Improved anti-noise adaptive long short-term memory neural network modeling for the robust remaining useful life prediction of lithium-ion batteries. (February 2023)

• Record Type: Journal Article
• Authors: Wang, Shunli; Fan, Yongcun; Jin, Siyu; Takyi-Aninakwa, Paul; Fernandez, Carlos
• Is Part Of: Reliability engineering & system safety. Volume 230(2023)
• Publication Date: 2023-02
• Subjects: Lithium-ion battery -- Remaining useful life prediction -- Anti-noise adaptive long short-term memory neural network -- Multi-feature collaboration -- Adaptive feedback correction; Reliability (Engineering) -- Periodicals; System safety -- Periodicals; Industrial safety -- Periodicals; Fiabilité -- Périodiques; Sécurité des systèmes -- Périodiques; Sécurité du travail -- Périodiques; 620.00452
• DOI: 10.1016/j.ress.2022.108920
• Languages: English
• ISSNs: 0951-8320

Abstract

Highlights: An improved ANA-LSTM model is built for RUL prediction of lithium-ion batteries. Multiple feature collaboration is conducted for internal parameter characterization. Adaptive feedback correction is established with the multi-feature collaboration. Collaborative and multiple factors are optimized through meta-structure fine-tuning. RUL prediction results show optimal MAE and RMSE of 0.390% and 0.604%, respectively. Abstract: Safety assurance is essential for lithium-ion batteries in power supply fields, and the remaining useful life (RUL) prediction serves as one of the fundamental criteria for the performance evaluation of energy and storage systems. Based on an improved dual closed-loop observation modeling strategy, an improved anti-noise adaptive long short-term memory (ANA-LSTM) neural network with high-robustness feature extraction and optimal parameter characterization is proposed for accurate RUL prediction. Then, an adaptive state parameter feedback correction strategy is constructed through multiple feature collaboration with its internal coupling mechanism characterization, which considers varying current rates, ambient temperatures, and other influencing parameters. Subsequently, a collaborative multi-parameter optimization is carried out along with the model training and meta-structure fine-tuning. Compared with other optimal existing methods, the maximum root mean square error decreases by 51.80%, the mean absolute error reduces by 26.95%, the maximum mean absolute percentage error decreases by 33.87%, and the R -squared increases by 4.11%. The established multiple-feature collaboration model realizes multi-scale parameter optimization and robust RUL prediction, thus advancing the industrial application of lithium-ion batteries. Graphical abstract: Image, graphical abstract