一种核事故场外扩散路网节点风险评估方法
By deploying sensors and cameras at road network nodes, and extracting and fusing radiation dose and video data, the problems of data simplification and risk transmission in off-site nuclear accident assessment methods have been solved, enabling accurate risk assessment and emergency decision support.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENZHEN TECH UNIV
- Filing Date
- 2026-05-13
- Publication Date
- 2026-07-17
AI Technical Summary
Existing methods for assessing the external radiation risk of nuclear accidents rely on a single data source, lack real-time perception of pedestrian dynamics and flow distribution at nodes, make it difficult to integrate multiple types of data, and fail to consider the risk transmission between road network nodes, resulting in assessment results that are out of touch with the actual scenario.
By deploying off-site radiation dose monitoring sensors and high-definition cameras at road network nodes, an adjacency matrix is established, high-dimensional feature vectors are extracted, dimensionality reduction and dynamic correction are performed, and dynamic influence coefficients and cross-node coupling correction values are calculated to achieve fusion evaluation of dual-modal data.
It enables accurate risk assessment of road network nodes outside nuclear accident sites, providing precise basis for emergency evacuation, traffic control and rescue route planning, reducing hardware investment and operation and maintenance costs, and improving the accuracy and reliability of assessment.
Smart Images
Figure CN122196932B_ABST