Knowledge based information processing of the weld pool using neural network in the robotic welding

Author

Ohshima, Kenji ; Hirai, Akira ; Yamane, Satoshi

Author_Institution

Dept. of Electr. Eng., Saitama Univ., Urawa, Japan

fYear

1995

Firstpage

47

Lastpage

51

Abstract

The paper deals with some problems concerning the controlling of the weld pool. The model of the weld pool is represented by using the neural network, since it may be not difficult to describe the model based on state equations. A new method based on the expert´s knowledge is proposed to construct the neural network. The learning time of the proposed network is shorter than the conventional neural network. Moreover, the neural network controller (NNC) is proposed for controlling the weld pool

Keywords

industrial robots; learning (artificial intelligence); neurocontrollers; position control; robots; shape control; welding; knowledge based information processing; learning time; neural network controller; robotic welding; state equations; weld pool; Control systems; Information processing; Input variables; Intelligent networks; Neural networks; Nonlinear control systems; Partial differential equations; Robots; Training data; Welding;

fLanguage

English

Publisher

ieee

Conference_Titel

Industrial Automation and Control: Emerging Technologies, 1995., International IEEE/IAS Conference on

Conference_Location

Taipei

Print_ISBN

0-7803-2645-8

Type

conf

DOI

10.1109/IACET.1995.527538

Filename

527538