WO2023227201A1 - Procédé mis en oeuvre par ordinateur et système pour commander la production d'un produit - Google Patents

Procédé mis en oeuvre par ordinateur et système pour commander la production d'un produit Download PDF

Info

Publication number
WO2023227201A1
WO2023227201A1 PCT/EP2022/064000 EP2022064000W WO2023227201A1 WO 2023227201 A1 WO2023227201 A1 WO 2023227201A1 EP 2022064000 W EP2022064000 W EP 2022064000W WO 2023227201 A1 WO2023227201 A1 WO 2023227201A1
Authority
WO
WIPO (PCT)
Prior art keywords
product
automation
template
production
sensor data
Prior art date
Application number
PCT/EP2022/064000
Other languages
German (de)
English (en)
Inventor
Daniel SCHALL
Original Assignee
Siemens Ag Österreich
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 Siemens Ag Österreich filed Critical Siemens Ag Österreich
Priority to PCT/EP2022/064000 priority Critical patent/WO2023227201A1/fr
Publication of WO2023227201A1 publication Critical patent/WO2023227201A1/fr

Links

Classifications

    • 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
    • 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]
    • G05B19/41845—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 system universality, reconfigurability, modularity
    • 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
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/32—Operator till task planning
    • G05B2219/32186—Teaching inspection data, pictures and criteria and apply them for inspection
    • 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
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/32—Operator till task planning
    • G05B2219/32193—Ann, neural base quality management
    • 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
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/32—Operator till task planning
    • G05B2219/32205—Use model error adapted to type of workpiece
    • 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
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/32—Operator till task planning
    • G05B2219/32212—If parameter out of tolerance reject product
    • 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
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/32—Operator till task planning
    • G05B2219/32218—Sort workpieces as function of quality data

