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

A method and device for automatic feature extraction based on system dynamics graph

A system dynamics and automatic extraction technology, applied in machine learning, instrumentation, design optimization/simulation, etc., can solve the problem that the characteristics of industrial systems are not fully extracted, and achieve the effect of low cost, improved efficiency and high work efficiency

Active Publication Date: 2021-01-05
北京工业大数据创新中心有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to provide a method and device for automatically extracting features based on system dynamics diagrams to solve the problem that the features of existing industrial systems have not been fully extracted and applied to automatic machine learning

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
  • A method and device for automatic feature extraction based on system dynamics graph
  • A method and device for automatic feature extraction based on system dynamics graph
  • A method and device for automatic feature extraction based on system dynamics graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0061] In the present invention, the system dynamics diagram describes the physical causal relationship between different variables on the basis of the connection relationship (P&ID, Piping & Instrumentation Diagram) diagram of the industrial system and the system mechanism; the control logic diagram describes the target control quantity (and its relationship with the original quantity), the relationship between the direct drive con...

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 embodiment of the invention provides an automatic feature extraction method and device based on a system dynamics diagram. The method comprises the following steps: acquiring a control logic diagram and a system dynamics diagram which represent the relationship between equipment in the industrial system; combining the control logic diagram and the system dynamics diagram to obtain a combined target diagram; obtaining at least one structural relationship element in the target graph, wherein the structural relationship element comprises at least one of an anchoring amount, an access, a branch structure and a control loop; and obtaining at least one characteristic quantity for data analysis according to the at least one structural relationship element. Through the basic control logic diagram and the system dynamics diagram, the characteristic quantity capable of being used for the automatic machine learning algorithm is finally obtained, the characteristic variable extraction efficiency in industrial data analysis is improved, and the method and device have the advantages of being low in cost and high in working efficiency.

Description

technical field [0001] The invention relates to the technical field of feature extraction of industrial systems, in particular to an automatic feature extraction method and device based on a system dynamics diagram. Background technique [0002] The purpose of automatic machine learning is to improve the efficiency of machine learning, make full use of information such as data structure characteristics and analysis task characteristics, automatically extract feature variables, and perform algorithm parameter tuning and model selection. Applied to the industrial field, in addition to data characteristics such as time series data, the physical connection relationship of industrial systems, such as pipeline connection relationship (fluid flow distribution, pressure loss along the way, etc.), the dynamic mechanism behind it: material balance, energy balance, etc., and The control logic of the system, etc., there are still many characteristics in the industrial field that have no...

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 Patents(China)
IPC IPC(8): G06F30/27G06N20/00G06F119/14
CPCG06N20/00G06F30/27G06F2119/14
Inventor 田春华李闯马国陆薇刘家扬王岩鹏
Owner 北京工业大数据创新中心有限公司
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