Prediction of Rail Wheel Deformity Using Rail Asset Monitoring and Predictive Maintenance

R. Angeline, S.S. Narayanan, Paruchuri Yaswanth, Ponna Darshan and P. Yasvanth

Modern rail infrastructure lays heavily on intensive operations than ever before, placing greater demands on trackcomponents. Wheel defects on railway freight trains have been measured as a huge cause of destructions in terms of financial as well as human loss. So many techniques such as vertical force measurements using sensor have been developed to detect those wheel defects. But the main complication arises in the reliability of the techniques. We propose an efficient method which detects different types of railway defects and predicts them during normal operation. The main focus of the project is to prevent the occurrence of the defect to the maximum possibility. For that we are using IOT sensors which are used to gather data on tracks and sends it to software called i-RAMP (IoT-enabled Platform for Rail Assets Monitoring and Predictive Maintenance). We will then use Artificial Intelligence (AI) techniques to dissect the data and to predict when a fault is likely to occur. This paper also focusses on detection of various types of cracks using an ultrasonic sensor and a PIR sensor is also used to sense the movement of people, animals or any other objects thus which helps in collision avoidance.

Volume 11 | 04-Special Issue

Pages: 1088-1092