An Intelligent Internet of Things (IoT) Powered Railway Track Crack Detection Scheme Based on Smart Sensors Association
This paper presents an IoT -powered railway track crack detection system that uses a combination of smart sensors and autonomous vehicles to detect cracks and obstacles in railway infrastructure. The system incorporates ultrasonic sensors, infrared (IR) sensors, and LED-LDR assemblies, enabling real-time monitoring and reporting of railway track conditions. Wireless communication protocols such as Wi- Fi, RF transmitters, and GPS are utilized to transmit data to central control systems. Through testing, the combined sensor setup demonstrated the highest crack detection accuracy of 98%, outperforming individual sensors with accuracies of 94 % for ultrasonic sensors, 90% for IR sensors, and 80% for LED-LDR. The system's response time averaged 460ms in the combined setup, with the LED-LDR setup being the slowest at 580ms. The system also showed resilience across varied environmental conditions, proving its robustness in both high and low temperature, humidity, and lighting scenarios. This efficient, solar-powered system reduces manual inspection efforts and ensures continuous, reliable operation. The proposed system offers an innovative, cost-effective solution to enhance railway safety and prevent potential accidents caused by track defects.
Authors
- Peter Prince (ORCID: https://orcid.org/0000-0002-4857-261X)
- L. Bharathi
- Kanchana Rajaram (ORCID: https://orcid.org/0000-0002-2591-2482)
- P. Seethalakshmi
- D. Prasad (ORCID: https://orcid.org/0000-0003-3963-1021)
- S. Leones Sherwin Vimalraj (ORCID: https://orcid.org/0000-0002-1679-4656)
Institutions
- Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology (IN)
- Institute of Science and Technology
- National Institute of Technology Meghalaya (IN)
Publication Details
- Published
- 2024-12-12
- DOI
- https://doi.org/10.1109/icses63760.2024.10910375
- Citations
- 2
- Primary Topic
- Engineering Applied Research
- Type
- article
- Field-Weighted Citation Impact
- 0.52