Unlock instant, AI-driven research and patent intelligence for your innovation.

A Boiler Combustion Optimization Control Method

A boiler combustion and optimization control technology, applied in the fields of data analysis and machine learning, can solve problems such as poor performance of nonlinear optimization methods

Inactive Publication Date: 2017-03-29
NORTH CHINA ELECTRIC POWER UNIV (BAODING)
View PDF9 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] Aiming at the problem of poor performance of the current nonlinear optimization method based on the boiler combustion model, the embodiment of the present invention proposes a boiler combustion optimization control 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
  • A Boiler Combustion Optimization Control Method
  • A Boiler Combustion Optimization Control Method
  • A Boiler Combustion Optimization Control Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] A preferred embodiment of the present invention will be described below with reference to the accompanying drawings.

[0064] Collect training samples:

[0065] The thermal test is designed at three typical load levels of 350, 300 and 250MW, and the orthogonal test method is adopted. The test data is representative of the working conditions. A total of 105 groups of thermal test data were selected, 90 groups were selected as training samples, and the remaining 15 groups were used as test samples. Since the characteristics of the boiler will change with the load, in order to improve the performance of the model, the load of the training sample must cover the operating range of the test condition; before the model training, the sample data is normalized to the [−1,1] interval.

[0066] (2) Train the least squares support vector machine (LS-SVM) model:

[0067] The least squares support vector machine has the advantages of strong generalization ability of support vector ...

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 embodiment of the invention provides an optimal control method for combustion of a boiler. The method comprises the steps of selecting training samples to build a training sample set; adopting the training sample set to build a boiler combustion model on the basis of a least squares support vector machine; according to the boiler combustion model, obtaining an optimal sample set to be used as a rule base through optimization of a particle swarm or a genetic algorithm; and on the basis of the rule base, extracting a relation model between the optimal value of variable parameters of the boiler and invariable parameters of the boiler from the base through a fuzzy association rule mining algorithm, and converting the relation model into a fuzzy association rule base. The optimal control method for combustion of the boiler can control combustion of the boiler more precisely and efficiently, and the optimal value of adjustable parameters of the boiler can be found out, and therefore the boiler can be adjusted at any time to achieve the optimal efficiency.

Description

technical field [0001] The invention relates to the technical fields of data analysis and machine learning, in particular to a boiler combustion optimization control method. Background technique [0002] In the face of increasingly intensified resource and environmental constraints, energy conservation and emission reduction will always be an important part of economic development. Coal-fired boilers have always been the main power system in my country, especially in the field of thermal power generation. Therefore, how to effectively control coal-fired boilers to maximize the energy generated by coal-fired is an important aspect of energy conservation and emission reduction. part. Especially with the increasing improvement of energy-saving regulations and standards and the continuous rise of coal prices, under the dual pressure of shrinking profit margins and increasing environmental protection requirements, thermal power plants urgently need to enhance the competition of e...

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 Patents(China)
IPC IPC(8): F23N5/00
Inventor 赵文杰
Owner NORTH CHINA ELECTRIC POWER UNIV (BAODING)