BP neural network intelligent industrial park energy consumption model establishment method based on principal component analysis

Abstract

The invention discloses a BP neural network intelligent industrial park energy consumption model establishment method based on principal component analysis. According to the method, the historical electricity consumption data of selected terminal users and the coal, oil including gasoline, diesel oil and kerosene, gas including liquefied petroleum gas and natural gas, and electricity energy consumption data of the users are pre-processed, after normalization processing, a gray association coefficient and a gray association matrix are calculated, input variables are selected according to a gray relational degree, principal component analysis is carried out to acquire multiple irrelevant outputs which are taken as inputs of a BP neural network model, a neural network output variable and a hidden layer number are determined, neural network initialization and network training are accomplished, and a park terminal user energy consumption model is established. Through the method, the input variables of the BP neural network energy consumption model can be effectively reduced through principal component analysis, relationships between energy consumption and each terminal user data can be effectively identified, the park terminal user energy consumption model can be more precisely established, and total energy consumption of the users of a whole industrial part can be effectively predicted.

Description

technical field [0001] The invention relates to a method for establishing an energy consumption model of a BP neural network intelligent industrial park based on principal component analysis. Background technique [0002] Energy is an important lifeblood of the country and society, which not only affects the economic growth of the entire country, but also affects the stability of the society. The end users in the intelligent park waste a lot of energy in the production process, and the energy consumption is mainly composed of two parts: one is the energy consumed by the user to maintain industrial production, and this part of the energy is mainly determined by the working characteristics of the user's product line and the product. The other part is similar to general public building users, mainly used to maintain the working environment of the user's building such as temperature, humidity, lighting, and other work-related energy consumption. This part of energy consumption i...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the deficiencies in the prior art, to provide a method for establishing an energy consumption model of a BP neural network intelligent industrial park based on principal component analysis, and to solve the problem that the accuracy of the energy consumption model in the prior art is not high, and users cannot be accurately predicted Technical issues with energy consumption

Images