Abstract
A pool imaging system is designed for pipe welding, which can capture clear images of molten pool in grooves and reduce the disturbances of arc light. Robust statistics method was adopted for pool images preprocessing, and the splash in images was inhibited. After segmentation and edge detection, intensity distribution of pool images and welding groove figures are selected as image features and extracted. Then the deviation of the pool and groove is detected, and the vibration amplitude and frequency of molten pool are calculated. Experiments of welding with image processing and features extraction are conducted to verify the effectiveness of the imaging system and the proposed method.
| Original language | English |
|---|---|
| Pages (from-to) | 57-60 |
| Number of pages | 4 |
| Journal | Hanjie Xuebao/Transactions of the China Welding Institution |
| Volume | 29 |
| Issue number | 8 |
| Publication status | Published - Aug 2008 |
Keywords
- Features extraction
- Pipe welding
- Pool image processing
- Seam tracking