Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Power plant combustion process machine learning modeling method based on load resampling

A technology of combustion process and machine learning, applied in the direction of instruments, electrical digital data processing, special data processing applications, etc., to achieve the effect of solving imbalance and ensuring generalization ability

Inactive Publication Date: 2014-05-07
ZHEJIANG UNIV
View PDF3 Cites 3 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 machine learning modeling method for the combustion process of a power plant based on load resampling for the deficiencies of the existing modeling methods

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 plant combustion process machine learning modeling method based on load resampling
  • Power plant combustion process machine learning modeling method based on load resampling
  • Power plant combustion process machine learning modeling method based on load resampling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention will be further described below in conjunction with accompanying drawing.

[0031] Taking the neural network modeling method based on Bayesian regularization as an example, the specific steps for establishing the combustion process model of a power plant based on load resampling are as follows: figure 1 Shown:

[0032] Step 1. Collect real-time operating data from the power plant. The sampling time for thermal power plants is generally 1 minute, and extract steady-state samples from it. Before extracting steady-state samples:

[0033] 1-1. Determine the time window length winSize=60 for steady-state sample extraction, which means 1 hour;

[0034] 1-2. Average the values ​​of the variables in the steady-state time interval to obtain the corresponding steady-state value;

[0035] Step 2. Based on the load, the obtained steady-state samples are divided into training subsets and test subsets:

[0036] 2-1. According to the actual operating range of...

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 power plant combustion process machine learning modeling method based on load resampling. The power plant combustion process machine learning modeling method comprises the steps that (1) a steady sample is extracted from real-time operation data; (2) the sample is divided into a training subset and a testing subset based on a load; (3) a model is trained through obtained training samples, and the generalization ability of the model is verified through testing samples. According to the power plant combustion process machine learning modeling method, the sample is divided into the subsets based on the load, the defects of an existing power plant combustion process modeling method based on thermal state experimental data are overcome, the obtained model can better reflect the feature of the combustion process of a boiler, the problem of malconformation of load distribution of the steady sample of a power plant is solved, and the generalization ability of the model is guaranteed.

Description

technical field [0001] The invention belongs to the field of process system modeling and optimization, and in particular relates to a method for extracting steady state data of a power plant and a machine learning modeling method for the combustion process of the power plant based on load resampling. Background technique [0002] In the process of machine learning modeling, in order to avoid the overfitting of the model and verify the generalization ability of the model, it is often necessary to divide the existing data samples into two or more independent sample subsets. The parameters also need to divide the sample into several equal subsets. In the process of dividing the sample subsets, if the samples are unbalanced (the unbalanced here refers to the inconsistency of the load distribution of the samples: there are more samples on high and low loads, and fewer samples on medium loads), the obtained The sample subsets are prone to significant differences in statistical ch...

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): G06F19/00
Inventor 徐祖华王占能赵均邵之江
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com