Abstract
A weightless neural network based intelligent monitoring strategy for automated self-tapping screw insertions is presented in this paper. Problems encountered with automated screw insertion workstations include screw jamming, thread stripping and cross threading. If such problems are not detected early, this could lead to defective assemblies. A weightless neural network is designed and trained to monitor automated screw fastenings. The network is first trained and tested using computer simulations. An experimental test rig is constructed and the weightless neural network is tested using both seen and unseen cases. Experimental results are presented to confirm the effectiveness of the approach.
| Original language | British English |
|---|---|
| Pages | 561-566 |
| Number of pages | 6 |
| State | Published - 1999 |
| Event | 1999 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'99): Human and Environment Friendly Robots whith High Intelligence and Emotional Quotients' - Kyongju, South Korea Duration: 17 Oct 1999 → 21 Oct 1999 |
Conference
| Conference | 1999 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'99): Human and Environment Friendly Robots whith High Intelligence and Emotional Quotients' |
|---|---|
| City | Kyongju, South Korea |
| Period | 17/10/99 → 21/10/99 |