Search

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. [ABSTRACT FROM AUTHOR]

Railway sleepers are safety–critical components of a railway structure. They support ballasted track superstructure and are a critical factor in track geometry and track components' deterioration. Unsupported sleepers are a common issue incurred after tracks have been utilized. When unsupported sleepers are present, they cause differential settlements of track superstructures, additional dynamic loading, and excessive train-track vibrations which affect passenger comfort, safety, and maintenance cost. This study is the world's first to develop new machine learning models to prognose and better diagnose defect severities of unsupported sleepers aligned with practical track inspection guidelines. Data used to develop machine learning models are based on a verified finite element model with actual field measurements, enabling unbiased full data ranges that govern all defect conditions. Different conditions of unsupported sleepers can be explored by varying locations of unsupported sleepers and the number of unsupported sleepers. Also, other operational parameters can be addressed such as speeds of rolling stock, the roughness of rail surface, and vertical stiffness of wheel-rail contact. In total, 2016 data sets have been obtained. Axle box accelerations are adopted as key indicators for machine learning models. Machine learning techniques used in the study are the convolutional neural network, recurrent neural network, ResNet, and fully convolutional neural network. Data fusion and assimilation have been conducted since the data points are dependent on the train speeds. Our new results reveal a breakthrough essential for real-world applications that the convolutional neural network model provides the best accuracy in both unsupported sleeper prognostics and severity identification. The accuracies of detection and severity identification are 99.34% and 97.02% respectively. [ABSTRACT FROM AUTHOR]