矿用皮带机故障预警方法、系统、设备及存储介质
By combining the acoustic signal and motor current signal of the belt conveyor, and using a fault identification method based on feature extraction and fusion modules and dynamic weight generation, the problems of low accuracy and poor real-time performance of existing coal mine belt conveyor fault monitoring have been solved, achieving more accurate fault warning and higher adaptability.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA COAL SCI & TECH GRP NANJING DESIGN & RES INST CO LTD
- Filing Date
- 2025-09-17
- Publication Date
- 2026-07-17
AI Technical Summary
Existing fault monitoring solutions for coal mine conveyor belts rely on manual inspections or local sensors, which are inefficient, have poor real-time performance and coverage blind spots, making it difficult to achieve accurate and reliable fault early warning. In particular, electrical sensors are susceptible to electromagnetic interference in complex underground environments.
By acquiring the associated acoustic signal and motor current signal of the belt conveyor, using optical fiber sensing to collect and convert the signal, and combining the feature extraction module, feature fusion module and fault classifier built by parallel LSTM layer, weights are dynamically generated, and fault identification and early warning are performed based on environmental parameters.
It improves the accuracy and timeliness of fault early warning, enhances the model's adaptability to different environments, and improves the intelligence level and applicability of fault early warning.
Smart Images
Figure CN120986945B_ABST