A Review of SOH Prediction of Li-Ion Batteries Based on Data-Driven Algorithms

Abstract

As an important energy storage device, lithium-ion batteries (LIBs) have been widely used in various fields due to their remarkable advantages. The high level of precision in estimating the battery’s state of health greatly enhances the safety and dependability of the application process. In contrast to traditional model-based prediction methods that are complex and have limited accuracy, data-driven prediction methods, which are considered mainstream, rely on direct data analysis and offer higher accuracy. Therefore, this paper reviews how to use the latest data-driven algorithms to predict the SOH of LIBs, and proposes a general prediction process, including the acquisition of datasets for the charging and discharging process of LIBs, the processing of data and features, and the selection of algorithms. The advantages and limitations of various processing methods and cutting-edge data-driven algorithms are summarized and compared, and methods with potential applications are proposed. Effort was also made to point out their application methods and application scenarios, providing guidance for researchers in this area.

Understanding the Energy Potential of Lithium‐Ion Batteries: Definition and Estimation of the State of Energy

“…As highlighted by Zhang et al, [38] data-driven methods do not consider a battery cell's internal dynamics. These methods model the input and output relationship as a black box, relying solely on the processed data.…”

“…These methods model the input and output relationship as a black box, relying solely on the processed data. [38] The three primary steps involved in the data-driven approach are the following: [11,39] data collection and feature extraction, model training, and estimation. An advantage is that these approaches do not require a comprehensive understanding of the battery cell's electrochemical processes and internal mechanisms.…”

“…An advantage is that these approaches do not require a comprehensive understanding of the battery cell's electrochemical processes and internal mechanisms. [38] Nonetheless, the high non-linearity of the cell that a simplified ECM cannot model can be captured. However, an extensive data set is needed, [40,38] and the method's transferability to other cells is usually limited.…”

“…[38] Nonetheless, the high non-linearity of the cell that a simplified ECM cannot model can be captured. However, an extensive data set is needed, [40,38] and the method's transferability to other cells is usually limited. The data quality also dramatically impacts the performance of the data-driven method.…”

A physical model of a supercapacitor to reveal the mechanism of the voltage recovery phenomenon

“…a non-porous structure, also has a voltage recovery characteristic which suggests that ion trapping is not the only mechanism in voltage recovery. Thus, it is important to know the mechanism, which could not only guide us in understanding the transfer of ions but also could give us some guidance in other fields such as SOH prediction, 13 estimation of the state of health for batteries, 14 and understanding the evolution of transition metals in batteries. 15 Thus, a physical model was proposed for the supercapacitor to explain the voltage recovery and aforementioned questions.…”