Research on the prediction algorithm of tread wear for locomotive wheels based on GA-ridge regression analysis

FANG Xin; LIU Tong; CHENG Yaping; SUN Yuduo; WANG Feier

doi:10.13890/j.issn.1000-128X.2023.06.009

您当前的位置：

首页 >

文章列表页 >

Research on the prediction algorithm of tread wear for locomotive wheels based on GA-ridge regression analysis

Railway Rolling Stock | 更新时间：2024-08-02

- Research on the prediction algorithm of tread wear for locomotive wheels based on GA-ridge regression analysis
- Electric Drive for Locomotives Issue 6, Pages: 71-78(2023)
- 作者机构：
  
  1.中国铁路上海局集团有限公司上海机辆段，上海 200070
  2.中国铁道科学研究院集团有限公司金属及化学研究所，北京;100081
- 作者简介：
- 基金信息：
- DOI：10.13890/j.issn.1000-128X.2023.06.009
  CLC： U260.331⁺.1
- Published：10 November 2023，
  
  Received：21 July 2023，
  
  Revised：06 September 2023，
- 稿件说明：
扫描看全文
方鑫, 刘通, 程亚萍, 等. 基于GA-岭回归分析的机车车轮踏面磨耗量预测算法研究[J]. 机车电传动, 2023(6): 71-78.

FANG Xin, LIU Tong, CHENG Yaping, et al. Research on the prediction algorithm of tread wear for locomotive wheels based on GA-ridge regression analysis[J]. Electric drive for locomotives,2023(6): 71-78.
方鑫, 刘通, 程亚萍, 等. 基于GA-岭回归分析的机车车轮踏面磨耗量预测算法研究[J]. 机车电传动, 2023(6): 71-78. DOI： 10.13890/j.issn.1000-128X.2023.06.009.

FANG Xin, LIU Tong, CHENG Yaping, et al. Research on the prediction algorithm of tread wear for locomotive wheels based on GA-ridge regression analysis[J]. Electric drive for locomotives,2023(6): 71-78. DOI： 10.13890/j.issn.1000-128X.2023.06.009.

摘要

车轮踏面磨耗量是评价机车运行安全的重要参数，但多数车轮运维现场的条件尚不能对踏面磨耗量及时、准确地进行监测。为了解决上述问题，文章提出了基于“GA-岭回归”分析的机车车轮踏面磨耗量预测算法（简称“GA-岭回归”预测算法）。“GA-岭回归”预测算法分为数据前处理和数据预测分析2部分。对于数据前处理，首先依据不同的测量方式对采集到的踏面磨耗量数据进行分类，基于车轮的实际运维情况，分析不同类型数据的特点；随后以镟修周期作为数据划分标准，对分类后的数据进行切片处理；最后采用相关标准和主成分分析法对相应的动态测量数据进行清洗、降噪。对于数据预测分析，首先划分数据集，进行数据整合，创建训练集数据的时间滑动窗口；随后采用岭回归算法对训练集数据进行回归分析训练，并结合遗传算法和验证集数据进行模型参数的调优，以提高预测准确性。基于测试集数据，分别采用传统预测算法、岭回归线性预测算法和“GA-岭回归”预测算法，对3类预测算法的预测效果进行对比分析；随后采用相同的测试方法，扩大车轮样本的数量，继续进行预测效果的对比分析。测试结果表明，采用“GA-岭回归”预测算法的预测误差和误差标准差均相对较低。经分析可知，“GA-岭回归”预测算法具有较高的预测精度，同时可保证更好的预测稳定性。

Abstract

Wheel tread wear is an important parameter to evaluate the operational safety of locomotives

yet timely and accurate monitoring is often lacking at wheel operation and maintenance sites. To this end

this paper proposed a prediction algorithm of tread wear for locomotive wheels based on GA-ridge regression analysis (hereinafter referred to as the "GA-ridge regression” prediction algorithm). This algorithm consisted of two steps: data pre-processing and data-based prediction analysis. In the first step

collected tread wear data was classified according to different measurement methods

and characteristics of different data types were analyzed considering the actual operation and maintenance of wheels. The classified data was then sliced using the profiling cycle as the data partitioning criterion

followed by cleaning and noise reduction of the corresponding dynamic measurement data by relevant criteria and principal component analysis. In the second step

data was integrated into datasets

and a time-sliding window was created for the training set data. The ridge regression algorithm was used to train the training set data for regression analysis

and the model parameters were tuned using a combination of the genetic algorithm and the validation set data to improve the prediction accuracy. The test set data was used for prediction by the traditional prediction algorithm

ridge regression linear prediction algorithm

and GA-ridge regression prediction algorithm respectively to compare and analyze their prediction effects. Additionally

a comparative analysis was conducted using the same evaluation method and sample wheels in an expanded size to further assess the prediction effects. The results indicate relatively lower prediction errors and standard deviations of errors when using the GA-ridge regression prediction algorithm. This research concludes that the GA-ridge regression prediction algorithm provides higher prediction accuracy and better prediction stability.

