EP3881142A1 - Procédé pour la fourniture d'un modèle pour au moins une machine, système de formation, procédé pour la simulation d'un fonctionnement d'une machine ainsi que système de simulation - Google Patents

Procédé pour la fourniture d'un modèle pour au moins une machine, système de formation, procédé pour la simulation d'un fonctionnement d'une machine ainsi que système de simulation

Info

Publication number
EP3881142A1
EP3881142A1 EP20706947.7A EP20706947A EP3881142A1 EP 3881142 A1 EP3881142 A1 EP 3881142A1 EP 20706947 A EP20706947 A EP 20706947A EP 3881142 A1 EP3881142 A1 EP 3881142A1
Authority
EP
European Patent Office
Prior art keywords
machine
model
measured values
trained model
trained
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
Application number
EP20706947.7A
Other languages
German (de)
English (en)
Inventor
Pandu Raharja
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.)
Siemens AG
Original Assignee
Siemens AG
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 filed Critical Siemens AG
Publication of EP3881142A1 publication Critical patent/EP3881142A1/fr
Pending legal-status Critical Current

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
    • G05B17/00—Systems involving the use of models or simulators of said systems
    • G05B17/02—Systems involving the use of models or simulators of said systems electric
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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
    • G05B2219/20—Pc systems
    • G05B2219/25—Pc structure of the system
    • G05B2219/25298—System identification

