Cement rotary kiln power consumption prediction method based on convolution-gating recurrent neural network

Abstract

The invention discloses a cement rotary kiln power consumption prediction method based on a gated recurrent neural network, and belongs to the technical field of cement rotary kiln power consumption prediction, and the method comprises the steps: (1) selecting 10 variables related to cement rotary kiln power consumption according to the experience and mechanism of a cement firing process, and fully considering the coupling and time delay among the variables in a cement production process; (2) firstly, extracting coupling features of related input by convolution; (3) extracting time sequence characteristics of the power consumption sequence by using a gated cycle unit network; and (4) calculating and obtaining a prediction result of the power consumption. According to the method, the problems of multivariable and strong coupling of complex working conditions of the rotary cement kiln and difficulty in establishing a mechanism model are solved, the problem of time-varying real delay of variable data is solved, a basis is provided for guiding scheduling of a cement firing process and reduction of comprehensive energy consumption, and a planning scheduling basis can be provided for management of the cement firing process.

Description

technical field [0001] The invention relates to the technical field of power consumption prediction of cement rotary kiln, in particular to a method for predicting power consumption of cement rotary kiln based on convolution-gated cyclic neural network. Background technique [0002] The cement industry is an indispensable raw material industry for my country's economic development, production and construction, and people's lives. The cement firing process is an important process in cement production, and the power consumption is an important parameter to measure the energy consumption of the cement firing process. Accurate prediction can provide a basis for the optimization of cement firing process scheduling and the reduction of comprehensive energy consumption, so the power consumption prediction in the cement firing process is of great significance. [0003] The cement firing process has the characteristics of complexity, randomness and dynamic time delay, so it is difficu...

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved in the present invention is to provide a method for predicting power consumption of cement rotary kiln based on convolution-gated cyclic neural network, which solves the characteristics of multi-variable, strong coupling and difficulty in establishing a mechanism model in complex cement firing conditions. It also solves the time-varying delay problem between variable data and power consumption

Images