Definitions

  • the invention relates to a computer-implemented method and a system for controlling the production of a product selected from at least two product groups that can be produced by the same production device.
  • the invention also relates to a computer program, an electronically readable data carrier and a data carrier signal.
  • Some production systems are configured in such a way that different product groups can be produced by the same system.
  • the object according to the invention is achieved by a method of the type mentioned at the beginning, comprising the following steps: a) Generating a product with a production system and detecting the product in the form of sensor data using a sensor means, b) Determining at least one classification parameter by classifying the product using the sensor data and a model based on artificial intelligence by a second device, and providing the at least one classification parameter to a third device, c) requesting an inspection template based on the at least one classification parameter from a fourth third device by the second device, d) requesting an automation -Template based on the at least one classification parameter from a fourth device and providing it to an automation device, e) analyzing the product using the sensor data and the inspection template by the first device, f) controlling the automation device based on the result of the previous analysis step using the automation template.
  • Parameterization of the automation device enables fast and trouble-free operation and the availability of the production system can be significantly improved.
  • the object according to the invention is also achieved by a production system for the operation of a technical device with a model based on federated learning, comprising memory Storing templates and a model, execution devices with a processor and a memory for executing procedural steps, a sensor means for detecting products as sensor data and an automation device having a handling device, and the system is set up to carry out the method according to the invention.
  • the object according to the invention is solved by a computer program comprising commands which, when executed by a computer, cause it to carry out the method according to the invention.
  • the object according to the invention is achieved by an electronically readable data carrier with readable control information stored thereon, which includes at least the computer program according to the invention and is designed in such a way that it carries out the method according to the invention when the data carrier is used in a computing device.
  • the object according to the invention is achieved by a data carrier signal which transmits the computer program according to the invention.
  • Fig. 1 an exemplary embodiment of a production facility with visual inspection
  • Fig. 2 an example of different product arrangements within a production system
  • FIG. 3 an exemplary embodiment of the invention in the form of a block diagram
  • FIG. 4 an exemplary embodiment of the invention in the form of a flowchart.
  • Fig. 1 shows an exemplary embodiment of a production system with a production facility which is monitored using a visual inspection.
  • a camera CAM uses optical sensors to capture products A, B as camera images, which are moved past the camera on a conveyor belt CB in a direction D.
  • sensor means can also be used for the sensor, for example laser measuring devices, metal detectors or radar sensors, etc.
  • products A, B are shown as pastries which are free of defects or have an optical defect and therefore should be sorted out using a robot R with a gripper.
  • a model based on artificial intelligence is used to recognize products outside of manufacturer specifications and, if necessary, sort them out with a robot arm.
  • a product deviation can be, for example, an undesirable shape, different dimensions or something similar.
  • Some production systems are configured in such a way that different product groups can be produced. Accordingly, it may be necessary to adapt the production system in one or more subsystems for each product group, in particular AI models and product handling devices such as a robot.
  • Fig. 2 represents an example of various product arrangements within the production system of the previous figure.
  • the products A, B and C to be analyzed correspond to a product type of the product group PI, and the products D, E and F correspond to a product type of the product group P2.
  • the products of the product groups are transported sequentially in time using the conveyor belt CB past the detection area of the sensor n of the camera CAM and recorded at times TI and T2 by an optical image sensor of the camera CAM.
  • Fig. 3 shows an exemplary embodiment of the invention in the form of a block diagram of a production system PS.
  • the method serves to control the production of a product which is selected from at least two product groups.
  • the at least two product groups are produced by the same production device.
  • a TR-AI template repository for artificial intelligence is formed by a database, which stores Al templates, makes them available and, through federated learning, shared by other similar clients with corresponding model parameters for visual inspection is supplied in the form of Al templates.
  • An AI template is an artifact, such as Python code with an AI model and all necessary software dependencies, that runs on the AI device.
  • An Al template is trained for a specific product within a product group to perform a visual quality inspection task.
  • a template memory TR-AU for automation is also formed in the cloud C, which stores and provides automation templates and, through federated learning, is jointly supplied by other similar clients with corresponding model parameters for the automation of manufacturing steps in the form of AU templates.
  • the cloud C is connected to an edge device DE, which includes a production machine M, a conveyor belt CB and a handling robot R.
  • the robot R is set up to remove products A-F from the conveyor belt CB.
  • the production machine M like a baking machine, produces the products A-C of the first product group PI, such as bread, and the products D-F of the second product group P2, such as rolls.
  • the baking machine M provides these products A-F on the conveyor belt CB, which transports the produced products A-F away from the machine M at a belt speed D.
  • the camera CAM then records products A-F using an optical sensor.
  • the handling device R such as a robot arm.
  • An AI template providing device instantiates templates in the artificial intelligence execution device.
  • Such an AI template carries out a visual quality inspection using a product classification model PC-M, which is suitable for a product A-F that is currently being analyzed.
  • One or more steps can be performed by a computer with a processor and memory.
  • the RE-AI device is an artificial intelligence execution device with a processor and a memory.
  • the TPE-AI device is an artificial intelligence template delivery device with a processor and memory.
  • the devices RE-AI, RE-E and TPE-AI as well as TPE-AU can be formed by an edge device DE.
  • the TPE-AU device is a template provision device for automation with a processor and a memory and can include a control device for controlling a robot.
  • Optimal parameterization of the automation device R enables fast and trouble-free operation and the availability of the production system can be improved.
  • a gripper of the robot arm R can attack a product with optimal pressure and does not lose it undesirably on the way from the conveyor belt CB.
  • the automation template T-AU-Pl can be requested by the control device or also by the execution unit of the edge device RE-E.
  • Fig. 4 shows an exemplary embodiment of the invention in the form of a flowchart based on the system of the previous figure.
  • the following procedure is carried out on a computer: a) generating a product A, F with a production system PS and detecting the product A, F in the form of sensor data using a sensor means CAM, b) determining at least one classification parameter by classifying the product A, F using the sensor data and a model based on artificial intelligence PC-M by a first device RE-AI, c) requesting an inspection template T-AI-Pl based on the at least one classification parameter from a second device TPE- AI by the first device RE -AI, d) requesting an automation template T-AU-Pl based on the at least one classification parameter from a third device TPE-AU and providing it to an automation device D-AU, e) analyzing of the product A, ..., F using the sensor data and the inspection template T-AI-Pl by the first device RE -AI, f) controlling the automation device D-AU based on the result of the previous analysis - Steps using the automation template T-AU-Pl.
  • step f only compliantly manufactured products are now on the conveyor belt CB.
  • RE-AI execution device for artificial intelligence English “runtime engine for artificial intelligence”

Landscapes

  • Engineering & Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Manufacturing & Machinery (AREA)
  • Quality & Reliability (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • General Factory Administration (AREA)

Abstract

La présente invention concerne un procédé mis en œuvre par ordinateur pour commander la production d'un produit choisi parmi au moins deux groupes de produits qui peuvent être fabriqués à l'aide du même appareil de production, comprenant les étapes suivantes : a) produire un produit (A, B) à l'aide d'un système de production (PS) et capturer le produit (A, B) sous forme de données de capteur à l'aide d'un moyen de capteur (CAM), b) déterminer au moins un paramètre de classification en classant le produit (A, B) à l'aide des données de capteur et d'un modèle basé sur l'intelligence artificielle (PC-M), c) demander un modèle d'inspection (T-AI-P1) sur la base d'au moins un paramètre de classification, d) demander un modèle d'automatisation (T-AU-P1) sur la base du ou des paramètres de classification et le mettre à la disposition d'un appareil d'automatisation (D-AU), e) analyser le produit (A, B) à l'aide des données de capteur et du modèle d'inspection (T-AI-P1), f) commander l'appareil d'automatisation (D-AU) sur la base du résultat de l'étape d'analyse précédente à l'aide du modèle d'automatisation (T-AU-P1).
PCT/EP2022/064000 2022-05-24 2022-05-24 Procédé mis en oeuvre par ordinateur et système pour commander la production d'un produit WO2023227201A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/EP2022/064000 WO2023227201A1 (fr) 2022-05-24 2022-05-24 Procédé mis en oeuvre par ordinateur et système pour commander la production d'un produit

