Spatial–Temporal Model to Identify the Deformation of Underlying High-Speed Railway Infrastructure

Li, Chen-Zhong; Wang, Ping; Gao, Tianci; Wang, Jianhui; Yang, Cuiping; Liu, Heng; He, Qing

doi:10.1061/jtepbs.0000408

Cited by 16 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Helming obtained the oscillation peak value of the tower by frequency domain analysis of the monitoring signal [8]. Li developed a spatialtemporal identification model for the deformation of the underlying high-speed railway infrastructure, including simply supported beams and track slabs based upon track geometry data [9]. Farzaneh proposed the least square correction technique to analyze dam deformation [10].…”

Section: Introductionmentioning

confidence: 99%

Analysis and Prediction of Railway Infrastructure Deformation Monitoring Data Based on Fractional Order Statistical Theory

Liu,

Li,

Feng

et al. 2023

IEEE Access

View full text Add to dashboard Cite

The deformation monitoring system of railway infrastructure comes with many non-Gaussian behaviors. These behaviors are the typical fractional order characteristics which are hard to analyze by traditional methods. This paper presents a detail fractional order statistical theory to capture the key deformation feature and further achieve active warning of railway infrastructure. Initially, α-stable distribution is applied to reveal the non-Gaussian features hidden in the monitored time series. Then, long-range correlation and multifractal properties are extracted by the fractional order statistical method. After that, a novel fractional Bi-long short term memory model (F-BiLSTM) capture long-term trends characteristic and simulate stochastic process of the monitoring system. The proposed method is used to predict the deformation of railway infrastructure and obtained the superior prediction performances.

show abstract

Section: Introductionmentioning

confidence: 99%

Analysis and Prediction of Railway Infrastructure Deformation Monitoring Data Based on Fractional Order Statistical Theory

Liu,

Li,

Feng

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The existence of track irregularities could not only compromise the operational safety of heavy-haul trains but also degrade track substructures [34][35][36]. Li et al [37,38] proposed a data-driven method for infrastructure deformation identification based on the characteristics of track geometry data, as well as a spatio-temporal identification model for identifying high-speed railway infrastructure deformation by using four years of track geometry data. Li et al [39] analyzed the time and frequency characteristics of track geometry irregularity signals at the locations of mud pumps and used a multi-scale signal decomposition method to extract defect-sensitive features and then realize automatic detection of mud pumping problems.…”

Section: Introductionmentioning

confidence: 99%

Characterizing Particle-Scale Acceleration of Mud-Pumping Ballast Bed of Heavy-Haul Railway Subjected to Maintenance Operations

Wang

Xiao

et al. 2022

Sensors

View full text Add to dashboard Cite

Fouling and mud-pumping problems in ballasted track significantly degrade serviceability and jeopardize train operational safety. The phenomenological approaches for post hoc forensic investigation and remedies of mud pumps have relatively been well studied, but there still lacks studies on inherent mechanisms and ex ante approaches for early-age detection of mud pumps. This paper was aimed to exploring the feasibility of using particle acceleration responses to diagnose and identify early-age mud-pumping risks in real-world field applications. The innovative wireless sensors with 3D-printed shells resembling real shape of ballast particles were instrumented in the problematic railway section to monitor ballast particle movement prior to, during, and after maintenance operations, respectively. The real-time particle-scale acceleration data of ballast bed under both degraded and maintenance-restored clean conditions were recorded. The time histories, power spectra, and marginal spectra of 3D acceleration were comparatively analyzed. The results showed the 3D acceleration of ballast particles underneath rail-supporting tie plates displayed relatively clear periodicity of about 0.8 s with adjacent bogies regarded as a loading unit. The tamping operation was effective for compacting ballast bed laterally and improving the lateral interlocking of ballast particles, whereas the stabilizing operation was effective mainly in the lateral direction and for ballast particles underneath the sleepers. The mud pumps caused intensive particle-scale acceleration, and ballast particles underneath the sleepers were affected more severely than those in between adjacent sleepers. The ballast particles directly underneath tie plates exhibit dramatic acceleration variations due to maintenance operations as compared to those in other positions studied; hence, it seems promising to use particle-scale acceleration underneath tie plates as readily-implementable indicators for smart in-service track health monitoring.

show abstract

“…In the literature, there are research studies concentrating on the identification of track deformation induced by mud pumping [ 21 ] and high temperature [ 22 , 23 ] by using TID. Moreover, the recognition of the 32 m cyclic-creep camber deformation of simply supported girders has also been fulfilled by early research using longitudinal-level inspection data [ 24 , 25 ]. The characteristic wavelengths of the deformation of the railway track and girders are below 10 m and cyclic 32 m, respectively.…”

Section: Introductionmentioning

confidence: 99%

Differential Deformation Identification of High-Speed Railway Substructures Based on Dynamic Inspection of Longitudinal Level

Liu

Zhang

et al. 2022

Sensors

View full text Add to dashboard Cite

High-speed railway administrations are particularly concerned about safety and comfort issues, which are sometimes threatened by the differential deformation of substructures. Existing deformation-monitoring techniques are impractical for covering the whole range of a railway line at acceptable costs. Fortunately, the information about differential substructure deformation is contained in the dynamic inspection data of longitudinal level from comprehensive inspections trains. In order to detect potential differential deformations, an identification method, combining digital filtering, a convolutional neural network and infrastructure base information, is proposed. In this method, a low-pass filter is designed to remove short-waveband components of the longitudinal level. Then, a one-dimensional convolutional neural network is constructed to serve as a feature extractor from local longitudinal-level waveforms, and a binary classifier of potential differential deformations in place of the visual judgement of humans with profound expertise. Finally, the infrastructure base information is utilized to further classify the differential deformations into several types, according to the positional distribution of the substructures. The inspection data of four typical high-speed railways are selected to train and test the method. The results show that the convolutional neural network can identify differential substructure-deformations, with the precision, recall, accuracy and F1 score all exceeding 98% on the test data. In addition, four types of deformation can be further classified with the support of infrastructure base information. The proposed method can be used for directly locating adverse substructure deformations, and is also becoming a promising addition to existing deformation monitoring methods.

show abstract

Spatial–Temporal Model to Identify the Deformation of Underlying High-Speed Railway Infrastructure

Cited by 16 publications

References 18 publications

Analysis and Prediction of Railway Infrastructure Deformation Monitoring Data Based on Fractional Order Statistical Theory

Analysis and Prediction of Railway Infrastructure Deformation Monitoring Data Based on Fractional Order Statistical Theory

Characterizing Particle-Scale Acceleration of Mud-Pumping Ballast Bed of Heavy-Haul Railway Subjected to Maintenance Operations

Differential Deformation Identification of High-Speed Railway Substructures Based on Dynamic Inspection of Longitudinal Level

Contact Info

Product

Resources

About