Thien Pham

Lithium‐ion batteries are widely used in moving devices due to their many advantages compared to other battery types. The prevalence of Lithium‐ion batteries is evident, playing its clear role in the operation of small devices as well as large systems such as electric vehicles, flying devices, mobile devices, and more. Monitoring lithium‐ion battery health is crucial for assessing, minimizing degradation, preventing explosions, and enabling timely replacements. Assessing health often involves predicting state‐of‐health (SoH) or remaining useful life (RUL), with numerous studies dedicated to this field. Hence, many research studies have been conducted on predicting SoH, with a primary focus on data‐driven methods based on machine learning, owing to the recent advancements in artificial intelligence (AI) techniques. To provide a systematic overview of the trends in this emerging problem, we present a comprehensive survey of classified SoH forecasting methods, with a primary focus on data‐driven approaches. The paper also offers an in‐depth focus on recent advancements in deep learning (DL) models, an area that has not been thoroughly discussed previously. Furthermore, we highlight the importance of input features and emphasize the critical role of temporal attributes incorporated into the models. The insights provided in this paper offer readers a comprehensive understanding of the field, equipping them to effectively advance related future work.

5G is the fifth generation of cellular networks and has been used in a lot of different areas. 5G often requires sudden rises in power consumption. To stabilize the power supply, a 5G system requires a lithium-ion battery (LIB) or a mechanism called AC main modernization to provide energy support during the power peak periods. The LIB approach is the best option in terms of simplicity and maintainability. Moreover, a 5G system requires not only high-performance energy but also the ability of tracking and prediction. Therefore, the requirement for a smart power supply for lithium-ion batteries with temporal monitoring and estimation is highly desirable. In this paper, we focus on artificial intelligence (AI) improvements to increase the accuracy of LIB state-of-health prediction. By observing the SeqInSeq nature of the battery data, our approach uses self-attention and fixed-point positional encoding. We also take advantage of autoregression to archive the trainable dependency from a non-linear branch and a linear branch in creating the final output. Compared with the current state-of-the-art (SOTA) method, our experimental results show that we provide better accuracy, compared with the baseline output using the NASA and CALCE datasets. From the same setting, we archive a reduction of 20.08% root mean square error (RMSE) and 29.01% mean absolute percentage error (MAPE) on NASA loss, compared to the SOTA approaches. On CALCE, the numbers are a 5.99% RMSE and 12.59% MAPE decrement, which is significant.