Scholarlink

We evaluated the performance of four machine learning algorithms to identify the performance of lithium-ion batteries, considering temperature variations. The training and test sets were performed for 60/40, 70/30, 80/20 and cross validation with 10 folds. Four algorithms: Naïve Bayes, Multi-Layer Perceptron, AdaBoost and JRip were implemented in the Waikato Environment for Knowledge Analysis framework. Based on the results, it was observed that the AdaBoost algorithm was the best at identifying lithium-ion battery performance with respect to temperature.

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

State-of-Health Identification in Lithium-Ion Batteries Using Machine Learning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Benjamín-Arturo Pérez-Peláez,
  • Irahan-Otoniel José-Guzmán,
  • Eddy Sánchez-DelaCruz

摘要

We evaluated the performance of four machine learning algorithms to identify the performance of lithium-ion batteries, considering temperature variations. The training and test sets were performed for 60/40, 70/30, 80/20 and cross validation with 10 folds. Four algorithms: Naïve Bayes, Multi-Layer Perceptron, AdaBoost and JRip were implemented in the Waikato Environment for Knowledge Analysis framework. Based on the results, it was observed that the AdaBoost algorithm was the best at identifying lithium-ion battery performance with respect to temperature.