Neural Fuzzy Logic Control for Gas Tungsten Arc Welding
弧焊过程神经网络模糊控制(英文)

A novel technique, that combines the FLC and neural network (NN) techniques, to control the gas tungsten arc welding (GTAW) process is presented. This technique overcomes the limitations such as the dependency on the experts for fuzzy rule generation, the fuzzy set that is non adaptive, etc. The adaptation of membership function as well as the self organizing of fuzzy rule are realized by the self learning and competitiveness of the NN. This approach facilitates a mechanism for an automatic determination of the fuzzy rule and in process adaptation of membership function for an advanced welding process control. This is because a fixed membership function cannot guarantee the required system performance, as the arc welding process is a highly time variable system. Taking GTAW process welds bead width that regulates the system as the controlled plant, the proposed algorithm has been verified to be highly effective for an arc welding process. Computer simulations confirm that the characteristics of the system have improved notably when compared with a number of currently available methods.