Research on the normalization method for identification of temperature field in intelligent building based on stereographic projection

The identification of temperature filed of monitored region is one of the key steps for the energy efficiency management in intelligent building. In this paper, the identification of temperature field is treated as one optimization problem and the identification structure for that optimization problem is implemented with a RBF neural network. To increase the accuracy of RBF based temperature field identification model, normalization methods based on stereographic projection for raw monitored data are discussed in this paper too. To test the performance of our proposed normalization methods, temperature matrix for the infrared photograph is used in our experiment. Experiment results show that the performance of RBF based temperature field identification model running with data preprocessed by stereographic projection and minimum - maximum method for the identification of temperature field in monitored region is best.