基于改进K-means聚类算法的储能电池健康状态预测模型研究
Power Equipment Maintenance Model Based on Artificial Intelligence Technology
谭程凯1
作者信息
- 1. 国网浙江省电力有限公司杭州供电公司,浙江杭州 310000
- 折叠
摘要
本研究通过分析储能电池容量和电阻变化来评估电池健康状态(State of Health,SOH),使用集合经验模态分解技术提取振动信号特征.采用改进的K-means聚类算法对信号特征进行分类,实现对电池SOH的预测.实验表明,文章提出的算法能准确预测电池SOH,在 600 次循环使用后,预测值与真实状态相差仅 1%,预测误差维持在2.6%,显示出算法在复杂状态下的高效性和可靠性.该研究为电力设备的智能化维护提供了新的视角和方法,有望提高电力系统的运行效率.
Abstract
This study evaluates the State of Health(SOH)of energy storage batteries by analyzing their capacity and resistance changes,and extracts vibration signal features using ensemble empirical mode decomposition technology.Using an improved K-means clustering algorithm to classify signal features and achieve prediction of battery SOH.The experiment shows that the algorithm proposed in the article can accurately predict battery SOH.After 600 cycles of use,the predicted value differs from the true state by only 1%,and the prediction error is maintained at 2.6%,demonstrating the efficiency and reliability of the algorithm in complex states.This study provides a new perspective and method for the intelligent maintenance of power equipment,which is expected to improve the operational efficiency of the power system.
关键词
储能电池/设备性能/健康状态(SOH)/电力系统Key words
energy storage battery/equipment performance/State of Health(SOH)/power system引用本文复制引用
出版年
2024
NETL
NSTL
万方数据