Neural network-based SCR intelligent ammonia-spraying optimization method and apparatus

A neural network, BP neural network technology, applied in the field of coal-fired denitrification, to achieve the effect of improving utilization rate, improving denitrification efficiency, and reducing emissions

Active Publication Date: 2017-04-26
BEIJING CPCEP ENERGY CONSERVATION & ENVIRONMENTAL PROTECTION TECH CO LTD
View PDF1 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of the above problems, the present invention is proposed in order to provide a neural network-based SCR intelligent ammonia injection optimization method and device that overcomes the above problems or at least partially solves the above problems, which can effectively reduce the ammonia escape rate and improve the denitrification efficiency. Effectively solve the blockage problem caused by SCR to the air preheater

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-based SCR intelligent ammonia-spraying optimization method and apparatus
  • Neural network-based SCR intelligent ammonia-spraying optimization method and apparatus
  • Neural network-based SCR intelligent ammonia-spraying optimization method and apparatus

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] figure 1 It shows a flow chart of a neural network-based intelligent ammonia injection optimization method for SCR according to an embodiment of the present invention. like figure 1 As shown, the neural network-based SCR intelligent ammonia injection optimization method provided in this embodiment specifically includes the following steps:

[0032] Step S101, when the system load remains constant, divide the ammonia injection pipe grid into n modules according to different regions, adjust the opening valves of the n ammonia injection modules, and collect the ammonia injection volumes of the n ammonia injection modules within a period of time as training Input data, collect the denitrification efficiency and ammonia escape rate of the SCR denitrification system as the training output data, where n is a natural number.

[0033] like figure 2 The schematic diagram of the ammonia injection grid area and catalyst area partition module shown in the diagram divides the amm...

Embodiment 2

[0044] image 3 It shows the flow chart of the neural network-based SCR intelligent ammonia injection optimization method according to the second embodiment of the present invention. like image 3 As shown, the neural network-based SCR intelligent ammonia injection optimization method provided in this embodiment specifically includes the following steps:

[0045] Step S201, model building.

[0046] Step S2011, system modeling.

[0047] Number the n nozzle modules equally divided into n nozzle modules from 1 to n, keep the system load constant, continuously adjust the opening valves of each module, collect the respective ammonia injection volumes of the n nozzles within a period of time, and set n nozzle modules at time t The ammonia injection volume of the module is respectively {x 1 (t),x 2 (t),x 3 (t)...x n (t)}, and these n variables are also input variables at this time. The output variable is the ammonia escape rate y of the SCR denitrification system 1 (t) and d...

Embodiment 3

[0118] Figure 5 A functional block diagram of a neural network-based SCR intelligent ammonia injection optimization device according to Embodiment 3 of the present invention is shown. like Figure 5 As shown, the neural network-based intelligent ammonia injection optimization device for SCR provided in this embodiment specifically includes: an acquisition module 301 , a normalization module 302 , a training module 303 , a prediction module 304 , and an optimization module 305 .

[0119] The acquisition module 301, when the system load is constant, divides the ammonia injection pipe grid into n modules according to different regions, adjusts the opening valves of the n ammonia injection modules, and collects the ammonia injection volume of the n ammonia injection modules within a period of time as Training input data, collecting the denitrification efficiency and ammonia escape rate of the SCR denitrification system as the training output data, where n is a natural number.

...

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 discloses a neural network-based SCR intelligent ammonia-spraying optimization method and apparatus, and relates to the field of a fire coal denitration technology. The method comprises the steps of dividing an ammonia-spraying pipe gate into n modules when system load is unchanged, adjusting valves of n ammonia-spraying modules, collecting ammonia-spraying quantity of the n ammonia-spraying modules within certain time to be used as training input data, and taking denitration efficiency and ammonia escape rate as training output data; performing BP neural network training based on the training input data and the training output data; taking ammonia-spraying quantity of each ammonia-spraying module as test input data, and predicting the denitration efficiency and the ammonia escape rate through a BP neural network model obtained by training; and searching an optimal value from multiple test input data through a genetic algorithm, and adjusting actual ammonia-spraying quantity of each ammonia-spraying module according to the optimal value. By adoption of the scheme, the differentiation control on the ammonia-spraying quantity can be realized, the denitration efficiency is improved, the ammonia escape rate is lowered, and the ammonia-spraying quantity of each ammonia-spraying module can be adjusted according to different targets of power plants flexibly.

Description

technical field [0001] The invention relates to the technical field of coal-fired denitrification, in particular to a neural network-based SCR intelligent ammonia injection optimization method and device. Background technique [0002] Selective Catalytic Reduction (SCR), as a denitrification process with mature technology and good effect, is widely used in denitrification projects of coal-fired power plants. With the implementation of GB13223-2011 "Emission Standards of Air Pollutants for Thermal Power Plants", there are stricter limit requirements for NOx emissions, and most coal-fired power plants need to install SCR denitrification systems. [0003] good NH 3 The uniformity of / NOx mixing and velocity distribution is the key to ensure SCR denitrification efficiency, reduce ammonia slip rate, and increase catalyst life. During the design process of the SCR system, repeated simulation tests are carried out by means of Computational Fluid Dynamics (CFD), and internal compo...

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): G06F19/00G06N3/08
CPCG06N3/084G06N3/086G16C20/10
Inventor 王德俊江浩单选户白云峰初炜马志刚纳宏波
Owner BEIJING CPCEP ENERGY CONSERVATION & ENVIRONMENTAL PROTECTION TECH CO LTD
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap