基于组合预测模型的轮轨力连续测试

李奕璠; 林建辉; 刘建新

doi:10.3969/j.issn.0258-2724.2012.04.010

基于组合预测模型的轮轨力连续测试

doi: 10.3969/j.issn.0258-2724.2012.04.010

基金项目:

国家863计划资助项目(2009AA11Z202)

国家自然科学基金资助项目(51075340)

第12届高等院校青年教师基金基础性研究课题(121075)

详细信息

通讯作者:
林建辉(1964-),男,教授,主要研究方向为测控技术、故障诊断、信号分析与处理,E-mail:lin13008104673@126.com

计量
- 文章访问数: 1574
- HTML全文浏览量: 65
- PDF下载量: 467
- 被引次数: 0
出版历程
- 收稿日期: 2011-12-27
- 刊出日期: 2012-08-25

Wheel-Rail Force Continuous Measurement Based on Combinational Forecast Model

摘要

摘要: 为了精确判断车辆的运行状态,提出了一种轮轨力连续测试方法.根据轮轨相互作用的特点,采用阈值判断法从测试数据中提取轮轨力的有效信息.针对轮轨力测试系统的时变性和不确定性,将动态测试序列作为灰色过程处理,提出用灰色理论对轮轨力进行连续测试.为了提高预测精度,结合遗传算法和神经网络对传统的GM(1,1)模型进行改进.建立了10个预测模型分别进行预测,然后将精度较高的预测值输入串联灰色神经网络进行二次预测,以提高预测精度与稳定性.将这10个预测模型应用到轮轨力连续测试中,结果表明:灰色系统、遗传算法与神经网络三者的组合模型具有较高的精度,平均相对误差不超过2%,满足轮轨力连续测试的要求,并且能够降低传感器失效对测试结果的影响.
- 轮轨力 /
- 车轮失圆 /
- 灰色模型 /
- 遗传算法 /
- 神经网络 /
- 组合预测
Abstract: In order to accurately judge vehicle operation state, a wheel-rail force continuous measure method was put forward. Based on the wheel-rail interaction characteristics, the available data of wheel-rail force were extracted from test data by using the threshold value judgmental method. From the uncertainty and time variation of a wheel-rail force measurement system, a dynamic measurement sequence was regarded as a grey process, so the grey theory was used to continuously measure wheel-rail force. In order to improve prediction accuracy, the traditional GM(1,1) model was improved by combining the genetic algorithm and neural network. Ten prediction models were established to predict respectively, and then the predicted values with high accuracy were imported into series grey neural network to predict once again to improve the prediction accuracy and stability. The 10 prediction models were applied to wheel-rail force continuous measurement. The results show that the combination model based on the grey system, genetic algorithm and neural network has a high accuracy, and the average relative error is less than 2%. This combination forecast model can meet the requirement of wheel-rail force continuous measurement and reduce the influence of sensor failures on measurement results.
- wheel-rail force /
- out-of-round wheel /
- grey model /
- genetic algorithm /
- neural network /
- combinational forecast

HTML全文

参考文献(18)

王开云,翟婉明. 纵向压力作用下重载机车与轨道的动态相互作用[J]. 西南交通大学学报,2009,44(1): 7-12. WANG Kaiyun, ZHAI Wanming. Dynamic interaction between heavy locomotive and track under longitudinal force of coupler[J]. Journal of Southwest Jiaotong University, 2009, 44(1): 7-12.

STRATMAN B, LIU Y M, MAHADEVAN S. Structural health monitoring of railroad wheels using wheel impact load detectors[J]. Journal of Failure Analysis and Prevention, 2007, 7(3): 218-225.

REMENNIKOV A M, KAEWUNRUEN S. A review of loading conditions for railway track structures due to train and track vertical interaction[J]. Structural Control and Health Monitoring, 2008, 15(2): 207-234.

刘思峰. 灰色系统理论及其应用[M]. 5版. 北京:科学出版社,2010: 146-168.

张大海,江世芳,史开泉. 灰色预测公式的理论缺陷及改进[J]. 系统工程理论与实践,2002,22(8): 140-142. ZHANG Dahai, JIANG Shifang, SHI Kaiquan. Theoretical defect of grey prediction formula and its improvement[J]. Systems Engineering Theory and Practice, 2002, 22(8): 140-142.

