Research On Forecasting City Central Heating Network Supply Parameters Based On ANFIS

The city central heating network has become a dominating form of supplying central heating in the north of China in winter. The application of condition and computer centralized control in heat supply network improve the level of heating supply system. In this network, Changing Tendency of the Parameters Forecasting will play a key role in controlling and running the city central heating network.At first, this paper expatiates on the basic principles and advantages as well as disadvantages of neural network, fuzzy control. And by virtue of fuzzy logic toolbox of Matlab, we set up adaptive neuro-fuzzy inference system--ANFIS, which is applied to parameters forecasting system. ANFIS is the product of fuzzy inference system and neural network. It can abstract and moderate fuzzy control system and grade of membership functions from given data, which makes the automate creation of fuzzy rules and grade of membership functions possible.Then this paper introduces the application of adaptive neuro-fuzzy inference system on changing tendency of the parameters forecasting and presents a method for thermal power supply parameters modeling and forecasting based on a ANFIS model by analyzing the indefinite information on central heating network, in which the Back Propagation algorithms is used to train the connection weights of the adaptive neural network. It has been shown by the modeling and forecasting results about the central heating network parameters of a supply site in Huhhot Thermal Power Company that the method has good properties of generalization, learning and reflecting capabilities. Thus the parameters forecast method based on the ANFIS is of referential significance for the development of central heating network.