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

Coal-fired boiler NOx emission prediction method based on intelligent KNN mechanism

A technology of coal-fired boilers and forecasting methods, applied in forecasting, computer components, data processing applications, etc., can solve the problems of expensive online monitoring instruments, increase the burden on power plants, and high operation and maintenance costs, and achieve easy promotion and use, Effects with low implementation difficulty and high compatibility

Pending Publication Date: 2022-05-13
HEBEI UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, online monitoring instruments are expensive, and the operation and maintenance costs are high, which greatly increases the burden on power plants

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
  • Coal-fired boiler NOx emission prediction method based on intelligent KNN mechanism
  • Coal-fired boiler NOx emission prediction method based on intelligent KNN mechanism
  • Coal-fired boiler NOx emission prediction method based on intelligent KNN mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention will NO x The predictive model is converted to a KNN query processing extension model. Assume is the set of all real numbers, and ( d(·,·)) is an n-dimensional real vector space with a distance function d(·,·). suppose is a finite dataset / relation whose schema is R(tid,A 1 ,...,A n ), with n attributes (A 1 ,...,A n ) corresponds to where the i-th dimension Each t=(tid,t 1 ,...,t n ) ∈ R is associated with tid (tuple identifier). R is usually stored as a base table in a relational database system, and |R| represents the size of R, that is, the number of tuples in R.

[0031] Consider query points and an integer K, a KNN query (q,K) is to find in R the sorted set of K-tuples closest to q according to a given distance function d( , ). Assume K<|R|; otherwise, just retrieve all tuples in R. For simplicity, sometimes, KNN query (q, K) is denoted by q, and it is also called top-K, top-k, top-N query.

[0032] The distance function ...

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 coal-fired boiler NOx emission prediction method based on an intelligent KNN mechanism. The method is based on a KNN model, the model adopts a learning-based mechanism and a knowledge base, and a space segmentation method, a Lebesgue integral idea, a clustering algorithm, other algorithms and the like are used. Firstly, a knowledge base is constructed; secondly, an LPBA algorithm is used based on a KNN model, input parameters are partitioned according to output data, and effective tuple clusters are obtained; and finding out the candidate cluster to which the query t belongs, finding out K nearest neighbors of the t, solving the weight of each nearest neighbor, and finally calculating the output of the query t according to a related formula. And the knowledge base needs to be updated continuously. By means of the method, the NOx emission prediction speed of the coal-fired boiler is at the sub-second level, the prediction error is smaller than 5 mg / m < 3 >, the implementation difficulty is low, compatibility to boiler parameters of different dimensions is high, and application and popularization are easy.

Description

technical field [0001] The invention relates to the technical field of coal-fired boiler operation, in particular to a coal-fired boiler NO x Emissions Forecasting Methods. Background technique [0002] Nitrogen oxides (NO x , such as NO and NO 2 ) is an important source of environmental pollution, and many countries in the world strictly control NO x emission concentration. For example, power plants in China must ensure that the NO x The emissions meet the emission standards; otherwise, they will be severely punished by the ecological and environmental professional departments. Therefore, it is necessary to carry out NO x Monitoring and emission concentration control. [0003] NO x Control technologies are mainly divided into two categories: combustion process control and flue gas denitrification. Combustion process control techniques attempt to reduce NO by adjusting controllable variables such as excess air ratio, air distribution pattern, and ratio of primary ai...

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): G06Q10/04G06K9/62G06Q50/26
CPCG06Q10/04G06Q50/26G06F18/24147
Inventor 朱亮宋鑫
Owner HEBEI UNIVERSITY