The feasibility of intelligent welding procedure qualification system for Q345R SMAW

An intelligent welding procedure qualification system has been developed in the current study. In this system, the welding procedure of Q345R is intelligently designed based on GBT25343.3-2010 welding standard. By setting the initial welding parameters including welding methods, base metal, and thickness, the welding procedure results will be launched after four steps reasoning of inference engine. To predict the mechanical properties and complete the welding procedure qualification, these initial welding procedure parameters are taken as the input values by artificial neural networks (ANN). Since the hyperbolic tangent function (tanh) is used in ANN, it performs well in dealing with nonlinear problem and controlling the prediction errors accuracy. To reasonably judge the qualification of the Welding Procedure Specifications, the mechanical properties as the output values are compared with the experimental results. Therefore, the ANN are imported to the expert system to control welding procedure design. Furthermore, the mutually beneficial relationship between them has been established. Artificial neural network provides a new approach to resolve the class of experience knowledge for the expert system. In turn, the expert system with a powerful knowledge base and dynamic database provides a lot of training samples for artificial neural networks.