Data-model fusion-driven adaptive positioning and control of arc starting points for the intermediate assembly welding of ships

Abstract Precise positioning of the arc starting point is the key to ensuring the accuracy of robot welding. In response to the problem of challenging precise positioning of the arc starting point and efficient control of the intermediate assembly welding of ships, a data-model fusion-driven adaptive positioning and control method for the arc starting point is proposed, and a digital twin-based management and control system for the intermediate assembly welding of ships is developed. In particular, based on boundary representation data and ontology mapping theory, weld seams are extracted from the design model of the intermediate assembly. The initial positioning of the arc starting point is achieved via model-driven methods. Furthermore, the position of the arc starting point is dynamically corrected based on real-time scanning data and multivariate regression methods to yield precise positioning using data-driven methods. The case study results demonstrate that the proposed method effectively improves the positioning accuracy of the arc starting point, and the research provides a technical foundation for the automation welding of intermediate assembly of ships.