基于ALO-SVR的锂离子电池剩余使用寿命预测

Remaining Useful Life Prediction of Lithium-ion Batteries Based on Support Vector Regression Optimized and Ant Lion Optimizations

锂离子电池(Lithium-ion batteries,LIBs)的剩余使用寿命(remaining useful life,RUL)预测在电池故障预测与健康管理(prognostics and health management,PHM)中起着十分重要的作用。准确预测电池RUL可以提前对存在安全隐患的电池进行维护和更换,以确保储能系统安全可靠。文章提出一种基于蚁狮优化和支持向量回归(ant lion optimization and support vector regression,ALO-SVR)的方法,可有效提高锂离子电池RUL预测的准确性。SVR方法在处理小样本数据和时间序列分析上具有优势,但SVR方法在内核参数选择上存在困难。因此,文章利用ALO算法优化SVR核参数,随后采用PCoE(NASA ames prognostics center of excellence)和CALCE(center for advanced life cycle engineering)电池数据集对所提方法进行仿真验证。通过对比SVR方法,ALO-SVR方法可以提供更精确的电池RUL预测结果,能有效提高锂离子电池剩余使用寿命预测的准确性和鲁棒性。

Remaining useful life(RUL)prediction of Lithium-ion batteries(LIBs)plays an important role in battery prognostics and health management(PHM).Accurate prediction of RUL can maintain and replace the batteries with potential safety hazards in advance to ensure the safety and reliability of the energy storage system.A method based on ant lion optimization and support vector regression(ALO-SVR)was proposed,which can improve the accuracy of RUL prediction of LIBs.Although the SVR method has advantages in processing small samples and time series analysis,but it has problems in the selection of kernel parameter.Thus,the ALO algorithm was utilized to optimize the SVR kernel parameters.Experimental data simulations were performed using NASA Ames Prognostics center of excellence(PCoE)and center for advanced life cycle engineering(CALCE)battery datasets to verify the proposed method.Compared with the SVR method,the ALO-SVR method can provide more accurate RUL prediction results,effectively improve the accuracy and robustness of RUL prediction of LIBs.