CN118400492A - Automatic recommendation system for inspection process - Google Patents
Automatic recommendation system for inspection process Download PDFInfo
- Publication number
- CN118400492A CN118400492A CN202410406540.3A CN202410406540A CN118400492A CN 118400492 A CN118400492 A CN 118400492A CN 202410406540 A CN202410406540 A CN 202410406540A CN 118400492 A CN118400492 A CN 118400492A
- Authority
- CN
- China
- Prior art keywords
- product
- node
- inspection process
- current
- inspection
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 144
- 238000007689 inspection Methods 0.000 title claims abstract description 140
- 238000012545 processing Methods 0.000 claims abstract description 112
- 238000004519 manufacturing process Methods 0.000 claims abstract description 38
- 238000012544 monitoring process Methods 0.000 claims abstract description 31
- 238000012549 training Methods 0.000 claims description 3
- 238000005520 cutting process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000005498 polishing Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41875—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by quality surveillance of production
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C3/00—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
- G07C3/14—Quality control systems
- G07C3/143—Finished product quality control
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C3/00—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
- G07C3/14—Quality control systems
- G07C3/146—Quality control systems during manufacturing process
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Databases & Information Systems (AREA)
- Automation & Control Theory (AREA)
- Manufacturing & Machinery (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Computational Linguistics (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- General Factory Administration (AREA)
Abstract
The invention discloses an automatic recommendation system for a checking process. The system comprises a plurality of front-end cameras, at least one front-end computing box and an inspection process recommending unit; the front-end camera is used for carrying out real-time video monitoring on the important monitoring area every time a product is identified in the important monitoring area and sending a real-time video stream to the front-end power calculating box; the front-end computing box is used for determining product information of a current product and a current processing node in a key monitoring area and sending the product information and the current processing node to the inspection process recommending unit; and the inspection process recommending unit is used for determining at least one node to be inspected, which is matched with the product information, and sending at least one inspection process, which is matched with the current processing node, to the MES when the current processing node is determined to belong to the node to be inspected. By adopting the technical scheme, the inspection process matched with the product can be automatically recommended to the user, and the production efficiency is improved.
Description
Technical Field
The invention relates to the technical field of monitoring management of the Internet of things, in particular to an automatic recommendation system for a checking process.
Background
The enterprise digital comprehensive upgrade is an important trend of the current enterprise development, and can help the enterprise to improve the production efficiency, optimize the business process, reduce the cost and improve the product quality, thereby creating greater value in the aspects of operation management, production management and the like.
Under the traditional production manufacturing scene, lack intelligent design in the product inspection process, the product inspection process often needs inspection personnel to look over the inspection technology at a specified platform or inspect according to experience, can not guarantee the efficiency of inspection and the accuracy of inspection technology.
Disclosure of Invention
The invention provides an automatic recommendation system for a checking process, which can automatically recommend the checking process matched with the current operation product to a user, thereby effectively improving the production efficiency.
According to an aspect of the present invention, there is provided an automatic recommendation system for an inspection process, including a plurality of front-end cameras, at least one front-end computing box, and an inspection process recommendation unit;
the front-end camera is used for carrying out real-time video monitoring on the important monitoring area every time a product is identified in the important monitoring area and sending a real-time video stream to the front-end computing box;
The front-end computing box is used for determining product information of a current product and a current processing node in a key monitoring area according to a real-time video stream sent by the front-end camera, and sending the product information and the current processing node to the inspection process recommending unit;
The inspection process recommending unit is used for determining at least one node to be inspected, which is matched with the product information, in a pre-established inspection template library, and sending at least one inspection process, which is matched with the current processing node, to an MES (Manufacturing Execution System ) when the current processing node is determined to belong to the node to be inspected, so that an inspector can check the inspection process to be executed in the MES.
Optionally, the front-end computing box is specifically configured to:
Intercepting a target image in a real-time video stream sent by a front-end camera, and extracting features of the target image to obtain a plurality of feature parameters matched with the current product;
and determining product information of the current product according to the characteristic parameters, comparing the characteristic parameters with a pre-established node template library, and determining the current processing node of the current product.
