CN114118878A - Online centralized quality analysis decision system based on hub detection and review framework - Google Patents

Online centralized quality analysis decision system based on hub detection and review framework Download PDF

Info

Publication number
CN114118878A
CN114118878A CN202210071260.2A CN202210071260A CN114118878A CN 114118878 A CN114118878 A CN 114118878A CN 202210071260 A CN202210071260 A CN 202210071260A CN 114118878 A CN114118878 A CN 114118878A
Authority
CN
China
Prior art keywords
hub
review
defect
information
quality analysis
Prior art date
Legal status (The legal status 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 status listed.)
Granted
Application number
CN202210071260.2A
Other languages
Chinese (zh)
Other versions
CN114118878B (en
Inventor
成建洪
廖宏军
王春洲
杜冬冬
罗启铭
熊皓
吴育校
覃江威
杨志宇
陈功
冯建设
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Xinrun Fulian Digital Technology Co Ltd
Original Assignee
Shenzhen Xinrun Fulian Digital Technology Co Ltd
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 Shenzhen Xinrun Fulian Digital Technology Co Ltd filed Critical Shenzhen Xinrun Fulian Digital Technology Co Ltd
Priority to CN202210071260.2A priority Critical patent/CN114118878B/en
Publication of CN114118878A publication Critical patent/CN114118878A/en
Application granted granted Critical
Publication of CN114118878B publication Critical patent/CN114118878B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N23/00Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N27/00Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
    • G01N27/72Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables
    • G01N27/82Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws
    • G01N27/90Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws using eddy currents
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N29/00Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
    • G01N29/04Analysing solids
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/27Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Immunology (AREA)
  • Biochemistry (AREA)
  • Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Databases & Information Systems (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Quality & Reliability (AREA)
  • Economics (AREA)
  • Educational Administration (AREA)
  • General Engineering & Computer Science (AREA)
  • Marketing (AREA)
  • Electrochemistry (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Game Theory and Decision Science (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Operations Research (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Acoustics & Sound (AREA)
  • General Factory Administration (AREA)
  • Analysing Materials By The Use Of Radiation (AREA)

Abstract

The invention provides an online centralized quality analysis decision system based on a hub detection and review framework, which comprises: the system comprises hub defect detection equipment, a distributed file storage unit, a hub defect detection algorithm model, a message middleware, a hub online centralized quality analysis review platform, a message queue, a database and data display application; and the hub online centralized quality analysis review platform distributes the preliminary review result to corresponding reviewers according to the defect grade and the defect type of the hub defects. The invention carries out centralized manual secondary evaluation on the hub detection results of a plurality of factories in an online centralized evaluation mode, adopts an automatic assignment mode and increases the condition limit of assignment: the defect types are distributed according to the defect grades of the hubs, and the same reviewer only reviews the defects of the same type, so that the review quality and efficiency are ensured; and automatically feeding back the artificial secondary evaluation result to the algorithm model to be used as a training and tuning basis, so that the evaluation accuracy of the algorithm model is improved.

