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.

Lithium battery state of health (SOH) is a key parameter to characterize the actual battery life. SOH cannot be directly measured. In order to further improve the accuracy of SOH estimation of lithium batteries, a model combining incremental capacity analysis (ICA) and bidirectional long- and short-term memory (Bi-LSTM) neural networks based on health characteristic parameters is proposed to predict the SOH of lithium-ion batteries. First, the health characteristic parameters are initially selected from the lithium battery charging curve, and the health characteristics are extracted by the Pearson correlation coefficient, including the charging time of constant current, charging time of constant voltage, voltage change rate from 300 s to 1000 s, 200s of voltage per cycle at a time. Second, ICA was used to deeply mine the deep associations related to SOH and the peaks of IC curves and their corresponding voltages were extracted as additional inputs to the model. Then, Bi-LSTM is used to form a combined SOH estimation model through adaptive weighting factors. Finally, the verification is based on the 5th battery parameters of the NASA lithium battery data set. The experimental results show that the proposed combined model reduces the mean square error by 55.17%, 49.28%, and 41.47%, respectively, compared with single models such as BP neural network (BPNN), LSTM, and gated recurrent neural network (GRU).

Summary The state of health (SOH) of the lithium‐ion battery (LIB) is a key parameter of the battery management system. Due to the complex internal electrochemical properties of LIBs and the uncertain external working environment, it is difficult to achieve accurate SOH determination. In this paper, we propose a new SOH estimation method using a directed acyclic graph (DAG) structure based on incremental capacity analysis and empirical mode decomposition (EMD), and finally with gated recurrent unit (GRU) for fitting. First, we combine IC curves and real features into the input feature map and use EMD to separate out high‐frequency capacity regeneration fluctuations. Then, the feature maps are input into the DAG‐GRU structure to fit multiple EMD decomposition functions and build SOH prediction models, which are compared with different neural network prediction models. The prediction method simplifies the prediction process, does not need to select complex health indicators as features, and has the ability to capture the fluctuations of capacity regeneration, and can fit the fluctuations in the capacity decay curve with high precision, this integrated multi‐linear model takes into account accuracy and computational efficiency, reduces manual subjective operations, and uses artificial intelligence to complete most of the work, which is one of the important directions in future SOH research. The experimental results show that using the method proposed in this paper, the minimum mean square error and mean absolute error of SOH are reduced to 0.65‰ and 1.61%, respectively, and it also possesses excellent generalization ability.

No abstract

No abstract