基于PSO混合算法优化BP网络在钢轨磨损量预测中的应用  

Application of BP ANN optimized by hybrid algorithm based on PSO in wear volume prediction of rail steel

作　　者：王平[1] 王彩芸[1] 王文健[1] 刘启跃[1] 

机构地区：[1]西南交通大学牵引动力国家重点实验室摩擦学研究所,四川成都610031

出　　处：《机械设计》2013年第8期15-20,共6页Journal of Machine Design

基　　金：国家自然科学基金资助项目(51174282);国家自然科学基金杰出青年基金资助项目(51025519);国家重点基础研究发展计划资助项目(2011CB711103)

摘　　要：提出基于PSO混合算法对BP网络进行优化,改善了BP网络权阈值求解所面临的局部极值与收敛速度慢的问题。通过赫兹模拟试验方法,在JD-1轮轨模拟试验机上获得BP神经网络训练数据,运用基于PSO混合算法优化BP网络对钢轨磨损量进行拟合。结果表明:基于PSO混合算法优化BP网络对钢轨磨损量数据能够进行极好的拟合,为钢轨磨损量预测提供一种更有效的数据分析途径。Hybrid algorithm based on PSO algorithm is pro-posed in this paper,which makes the local extremum and slows convergence velocity of BP ANN faster.With the Hertz testing simulation method,the experiment investigation on rolling wear of railwheel is performed on JD-1 wheel / rail simulation facilities obtain wear volume as ANN’s training data.Then,PSO hybrid algorithm is applied in the fitting of wear volume data of rail steel.The results show that PSO hybrid algorithm can be fitting for wear volume data of rail steel perfectly,which provides a more effective data analysis approach for prediction rail steel wear volume.

关 键 词：PSO BP神经网络 钢轨 磨损量 

分 类 号：U213.42[交通运输工程—道路与铁道工程]