A hybrid remaining useful life prediction method for lithium-ion batteries based on transfer learning with CDRSN-BiGRU-AM

被引:4
作者
Li, Lei [1 ]
Li, Yuanjiang [1 ,2 ]
Zhang, Jinglin [3 ,4 ,5 ]
机构
[1] Jiangsu Univ Sci & Technol, Sch Oceanog, Zhenjiang, Peoples R China
[2] Jiangsu Daquan Box Transformer Technol Co Ltd, Dept Engn, Zhenjiang, Peoples R China
[3] Shandong Univ, Dept Control Sci & Engn, Jinan, Peoples R China
[4] Linyi Univ, Dept Informat Sci & Engn, Linyi, Peoples R China
[5] Shandong Res Inst Ind Technol, Jinan, Peoples R China
基金
中国国家自然科学基金;
关键词
lithium-ion battery; remaining useful life; channel-wise deep residual shrinkage network; bidirectional gated recurrent unit; attention mechanism; HEALTH DIAGNOSIS; STATE; MODEL; NETWORK;
D O I
10.1088/1361-6501/ad282e
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
The prediction of the remaining useful life (RUL) of widely used lithium-ion batteries (LIBs) is of great importance. Existing techniques struggle to balance prediction accuracy with execution time. To achieve accurate RUL prediction quickly, a hybrid RUL prediction method for LIBs has been developed. This method first employs a channel-wise deep residual shrinkage network to adaptively extract features from input data enhancing important information features and suppressing ineffective ones based on the significance of the feature information. Subsequently, a bidirectional gated recurrent unit is used to extract bidirectional temporal features from the processed data, and an attention mechanism is introduced to maximize the extraction of significant temporal mutual information. Finally, a fully connected layer transfer strategy is applied to transition the model from offline training to online prediction, which avoids unstable predictions due to random model initialization and significantly improves the model's computational efficiency. The simulation results show that the root mean square error of the proposed method did not exceed 1.77% and the mean absolute error did not exceed 1.44% on the NASA dataset. Consequently, the proposed method can achieve accurate online RUL prediction accuracy for LIBs.
引用
收藏
页数:17
相关论文
共 42 条
[1]   Remaining Useful Life Estimation for Prognostics of Lithium-Ion Batteries Based on Recurrent Neural Network [J].
Catelani, Marcantonio ;
Ciani, Lorenzo ;
Fantacci, Romano ;
Patrizi, Gabriele ;
Picano, Benedetta .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2021, 70
[2]   Remaining Useful Life Prediction of Lithium-Ion Battery via a Sequence Decomposition and Deep Learning Integrated Approach [J].
Chen, Zhang ;
Chen, Liqun ;
Shen, Wenjing ;
Xu, Kangkang .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2022, 71 (02) :1466-1479
[3]   Temporal Attention Convolutional Neural Network for Estimation of Icing Probability on Wind Turbine Blades [J].
Cheng, Xu ;
Shi, Fan ;
Zhao, Meng ;
Li, Guoyuan ;
Zhang, Houxiang ;
Chen, Shengyong .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2022, 69 (06) :6371-6380
[4]   Useful life prediction based on wavelet packet decomposition and two-dimensional convolutional neural network for lithium-ion batteries [J].
Ding, Pan ;
Liu, Xiaojuan ;
Li, Huiqin ;
Huang, Zequan ;
Zhang, Ke ;
Shao, Long ;
Abedinia, Oveis .
RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2021, 148 (148)
[5]   SOC Estimation Using Deep Bidirectional Gated Recurrent Units With Tree Parzen Estimator Hyperparameter Optimization [J].
How, Dickson N. T. ;
Hannan, M. A. ;
Lipu, Molla S. Hossain ;
Ker, Pin Jern ;
Mansor, Muhamad ;
Sahari, Khairul S. M. ;
Muttaqi, Kashem M. .
IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 2022, 58 (05) :6629-6638
[6]   LightGBM-Based Framework for Lithium-Ion Battery Remaining Useful Life Prediction Under Driving Conditions [J].
Jiao, Zhipeng ;
Wang, Hongda ;
Xing, Jianchun ;
Yang, Qiliang ;
Yang, Man ;
Zhou, Yutao ;
Zhao, Jiubin .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2023, 19 (11) :11353-11362
[7]   Remaining useful life prediction of lithium-ion batteries using EM-PF-SSA-SVR with gamma stochastic process [J].
Keshun, You ;
Guangqi, Qiu ;
Yingkui, Gu .
MEASUREMENT SCIENCE AND TECHNOLOGY, 2024, 35 (01)
[8]   Remaining Useful Life Prediction for Lithium-Ion Batteries With a Hybrid Model Based on TCN-GRU-DNN and Dual Attention Mechanism [J].
Li, Lei ;
Li, Yuanjiang ;
Mao, Runze ;
Li, Li ;
Hua, Wenbo ;
Zhang, Jinglin .
IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION, 2023, 9 (03) :4726-4740
[9]   State-of-health estimation and remaining useful life prediction for the lithium-ion battery based on a variant long short term memory neural network [J].
Li, Penghua ;
Zhang, Zijian ;
Xiong, Qingyu ;
Ding, Baocang ;
Hou, Jie ;
Luo, Dechao ;
Rong, Yujun ;
Li, Shuaiyong .
JOURNAL OF POWER SOURCES, 2020, 459
[10]   Hybrid Data-Driven Approach for Predicting the Remaining Useful Life of Lithium-Ion Batteries [J].
Li, Yuanjiang ;
Li, Lei ;
Mao, Runze ;
Zhang, Yi ;
Xu, Song ;
Zhang, Jinglin .
IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION, 2024, 10 (02) :2789-2805