摘要
为了及时掌握轮对尺寸信息,从而保证列车正常运行,提出了建立粒子群优化支持向量机模型对轮对尺寸进行预测的方法.介绍了粒子群优化算法(PSO)及支持向量机(SVM)的相关概念,并利用粒子群优化算法能够实现快速全局优化的特点对支持向量机进行参数优化,解决了支持向量机参数选择盲目性的问题.以某城轨列车轮径值为研究对象,建立基于PSO-SVM的轮对尺寸预测模型,对轮径值进行预测分析.结果表明,轮径值预测相关度达到0.94,证实了建立的预测模型在轮对尺寸预测方面的可行性及有效性.
In order to timely master the wheelset size information to ensure the normal operation of urban rail train,a particle swarm optimization-support vector machine(PSO-SVM) model was proposed to forecast the wheelset size.The related concepts of PSO and SVM were introduced,and the parameters for the SVM was optimized with utilizing the feature that the PSO algorithm could realize the rapid global optimization so as to solve the blindness in the parameter selection of SVM.The wheel diameter of a urban rail train was chosen as the research object,the forecasting model of wheelset size based on PSO-SVM was established,and the wheel diameter was forecasted and analyzed.The results show that the prediction correlation of wheel diameter reaches 0.94,which proves the feasibility and effectiveness of established forecasting model in the forecasting of wheelset size.
出处
《沈阳工业大学学报》
EI
CAS
北大核心
2014年第4期411-415,共5页
Journal of Shenyang University of Technology
基金
国家高技术研究发展计划(863)资助项目(2011AA110501)
关键词
预测模型
轮对尺寸
支持向量机
粒子群优化
城轨列车
轮径
安全运营
参数优化
forecasting model
wheelset size
support vector machine
particle swarm optimization
urban rail train
wheel diameter
safe operation
parameter optimization
