Bed temperature modeling of circulating fluidized bed boiler based on PCA and neural network

Dense-phase zone bed temperature is the key parameters of circulating fluidized bed boiler (CFB) in stable combustion and economic operation. There are great significances on building its bed temperature model. A new method based on PCA and neural network is proposed in this paper, meanwhile, the bed temperature model of CFB is established using this method. Firstly, using principal component analysis to make a compression and feature extraction of the field data, eliminating the correlation between data and extracting the principal components which contain sufficient information of initial samples. And then take the principal components as the input vectors of BP neural network, this will reducing the dimension of sample space and computational complexity, while improving the model accuracy. Simulation results show that the method proposed is the effective and superior to traditional methods.