DocumentCode :
2790889
Title :
Self-adaptive RBF neural network PID control in exhaust temperature of micro gas turbine
Author :
Wang, Jiang-Jiang ; Zhang, Chun-Fa ; Jing, You-Yin
Author_Institution :
Sch. of Energy & Power Eng., North China Electr. Power Univ., Baoding
Volume :
4
fYear :
2008
fDate :
12-15 July 2008
Firstpage :
2131
Lastpage :
2136
Abstract :
Mathematical model of exhaust temperature control in micro gas turbine is introduced. To obtain better performance, a self-adaptive PID control is applied to the exhaust temperature control. The parameters of PID control are tuned by radial basis function (RBF) neural network. In this paper, the RBF neural network is given which has been used extensively in the areas of pattern recognition, systems modeling and identification. The effectiveness and efficiency of the proposed control strategy is demonstrated by applying it to the exhaust temperature control. The simulations show that the dynamic responses of the exhaust control system can be effectively improved and the anti-disturbance of the proposed controller is better than that of the PID controller. However, the learning rate of RBF neural network and PID parameters is not too large due to the great gain of micro gas turbine. Otherwise the output will surge acutely.
Keywords :
gas turbines; learning systems; neurocontrollers; radial basis function networks; self-adjusting systems; temperature control; three-term control; PID control; dynamic responses; exhaust temperature control; learning rate; mathematical model; micro gas turbine; self-adaptive radial basis function neural network; Cogeneration; Cybernetics; Distributed power generation; Global warming; Machine learning; Mathematical model; Neural networks; Temperature control; Three-term control; Turbines; Exhaust temperature control; Micro gas turbine; Neural network; PID control; Radial basis function(RBF); Self-adaptive;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine Learning and Cybernetics, 2008 International Conference on
Conference_Location :
Kunming
Print_ISBN :
978-1-4244-2095-7
Electronic_ISBN :
978-1-4244-2096-4
Type :
conf
DOI :
10.1109/ICMLC.2008.4620758
Filename :
4620758
Link To Document :
بازگشت