The article presents a multi-stage algorithm for automatic (without any human, user – diagnostician intervention) detection of vanes-blades (technical objects) and their surfaces on a digital image, combined with color analysis, aimed at determining the technical condition of the tested turbine elements. The images recorded with the use of a camera, containing previously dismantled from the turbine operated stator vanes, were used as the exemplary analysis material. The paper presents the algorithm for the detection of the vanes’ airfoil surfaces with the impact of the applied techniques and methods of image processing and analysis on the final result (software localization of the vane’s trailing and leading edge), Then, the obtained image data, including the structural changes of both the vane’s coating and material (metallographic testing) were correlated with the surface colour scheme (colour segmentation based on the YCbrCr colour space model). Thanks to this approach, areas on the surface of the blade were distinguished, characteristic for proper, overheated and transient condition.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.