Metallurgical enterprise energy consumption prediction method based on integrated long-term and short-term memory network

Abstract

The invention discloses a metallurgical enterprise energy consumption prediction method based on an integrated long-term and short-term memory network. The method comprises the steps of 1, collectingmetallurgical enterprise energy consumption data and performing preprocessing; 2, extracting deep learning features of metallurgical enterprise energy consumption data by using a long-term and short-term memory network; 3, constructing a training set of energy consumption data of a plurality of metallurgical enterprises, and training a support vector regression prediction model of the energy consumption data of the plurality of metallurgical enterprises; and 4, selecting the K trained support vector regression prediction models by using Jensen-Shannon divergence, and fusing the results of theselected support vector regression prediction models by using an adaptive linear normalization combination method. According to the method, the problem of low robustness of the support vector regression prediction model of the energy consumption data of the single metallurgical enterprise can be solved, and the prediction effect of the energy consumption data of the metallurgical enterprise is improved.

Description

technical field [0001] The invention relates to the technical field of energy consumption prediction in metallurgical enterprises, and mainly relates to a method for predicting energy consumption in metallurgical enterprises based on an integrated long-term and short-term memory network. Background technique [0002] Energy is an important material basis for the development of the national economy and an important guarantee for determining the future development of national science and technology, economic development and national defense construction. Energy saving is a long-term strategic policy for my country's economic and social development, and it is also an extremely urgent task at present. However, with the development of the metallurgical industry, the problem of energy has become more and more serious, especially in the production of steel, copper and other products in metallurgical enterprises, if the production plan is arranged unreasonably, or the management met...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above-mentioned problems in the prior art, the present invention provides a metallurgical enterprise energy consumption prediction method based on integrated long-term short-term memory network, in order to fully consider the time characteristics of metallurgical enterprise energy consumption data and the performance of a single prediction model, through The integration method is used to solve the problem of the weak robustness of the support vector regression prediction model of the energy consumption data of a single metallurgical enterprise, so as to improve the prediction effect of the energy consumption data of the metallurgical enterprise

Images