A Machine Learning-Based Process Programming Method

A process specification and machine learning technology, which is applied to instruments, computer parts, unstructured text data retrieval, etc., can solve time-consuming problems, achieve high efficiency, shorten process preparation time, and shorten compilation time.

Active Publication Date: 2021-10-01
SHENYANG AIRCRAFT CORP
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This editing method is not only time-consuming, but also limited by the personal experience of the craftsman
Although aircraft manufacturers have a very rich historical accumulation, they cannot quickly apply the contents of these historical process regulations to the preparation of new aircraft model process regulations

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 Machine Learning-Based Process Programming Method
  • A Machine Learning-Based Process Programming Method
  • A Machine Learning-Based Process Programming Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The present invention will be further described below in conjunction with specific examples. Different assembly process regulations have some similarities in the assembled parts, so the contents of the assembly process regulations have certain reference.

[0062] A machine learning-based assembly process specification preparation method is implemented through five steps:

[0063] The first step is to analyze the historical process regulations

[0064] Process the data of historical process regulations, carry out cluster analysis on the content of the process regulations in units of work steps, and select the characteristics of work steps in units of each cluster. Such as figure 1 The steps shown are divided into four small steps to analyze the historical process regulations:

[0065] S1) Obtain the content of the work steps of all process regulations, and process the drawing number, part number, part size and other information in the work step with different codes, f...

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 belongs to the technical field of aircraft digital manufacturing, and relates to a process specification preparation method based on machine learning. The unit selects the characteristics of the working steps; processes the characteristic information of the working steps in the historical process regulations; according to the selected characteristic information, the corresponding index information is established for the working steps by means of inverted index; obtains the working steps written by the current user Feature information, process the feature information of the currently written work step; use the index information to calculate the correlation of the features obtained in the first step according to the category, and perform linear weighted scoring on the correlation of these categories, and according to the final scoring result, put The work step content with the highest score is pushed to the user. The invention can greatly shorten the preparation time of the process specification, improve the compilation efficiency of the assembly process specification, and improve the production efficiency.

Description

technical field [0001] The invention belongs to the technical field of aircraft digital manufacturing, and relates to a machine learning-based process specification preparation method. [0002] technical background [0003] The assembly process specification is a technical document that guides aircraft assembly and is an important basis in the aircraft manufacturing process. In the traditional assembly process specification compilation mode, craftsmen need to compile the process specification based on personal experience and find some historical process specification documents. This editing method is not only time-consuming, but also limited by the craftsman's personal experience. Although aircraft manufacturers have a very rich historical accumulation, they cannot quickly apply the contents of these historical process regulations to the preparation of new aircraft model process regulations. Contents of the invention [0004] Aiming at the low utilization rate of historic...

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): G06F16/35G06F40/216G06K9/62
CPCG06F40/289G06F18/23213
Inventor 杨楠褚福广王裴岩王胜任
Owner SHENYANG AIRCRAFT CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap