Neural network-based defect detection method for gluing quality on aircraft skin
US12423796B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Jun 9, 2025 |
| Grant date | Sep 23, 2025 |
| Priority date | — |
| Expiry date | Jun 9, 2045 |
Classification
- Technology area (CPC Y)Emerging Cross-Sectional Technologies
- CPC primaryY02P90/30
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Disclosed in the present invention is a neural network-based defect detection method for gluing quality on aircraft skin. The method includes: data acquisition: taking photos of aircraft skin by using a camera to acquire image data; preprocessing the acquired image data; annotating the data by using annotation software to acquire a data set for network training; establishing a defect detection network model based on feature erasure and boundary refinement, where the defect detection network model includes a feature extraction network, a semantic-guided feature erasure module, a multi-scale feature fusion network, and a defect prediction network based on boundary refinement, which are sequentially connected, the data set is used for training the network model, and trained model parameters are saved; and detecting a directly collected skin gluing image by using the trained network model and outputting detection results.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.