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/EP2022/064000 WO2023227201A1 (fr) 2022-05-24 2022-05-24 Procédé mis en oeuvre par ordinateur et système pour commander la production d'un produit

Publications (1)

Publication Number Publication Date
WO2023227201A1 true WO2023227201A1 (fr) 2023-11-30

Family

ID=82163323

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2022/064000 WO2023227201A1 (fr) 2022-05-24 2022-05-24 Procédé mis en oeuvre par ordinateur et système pour commander la production d'un produit

Country Status (1)

Country Link
WO (1) WO2023227201A1 (fr)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102017103588A1 (de) * 2016-02-24 2017-08-24 Jtekt Corporation Analysevorrichtung und analysesystem
EP3778142A1 (fr) * 2019-08-14 2021-02-17 Google LLC Cellules de fabrication robotique reconfigurables
WO2021171287A1 (fr) * 2020-02-24 2021-09-02 Saccade Vision Ltd. Système et procédé de contrôle de l'inspection automatique d'articles
WO2022029787A1 (fr) * 2020-08-05 2022-02-10 Kitov Systems Ltd Codage de conception d'exigences d'inspection intercomposants

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102017103588A1 (de) * 2016-02-24 2017-08-24 Jtekt Corporation Analysevorrichtung und analysesystem
EP3778142A1 (fr) * 2019-08-14 2021-02-17 Google LLC Cellules de fabrication robotique reconfigurables
WO2021171287A1 (fr) * 2020-02-24 2021-09-02 Saccade Vision Ltd. Système et procédé de contrôle de l'inspection automatique d'articles
WO2022029787A1 (fr) * 2020-08-05 2022-02-10 Kitov Systems Ltd Codage de conception d'exigences d'inspection intercomposants

Similar Documents

Publication Publication Date Title
EP3797337B1 (fr) Procédé de manipulation d'une pièce a l'aide d'un outil de retrait et machine permettant de mettre en oeuvre le procédé
DE102018212531B4 (de) Artikeltransfervorrichtung
EP3767403B1 (fr) Mesure de forme et de surface assistée par apprentissage automatique destinée à la surveillance de production
WO2021028084A1 (fr) Système et procédé d'automatisation destinés à la manipulation de produits
EP3847517B1 (fr) Procédé et dispositif de fabrication d'un produit ainsi que produit programme d'ordinateur
EP2358601B1 (fr) Procédé pour aligner un contenant et programme d'ordinateur
DE102009012832A1 (de) Verfahren und Vorrichtung zur automatischen Einbindung von Sensorvorrichtungen in eine zentrale Steuerung
EP3468727B1 (fr) Dispositif de triage et procédé de triage correspondant
WO2023227201A1 (fr) Procédé mis en oeuvre par ordinateur et système pour commander la production d'un produit
DE102018008366B4 (de) Verfahren und Anlage zum gestenbasierten Steuern eines Prüfprozesses an einem industriellen teilautomatisierten Sichtprüfplatzes eines industriellen technischen Prozesses oder einer industriellen technischen Produktionsanlage
AT519777B1 (de) Verfahren zur Erkennung des normalen Betriebszustands eines Arbeitsprozesses
EP3425324B2 (fr) Procédé de paramétrage d'un capteur
DE102018110063A1 (de) Industrielle fertigungsstätte und verfahren zur automatisierten verbuchung von manuellen tätigkeiten
EP2297700B1 (fr) Procédé de contrôle optique lors du traitement ultérieur de produits d'impression
EP3650223B1 (fr) Dispositif et procédé de contrôle d'une impression d'un article
DE102021211610A1 (de) Verfahren zum Trainieren eines neuronalen Lernmodells zum Detektieren von Produktionsfehlern
WO2013037987A1 (fr) Identification de composants mécatroniques réutilisables dans le domaine de l'automatisation d'usine
DE10013137B4 (de) Verfahren zur bildgesteuerten Prüfung und Bearbeitung von Produkten
WO2023198290A1 (fr) Procédé mis en œuvre par ordinateur et systèmes pour le repositionnement de produits défectueux
DE102018219169A1 (de) Vorrichtung und Verfahren zum Prüfen einer Bedruckung eines Artikels
WO2024052264A1 (fr) Examen de composants pour pannes au moyen d'un analyseur de composants
DE102022131925A1 (de) Selbstlernendes verfahren für einen fertigungs- und/oder montageprozess
WO2023046653A1 (fr) Procédé pour déterminer si un article à transporter prédéfini est disposé dans une zone de surveillance
DE102016000821A1 (de) Herstellungsverfahren und Anlage zur Anwendung des Herstellungsverfahrens
WO2024115613A1 (fr) Procédé d'auto-apprentissage pour un processus de fabrication et/ou de montage

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22732903

Country of ref document: EP

Kind code of ref document: A1