基于PSO-MK-ELM的动车轮对尺寸预测模型

陈紫薇; 张渝; 邱春蓉

基于PSO-MK-ELM的动车轮对尺寸预测模型

西南交通大学物理科学与技术学院, 成都 610031

基金项目:

西南交通大学横向项目(2018H1100)

国家自然科学基金(61471304)

详细信息

作者简介:
陈紫薇,在读硕士研究生;张渝,副教授。

中图分类号: U270.331.1;TP39
计量
- 文章访问数: 92
- HTML全文浏览量: 0
- PDF下载量: 10
出版历程
- 收稿日期: 2019-03-12

Prediction model of EMU wheel set size based on PSO-MK-ELM

School of Physical Science and Technology, Southwest Jiaotong University, Chengdu 610031, China

摘要

摘要: 动车轮对安全尺寸预测为动车安全性评估提供了依据。由于轮对尺寸变化受到运行环境等因素影响的复杂性,提出了一种适用于动车轮对尺寸数据的粒子群优化多核极限学习机(PSO-MK-ELM)预测模型。将多项式核函数和径向基核函数加权构成的多核函数(MK)引入极限学习机中,并采用粒子群优化算法对模型的4个关键参数进行寻优。针对CRH2车型的动车车轮直径数据,通过对比不同算法的预测结果,验证该方法的合理性和准确性。预测结果表明,在动车轮对尺寸数据的预测上,PSO-MK-ELM预测模型能够获取比BP模型、ELM模型和3种常用KELM模型更好的拟合优度、均方差、平均绝对误差和平均绝对百分比误差,验证了模型在动车轮对尺寸预测上的有效性。
- 预测模型 /
- 轮对尺寸 /
- 极限学习机 /
- 多核 /
- 粒子群优化
Abstract: The prediction of safety size of EMU wheel set provides a basis for EMU safety evaluation.Due to the complexity of wheel set size change affected by operating environment and other factors, this paper proposed a particle swarm optimization multi-kernel extreme learning machine (PSO-MK-ELM) prediction model which was suitable for wheel set size data.The multi-kernel (MK)function, which was composed of polynomial kernel function and radial basis kernel function, was introduced into the extreme learning machine, and four key parameters of the model were optimized by particle swarm optimization.According to the wheel diameter data of CRH2 model, the rationality and accuracy of this method were verified by comparing the prediction results of different algorithms.The prediction results show that PSO-MK-ELM model can obtain better goodness of fit, mean square deviation, mean absolute error and mean absolute percentage error than BP model, ELM model and three kinds of commonly used KELM model in the prediction of EMU wheelset size data, which verifies the validity of the model in the prediction of EMU wheelset size.
- prediction model /
- wheel set size /
- extreme learning machine /
- multiple kernel /
- particle swarm optimization

HTML全文

参考文献(13)

[1]	邢宗义,冒玲丽,廖贵玲,等. 基于PSO-SVM模型的城轨列车轮对尺寸预测[J]. 沈阳工业大学学报, 2014, 36(4):411-415.
[2]	曾旗,丁阳春,李邦伟,等. CRH-3动车组横向加速度超限报警与轮对踏面外形尺寸的相关性分析研究[J]. 铁道机车车辆, 2015, 35(6):115-119.
[3]	衷路生,陈立勇,龚锦江. 基于耦合模拟退火优化最小二乘支持向量机的车轮踏面磨耗量预测[J]. 计算机应用研究, 2015(2):397-402.
[4]	何蕾. Health Research of Wheel-Set Based on Data Mining[D]. 成都:西南交通大学, 2018.
[5]	廖贵玲. 城轨列车轮对安全状态分析预测与镟修策略优化方法研究[D]. 北京:北京交通大学, 2014.
[6]	Hua S, Yuan J, Ding W. LS-SVM-Based Prediction Model of Tread Wear Optimized by PSO-GA-LM[C]//International Conference on Cloud Computing & Security. Springer International Publishing, 2016.
[7]	宋坤骏,丁建明. 代价敏感正则化有限记忆多隐层在线序列极限学习机及图像识别应用[J]. 铁路计算机应用, 2018, 27(5):18-22 ,37.
[8]	涂异,汪金能,朱曲平,等. 应用PSO-KELM模型预测水文时间序列[J]. 中国农村水利水电, 2018(7):21-24.
[9]	郑志成,徐卫亚,徐飞,等. 基于混合核函数P S O-LSSVM的边坡变形预测[J]. 岩土力学, 2012, 33(5):145-150.
[10]	Chengzhang Z, Xinwang L, Qiang L, et al. Distance Based Multiple Kernel ELM:A Fast Multiple Kernel Learning Approach[J]. Mathematical Problems in Engineering, 2015, 2015:1-9.
[11]	Huang G B, Zhu Q Y, Siew C K. Extreme learning machine:Theory and applications[J]. Neurocomputing, 2006, 70(1):489-501.
[12]	汪洪桥,孙富春,蔡艳宁,等. 多核学习方法[J]. 自动化学报, 2010, 36(8):1037-1050.
[13]	Zheng X., Zhou G., Ren H., et al. A Rolling Bearing Fault Diagnosis Method Based on Variational Mode Decomposition and an Improved Kernel Extreme Learning Machine[J]. Journal of Vibration and Shock,2017,36(22):22-28.