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

Minimization method of product inspection total completion time based on sparkr

A completion time and minimization technology, applied in prediction, genetic rules, genetic models, etc., can solve problems such as data volume expansion, achieve convenient call and operation, and optimize the effect of sequencing large-scale test plans

Active Publication Date: 2021-01-05
无锡启工数据科技有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to overcome the defects and deficiencies in the above-mentioned method, and propose a method for minimizing the total completion time of product inspection based on SparkR, which is better in sorting and capable of large-scale data processing, to solve the problem of existing product test detection Optimization problems in sorting methods, problems of data volume expansion, and problems of combining statistical analysis of data with efficient programming models

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
  • Minimization method of product inspection total completion time based on sparkr
  • Minimization method of product inspection total completion time based on sparkr
  • Minimization method of product inspection total completion time based on sparkr

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] At present, the product testing and testing methods of manufacturing enterprises are mainly based on manual experience, the efficiency is low, and the resource utilization is not sufficient. Moreover, the data volume of product testing and testing tasks continues to expand. The amount of data that can be processed by existing algorithm optimization models is limited by a single machine Large memory capacity makes it impossible to analyze large-scale data. Although the product scheduling method based on Hadoop enables users to process big data, it does not consider the cluster problem, which is not conducive to the scalability of the algorithm model, and the data statistics and analysis capabilities are insufficient. .

[0030]The present invention proposes a method for minimizing the total completion time of product testing plans based on SparkR, aiming at the optimization problems urgently needed to be solved in the existing product test detection and sorting methods, t...

Embodiment 2

[0040] The total completion time minimization method of the product test detection plan based on SparkR is the same as embodiment 1, and the DataFrame described in step (2) of the present invention is a two-dimensional data.frame similar to R created for storing product test detection task data Table, use the schema to represent the name and data type of the product test plan task data column. All the test test task data in the DataFrame are stored in the data type of the JVM. The implementation of a DataFrame method is simply to call the DataFrame on the JVM side. The data processing method directly calls and preprocesses the test detection task data stored in the DataFrame through the R program. The DataFrame API also includes a part of the RDD API. It is necessary to convert the DataFrame into an RDD first, and then call the data grouping, aggregation, and repartition operations of the RDD. In this case, it is necessary to start the R Worker process to perform distributed co...

Embodiment 3

[0043] The total completion time minimization method of the product test detection plan based on SparkR is the same as embodiment 1-2, the mathematical model of determining the test detection task objective function and constraint conditions in the step (3) of the present invention, and the test detection plan scheduling problem includes determining each detection The sequence of inspections on the laboratory and the constraints to be satisfied by the test and inspection tasks in the test plan scheduling problem, where the constraints specifically include:

[0044] (3.1) Each test task consists of several test products, and each test product is tested in different testing rooms. Each test room can only test one test product at the same time, and each test product is Only one test room can be tested at a time. In the present invention, the test product is referred to as product for short.

[0045] (3.2) Each test product must be tested in the testing room designated by the tes...

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 SparkR-based total detection plan completion time minimization method, so as to solve the problems that the task of a test and detection plan in a manufacturing enterprise is complex and the allocation of resources in a detection room is unreasonable. The method comprises steps: DataFrame is created, and the original test plan task data are imported; DataFrame operation is called for data preprocessing; an objective function and constraint conditions are set; a genetic algorithm model is built to optimize ranking of test and detection plans; the optimal test and detection plan rank of products is obtained; the starting time and the completing time of each step are outputted; the minimization completion time for the whole detection plan is outputted; and a visualization package is called to display the test and detection plan rank. In combination of the data processing function and the visualization ability of an R language and with the help of advantages of Spark memory computing and supporting multiple computing models, the whole process is efficient and optimal, a large-scale test task data set can be analyzed and processed, and the completion time of the product test and detection plan is optimized.

Description

technical field [0001] The invention belongs to the technical field of intelligent manufacturing, and mainly relates to the optimization of product testing and testing plan sequencing in intelligent manufacturing, and in particular to a method for minimizing the total completion time of product testing based on SparkR. It is applied to manufacturing enterprises to solve the sequencing problem of large-scale test and inspection tasks, and optimize the test and inspection process in product manufacturing. and intelligent system Background technique [0002] The "total completion time of product testing plan" in intelligent manufacturing refers to the goal of optimizing the total completion time of the test plan in the scheduling of product testing and testing, so that testing and testing resources can be used stably and effectively, and the total turnaround time of testing and testing can be reduced. , to improve work efficiency in manufacturing testing. [0003] In the era ...

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): G06Q10/04G06Q50/04G06N3/12
CPCG06N3/126G06Q10/04G06Q50/04Y02P90/30
Inventor 常建涛孔宪光王奇斌黄小瑜刘尧
Owner 无锡启工数据科技有限公司
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