Unlock instant, AI-driven research and patent intelligence for your innovation.

Neural network hybrid optimization method for cement denitration

A neural network and optimization method technology, which is applied in the field of automation industry, can solve the problems that the emission does not meet the national standard, and it is difficult for cement enterprises to accurately control the amount of ammonia injection, and achieve the effect of improving the accuracy and improving the prediction accuracy.

Active Publication Date: 2020-04-10
HANGZHOU DIANZI UNIV +1
View PDF1 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention is aimed at the fact that it is difficult for cement enterprises to precisely control the amount of ammonia sprayed, resulting in NO x Disadvantages such as emissions not meeting national standards, a neural network hybrid optimization method for cement denitrification was proposed

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Neural network hybrid optimization method for cement denitration
  • Neural network hybrid optimization method for cement denitration
  • Neural network hybrid optimization method for cement denitration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] Take the cement denitrification reactor system as an example:

[0053] There is an ammonia injection grid at the entrance of the reactor. The ammonia gas from the liquid ammonia evaporation system passes through an ammonia supply adjustment door, mixes with the diluted air from the dilution fan, and is sprayed out through the nozzle. x Under the action of the catalyst, a selective catalytic reduction reaction occurs to generate water and ammonia. In the process of this system, the amount of ammonia injection is a key control indicator. By establishing a prediction model for the cement denitrification reactor, the unit load, ammonia injection amount, SCR inlet smoke temperature, inlet NO x Concentration, inlet flue gas oxygen content, outlet flue gas oxygen content, and denitrification efficiency are 7 pairs of variables as the input of the model, and SCR outlet NO x Concentration is used as the output of the model.

[0054] Step 1. Collection of cement denitrification...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a neural network hybrid optimization method for cement denitration. The method comprises the following steps: collecting a plurality of variables affecting the outlet concentration in a cement denitration process, and preprocessing the data by using principal component analysis to reduce the data dimension; optimizing the center, the width and the weight of a neural network by using a genetic algorithm and an LM algorithm to obtain a neural network prediction model; and finally inputting the preprocessed data into the model to improve the accuracy of model prediction.The neural network hybrid optimization method of the invention is different from a conventional neural network prediction method, combines data processing and neural network parameter optimization, and improves the prediction precision.

Description

technical field [0001] The invention belongs to the technical field of automation industry and relates to a neural network mixing optimization method for cement denitrification. Background technique [0002] NO x The emission is an unavoidable process in cement production, as the environmental protection department x Increasingly stringent emission limits, low NO x Combustion technology and denitrification technology are widely used in cement enterprises, but at this stage, most cement enterprises are difficult to achieve precise control of the amount of ammonia injection, or even automatic control, resulting in NO x The emissions cannot meet the environmental protection standards required by the state, so this invention proposes a neural network mixing optimization method for cement denitrification, which controls a reasonable amount of ammonia injection and ensures that NO x Emissions meet national standards to avoid secondary pollution. Contents of the invention [...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): B01D53/86G06K9/62G06N3/04G06N3/08G06N3/12B01D53/56
CPCB01D53/8625G06N3/086G06N3/126B01D2251/2062G06N3/045G06F18/2135G06F18/23213
Inventor 于征张日东袁亦斌吴胜王璟琳
Owner HANGZHOU DIANZI UNIV