An Approach to Welding Penetration Control with Neighborhood Rough Set and ANFIS

Abstract Owing to process conditions such as uneven clearance of base metal assembly and welding deformation, it is difficult to obtain well-formed structural welds with robot constant specification parameters welding. Determining how to extract a structured, anti-interference, concise, and dynamic knowledge model from measurable data, and then adjust the welding parameters with corresponding control methods in real time is a central problem to be solved in welding formation control. Hence, this paper proposes a welding penetration control method based on a Neighborhood Rough Set-Adaptive Neuro-Fuzzy Inference System (NRS-ANFIS) to achieve effective penetration control for the GMAW welding process. In orthogonal experiments, the NRS algorithm, which is based on visual sensing to obtain the properties of the weld pool and gap changes, is used to reduce the established frontal weld pool feature information decision table, and the minimum feature set of the weld pool tail width W T and the tail area coefficient C TS is obtained. The minimum feature set of the effective frontal weld pool, real-time line laser distance change, and real-time current information are used as the input for the ANFIS control system. The experimental results for the two groups of time-varying gaps demonstrate that under the condition of no preheating of the base metal, the complete welding penetration rate of the adjusted welding process parameters output by the trained ANFIS model reaches 87%, and the backside melting width is uniform and consistent, which meets the welding specification requirements.