基于CS-DBN的锂电池剩余寿命预测

PREDICTION OF REMAINING USEFUL LIFE OF LITHIUM BATTERIES BASED ON CS-DBN

为了更准确地对锂电池剩余使用寿命进行预测,提出一种基于布谷鸟算法(CS)和深度信念网络(DBN)的预测模型。首先,引进16个影响锂电池RUL的健康因子(HI),通过随机森林(RF)选择出对于剩余寿命预测较为重要的9个HI。随后用CS去寻优深度信念网络模型中隐藏层的参数,通过寻优,建立最优的深度信念网络预测模型。最后,使用马里兰大学所收集的电池数据(CALCE)进行实验,结果表明:所提出的CS-DBN模型的拟合优度高达98%,且与其他模型的预测结果进行对比,具有更小的误差,验证了所提方法的有效性。

In order to predict the remaining service life of lithium batteries more accurately,a prediction model based on cuckoo algorithm(CS)and deep belief network(DBN)is proposed in this paper.Firstly,16 health indicators(HI)that affect the RUL of lithium batteries are introduced,and nine HIs that are more important for the RUL through random forest(RF)are selected.Then the CS is used to optimize the parameters of the hidden layer in the deep belief network model,and the optimal deep belief network prediction model is established through optimization.Finally,the battery data collected by the University of Maryland(CALCE)is used for the experiment.The results show that the goodness of fit of the CS-DBN model proposed in this paper is up to 98%,and compared with the prediction results of other models,it has smaller error,which verifies the effectiveness of the proposed method.