LU504090B1 - Multi-link quality detection prediction system based on big data - Google Patents

Multi-link quality detection prediction system based on big data Download PDF

Info

Publication number
LU504090B1
LU504090B1 LU504090A LU504090A LU504090B1 LU 504090 B1 LU504090 B1 LU 504090B1 LU 504090 A LU504090 A LU 504090A LU 504090 A LU504090 A LU 504090A LU 504090 B1 LU504090 B1 LU 504090B1
Authority
LU
Luxembourg
Prior art keywords
production
quality detection
data
module
prediction system
Prior art date
Application number
LU504090A
Other languages
French (fr)
Inventor
Ying Yang
Original Assignee
Univ Guangxi
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Univ Guangxi filed Critical Univ Guangxi
Priority to LU504090A priority Critical patent/LU504090B1/en
Application granted granted Critical
Publication of LU504090B1 publication Critical patent/LU504090B1/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0639Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06395Quality analysis or management
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/04Manufacturing
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40Business processes related to the transportation industry
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q90/00Systems or methods specially adapted for administrative, commercial, financial, managerial or supervisory purposes, not involving significant data processing

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • General Health & Medical Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Data Mining & Analysis (AREA)
  • Manufacturing & Machinery (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Automobile Manufacture Line, Endless Track Vehicle, Trailer (AREA)

Abstract

The invention discloses a multi-link quality detection prediction system based on big data, which comprises a data acquisition module for acquiring historical production data of automobiles; A model construction module connected with the data acquisition module and used for constructing an initial deep learning model and training the initial deep learning model based on historical production data to obtain a target deep learning model; The quality detection module is connected with the model construction module and used for inputting the production data obtained in real time into the target deep learning model for quality detection prediction and obtaining a prediction result; And the production adjustment module is connected with the quality detection module and used for comparing the predicted result with the historical production result, and if there is a difference, adaptively adjusting the production parameters according to the historical production result.

