Aerospace composite material nondestructive testing method and system based on terahertz spectrum

By converting terahertz spectral signals into two-dimensional time-frequency maps and combining them with time-frequency feature fusion, the problem of incomplete feature extraction in existing technologies is solved, enabling high-precision, rapid, and easily interpretable non-destructive testing of aerospace composite materials, thus meeting the testing requirements of aerospace composite materials.

CN122109008APending Publication Date: 2026-05-29SHANDONG ACAD OF SCI INST OF AUTOMATION +1
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Applications(China)
Current Assignee / Owner
SHANDONG ACAD OF SCI INST OF AUTOMATION
Filing Date
2026-02-05
Publication Date
2026-05-29

AI Technical Summary

Technical Problem

Existing terahertz spectroscopy nondestructive testing algorithms suffer from incomplete feature extraction, poor generalization to small samples, insufficient real-time performance, and difficulty in interpreting results, making it difficult to meet the high-precision, rapid, and easily interpretable testing requirements of aerospace composite materials.

Method used

A non-destructive testing method for aerospace composite materials based on terahertz spectroscopy is adopted. The time-domain signal is converted into a two-dimensional time-frequency graph through continuous wavelet transform. Local and global features are extracted by combining time-domain branching and frequency-domain branching. Feature fusion is performed using a classifier to achieve rapid and accurate detection of defects in composite materials.

Benefits of technology

It improves the signal-to-noise ratio, enhances detection accuracy, can identify minute defects with a diameter of less than 1 mm, shortens detection time, and strengthens the model's generalization ability, making it suitable for the detection needs of various aerospace components.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122109008A_ABST
    Figure CN122109008A_ABST
Patent Text Reader

Abstract

The present application belongs to the technical field of aerospace composite material nondestructive testing, and proposes a method and system for nondestructive testing of aerospace composite materials based on terahertz spectroscopy. The terahertz time-domain signal is converted into a two-dimensional time-frequency graph through continuous wavelet transform. The time-frequency local features of the two-dimensional time-frequency graph are extracted using the time-domain branch, and the frequency-domain global features of the preprocessed frequency-domain signal are extracted using the frequency-domain branch. The extracted time-frequency local features and frequency-domain global features are fused, and the fused features are classified by a classifier to obtain the defect detection result of the composite material to be detected. The present application enhances the signal response through terahertz metasurfaces and combines time-frequency dual-domain feature fusion to solve the problem of insufficient detection accuracy caused by low signal-to-noise ratio, single feature extraction, and small sample size in the prior art, achieving rapid and accurate detection of composite material defects.
Need to check novelty before this filing date? Find Prior Art