Position synchronization for track geometry inspection data via big-data fusion and incremental learning

Wang, Yuan; Wang, Ping; Wang, Xin; Liu, Xiang

doi:10.1016/j.trc.2018.06.018

Cited by 30 publications

(23 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite HSTGC representing the cutting-edge technology in rail infrastructural condition inspection, a chance of measurement error due to various factors cannot be completely eliminated. Among these errors, milepost positional error [43,48] is a critical one, especially when there is a need to locate the track segment corresponding to anomalies on the waveform of track geometry data. In practice, the mileage information is obtained from the rotation angles and the wheel radius.…”

Section: Data Pre-processing: Eliminating Milepost Errormentioning

confidence: 99%

“…In practice, the mileage information is obtained from the rotation angles and the wheel radius. However, positional errors can inevitably occur and accumulate due to radial errors of the wheels, faulty encoder output, degraded adhesive conditions, and track geometry irregularities [48]. Field investigations have found that the milepost position could be off up to 200 m [43], which is much longer than the length of track slab.…”

Section: Data Pre-processing: Eliminating Milepost Errormentioning

confidence: 99%

See 1 more Smart Citation

Identification of Temperature-Induced Deformation for HSR Slab Track Using Track Geometry Measurement Data

Liu

2019

Sensors

View full text Add to dashboard Cite

Slab track is widely used in many newly built high-speed rail (HSR) lines as it offers many advantages over ballasted tracks. However, in actual operation, slab tracks are subjected to operational and environmental factors, and structural damages are frequently reported. One of the most critical problems is temperature-induced slab-warping deformation (SWD) which can jeopardize the safety of train operation. This paper proposes an automatic slab deformation detection method in light of the track geometry measurement data, which are collected by high-speed track geometry car (HSTGC). The characteristic of track vertical irregularity is first analyzed in both time and frequency domain, and the feature of slab-warping phenomenon is observed. To quantify the severity of SWD, a slab-warping index (SWI) is established based on warping-sensitive feature extraction using discrete wavelet transform (DWT). The performance of the proposed algorithm is verified against visual inspection recorded on four sections of China HSR line, which are constructed with the China Railway Track System II (CRTSII) slab track. The results show that among the 24,806 slabs being assessed, over 94% of the slabs with warping deformation can be successfully identified by the proposed detection method. This study is expected to provide guidance for efficiently detecting and locating slab track defects, taking advantage of the massive track inspection data.

show abstract

Section: Data Pre-processing: Eliminating Milepost Errormentioning

confidence: 99%

Section: Data Pre-processing: Eliminating Milepost Errormentioning

confidence: 99%

Identification of Temperature-Induced Deformation for HSR Slab Track Using Track Geometry Measurement Data

Liu

2019

Sensors

View full text Add to dashboard Cite

show abstract

“…Generally, track geometry measurement data obtained by inspection cars suffer from measurement errors and positional errors. The positional error can be as much as 100 m in some cases (Wang, Wang, Wang, & Liu, 2018). Positional errors negatively affect the accuracy of the track irregularity predictions achieved by track geometry degradation models.…”

Section: Data Alignmentmentioning

confidence: 99%

“…RPB methods are used to align measurement data collected in different inspections (Xu, Sun, Liu, & Souleyrette, 2016). For more studies regarding the ABP methods and RBP methods, readers are referred to the work by Wang et al (2018) and Xu et al (2016).…”

Section: Data Alignmentmentioning

confidence: 99%

Prediction of railway track geometry defects: a case study

Soleimanmeigouni

Ahmadi

Nissen

et al. 2019

Structure and Infrastructure Engineering

View full text Add to dashboard Cite

The aim of this study has been to develop a data-driven analytical methodology for prediction of isolated track geometry defects, based on the measurement data obtained from a field study. Within the study, a defect-based model has been proposed to identify the degradation pattern of isolated longitudinal level defects. The proposed model considered the occurrence of shock events in the degradation path. Furthermore, the effectiveness of tamping intervention in rectifying the longitudinal level defects was analysed. The results show that the linear model is an appropriate choice for modelling the degradation pattern of longitudinal level defects. In addition, a section-based model has been developed using binary logistic regression to predict the probability of occurrence of isolated defects associated with track sections. The model considered the standard deviation and kurtosis of longitudinal level as explanatory variables. It has been found that the kurtosis of the longitudinal level is a statistically significant predictor of the occurrence of isolated longitudinal level defects in a given track section. The validation results show that the proposed binary logistic regression model can be used to predict the occurrence of isolated defects in a track section.

show abstract

“…For collecting track conditions, the railway industry has employed various dedicated devices, such as track inspection vehicles [31] and visual inspection systems [32]. Although these devices perform well in detecting track conditions, the expensive cost and the interference for regular operation limit their usage in urban rail transit systems.…”

Section: Introductionmentioning

confidence: 99%

Using Vehicle Interior Noise Classification for Monitoring Urban Rail Transit Infrastructure

Wang

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

This study developed a multi-classification model for vehicle interior noise from the subway system, collected on smartphones. The proposed model has the potential to be used to analyze the causes of abnormal noise using statistical methods and evaluate the effect of rail maintenance work. To this end, first, we developed a multi-source data (audio, acceleration, and angle rate) collection framework via smartphone built-in sensors. Then, considering the Shannon entropy, a 1-second window was selected to segment the time-series signals. This study extracted 45 features from the time- and frequency-domains to establish the classifier. Next, we investigated the effects of balancing the training dataset with the Synthetic Minority Oversampling Technique (SMOTE). By comparing and analyzing the classification results of importance-based and mutual information-based feature selection methods, the study employed a feature set consisting of the top 10 features by importance score. Comparisons with other classifiers indicated that the proposed XGBoost-based classifier runs fast while maintaining good accuracy. Finally, case studies were provided to extend the applications of this classifier to the analysis of abnormal vehicle interior noise events and evaluate the effects of rail grinding.

show abstract

Position synchronization for track geometry inspection data via big-data fusion and incremental learning

Cited by 30 publications

References 20 publications

Identification of Temperature-Induced Deformation for HSR Slab Track Using Track Geometry Measurement Data

Identification of Temperature-Induced Deformation for HSR Slab Track Using Track Geometry Measurement Data

Prediction of railway track geometry defects: a case study

Using Vehicle Interior Noise Classification for Monitoring Urban Rail Transit Infrastructure

Contact Info

Product

Resources

About