Description

Online centralized quality analysis decision system based on hub detection and review framework
Technical Field
The invention relates to the technical field of quality analysis systems, in particular to an online centralized quality analysis decision-making system based on a hub detection and review framework.
Background
During transportation or hub production, many defects such as air holes, cracks, slag inclusions, shrinkage cavities and the like are inevitably generated in the casting process, and various off-line or on-line hub defect detection methods are generally adopted for detection, such as a visual detection method, a fluorescence penetration method, an ultrasonic detection method, an eddy current detection method, an X-ray detection method and the like.
The results detected by all hub defect detection methods still have a certain proportion of misjudgments or inaccuracy, and the detection results need to be manually reviewed, recorded and analyzed for the second time, so that the reliability of the final hub defect detection results is further guaranteed.
However, in the existing hub production and casting process, the defect detection method has the following problems:
1) at present, in offline manual review, a special technician is required to wait for a primary hub defect result analyzed and judged by an algorithm model before each X-ray machine to perform secondary confirmation review on the defect result, so that great labor waste is caused;
2) the offline manual secondary evaluation of each X-ray machine is relatively independent, and the data such as the primary evaluation result, the secondary manual evaluation result and the like cannot be automatically gathered, counted and analyzed, so that a better adjustment scheme and decision suggestion can be made;
3) the existing off-line model and the feedback of the off-line manual review result have small and single sample data and are not beneficial to the training and optimization of the algorithm model;
4) the leadership decision layer cannot intuitively know the production and detection conditions of the hubs of the multiple factories in a simple mode, so that the operation decision is adjusted.
Therefore, the prior art has drawbacks and needs further improvement.
Disclosure of Invention
Aiming at more than one problem in the prior art, the invention provides an online centralized quality analysis decision-making system based on a hub detection and review framework.
In order to achieve the purpose, the invention adopts the following specific scheme:
an online centralized quality analysis decision-making system based on a hub detection review framework, comprising: the system comprises hub defect detection equipment, a distributed file storage unit, a hub defect detection algorithm model, a message middleware, a hub online centralized quality analysis review platform, a message queue, a database and data display application;
the hub defect detection equipment is used for acquiring an original picture of hub defects and storing the original picture in the distributed file storage unit; the hub defect algorithm model acquires original pictures of hub defects from the distributed file storage unit for preliminary review, and sends the preliminary review results to the message middleware, the message middleware sends the preliminary review results of the hub defects to the hub online centralized quality analysis review platform, the hub online centralized quality analysis review platform caches the preliminary review results needing manual secondary review in a message queue for gradual manual secondary review according to the sequence, the hub online centralized quality analysis review platform transmits the manual secondary review results to the message middleware, the message middleware sends the manual secondary review results to the hub defect detection algorithm model and the database, and the data display is used for displaying relevant data of the preliminary review results and the manual secondary review results;
the hub online centralized quality analysis review platform distributes the primary review result to the reviewers for manual secondary review, and distributes step by step according to the priority of the review task distribution strategy, the review task distribution strategy sets three priorities, and distributes step by step according to the sequence of the first, second and third levels:
a first stage: reviewers in an idle state in the same hub defect field;
and a second stage: when a plurality of idle reviewers exist in the first level, preferentially distributing to the reviewers with higher efficiency;
and a third stage: when a plurality of reviewers are in the second level of priority at the same time, the reviewers are firstly allocated to the reviewers with higher default priority;
wherein, higher efficiency means: the average value of the evaluation time of a single task in the historical evaluation tasks is shorter than that of other evaluation personnel at the same level;
the default priority level refers to: setting according to the total amount of tasks processed in the past, wherein the priority level is higher when the total amount of the processed tasks is more, and the tasks can be received preferentially;
the field of hub defects is as follows: and dividing the review tasks with the same hub defect grade and hub defect type into the same hub defect field, and dividing and distributing the review tasks by the reviewers according to the hub defect field.
