一种爆炸复合板坯性能检测系统
By combining multi-physics field excitation and synchronous acquisition with deep feature fusion and adaptive recognition technology, the problem of accurate detection of minute defects in complex ultrasonic signal environments has been solved, and efficient and reliable detection of interface defects in exploded composite slabs has been achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BAOJI HAIHUA METAL COMPOSITE MATERIALS CO LTD
- Filing Date
- 2026-03-20
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to accurately detect minute and weak bonding defects in exploded composite slabs in complex ultrasonic signal environments. In particular, the low signal-to-noise ratio caused by acoustic impedance mismatch in the constituent materials and the insufficient generalization ability of traditional detection methods result in a high rate of missed detections, failing to meet the requirements for high-reliability quality testing.
By employing multi-physics excitation and synchronous acquisition, and combining a data acquisition module, a feature fusion module, an adaptive recognition module, and a quantization inversion module, a defect recognition classifier is optimized using a meta-learning framework through deep feature extraction and cross-modal attention fusion. Combined with a quantization regression network constrained by physical information, a quantitative assessment of minute defects in complex interfaces is achieved.
It improves the ability to identify and distinguish minute defects in complex interfaces, reduces the number of calibration samples and model adjustment time required for the inspection of new material slabs, enhances generalization, and achieves efficient and reliable detection from qualitative to quantitative methods.
Smart Images
Figure CN121878034B_ABST