DESIGN OF A BEARING TEMPERATURE DETECTION SYSTEM FOR RAILWAY VEHICLES USING COMPUTER VISION TECHNOLOGY AND THERMAL CAMERAS
Tapered Roller Bearings (TRBs) are vital components in railway vehicles, functioning to support the rotation of wheels and transmit the load between the wheels and the axle. This ensures that the wheels rotate smoothly and efficiently. However, trains that operate for extended periods and under heav...
Saved in:
| Main Author: | |
|---|---|
| Format: | Theses |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/82741 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | Tapered Roller Bearings (TRBs) are vital components in railway vehicles, functioning to support the rotation of wheels and transmit the load between the wheels and the axle. This ensures that the wheels rotate smoothly and efficiently. However, trains that operate for extended periods and under heavy operational conditions can cause the TRBs to experience wear and damage. If the condition of the TRBs deteriorates, it can disrupt train operations and endanger the safety of both passengers and railway personnel. Therefore, the inspection of TRBs is crucial in maintaining the reliability, operational integrity, and safety of the railway transportation system. One increasingly popular and effective inspection approach is the use of thermal cameras. These cameras, also known as infrared cameras, function by measuring the infrared radiation emitted by objects and producing images based on temperature differences. In the context of railway bearings, an increase in temperature can indicate excessive friction or other issues. By detecting temperature differences at an early stage, preventive maintenance actions can be taken before serious damage occurs, ultimately enhancing safety and maintenance cost efficiency.
This research aims to design a bearing inspection method for railway vehicles utilizing computer vision technology and the YOLO (You Only Look Once) object detection algorithm. The research results indicate that the system can detect and measure bearing temperature with adequate accuracy, achieving a Mean Absolute Error (MAE) of 3.99% and a Root Mean Square Error (RMSE) of 5.35%. This system demonstrates potential for integration with existing railway monitoring and maintenance systems. Advantages of inspection using thermal cameras include the ability to inspect railway bearings under operational conditions without stopping the train or needing direct physical inspection.
|
|---|