Continuous ship unloader chain bucket abnormity identification method and system
Through deep learning technology, the limitations of manual monitoring are solved, and the accurate identification and timely alarm of chain bucket abnormalities are achieved, ensuring the safe and efficient operation of the continuous ship unloader.
Patent Information
- Application Number
- CN202411781773.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-05
- Publication Date
- 2025-03-28
AI Technical Summary
In the prior art, abnormal monitoring of chain bucket continuous ship unloader mainly relies on manual labor, and there are problems of visual fatigue, subjective judgment and high false alarm rate, and it is difficult to monitor the abnormal working conditions of chain bucket in a timely and accurate manner.
The video picture deep learning is used to automatically identify the abnormal working conditions of the chain bucket, and the chain bucket position and guide wheel state are identified through the YOLO-Pose position detection model and PP-YOLO algorithm, and alarm information is output and connected to the PLC to pause the chain bucket lifting action.
It realizes accurate and rapid identification of chain bucket abnormalities, reduces the labor intensity of operation and monitoring personnel, reduces the false alarm and missed rate, and ensures the safe and efficient operation of the continuous ship unloading machine.