RBF (Radial Basis Function) neural network based supercritical boiler nitric oxide discharging dynamic predication method

An ultra-supercritical boiler and neural network technology, applied in the biological neural network model, etc., can solve the problems that do not meet the sensitivity and accuracy requirements of modeling auxiliary variables, and cannot accurately represent the instantaneous pulverized coal amount.

Active Publication Date: 2015-02-04
STATE GRID CORP OF CHINA +2
View PDF7 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The instantaneous coal feed amount cannot accurately represent the instantaneous coal powder amount entering the furnace, and the selection of the inst...

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
  • RBF (Radial Basis Function) neural network based supercritical boiler nitric oxide discharging dynamic predication method
  • RBF (Radial Basis Function) neural network based supercritical boiler nitric oxide discharging dynamic predication method
  • RBF (Radial Basis Function) neural network based supercritical boiler nitric oxide discharging dynamic predication method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.

[0032] The test object of the present invention is Guohua Xuzhou Power Generation Co., Ltd. SG3099 / 27.46-M545 type ultra-supercritical parameter variable pressure operation spiral tube coil direct current furnace. The SCR in the process of increasing the load from 500MW to 1000MW within 24 hours, and then reducing from 1000MW to 500MW Reactor inlet NOx content (dry basis standard state, 6% O2 state).

[0033] Before model training, the invalid data set locked in the probe purge stage should be eliminated first, and the data set should be normalized to the range of [-1,1] according to formula (12), and then restored according to Equation (13) is denormalized.

[0034] x'=(2x-x max -x min ) / (x...

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 an RBF (Radial Basis Function) neural network based supercritical boiler nitric oxide discharging dynamic predication method and belongs to the technical field of environmental protection discharging parameter measurement. According to the technical scheme, the RBF neural network based supercritical boiler nitric oxide discharging dynamic predication method comprises the following steps of SS1 selecting a static auxiliary variable and a dynamic auxiliary variable; SS2 performing RBF neural network structure fitting on the static auxiliary variable and the dynamic auxiliary variable to obtain an RBF neural network structure based training boiler nitric oxide discharging dynamic predication model; adjusting RBF neural network parameters and obtaining an RBF neural network structure based supercritical boiler nitric oxide discharging dynamic predication model. According to the RBF neural network based supercritical boiler nitric oxide discharging dynamic predication method, under conditions that a same training error is set and the like, the number of interior nerve cells of the dynamic model is obviously smaller than that of a static model, the model structure is simple, the training time is short, and the generalization ability is strong.

Description

technical field [0001] The invention relates to a current mainstream ultra-supercritical boiler NOx emission prediction method, in particular to an RBF neural network-based ultra-supercritical boiler NOx emission dynamic prediction method, and belongs to the technical field of environmental protection emission parameter measurement. Background technique [0002] With the development of ultra-supercritical thermal power technology and the increasingly complex power production process, to ensure the stable, efficient, and green operation of production equipment, it is necessary to monitor and monitor important process variables closely related to the system's safe production, economical operation, and environmental protection. optimized control. However, some important parameters are often located in high-temperature, high-pressure, high-dust, and highly corrosive environments, which are difficult to measure directly. Taking the CEMS instrument of a coal-fired power plant as ...

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): G06N3/02
Inventor 张卫庆李凡军熊志化高爱民丁建良柯炎丁苏栋殳建军钱庆生于国强
Owner STATE GRID CORP OF CHINA
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