Method for automatic railway track surface defect classification and evaluation using a laser‐based 3D model

Ye, Jiaqi; Stewart, Edward; Zhang, Dingcheng; Chen, Qianyu; Roberts, Clive

doi:10.1049/iet-ipr.2019.1616

Cited by 14 publications

(9 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Where 𝑔(•) is the model and 𝜃 is parameters. During the training, the algorithm minimizes the error using a loss function as (3).…”

Section: Supervised Learningmentioning

confidence: 99%

“…2 In this study, data obtained from the TGC consist of longitudinal level (surface), alignment, gauge (gage), twist (crosslevel) and superelevation as shown in Figure 1. Track component defects are inspected using manual inspection, laser technology 3 or axle box acceleration, 4 etc. It can be seen that component defect inspection is time-consuming or requires the additional installation cost of equipment while track geometry can be measured faster.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Railway defect detection based on track geometry using supervised and unsupervised machine learning

Sresakoolchai

Kaewunruen

2022

Structural Health Monitoring

View full text Add to dashboard Cite

Track quality affects passenger comfort and safety. To maintain the quality of the track, track geometry and track component defects are inspected routinely. Track geometry is inspected using a track geometry car (TGC). Measured values are stored in the machine and processed to evaluate the track quality. However, track component defects require more effort to inspect. Track component defects can be inspected manually which is time- and workload-consuming or using sensors installed at additional cost. This study presents an approach using track geometry obtained by a TGC to detect track component defects, namely, rail, switch and crossing, fastener and rail joint defects. Detection models are developed using several supervised machine learnings. The relationships between track component defects are analysed to gain insights using unsupervised machine learnings. From the study, the best model for detecting track component defects using track geometry is a deep neural network with an accuracy of 94.31% followed by a convolutional neural network with an accuracy of 93.77%. For the exploration of insights, k-means clustering is used to cluster the track components defects, and association rules are used to find the relationships between them. Examples of the insights from applying these two techniques are that switch and crossing defects are usually found where the radius of curvature is less than 2000 m and the gradient is positive, the most common defects when the radius of curvature higher than 4000 m are rail defects, or a worn wing rail will be found when the rail section has failed, ties in switches and worn point blades are found with the confidence of 92.17%. The findings of the study can be applied to detect track component defects using track geometry where additional cost is not required and unsupervised machine learning provides the insights that will be beneficial for railway maintenance. The information obtained from machine learning models will be complementary information to support decision making and improve the maintenance efficiency in the railway industry.

show abstract

“…Where 𝑔(•) is the model and 𝜃 is parameters. During the training, the algorithm minimizes the error using a loss function as (3).…”

Section: Supervised Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Railway defect detection based on track geometry using supervised and unsupervised machine learning

Sresakoolchai

Kaewunruen

2022

Structural Health Monitoring

View full text Add to dashboard Cite

show abstract

“…In the railway, such systems have also been applied to provide more accurate and effective condition monitoring solutions. [19][20][21][22] An example is the overhead track detection and gauge measurement system proposed by Singh et al, 21 which employs computer visionbased monitoring through drone imagery. Z. Liu et al 22 proposed a vision-based monitoring approach for catenary support components using fixed high-resolution cameras and LED lights.…”

Section: Introductionmentioning

confidence: 99%

A vision-based method for line-side switch rail condition monitoring and inspection

Stewart

Chen

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part F:

Self Cite

View full text Add to dashboard Cite

In railway systems, switch rails are one of the key components of switches & crossings (S&C). They are controlled by switch machines to guide trains from one track to another. Due to the discontinuity in geometry, switch rails are exposed to high-impact loads as train wheels pass through. The long-term impact loads can cause local plastic deformation. These faults, and general alignment changes, can lead to the development of a gap between the switch rail and the stock rail known as a toe gap, as well as non-optimal contact with the wheel flange, both of which can endanger the safe operation of passing trains. Currently, periodic visual inspection is the main method for detecting these defects. This is not efficient or reliable enough to support the ever-shortening maintenance windows available in modern railway systems. The development of computer vision technologies and constantly improving processors make it possible to monitor the health status of such safety-critical components in real time. This research proposes a line-side condition monitoring approach for the switch rail. With the use of dedicated identification algorithms, the status of the switch rail, including movement, position, toe gap and the edge of the toes, can be monitored remotely in real time. This approach has been tested in a high-speed train testing centre in China. The results show a capability to further improve the safe operation of S&C while simultaneously reducing the cost and increasing the safety of inspection.

show abstract

“…e 3D size measurement results directly a ect the amount of lling and the quality of pavement maintenance. With the rapid development of computer vision and sensors, many pothole detection [2,4,8] and measurement methods [5,9,10] have emerged. e maturity of pothole detection technology [2,4,11,12] and 2D pro le measurement [5,9,13,14] has been driven by large computing power and data.…”

Section: Introductionmentioning

confidence: 99%

“…With the rapid development of computer vision and sensors, many pothole detection [2,4,8] and measurement methods [5,9,10] have emerged. e maturity of pothole detection technology [2,4,11,12] and 2D pro le measurement [5,9,13,14] has been driven by large computing power and data. However, little attention has been paid to high-precision 3D measurement, especially for volume measurement.…”

Section: Introductionmentioning

confidence: 99%

High-Precision Volume Measurement of Potholes in Pavement Maintenance

Huang

Zhou

Liu

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Accurate three-dimensional measurement of potholes is a significant concern in road maintenance. However, the assessment of road potholes still relies heavily on human inspectors to make maintenance suggestions. To realize full-field measurement of pavement pothole automatically, a high-precision volume measurement method based on second-order Taylor expansion is proposed, where the second-order Taylor estimation of each point is converted into a convolution operation. On the one hand, this method discards the second-order fitting of the surface, which greatly reduces the computational complexity. On the contrary, the second-order Taylor estimation is not restricted by the surface shape because it only depends on the distribution of the adjacent points. Experiments on synthesized and real point sets demonstrate that the proposed method outperforms the state-of-the-art methods under various point cloud shapes.

show abstract

Method for automatic railway track surface defect classification and evaluation using a laser‐based 3D model

Cited by 14 publications

References 27 publications

Railway defect detection based on track geometry using supervised and unsupervised machine learning

Railway defect detection based on track geometry using supervised and unsupervised machine learning

A vision-based method for line-side switch rail condition monitoring and inspection

High-Precision Volume Measurement of Potholes in Pavement Maintenance

Contact Info

Product

Resources

About