Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

NOx emission prediction method of thermal power plant based on generalized mutual entropy auto-encoder

A self-encoder and prediction method technology, applied in prediction, neural learning methods, instruments, etc., can solve the problem of poor robustness of the loss function, and achieve the effect of improving robustness, accurate and reliable prediction, and high practical engineering application value

Active Publication Date: 2020-02-11
TAIYUAN UNIV OF TECH
View PDF9 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention aims at the problem that the stacked autoencoder does not obtain information related to the target value in the training phase, and only uses the feature representation in the last hidden layer for final prediction and the loss function based on mean square error under non-Gaussian noise is poor in robustness , proposed a generalized cross-entropy autoencoder based NO x Emissions Forecast Method

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
  • NOx emission prediction method of thermal power plant based on generalized mutual entropy auto-encoder
  • NOx emission prediction method of thermal power plant based on generalized mutual entropy auto-encoder
  • NOx emission prediction method of thermal power plant based on generalized mutual entropy auto-encoder

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The invention takes real data collected from a PI real-time database system of a power station under the Guodian Group as an experimental object, and trains a gated stacking target correlation autoencoder based on generalized mutual entropy.

[0027] A thermal power plant NO based on generalized cross-entropy autoencoder xEmissions prediction method, the steps are as follows:

[0028] Step 1: Select the boiler load (x 1 ), flue gas oxygen content (x 2 ~x 6 ), primary wind speed (x 7 ~x 12 ), secondary air volume (x 13 ~x 39 ), exhaust gas temperature (x 40 ) and coal quality data (x 41 ~x 43 ), pulverizer feeding amount (x 44 ~x 49 ), the opening parameter of the burnout air baffle (x 50 ~x 57 ) with a total of 57 dimensional parameters as the input of the model, while NO x Emissions are taken as the real output y of the model.

[0029] Step 2: Perform preprocessing on the collected input volume and real output volume. The preprocessing formula is as foll...

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 NOx emission prediction method of a thermal power plant based on a generalized mutual entropy auto-encoder, in particular to a thermal power plant NOx emission prediction method based on a generalized mutual entropy gated stacked target related auto-encoder. The method comprises the following steps: acquiring thermal power plant data including NOx emission and related influence factors, preprocessing all data, taking the related factors influencing NOx emission as input, performing nonlinear dimensionality reduction and feature extraction through an auto-encoder, and establishing a model between the NOx emission influence factors and the NOx emission. The NOx emission prediction method is accurate and reliable in NOx emission prediction and has high practical engineering application value.

Description

technical field [0001] The present invention relates to NO x A method for predicting emissions, specifically a generalized cross-entropy autoencoder-based NO x Emissions Forecasting Methods. Background technique [0002] Facing the increasingly severe environmental problems in China, there is an urgent need for a method that can reduce energy consumption and pollutant emissions of power plant boilers. Boiler combustion optimization technology has always been an effective means to improve boiler efficiency and reduce pollutant emissions. It is of great significance to establish an accurate power plant boiler combustion model and optimize the input parameters of the model. However, how to establish a power plant boiler combustion model to achieve efficient, automatic, fast and accurate prediction of data is particularly important. [0003] Generally speaking, there are three types of soft sensor modeling methods, which are mechanism-based models, knowledge-based models, an...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04G06N3/08G06Q10/04G06Q50/06
CPCG06N3/084G06Q10/04G06Q50/06G06N3/044G06N3/045
Inventor 任密蜂齐慧月巩明月方茜茜马建飞
Owner TAIYUAN UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com