Large Language Model-Based Intelligent Pre-Design of Lithium-Ion Battery Accelerated Life Tests

View at publisher Summarise with VIRAT
Authors: Jaeyoung Jeong, Gwanghui Shin, Yongsoo Kim
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Purpose: This study proposes an intelligent pre-design method for lithium-ion battery accelerated life tests (ALT) based on large language models (LLMs) operating in a local environment, in order to address risks related to design errors and data security. Methods: A local retrieval-augmented generation (RAG) system, utilizing an open-source LLM and a vector database, derives intelligent pre-design results using literature-based thresholds. The effectiveness of the design is validated by reviewing analytical results from actual datasets to ensure compliance with design requirements. Results: Optimal thresholds for LiCoO2-graphite cells were derived to generate pre-design reports. Design validity was verified through comparisons with actual datasets and supporting literature. High consistency and accuracy were demonstrated across 10 repeated experiments, confirming the practical stability of the proposed approach. Conclusion: The proposed method serves as a practical tool for improving design precision and analytical objectivity. It enhances the efficiency of battery reliability test design by safeguarding technological assets and automating the review of relevant industrial standards.

Fields of Study & Subjects

Battery Modeling and Management Reliability and Maintenance Optimization Advancements in Battery Materials

Publication details

Journal / source
Journal of Applied Reliability
Volume
26
Issue
1
Pages
36–48
Publication date
31 March 2026
Language
EN