Development of an Intelligent On-Line Monitoring System Based on ANFIS Algorithm for Resistance Spot Welding Process

Karama K.K, Ikua B.W., Nyakoe G.N., Abdallah A. A.


This paper presents an on-line quality assessment model based on Adaptive Neuro-Fuzzy Inference System (ANFIS).The ANFIS model is realized for identifying the RSW dynamical system based on given input output data. As a special neural network, ANFIS can approximate all nonlinear systems with less training data, quicker learning speed and higher precision.In this study, a system for monitoring various signals which provide real-time information of nugget formation and growth for RSW is established, and a series of experiments are conducted to research the correlation between these signals and weld quality. These signals include welding current, welding time and dynamic resistance. A set of dynamic resistance patterns are grouped based on their corresponding weld nugget quality, and were selected as the input data to train the proposed ANFIS model. Once the monitoring system had been trained, it was then tested to evaluate its efficiency and validity.The classifier based on ANFIS algorithm indicates the fast classification, showing a total success rate of 82.1 per cent for test data.

Keywords: ANFIS, dynamic resistance, resistance spot welding.

Full Text: PDF
Download the IISTE publication guideline!

To list your conference here. Please contact the administrator of this platform.

Paper submission email:
ISSN (Paper)2224-5782 ISSN (Online)2225-0506
Please add our address "" into your email contact list.
This journal follows ISO 9001 management standard and licensed under a Creative Commons Attribution 3.0 License.
Copyright ©