Method for automatically searching for at least one fabric pattern in a composite reinforcement

CN116569025BActive Publication Date: 2026-06-12SAFRAN AIRCRAFT ENGINES SAS
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SAFRAN AIRCRAFT ENGINES SAS
Filing Date
2021-11-22
Publication Date
2026-06-12

AI Technical Summary

⚠Technical Problem

In the prior art, the identification of fabric defects in composite reinforcements relies on time-consuming visual inspection, which is prone to errors and makes it difficult to accurately detect the consistency between the actual reinforcement geometry and the theoretical shape, leading to performance changes and component rejection.

⚗Method used

Artificial neural networks are used to automatically detect 3D images of composite material reinforcements. By training a database, fabric patterns are identified and the geometry of the reinforcements is reconstructed. Multilayer perceptrons or convolutional neural networks are used for automated detection and comparison.

🎯Benefits of technology

It enables rapid and accurate identification of fabric defects, reduces the risk of errors, improves the consistency of thermophysical and thermomechanical properties of composite reinforcements, and reduces the system rejection rate.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116569025B_ABST
    Figure CN116569025B_ABST
Patent Text Reader

Abstract

The invention relates in one of its aspects to a method for automatically searching for at least one given fabric pattern (3021) in a composite reinforcement (300) comprising a plurality of fabric patterns (3021), each fabric pattern (3021) comprising a plurality of reinforcing yarns (3002) arranged according to a fabric topology (302), the method (100) comprising the steps of: acquiring (301) a three-dimensional image of the composite reinforcement (300); detecting the given fabric pattern in the three-dimensional image of the composite reinforcement using an artificial neural network trained on a training database, searching for the given fabric pattern (3021) on the acquired three-dimensional image.
Need to check novelty before this filing date? Find Prior Art