摘要
为了保证储能系统的安全性和可靠性,本文提出一种新的锂电池剩余寿命预测的方法。该方法采用联想记忆层和权值记忆层都具有递归单元的递归小脑模型神经网络来预测锂电池的剩余寿命。采用马里兰大学的先进寿命周期工程中心的数据集进行验证测试,测试的结果表明,该方法在不同的预测起始点都具有很好的准确性。
In order to ensure the safety and reliability of energy storage system,a new method for predicting the remaining life of lithium battery is proposed in this paper.This method uses recurrent cerebellar model neural network with recursive units in both associative memory layer and weight memory layer to predict the remaining life of lithium battery.Validation tests were performed using a dataset from the University of Maryland’s advanced life cycle engineering center.The test results show that the method has good accuracy at different prediction starting points.
作者
徐智帆
XU Zhifan(State Grid Xiamen Electric Power Supply Company,Xiamen,China,361001)
出处
《福建电脑》
2022年第4期7-11,共5页
Journal of Fujian Computer
关键词
锂电池
递归小脑模型神经网络
剩余寿命
Lithium-ion Battery
Recurrent Cerebellar Model Neural Network
Remaining Useful Life
