A New Soft Sensing Model of C3Concentration of FCCU Based on Chaos-RBF Neural Network

Real-time measuring the C₃ concentration is important for the process of fluid catalytic cracking unit (FCCU), but it's difficult to measure it directly, so soft-sensing method is applied to solve this question. The neural network model based on PCA-RBF and chaos-RBF neural network model are established, and the simulation results are analyzed and compared. The results show that soft sensing model based on chaos-RBF neural network has good precision and quality, and it can meet the demands of process in chemical plant