Preferably, the hub defect detecting apparatus includes: an ultrasonic detector, an eddy current detector and an X-ray machine;
the hub defect detection device is used for acquiring an original picture of hub defect detection and information of a hub, and storing the original picture of hub defect detection, the information of the hub and the information of the hub defect detection device into the distributed file storage unit;
the hub own information includes: the hub brand, the hub number, and the number of the mold used for producing the hub;
the information of the hub defect detection equipment comprises: equipment name, equipment number, position sensor data, valve status data.
Preferably, the hub defect algorithm model acquires an original picture of hub defect detection, hub self-information and hub defect detection device self-information from the distributed file storage unit, performs preliminary review to obtain a preliminary review result of hub defects, and then transmits the preliminary review result, the original picture of hub defect detection, the hub self-information and the hub defect detection device self-information to the message middleware;
the hub defect algorithm model stores the initial evaluation result and the information of the hub to a database;
the hub defect algorithm model adopts a fast-RCNN model;
the hub own information includes: the wheel hub brand, the wheel hub serial number, the serial number of the mould used for producing the wheel hub.
Preferably, the hub online centralized quality analysis review platform acquires a primary review result, an original picture of hub defect detection, hub self-information and hub defect detection equipment self-information from a message middleware, and caches the primary review result to a message queue according to the time sequence, and is used for performing manual secondary review on the primary review result and obtaining a secondary review result;
and the hub online centralized quality analysis review platform stores the information of the reviewers into a database.
Preferably, the message queue is used for temporarily caching the preliminary review result transmitted by the message middleware;
the message queue distributes the primary evaluation result to the logged corresponding examiners in the idle state for manual secondary evaluation according to the defect grade, the defect type and the time sequence;
and the message queue lists the overtime unviewed primary evaluation results into an abnormal alarm data queue according to the time sequence, and the primary evaluation results in the abnormal alarm data queue are distributed prior to the overtime unviewed primary evaluation results.
Preferably, the message middleware transmits the primary review result transmitted by the hub defect algorithm model, the original picture of the hub defect detection, the information of the hub and the information of the hub defect detection device to the hub online centralized quality analysis review platform, transmits the manual secondary review result transmitted by the hub online centralized quality analysis review platform to the hub defect algorithm model, and simultaneously stores the manual secondary review result to the database.
Preferably, the data display application is used for displaying the data transmitted by the hub online centralized quality analysis review platform;
the types of the data presentation application include: WEB, APP, or H5;
the data displayed by the data display application comprises: the method comprises the steps of obtaining queue data of preliminary review results to be reviewed, original pictures of hub defect detection, hub self information, hub defect detection equipment self information, overall hub qualification rate of manual secondary review, hub quantity detected by the hub defect detection equipment, hub quantity of the preliminary review of a hub defect algorithm model, and quantity and qualification rate of the manual secondary review.
Preferably, the hub online centralized quality analysis review platform comprises: the system comprises a user management module, a decision center module, a review center module, an X-ray machine state module and a statistical analysis module;
the user management module is used for managing the account number of the reviewer, and specifically comprises the following steps: adding, modifying, deleting and configuring authority;
the decision center module is used for counting, analyzing and predicting relevant data of hub production information, hub defect detection information, hub defect distribution information and manual review information;
the evaluation center module is used for manually rechecking the primary evaluation result of the hub defect algorithm model after the evaluation personnel log in;
the hub defect detection equipment state module is used for displaying the equipment state of the hub defect detection equipment in real time, so that a reviewer can conveniently judge whether the hub defect detection equipment is in a normal working state;
and the statistical analysis module is used for further performing statistics and analysis on the hub defect data subjected to the manual secondary review.
By adopting the technical scheme of the invention, the invention has the following beneficial effects:
1. the hub detection results of a plurality of factories are sent to a system for manual secondary evaluation in an online centralized evaluation mode, and once a set of hub photos are evaluated by an evaluation staff, the evaluation staff automatically distribute the next set of hub photos; conditional limits of dispatch are also increased: the hub defect classification, defect type and time sequence are distributed, and the same reviewer only reviews the defects of the same type, so that the review quality and efficiency are ensured;
