Detection and Severity Evaluation of Combined Rail Defects Using Deep Learning

Abstract

Various techniques have been developed to detect railway defects. One of the popular techniques is machine learning. This unprecedented study applies deep learning, which is a branch of machine learning techniques, to detect and evaluate the severity of rail combined defects. The combined defects in the study are settlement and dipped joint. Features used to detect and evaluate the severity of combined defects are axle box accelerations simulated using a verified rolling stock dynamic behavior simulation called D-Track. A total of 1650 simulations are run to generate numerical data. Deep learning techniques used in the study are deep neural network (DNN), convolutional neural network (CNN), and recurrent neural network (RNN). Simulated data are used in two ways: simplified data and raw data. Simplified data are used to develop the DNN model, while raw data are used to develop the CNN and RNN model. For simplified data, features are extracted from raw data, which are the weight of rolling stock, the speed of rolling stock, and three peak and bottom accelerations from two wheels of rolling stock. In total, there are 14 features used as simplified data for developing the DNN model. For raw data, time-domain accelerations are used directly to develop the CNN and RNN models without processing and data extraction. Hyperparameter tuning is performed to ensure that the performance of each model is optimized. Grid search is used for performing hyperparameter tuning. To detect the combined defects, the study proposes two approaches. The first approach uses one model to detect settlement and dipped joint, and the second approach uses two models to detect settlement and dipped joint separately. The results show that the CNN models of both approaches provide the same accuracy of 99%, so one model is good enough to detect settlement and dipped joint. To evaluate the severity of the combined defects, the study applies classification and regression concepts. Classification is used to evaluate the severity by categorizing defects into light, medium, and severe classes, and regression is used to estimate the size of defects. From the study, the CNN model is suitable for evaluating dipped joint severity with an accuracy of 84% and mean absolute error (MAE) of 1.25 mm, and the RNN model is suitable for evaluating settlement severity with an accuracy of 99% and mean absolute error (MAE) of 1.58 mm.

Ensemble model for rail surface defects detection

“…The rise and development of machine learning provides a new effective approach for rail defect detection. DNNs have been successfully adopted to detect rail corrugation [ 12 ], rail flat [ 13 ], and have been applied to investigate the condition of railway sleepers [ 14 , 15 ], settlement/dipped joints [ 16 ], and other rail track components [ 17 ]. Recently, object detection has achieved a substantial breakthrough by using Convolutional Neural Networks (CNNs), and has been introduced for rail surface defect detection in the past decades [ 11 , 18 , 19 ].…”

Quantification of Dynamic Track Stiffness Using Machine Learning

“…As aforementioned, using pre-defined hand-crafted features is notoriously difficult, not least because of the hardness of selecting the features and the human biases when defining the features. This argument has been further proven by [22], concluding that the CNN using vibration data shows superior performance compared to the deployment of the deep neural network with the handcrafted features. Vibration-based machine learning models have been thriving and used in various aspects such as structural damage monitoring [23] and railway track condition monitoring [24].…”

Identification of Sleeper Support Conditions Using Mechanical Model Supported Data-Driven Approach

“…Therefore, the void interaction cannot be good enough differentiated with the classifiers trained only for void case. The model training for combined rail defects or irregularities as presented in [ 89 ] would probably improve the classification results.…”

“…The measurements were pre-processed before the model training by using a continuous wavelet transform. The paper [ 89 ] demonstrates three different approaches for combined defect detection and evaluation: deep neural network, convolutional neural network, and recurrent neural network. The simulated axle-box accelerations were used as statistical information for model training.…”