A Nox Emission Prediction Method for Thermal Power Plants Based on Generalized Cross-Entropy Autoencoder

An autoencoder and emission technology, which is applied in the field of NOx emission prediction of thermal power plants based on generalized mutual entropy autoencoder, can solve problems such as poor robustness of loss function, and achieve improved robustness and high practical engineering application value. , predict accurate and reliable results
CN110782013BActive Publication Date: 2022-06-21TAIYUAN UNIV OF TECH
9 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Patents(China)
Current Assignee / Owner
TAIYUAN UNIV OF TECH
Publication Date
2022-06-21

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention is a thermal power plant NO based on a generalized cross-entropy autoencoder x Emissions prediction method, specifically using the gated stacked target correlation autoencoder based on generalized cross-entropy to predict the NO x emissions. The steps included in the method are as follows: collecting thermal power plant data, including NO x Emissions and related influencing factors, preprocessing all data, will affect NO x The relevant factors of emissions are used as input to perform nonlinear dimension reduction and feature extraction through the self-encoder, and the NO x Emission impact factor and NO x Model between emissions. NO x The emission prediction is accurate and reliable, and has high practical engineering application value.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present invention relates to NO x Prediction method of emissions, specifically a generalized cross-entropy autoencoder based NO for thermal power plants x Emissions Prediction Methods. Background technique

[0002] Facing the increasingly severe environmental problems in China, there is an urgent need for a method that can reduce the energy consumption and pollutant discharge of power plant boilers. Boiler combustion optimization technology has always been an effective means to improve boiler efficiency and reduce pollutant emissions. It is very important for the power station to establish an accurate combustion model of the power station boiler and optimize the input parameters of the model. However, how to establish a boiler combustion model in a power plant to achieve efficient, automatic, fast and accurate prediction of data is particularly important.

[0003] Generally speaking, there are three kinds of soft-sensor modeling methods, namely...

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