Construction of digital twin workshop integrated with edge computing and deep learning

Abstract This study addresses the challenges of real-time data synchronization and big data processing in the construction of digital twin workshops under the background of intelligent manufacturing. A solution that integrates edge computing with deep learning technology is proposed. Through a multi-layered, modular framework structure, this solution achieves real-time synchronous mapping and interaction between physical workshops and virtual workshops, effectively improving production efficiency, reducing maintenance costs, and ensuring product quality. The edge computing layer in the research is responsible for preprocessing heterogeneous data from multiple sources and making rapid response decisions. Simultaneously, deep learning algorithms are employed to conduct in-depth analysis, forecasting, and optimization of the production process. Case studies demonstrate that this solution can significantly improve equipment utilization and optimize workpiece scheduling, validating its application value in actual manufacturing environments.