With the deepening of Industry 4.0, intelligent manufacturing has entered a new stage of data-driven development, generating massive amounts of heterogeneous data from multiple sources, such as sensor signals, process parameters, and equipment logs, during the production process. However, traditional intelligent monitoring and decision-making systems suffer from problems such as prominent data silos, low monitoring accuracy, poor real-time decision-making, and inability to adapt to dynamic changes in production conditions, severely restricting the improvement of production efficiency and product quality. To address these issues, this paper first reviews the current research status of multi-source data fusion and intelligent manufacturing process monitoring, then designs an intelligent monitoring and decision-making system based on multi-source data fusion, clarifying the overall system architecture and functional modules; next, it delves into key technologies such as multi-source data preprocessing, feature-level fusion, and decision-level fusion, optimizing corresponding algorithm models to improve data fusion accuracy and decision rationality; finally, the system is tested and verified in an actual intelligent manufacturing workshop. Experimental results show that, compared with traditional systems, the proposed system achieves monitoring accuracy of 98%, 97%, and 99% in parts processing, assembly, and packaging processes, respectively, which are 10, 11, and 9 percentage points higher than traditional single-source systems. It can effectively realize real-time monitoring, accurate early warning, and scientific decision-making in intelligent manufacturing processes, providing reliable technical support for the intelligent transformation and upgrading of manufacturing enterprises.
LIU Congcong (Thu,) studied this question.