Description

DESCRIPTION LU504090
MULTI-LINK QUALITY DETECTION PREDICTION SYSTEM BASED ON BIG
DATA
TECHNICAL FIELD
The invention belongs to the field of quality detection, in particular to a multi-link quality detection prediction system based on big data.
BACKGROUND
With the development of China's economic construction and social progress, private cars have entered people's daily lives and gradually become people's necessities. With the frequent occurrence of automobile quality and safety accidents, people are more and more aware of the importance of automobile quality and safety, which requires industrial production enterprises to carry out quality detection and evaluation on manufactured automobile products. The existing off-line detection system of vehicle production line can't realize fully automatic off-line configuration and off-line detection, and all departments can't realize server platform operation. Therefore, it is necessary to design a multi-link quality detection and prediction system based on big data, which can measure the quality distribution and have a long service life.
SUMMARY LU504090
In order to achieve the above objectives, the present invention provides the following scheme: a multi-link quality detection prediction system based on big data, including:
The data acquisition module is used for acquiring historical production data of automobiles;
A model construction module connected with the data acquisition module and used for constructing an initial deep learning model and training the initial deep learning model based on the historical production data to obtain a target deep learning model:
The quality detection module is connected with the model construction module and used for inputting the production data obtained in real time into the target deep learning model for quality detection prediction and obtaining a prediction result;
And the production adjustment module is connected with the quality detection module and used for comparing the predicted result with the historical production result, and if there is a difference, adaptively adjusting the production parameters according to the historical production result.
Preferably, the data acquisition module comprises a first acquisition unit and a second acquisition unit;
The first acquisition unit is used for acquiring production parameter data of production equipment in each production workshop; The production parameter data includes stamping data, welding data, painting data and assembly data:
The second acquisition unit is used for acquiring the production image data of each automobile part.
Preferably, the stamping data is obtained based on stamping production equipment, which includes a punch seat for placing parts, a hydraulic press arranged above the punch seat, and a punch connected to the hydraulic press;
The stamping production equipment is connected with an external processing support device, a damping spring device is installed at one side of the bottom of the external processing support device, an adjusting device is installed at the center of the bottom of the external processing support device, the adjusting device is connected witHJ504090 the bottom of the damping spring device, the adjusting device is connected with a deburring device, and the deburring device is embedded with a positioning strip.
Preferably, the quality detection and prediction system further comprise a processing module, which is connected with the second acquisition unit and used for image processing operations such as image cutting, image rotation, image mirroring, image enhancement, image mosaic, spatial filtering, smoothing, projection change and numerical statistics.
Preferably, that production quality detection carry out by the quality detection module includes car body weld quality scanning detection, car body surface smoothness detection, car seal detection, tire hub quality detection, car machine circuit safety detection, brake detection and fender production strength detection.
Preferably, the quality detection module includes a quality detection identification unit, a type identification unit and a position identification unit;
The quality detection identification unit is used for identifying and judging whether the production image to be identified has production quality problems;
The category identification unit is used for identifying the production quality category information of the production image with quality problems;
The position identification unit is used for corresponding the quality position icon of the production image with the position information of the production parts to obtain the position information of the production parts.
Preferably, the quality detection and prediction system further comprise an alarm module, which is respectively connected with the quality detection module and the production adjustment module, and is used for giving an alarm according to the parts yield result of quality detection;
The alarm module comprises a yield threshold dividing unit and an alarm unit;
The yield threshold dividing unit is used for setting different yield thresholds according to different automobile parts;
The alarm unit is used to judge whether the yield of automobile parts is lower than the yield threshold, and if it is lower than the yield threshold, a background alarm display is performed, and the production adjustment module performs adaptive adjustmeht/504090 according to the production parameters of the production line parts displayed by the alarm.
Preferably, the alarm unit includes an acoustic alarm device and a photoelectric alarm device.
Compared with the prior art, the invention has the following advantages and technical effects:
Based on the deep learning model of big data, the deep learning model is trained by a large number of historical production data and then the quality detection quality is predicted, so that the quality detection of a plurality of automobile parts production lines can be realized, such as whether the outside of the automobile is clean or not, the quality distribution inside the automobile parts can be detected, and the detection fixture can be prevented from being damaged by inferior automobile parts in the detection process, and the service life of the detection fixture can be prolonged.
The invention realizes multi-link quality detection of automobiles in an automatic and intelligent way, has the advantages of high detection efficiency and accuracy, can effectively reduce the production cost of enterprises and improve the economic benefits of enterprises.
BRIEF DESCRIPTION OF THE FIGURES LU504090
The accompanying drawings, which constitute a part of this application, are used to provide a further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application, and do not constitute an improper limitation of this application. In the attached drawings:
Fig. 1 is a schematic diagram of the system structure of an embodiment of the present invention.
DESCRIPTION OF THE INVENTION
It should be noted that the embodiments in this application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail with reference to the attached drawings and examples.
It should be noted that the steps shown in the flowchart of the accompanying drawings may be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order from here.
As shown in fig. 1, a multi-link quality detection prediction system based on big data provided by the present invention includes,
The data acquisition module is used for acquiring historical production data of automobiles;
A model construction module connected with the data acquisition module and used for constructing an initial deep learning model and training the initial deep learning model based on the historical production data to obtain a target deep learning model,
The quality detection module is connected with the model construction module and used for inputting the production data obtained in real time into the target deep learning model for quality detection prediction and obtaining a prediction result;
And the production adjustment module is connected with the quality detection module and used for comparing the predicted result with the historical production result,
