Generally welding is one of the most important processes to have a strong influence on the quality and productivity from a manufacture-based industry such as shipbuilding, automotive and machinery. The GMA(Gas Metal Arc) welding process involves large number of interdependent welding parameters which may affect product quality, productivity and cost effectiveness. To solve such problems, mathematical models are required to select the welding parameters for GMA welding process. In this study, the GMA welding process was studied using the information generated during the welding. The statistical analysis of a generalized regression approach was conducted by the following three methods: Firstly using the mathematical model (linear regression, 2nd regression); Secondly GA(Genetic Algorithm) with intelligent models; And finally using response surface analysis of models to develop the relationships between welding parameters and bead width as welding quality.
Determination of the optimal welding parameters to achieve specific weldments on a new material is usually an expensive and time consuming. To determine the welding parameters using Artificial Intelligence (AI) technologies, one must consider many factors including productivity, thermal input, defect formation, and process robustness. Determination of the welding parameters for pipeline welding is based on a skilled welders long-term experience rather than on a theoretical and analytical technique. In this paper, a smart system develops which determines welding parameters and position for each weld pass in pipeline welding based on one database and FEM model, two BP neural network models and a C-NN model. The preliminary test of the system has indicated that the system could determine the welding parameters for pipeline welding quickly, from which good weldments can be produced without experienced welding personnel. Experiments using the predicted welding parameters from the developed system proved the feasibility of interface standards and intelligent control technology to increase productivity, improve quality, and reduce the cost of system integration.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citationsโcitations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.