关键词

机车车轮车轮踏面磨耗量预测主成分分析岭回归遗传算法

Keywords

locomotive wheelswheel tread wear predictionprincipal component analysisridge regressiongenetic algorithm

references

杨艳丽, 孙传喜, 张军, 等. 我国机车车辆车轮磨耗型踏面外形及设计方法[J]. 内燃机车, 2011(1): 6-9.

YANG Yanli, SUN Chuanxi, ZHANG Jun, et al. Review of profile and design of all kinds of domestic worn profile treads for locomotive and rolling stock[J]. Diesel locomotives, 2011(1): 6-9.

韩鹏, 张卫华. 高速列车轮对磨耗统计规律及预测模型[J]. 机械工程学报, 2016, 52(2): 144-149.

HAN Peng, ZHANG Weihua. Prediction model and verification of wheel wear in high-speed trains[J]. Journal of mechanical engineering, 2016, 52(2): 144-149.

王红兵, 李艺, 李国芳, 等. 高速车辆车轮踏面磨耗预测及系统参数影响分析[J]. 机械科学与技术, 2022, 41(5): 786-794.

WANG Hongbing, LI Yi, LI Guofang, et al. Prediction of wheel tread wear of high speed vehicles and analysis of influence of system parameters[J]. Mechanical science and technology for aerospace engineering, 2022, 41(5): 786-794.

常崇义, 王成国, 金鹰. 基于三维动态有限元模型的轮轨磨耗数值分析[J]. 中国铁道科学, 2008, 29(4): 89-95.

CHANG Chongyi, WANG Chengguo, JIN Ying. Numerical analysis of wheel/rail wear based on 3D dynamic finite element model[J]. China railway science, 2008, 29(4): 89-95.

钟绍林, 秦梦瑶, 廖时元, 等. 基于数据拟合的铁路车站旅客最高聚集人数计算研究[J]. 铁路计算机应用, 2022, 31(8): 1-6.

ZHONG Shaolin, QIN Mengyao, LIAO Shiyuan, et al. Calculation of maximum number of gathering passengers in railway station based on data fitting[J]. Railway computer application, 2022, 31(8): 1-6.

张贺, 范梦萱. 基于Lasso回归模型的青岛海洋经济和海洋产业分析[J]. 海洋开发与管理, 2022, 39(8): 22-28.

ZHANG He, FAN Mengxuan. The marine economy and marine industry in Qingdao based on Lasso regression model[J]. Ocean development and management, 2022, 39(8): 22-28.

李宏伟, 赵杨坤. 350 km/h复兴号动车组制动闸片在服役过程中的磨损行为及其使用寿命预测[J]. 铁道机车车辆, 2021, 41(2): 22-27.

LI Hongwei, ZHAO Yangkun. Wear performance and life prediction of brake pad in service process of 350 km/h high-speed train[J]. Railway locomotive & car, 2021, 41(2): 22-27.

杨晓炳, 闫泽鹏, 尹升华, 等. 基于GA-SVM的钢渣基胶凝材料开发及料浆配比优化[J]. 工程科学学报, 2022, 44(11): 1897-1908.

YANG Xiaobing, YAN Zepeng, YIN Shenghua, et al. Development of steel-slag-based cementitious material and optimization of slurry ratio based on genetic algorithm and support vector machine (GA-SVM)[J]. Chinese journal of engineering, 2022, 44(11): 1897-1908.

程中国. 地铁车辆轮对外形尺寸在线检测系统[J]. 城市轨道交通研究, 2021, 24(9): 228-231.

CHENG Zhongguo. Online detection system of metro vehicle wheelset profile size[J]. Urban mass transit, 2021, 24(9): 228-231.

颜湘武, 李君岩. 基于主成分分析法的直驱式风电场分群方法[J]. 电力系统保护与控制, 2020, 48(5): 127-133.

YAN Xiangwu, LI Junyan. Grouping method of direct drive wind farm based on principal component analysis[J]. Power system protection and control, 2020, 48(5): 127-133.

张晓英, 吴宏强, 舒子江, 等. 基于PCA和改进ABC-K聚类算法的双馈机组风电场等值建模[J]. 电气工程学报, 2023, 18(1): 201-210.