and if there is a difference, adaptively adjusting the production parameters according tdJ504090 the historical production result.
Further, the data acquisition module comprises a first acquisition unit and a second acquisition unit;
The first acquisition unit is used for acquiring production parameter data of production equipment in each production workshop; The production parameter data includes stamping data, welding data, painting data and assembly data;
The second acquisition unit is used for acquiring the production image data of each automobile part.
Further, the stamping data is obtained based on stamping production equipment, which comprises a punch base for placing parts, a hydraulic press arranged above the punch base, and a punch connected to the hydraulic press;
The stamping production equipment is connected with an external processing support device, a damping spring device is installed at one side of the bottom of the external processing support device, an adjusting device is installed at the center of the bottom of the external processing support device, the adjusting device is connected with the bottom of the damping spring device, the adjusting device is connected with a deburring device, and the deburring device is embedded with a positioning strip.
The painting data is obtained based on painting production equipment, which comprises a supporting system, a supporting container, a filtering mechanism, a stirring container, a discharging container, a feeding hose and a filter;
A supporting container is installed on the right side of the supporting system, a filtering mechanism is installed on the upper part of the supporting system, a stirring container is installed on the upper part of the filtering mechanism, a discharge port is installed on the lower part of the right side of the stirring container, a discharge container is installed on the right side of the discharge port, and a plurality of discharge holes are installed on the right side of the discharge container; The lower part of the left side of the stirring container is provided with a sleeve, a push rod is arranged in the sleeve, and a push plate is arranged on the right side of the push rod; The left and right sides of the upper part of the mixing container are respectively provided with a left power mechanism and a right power mechanism, a left roller transmission mechanism and a right roll&t)504090 transmission mechanism are respectively arranged below the left power mechanism and the right power mechanism, a left transmission belt is arranged between the left power mechanism and the right roller transmission mechanism, a plurality of mixing columns are arranged on the left roller transmission mechanism and the right roller transmission mechanism, and a feeding container is arranged on the upper part of the mixing container; The left side of the mixing container is provided with a paint spraying power supply mechanism; the upper part of the paint spraying power supply mechanism is provided with a feed pipe; the upper part of the feed pipe is provided with a discharge pipe; the lower part of the paint spraying power supply mechanism is provided with a feed hose; and the lower part of the feed hose is provided with a filter.
Further, the quality detection and prediction system also comprises a processing module, which is connected with the second acquisition unit and used for image processing operations such as image cutting, image rotation, image mirroring, image enhancement, image mosaic, spatial filtering, smoothing, projection change and numerical statistics.
Further, that production quality detection carry out by the quality detection module includes car body weld quality scanning detection, car body surface smoothness detection, car seal detection, tire hub quality detection, car machine circuit safety detection, brake detection and fender production strength detection.
Taking the scanning detection of car body welding quality as an example, the scanning detection equipment of car body welding quality includes a supporting platform which moves on the working platform and is used for placing the car body, and also includes a moving component which is positioned above the supporting platform and driven to lift by a lifting component; The moving component comprises a support ring and a scanning camera; The scanning camera moves circularly on the supporting ring through the driving component. The driving assembly comprises a support frame, a first motor fixedly installed on the support frame, an inner gear ring coaxially and fixedly installed on the support ring, and a first gear engaged with the inner gear ring; The output end of that first motor is connecte with the first gear through a gear assembly, and the support frame with the scanning camera and the support re are in annular slidirldJ504090 connection through an annular guide rail.
The tire wheel hub quality detection equipment comprises a mounting bottom plate, supporting feet, a supporting mechanism, a positioning mechanism and a detection mechanism. When the rubber tire production automatic detection device is used for automatic detection of rubber tire production, the specific method is as follows:
S1, equipment detection: firstly, rubber tires to be inspected are prepared manually, and the running state of the equipment is inspected,
S2, positioning and supporting: manually placing the rubber tire to be detected into the supporting mechanism, and positioning and clamping the rubber tire through the positioning mechanism;
S3, data detection: after the step S2 is completed, the rubber tire is driven to rotate around at a uniform speed by the support mechanism, so that the detection mechanism is further attached to the outer wall of the tire;
S4, collection processing: at the same time as the step S3, the data of the tire outer rim diameter are collected and analyzed by the detection mechanism;
Support feet are uniformly arranged at the corners around the lower end of the mounting base plate, a support mechanism is installed at the upper end of the mounting base plate, a positioning mechanism is installed on the support mechanism, and a detection mechanism is installed on the mounting base plate at one side of the support mechanism.
Further, the quality detection module comprises a quality detection identification unit, a type identification unit and a position identification unit;
The quality detection identification unit is used for identifying and judging whether the production image to be identified has production quality problems;
The category identification unit is used for identifying the production quality category information of the production image with quality problems;
The position identification unit is used for corresponding the quality position icon of the production image with the position information of the production parts to obtain the position information of the production parts.
Further, the quality detection and prediction system also comprises an alarkW504090 module, which is respectively connected with the quality detection module and the production adjustment module and used for giving an alarm according to the parts yield result of quality detection;
The alarm module comprises a yield threshold dividing unit and an alarm unit;
The yield threshold dividing unit is used for setting different yield thresholds according to different automobile parts;
The alarm unit is used to judge whether the yield of automobile parts is lower than the yield threshold, and if it is lower than the yield threshold, a background alarm display is performed, and the production adjustment module performs adaptive adjustment according to the production parameters of the production line parts displayed by the alarm.
Further, the alarm unit comprises an acoustic alarm device and a photoelectric alarm device.
The above is only the preferred embodiment of this application, but the protection scope of this application is not limited to this. Any change or replacement that can be easily thought of by a person familiar with this technical field within the technical scope disclosed in this application should be included in the protection scope of this application.
Therefore, the protection scope of this application should be based on the protection scope of the claims.

