Supercharge Your Innovation With Domain-Expert AI Agents!

Industrial control intrusion detection classifier parameter selection method based on multi-population genetic algorithm

A genetic algorithm and intrusion detection technology, applied in the field of industrial control intrusion detection classifier parameter selection based on multi-swarm genetic algorithm, can solve the problem of low accuracy of the classifier model, avoid easily falling into local optimum, provide accuracy, increase The effect of species diversity

Pending Publication Date: 2021-07-16
BEIJING INSTITUTE OF PETROCHEMICAL TECHNOLOGY
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, a method for selecting parameters of an industrial control intrusion detection classifier based on a multi-population genetic algorithm is provided to solve the inaccuracy of the classifier model constructed by the optimal solution found by the traditional genetic algorithm in the related art. high problem

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
  • Industrial control intrusion detection classifier parameter selection method based on multi-population genetic algorithm
  • Industrial control intrusion detection classifier parameter selection method based on multi-population genetic algorithm
  • Industrial control intrusion detection classifier parameter selection method based on multi-population genetic algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0030] refer to Figure 1~3 , the method for selecting the parameters of the industrial control intrusion detection classifier based on the multi-population genetic algorithm provided by the application includes:

[0031] S101. Acquire data, and set different genetic algorithm parameters according to the characteristics of the classifier and the scale of the problem;

[0032] Specifically, the initialization includes: generating the first-generation population according to the preset encoding method; determining the parameters of the classifier; constructing the classifier; obtaining the fitness value corresponding to the first-generation individuals; storing the first-generation individuals and their fitness values ​​into the preset hash table middle.

[0033] Further, the classifier in the solution provided by this application may be, but not limited to, any one of classifiers such as BPNN, XGBoost, and SVM.

[0034] BPNN is a kind of feedforward neural network. Its output...

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 an industrial control intrusion detection classifier parameter selection method based on a multi-population genetic algorithm, and the method comprises the steps of: obtaining data, and setting different genetic algorithm parameters; randomly generating a specified number of individuals according to a set scale of an initial population, putting each individual of the initial population into a classifier to obtain a corresponding fitness value, sorting according to the fitness values, and dividing the individuals into a population I, a population II and a reserved population from high to low; cyclically controlling the three populations to evolve, wherein different populations adopt different evolutionary modes; after each evolution is finished, putting the optimal individuals of the population I and the population II into a high-quality population; when the cycle is determined to be carried out and before each generation of cycle starts, enabling the reserved population to provide new genotypes for the population I and the population II according to a preset rule; stopping the cycle until the execution reaches a specified number of generations; using a directed evolution operator to evolve the high-quality group again to obtain an optimal individual; and decoding based on the optimal individual to obtain an optimal parameter.

Description

technical field [0001] The invention relates to the related technical field of industrial control network security issues, in particular to a parameter selection method of an industrial control intrusion detection classifier based on a multi-population genetic algorithm. Background technique [0002] Any abnormal intrusion behavior in the industrial control network will cause serious losses, so a high-accuracy, high-robust intrusion detection model is required, while the rule-based intrusion detection method has poor portability, and the construction of the model requires Have a deep understanding of the implementation of application scenarios. [0003] Furthermore, the parameter selection of the classifier model of each intrusion detection model directly affects the final classification result. In the prior art, the accuracy of the classifier model constructed by the optimal solution found by the traditional genetic algorithm is not high. Contents of the invention [000...

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): G06N3/00G06N3/04G06N3/08G06N3/12
CPCG06N3/006G06N3/084G06N3/126G06N3/044G06N3/045
Inventor 刘学君王昊张小妮晏涌沙芸曹雪莹孔祥旻李凯丽
Owner BEIJING INSTITUTE OF PETROCHEMICAL TECHNOLOGY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com