Title :
Weightless neural network based monitoring of screw fastenings
Author :
Seneviratne, L.D. ; Visuwan, P. ; Althoefer, K.
Author_Institution :
Dept. of Mech. Eng., King´´s Coll., London, UK
Abstract :
A weightless neural network based intelligent monitoring strategy for automated self-tapping screw insertions is presented. 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
Keywords :
assembling; computerised monitoring; digital simulation; learning (artificial intelligence); neural nets; process monitoring; cross threading; intelligent monitoring strategy; screw fastenings; screw jamming; thread stripping; weightless neural network based monitoring; Assembly; Computerized monitoring; Fasteners; Intelligent networks; Jamming; Joining processes; Neural networks; Testing; Workstations; Yarn;
Conference_Titel :
Intelligent Robots and Systems, 1999. IROS '99. Proceedings. 1999 IEEE/RSJ International Conference on
Conference_Location :
Kyongju
Print_ISBN :
0-7803-5184-3
DOI :
10.1109/IROS.1999.813063