Title :
Simulation study on coordinated PID neural network control for boiler-turbine unit
Author :
Wan, Jingfang ; Jiang, Xuezhi ; Wang, Wei
Author_Institution :
Dept. of Thermal Eng., Tsinghua Univ., Beijing, China
Abstract :
A boiler-turbine unit is a complex multivariable system with strong time-variation, uncertainty and coupling. The improvement of its control quality is a key problem for automation improvement in thermal engineering. The PID neural network is a feedforward multiplayer network with a simplified and normalized structure and good static and dynamic properties. Based on the modification of its learning algorithm, a coordinated control system for the boiler-turbine unit has been designed. Simulation results verify the satisfactory decoupling-control property and robustness.
Keywords :
boilers; feedforward neural nets; learning (artificial intelligence); multivariable systems; neurocontrollers; three-term control; PID neural network; boiler-turbine unit; decoupling control; feedforward neural network; learning algorithm; multivariable system; Algorithm design and analysis; Automatic control; Automation; Control systems; Feedforward neural networks; MIMO; Neural networks; Thermal engineering; Three-term control; Uncertainty;
Conference_Titel :
Intelligent Control and Automation, 2002. Proceedings of the 4th World Congress on
Print_ISBN :
0-7803-7268-9
DOI :
10.1109/WCICA.2002.1020707
