NGO-BP神经网络在便携式医疗设备电池寿命预测中的应用

Application of NGO-BP Neural Network in Battery Life Prediction of Portable Medical Devices

便携式医疗设备的发展离不开安全高效的电池。精准预测锂电池的荷电状态(state of charge,SOC)可以极大提高电池的可靠性,这对便携式医疗设备来说具有重要意义。针对BP神经网络算法对初始权值和阈值依赖程度高,容易陷入局部最小值等问题,该文采用北方苍鹰算法来优化BP神经网络,并测试了医疗设备在不同的环境温度(4、24、43℃)条件下,18650型锂电池的数据。实验结果表明,北方苍鹰算法能够在不同的温度环境下显著提高BP神经网络的预测精度,实现对电池荷电状态的精准有效预测。

The development of portable medical devices cannot be separated from safe and efficient batteries.Accurately predicting the remaining life of batteries can greatly improve the reliability of batteries,which is of great significance for portable medical devices.This article focuses on the high dependence of the BP neural network algorithm on initial weights and thresholds,as well as its tendency to fall into local minima.The Northern Goshawk Optimization(NGO)algorithm is used to optimize the BP neural network and to test the 18650 lithium battery data under different ambient temperatures(4,24,43°C)typical of medical equipment.The experimental results show that the NGO algorithm can significantly improve the prediction accuracy of the BP neural network under various temperature conditions,achieving accurate and effective prediction of the remaining battery life.