DocumentCode :
30322
Title :
Iterative Local ANFIS-Based Human Welder Intelligence Modeling and Control in Pipe GTAW Process: A Data-Driven Approach
Author :
YuKang Liu ; YuMing Zhang
Author_Institution :
Dept. of Electr. Eng., Univ. of Kentucky, Lexington, KY, USA
Volume :
20
Issue :
3
fYear :
2015
fDate :
Jun-15
Firstpage :
1079
Lastpage :
1088
Abstract :
Combining human welder (with intelligence and versatility) and automated welding systems (with precision and consistency) can lead to intelligent welding systems. This paper aims to present a data-driven approach to model human welder intelligence and use the resultant model to control automated gas tungsten arc welding process. To this end, an innovative machine-human cooperative virtualized welding platform is teleoperated to conduct training experiments. The welding current is randomly changed to generate fluctuating weld pool surface and the human welder tries to adjust his arm movement (welding speed) based on his observation on the real-time weld pool feedback/image superimposed with an auxiliary visual signal which instructs the welder to increase/reduce the speed. Linear model is first identified from the experimental data to correlate welder´s adjustment on the welding speed to the 3-D weld pool surface and a global adaptive neuro-fuzzy inference system (ANFIS) model is then proposed to improve the model accuracy. To better distill the detailed behavior of the human welder, K -means clustering is performed on the input space such that a local ANFIS model is identified. To further improve the accuracy, an iterative procedure has been performed. Compared to the linear, global and local ANFIS model, the iterative local ANFIS model provides better modeling performance and reveals more detailed intelligence human welders possess. To demonstrate the effectiveness of the proposed model as an effective intelligent controller, automated control experiments have been conducted. Experimental results verified that the controller is robust under different welding currents and welding speed disturbance.
Keywords :
arc welding; fuzzy reasoning; intelligent control; iterative methods; neural nets; pattern clustering; pipes; process control; production engineering computing; telecontrol; 3D weld pool surface; K-means clustering; automated control experiments; automated gas tungsten arc welding process control; automated welding systems; auxiliary visual signal; data-driven approach; fluctuating weld pool surface generation; global adaptive neuro-fuzzy inference system model; human welder intelligence modeling; intelligent controller; intelligent welding systems; iterative local ANFIS; linear model; local ANFIS model; machine-human cooperative virtualized welding platform; pipe GTAW process control; teleoperation; training experiments; weld pool feedback; welding current; Adaptation models; Cameras; Process control; Robot kinematics; Robot sensing systems; Welding; Gas tungsten arc welding (GTAW); k-means clustering; local ANFIS; machine–human cooperative control; machine???human cooperative control; virtualized welding;
fLanguage :
English
Journal_Title :
Mechatronics, IEEE/ASME Transactions on
Publisher :
ieee
ISSN :
1083-4435
Type :
jour
DOI :
10.1109/TMECH.2014.2363050
Filename :
6949113
Link To Document :
بازگشت