论文部分内容阅读
Considering the issues that the control system of the welding gun pose in whole-position welding is complicated and radial basis function neural network (RBFNN) can effectively overcome the weakness of BP network,an intelligent control system of welding gun pose for pipeline welding robot based on RBFNN and expert system is presented in this paper.This control system makes full use of characteristics of RBFNN and expert system.The ADXRS300 micro-mechanical gyro is used as the welding gun position sensor in this system.When the welding gun position is obtained,an appropriate pitch angle can be obtained through the expert knowledge and the numeric reasoning capacity of the RBFNN.ARM is used as the controller to drive the welding gun pitch angle step motor in order to real-time adjust the pitch angle of the welding gun.The experiment result shows that the intelligent control system of welding gun pose using RBFNN and expert system is feasible and it enhances the welding quality.This system has wide application prospect.