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

Machine learning algorithm module configuration and automated assembly method for intelligent controller

An intelligent controller and machine learning technology, applied in the direction of adaptive control, general control system, control/regulation system, etc., can solve problems such as assembly of embedded intelligent controller algorithm modules

Inactive Publication Date: 2019-07-05
HANGZHOU DIANZI UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the existing product configuration and problem-solving models cannot be directly applied to the assembly of embedded intelligent controller algorithm modules, and how to express and solve problems for the configuration knowledge in the intelligent controller machine learning algorithm module remains to be studied

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
  • Machine learning algorithm module configuration and automated assembly method for intelligent controller

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] The production process of intelligent controller software products based on software assembly can be divided into two steps: feature selection under the constraints of feature configuration dependencies and feature realization software product selection under the constraints of non-functional application requirements. The former is based on the feature model and establishes a set of features and their relationships that meet the feature configuration dependencies and constraints according to the functional requirements of the specific application. The latter obtains software products that implement the selected features according to the non-functional requirements of the specific application. to assemble.

[0047] Correspondingly, the configuration of software products for intelligent controllers can be divided into two stages: feature configuration and algorithm primitive component configuration, which are used to obtain feature sets and machine learning algorithm primi...

Embodiment 2

[0056] The production process of intelligent controller software products based on software assembly can be divided into two steps: feature selection under the constraints of feature configuration dependencies and feature realization software product selection under the constraints of non-functional application requirements. The former is based on the feature model and according to the functional requirements of the specific application, establishes a set of features and their relationships that meet the feature configuration dependencies and constraints, that is, configuration modeling, and generates the corresponding SWRL configuration rule base; the latter is obtained according to the non-functional requirements of the specific application. Realize the software products with the selected features and assemble them according to the architecture of the intelligent control domain. This process is to use the configuration rule solver to perform semantic reasoning and solve the co...

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 machine learning algorithm module configuration and automated assembly method for an intelligent controller. According to the invention, a configuration model of a machine learning algorithm module is established on the basis of analyzing the development process of a software product based on industrial control, and a configuration solving algorithm is designed to acquirefeature and software sets which meet application requirements in the industrial control field. The method comprises the steps that based on an extended feature model, a configuration rule set is established according to a software production process of industrial control, wherein the rules can describe feature constraints and feature realization diversity; a configuration rule solving algorithm isdesigned to acquire a configuration result set which meets constraints and field application requirements; and the variation spread range of a variable configuration entity and the scalability of a machine learning algorithm are increased through rule reasoning. According to the invention, the machine learning algorithm module configuration and automated assembly method for an intelligent factoryis a key enabling technology for realizing large-scale personalized customized production of intelligent control software.

Description

technical field [0001] The invention relates to a machine learning algorithm module configuration and assembly method, in particular to an intelligent controller-oriented machine learning algorithm module configuration and automatic assembly method. Background technique [0002] The embedded intelligent controller software product configuration method is closely integrated with the product construction, which can support the variability modeling biased towards the implementation level. Since the configuration rules in the configuration model often need to be mapped to system implementation files, when the system scale becomes larger, changes in system modules related to configuration rules may lead to changes in the configuration model. Therefore, the maintenance of variable configuration information is more difficult. Large, requires effective management of the configuration model. [0003] At present, researches related to software products and configurations focus on con...

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): G05B13/04
CPCG05B13/042
Inventor 邬惠峰秦飞巍朱毅明
Owner HANGZHOU DIANZI 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