铁路轨道不平顺预测模型研究与应用  

Research and Application of Track Irregularity Prediction Model

作　　者：张念[1] 朱焱[1] 王小敏[1] 郭进[1] 

机构地区：[1]西南交通大学信息科学与技术学院,成都611756

出　　处：《铁道标准设计》2015年第9期56-63,共8页Railway Standard Design

基　　金：中国铁路总公司科技研究开发计划课题(2013X012-A-1;2013X012-A-2)

摘　　要：在保障列车行车安全的前提下提高维修效率和减少经济开支具有重要意义。为此,利用综合轨道检测车检测的历史轨道不平顺动态检测数据TQI值进行科学合理的分析,建立一种基于数据选择向量的非等时距灰色模型和神经网络理论相结合的预测方法,对实际线路轨道不平顺值进行预测,相对误差分别为2.63%、2.516%和2.025%。将预测模型应用在年度轨道状态最优综合维修计划的编排中,以养护维修时间和维修地点为决策变量,以年度轨道不平顺平均值最小为目标函数,在考虑了一系列约束函数的情况下,建立了利用遗传算法求解最优解的辅助决策模型。实验结果表明,该方法提高了预测精度,具有较好的实用性,能够快速地编排出线路的年度养护计划。It is significant to improve the maintenance efficiency and reduce the economic costs on the promise of the safety of train operation. For this reason, a scientific and rational analysis is conducted by using the track quality index of the synthesis of track measuring car, a prediction method is established with the non-equal interval weighted grey model based on data selection vector and neural network theory to predict actual track irregularities. The relative errors are 2.63%, 2. 516% and 2. 025%. The prediction model is applied in the arrangement of annual Optimization Track Synthetic Maintenance Plan with decision-making variables of maintenance time and maintenance location and the minimum annual average of the track quality index as the target function. With reference to a series of constraint functions, a aided decision model is established to acquire the optimum solution through genetic algorithms. Experimental results show that this method has improved prediction accuracy and is practical to work out annual railway maintenance plan quickly.

关 键 词：铁路轨道 轨道不平顺 TQI值 灰色模型 神经网络 遗传算法 最优解 

分 类 号：U213.2[交通运输工程—道路与铁道工程]