Neuro-fuzzy modeling of human welder's response to 3D weld pool surface in GTAW

Yu Kang Liu, Weijie Zhang, Yu Ming Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Understanding and modeling of welder response to 3D weld pool surface help develop intelligent welding robotic systems and better train welders. In this paper, a welder's adjustment on the welding current as a response to the 3D weld pool surface as characterized by its width, length, and convexity is studied. A vision sensing system is developed to real-time measure the specular 3D weld pool in gas tungsten arc welding (GTAW). Experiments are designed to produce random changes in the welding speed resulting in fluctuating 3D weld pool surface. Adaptive Neuro Fuzzy Inference System (ANFIS) model is developed for the human welder response in order to correlate the current adjustment to the 3D weld pool surface. To justify the use of the neuro-fuzzy model, linear model has also been fitted and compared. It is found that the proposed ANFIS modeling can derive detailed correlation between the human welder's responses and the weld pool geometry and help better understand the nonlinear response of the human welder to 3D weld pool surfaces.

Original languageEnglish
Title of host publicationProceedings - 2012 IEEE International Symposium on Industrial Electronics, ISIE 2012
Pages875-880
Number of pages6
DOIs
StatePublished - 2012
Event21st IEEE International Symposium on Industrial Electronics, ISIE 2012 - Hangzhou, China
Duration: May 28 2012May 31 2012

Publication series

NameIEEE International Symposium on Industrial Electronics

Conference

Conference21st IEEE International Symposium on Industrial Electronics, ISIE 2012
Country/TerritoryChina
CityHangzhou
Period5/28/125/31/12

Keywords

  • 3D weld pool surface
  • ANFIS
  • human welder response
  • neuro-fuzzy modeling

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering

Fingerprint

Dive into the research topics of 'Neuro-fuzzy modeling of human welder's response to 3D weld pool surface in GTAW'. Together they form a unique fingerprint.

Cite this