Scholarlink

This paper introduces a robust methodology for predicting the State of Health (SOH) of battery utilizing the LightGBM gradient-boosting algorithm. Through an extensive analysis of battery data collected from diverse sources, it showcases the effectiveness of the approach used. The methodology encompasses critical steps such as data pre-processing, feature selection, hyperparameter tuning, model evaluation, and visualization. In this paper, the results affirm 90.69 high accuracy of LightGBM in predicting battery SOH, establishing it as a valuable tool for battery management and diagnostics.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

EV Lithium-Ion Battery SOH Estimation Based on LightGBM Model

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Mayur More,
  • Jayesh Sarode,
  • Amey Panchbhayye,
  • Govind Sharma,
  • Smita Bhagwat,
  • Nilesh Gawali

摘要

This paper introduces a robust methodology for predicting the State of Health (SOH) of battery utilizing the LightGBM gradient-boosting algorithm. Through an extensive analysis of battery data collected from diverse sources, it showcases the effectiveness of the approach used. The methodology encompasses critical steps such as data pre-processing, feature selection, hyperparameter tuning, model evaluation, and visualization. In this paper, the results affirm 90.69 high accuracy of LightGBM in predicting battery SOH, establishing it as a valuable tool for battery management and diagnostics.