基于遗传算法的BP神经网络蓄电池寿命预测研究  

Research on Battery Life Prediction of BP Neural Network Based on Genetic Algorithm

作　　者：吴海洋 缪巍巍 郭波 吕顺利[2] 吴昊 滕欣元 WU Haiyang;MIAO Weiwei;GUO Bo;LV Shunli;WU Hao;TENG Xinyuan(State Grid Jiangsu Power Company,Nanjing 210000;NARI Group(State Grid Electric Power Research Institute), Nanjing 210000;Information and Communication Branch,State Grid Qinghai Electric Power Co.,Ltd.,Xining 810000;Changsha University of Technology,Changsha 410000)

机构地区：[1]国网江苏省电力公司,南京210000 [2]南瑞集团(国网电力科学研究院),南京210000 [3]国网青海省电力有限公司信息通信分公司,西宁810000 [4]长沙理工大学,长沙410000

出　　处：《计算机与数字工程》2019年第5期1275-1278,共4页Computer & Digital Engineering

摘　　要：论文基于电网蓄电池的充放电实验数据,建立了一种基于遗传算法的神经网络模型,实现了蓄电池寿命预测,提升了预测准确度5.97%,分析了蓄电池最佳运行温度和型号差异,指导了蓄电池运维检修和状态监控,有效支撑了电池系统的安全运行监控、健康状态管理。Based on the data of charging and discharging of the grid,a neural network model based on genetic algorithm is es. tablished to realize the battery life prediction and improve the prediction accuracy of 5.97%. The optimal running temperature and model difference of the battery are analyzed. Dimensional maintenance and status monitoring is guided,the safe operation of the bat. tery system monitoring,health management is supported effectively.

关 键 词：蓄电池 寿命预测 BP神经网络 遗传算法改进 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]