Autonomous Smart Rail Crack Detection with Multi-Sensory AI (utilizing video, sound & smell)
| I&T Solution |
Autonomous Smart Rail Crack Detection with Multi-Sensory AI (utilizing video, sound & smell)
(REF: S-1705) |
| Trial Project |
|
| Solution Feature |
- 1. Visual AI: WildFaces' visual AI detects flaws, cracks, and broken sections on rail tracks in real-time, focusing on visible external defects.
- 2. Sound & Smell AI: The system also analyzes engine and vibration sounds, along with smells like burning or grease, to detect internal issues imperceptible visually.
- 3. On-The-Move Technology: WildFaces employs patented WildAI On-The-Move tech, compatible with moving IoTs like cameras on trains traveling at 80kph.
- 4. Sensor Setup: Each track line requires one set of multiple sensors (high-speed camera, microphone, smell sensor) installed under the carriage, with two sets per train for both track sides.
- 5. Real-time Notification: Connected to an edge computer with onboard 4G/5G, the system instantly alerts personnel with images and location IDs upon detecting flaws, enabling immediate action.
|
| Trial Application and Expected Outcome |
- Our visual based algorithms are ready for some defects but we need to get more examples of MTR specific types of defects. Defects examples that we can already do such as loosen screws, scratches & cracks. However, sound and smell analytics will be to be developed.
- Visual based AI can be ready to demonstrate in 2-3 months time whereas sound and smell for known types that we have trained for are ready to demonstrate now. However, we will need extra 3 months if it is required to pick up specific types of MTR defects.
- Real-time Alert can be sent via 4G or 5G as an email to designated email addresses of first Responder/Supervisor.
- Each alert is also associated with a 20-second of jump-to-event video clip showing 10-second of pre alarm and another 10-second of post alarm along with Visual based Positioning System (VPS) location information helping supervisor to understand the seriousness of the track defects before calling for maintenance.
- Please refer to ppt for our proposal.
|
| Info on I&T Solution Provider |
| Solution Provider | : | WildFaces Technology Limited | | Address | : | Unit 22, Level 6, Core C, Cyberport 3, 100 Cyberport Road, Hong Kong | | Contact Person | : | Eric Wong |
| Position | : | Senior AI Business Consultant | | Tel | : | +852 8216 2219 | | Email | : |
bd@wildfaces.ai | | Webpage | : | www.wildfaces.ai |
|
For details of the above I&T solution, please contact the I&T solution provider.