Definitions

  • the present invention relates to a method for providing a model for at least one machine, in particular a machine tool.
  • the present invention also relates to a training system, a computer program and a computer-readable (storage) medium.
  • the present invention also relates to a method for simulating an operation of a machine.
  • the present invention also relates to a simulation system and an associated computer program.
  • machine learning methods can in principle be used.
  • the machine is in operation, it is possible, for example, to record a time series of measured values, the measured values describing operating parameters or an operating state of the machine.
  • Machine learning methods can be used to derive operating variables the behavior of the controller device.
  • the linear regression in which either a linear or a non-linear kernel can be used, can be known here.
  • the training of a corresponding model, by means of which the control device can be mapped, is often very time-consuming and complicated, especially in the case of complex control devices such as those used in machine tools.
  • a device for identifying a structure and for estimating parameters of a controlled system is known.
  • a structure of a function is to be determined using structure identification means, which describes a mathematical relationship between inputs in a system and outputs of the system.
  • structure identification means which describes a mathematical relationship between inputs in a system and outputs of the system.
  • the parameters associated with the function are then estimated by means of parameter estimation means.
  • US 2002/0072828 A1 describes a method for modeling a non-linear empirical process. Based on an initial model, a non-linear network model is to be constructed with several inputs based on the initial model. A global behavior of the non-linear network model as a whole should generally conform to an initial output of the initial model. The non-linear network model is optimized based on empirical inputs while limiting the global behavior.
  • DE 10 2006 054 425 A1 discloses a method for determining a value of a model parameter of a reference vehicle model.
  • An estimated value of the model parameter is determined several times as a function of a second driving state variable and / or a variable specified by a driver by means of an artificial neural network.
  • the artificial neural network is adapted using a learning process. It is the object of the present invention to show a solution as to how the operation of a machine which is controlled by means of a control device can be modeled more simply and reliably at the same time.
  • this object is achieved by a method for providing a model, by a training system, by a computer program product, by a computer-readable one
  • a method according to the invention is used to provide a model for at least one machine, in particular a machine tool.
  • operation of the machine is regulated by means of a regulator device.
  • the method includes receiving a time series of measured values, the measured values describing an operating variable of the machine.
  • the method includes the provision of an untrained model in the form of an artificial neural network.
  • the method also includes training the untrained model using the received measured values and determining derived control variables that describe the controller device using the trained model.
  • the trained model is preferably expanded on the basis of the measured values of the further machine by means of transfer learning, that is, further trained.
  • transfer learning is known in principle.
  • a model that is trained for a specific application is applied to a similar application.
  • a model that is trained to detect objects can be further trained or expanded to that effect can recognize these corresponding machines or machine types.
  • the model that is trained on the basis of the time series of the machine or a first machine is expanded with the time series of the further machine or a second machine.
  • the machine can be, for example, a first machine from one manufacturer and the further machine can be a second machine or a similar machine from the same manufacturer.
  • the trained model can already be stable.
  • This trained model can be expanded by the measured values of the other machine. If the time sequence of the measured values of the further machine is now fed to the model that has already been trained, the transfer learning can be carried out.
  • the model can be adapted to the changing measured values or parameters, for example. If, for example, a neural network with several hidden layers is used for the model, the respective weights can be adapted to the changed parameters.
  • a model that has already been created for the machine can also be used for the other machine by means of transfer learning.
  • This also offers the possibility of providing a reference model for a machine, which can then be adapted to the specific machine by means of transfer learning.
  • the method is in particular a computer-implemented method.
  • the machine can basically be an electrical machine.
  • the machine is a machine tool, for example a CNC machine.
  • the machine can therefore be a CNC milling machine, a CNC lathe or the like.
  • the operation of the machine is regulated by means of the Reglervor direction.
  • This regulator device can comprise at least one regulator.
  • the regulator device preferably comprises but a plurality of controllers or control loops.
  • An operating variable of the machine can be regulated by means of the regulator device.
  • an actual value for the operating variable can be recorded by means of the control device and compared with a setpoint value for the operating variable.
  • the operating variable can be regulated to the target value by means of the regulating device.
  • the operating variable of the machine can be, for example, a speed, a direction of rotation, a torque, a feed rate, an electrical voltage, an electrical current or the like.
  • the time series or sequence of measured values can now be provided.
  • the measured values describe at least one operating variable of the machines.
  • the measured values can also describe several operating parameters of the machine. It can also be provided that several or different measured values are recorded.
  • a sensor signal can be scanned accordingly by the sensor or the detection device. These sampled measured values can then be further processed accordingly.
  • the time series of measured values can be fed to a training system.
  • This training system can be used to determine the model for the machine or for several machines.
  • the training system can have a corresponding computing device by means of which the model can be created. For this purpose, a corresponding computer program can be executed on the computing device.
  • the untrained model is first made available.