Optionally, the characteristic parameters include a product type, a name, a material, a specification, a processing route and a processing procedure.
Optionally, the front-end computing box is further specifically configured to:
performing image recognition on a current product in the target image to obtain the material and specification of the current product;
And inputting the material and specification of the current product into a pre-trained product identification model, and obtaining the type and name of the current product output by the product identification model.
Optionally, the automatic recommendation system of the inspection process further comprises an intelligent management unit;
The intelligent management unit stores processing routes and processing procedures monitored by the front-end cameras.
Optionally, the front-end computing box is further specifically configured to:
acquiring a camera number of a front-end camera for transmitting a real-time video stream, and determining a target processing route and a target processing procedure matched with the camera number in the intelligent management unit;
And determining the target processing route and the target processing procedure as the processing route and the processing procedure of the current product.
Optionally, the inspection process recommending unit is further configured to:
When the product information is determined to have a plurality of matched nodes to be inspected, at least one inspection process matched with each node to be inspected is acquired;
Sending each inspection process respectively matched with each node to be inspected to the MES, and associating each inspection process with each node to be processed in the MES so that an inspector can check the inspection process under each node to be processed in the MES in advance.
Optionally, the intelligent management unit is further configured to:
and acquiring a misrecognized product image, training and updating a product recognition model in a front-end computing box by utilizing the misrecognized product image, and transmitting the updated product recognition model to the front-end computing box.
Optionally, the intelligent management unit is further configured to:
When an update request is detected, updating the inspection template library and/or the node template library, and issuing the updated inspection template library and/or the node template library to the front-end computing box.
Optionally, the intelligent management unit is further configured to:
managing equipment information of each front-end camera and a front-end computing box;
The equipment information comprises purchasing time, equipment number, input use time, working state and coverage working area.
According to the technical scheme, the front-end cameras, the at least one front-end computing box and the inspection process recommending unit are configured in the automatic recommending system of the inspection process, the front-end cameras are used for carrying out real-time video monitoring on the heavy-point monitoring area every time a product is identified in the heavy-point monitoring area, the real-time video stream is sent to the front-end computing box, the product information and the current processing node of the current product in the heavy-point monitoring area are determined according to the real-time video stream sent by the front-end cameras, the product information and the current processing node are sent to the inspection process recommending unit, the at least one node to be inspected, which is matched with the product information, is determined in the pre-established inspection template library, and when the current processing node is determined to belong to the node to be inspected, the at least one inspection process matched with the current processing node is sent to the MES of the manufacturing execution system, so that inspection process matched with the current operation product can be automatically recommended to the inspection personnel according to the real-time video stream sent by the front-end computing box, the inspection process information and the current processing node are not needed, the inspection process manual is not needed to be clearly and conveniently checked in a manufacturing workshop, and the efficiency is not needed to be improved in the manufacturing process manual inspection system, and the manual inspection system is not needed.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of an automatic recommendation system for inspection process according to a first embodiment of the present invention;
fig. 2 is a schematic structural diagram of an automatic recommendation system for another inspection process according to a second embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a schematic structural diagram of an automatic recommendation system for an inspection process according to an embodiment of the present invention, and as shown in fig. 1, the automatic recommendation system for an inspection process includes a plurality of front-end cameras 110, at least one front-end computing box 120, and an inspection process recommendation unit 130.
The front-end camera 110 is configured to perform real-time video monitoring on the heavy-point monitoring area whenever a product is identified in the heavy-point monitoring area, and send a real-time video stream to the front-end computing box 120.
The front-end computing box 120 is configured to determine product information of a current product and a current processing node in a key monitoring area according to a real-time video stream sent by a front-end camera, and send the product information and the current processing node to the inspection process recommending unit 130.
The inspection process recommending unit 130 is configured to determine at least one node to be inspected, which is matched with the product information, in a pre-established inspection template library, and send at least one inspection process, which is matched with the current processing node, to the MES for inspection personnel to view the inspection process to be executed in the MES when it is determined that the current processing node belongs to the node to be inspected.
