基于ELM锂离子电池RUL预测优化方法研究

Research on RUL Predictive Optimization Method Based on ELM Lithium-Ion Battery

针对传统的极限学习机ELM(Extreme Learning Machine)算法对锂离子电池剩余使用寿命RUL(Remaining Useful Life)的预测效果不准确等问题,提出通过考察循环次数基础数据导入值对预测结果的影响,及通过集成度调整即前期降低算法RUL估计的频率,后期提高算法集成度和RUL估计的频率,进一步提高锂离子电池RUL预测的准确性。结果表明该方法具有测试时间短和误差小等优点,可为锂离子电池检测机构及生产企业提供一种更加快捷及低成本的电池剩余使用寿命或循环寿命测试方案。

In view of the inaccurate prediction effect of the traditional Extreme Learning Machine(ELM)algorithm on the Remaining Useful Life(RUL)of lithium-ion battery,this paper proposes to investigate the influence of the basic data import value of the number of cycles on the prediction result.Through integration adjustment,the frequency of RUL estimation is reduced in the early stage,and the frequency of algorithm integration and RUL estimation is increased in the later stage,so as to further improve the accuracy of RUL prediction of lithium-ion batteries.The results show that this method has the advantages of short test time and small error,and can provide a more rapid and lowcost testing scheme for the remaining service life or cycle life of lithium-ion battery.