Research on Dynamic and Static Data Inversion of Track Irregularity of High-speed Railway

被引：0

作者：

He, Qing ^{[1
,2
]}

Ma, Yusong ^{[1
,3
]}

Sun, Huakun ^{[1
]}

Li, Chenzhong ^{[1
]}

He, Hongyu ^{[3
]}

Wang, Ping ^{[1
,2
]}

机构：

[1] School of Civil Engineering, Southwest Jiaotong University, Chengdu

[2] Key Laboratory of High-speed Railway Engineering, Ministry of Education, Southwest Jiaotong University, Chengdu

[3] Rail Transit Business Group, Zhejiang Supcon Information Technology Co., Ltd., Hangzhou

来源：

Tiedao Xuebao/Journal of the China Railway Society | 2025年 / 47卷 / 04期

关键词：

bidirectional long short-term memory network; data inversion; dynamic and static track inspection data; high-speed railway; multi-step matching mechanism;

D O I：

10.3969/j.issn.1001-8360.2025.04.011

中图分类号：

学科分类号：

摘要：

It is an important management method for the railway permanent way department to evaluate the geometric state of the track according to the over-limit classification and penalty point evaluation of the track irregularity detection data. In response to few models for dynamic and static detection data inversion in existing research, plus with their relatively weak applicability, in this paper, a peak prediction model based on bidirectional long short-term memory network was established by using the mapping relationship between dynamic and static data. The model used dynamic detection data as input to realize static detection data prediction inversion. At the same time, a three-step data transformation method and a multi-step matching mechanism were proposed to improve the performance of the model. A case analysis was carried out based on the track geometry detection data of different sections of a high-speed railway line. The results show that the improved model achieves an accuracy improvement by more than 70％, realizing accurate prediction of the vertical and horizontal detection data of different sections, with the reduction of average absolute error and root mean square error of the prediction results by 75. 27％ and 71. 21％, respectively. © 2025 Science Press. All rights reserved.

引用

页码：94 / 102

页数：8

共 21 条

[1]

LUO Lin, High Smoothness,a Must for the High-speed Railway Track, China Railway, 10, pp. 8-11, (2000)

[2]

LUO Lin, ZHANG Geming, WU Wangqing, Et al., Control of Track Smoothness of Wheel-Rail System, (2006)

[3]

YANG Fei, SUN Xianfu, TAN Shehui, Et al., Evaluation Difference of Dynamic and Static Track Irregularity and Characteristics of Dynamic Chord Measurement Method [J], Journal of Southwest Jiaotong University, 57, 6, pp. 1239-1249, (2022)

[4]

IIDA H, HIRATA K, HOYAMA H., Correlation of Track Irregularity Measurements by Different Measurement Methods, Railway Track, 36, 6, pp. 274-279, (1986)

[5]

YAMAWAKI H, IIDA H., Interrelation between Dynamic and Static Irregularities by Finite Element Analysis, Proceedings of the 42nd Annual Meeting of the Japan Society of Civil Engineers, pp. IV-251, (1987)

[6]

ZHANG Wei, Numerical Difference between Dynamic and Static Inspection of Lines, Railway Operation Technology, 5, 4, pp. 160-165, (1999)

[7]

DENG Xuetong, Analysis of Dynamic and Static Test Results of Quasi-high-speed Track Inspection Car and GJ-3 Track Inspection Car, Railway Standard Design, 44, 4, pp. 42-44, (2000)

[8]

REN Zhiqiang, Study on the Correlation between the Static Value of Ballastless Track Irregularity and the Dynamic Detection Result of 160 km/ h in Track Inspection Car, Railway Engineering, 52, 4, pp. 125-127, (2012)

[9]

LYU Guanren, Analysis of Dynamic and Static Geometric State Change of Beijing―Shanghai High-speed Railway Track, China Railway, 6, pp. 28-31, (2014)

[10]

ZHANG Zhichuan, LIU Xiubo, QIANG Weile, Et al., Research on Correlation between Dynamic and Static Track Irregularities of Normal Speed Railway, Railway Engineering, 62, 9, pp. 47-51, (2022)

← 1 2 3 →