基于微量位移识别的老化电缆载流能力评估方法及系统
By using a method based on micro-displacement identification and combining video image processing and frequency domain analysis with an SVR model, the problems of low accuracy and high cost in existing cable current-carrying capacity assessments are solved. This achieves non-destructive and accurate assessment of the current-carrying capacity of aging cables, reducing operational risks and improving measurement accuracy.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HUNAN UNIV
- Filing Date
- 2026-01-09
- Publication Date
- 2026-07-17
AI Technical Summary
Existing methods for assessing the current-carrying capacity of cables suffer from low accuracy, high cost, and potential damage to the cable structure. In particular, the thermocouple method is susceptible to electromagnetic interference, and the fiber Bragg grating method requires invasive installation.
By using a method based on micro-displacement recognition, high-speed industrial cameras are used to acquire video images of cables. Vibration features are extracted by combining the Euler video magnification algorithm and the Horn-Schunck optical flow algorithm. A frequency domain analysis model is constructed, and a mapping relationship between vibration and aging state is established by combining a support vector regression model (SVR) to achieve non-destructive evaluation.
It enables non-destructive and accurate assessment of the current-carrying capacity of aging cables, reduces operational risks, improves anti-interference capabilities and measurement accuracy, and has high generalization ability and reliability in engineering applications.
Smart Images
Figure CN121937403B_ABST