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

Digital workshop process decision method based on decision tree and expert system

An expert system and process decision-making technology, applied in the field of digital workshops, can solve problems such as low reasoning efficiency, achieve the effects of improving reasoning speed, ensuring completeness, and reducing the amount of matching calculations

Active Publication Date: 2018-06-26
SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the deficiencies of the prior art, the present invention provides a digital workshop process decision-making method based on a decision tree and an expert system, using a decision tree algorithm to train and learn for the digital workshop process production data, generate knowledge rules, and then realize daily Process decision-making rules are found in process production data to overcome the bottleneck of expert knowledge acquisition; in the reasoning process, only the newly added fuzzy facts in the fact base are matched with the fuzzy rule antecedents in the fuzzy rule base, which improves the reasoning speed. Try to avoid the problem of low reasoning efficiency when the number of knowledge rules is large

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
  • Digital workshop process decision method based on decision tree and expert system
  • Digital workshop process decision method based on decision tree and expert system
  • Digital workshop process decision method based on decision tree and expert system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0055] 1) Binning processing of process production data

[0056] Taking the electrolytic cell as an example, the selected process parameter variables are electrolysis temperature and aluminum level, and the process decision result quantity is the daily aluminum output of the electrolytic cell. Such as figure 2 , image 3 , Figure 4 Shown are the 2015 aluminum level data distribution map, the electrolysis temperature data distribution map; the electrolytic cell daily aluminum volume data distribution map, it can be seen that the data distribution span is small, in order to reduce the complexity of the subsequent fuzzy rules based on decision tree production, and To improve the generalization ability of fuzzy rules, set fewer equal-width binning intervals for electrolysis temperature and aluminum level, here we set 3; There are more equal-width binning intervals with more aluminum content, here is set to 5. The self-defined binning intervals of electrolysis temperature, al...

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 relates to a digital workshop process decision method based on a decision tree and an expert system. Binning processing is carried out for process production data, and interval fuzzy process production data is generated; training learning based on a decision tree algorithm is carried out for the fuzzy process production data, fuzzy rules are generated, and the fuzzy rules are inputted to a fuzzy rule database; based on real-time parameter data of a real-time process monitoring database, fuzzy reasoning is carried out by an inference machine through interaction with the fuzzy ruledatabase, and the process decision is generated. The method is advantaged in that training learning of the digital workshop process production data is carried out to generate knowledge rules, processdecision rules are found from the digital workshop daily process production data, and the expert experience knowledge acquisition bottleneck is overcome; in the inference process, new fuzzy facts ina fact database are matched with fuzzy rule antecedents in the fuzzy rule database, the inference speed is improved, and a problem of low inference efficiency caused by the relatively large quantity of knowledge rules can be avoided.

Description

technical field [0001] The invention relates to the technical field of digital workshops, in particular to a digital workshop process decision-making method based on a decision tree and an expert system. Background technique [0002] The digital workshop is the comprehensive application of digitalization and network technology in the production workshop. It integrates the information of numerical control equipment and process design system, production organization system and other management systems to form an integrated manufacturing system with comprehensive information flow automation. Due to the industrial characteristics of the digital workshop process, such as various product specifications, complex structure, and high technical difficulty, higher requirements are put forward for the efficiency, stability and reliability of the digital workshop process decision-making, and the intelligent decision-making technology has opened up for this requirement. The new approach, ...

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): G06Q10/06G06Q50/04
CPCG06Q10/0631G06Q50/04Y02P90/30
Inventor 史海波潘福成里鹏于淼段彬胡国良
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