Composite material defect detection method based on generated kernel principal component thermal image analysis

Abstract

The invention discloses a composite material defect detection method based on generated kernel principal component thermal image analysis, and belongs to the technical field of composite material thermal imaging nondestructive testing. The method comprises the following steps: step 1, acquisition of a thermal image data set of a composite material; step 2, amplification and preprocessing of thermal image data: establishing a spectrum normalization generative adversarial network to generate a thermal image; step 3, establishment of a kernel principal component analysis model: performing feature space mapping and projection matrix calculation; step 4, image reconstruction and defect visualization; and step 5, model performance evaluation. According to the method, a data amplification strategy based on a generative adversarial network and a nonlinear dimension reduction technology based on kernel mapping are adopted to analyze thermal image data with nonlinear characteristics; under the condition that the original thermal image data is less, generating data with the same distribution as the thermal image of the experiment record; a kernel principal component thermal imaging analysis model is adopted to solve the problem that defects and backgrounds are difficult to separate in thermal image analysis, and the visibility of the defects is improved.

Description

technical field [0001] The invention belongs to the technical field of non-destructive detection of thermal imaging of composite materials, and in particular relates to a defect detection method of composite materials based on thermal image analysis of generated nuclear principal components. Background technique [0002] Infrared thermal imager (IRT) has the advantages of fast response, wide measurement range, and intuitive results, and is widely used in the quality evaluation of non-destructive testing of composite products or structures. However, especially in the defect assessment task, it is difficult for IRT to achieve the expected detection results due to the influence of experimental settings and environments. The inhomogeneity and noise of the background in the infrared thermal image are often the main factors affecting the detection accuracy and efficiency. Therefore, it has become a common phenomenon to use data analysis methods to assist in improving IRT performa...

AI Technical Summary

Problems solved by technology

A single test produces only a few dozen thermal images, which often limits the model's ability to perform as expected

Images