Method of inspecting and evaluating coating state of steel structure and system therefor

A system for inspecting and evaluating a coating state of a steel structure, the system comprising:

• a vision camera configured to acquire a plurality of vision images by photographing a desired region of a surface of an inspection target steel structure to which a coating is applied;
• an exciter configured to heat the steel structure by irradiating a heat source to the steel structure;
• a thermal imaging camera configured to acquire a plurality of thermal images by photographing the desired region of the surface of the steel structure heated by the exciter;
• a moving unit including an unmanned moving body configured to provide a movement while maintaining a desired interval with respect to the surface of the steel structure in a state where the vision camera, the thermal imaging camera, and the exciter are mounted on the unmanned moving body so as to allow the vision camera and the thermal imaging camera to photograph the desired region, and a moving body controller configured to control the movement of the unmanned moving body;
• and
• a control unit configured to execute a computer program to inspect the coating state of the steel structure,
• wherein the computer program includes:
• a preprocessing function of reconstructing the thermal images and the vision images in a dynamic state, which are provided by the vision camera and the thermal imaging camera, into a time-spatial-integrated thermal image and a time-spatial-integrated vision image in a static state, respectively, by performing coordinate transformation according to a time-spatial-integrated coordinate transformation (TSICT) algorithm;
• a function of generating an overlay image by overlaying the time-spatial-integrated vision image with the time-spatial-integrated thermal image;
• a function of detecting deterioration of the coating applied to the steel structure by inputting the overlay image to an artificial intelligence-based coating deterioration detection model constructed by learning a plurality of learning overlay images in advance based on an artificial neural network;
• a function of classifying the deterioration of the coating of the steel structure by characteristics by inputting an image of a coating deterioration region determined according to a position of the detected coating deterioration to a coating deterioration classification model;
• a function of quantifying a size of the deterioration region by processing the image of the coating deterioration region;
• a function of generating a coating deterioration inspection result by combining a result of classifying the coating deterioration by the characteristics and a quantification result;
• a function of inspecting a thickness of the coating of the steel structure by analyzing thermal energy measured from the time-spatial-integrated thermal image based on a coating thickness inspection algorithm;
• and
• a function of calculating a coating grade by comprehensively evaluating a deterioration state inspection result of the coating and a thickness inspection result of the coating based on a predetermined coating evaluation criterion.