基于红外监测的储煤场防自燃智能报警与消防联动系统
By acquiring infrared and visible light data and combining them with the bucket wheel excavator's pose, a physical occlusion boundary mask matrix is generated to remove metal reflection interference. This enables accurate identification of potential spontaneous combustion points and fire-fighting linkage during the movement of mechanical equipment, solving the problems of false alarms and missed alarms in existing technologies.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HEBEI HANFENG POWER GENERATION CO LTD
- Filing Date
- 2026-03-18
- Publication Date
- 2026-07-17
AI Technical Summary
Existing intelligent alarm and fire-fighting linkage systems for coal storage yards based on infrared monitoring suffer from false alarms and missed alarms because the infrared thermal imager cannot accurately identify potential spontaneous combustion points in areas obscured by metal components during the movement of large mechanical equipment.
The infrared thermal radiation tensor, visible light matrix, and bucket wheel stacker-reclaimer pose coordinate array are obtained by the sensing module. The decoupling module generates a physical occlusion boundary mask matrix to remove the interference of metal surface reflection. The inference module performs frequency domain calculation to reconstruct the temperature field spectrum. The intervention module calculates the fire spray angle to avoid the mechanical motion trajectory, so as to achieve accurate identification and fire linkage.
During the movement of large mechanical equipment, potential spontaneous combustion points can be accurately identified and non-interference fire-fighting linkage can be achieved, reducing the probability of false alarms and solving the problem of missed fire sources in dynamic shadow areas.
Smart Images
Figure CN122416611A_ABST