A non-contact multi-scale crack identification method

Abstract

The invention discloses a non-contact multi-scale crack identification method. The method comprises the following steps: (1) acquiring surface image data of a to-be-detected object; (2) converting theimage into a grayscale image; (3) performing threshold processing on the image to separate the crack from the background; (4) setting a local threshold value, processing the selected local area, andremoving stains in the background; (5) extracting independent cracks in the image; (6) performing noise point filtering on the independent cracks, and judging true cracks in the independent cracks; (7) assembling all the true cracks to obtain a final crack image; meanwhile, analyzing the geometrical characteristics of the cracks, and outputting the geometrical information of the cracks. The methodis ingenious in design and convenient to apply, non-contact real-time monitoring of cracks is achieved in mechanical research, and the crack behavior can be monitored in the loading process; meanwhile, automatic monitoring, detection and analysis of cracks in the engineering field can be achieved, and the problem that time and labor are consumed for crack monitoring in the engineering field is solved.

Description

technical field [0001] The invention relates to the technical field of image recognition engineering, in particular to a non-contact multi-scale crack recognition method. Background technique [0002] The appearance of cracks often means the fracture and failure of materials and components (such as concrete-like material components, metal and other texture material components). Therefore, crack behavior is one of the key issues in engineering monitoring and mechanical research. In the research of mechanical science, it is often necessary to closely monitor whether there are cracks on the surface of the component, the condition of the crack tip, and the development direction of the crack, so as to evaluate the condition of the component. At present, the existing technology generally adopts the method of installing sensors or coatings on the surface of components to obtain crack conditions, but the crack initiation location and development path are often unpredictable, so the...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the deficiencies of the above-mentioned prior art, the present invention provides a non-contact multi-scale crack identification method, which can realize non-contact real-time monitoring of cracks in mechanical research, and monitor crack behavior during loading; at the same time, its It can also realize the automatic monitoring, detection and analysis of cracks in the engineering field, and solve the problem of time-consuming and labor-consuming crack monitoring in the engineering field

Images