Optionally, after sending at least one inspection process matched with the current processing node to the MES, a background technician may check and determine whether the current processing node is matched with the inspection process in the MES, if so, the background technician may click a confirmation button or the like to confirm in the MES, after the background technician confirms, the inspection process to be executed may be displayed in the MES system at the inspector side, if not, the technician may cancel the recommendation of the inspection process, or the technician may manually select the matched inspection process and push the same to the MES system at the inspector side.
In the current production and manufacturing scene, each time a product reaches a processing node, the current quality of the product is checked to ensure that the product can meet production standards, currently, a checker generally determines a checking process through historical experience or selects a product model and a processing node from a designated platform, so that the checking process of the product is checked, automatic recommendation of the checking process of the product cannot be realized, the checking process is determined according to the historical experience of the checker, the checker needs to have a large amount of checking experience and has strong judging ability on the product type and the processing node, the method of checking the checking process on the designated platform needs to consume a large amount of time of the checker to search and check, and the checking efficiency is reduced.
The automatic recommendation system of the inspection process can automatically identify the product information and the processing nodes, so that the inspection process matched with the current product is determined, the inspection process is directly displayed to a user, the user can directly check the inspection process which is required to be executed at present without operating, the inspection efficiency can be improved, the inspection accuracy is ensured, unnecessary inspection links and time are reduced, inspection standards can be provided, and responsibility division is enhanced.
Optionally, the key monitoring area may refer to a pre-divided product flowing area, for example, when the product flows through a designated area to reach a detection personnel after being cut, the designated area may be used as a key monitoring area, where only the key monitoring area is illustrated, and a specific area range may be set according to actual requirements.
Optionally, the front-end camera 110 may be configured in a manufacturing shop, where the front-end camera 110 may be a high-definition camera, and it is required to ensure that a shooting range of the front-end camera can cover a specified working area, and the overall appearance of a product can be clearly shot. In general, a front-end camera 110 may be disposed at the end of a processing line, or a front-end camera 110 may be disposed in a designated detection area of a product, but other configurations are also possible, and are not limited thereto.
Optionally, the front-end camera 110 may perform real-time video monitoring on a working area within a shooting range, and when a product is identified in a key monitoring area, send a real-time video stream to the front-end computing box 120 connected to the front-end camera 110.
Optionally, the real-time video stream may be a video stream of a preset specified time period, for example, 10 seconds after the start of detecting the product, or may be all video streams of the product in the key monitoring area, but the real-time video stream is not specifically limited, and only a clear and complete product image in the real-time video stream needs to be ensured.
Alternatively, front-end power box 120 may be disposed in a manufacturing shop, where front-end power box 120 is connected to front-end cameras 110, and one front-end power box 120 may be connected to one front-end camera 110 or may be connected to a plurality of front-end cameras 110. The front-end computing box 120 is mainly used for processing the video stream sent by the front-end camera 110, and sending the processing result to the inspection process recommending unit 130.
Optionally, front-end computing box 120 may be specifically configured to:
Intercepting a target image in a real-time video stream sent by a front-end camera, and extracting features of the target image to obtain a plurality of feature parameters matched with the current product;
and determining product information of the current product according to the characteristic parameters, comparing the characteristic parameters with a pre-established node template library, and determining the current processing node of the current product.
Optionally, the target image may be a clear image capable of containing the overall appearance of the product, in which the appearance of the product needs to be ensured to be complete and free of shielding, the detail shooting is clear and accurate, the front-end computing box 120 can intercept an image in a video frame of the real-time video stream after acquiring the real-time video stream, evaluate the image quality of the intercepted image, and take the intercepted image as the target image when the image quality of the target image meets the requirement of definition and integrity.
Optionally, the feature parameters may include product type, name, material, specification, processing route and processing procedure, but are not limited to specific feature parameters, and other features may be added according to actual requirements, such as product numbers, different products and different product processing nodes, and the number and types of feature parameters obtained by the feature parameters may be different, for example, when the product is still in an initial form or in a preamble processing procedure, the product name may not exist.
Optionally, the product information of the current product may be a product name, a combination of a product name and a product material, or a combination of a product name and a product number, but is not limited to the product information content, and the product information content may be modified according to actual requirements.
