Structural health monitoring of railway tracks using IoT-based multi-robot system
- PDF / 2,941,521 Bytes
- 19 Pages / 595.276 x 790.866 pts Page_size
- 94 Downloads / 197 Views
(0123456789().,-volV)(0123456789(). ,- volV)
ORIGINAL ARTICLE
Structural health monitoring of railway tracks using IoT-based multirobot system Srikrishna Iyer1 • T. Velmurugan2 • A. H. Gandomi3 • V. Noor Mohammed2 • K. Saravanan2 S. Nandakumar2
•
Received: 12 July 2019 / Accepted: 16 September 2020 Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract A multi-robot-based fault detection system for railway tracks is proposed to eliminate manual human visual inspection. A hardware prototype is designed to implement a master–slave robot mechanism capable of detecting rail surface defects, which include cracks, squats, corrugations, and rust. The system incorporates ultrasonic sensor inputs coupled with image processing using OpenCV and deep learning algorithms to classify the surface faults detected. The proposed Convolutional Neural Network (CNN) model fared better compared to the Artificial Neural Network (ANN), random forest, and Support Vector Machine (SVM) algorithms based on accuracy, R-squared value, F1 score, and Mean-Squared Error (MSE). To eliminate manual inspection, the location and status of the fault can be conveyed to a central location enabling immediate attention by utilizing GSM, GPS, and cloud storage-based technologies. The system is extended to a multi-robot framework designed to optimize energy utilization, increase the lifetime of individual robots, and improve the overall network throughput. Thus, the Low Energy Adaptive Clustering Hierarchy (LEACH) protocol is simulated using 100 robot nodes, and the corresponding performance metrics are obtained. Keywords Multi-robot system Convolutional neural network (CNN) Artificial Neural Network (ANN) Random forest Support Vector Machine (SVM) LEACH protocol
1 Introduction & T. Velmurugan [email protected] Srikrishna Iyer [email protected] A. H. Gandomi [email protected] V. Noor Mohammed [email protected] K. Saravanan [email protected] S. Nandakumar [email protected] 1
Software Engineer II, ASM Pacific Technology, Yishun Avenue, Singapore 768924, Singapore
2
School of Electronics Engineering, VIT University, Vellore, India
3
Faculty of Engineering and IT, University of Technology Sydney, Sydney, Australia
Indian railways provide a major mode of transportation for more than 25 million people every single day. Now, the world’s third-largest rail network, structurally monitoring railway tracks, has become an integral part of avoiding railway accidents and loss of life. While the number of railway mishaps has reduced over the last ten years, the death toll due to the derailment has risen significantly. In 2016–2017, 193 people died in these accidents out of which 78 of these accidents occurred due to derailment, bringing the count to an all-time high in the past decade. According to a study conducted, in the 6 years between 2009 and 2015, there were a total of 803 accidents in Indian Railways killing 620 people and injuring 1855 people. Moreover, 47% of these accidents were due to the dera
Data Loading...
