Concrete Crack Identification Method Based on Improved SSA in the Engineering Management Program

A Concrete structures are widely used in engineering construction, but their cracking problems have an important impact on structural safety and durability. Salp Swarm Algorithm (SSA) is a new type of intelligent optimization algorithm, which has the advantages of simple structure, small number of parameters and easy to operate, and is often used in the fields of image processing and path planning. The study investigates the use of a concrete crack recognition method based on improved SSA in engineering management and creates an improved SSA image segmentation algorithm by combining the area growth image segmentation method with the improved SSA algorithm. The improved SSA image segmentation algorithm is then used to create a GUI-based crack recognition algorithm by combining computer vision technology with the GUI. A crack recognition system based on GUI is constructed. Seams are a common quality hazard in concrete engineering, and traditional detection methods are not only inefficient, but also have the problem of subjectivity. To solve this problem, using machine vision technology in computer technology for crack recognition has become an effective method. Through machine vision technology, crack features can be quickly extracted, reducing manual detection errors, and improving detection efficiency and accuracy. In computer vision technology, the image segmentation algorithm based on the bottle sea scabbard swarm algorithm is an excellent algorithm. This algorithm has the advantages of small computational volume, short time consumption, and good segmentation effect. In order to further improve the accuracy of concrete crack identification, a concrete crack identification method based on improved SSA has been proposed. The main difference between this method and recently published related works is that simple image recognition methods are only suitable for simple crack recognition, while in practical engineering, crack images are complex and variable, and improved crack recognition algorithms are needed to achieve more accurate recognition. The results show that the horizontal coordinates of crack projections are concentrated in the interval of 200~270, the maximum number of pixels in the horizontal direction is about 220, the column positions of cracks are concentrated in the interval of 1~450, and the number of pixel values in the vertical direction is distributed in the interval of 4~18 . In summary, it can be seen that the concrete crack recognition method based on improved SSA has high recognition accuracy.