Power station boiler combustion modeling and optimization method facing mass high-dimensional data

A high-dimensional data and boiler combustion technology, applied in data processing applications, electrical digital data processing, design optimization/simulation, etc., can solve problems such as insufficient computer resources on a single machine, and achieve high-efficiency training by getting rid of the constraints of computing and storage capabilities Effect

Inactive Publication Date: 2018-05-15
TAIYUAN UNIV OF TECH
View PDF2 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a combustion modeling and optimization method for massive high-dimensional data, so as to solve the pr

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
  • Power station boiler combustion modeling and optimization method facing mass high-dimensional data
  • Power station boiler combustion modeling and optimization method facing mass high-dimensional data
  • Power station boiler combustion modeling and optimization method facing mass high-dimensional data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] Below in conjunction with accompanying drawing, further illustrate the present invention.

[0069] A method for combustion modeling and optimization of power plant boilers oriented to massive high-dimensional data, the specific steps of which are as follows:

[0070] 1. Extract the input data and output data from the historical operation data of the distributed control system of the power plant, and perform data processing on the input data and output data;

[0071] 2. Using the improved distributed extreme learning machine to NO x Emissions are modeled as a boiler combustion emission model, and boiler efficiency is modeled as a boiler combustion efficiency model;

[0072] The boiler combustion emission model is:

[0073]

[0074] Among them, w i =(ω i1 ,ω i2 ,...,ω in ) T is the input weight vector between the network input node of the boiler combustion emission model and the i-th hidden layer node, x j is the jth dimension parameter of the input data of the...

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 power station boiler combustion modeling and optimization method facing mass high-dimensional data, belongs to the field of power station boiler optimization running and particularly relates to the power station boiler combustion modeling and optimization method facing the mass high-dimensional data. The method comprises the following steps that 1, input data and output data are extracted from history running data of a power plant distributed control system and subjected to data processing; 2, the NOx emission amount is modeled to a boiler combustion emission model byusing an improved distributed extreme learning machine, and the boiler efficiency is modeled to a boiler combustion efficiency model; 3, the boiler combustion emission model and the boiler combustionefficiency model are combined, and a multi-target boiler combustion model is established; 4, the multi-target boiler combustion model is converted to a single-target boiler combustion model by adopting a weight coefficient method; 5, the single-target boiler combustion model is subjected to parameter optimization by using a distributed particle swarm algorithm, and optimization control over the boiler combustion process is achieved.

Description

technical field [0001] The invention belongs to the field of modeling and optimal operation of power plant boilers, and in particular relates to a method for establishing a combustion model and multi-objective optimal control aiming at massive high-dimensional data. Background technique [0002] In recent years, due to the good nonlinear processing ability of artificial intelligence technology, it has been widely used in the modeling and optimization of power plant boilers. This method only needs to extract data from the distributed control system (DCS) of the power plant or establish the input and output models of the combustion system according to the data of the boiler combustion adjustment optimization test, and then use the optimization algorithm to optimize the boiler efficiency and pollutant discharge to obtain the boiler efficiency and pollution The comprehensive and optimal operating parameters of pollutant emissions are used to guide the safe and economical operati...

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): G06F17/50G06Q50/06
CPCG06F30/20G06Q50/06
Inventor 续欣莹徐晨晨陈琪谢珺
Owner TAIYUAN UNIV OF TECH
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