Optionally, the front-end computing box 120 is preloaded with a node template library, where node information of a plurality of products is stored, where the products in the node template library may generally cover all the products currently produced in the production and manufacturing shop, and the node information may include feature parameters of each product under different processing nodes.
Optionally, after each feature parameter of the current product is obtained, each feature parameter of the current product may be compared with the node template library, so as to determine a current processing node of the current product, in an optional example, product information may be determined according to the feature parameter, further, a plurality of processing nodes matched with the product information may be determined in the node template library, and then, according to information such as product specification, processing procedure, etc., the current processing node may be determined in a plurality of processing nodes under the product information, where the foregoing example is only used for illustration, and processing node matching may also be performed by other manners, and only the feature parameter of the current product needs to be ensured to be matched with the feature parameter of the current processing node.
Optionally, in the process of manufacturing the product, a plurality of processing nodes, such as cutting, polishing, secondary cutting, secondary polishing, punching, threading, assembling and the like, can be designed, and for similar operations of cutting and secondary cutting, corresponding inspection processes are different, and the current processing node matched through characteristic parameters can realize accurate node positioning, so that a proper inspection process is recommended.
Optionally, front-end computing box 120 may be further specifically configured to:
performing image recognition on a current product in the target image to obtain the material and specification of the current product;
And inputting the material and specification of the current product into a pre-trained product identification model, and obtaining the type and name of the current product output by the product identification model.
Optionally, after the front-end computing box 120 acquires the target image, the product texture and specification may be identified by image recognition, in an alternative example, the product texture may be determined by identifying the texture and color characteristics of the product, and the product specification may be determined by identifying and extracting the edge of the product, which is only used as an illustration and not a specific limitation.
Optionally, the front-end computing box 120 may also be preloaded with a product identification model, and after inputting the material and the specification of the product into the product identification model, the product identification model may compare the preloaded three-dimensional model or multi-angle image with the input material and specification, so as to locate a specific product, and output the type and name of the product.
Optionally, the front-end computing box 120 may also directly extract shape features from the product's outline in the target image, and compare the extracted shape features to a preloaded three-dimensional model or multi-angle image, thereby locating a specific product.
Optionally, the front-end computing box 120 may further determine a specific processing area monitored by the front-end camera 110 according to the information of the front-end camera 110 that sends the real-time video stream, so as to determine the processing route and the processing procedure of the current product.
Optionally, the front-end power box 120 and the inspection process recommending unit 130 may be connected wirelessly through a network, and the inspection process recommending unit 130 and the front-end power box 120 may be connected through various connection modes such as an intranet or a public network. The inspection process recommendation unit 130 may be configured in a computer or a processor at the back end, and the inspection process recommendation unit 130 may open an interface with the MES to implement data interaction between the inspection process recommendation unit 130 and the MES.
Optionally, the MES is a manufacturing execution system facing the execution layer of the workshop of the manufacturing enterprise, and the MES can be used for managing multiple information such as personnel, equipment, materials and the like in the workshop.
Optionally, the inspection process recommending unit 130 is preloaded with an inspection template library, in which inspection processes corresponding to a plurality of products under different processing nodes are prestored, and the products in the inspection template library may generally cover all the products currently produced in the production workshop.
Optionally, the inspection process recommendation unit 130 may be further configured to:
When the product information is determined to have a plurality of matched nodes to be inspected, at least one inspection process matched with each node to be inspected is acquired;
Sending each inspection process respectively matched with each node to be inspected to the MES, and associating each inspection process with each node to be processed in the MES so that an inspector can check the inspection process under each node to be processed in the MES in advance.
Optionally, when a product corresponds to a plurality of processing nodes, only part of the processing nodes may need to be subjected to product inspection after finishing, that is, only part of the processing nodes have matched inspection processes, and then the nodes needing to be subjected to product inspection are nodes to be inspected, in an optional example, if the processing node corresponding to the product 1 is node 1-node 5, then the product 1 may need to be inspected after finishing the nodes 1,2 and 5, and the nodes 1,2 and 5 are nodes to be inspected of the product 1, and there is no corresponding inspection process at the nodes 3 and 4.
