Multi-disaster type identification device for realizing mine safety intelligent guarantee
By processing sensor data and analyzing spatiotemporal features, combined with an extreme gradient boosting model, the problems of low data correlation and insufficient identification of multiple disasters in existing coal mine disaster monitoring systems have been solved, enabling intelligent identification and accurate early warning of multiple disaster types.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA UNIV OF MINING & TECH
- Filing Date
- 2026-06-12
- Publication Date
- 2026-07-17
AI Technical Summary
Existing coal mine disaster monitoring systems suffer from low data correlation and insufficient depth of intelligent analysis, resulting in a lack of targeted disaster prevention measures, a lack of universality in multi-hazard monitoring and analysis functions, and an inability to effectively identify multiple potential disasters.
Data is processed by a sensor-based first filter to obtain sensor scores. Combined with the weights of mine zoning and sensor type, spatiotemporal features are calculated. An extreme gradient boosting model is used to quantify the distribution of potential disaster types, thereby achieving intelligent identification of multiple disaster types.
It has improved the comprehensiveness and accuracy of disaster early warning, avoided false alarms and missed alarms, effectively identified a variety of potential disasters, and enhanced the level of intelligent safety protection in mines.
Smart Images
Figure CN122407293A_ABST