PROJECT TITLE :
Iterative Local ANFIS-Based Human Welder Intelligence Modeling and Control in Pipe GTAW Process: A Data-Driven Approach
Combining human welder (with intelligence and flexibility) and automatic welding systems (with precision and consistency) will lead to intelligent welding systems. This paper aims to present a information-driven approach to model human welder intelligence and use the resultant model to manage automated gas tungsten arc welding method. To this finish, 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 regulate his arm movement (welding speed) based mostly on his observation on the $64000-time weld pool feedback/image superimposed with an auxiliary visual signal that instructs the welder to extend/reduce the speed. Linear model is 1st identified from the experimental information to correlate welder's adjustment on the welding speed to the three-D weld pool surface and a world 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 that clustering is performed on the input area such that a native ANFIS model is identified. To additional improve the accuracy, an iterative procedure has been performed. Compared to the linear, global and local ANFIS model, the iterative local ANFIS model provides higher modeling performance and divulges additional detailed intelligence human welders possess. To demonstrate the effectiveness of the proposed model as an efficient intelligent controller, automated management experiments are conducted. Experimental results verified that the controller is sturdy beneath different welding currents and welding speed disturbance.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here