Comparison of Three Control Methods in Penetration Control of Pulsed Gas Tungsten Arc Welding  

作　　者：陈文杰 陈善本 林涛 

机构地区：[1]Inst. of Welding Technology, Shanghai Jiaotong Univ.

出　　处：《Journal of Shanghai Jiaotong university(Science)》2003年第1期63-66,共4页上海交通大学学报（英文版）

基　　金：National Natural Science Foundation ofChina( No. 5 95 75 0 5 7,No. 5 963 5 160 )

摘　　要：An artificial neural network model for backside bead width was established and three control methods——PID, fuzzy and neuron were designed, simulated and tested. The test results of bead on plate weld of GTAW indicate that the artificial neural network (ANN) modeling and learning control method have more advantages than the conventional method. They show that the ANN modeling and learning control method is an effective approach to real time control of welding dynamics and ideal quality.An artificial neural network model for backside bead width was established and three control methods——PID, fuzzy and neuron were designed, simulated and tested. The test results of bead on plate weld of GTAW indicate that the artificial neural network (ANN) modeling and learning control method have more advantages than the conventional method. They show that the ANN modeling and learning control method is an effective approach to real time control of welding dynamics and ideal quality.

关 键 词：PID control fuzzy control neuron control ANN modeling GTAW 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置] TP183[自动化与计算机技术—控制科学与工程]