Research on multi-source data fusion and dynamic modeling technology for industrial production processes based on digital twins

Under the background of Industry 4.0, the manufacturing industry is accelerating towards digitization and intelligence, especially the traditional industries such as garment manufacturing are facing the challenges of complex production process, diverse data sources, and insufficient real-time response capability. To enhance both the effectiveness of integrating multi-source data and the precision of dynamic modeling in industrial production, this study introduces a method rooted in digital twin technology for achieving optimized data fusion and modeling processes. By integrating digital twin technology with 5G, Internet of Things (IoT), Artificial Intelligence (AI) and other advanced means, a fusion mechanism is constructed to cover multi-source heterogeneous data, such as equipment data, production information, sensor data, etc., and a dynamic modeling system is designed to have real-time feedback and self-evolution capabilities. The study shows that this method not only significantly improves the timeliness and accuracy of data processing and modeling, but also effectively optimizes resource allocation and enhances the flexibility and intelligence of the manufacturing system. This study has important theoretical and practical significance for promoting the digital transformation and intelligent upgrading of manufacturing industry.