A method and a system for on-line prediction of free calcium oxide content of cement clinker

Abstract

The invention discloses a method and a system for on-line prediction of free calcium oxide content of cement clinker. The method includes: obtaining the input vector and output vector of the deep belief network model; according to the input vector and output vector, constructing a deep belief network model for calcium oxide content prediction; acquiring a plurality of training samples of a deep belief network model, wherein the training samples include input samples and output samples; according to the training samples, repeatedly training the depth belief network model, and generating the depth belief network model after training; obtaining the input variables related to the free calcium oxide index in the cement firing process as the current input vectors, wherein the input vectors are the input vectors introduced into the time series; obtaining the free calcium oxide content of cement clinker d by predicting the depth of belief network model after the current input vector is input into the training. The invention can solve the problem of time-varying delay between the variable data and the free calcium oxide index in the cement firing process.

Description

technical field [0001] The invention relates to the field of prediction of free calcium oxide content in cement production, in particular to an online prediction method and system for free calcium oxide content of cement clinker. Background technique [0002] The content of free calcium oxide in clinker in the process of cement firing is an important standard to measure the quality of cement. It indicates the remaining degree of calcium oxide combined with silicon oxide, aluminum oxide and iron oxide in the raw meal calcining. Its level directly affects the cement quality. Clinker strength. Therefore, accurate prediction of free calcium oxide content in cement clinker can provide a basis for further optimization of cement clinker quality. At present, the content of calcium oxide in cement clinker is difficult to detect online, and its content is obtained mainly by manual sampling and testing, which has a large lag, and it is difficult to ensure real-time optimization of cem...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide an online prediction method and system for the content of free calcium oxide in cement clinker, which solves the problem of time-varying time delay between the variable data and the free calcium oxide index in the cement firing process

Images