Automatic defect detection and identification method for ECPT (eddy current pulsed thermography)

Abstract

The invention discloses an automatic defect detection and identification method for ECPT (eddy current pulsed thermography). The automatic defect detection and identification method comprises steps as follows: a thermal image video is acquired through the ECPT, vectorization is performed, and a new matrix is reconstructed; and principle component analysis and independent component analysis are performed on the new matrix to generate a hybrid matrix and an independent component matrix, column vectors of the hybrid matrix are normalized, locations of the maximums of the column vectors are calculated, an independent component row vector corresponding to the foremost hybrid matrix column vector is selected and converted into a matrix according to original thermal image size so as to position and identify a defect. The automatic defect detection and identification method is combined with an ECPT nondestructive testing physical principle to construct a single-channel blind source separation model and is used for automatic defect detection and identification of a conductor material. The technology can process the ECPT thermal image video directly without manual selection of thermal image or pixel features, so that loss of mass data information is avoided, and the defect can be positioned automatically and accurately.

Description

technical field [0001] The invention belongs to the technical field of non-destructive testing, and more specifically relates to a pulse eddy current thermal imaging defect automatic detection and identification method. Background technique [0002] Non-destructive testing technology is an important means to control product quality and ensure the safe operation of in-service equipment. Eddy current pulsed thermal imaging (ECPT) combines eddy current and thermal imaging technology to realize rapid detection of defects at different depths in a wide range. [0003] At present, ECPT’s detection and characterization of conductor material defects is still limited to the artificial selection of frame images recorded by thermal imaging cameras to identify and locate defects. This type of processing will lose a lot of data information, and cause inaccurate defect detection and positioning, and even wrongly determine defects. quantity. Contents of the invention [0004] The purpos...

AI Technical Summary

Problems solved by technology

[0003] At present, ECPT’s detection and characterization of conductor material defects is still limited to the artificial selection of frame images recorded by thermal imaging cameras to identify and locate defects. This type of processing will lose a lot of data information, and cause inaccurate defect detection and positioning, and even wrongly determine defects. quantity

Images