Quality Prediction and Control of Assembly and WeldingProcess for Ship Group Product Based on Digital Twin

In view of the problems of lagging and poor predictability for ship assembly and welding quality control, the digital twin technologyis applied to realize the quality prediction and control of ship group product. Based on the analysis of internal and external qualityfactors, a digital twin-based quality prediction and control process was proposed. Furthermore, the digital twin model of qualityprediction and control was established, including physical assembly and welding entity, virtual assembly and welding model, thequality prediction and control system, and twin data. Next, the real-time data collection based on the Internet of Things and thetwin data organization based on XML were used to create a virtual-real mapping mechanism. Then, the machine learningtechnology is applied to predict the process quality of ship group products. Finally, a small group is taken as an example toverify the proposed method. The results show that the established prediction model can accurately evaluate the welding angulardeformation of group products and also provide a new idea for the quality control of shipbuilding