Optionally, when determining the current processing node of the product, the inspection process recommending unit 130 may determine a plurality of nodes to be inspected corresponding to the product in the inspection template library according to the product information, determine whether the current processing node belongs to the nodes to be inspected, if not, the current processing node does not have a corresponding inspection process, that is, does not need to recommend an inspection process to an inspector, and if so, send the inspection process matched with the current processing node to the MES.
Alternatively, a plurality of display systems, such as computer displays, may be provided in the manufacturing shop, and the MES may be preloaded in the display systems, and the recommended processes received by the MES may be directly displayed in the display systems after the inspection process recommending unit 130 sends the inspection process matched with the current processing node into the MES.
Optionally, if the product has a plurality of nodes to be inspected, and the current processing node of the product is located at one of the nodes to be inspected, in addition to the inspection process of the current processing node, the inspection processes of other nodes to be inspected of the product can be simultaneously acquired, and the inspection processes of other nodes to be inspected are sent to the MES, so that an inspector can view the current inspection process and view the subsequent inspection process in advance.
According to the technical scheme, the front-end cameras, the at least one front-end computing box and the inspection process recommending unit are configured in the automatic recommending system of the inspection process, the front-end cameras are used for carrying out real-time video monitoring on the heavy-point monitoring area every time a product is identified in the heavy-point monitoring area, the real-time video stream is sent to the front-end computing box, the product information and the current processing node of the current product in the heavy-point monitoring area are determined according to the real-time video stream sent by the front-end cameras, the product information and the current processing node are sent to the inspection process recommending unit, the at least one node to be inspected, which is matched with the product information, is determined in the pre-established inspection template library, and when the current processing node is determined to belong to the node to be inspected, the at least one inspection process matched with the current processing node is sent to the MES of the manufacturing execution system, so that inspection process matched with the current operation product can be automatically recommended to the inspection personnel according to the real-time video stream sent by the front-end computing box, the inspection process information and the current processing node are not needed, the inspection process manual is not needed to be clearly and conveniently checked in a manufacturing workshop, and the efficiency is not needed to be improved in the manufacturing process manual inspection system, and the manual inspection system is not needed.
Example two
Fig. 2 is a schematic structural diagram of an automatic recommendation system for an inspection process according to a second embodiment of the present invention, and as shown in fig. 2, the automatic recommendation system for an inspection process includes a plurality of front-end cameras 110, at least one front-end computing box 120, an inspection process recommendation unit 130, and an intelligent management unit 140.
The intelligent management unit 140 stores the processing route and the processing procedure monitored by each front-end camera.
Optionally, front-end computing box 120 may be further specifically configured to:
acquiring a camera number of a front-end camera for transmitting a real-time video stream, and determining a target processing route and a target processing procedure matched with the camera number in the intelligent management unit;
And determining the target processing route and the target processing procedure as the processing route and the processing procedure of the current product.
Alternatively, in a manufacturing shop, a plurality of processing paths, such as a motor assembling path, a rotor processing path, etc., may be configured, and each processing path may include a plurality of processing steps, such as cutting, polishing, etc., typically, one front-end camera 110 may be configured at a different processing step on each processing path, the number and specific configuration position of the front-end camera 110 may be stored in the intelligent management unit 140, and the front-end computing box 140 may determine the specific configuration position of the front-end camera 110 in the intelligent management unit 140 according to the camera number, thereby determining the target processing path and the target processing step monitored by the front-end camera 110.
Optionally, in the production shop, different products may be processed through different processing routes and processing procedures, so as to save cost, and one front end camera 110 may be configured by multiple processing routes and multiple processing procedures, and after the front end computing box 120 acquires the real-time video stream sent by the front end camera 110, each processing route and processing procedure that can be monitored by the front end camera 110 are determined according to the camera number, so that the target processing route and target processing procedure corresponding to the current product in the real-time video stream are determined.
Optionally, the intelligent management unit 140 may be further configured to:
and acquiring a misrecognized product image, training and updating a product recognition model in a front-end computing box by utilizing the misrecognized product image, and transmitting the updated product recognition model to the front-end computing box.
