Release Time:2019-03-11  Hits:

Indexed by: Conference Paper

Date of Publication: 2010-04-06

Included Journals: Scopus、CPCI-S、EI

Volume: 2

Page Number: 314-317

Key Words: Anti-Surge Control; Predictive Control; LS-SVM; Genetic Algorithm; Compressor

Abstract: An anti-surge nonlinear model predictive control system based on Least-Squared Support Vector Machine (LS-SVM) is proposed to increase the efficiency of compressor. In controller design, a compressor dynamic model is created by LS-SVM. A rolling optimization method combing genetic algorithm and LS-SVM is taken to get better real-time performance. Use the control signal of next equipment's inlet valve as feedforward to adjust the reference trajectory. Simulation and experiment are performed to show the effective of this method.