2. the result of the artificial secondary evaluation is automatically fed back to the algorithm model to be used as a training and tuning basis, so that the evaluation accuracy of the algorithm model is improved;
3. the leadership decision-making layer can visually and effectively master the hub production operation conditions of a plurality of factories through the automatic statistics of the system, and make scientific and reasonable decisions.
Drawings
FIG. 1 is a system architecture diagram of the present invention;
FIG. 2 is a functional block diagram of the hub online centralized quality analysis review platform of the present invention;
FIG. 3 is a flow chart of the present invention for performing a manual secondary review.
Detailed Description
The invention is further described below with reference to the following figures and specific examples.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments.
As shown in fig. 1, the present invention provides an online centralized quality analysis decision system based on a hub detection review framework, which includes: the system comprises hub defect detection equipment, a distributed file storage unit, a hub defect detection algorithm model, a message middleware, a hub online centralized quality analysis review platform, a message queue, a database and data display application;
the hub defect detection equipment is used for acquiring an original picture of hub defects and storing the original picture in the distributed file storage unit; the hub defect algorithm model acquires original pictures of hub defects from the distributed file storage unit for preliminary review, and sends the preliminary review results to the message middleware, the message middleware sends the preliminary review results of the hub defects to the hub online centralized quality analysis review platform, the hub online centralized quality analysis review platform caches the preliminary review results needing manual secondary review in a message queue for gradual manual secondary review according to the sequence, the hub online centralized quality analysis review platform transmits the manual secondary review results to the message middleware, the message middleware sends the manual secondary review results to the hub defect detection algorithm model and the database, and the data display is used for displaying relevant data of the preliminary review results and the manual secondary review results;
the hub online centralized quality analysis review platform distributes the primary review result to the reviewers for manual secondary review, and distributes step by step according to the priority of the review task distribution strategy, the review task distribution strategy sets three priorities, and distributes step by step according to the sequence of the first, second and third levels:
a first stage: reviewers in an idle state in the same hub defect field;
and a second stage: when a plurality of idle reviewers exist in the first level, preferentially distributing to the reviewers with higher efficiency;
and a third stage: when a plurality of reviewers are in the second level of priority at the same time, the reviewers are firstly allocated to the reviewers with higher default priority;
wherein, higher efficiency means: the average value of the evaluation time of a single task in the historical evaluation tasks is shorter than that of other evaluation personnel at the same level;
the default priority level refers to: setting according to the total amount of tasks processed in the past, wherein the priority level is higher when the total amount of the processed tasks is more, and the tasks can be received preferentially;
the field of hub defects is as follows: and dividing the review tasks with the same hub defect grade and hub defect type into the same hub defect field, and dividing and distributing the review tasks by the reviewers according to the hub defect field.
The hub defect detecting apparatus includes: an ultrasonic detector, an eddy current detector and an X-ray machine;
the hub defect detection device is used for acquiring an original picture of hub defect detection and information of a hub, and storing the original picture of hub defect detection, the information of the hub and the information of the hub defect detection device into the distributed file storage unit;
the hub own information includes: the hub brand, the hub number, and the number of the mold used for producing the hub;
the information of the hub defect detection equipment comprises: equipment name, equipment number, position sensor data, valve status data.
The hub defect algorithm model acquires an original picture of hub defect detection, hub self-information and hub defect detection equipment self-information from the distributed file storage unit, performs preliminary review to obtain a preliminary review result of hub defects, and then transmits the preliminary review result, the original picture of hub defect detection, the hub self-information and the hub defect detection equipment self-information to a message middleware;
the hub defect algorithm model stores the initial evaluation result and the information of the hub to a database;
the hub defect algorithm model adopts a fast-RCNN model;
the hub own information includes: the wheel hub brand, the wheel hub serial number, the serial number of the mould used for producing the wheel hub.
