Infrared thermal imaging coating detection method based on long short-term memory network

Abstract

The invention belongs to the field of infrared non-destructive testing, and specifically relates to an infrared thermal imaging coating detection method, system, and device based on a long-short-term memory network, aiming to solve the problems of poor real-time detection, low accuracy, and poor applicability of existing coating detection methods The problem. The method of the system includes collecting infrared thermal images of the area to be detected of the object before and after being subjected to pulse thermal excitation; processing the infrared thermal images to obtain a background thermal image sequence; and constructing a temperature-time sequence based on the background subtraction thermal image sequence Change the discrete sequence and perform filter processing; based on the filter processing sequence, the transfer cut-off time and coating quality classification results of each position in the area to be detected in the coating thickness direction are obtained through the coating detection network model; based on each transfer cut-off The coating thickness is obtained according to the time, and combined with the corresponding coating quality classification results, the detection result of the area to be detected is obtained. The invention improves the real-time performance, accuracy and applicability of detection.

Description

technical field [0001] The invention belongs to the field of infrared non-destructive testing, and in particular relates to an infrared thermal imaging coating detection method, system and device based on a long-short-term memory network. Background technique [0002] Key parts such as aerospace vehicles and composite materials need to be coated with coatings. The exposed coatings are subject to various stresses, the adhesion between the substrate and the substrate is reduced, and contact debonding, non-contact debonding or even falling off are prone to occur. Issues that affect the implementation of security and functional features of the device. At the same time, for some expensive coatings, the thickness control during spraying has high economic benefits, but the thickness detection of wet coatings is difficult to achieve. Therefore, there is an urgent need for an efficient non-destructive testing method for dry and wet coating quality and thickness, which is used for th...

AI Technical Summary

Problems solved by technology

[0008] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the problems of poor real-time detection of existing coating detection methods, low accuracy of manual feature extraction, and poor applicability to detection of coatings of different types and thicknesses, the first aspect of the present invention , a method of infrared thermal imaging coating inspection based on long short-term memory network is proposed, which includes:

Images