Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

SCR denitration system bad data identification method based on Elman neural network

A neural network and bad data technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve the problems of validity verification and bad data, SCR denitrification system bad data identification method, unusable and other problems, and achieve strong prediction and recognition ability, avoiding misjudgment, and improving accuracy

Pending Publication Date: 2020-12-01
NORTH CHINA ELECTRIC POWER UNIV (BAODING)
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In terms of flue gas denitrification, the Chinese patent application CN201910138858.7 proposes a life prediction method for SCR flue gas denitrification catalyst based on the Elman neural network model, which fully proves that the neural network has a good nonlinear fitting and prediction ability for the relevant data of the denitrification system, but The main purpose of this method is to predict catalyst activity. The model only involves two parameters of catalyst service time and activity, and cannot be used for the validity verification and bad data identification of related parameters such as flue gas volume and denitration efficiency involved in SCR denitrification system.
Up to now, there is no report on the identification method of bad data of SCR denitrification system

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
  • SCR denitration system bad data identification method based on Elman neural network
  • SCR denitration system bad data identification method based on Elman neural network
  • SCR denitration system bad data identification method based on Elman neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] Denitration system based on bad data identification method of Elman neural network SCR, such as figure 1 and figure 2 , The specific embodiment the steps of:

[0040] Step 1, to obtain accurate sample data from the original system of SCR total 300 groups, each group including sample SCR DeNOx catalyst service time, the amount of flue gas, an inlet NO x Concentration of exports NO x Concentration, denitration efficiency, ejection amount of ammonia, the ammonia-air ratio, temperature of flue gas, ammonia ratio, the SCR denitration catalyst activity of a total of 10 parameters, take the first nine parameters as neural network input parameters, the last parameter as a neural network output parameter, from original sample 5 randomly selected set of samples, the value artificially added error of 10%, after treatment of the samples were normalized according to the following equation (1);

[0041]

[0042] In: Z ni It is normalized parameters Z i , Z i ParametersZ First i Values,...

Embodiment 2

[0056] Denitration system based on bad data identification method of Elman neural network SCR, such as figure 1 and figure 2 , The specific embodiment the steps of:

[0057] Step 1, to obtain accurate sample data from the original system of SCR total 300 groups, each group including sample SCR DeNOx catalyst service time, the amount of flue gas, an inlet NO x Concentration of exports NO x Concentration, denitration efficiency, ejection amount of ammonia, the ammonia-air ratio, temperature of flue gas, ammonia ratio, the SCR denitration catalyst activity of a total of 10 parameters, take the first nine parameters as neural network input parameters, the last parameter as a neural network output parameter, from original sample 5 randomly selected set of samples, the value artificially added error of 10%, after treatment of the samples were normalized according to the following equation (1);

[0058]

[0059] In: Z ni It is normalized parameters Z i , Z i Parameters Z First i Values...

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 provides a method for predicting, estimating and identifying bad data of a denitration system based on an Elman neural network. The method mainly comprises the following steps: acquiringoriginal data, constructing an Elman neural network, learning the neural network, screening, marking bad samples, removing the bad samples, then reconstructing and training the Elman neural network,and finally inspecting and correcting the bad samples by using the trained neural network. According to the invention, the bad data of the denitration system is predicted, estimated and identified based on the Elman neural network; the influence of bad samples on the network prediction precision is reduced by constructing and training the Elman neural network for many times; the subjectivity of manual selection is avoided by randomly testing an original sample; by optimizing sample construction and training the Elman neural network, the identified bad samples are inspected and corrected, misjudgment of the bad samples is avoided, and the method has the advantages of being suitable for large fluctuation and time-varying characteristics of denitration system data parameters, high in identification precision and accuracy and capable of being widely applied to identification of bad data in the field of flue gas denitration.

Description

Technical field [0001] The present invention is in the field of nitrogen oxides control, particularly relates to bad data identification system denitration method of Elman neural network based SCR. Background technique [0002] Selective catalytic reduction (SCR) using the denitration system during operation, in order to ensure stable and efficient operation of the control system, typically in real time through the data collection and monitoring the distributed computer control system (DCS). However, since the data collection instrument failures exist in the process, delays in transmission, recording errors and other issues, the sample often contains some bad data. These adverse interference data only denitration system control, while for the latter the data analysis, the system optimization adverse effects. Therefore, how to identify bad data SCR denitration system for stable and efficient operation is important. [0003] The traditional method is mainly based on bad data identi...

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): G06F30/27G06N3/04G06N3/08
CPCG06F30/27G06N3/08G06N3/045
Inventor 陆强马善为曲艳超陈晨吴洋文张镇西郑树
Owner NORTH CHINA ELECTRIC POWER UNIV (BAODING)
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
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