Claims (8)

CLAIMS LU504090
1. A multi-link quality detection prediction system based on big data, comprising: a data acquisition module is used for acquiring historical production data of automobiles; a model construction module connected with the data acquisition module and used for constructing an initial deep learning model and training the initial deep learning model based on the historical production data to obtain a target deep learning model; a quality detection module is connected with the model construction module and used for inputting the production data obtained in real time into the target deep learning model for quality detection prediction and obtaining a prediction result; and a production adjustment module is connected with the quality detection module and used for comparing the predicted result with the historical production result, and if there is a difference, adaptively adjusting the production parameters according to the historical production result.
2. The multi-link quality detection prediction system based on big data according to claim 1, characterized in that, the data acquisition module comprises a first acquisition unit and a second acquisition unit; the first acquisition unit is used for acquiring production parameter data of production equipment in each production workshop; the production parameter data includes stamping data, welding data, painting data and assembly data; the second acquisition unit is used for acquiring the production image data of each automobile part.
3. The multi-link quality detection prediction system based on big data according t&J504090 claim 2, characterized in that, the stamping data is obtained based on stamping production equipment, and the stamping production equipment comprises a punch seat for placing parts, a hydraulic press arranged above the punch seat, and a punch connected to the hydraulic press; the stamping production equipment is connected with an external processing support device, a damping spring device is installed at one side of the bottom of the external processing support device, an adjusting device is installed at the center of the bottom of the external processing support device, the adjusting device is connected with the bottom of the damping spring device, the adjusting device is connected with a deburring device, and the deburring device is embedded with a positioning strip.
4. The multi-link quality detection prediction system based on big data according to claim 1, characterized in that the quality detection prediction system further comprises a processing module, which is connected with the second acquisition unit and used for image processing operations such as image cutting, image rotation, image mirroring, image enhancement, image mosaic, spatial filtering, smoothing, projection change and numerical statistics.
5. The multi-link quality detection prediction system based on big data according to claim 1, characterized in that, the production quality detection carry out by that quality detection module comprises car body weld quality scanning detection, car body surface smoothness detection, automobile sealing element sealing detection, tire hub quality detection, car machine circuit safety detection, brake detection and fender production strength detection.
6. The multi-link quality detection prediction system based on big data according tdJ504090 claim 1, characterized in that, the quality detection module comprises a quality detection identification unit, a type identification unit and a position identification unit; the quality detection identification unit is used for identifying and judging whether the production image to be identified has production quality problems; the category identification unit is used for identifying the production quality category information of the production image with quality problems; the position identification unit is used for corresponding the quality position icon of the production image with the position information of the production parts to obtain the position information of the production parts.
7. The multi-link quality detection prediction system based on big data according to claim 1, characterized in that, the quality detection prediction system also comprises an alarm module, which is respectively connected with the quality detection module and the production adjustment module, and is used for giving an alarm according to the parts yield result of quality detection; the alarm module comprises a yield threshold dividing unit and an alarm unit; the yield threshold dividing unit is used for setting different yield thresholds according to different automobile parts; the alarm unit is used to judge whether the yield of automobile parts is lower than the yield threshold, and if it is lower than the yield threshold, a background alarm display is performed, and the production adjustment module performs adaptive adjustment according to the production parameters of the production line parts displayed by the alarm.
8. The multi-link quality detection prediction system based on big data according to claim 7, characterized in that the alarm unit comprises an audio alarm device and a photoelectric alarm device.
LU504090A 2023-04-27 2023-04-27 Multi-link quality detection prediction system based on big data LU504090B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
LU504090A LU504090B1 (en) 2023-04-27 2023-04-27 Multi-link quality detection prediction system based on big data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
LU504090A LU504090B1 (en) 2023-04-27 2023-04-27 Multi-link quality detection prediction system based on big data

