便携式医疗设备电池剩余寿命预测算法研究

Research on battery remaining life prediction algorithm for portable medical devices

目的:为精准有效地预测便携式医疗设备的电池剩余寿命,提出一种基于反向传播(back propagation,BP)神经网络和麻雀搜索(sparrow search algorithm,SSA)算法的SSA-BP算法。方法:首先,通过BP神经网络的结构确定权值以及阈值的总数;其次,利用SSA算法优化初始权值和阈值,并赋值给BP神经网络;最后,通过对输入样本的训练获取预测的输出值。选取不同环境温度(4、24、43℃)下的18650型号锂电池数据进行测试,通过平均绝对误差、均方根误差、平均绝对百分比误差验证SSA-BP神经网络算法和BP神经网络算法对医疗设备电池剩余寿命的预测精度。结果:SSA-BP神经网络算法预测医疗设备电池剩余寿命的平均绝对误差、均方根误差、平均绝对百分比误差均低于BP神经网络算法。结论:SSA-BP神经网络算法能够精准有效地对电池的使用寿命进行预测,提高了电池在实际应用中的可靠性。

Objective To propose a SSA-BP algorithm based on the back propagation(BP)neural network and sparrow search algorithm(SSA)to predict battery remaining life accurately.Methods Firstly,the total number of the weights and thresholds was determined with the structure of the BP neural network;secondly,the initial weights and thresholds were optimized using the SSA algorithm and assigned to the BP neural network;and finally,the predicted output values were obtained by training the input samples.The data of 18650 model lithium batteries at different ambient temperatures(4,24,43℃)were selected for testing,and the prediction accuracy of the SSA-BP neural network algorithm and BP neural network algorithm on the remaining life of medical device batteries was verified by the mean absolute error,root mean square error and mean absolute percentage error.Results The SSA-BP algorithm had the average absolute error,root mean square error and mean absolute percentage error lower than those of the BP neural network when used to predict battery remaining life.Conclusion The SSA-BP algorithm can effectively predict battery remaining life,and enhances battery reliability during practical application.