  • the untrained model is an artificial neural network. This model can be trained accordingly to determine the model or to provide the trained model.
  • the time series is used as training data the measured values are used.
  • the trained model which describes the regulated operation of the electrical machine, can be output.
  • the model is an artificial neural network.
  • This artificial neural network can also be referred to as an artificial neural network or a neural network.
  • An artificial neural network is formed by artificial neurons or nodes that are connected to one another. The connections can provide direct connections between two nodes.
  • the respective nodes can be arranged in respective layers or hidden layers.
  • the nodes can be arranged one behind the other in several layers.
  • the artificial neural network has an input layer and an output layer as well as the hidden layers in between.
  • the artificial neural network can first be constructed. The topology of the artificial neural network or the assignment of connections to nodes can be provided for the application.
  • the training phase can take place in which the artificial neural network is trained.
  • the training data are fed to the artificial neural network for training purposes.
  • the artificial neural network or the untrained model can be provided as training data with the chronological sequence of measured values and, if applicable, data for control theory.
  • new connections can be developed and / or existing connections can be deleted. It can also be provided that corresponding weightings or weighting factors of the nodes or neurons are adapted. Nodes can also be added and / or removed become.
  • the training can be carried out as supervised or supervised learning. In this case, the output is given to the neural network. However, it can also be provided that unsupervised or unsupervised learning is carried out during the training. In this case the output is not specified. In addition, reinforcement learning can be used during the training phase.
  • the trained model describes the operation of the machine, which is controlled by means of the control device.
  • control parameters or control variables that describe the control device can now be derived after the training.
  • These derived controlled variables can describe a transfer function of the controller device, for example.
  • the controlled variables can describe a type of regulator device or of individual regulators of the regulator device.
  • the trained model or the artificial neural network is used to identify how the operating variable of the machine is regulated based on the time profile of the measured values. It should therefore be recognized in which way the operating variable is influenced by the controller.
  • the transfer function of the controller device has a proportional transfer behavior, an integrative transfer behavior, a differentiating transfer behavior and / or a time-delaying transfer behavior.
  • the controller behavior of the controller device can thus be derived with the aid of the trained model. Additional information about the regulator device can thus be obtained in a simple yet reliable manner.
  • the determination of the derived control variables is preferably carried out on the basis of control theory data, the control theory data operating modes of control devices describe.
  • the control theory data can describe known methods of control engineering.
  • the control theory data can describe different transmission functions of controllers.
  • This transfer function can describe the ratio of the input variable to the output variable.
  • the time series of measured values can describe the output variable. It can also be provided that the output variable can be derived from the measured values.
  • the control theory data can describe the different known transfer functions that are usually used in controllers or controller devices. As already explained, the transfer function can describe proportional behavior, an integrative behavior, a differentiating behavior, a time-delaying behavior, a control with dead time or corresponding combinations thereof.
  • These control theory data can be fed to the untrained model or the artificial neural network as training data. During the training, the time courses of the measured values can then be assigned to the corresponding transfer functions. The control theory data can thus be determined in a simple and reliable manner.
  • the artificial neural network that is being trained has a plurality of hidden layers.
  • the neural network is a so-called deep neural network.
  • Such a multi-layer artificial neural network also includes several concealed layers in the output layer, the output of which is not visible outside the network. With such an artificial neural network, deep learning or deep learning can be made possible. The model or the artificial neural network can thus be trained in a reliable manner so that it describes the operation of the controlled machine.
  • the measured values describe different operating states of the machine.
  • the under- Different operating states can describe a change in the speed of the electrical machine, for example.
  • different operating states can describe, for example, starting up the machine, changing the speed, changing the thrust, using different tools or the like.
  • corresponding setpoint values of the controller device are taken into account.
  • These target values can be specified, for example, by operating the machine accordingly. It can also be provided that these setpoint values are recorded accordingly.
  • the respective target values can be taken into account when training the model or the artificial neural network or used as training data. It can thus be deduced how the operating variable of the machine is regulated to the target value by means of the controller device. The controlled variables can then be derived from this.
  • the present invention provides in particular that further derived control variables, which describe the further controller device, are determined on the basis of the expanded trained model.
  • the expanded, trained model which was created by transfer learning on the basis of the trained model, can now be used to derive the control variables of the further control device by means of which the further machine is controlled.
  • the trained model is already available, the advanced trained model can be made available with little effort through the transfer learning. From this the properties of the further control device can then be derived.
  • a training system comprises a first interface for receiving a time series of measured values from a machine.
  • the training system comprises a computing device for determining a trained model based on the received measured values.
  • the training system comprises a second interface for outputting the trained model.
