基于BP神经网络的电池电解液密度预测

发布时间：2018-05-01 17:21

本文选题：电池 + BP神经网络　；参考：《电源技术》2017年11期

【摘要】：为了对电池电解液密度进行预测,建立了BP神经网络模型,用电池充放电试验数据对其进行了训练和检验。利用训练后的神经网络模型进行了电池电解液密度的预测,预测值与实测值的最大误差值为0.020 9 g/cm3,均方根误差值为0.004 0 g/cm3左右。结果表明,BP神经网络方法可以满足预测精度要求,从而可用于建立电池剩余电量实时监测系统,降低电池维护工作量并延长电池的使用寿命。
[Abstract]:In order to predict the density of battery electrolyte, a BP neural network model was established and trained and tested with battery charge and discharge test data. Using the trained neural network model, the density of battery electrolyte is predicted. The maximum error between the predicted value and the measured value is 0.020 9 g / cm ~ 3, and the root mean square error is about 0.004 g/cm3. The results show that the BP neural network method can meet the requirement of prediction precision, and it can be used to establish the real-time monitoring system of battery residual quantity, reduce the battery maintenance workload and prolong the battery service life.
【作者单位】：武汉船用电力推进装置研究所;
【分类号】：TM912

【相似文献】