A ship composite material structure damage positioning method, device, equipment, medium and product
By setting overlapping subarray sensors on the surface of ship composite material structures and utilizing Lamb wave signals and deep learning technology, the problems of insufficient damage localization accuracy and adaptability in traditional methods are solved, achieving high-precision and low-cost damage localization results.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- NANJING HIGH ACCURATE MARINE EQUIP CO LTD
- Filing Date
- 2026-06-05
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to achieve high-precision and adaptable damage localization in ship composite structures, especially in small-sample scenarios. Traditional non-destructive testing methods suffer from limited applicability, poor model generalization, and insufficient intelligence in multi-sensor fusion.
Overlapping subarray sensors are installed on the surface of the ship's composite material structure. Time-domain signals are acquired by excitation signal of Lamb wave pulse. Damage features are extracted by a three-branch parallel one-dimensional convolutional neural network and an adaptive gated hierarchical attention fusion mechanism. Damage localization is performed by combining cross-domain transfer learning and regularized fully connected regression network.
It achieves high-precision, rotation-invariant damage localization in composite material structures, improving localization accuracy and adaptability under small sample conditions, and reducing detection costs and time.
Smart Images
Figure CN122409845A_ABST