基于BP神经网络的阀控铅酸盐蓄电池劣化程度预测
Impairment degree forecast for valve regulated lead acid battery based on BP neural network
-
摘要: 为了提高对阀控铅酸盐蓄电池劣化程度的预测准确度,构建了一个具有自学习功能的BP神经网络预报模型,使用不同放电深度下的192组数据对BP神经网络进行训练和学习,然后使用训练好的BP神经网络对实时采集到的数据进行预报和分析,预报准确率达93%以上,证明预报模型具有较高的可靠性.Abstract: In order to improve forecast accurancy of impairment degree for valve regulated lead acid battery,a forecast model based on neural network with autonomic learning function was structured.The BP neural network was trained and learned using 192 different discharge degree data,then the real time collection data were forecasted and analyzed using trained BP neural network.The forecast accurancy is above 93%,which proves the forecast model's validity.
-
-
[1]
Rand D A J,Moseley P T,Garche J,et al.Valve-regulated Lead-acid Batteries[M].London:Elsevier,2004:8-12.
-
[2]
朱松然.铅酸蓄电池实用手册[M].北京:机械工业出版社,1992:22-46.
-
[3]
刘百芬,程海林.一种新型的蓄电池内阻测量方法的研究及实现[J].仪表技术与传感器,2004,40(5):49.
-
[4]
韩团军.基于神经网络的铅酸蓄电池剩余容量预测[J].陕西理工学院学报,2008,24(4):26.
-
[5]
舒服华.基于最小二乘支持向量机的电池剩余电量预测[J].电源技术,2008,32(7):452.
-
[1]
计量
- PDF下载量: 28
- 文章访问数: 830
- 引证文献数: 0