Title :
Study on real-time measurement of nugget diameter for resistance spot welding using a neuro-fuzzy algorithm
Author :
Lin, Zhongqin ; Zhang, Yansong ; Chen, Guanlong ; Li, Yongbing
Author_Institution :
Sch. of Mech. Eng., Shanghai Jiao Tong Univ., China
Abstract :
Resistance spot welding (RSW) is still the most successful sheet metal joining method in the automobile industry. However, an effective quality evaluation method has not yet been developed. Real-time quality inspection of RSW is necessary in order to deal with all kinds of problems during welding. This paper developed an experimental system using for measuring electrode displacement. Accordingly based on electrode displacement curve proposes a neuro-fuzzy algorithm to inference nugget diameter online. Inference results showed that among the total number of specimens, 88% were successfully inferred within a range of 1.5% error.
Keywords :
automobile industry; diameter measurement; fuzzy neural nets; fuzzy set theory; gradient methods; inference mechanisms; learning (artificial intelligence); measurement by laser beam; process control; quality control; spot welding; welding electrodes; automobile industry; electrode displacement; electrode velocity; fuzzy if-then rules; gradient-descent algorithm; intelligent weld quality control systems; laser displacement sensor; learning algorithms; membership functions selection; neuro-fuzzy algorithm; nugget diameter; real-time measurement; real-time quality inspection; resistance spot welding; sheet metal joining; Artificial neural networks; Automobiles; Costs; Displacement control; Electrical resistance measurement; Electrodes; Immune system; Manufacturing; Spot welding; Thermal expansion;
Conference_Titel :
Instrumentation and Measurement Technology Conference, 2004. IMTC 04. Proceedings of the 21st IEEE
Print_ISBN :
0-7803-8248-X
DOI :
10.1109/IMTC.2004.1351535