  • the training system can, for example, be provided by an appropriate computer. This training system can be connected for data transmission via the first interface of the machine or a sensor of the machine with which the measured values are provided. A corresponding computer program can then be executed on a computing device of the training system in order to train the model on the basis of the measured values.
  • the method according to the invention for providing the model can be carried out with the aid of the training system.
  • a computer program according to the invention comprises commands which, when the program is executed by a training system or a computing device of the training system, cause this or these to execute the method according to the invention and the advantageous refinements thereof.
  • a computer-readable (memory) medium comprises commands which, when executed by a training system, cause the latter to execute the method according to the invention and the advantageous refinements thereof.
  • a further aspect of the invention relates to a method for simulating the operation of a machine, in particular a machine tool, with operation of the machine being regulated by means of a regulator device.
  • the operation of the machine is based on a model, which is according to the method for providing a model and / or the advantageous embodiments thereof is determined, modeled.
  • the model can be provided for a specific machine.
  • the model can be used to simulate the operation of this controlled machine.
  • the model can be executed on a corresponding simulation system or a computer. In this way, the controlled operation of the machine can be simulated or modeled.
  • the operation of the machine and, in particular, a manufacturing method that is carried out with the machine can be tested beforehand, for example. It is therefore not necessary, for example, to carry out corresponding tests with the real machine. Damage to workpieces and / or the machine can thus be prevented.
  • the model can be used for an error analysis in the real machine.
  • control device is emulated by means of the trained model.
  • the function of the control device can thus be simulated with the model or with the artificial neural network. In this way it can be checked how the control device reacts to certain input variables. In this way, appropriate settings can be derived or optimized in real operation of the machine.
  • a simulation system is used to simulate the operation of a machine, in particular a machine tool, with operation of the machine being regulated by means of a controller device.
  • the simulation system is designed to carry out a method according to the invention for simulating an operation of a machine.
  • the invention relates to a computer program comprising commands which, when the program is executed by a simulation system, cause the program to execute the method according to the invention for simulating the operation of a machine.
  • Another aspect of the invention relates to a computer-readable (storage) medium, comprising commands which, when executed by a simulation system, cause the simulation system to execute a method according to the invention for simulating an operation of a machine.
  • FIG. 1 shows a schematic flow diagram of a method for providing a model for a machine, operation of the machine being regulated by means of a regulator device;
  • FIG. 2 shows a schematic flow diagram of a method for determining a model for a machine according to a further embodiment.
  • the machine A can be a machine tool.
  • the machine A is a CNC machine.
  • the operation of the machine A is regulated by means of a regulator device 2.
  • This regulator device 2 can have several regulators or control loops.
  • the model M A for the machine A can be determined by means of a training system 1.
  • This training system 1 can be formed by a corresponding computer.
  • the training system 1 has a corresponding computing device 6.
  • An untrained model is fed to the training system 1 via an interface 3.
  • the untrained model is an artificial neural network, in particular a so-called deep neural network.
  • a time series of measured values X A are fed to the training system 1 via an interface 4.
  • These values X A describe operating variables of the machine A.
  • the measured values X A can describe a speed, a direction of rotation, a torque, an electrical voltage, an electrical current or the like.
  • the regulation of the machine A by means of the regulator device 2 is carried out on the basis of Re gel variables Q A.
  • control theory data can also be fed to it.
  • These control theory data describe, in particular, properties of known control devices 2.
  • the control theory data can describe different transfer functions that are used by control devices 2.
  • the properties of the control device 2 or the control algorithm of the control device 2 can be approximated or determined based on the time course of the measured values X A or the operating variables and the known control theory data.
  • the trained model M A can then be output by the training system 1 via an interface 5.
  • derived control variables Q ' A can then be provided.
  • the derived controlled variables Q ' A be describing the properties of the controller device 2 that were determined during the training.
  • the trained model M A thus describes the operation of the machine A, which is controlled by means of the control device 2.
  • FIG. 2 shows a schematic flow diagram for determining a model M AB according to a further embodiment.
  • the untrained model M ö is first trained on the basis of the measured values X A of the machine A. After this training, the trained model M A can be provided. In this case, what is known as transfer learning is also carried out.
  • the trained model M A is fed to the training system 1 in a subsequent step.
  • measured values X B are determined by a further machine B and fed to the training system 1.
  • the operation of the further machine B is controlled by means of a further control device 2 '.
  • the machines A and B can, for example, come from the same manufacturer and different or similar types of machines be.
  • the trained model M A can then be expanded and the expanded, trained model M AB can be output by means of the training system 1.
  • This expanded, trained model M AB can in turn be used to determine derived control variables 0 ' A', Q b , which were determined on the basis of the control devices 2, 2 'of the machines A, B.
  • the trained model M A or the expanded trained model M AB can be used to simulate the operation of the machine A, B.
  • the model M A , M AB can be run on a corresponding simulation system 7 or computer. This is shown schematically in FIG.
  • the operation of the machine A, B, which is controlled by the control device 2, 2 ', can thus be simulated or reproduced. In this way, information about the usually unknown functionality of the complex controller device 2, 2 'can be obtained. Overall, this makes it possible to optimize the operation of the machine A, B and to avoid errors.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Automation & Control Theory (AREA)
  • Feedback Control In General (AREA)

