多源数据融合的工业数字孪生建模及决策可视化方法
By constructing a collaborative linkage model of process, equipment, and personnel, the accuracy and real-time issues of multi-source data fusion and collaborative modeling in digital twin models were solved, enabling precise quantitative assessment of risks and benefits and visualization of decisions, thereby improving the safety and efficiency of industrial production.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANGHAI RUNBA INFORMATION TECH CO LTD
- Filing Date
- 2026-05-07
- Publication Date
- 2026-07-17
AI Technical Summary
Existing digital twin models lack accuracy and real-time performance in multi-source data fusion and collaborative modeling decision-making. They cannot achieve deep collaboration and dynamic mapping among processes, equipment, and personnel, and lack multi-dimensional indicator visualization methods for decision-making, making it difficult for managers to quickly and accurately obtain key information.
By acquiring heterogeneous data across all dimensions, and utilizing unified time benchmark alignment and domain knowledge graph-driven semantic mapping and logical repair, a collaborative linkage model of process, equipment, and personnel is constructed. Dynamic coupling indicators and time decay functions are introduced, and a deep collaborative state embedding vector is generated by combining graph attention networks. Risk and benefit indicators are calculated in real time, and a multi-dimensional decision visualization interface is generated.
It has achieved precise quantitative assessment of the three factors of process, equipment, and personnel, improved the safety, efficiency, and quality of production, formed an autonomous intelligent control closed loop, and improved the safety and economy of the production process.
Smart Images
Figure CN122174680B_ABST