Automatic detection and classification of defects in boiler pressure vessels based on simulated annealing algorithm

Abstract In recent years, frequent incidents of pressure vessel explosions have posed a serious threat to national construction and the safety of people’s lives and property to a certain extent. Boiler pressure vessels are a type of special equipment that can pose safety hazards during long-term operation. Therefore, it is necessary to carry out proper inspection of boiler pressure vessels. However, conventional inspection methods can not only affect the normal operation of the boiler, but also cause wear and tear to the boiler. Human factors are the main reason affecting the regular inspection and defect handling results of boiler pressure vessels in the power workshop of smelters. The existing methods for handling common defects mainly rely on the experience of maintenance personnel, and cannot accurately handle internal defects of boiler pressure vessels. To achieve accurate identification of defects in boiler pressure vessels, and improve the precision and detection efficiency of defect assessment, this paper proposes an automatic detection and classification method for boiler pressure vessel defects based on a simulated annealing algorithm (SAA). This method utilizes SAA optimized support vector machine (SVM) classifier to achieve efficient automatic detection and classification of boiler pressure vessel defects. The experimental results show that this method greatly improves the detection efficiency of boiler pressure vessel defects, and has good performance and application value.