Detection and Classification System for Rail Surface Defects Based on Eddy Current.

The prospect of growth of a railway system impacts both the network size and its occupation. Due to the overloaded infrastructure, it is necessary to increase reliability by adopting fast maintenance services to reach economic and security conditions. In this context, one major problem is the excessive friction caused by the wheels. This contingency may cause ruptures with severe consequences. While eddy's current approaches are adequate to detect superficial damages in metal structures, there are still open challenges concerning automatic identification of rail defects. Herein, we propose an embedded system for online detection and location of rails defects based on eddy current. Moreover, we propose a new method to interpret eddy current signals by analyzing their wavelet transforms through a convolutional neural network. With this approach, the embedded system locates and classifies different types of anomalies, enabling an optimization of the railway maintenance plan. Field tests were performed, in which the rail anomalies were grouped in three classes: squids, weld and joints. The results showed a classification efficiency of ~98%, surpassing the most commonly used methods found in the literature.

Identification and Localization of Track Circuit False Occupancy Failures Based on Frequency Domain Reflectometry.

Railway track circuit failures can cause significant train delays and economic losses. A crucial point of the railway operation system is the corrective maintenance process. During this operation, the railway lines have the circulation of trains interrupted in the respective sector, where traffic restoration occurs only after completing the maintenance process. Depending on the cause and length of the track circuit, identifying and solving the problem may take a long time. A tool that assists in track circuit fault detection during an inspection adds agility and efficiency in its restoration and cost reduction. This paper presents a new method, based on frequency domain reflectometry, to diagnose and locate false occupancy failures of track circuits. Initially, simulations are performed considering simplified track circuit approximations to demonstrate the operation of the proposed method, where the fault position is estimated by identifying the null points and through non-linear regression on signal amplitude response. A field test is then carried out in a track circuit approximately 1500 m long to validate the proposed method. The results show that the proposed method can identify and estimate the fault location due to a short circuit between rails with high accuracy.