Publications (1)

Publication Number Publication Date
LU504090B1 true LU504090B1 (en) 2023-10-27

Family

ID=88469826

Family Applications (1)

Application Number Title Priority Date Filing Date
LU504090A LU504090B1 (en) 2023-04-27 2023-04-27 Multi-link quality detection prediction system based on big data

Country Status (1)

Country Link
LU (1) LU504090B1 (en)

Similar Documents

Publication Publication Date Title
CN110385618B (en) Flexible production system for polishing and detecting miniature die castings
EP0956213B1 (en) Automatic adjustable width chuck apparatus for tire testing systems
LU504090B1 (en) Multi-link quality detection prediction system based on big data
CN104596621A (en) Weighing device, weighing production line and product weighing method
CN2808459Y (en) Automobile half bearing mounting/dismounting machine
EP2108532B1 (en) Method and device for managed filling of fitted vehicle wheels
CN207358978U (en) The disassembling fixture of crankshaft sprocket
CN116140994A (en) Automatic assembly process for balance shaft assembly with shaft housing
CN109290809A (en) Engine mounting axle sleeve assembly assembling device
CN115816003A (en) Automatic press-fitting device for hub oil seal
CN205764861U (en) Passenger cabin system Intelligent assembly line
CN102133703A (en) Engine cylinder liner assembly detector
CN210862618U (en) Thread verticality detection device for rotary filter
CN2888429Y (en) Seal structure for positioning and locking device of tyre dynamic balance tester
CN110153698B (en) Heavy truck drive axle wheel hub pressure equipment transfer machine
CN111731045A (en) Automatic spare tire replacement device, control system and method
CN104772299B (en) The master of the double fuel tanks of band subtracts assembly oil wash machine
CN102489964A (en) Method for machining bracket of automobile braking system
CN107914678B (en) Automatic tire deflation equipment and automatic automobile detection system
CN205869122U (en) Scrap steel ring green tire utensil again
CN111351647A (en) Intelligent multi-station running-in no-load detection table and working method thereof
CN220126627U (en) Carousel formula tensioning ware equipment fat liquoring equipment
CN107165102A (en) A kind of control method of automobile tyre puncture-preventing device
CN205345984U (en) Transmission device of blank steel sheet
CN220316217U (en) Automatic conveying device for automobile hub casting

Legal Events

Date Code Title Description
FG Patent granted

Effective date: 20231027