The hub online centralized quality analysis review platform acquires a primary review result, an original picture of hub defect detection, hub self-information and hub defect detection equipment self-information from a message middleware, caches the primary review result to a message queue according to the time sequence, and is used for performing manual secondary review on the primary review result and obtaining a secondary review result;
and the hub online centralized quality analysis review platform stores the information of the reviewers into a database.
The message queue is used for temporarily caching the primary review result transmitted by the message middleware;
the message queue distributes the primary evaluation result to the logged corresponding examiners in the idle state for manual secondary evaluation according to the defect grade, the defect type and the time sequence;
and the message queue lists the overtime unviewed primary evaluation results into an abnormal alarm data queue according to the time sequence, and the primary evaluation results in the abnormal alarm data queue are distributed prior to the overtime unviewed primary evaluation results.
The message middleware transmits the primary review result transmitted by the hub defect algorithm model, the original picture of the hub defect detection, the information of the hub and the information of the hub defect detection equipment to the hub online centralized quality analysis review platform, transmits the manual secondary review result transmitted by the hub online centralized quality analysis review platform to the hub defect algorithm model, and simultaneously stores the manual secondary review result to the database.
The data display application is used for displaying the data transmitted by the hub online centralized quality analysis review platform;
the types of the data presentation application include: WEB, APP, or H5;
the data displayed by the data display application comprises: the method comprises the steps of obtaining queue data of preliminary review results to be reviewed, original pictures of hub defect detection, hub self information, hub defect detection equipment self information, overall hub qualification rate of manual secondary review, hub quantity detected by the hub defect detection equipment, hub quantity of the preliminary review of a hub defect algorithm model, and quantity and qualification rate of the manual secondary review.
As shown in fig. 2, the hub online centralized quality analysis review platform comprises: the system comprises a user management module, a decision center module, a review center module, an X-ray machine state module and a statistical analysis module;
the user management module is used for managing the account number of the reviewer, and specifically comprises the following steps: adding, modifying, deleting and configuring authority;
the decision center module is used for counting, analyzing and predicting relevant data of hub production information, hub defect detection information, hub defect distribution information and manual review information;
the evaluation center module is used for manually rechecking the primary evaluation result of the hub defect algorithm model after the evaluation personnel log in;
the hub defect detection equipment state module is used for displaying the equipment state of the hub defect detection equipment in real time, so that a reviewer can conveniently judge whether the hub defect detection equipment is in a normal working state;
and the statistical analysis module is used for further performing statistics and analysis on the hub defect data subjected to the manual secondary review.
As shown in fig. 3, the step of manual secondary review includes:
the hub online centralized quality analysis review platform is logged in by the reviewers;
entering a review center module, then entering a review function page,
carrying out manual secondary evaluation on the automatically distributed primary evaluation result to be evaluated;
and the statistical analysis module further performs statistics and analysis on the manual secondary evaluation result.
Compared with the prior art, the technical scheme of the invention has the following beneficial effects:
1. the hub detection results of a plurality of factories are sent to a system for manual secondary evaluation in an online centralized evaluation mode, and once a set of hub photos are evaluated by an evaluation staff, the evaluation staff automatically distribute the next set of hub photos; conditional limits of dispatch are also increased: the hub defect classification, defect type and time sequence are distributed, and the same reviewer only reviews the defects of the same type, so that the review quality and efficiency are ensured;
2. the result of the artificial secondary evaluation is automatically fed back to the algorithm model to be used as a training and tuning basis, so that the evaluation accuracy of the algorithm model is improved;
3. the leadership decision-making layer can visually and effectively master the hub production operation conditions of a plurality of factories through the automatic statistics of the system, and make scientific and reasonable decisions.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all modifications and equivalents of the present invention, which are made by the contents of the present specification and the accompanying drawings, or directly/indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims (8)

