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

Parameter optimization-based method and system for predicting gas concentration in random forest oil

A random forest algorithm and concentration prediction technology, applied in the field of transformers, can solve the problems of poor practicability and robustness, ignore the problem of parameter values, affect the prediction results, etc., and achieve the effect of good applicability and feasibility

Pending Publication Date: 2022-03-15
ELECTRIC POWER RES INST OF EAST INNER MONGOLIA ELECTRIC POWER +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The inventors of the present disclosure found that in the existing method for predicting the concentration of dissolved gas in transformer oil by random forest, the problem of parameter value selection is ignored, which affects the prediction results, and the practicability and robustness of the existing method are poor

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
  • Parameter optimization-based method and system for predicting gas concentration in random forest oil
  • Parameter optimization-based method and system for predicting gas concentration in random forest oil
  • Parameter optimization-based method and system for predicting gas concentration in random forest oil

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] This embodiment provides a method for predicting gas concentration in random forest oil based on parameter optimization, including:

[0047] Obtain the oil chromatographic data of the transformer;

[0048] According to the oil chromatographic data and the preset prediction model of the gas concentration in the oil, the gas concentration in the oil is obtained;

[0049] Wherein, the gas concentration prediction model in oil is obtained through random forest algorithm training; when predicting the gas concentration in oil, the number of decision trees in the random forest, the maximum depth of the decision tree, the minimum number of samples that can be divided into nodes, and the minimum number of leaf nodes The number of samples and the maximum number of leaf nodes are optimized for parameters, and then the optimized parameter values ​​are brought into the random forest algorithm, and the concentration of dissolved gas in transformer oil is predicted.

[0050] In this ...

Embodiment 2

[0094] This embodiment provides a random forest oil gas concentration prediction system based on parameter optimization, including a data acquisition module and a concentration prediction module;

[0095] The data acquisition module is configured to: acquire the oil chromatographic data of the transformer;

[0096] The concentration prediction module is configured to: obtain the gas concentration in oil according to the oil chromatographic data and the preset gas concentration prediction model in oil;

[0097] Wherein, the gas concentration prediction model in oil is obtained through random forest algorithm training; when predicting the gas concentration in oil, the number of decision trees in the random forest, the maximum depth of the decision tree, the minimum number of samples that can be divided into nodes, and the minimum number of leaf nodes The number of samples and the maximum number of leaf nodes are optimized for parameters, and then the optimized parameter values ​...

Embodiment 3

[0099] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps of the method for predicting gas concentration in random forest oil based on parameter optimization described in Embodiment 1 are realized.

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 parameter optimization-based method for predicting gas concentration in random forest oil. The method comprises the following steps: acquiring oil chromatographic data of a transformer; obtaining the gas concentration in the oil according to the oil chromatographic data and a preset prediction model of the gas concentration in the oil; the in-oil gas concentration prediction model is obtained by training through a random forest algorithm; when the gas concentration in oil is predicted, parameter optimization is carried out on the number of decision trees in the random forest, the maximum depth of the decision trees, the node divisible minimum number of samples, the minimum number of samples of leaf nodes and the maximum number of leaf nodes, and then optimized parameter values are substituted into a random forest algorithm. Predicting the concentration of the dissolved gas in the oil of the transformer; according to the method, the five key parameters of the random forest algorithm are optimized, the optimized parameter values are substituted into the random forest algorithm, the concentration of the gas dissolved in the oil of the transformer is predicted, an ideal simulation result is obtained, and the improved random forest algorithm has better applicability and feasibility.

Description

technical field [0001] The disclosure belongs to the technical field of transformers, and in particular relates to a method and system for predicting gas concentration in random forest oil based on parameter optimization. Background technique [0002] As the key equipment in power grid operation, the prediction of the concentration of dissolved gas in the transformer has always been a hot research topic; as a centralized machine learning algorithm with strong generalization ability, the random forest algorithm has a close influence on the performance of the algorithm and the selection of algorithm parameters; currently There are many methods of using random forest algorithm to solve the concentration prediction of dissolved gas in transformer oil. [0003] The inventors of the present disclosure found that in the existing method for predicting the concentration of dissolved gas in transformer oil by random forest, the problem of parameter value selection is ignored, which af...

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): G01N30/02G01N30/86G06K9/62G06N3/12
CPCG01N30/02G01N30/8693G06N3/126G06F18/24323G06F18/214
Inventor 佟敏党乐史昌明刘慧崔亚茹陈忠源张欣伟林阿丽王钰秘立鹏安义岩张琰华李钰莹孔艺慧王哲
Owner ELECTRIC POWER RES INST OF EAST INNER MONGOLIA ELECTRIC POWER
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