Scholarlink

Batteries are fundamental to modern life because they run critical systems and gadgets in various industries, such as emergency response, logistics, and healthcare. Rechargeable battery packs are in greater demand, especially for energy storage and electric cars, emphasizing their significance in the worldwide energy transition. Dong (Wang et al., Microelectronics Reliability, ScienceDirect 78:212–219, 2017) Predicting the battery’s Remaining Useful Life (RUL) is the essential for the maintenance planning and resource management optimization. This work uses cutting-edge Machine Learning (ML) techniques to create a predictive model to calculate RUL based on past battery data. The techniques used included linear regression, complicated algorithms like XGBoost and AdaBoost, and ensemble approaches like Random Forest and Gradient Boosting. With an astounding 99.98% accuracy rate, the XGBoost model proved useful for predicting battery RUL. Important parameters were found to include voltage and discharge. Important criteria that greatly impact battery longevity include discharge and voltage. By reliably predicting the RUL of batteries for fresh, unknown data, the final trained model promotes sustainable battery usage across various applications, improves operational efficiency, and allows for well-informed decision-making.

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

A Novel Approach for Enhancing Battery Reliability in Market Using Machine Learning-Based RUL Prediction

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Ch. Rajendra Babu,
  • Thalla Swapna,
  • Ramisetty Siva Naga Lakshmi,
  • Avanigadda Durga Sankar,
  • Bezawada Naga Venkata Reddy

摘要

Batteries are fundamental to modern life because they run critical systems and gadgets in various industries, such as emergency response, logistics, and healthcare. Rechargeable battery packs are in greater demand, especially for energy storage and electric cars, emphasizing their significance in the worldwide energy transition. Dong (Wang et al., Microelectronics Reliability, ScienceDirect 78:212–219, 2017) Predicting the battery’s Remaining Useful Life (RUL) is the essential for the maintenance planning and resource management optimization. This work uses cutting-edge Machine Learning (ML) techniques to create a predictive model to calculate RUL based on past battery data. The techniques used included linear regression, complicated algorithms like XGBoost and AdaBoost, and ensemble approaches like Random Forest and Gradient Boosting. With an astounding 99.98% accuracy rate, the XGBoost model proved useful for predicting battery RUL. Important parameters were found to include voltage and discharge. Important criteria that greatly impact battery longevity include discharge and voltage. By reliably predicting the RUL of batteries for fresh, unknown data, the final trained model promotes sustainable battery usage across various applications, improves operational efficiency, and allows for well-informed decision-making.