Optionally, after the product information is identified as being wrong in the front-end computing box 120, the matching inspection process cannot be corresponding, and after the wrong inspection process is found by an inspector, the inspector can report the wrong identification product image.
Alternatively, the intelligent management unit 140 may train the product recognition model according to the misrecognized product image, improve the recognition accuracy of the product recognition model, and issue the updated product recognition model to the front-end computing box 120.
Optionally, the intelligent management unit 140 may be further configured to:
When an update request is detected, updating the inspection template library and/or the node template library, and issuing the updated inspection template library and/or the node template library to the front-end computing box.
Optionally, when the number of producible products in the production and manufacturing shop increases, or the product processing nodes and the product inspection nodes change, the inspection template library and/or the node template library may be updated by the intelligent management unit 140, so that the inspection template library and the node template library can be matched with the current production and manufacturing scenario, thereby meeting the use requirement, and the updated inspection template library and/or the node template library is issued to the front-end computing box 120.
Optionally, the benefits of updating and issuing the product identification model, the inspection template library and the node template library through the intelligent management unit 140 are that: the expandability of the automatic inspection process recommendation system can be effectively improved, the automatic inspection process recommendation system is not limited to a fixed production and manufacturing scene, and the intelligent management unit 140 is isolated from the front-end computing box 120, so that the normal use of models and libraries in the front-end computing box 120 can be ensured in the updating process.
The optional intelligent management unit 140 may also be used to:
managing equipment information of each front-end camera and a front-end computing box;
The equipment information comprises purchasing time, equipment number, input use time, working state and coverage working area.
Optionally, by managing the device information of the front-end camera 110 and the front-end computing box 120, the device state in the production and manufacturing workshop can be monitored, so that the use state of the device in the workshop can be conveniently known, the device can be timely replaced when the device is in a problem or aged, and the stable operation of the automatic recommending system of the inspection process in the production and manufacturing workshop is ensured.
According to the technical scheme, the intelligent management unit is arranged in the automatic recommendation system of the inspection process, the intelligent management unit is used for managing the equipment information of the front-end computing box and the front-end camera, and the product identification model, the inspection template library and the node template library can be updated and issued to the front-end computing box, so that iterative updating of the model and the database can be guaranteed under the condition that the automatic recommendation system resource of the inspection process is not occupied, the use condition of equipment is monitored in real time, and the recommendation precision of the automatic recommendation system of the inspection process can be guaranteed.
Claims (10)
1. An automatic recommendation system for a checking process is characterized by comprising a plurality of front-end cameras, at least one front-end computing box and a checking process recommendation unit;
the front-end camera is used for carrying out real-time video monitoring on the important monitoring area every time a product is identified in the important monitoring area and sending a real-time video stream to the front-end computing box;
The front-end computing box is used for determining product information of a current product and a current processing node in a key monitoring area according to a real-time video stream sent by the front-end camera, and sending the product information and the current processing node to the inspection process recommending unit;
The inspection process recommending unit is used for determining at least one node to be inspected matched with the product information in a pre-established inspection template library, and sending at least one inspection process matched with the current processing node to a Manufacturing Execution System (MES) when the current processing node is determined to belong to the node to be inspected, so that inspection personnel can check the inspection process to be executed in the MES.
2. The system according to claim 1, characterized in that the front-end computing box is specifically adapted to:
Intercepting a target image in a real-time video stream sent by a front-end camera, and extracting features of the target image to obtain a plurality of feature parameters matched with the current product;
and determining product information of the current product according to the characteristic parameters, comparing the characteristic parameters with a pre-established node template library, and determining the current processing node of the current product.
3. The system of claim 2, wherein the characteristic parameters include a product type, a name, a material, a specification, a processing route, and a processing procedure.
4. A system according to claim 3, wherein the front-end computing box is further specifically configured to:
performing image recognition on a current product in the target image to obtain the material and specification of the current product;
And inputting the material and specification of the current product into a pre-trained product identification model, and obtaining the type and name of the current product output by the product identification model.
5. The system of claim 4, wherein the automated recommendation system for inspection processes further comprises an intelligent management unit;
The intelligent management unit stores processing routes and processing procedures monitored by the front-end cameras.
