Intelligent method for analysis of the active phase of hydrogenation catalysts: stripe phase identification of UC-S/SC-S

Abstract

In order to realize the intelligent recognition and statistics of hydrogenation catalyst image information, different from traditional methods, this paper presents a new method to judge the active phase by image recognition. Firstly, image enhancement and Gabor filtering are used for image preprocessing to suppress the background and obtain the region with strong contrast. The fringe of the hydrogenation catalyst was extracted using a morphological algorithm. Finally, the edge of the fringe was extracted using a Sobel operator to detect the end of the skeleton line, which realized segmentation and recognition of the hydrogenation catalyst image. This method extracts features through data analysis of a large number of image samples to improve the robustness of the method and reduce the errors caused by manual judgment. The experimental results show that the proposed method has high accuracy and is highly consistent with the traditional method of judging the active phase, which has practical engineering application value.