DocumentCode
3573412
Title
Multi-model predictive control based on neural network and its application in power plant
Author
Guolian Hou ; Xu Bai ; Jinfang Zhang ; Zhilong Zhao
Author_Institution
Sch. of Control & Comput. Eng., North China Electr. Power Univ., Beijing, China
fYear
2014
Firstpage
4379
Lastpage
4383
Abstract
In this paper, the algorithm of multi-model predictive control based on neural network is proposed and applied in 160MW Bell-Åström model. Firstly, the algorithm is described. Each sub-controller is designed based on state space model predictive control, and the global controller is gained from neural network weights. Then, sub-models of Bell-Åström are given. Lastly, multi-model predictive control and constrained multi-model predictive control are applied in Bell-Åström model. The algorithm is effective in controlling the unit and has good performance.
Keywords
neural nets; power plants; power system control; predictive control; Bell-Åström model; multimodel predictive control; neural network; power 160 MW; power plant; state space model predictive control; Aerospace electronics; Algorithm design and analysis; Neural networks; Power systems; Prediction algorithms; Predictive control; Predictive models; Bell-Åström model; Multi-model predictive control; constrained multi-model predictive control; neural network;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Control and Automation (WCICA), 2014 11th World Congress on
Type
conf
DOI
10.1109/WCICA.2014.7053450
Filename
7053450
Link To Document