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

Edge network state sensing modeling method based on representation learning

An edge network and state-aware technology, applied in biological neural network models, character and pattern recognition, advanced technology, etc., to achieve the effect of improving accuracy

Pending Publication Date: 2022-07-08
SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI +1
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the rise of edge computing also brings new challenges to the security protection of users, edge nodes, and cloud servers in the edge computing network, especially in terms of security and privacy.

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
  • Edge network state sensing modeling method based on representation learning
  • Edge network state sensing modeling method based on representation learning
  • Edge network state sensing modeling method based on representation learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] The present invention will be further described in detail below in conjunction with the accompanying drawings and examples.

[0057] The present invention includes:

[0058] 1. Collect industrial edge network data packets in the real environment;

[0059] 2. Carry out preprocessing projects such as segmentation, deduplication, image transfer, and packaging;

[0060] 3. Establish a representation learning (convolutional neural network) model, pass the packaged training data set into the model for training, and pass the verification data set into the trained model for tuning;

[0061] 4. Pass the test data set into the model for model tuning result test;

[0062] 5. Obtain the optimal model and encapsulate the access edge network for comprehensive state awareness tasks.

[0063] Specifically include the following steps:

[0064] Data collection: The industrial edge network developed on the basis of industrial Ethernet technology and Modbus, S7, DNP3 and other industri...

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 edge network-oriented comprehensive state sensing modeling method based on representation learning on the basis of a deep neural network (DNN) algorithm. According to the method, a convolutional neural network (CNN) taking representation learning as a technical feature is utilized, so that the situation that the feature is manually extracted and directly deployed in an industrial edge network environment can be avoided; original data automatic learning features in the edge network are collected in a bypass monitoring or direct embedding mode, and a comprehensive state perception analysis task is executed. Behavior states generated by different devices and different service logics in an edge network environment are modeled, perceived and detected, and the purpose of perceiving the comprehensive state of an overall framework is achieved.

Description

technical field [0001] The invention belongs to the field of industrial control systems and network edge intelligent computing, in particular to an industrial edge network state perception modeling method based on a deep learning convolutional neural network. Background technique [0002] The world has set off a wave of industry digital transformation, and intelligent technology has taken the lead in the application of manufacturing, electric power, transportation and other industries, and the era of industry intelligence has arrived. In 2015, edge computing entered Gartner's Hype Cycle (technology maturity curve). Edge computing has set off a wave of industrialization. Various industrial and commercial organizations are actively initiating and promoting edge computing research, standards, and industrialization activities. There is a "natural" fit between the network topology of the smart grid and the edge computing architecture. All kinds of terminals can have computing and...

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): H04L41/14H04L67/10H04L9/40G06K9/62G06N3/04
CPCH04L41/145H04L67/10H04L63/1425G06N3/045G06F18/214Y04S10/50
Inventor 赵剑明刘琦刘贤达王天宇张明轩张博文王传君
Owner SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI
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