Abstract

L'invention concerne un procédé pour la fourniture d'un modèle (MA, MA,B) pour au moins une machine (A, B), en particulier une machine-outil, un fonctionnement de la machine (A) étant réglé au moyen d'un dispositif de réglage (2), comprenant les étapes de : - réception d'une série temporelle de valeurs de mesure (XA), les valeurs de mesure (XA) décrivant une grandeur de fonctionnement de la machine (A), - fourniture d'un modèle (MU) non-formé d'un réseau de neurones artificiels, - formation du modèle non-formé (MU) au moyen des valeurs de mesure (XA) reçues, et - détermination de grandeurs de réglage (Ө'A) dérivées, lesquelles décrivent le dispositif de réglage (2), au moyen du modèle formé (MA)), une série temporelle de valeurs de mesure (XB) d'une autre machine (B), dont le fonctionnement est réglé au moyen d'un autre dispositif de réglage (2'), étant reçue, la machine (A) et l'autre machine (B) étant des types de machines (A, B) différents, et le modèle formé (MA) étant formé davantage par apprentissage de transfert au moyen des valeurs de mesure (XB) de l'autre machine (B).
EP20706947.7A 2019-02-19 2020-02-07 Procédé pour la fourniture d'un modèle pour au moins une machine, système de formation, procédé pour la simulation d'un fonctionnement d'une machine ainsi que système de simulation Pending EP3881142A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
EP19157949.9A EP3699699A1 (fr) 2019-02-19 2019-02-19 Procédé de fourniture d'un modèle pour au moins une machine, système d'apprentissage, procédé de simulation de fonctionnement d'une machine ainsi que système de simulation
PCT/EP2020/053099 WO2020169363A1 (fr) 2019-02-19 2020-02-07 Procédé pour la fourniture d'un modèle pour au moins une machine, système de formation, procédé pour la simulation d'un fonctionnement d'une machine ainsi que système de simulation

Publications (1)

Publication Number Publication Date
EP3881142A1 true EP3881142A1 (fr) 2021-09-22

Family

ID=65529270

Family Applications (2)

Application Number Title Priority Date Filing Date
EP19157949.9A Withdrawn EP3699699A1 (fr) 2019-02-19 2019-02-19 Procédé de fourniture d'un modèle pour au moins une machine, système d'apprentissage, procédé de simulation de fonctionnement d'une machine ainsi que système de simulation
EP20706947.7A Pending EP3881142A1 (fr) 2019-02-19 2020-02-07 Procédé pour la fourniture d'un modèle pour au moins une machine, système de formation, procédé pour la simulation d'un fonctionnement d'une machine ainsi que système de simulation

Family Applications Before (1)

Application Number Title Priority Date Filing Date
EP19157949.9A Withdrawn EP3699699A1 (fr) 2019-02-19 2019-02-19 Procédé de fourniture d'un modèle pour au moins une machine, système d'apprentissage, procédé de simulation de fonctionnement d'une machine ainsi que système de simulation

Country Status (4)

Country Link
US (1) US20220138567A1 (fr)
EP (2) EP3699699A1 (fr)
CN (1) CN113454544A (fr)
WO (1) WO2020169363A1 (fr)

