Title :
A novel online model for furnace exit gas temperature of coal-fired boiler
Author :
Liu Zhengfeng ; Wang Jingcheng ; Shi Yuanhao ; Zhang Langwen ; Li Kang
Author_Institution :
Dept. of Autom., Shanghai Jiao Tong Univ., Shanghai, China
Abstract :
Furnace exit gas temperature (FEGT) is the key parameter in the furnace ash fouling monitoring system. Since the standard least squares support vector machine (LSSVM) is not suitable for online identification and control of FEGT, a novel CM-LSSVM-PLS method is proposed to predict FEGT in this paper. In the process of CM-LSSVM-PLS method, c-means cluster (CM) algorithm is used to partition the training data into several different subsets by considering the characteristics of operational data. Submodels are subsequently developed in the individual subsets based on LSSVM method. Partial least squares algorithm (PLS) is employed as the combination strategy. The online updating algorithm is then applied to the CM-LSSVM-PLS model. The proposed online model is verified through operation data of a 300MW generating unit. The simulation results show that the proposed online updating model is effective for online FEGT forecasting.
Keywords :
boilers; furnaces; least squares approximations; power engineering computing; steam power stations; support vector machines; temperature control; CM-LSSVM-PLS method; FEGT; c-means cluster algorithm; coal-fired boiler; furnace ash fouling monitoring system; furnace exit gas temperature; least squares support vector machine; online model; online updating algorithm; partial least squares algorithm; power 300 MW; training data partitioning; Boilers; Computational modeling; Data models; Furnaces; Prediction algorithms; Support vector machines; Vectors; C-means cluster; Coal-fired boiler; Furnace exit gas temperature; Least squares support vector machine; Online updating; Partial least squares;
Conference_Titel :
Control Conference (CCC), 2014 33rd Chinese
Conference_Location :
Nanjing
DOI :
10.1109/ChiCC.2014.6896081
