Enhancing Railway Safety with an IoT Based System for Real Time Fault Detection and Crack Monitoring
Safety of railway is the major problem worldwide. It has problems like cracks or any fault in the railway tracks. These problems can cause severe accidents if it is not detected regularly and early. In traditional fault finding and crack detecting method, the manual method is involved which is very slow and consist of many errors. By considering all these challenges and issues in track detection method, we have implemented an advanced IoT based railway crack and fault-finding system. It uses advanced sensors, microcontroller, GPS and GSM module which can detect and report faults of the railway track. The system uses real time mechanism. The system is implemented and tested on a prototype railway track to detect crack or any fault. The internet of things technology added modern and accurate fault-finding feature in the system. The IoT plays an important role in implementing advance technologies, as it uses sensors and advance microcontroller. The accuracy rate of fault and crack detection is around 97%, which is for 2 mm crack. Along with this GPS module accurately track fault location. GSM module successfully send the alert message quickly after detecting the fault in the track. Hence the response time is very less and accurate. This system is implemented in order to ensure safety for the railway track and prevent the accidents. Hence the system is useful for improving overall transport safety.
Authors
- Ravindra Raman Cholla (ORCID: https://orcid.org/0000-0003-3311-2407)
- Rajermani Thinakaran (ORCID: https://orcid.org/0000-0002-9525-8471)
- Vikram Neerugatti (ORCID: https://orcid.org/0000-0002-2203-7002)
- Madhusudana Rao Nalluri (ORCID: https://orcid.org/0000-0002-5315-1932)
- Somasekar Jalari
- Santhaiah Chukka
Institutions
- Jain University (IN)
- INTI International University (MY)
- ICFAI Foundation for Higher Education (IN)
Publication Details
- Published
- 2024-11-07
- DOI
- https://doi.org/10.1109/icitda64560.2024.10809610
- Citations
- 2
- Primary Topic
- Machine Fault Diagnosis Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.66