A Quality Assurance Technique for Resistance Spot Welding Using a Neuro-Fuzzy Algorithm

摘要

Resistance spot welding is widely used in the field of plate assembly; however, there is currently no satisfactory nonde- structive quality evaluation for this type of welding, either in real time or on-line. Moreover, even though the rate of weld- ing under conditions of expulsion has been high until now, there is still no established method of quality control against expulsion. Accordingly, this paper proposes a quality assurance Technique for resistance spot welding using a neuro-fuzzy Algorithm. Four parameters from an electrode separation sig- Nal, in the case of non-expulsion, and dynamic resistance Patterns, in the case of expulsion, are selected as the fuzzy Input parameters.