1. An online centralized quality analysis decision system based on a hub detection review framework, comprising: the system comprises hub defect detection equipment, a distributed file storage unit, a hub defect detection algorithm model, a message middleware, a hub online centralized quality analysis review platform, a message queue, a database and data display application;
the hub defect detection equipment is used for acquiring an original picture of hub defects and storing the original picture in the distributed file storage unit; the hub defect algorithm model acquires original pictures of hub defects from the distributed file storage unit for preliminary review, and sends the preliminary review results to the message middleware, the message middleware sends the preliminary review results of the hub defects to the hub online centralized quality analysis review platform, the hub online centralized quality analysis review platform caches the preliminary review results needing manual secondary review in a message queue for gradual manual secondary review according to the sequence, the hub online centralized quality analysis review platform transmits the manual secondary review results to the message middleware, the message middleware sends the manual secondary review results to the hub defect detection algorithm model and the database, and the data display is used for displaying relevant data of the preliminary review results and the manual secondary review results;
the hub online centralized quality analysis review platform distributes the primary review result to the reviewers for manual secondary review, and distributes step by step according to the priority of the review task distribution strategy, the review task distribution strategy sets three priorities, and distributes step by step according to the sequence of the first, second and third levels:
a first stage: reviewers in an idle state in the same hub defect field;
and a second stage: when a plurality of idle reviewers exist in the first level, preferentially distributing to the reviewers with higher efficiency;
and a third stage: when a plurality of reviewers are in the second level of priority at the same time, the reviewers are firstly allocated to the reviewers with higher default priority;
wherein, higher efficiency means: the average value of the evaluation time of a single task in the historical evaluation tasks is shorter than that of other evaluation personnel at the same level;
the default priority level refers to: setting according to the total amount of tasks processed in the past, wherein the priority level is higher when the total amount of the processed tasks is more, and the tasks can be received preferentially;
the field of hub defects is as follows: and dividing the review tasks with the same hub defect grade and hub defect type into the same hub defect field, and dividing and distributing the review tasks by the reviewers according to the hub defect field.
2. The hub detection review framework-based online centralized quality analysis decision making system according to claim 1, wherein the hub defect detection apparatus comprises: an ultrasonic detector, an eddy current detector and an X-ray machine;
the hub defect detection device is used for acquiring an original picture of hub defect detection and information of a hub, and storing the original picture of hub defect detection, the information of the hub and the information of the hub defect detection device into the distributed file storage unit;
the hub own information includes: the hub brand, the hub number, and the number of the mold used for producing the hub;
the information of the hub defect detection equipment comprises: equipment name, equipment number, position sensor data, valve status data.
3. The on-line centralized quality analysis and decision making system based on the hub detection and review framework as claimed in claim 1, wherein the hub defect algorithm model obtains an original picture of hub defect detection, hub self-information and hub defect detection device self-information from the distributed file storage unit, performs preliminary review to obtain a preliminary review result of hub defects, and then transmits the preliminary review result, the original picture of hub defect detection, the hub self-information and the hub defect detection device self-information to the message middleware;
the hub defect algorithm model stores the initial evaluation result and the information of the hub to a database;
the hub defect algorithm model adopts a fast-RCNN model;
the hub own information includes: the wheel hub brand, the wheel hub serial number, the serial number of the mould used for producing the wheel hub.
4. The on-line centralized quality analysis and decision-making system based on the hub detection and review frame as claimed in claim 1, wherein the hub on-line centralized quality analysis and review platform obtains a preliminary review result, an original picture of hub defect detection, hub self information and hub defect detection device self information from a message middleware and caches the preliminary review result in a message queue according to the time sequence, and is used for performing manual secondary review on the preliminary review result and obtaining a secondary review result;
and the hub online centralized quality analysis review platform stores the information of the reviewers into a database.
5. The hub detection review framework based online centralized quality analysis decision making system according to claim 1, wherein the message queue is used for temporarily caching the preliminary review results transmitted by the message middleware;
the message queue distributes the primary evaluation result to the logged corresponding examiners in the idle state for manual secondary evaluation according to the defect grade, the defect type and the time sequence;
and the message queue lists the overtime unviewed primary evaluation results into an abnormal alarm data queue according to the time sequence, and the primary evaluation results in the abnormal alarm data queue are distributed prior to the overtime unviewed primary evaluation results.
6. The on-line centralized quality analysis and decision-making system based on the hub detection and review framework as claimed in claim 1, wherein the message middleware transfers the primary review result transmitted by the hub defect algorithm model, the original picture of the hub defect detection, the information of the hub itself and the information of the hub defect detection device itself to the hub on-line centralized quality analysis and review platform, and transfers the manually performed secondary review result transmitted by the hub on-line centralized quality analysis and review platform to the hub defect algorithm model, and simultaneously saves the manually performed secondary review result to a database.
7. The hub detection and review framework based online centralized quality analysis decision making system according to claim 1, wherein the data presentation application is configured to present data transmitted from the hub online centralized quality analysis review platform;
the types of the data presentation application include: WEB, APP, or H5;
the data displayed by the data display application comprises: the method comprises the steps of obtaining queue data of preliminary review results to be reviewed, original pictures of hub defect detection, hub self information, hub defect detection equipment self information, overall hub qualification rate of manual secondary review, hub quantity detected by the hub defect detection equipment, hub quantity of the preliminary review of a hub defect algorithm model, and quantity and qualification rate of the manual secondary review.
8. The hub detection review framework-based online centralized quality analysis decision making system according to claim 1, wherein the hub online centralized quality analysis review platform comprises: the system comprises a user management module, a decision center module, a review center module, an X-ray machine state module and a statistical analysis module;
the user management module is used for managing the account number of the reviewer, and specifically comprises the following steps: adding, modifying, deleting and configuring authority;
the decision center module is used for counting, analyzing and predicting relevant data of hub production information, hub defect detection information, hub defect distribution information and manual review information;
the evaluation center module is used for manually rechecking the primary evaluation result of the hub defect algorithm model after the evaluation personnel log in;
the hub defect detection equipment state module is used for displaying the equipment state of the hub defect detection equipment in real time, so that a reviewer can conveniently judge whether the hub defect detection equipment is in a normal working state;
and the statistical analysis module is used for further performing statistics and analysis on the hub defect data subjected to the manual secondary review.
CN202210071260.2A 2022-01-21 2022-01-21 Online centralized quality analysis decision system based on hub detection and review framework Active CN114118878B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210071260.2A CN114118878B (en) 2022-01-21 2022-01-21 Online centralized quality analysis decision system based on hub detection and review framework

