ISSN 1008-5548

CN 37-1316/TU

Last Issue

Applications of artificial intelligence in lithium‑ion batteries research

CHEN Yanan1 , WANG Yujie2

1. School of Materials Science and Engineering, Tianjin University, Tianjin 300072, China;

2. College of Resource and Environment, Baoshan University, Baoshan 678000, China


Abstract

Significance To develop high-performance lithium-ion batteries, this paper reviews and analyzes the applications of artificial intelligence(AI) technologies in lithium-ion batteries,promoting the innovation and development of lithium-ion battery technolo-gies.

Progress This work provides a comprehensive overview of AI technologies used in lithium-ion batteries (LIBs),covering descriptive, predictive, and prescriptive applications, as well as their core machine learning (ML) components,including artificial neural networks (ANNs), support vector machines (SVMs), logistic regression, partial least squares (PLS) regression, and random forest (RF) algorithms. First, by exploring hidden statistical patterns within high-dimensional data, machine learning can efficiently and accurately obtain the composition-structure-performance relationships in LIB materials.This capability guarantees the batteries’ operational safety and facilitates efficient battery management. The crystal structure of the electrode material determines the intrinsic physical and chemical properties of batteries.Based on this structure-property relationship, feature engineering in ML can identify key conditional attributes, which are then used to train models that establish relationships between these conditional factors and decision attributes.The trained models can subsequently predict battery properties such as voltage, capacity, and ionic conductivity. The selection of appropriate descriptors and models isalso a key step in achieving the accurate prediction of material properties.However, the relationships between selected descriptors and target properties are typically complex and nonlinear. Therefore, substantial datasets are required to effectively train the ML models. In the reverse design approach, where material properties serve as the inputs and structure and composition as the outputs, success depends on three factors: 1) identifying descriptors closely related to target properties of the material,2) establishing accurate models between descriptors and target properties,and 3) experimental synthesis and validation. Although AI shows great potential for reverse material design,several challenges remain,including the mismatch between experimental validation cycles and algorithm iteration speeds, limited descriptor universality for complex systems, and the lack of closed-loop data feedback mechanisms. These limitations indicate that closed-loop reverse material design still has a long way to go. Furthermore, accurate prediction of battery parameters, such as capacity, state of health (SOH), service life, and remaining charge,is crucial for improving battery performance, extending lifespan, and reducing costs. ML models such as SVMs and RF algorithms in AI approaches overcome the limitations of traditional empirical and statistical prediction methods.These AI-based approaches are able to accurately cope with nonlinear conditions arising from complex working scenarios and battery aging effects.Furthermore, through deep learning techniques, models such as convolutional neural networks (CNNs)can effectively extract and utilize time-series features for improved predictions. Moreover, LIB manufacturing involves complex processes covering material preparation, electrode manufacturing, battery assembly, and formation testing. Traditional production methods often rely on manual operations and static controls, leading to inefficiency and product inconsistency. The introduction of AI technologies has revolutionized lithium battery manufacturing, emerging as a key driving force for higher production efficiency, lower costs, and better product quality. However, successful implementation of AI-assisted industrial manufacturing still requires continued advancements in terms of sensor development, digital-physical world integration infrastructure, and accurate battery health state estimation. Additionally, accurate real-time monitoring of battery parameters, such as temperature, charge/discharge rates, cycle count, and environmental conditions,is critical for ensuring battery safety, extending lifespan, and optimizing performance. Traditional monitoring methods often rely on one-dimensional measurements of voltage, current, and temperature, making it difficult to capture the complex dynamic processes within batteries. AI technologies bring new solutions through powerful data processing, machine learning, and prediction. Despite these benefits, challenges remain in terms of data quality, model interpretability, computational resources, and practical applications. Finally, charge or discharge control and thermal management during battery operation directly impact its efficiency, safety, lifespan, and overall performance. Traditional methods based on fixed rules and simple algorithms cannot address the various complexities and uncertainties in battery operation. AI technologies,with their excellent data processing, machine learning, and optimization, enable more sophisticated battery system management. As AI technologies and battery management systems continue to develop, future research directions may focus on intelligent control strategies, refined management,and personalized battery management solutions.

Conclusions and Prospects AI has demonstrated significant potential to upgrade manufacturing quality and efficiency while accelerating the research and development of LIB technologies. However, persistent challenges remain in four critical domains,i.e., data quality and availability, model performance, computational resource, and practical implementation. Future research endeavors should focus on several key priority areas:acquiring, sharing, and standardizing high-quality datasets, improving model interpretability and generalizability, integrating and enhancing other technologies,expanding AI applications to new battery systems, and fostering interdisciplinary cooperation and development.

Keywords: artificial intelligence; lithium-ion battery; battery performance;material development; battery life monitoring


Get Citation:CHEN Yanan, WANG Yujie. Applications of artificial intelligence in lithium‑ion batteries research[J]. China Powder Science and Technology, 2026, 32(3): 1-13.

Received: 2024-12-31 .Revised: 2025-04-11,Online: 2025-08-24.

Funding Project:国家自然科学基金项目, 编号: 92372107; 国家重大基础研究项目, 编号: 52171219。

First Author:陈亚楠(1990—),男,研究员,博士,博士生导师,中国科协青年托举人才,研究方向为高通量筛选与数据获取。E-mail:yananchen@tju.edu.cn。

Corresponding Author:汪玉洁(1986—),男,教授,博士,研究方向为功能材料合成。E-mail:wangyujieufo@163.com。

DOI:10.13732/j.issn.1008-5548.2026.03.006

CLC No:TQ152;O646.21;TB4                 Type Code: A

Serial No:1008-5548(2026)03-0001-13