Deep belief network model based cement clinker free calcium content prediction method

Abstract

The invention relates to a deep belief network model based cement clinker fCaO prediction method. The method comprises the steps that major variables capable of reflecting the firing situation of a cement clinker are preliminarily selected to form an auxiliary variable set, and a prediction variable is the cement clinker fCaO content; a field instrument and an operator recorder respectively acquires auxiliary variables and field data of the cement clinker fCaO content, a grey relational analysis method is adopted conduct dimensionality reduction on the auxiliary variable set; parameters in a deep belief network structure, namely parameters training the deep belief network are determined according to a deep belief network algorithm and sample data volume, and further optimization of weighting and bias of the whole network is achieved; a counter-propagation algorithm is adopted to conduct error correction on the determined parameters in a deep belief network structure, and further a prediction model of the cement clinker fCaO is determined; real-time data of the auxiliary variable set is acquired, and errors of the obtained real-time data of the auxiliary variable set are eliminated according to 3delta criterions; further, the cement clinker fCaO content is predicted.

Description

technical field [0001] The invention relates to the field of prediction of clinker free calcium in a cement firing system, in particular to a method for predicting the content of cement clinker free calcium based on a deep belief network model. Background technique [0002] Cement clinker free calcium (free calcium oxide in cement clinker, fCaO) is the pre-decomposition of cement raw meal in the calciner, high-temperature calcination in the rotary kiln, and finally cooled by the grate cooler without participating in the chemical reaction, and exists in the cement clinker in a free state. calcium oxide in. The content of fCaO in cement clinker is the main factor affecting the stability of cement, which can directly reflect the firing status of the material in the firing zone of the rotary kiln. If the fCaO content of cement clinker is too high, the material will not be calcined sufficiently in the rotary kiln, the clinker strength will be low, and local expansion stress will...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem that the free calcium (fCaO) content of cement is difficult to predict online in real time, the present invention provides a method for predicting the fCaO content of cement clinker based on a deep belief network model (deep belief network, DBN)

Images