ZHANG Xiaoying, WU Hongqiang, SHU Zijiang, et al. Equivalent modeling of DFIG wind farm based on PCA and improved ABC-K clustering algorithm[J]. Journal of electrical engineering, 2023, 18(1): 201-210.

VASWANI N, NARAYANAMURTHY P. Static and dynamic robust PCA and matrix completion: a review[J]. Proceedings of the IEEE, 2018, 106(8): 1359-1379.

李雪. 一种基于正态分布密度函数的模糊查询方法[J]. 计算机技术与发展, 2018, 28(9): 1-6.

LI Xue. A fuzzy matching method based on normal distribution density function[J]. Computer technology and development, 2018, 28(9): 1-6.

王巍, 陈崇双, 周宏宇, 等. 基于KS检验的铁路车站日常货运量预测[J]. 综合运输, 2018, 40(12): 93-96.

WANG Wei, CHEN Chongshuang, ZHOU Hongyu, et al. Daily freight volume prediction of railway station based on KS test[J]. China transportation review, 2018, 40(12): 93-96.

何小年, 段凤华. Python在统计学课程实训中的应用探索[J]. 软件, 2021, 42(9): 32-34.

HE Xiaonian, DUAN Fenghua. Exploration on the application of Python in the practical training of statistics course[J]. Computer engineering & software, 2021, 42(9): 32-34.

孟建军, 潘彦龙, 陈晓强, 等. 基于灰色BP神经网络的高速列车轴箱轴承温度预测方法[J]. 轴承, 2022(4): 77-82.

MENG Jianjun, PAN Yanlong, CHEN Xiaoqiang, et al. Prediction method for temperature of axle box bearings for high speed train based on grey BP neural network[J]. Bearing, 2022(4): 77-82.

朱旺, 毛宝俊, 谢强. 1 100 kV特高压变压器套管震后力学性能快速评估方法[J]. 高电压技术, 2022, 48(12): 4904-4914.

ZHU Wang, MAO Baojun, XIE Qiang. Fast evaluation method on post-earthquake mechanical performance of 1 100 kV UHV transformer bushing[J]. High voltage engineering, 2022, 48(12): 4904-4914.

刘恩江, 宋云胜, 梁吉业. 基于数据划分的核岭回归加速算法[J]. 中国科学技术大学学报, 2018, 48(4): 284-289.

LIU Enjiang, SONG Yunsheng, LIANG Jiye. An accelerator for kernel ridge regression algorithms based on data partition[J]. Journal of university of science and technology of China, 2018, 48(4): 284-289.

马砺, 张鹏宇, 郭睿智, 等. 巷道火灾密闭过程烟气温度预测的GA-SVM模型[J]. 中国矿业大学学报, 2021, 50(4): 641-648.

MA Li, ZHANG Pengyu, GUO Ruizhi, et al. GA-SVM model for prediction flue gas temperature of roadway fire under sealing process[J]. Journal of China university of mining & technology, 2021, 50(4): 641-648.

薛赛, 贺青川, 潘骏, 等. 基于GA-SVM的永磁同步电机动态偏心故障诊断[J]. 组合机床与自动化加工技术, 2022(9): 99-103.

XUE Sai, HE Qingchuan, PAN Jun, et al. Research on dynamic eccentricity fault diagnosis method of permanent magnet synchronous motor based on GA-SVM[J]. Modular machine tool & automatic manufacturing technique, 2022(9): 99-103.

Views

下载量

CSCD

CNKI被引量

Alert me when the article has been cited

提交

Tools

Publicity Resources

A study on life assessment of metro cowcatcher based on multi-axis vibration environment reconstruction

Train adaptive energy saving strategy based on iterative induced genetic algorithm

Optimization design on process parameters of copper wire bonding for power modules

Fault diagnosis technology for three-level inverter based on ICEEMDAN-FE and SVM

Research on IGBT Sequentially Prediction Algorithm Based on Improved Wavelet Neural Network

Related Author

LIANG Shulin

CHI Maoru

LIU Yang

WU Xingwen

ZHENG Yuhao

ZHANG Zhengfang

SHI Ke

MEI Wenqing

Related Institution

School of Mechanical Engineering, Southwest Jiaotong University

State Key Laboratory of Rail Transit Vehicle System, Southwest Jiaotong University

Zhuzhou CRRC Times Electric Co., Ltd.

College of Electronic Engineering (College of Artificial Intelligence), South China Agricultural University

Coresing Semiconductor Technology Co., Ltd.

⁰