An approach to the identification of temperature in intelligent building based on feed forward neural network and genetic algorithm

Methods for the identification of temperature in intelligent building and building equipments is one of hot topics focused by lots of researchers in that research area. To implement the process of inspecting and forecasting of energy efficiency in building and its accessory, a feed forward neural network is used as the identification structure for temperature identification of internal space in building in this paper and Identification parameters of the identification structure optimized with genetic algorithm is given in this paper too. The number of neurons in input layer of desired network is optimized with RBF neural network and the number of neurons in hidden of the desired network is optimized with BP neural network in our experiment. Experimental results show that the precision and stability of our proposed method are good enough with time requirement satisfied.