吉培荣,黄巍松,胡翔勇. 灰色预测模型特性的研究[J]. 系统工程理论与实践,2001,21(9): 105-109. JI Peirong, HUANG Weisong, HU Xiangyong. A study on the properties of gray forecasting model[J]. Systems Engineering Theory and Practice, 2001, 21(9): 105-109.

林晓言,陈有孝. 基于灰色-马尔科夫链改进方法的铁路货运量预测研究[J]. 铁道学报,2005,27(3): 15-19. LIN Xiaoyan, CHEN Youxiao. Study on railway freight volume forecast by the grey-Markov chain method[J]. Journal of China Railway Society, 2005, 27(3): 15-19.

WANG C H. Predicting tourism demand using fuzzy times series and hybrid grey theory[J]. Tourism Management, 2004, 25(3): 367-374.

周铭,王洪发. 基于遗传算法的灰色GM(1,1)模型[J]. 南昌大学学报:理科版,2002,12(4): 331-333. ZHOU Ming, WANG Hongfa. Gray model GM(1,1) based on genetic algorithm[J]. Journal of Nanchang University: Natural Science, 2002, 12(4): 331-333.

HSU L C. Forecasting the output of integrated circuit industry using genetic algorithm based multivariable grey optimization models[J]. Expert System with Applications, 2009, 36(4): 7898-7903.

陈淑燕,王炜. 交通量的灰色神经网络预测方法[J]. 东南大学学报:自然科学版,2004,34(4): 541-544. CHEN Shuyan, WANG Wei. Grey neural network forecasting for traffic flow[J]. Journal of Southeast University: Natural Science Edition, 2004, 34(4): 541-544.

PAI T Y, TSAI Y P, LO H M, et al. Grey and network prediction of suspended solids and chemical oxygen demand in hospital wastewater treatment plant effluent[J]. Computer and Chemical Engineering, 2007, 31(10): 1272-1281.

曹建华,刘渊,代悦. 一种基于灰色神经网络的网络流量预测模型[J]. 计算机工程与应用,2008,44(5): 155-157. CAO Jianhua, LIU Yuan, DAI Yue. Network traffic prediction based on grey neural network integrated model[J]. Computer Engineering and Applications, 2008, 44(5): 155-157.

万星,周建中. 改进灰色神经网络模型在电量预测中的应用[J]. 水力发电,2007,33(6): 69-72. WAN Xing, ZHOU Jianzhong. Application of improved grey neural networks model in electricity load forecast[J]. Water Power, 2007, 33(6): 69-72.

翟婉明. 车辆-轨道耦合动力学[M]. 3版. 北京:科学出版社,2007: 147-148.

李奕璠,刘建新,王开云,等. 测力钢轨轮轨力连续输出算法[J]. 交通运输工程学报,2011,11(4): 36-40. LI Yifan, LIU Jianxin, WANG Kaiyun, et al. Wheel/rail force continuous exporting algorithm of instrumented rail[J]. Journal of Traffic and Transportation Engineering, 2011, 11(4): 36-40.

党耀国,刘思峰,刘斌. 以x(1)(n)为初始条件的GM模型[J]. 中国管理科学,2005,13(1): 132-135. DANG Yaoguo, LIU Sifeng, LIU Bin. The GM models that be taken as initial value[J]. Chinese Journal of Management Science, 2005, 13(1): 132-135.

宋颖,杜彦良,孙宝臣. 压电传感技术在轮轨力实时监测中的应用探讨[J]. 振动与冲击,2010,29(1): 228-232. SONG Ying, DU Yanliang, SUN Baochen. Study on wheel/rail interaction force real-time monitoring method based on piezoelectric sensing technology[J]. Journal of Vibration and Shock, 2010, 29(1): 228-232.

施引文献

附加材料(0)

访问统计

点击查看大图

计量

文章访问数: 1574
HTML全文浏览量: 65
PDF下载量: 467
被引次数: 0

基于组合预测模型的轮轨力连续测试

doi: 10.3969/j.issn.0258-2724.2012.04.010

通讯作者: 林建辉(1964-),男,教授,主要研究方向为测控技术、故障诊断、信号分析与处理,E-mail:lin13008104673@126.com

计量

出版历程

Wheel-Rail Force Continuous Measurement Based on Combinational Forecast Model

计量

出版历程

目录

通讯作者:
林建辉(1964-),男,教授,主要研究方向为测控技术、故障诊断、信号分析与处理,E-mail:lin13008104673@126.com