改进梯度下降BP算法在地下水位预测中的应用  

Application of Improved Gradient Descent by BP Algorithm to Groundwater Level Forecast

作　　者：梁斌梅[1,2] 

机构地区：[1]广西大学数学与信息科学学院,南宁530004 [2]四川大学计算机学院,成都610065

出　　处：《煤炭技术》2009年第11期144-146,共3页Coal Technology

基　　金：广西教育厅科研项目资助(批准号:[2006]026)

摘　　要：本文给出了BP神经网络预测模型的原理,分析了标准BP算法缺陷,通过改变学习率和增加动量项改进BP算法。用改进的算法预测某地地下水位,并对训练过程进行优化,实验结果表明,改进的BP神经网络能有效地提高地下水位预测的速度和精度,比标准BP算法预测性能有较大改善。This paper gives the principles of BP neural network forecast model .After analyzing the limitations of the standard BP algorithm, improves BP algorithm by modifying the learning rote and adding a momentum item. To forcast the groundwater level in a certain place by the improved BP algorithm, and optimize the training process. The experimental results show that the improved BP neural network can effectively increase speed and aeeumey of the groundwater level forecast, has a great improvement in performance compared with the standard BP algorithm.

关 键 词：神经网络 BP算法 预测 

分 类 号：TD17[矿业工程—矿山地质测量]