6. The system of claim 5, wherein the front-end computing box is further specifically configured to:
acquiring a camera number of a front-end camera for transmitting a real-time video stream, and determining a target processing route and a target processing procedure matched with the camera number in the intelligent management unit;
And determining the target processing route and the target processing procedure as the processing route and the processing procedure of the current product.
7. The system of claim 1, wherein the inspection process recommendation unit is further configured to:
When the product information is determined to have a plurality of matched nodes to be inspected, at least one inspection process matched with each node to be inspected is acquired;
Sending each inspection process respectively matched with each node to be inspected to the MES, and associating each inspection process with each node to be processed in the MES so that an inspector can check the inspection process under each node to be processed in the MES in advance.
8. The system of claim 5, wherein the intelligent management unit is further configured to:
and acquiring a misrecognized product image, training and updating a product recognition model in a front-end computing box by utilizing the misrecognized product image, and transmitting the updated product recognition model to the front-end computing box.
9. The system of claim 5, wherein the intelligent management unit is further configured to:
When an update request is detected, updating the inspection template library and/or the node template library, and issuing the updated inspection template library and/or the node template library to the front-end computing box.
10. The system of claim 5, wherein the intelligent management unit is further configured to:
managing equipment information of each front-end camera and a front-end computing box;
The equipment information comprises purchasing time, equipment number, input use time, working state and coverage working area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410406540.3A CN118400492A (en) | 2024-04-07 | 2024-04-07 | Automatic recommendation system for inspection process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410406540.3A CN118400492A (en) | 2024-04-07 | 2024-04-07 | Automatic recommendation system for inspection process |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118400492A true CN118400492A (en) | 2024-07-26 |
Family
ID=91998265
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410406540.3A Pending CN118400492A (en) | 2024-04-07 | 2024-04-07 | Automatic recommendation system for inspection process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118400492A (en) |
-
2024
- 2024-04-07 CN CN202410406540.3A patent/CN118400492A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lee et al. | A big data analytics platform for smart factories in small and medium-sized manufacturing enterprises: An empirical case study of a die casting factory | |
| US6725181B2 (en) | Method and system for collecting and monitoring shop floor information | |
| CA2924611C (en) | Systems and methods for non-destructive testing involving remotely located expert | |
| US5767848A (en) | Development support system | |
| JP5254612B2 (en) | Graphic review user setting interface | |
| US10423669B2 (en) | Manufacturing process visualization apparatus and method | |
| CN113780900B (en) | Welding detection system and method based on edge calculation | |
| JP4286296B2 (en) | Requirement Confirmation Support Program, Requirement Confirmation Support Method, and Requirement Confirmation Support Device | |
| CN105760555B (en) | A kind of filter stick formation analysis of processing quality and traceability system and its method | |
| US7310591B2 (en) | Factor estimating device, method and program recording medium therefor | |
| US20220284699A1 (en) | System and method of object detection using ai deep learning models | |
| CN113838480B (en) | Washing machine abnormal sound detection method and device and electronic equipment | |
| CN112465288A (en) | System and method for automatically capturing technology transfer knowledge | |
| CN111652659B (en) | VR product evaluation system based on big data | |
| KR102524151B1 (en) | Labeling learning method of artificial intelligence machine for smart products inspection | |
| JP2002251212A (en) | Method for quality control and system for the same and recording medium with its program recorded | |
| CN118400492A (en) | Automatic recommendation system for inspection process | |
| JPH10275168A (en) | Design support method and system therefor | |
| JP2023073074A (en) | Quality management system, quality management method, quality management program, and information processor | |
| JP4351578B2 (en) | Production planning support system and computer program | |
| Barreto et al. | Defining and monitoring strategically aligned software improvement goals | |
| US20240090516A1 (en) | system and method to measure, identify, process and reduce food defects during manual or automated processing | |
| CN111652526A (en) | VR product analysis and evaluation method | |
| CN117314269B (en) | Quality inspection model management method, system, electronic equipment and storage medium | |
| JP7331572B2 (en) | Manufacturing cost calculation forecast system, manufacturing cost calculation forecast method, and manufacturing cost calculation forecast program |
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 |