Composite insulating material detection method, device and equipment based on terahertz spectrum
By employing terahertz spectroscopy and data processing methods, the challenge of assessing the aging and defect states of composite insulation materials has been solved, enabling efficient and accurate detection and improving the safety and reliability of power systems.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- STATE GRID GANSU ELECTRIC POWER RESEARCH INSTITUTE
- Filing Date
- 2026-03-06
- Publication Date
- 2026-06-30
AI Technical Summary
Existing testing methods are unable to efficiently integrate information related to the aging and defect states of composite insulation materials, making it difficult to accurately assess their performance.
A terahertz-based detection method for composite insulating materials is adopted. By acquiring terahertz time-domain spectrum, frequency-domain spectrum and imaging data, multi-scale decomposition is performed using super-resolution convolutional neural network and stationary wavelet transform. Combined with principal component analysis and target detection model, aging score and defect identification results are generated.
It enables accurate assessment of the aging and defect states of composite insulation materials, improves the efficiency and reliability of detection information generation, and can promptly detect hidden defects, ensuring the stable operation of the power system.
Smart Images

Figure CN122306741A_ABST