Autonomous IoT-Based Railway Track Crack Detection Robot
Team
- E21/096,Chamodi Dikela,e21096@eng.pdn.ac.lk
- E/21/127,Navoda Erandi,e21127@eng.pdn.ac.lk
- E/21/140,Suvini Fonseka,e21140@eng.pdn.ac.lk
- E/21/363,Tharushi Savindi,e21363@eng.pdn.ac.lk
Table of Contents
- Introduction
- Solution Architecture
- Hardware & Software Designs
- Testing
- Detailed budget
- Conclusion
- Links
Introduction
Real-World Problem
Railway track failures caused by cracks, wear, and structural defects are a major reason for train derailments and service disruptions worldwide. Traditional inspection methods rely heavily on manual patrols and scheduled checks, which are time-consuming, expensive, and expose workers to dangerous environments. These methods often fail to detect small or early-stage cracks, allowing defects to worsen over time and increasing the risk of accidents.
Additionally, the lack of real-time monitoring and precise location tracking makes it difficult for maintenance teams to respond quickly and efficiently when issues are detected.
Proposed Solution
This project introduces an autonomous IoT-based railway track crack detection robot that continuously monitors railway tracks in real time. The robot uses a combination of IR sensors and ultrasonic sensors to detect cracks and surface irregularities with high accuracy.
When a defect is detected:
- An onboard camera captures clear images of the affected track section
- GPS data is recorded to identify the exact location of the defect
- All data is instantly uploaded to a cloud platform, where alerts are displayed on a monitoring dashboard
This enables railway authorities to identify issues early, prioritize maintenance tasks, and respond without sending personnel into hazardous areas.
Impact and Benefits
- Improved Safety: Early crack detection significantly reduces the risk of derailments and accidents
- Reduced Human Risk: Minimizes the need for manual track inspections in dangerous environments
- Real-Time Monitoring: Enables immediate alerts and faster decision-making
- Cost-Effective Maintenance: Prevents minor defects from developing into major infrastructure failures
- Scalable Solution: Can be deployed across large railway networks and integrated with existing maintenance systems
By leveraging automation, IoT connectivity, and cloud analytics, this system contributes to safer, smarter, and more efficient railway infrastructure management.
Solution Architecture
High level diagram + description
Hardware and Software Designs
Detailed designs with many sub-sections
Testing
Testing done on hardware and software, detailed + summarized results
Detailed budget
All items and costs
All Items and Costs
| Item | Quantity | Unit Cost (LKR) | Total (LKR) |
|---|---|---|---|
| ESP32-S3-N16R8 | 1 | 1840 | 1340 |
| ESP32-CAM Module OV2640 | 1 | 2190 | 2190 |
| Ultrasonic Sensors (HC-SR04) | 2 | 230 | 460 |
| DC Geared Motors (TT / BO Motors, 100–200 RPM) | 4 | 1290 | 5160 |
| Motor Driver Module (L298N / L293D) | 1 | 440 | 440 |
| GPS Module (NEO-6M / NEO-7M) | 1 | 2590 | 2590 |
| Rechargeable Battery | 1 | 1377 | 1377 |
| Buck Converter (DC-DC Step-Down Module) | 1 | 1275 | 1275 |
| PCB / Perfboard (for prototyping or final soldering) | 1 | 1000 | 1000 |
| Switch / Power Button | 1 | 85 | 85 |
| Buzzer (Audible alert) | 1 | 500 | 500 |
| 16x2 LCD Display with I2C Module | 1 | 1200 | 1200 |
| Micro SD Card Module | 1 | 330 | 330 |
| Other miscellaneous components (wires, mounts, fasteners, etc.) | – | – | 3000 |
| Total Estimated Cost | 23297 |
Conclusion
What was achieved, future developments, commercialization plans