become a research hotspot in the field of power batteries. This paper proposes a new composite deep neural network attention after CNN-LSTM (AACNN-LSTM) based on the characteristics and limitations of long- and short-term memory (LSTM) neural network, one-dimensional convolution neural network (1D-CNN) and other methods. We have carried out comparative experiments such as data division of different life stages, ablation experiments of multiple architecture combinations, and comparison with different types of algorithms. The results show that compared with other methods, the precision is significantly improved and the operation efficiency is maintained. Finally, the proposed health state estimation method is verified by three different battery accelerated aging test datasets. The experimental results show that the proposed method shows excellent battery health state estimation performance and good robustness under different working conditions and different number of training cycles.

Keywords: life prediction; attention mechanism; time series prediction; LSTM.

DOI: 10.1504/IJICT.2024.138451

International Journal of Information and Communication Technology, 2024 Vol.24 No.5, pp.74 - 94

Received: 11 Dec 2023
Accepted: 29 Dec 2023
Published online: 03 May 2024 *

Title: A health prediction method for new energy vehicle power batteries based on AACNN-LSTM neural network

Keep up-to-date