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0496570B1 (fr) * 1991-01-22 1998-06-03 Honeywell Inc. Dispositif d'identification d'un système à deux niveaux avec optimisation
EP1163062B1 (fr) * 1999-03-23 2002-11-13 Siemens Aktiengesellschaft Procede et dispositif pour determiner la force de laminage dans une cage de laminoir
DE60102242T2 (de) * 2000-06-29 2005-01-27 Aspen Technology, Inc., Cambridge Rechnerverfahren und gerät zur beschränkung einer nicht-linearen gleichungsnäherung eines empirischen prozesses
WO2007060134A1 (fr) * 2005-11-22 2007-05-31 Continental Teves Ag & Co. Ohg Procede et dispositif de determination d'un parametre d'un modele de vehicule de reference
CN108280462A (zh) * 2017-12-11 2018-07-13 北京三快在线科技有限公司 一种模型训练方法及装置，电子设备

Also Published As

Publication number Publication date
WO2020169363A1 (fr) 2020-08-27
US20220138567A1 (en) 2022-05-05
CN113454544A (zh) 2021-09-28
EP3699699A1 (fr) 2020-08-26

Similar Documents

Publication Publication Date Title
DE102017011754B4 (de) Maschinenlerneinrichtung zum Lernen eines Montagevorgangs und Komponentenmontagesystem
DE102020100316B4 (de) Bestimmungsgerät
DE102017108169A1 (de) Produktionssystem, das einen Bestimmungswert einer Variablen in Bezug auf eine Produktabweichung festlegt
DE102007017039A1 (de) Robuste Prozessmodellidentifikation bei modellbasierten Steuerungstechniken
WO2021058223A1 (fr) Procédé d'application de fonctions de conduite automatisée de manière efficace et simulée
DE102018001028B4 (de) Numerische Steuerung
DE102019006725A1 (de) Steuereinrichtung und Steuersystem
DE102020102863A1 (de) Parametrierung einer Komponente in der Automatisierungsanlage
DE102019134053A1 (de) Verfahren zur kontinuierlichen Absicherung im Fahrversuch applizierter automatisierter Fahrfunktionen
WO2020187591A1 (fr) Procédé et dispositif de commande d'un robot
DE102019104922A1 (de) Kollisionspositionsschätzvorrichtung und maschinenlernvorrichtung
DE102019001177B4 (de) Steuergerät, maschinelle Lernvorrichtung und System
WO2013026636A1 (fr) Procédé d'établissement d'un modèle
DE112021005541T5 (de) Simulationsprogramm, Simulationsvorrichtung und Simulationsverfahren
DE102018003244A1 (de) Numerische Steuerung
WO2020169363A1 (fr) Procédé pour la fourniture d'un modèle pour au moins une machine, système de formation, procédé pour la simulation d'un fonctionnement d'une machine ainsi que système de simulation
EP3999925B1 (fr) Procédé et dispositifs de détermination d'une qualité de produit
EP3979009A1 (fr) Génération d'un modèle simplifié pour systèmes xil
WO2021089499A1 (fr) Procédé et système pour vérifier une fonction de conduite automatisée par apprentissage par renforcement
DE102019131456A1 (de) Verfahren zum Bestimmen einer Eigenschaft einer Maschine, insbesondere einer Werkzeugmaschine, ohne messtechnisches Erfassen der Eigenschaft
DE102018217139B4 (de) Verfahren und Vorrichtung zum Konfigurieren einer Kennfunktion eines Steuergeräts eines Kraftfahrzeugs
DE102023106248A1 (de) Spurstangenkraftschätzung bei Steer-by-Wire-Systemen mittels intelligentem Modellübergang
WO2011082909A1 (fr) Dispositif de détermination de paramètres d'appareil de commande
WO2024002705A1 (fr) Procédé de détermination d'une configuration de régulateur pour un système d'entraînement, programme informatique, support lisible par ordinateur, dispositif et système d'entraînement
EP3491517B1 (fr) Programme informatique basé sur un flux de signaux comportant des boucles de traversée directe (df)

Legal Events

Date Code Title Description
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: UNKNOWN

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE

PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

17P Request for examination filed

Effective date: 20210615

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

DAV Request for validation of the european patent (deleted)
DAX Request for extension of the european patent (deleted)
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: EXAMINATION IS IN PROGRESS

17Q First examination report despatched

Effective date: 20231002