A multi-agent AI framework for explainable battery system maintenance

Cell Reports Physical Science, vol. 7, pp. 103388

Abstract

The operation and maintenance (O&M) of battery energy-storage systems (BESSs) remain dominated by reactive, expert-dependent diagnostics. Although cell-level inconsistencies can provide early warning signals of degradation and safety risks, the lack of scalable and interpretable decision-support frameworks prevents these signals from being effectively translated into operational actions. Here, we introduce an inconsistency-driven O&M paradigm for large-scale BESSs that systematically transforms routine monitoring data into explainable and decision-oriented guidance via large language model-based semantic reasoning. Using 8 months of field data from an in-service BESS comprising 3,564 cells, we demonstrate how real-world O&M queries are converted into actionable maintenance insights, reducing response time and operational cost by over 80% compared with conventional expert-driven practices. These results establish a scalable pathway for intelligent O&M of BESSs, with direct implications for reliability and cost-effective integration of energy storage into modern power systems.

Authors 5

1. Yijie Wang corresponding

   Shanghai Jiao Tong University

   Affiliation as printed

   Global Institute of Future Technology, Shanghai Jiao Tong University, 800 Dongchuan Road, Minhang District, Shanghai 200240, China

   Key Laboratory of Urban Complex Risk Control and Resilience Governance, Shanghai Jiao Tong University, 800 Dongchuan Road, Minhang District, Shanghai 200240, China

2. Yujie Fu

   Shanghai Jiao Tong University

   Affiliation as printed

   Global Institute of Future Technology, Shanghai Jiao Tong University, 800 Dongchuan Road, Minhang District, Shanghai 200240, China

3. Putai Zhang

   Shanghai Jiao Tong University

   Affiliation as printed

   Global Institute of Future Technology, Shanghai Jiao Tong University, 800 Dongchuan Road, Minhang District, Shanghai 200240, China

4. Weihan Li corresponding Aachen Center for Ageing Junior Professorship for Artificial Intelligence and Digitalization for Batteries Institute for Power Electronics and Electrical Drives (ISEA)

   RWTH Aachen University

   Affiliation as printed

   Center for Ageing, Reliability and Lifetime Prediction of Electrochemical and Power Electronic Systems (CARL), RWTH Aachen University, Campus-Boulevard 89, 52074 Aachen, Germany

   Junior Professorship for Artificial Intelligence and Digitalization for Batteries, Institute for Power Electronics and Electrical Drives (ISEA), RWTH Aachen University, Campus-Boulevard 89, 52074 Aachen, Germany

5. Mian Li corresponding

   Shanghai Jiao Tong University

   Affiliation as printed

   Global Institute of Future Technology, Shanghai Jiao Tong University, 800 Dongchuan Road, Minhang District, Shanghai 200240, China

   Key Laboratory of Urban Complex Risk Control and Resilience Governance, Shanghai Jiao Tong University, 800 Dongchuan Road, Minhang District, Shanghai 200240, China