Research on fault diagnosis in reactor-regenerator system of FCCU based on PSO-SVM

A fault diagnosis method in reactor-regenerator system of Fluidized Catalytic Cracking Unit (FCCU) based on Support Vector Machine (SVM) and Particle Swarm Optimization (PSO) was proposed. The algorithm was implemented for optimization selection for parameter of SVM classifier utilizing global searching property of PSO. A fault diagnosis model in reactor-regenerator System of FCCU based on SVM algorithm was constructed. The results show this fault diagnosis method can achieve high diagnostic accuracy, and this method is practical.