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210071260.2A CN114118878B (en) 2022-01-21 2022-01-21 Online centralized quality analysis decision system based on hub detection and review framework

Publications (2)

Publication Number Publication Date
CN114118878A true CN114118878A (en) 2022-03-01
CN114118878B CN114118878B (en) 2022-05-24

Family

ID=80360959

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210071260.2A Active CN114118878B (en) 2022-01-21 2022-01-21 Online centralized quality analysis decision system based on hub detection and review framework

Country Status (1)

Country Link
CN (1) CN114118878B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117973945A (en) * 2024-03-29 2024-05-03 南京认知物联网研究院有限公司 Quality inspection model continuous optimization method and system for personalized intelligent manufacturing

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104899143A (en) * 2015-06-15 2015-09-09 中国航空无线电电子研究所 Software peer review system realizing device for providing DM (Data Mining)
CN110376220A (en) * 2019-08-02 2019-10-25 中电九天智能科技有限公司 Realize the device and method of real-time judgment glass panel defect
CN112308241A (en) * 2020-09-28 2021-02-02 深圳优地科技有限公司 Robot production management system, method, device and storage medium
WO2021120186A1 (en) * 2019-12-20 2021-06-24 京东方科技集团股份有限公司 Distributed product defect analysis system and method, and computer-readable storage medium
CN113112216A (en) * 2021-03-03 2021-07-13 广东电网有限责任公司 Prejudgment analysis method for equipment defects
CN113470018A (en) * 2021-09-01 2021-10-01 深圳市信润富联数字科技有限公司 Hub defect identification method, electronic device, device and readable storage medium
CN113567446A (en) * 2021-07-06 2021-10-29 北京东方国信科技股份有限公司 Method and system for grading component defect detection quality

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104899143A (en) * 2015-06-15 2015-09-09 中国航空无线电电子研究所 Software peer review system realizing device for providing DM (Data Mining)
CN110376220A (en) * 2019-08-02 2019-10-25 中电九天智能科技有限公司 Realize the device and method of real-time judgment glass panel defect
WO2021120186A1 (en) * 2019-12-20 2021-06-24 京东方科技集团股份有限公司 Distributed product defect analysis system and method, and computer-readable storage medium
CN112308241A (en) * 2020-09-28 2021-02-02 深圳优地科技有限公司 Robot production management system, method, device and storage medium
CN113112216A (en) * 2021-03-03 2021-07-13 广东电网有限责任公司 Prejudgment analysis method for equipment defects
CN113567446A (en) * 2021-07-06 2021-10-29 北京东方国信科技股份有限公司 Method and system for grading component defect detection quality
CN113470018A (en) * 2021-09-01 2021-10-01 深圳市信润富联数字科技有限公司 Hub defect identification method, electronic device, device and readable storage medium

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117973945A (en) * 2024-03-29 2024-05-03 南京认知物联网研究院有限公司 Quality inspection model continuous optimization method and system for personalized intelligent manufacturing
CN117973945B (en) * 2024-03-29 2024-05-31 南京认知物联网研究院有限公司 Quality inspection model continuous optimization method and system for personalized intelligent manufacturing

Also Published As

Publication number Publication date
CN114118878B (en) 2022-05-24

Similar Documents

Publication Publication Date Title
CN110505102B (en) Power information communication fusion monitoring and service standardization management platform system and method
CN114118878B (en) Online centralized quality analysis decision system based on hub detection and review framework
CN114021971A (en) Comprehensive evaluation system, method and storage medium for expressway operation and maintenance management
CN111178778A (en) Security activity scheme generation method and system based on machine learning and security activity management system
CN113362210A (en) Window queuing service evaluation method, system and device
CN110570113A (en) Work order processing method and system
CN111966034B (en) Intelligent water affair system
CN117952571B (en) Multi-terminal fusion-based data information intelligent supervision system and method
CN109324978A (en) A kind of software testing management system of multi-person synergy
CN107742160B (en) Electromechanical equipment maintenance period self-adaptive prediction method and device
CN112884212A (en) Cigarette single gram weight deviation analysis and prediction method
KR102489119B1 (en) Smart FMEA system and process management system and method using thereof
CN116720720A (en) Geotechnical engineering equipment interconnection scheduling management method and system
CN110266811B (en) Workshop abnormal information pushing device and method based on MQTT technology
CN117350542A (en) Digital delivery data visualization system and application method thereof
CN117037530A (en) Dynamic supervision and analysis method for parking resources
TWM503595U (en) Production progress monitoring system
CN113570230B (en) Contaminated land parcel restoration site informatization management method and system
CN115641111A (en) Big data drive-based power transmission line fault early warning system
CN109711565A (en) Property facility maintenance of equipment dispatching method and its system, property total management system
CN116258381A (en) Quantitative evaluation method and device for operation command work
CN114240211A (en) Intelligent production management system and management method
CN118674433B (en) Intelligent gas inspection supervision method, internet of things system and medium
CN117408643B (en) Progress monitoring management method and system applied to engineering number intelligent management platform
CN116805194A (en) Big data processing analysis system based on cloud platform

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant