TPANet: A novel triple parallel attention network approach for remaining useful life prediction of lithium-ion batteries

• 全文链接
• 请求原文

作   者：

Yuanjiang Li;  Runze Mao;  Yueling Li;  Weizhi Lu;  Jinglin Zhang;  Lei Li; 

作者机构：

Department of Signal Reception and Processing;  Jinan 250100;  Shandong University;  Jiangsu University of Science and Technology;  China||Department of Information Science and Engineering;  Yangzhou 225000;  China||Shandong Research Institute of Industrial Technology;  China;  School of Control Science and Engineering;  250100;  Jinan;  212003;  China State Shipbuilding Corporation(CSSC)723rd Research Institute;  School of Oceanography;  Linyi University;  Linyi 276000;  China||School of Oceanography;  Zhenjiang; 

关键词：

Lithium-ion batteries (LIBs);  Triple parallel attention network (TPANet);  Remaining useful life (RUL);  False nearest neighbors (FNN); 

期刊名称：

Energy

i s s n：

0360-5442

年卷期：

2024 年 309 卷 Nov.15 期

页   码：

1-14

页   码：

摘   要：

Accurate remaining useful life (RUL) prediction for lithium-ion batteries (LIBs) is important for proper equipment operation. Among the numerous existing studies on battery research, data-driven approaches have gained significant attention because they obviate the need for complex chemical and physical modeling of battery processes. However, in most current data-driven methods, the sliding window size values are determined empirically, which affects both the time required for model prediction and the prediction accuracy. To address this issue, this paper proposes a two-stage prediction method for battery capacity aging trajectories. In the first stage, a false nearest neighbor (FNN) technique is utilized to infer the sliding window size of the battery, reducing the error associated with manually selecting the sliding window size. In the second stage, a novel triple parallel attention network (TPANet) based on convolutional neural networks (CNNs) and attention units is developed, which extracts the input battery capacity degradation features through a parallel mechanism. The introduction of attention units in each parallel branch allows the model to enhance the capture of capacity regeneration phenomena as well as long-term dependence on input data. The proposed approach is validated on two publicly available datasets as well as a battery developed by ourselves. Diverse simulation results demonstrate the ability of the proposed approach to accurately predict the RUL of LIBs in a short time with broad generalization capabilities.