EP3969230A1 - Intelligence artificielle dans la fabrication discrète - Google Patents

Intelligence artificielle dans la fabrication discrète

Info

Publication number
EP3969230A1
EP3969230A1 EP19724411.4A EP19724411A EP3969230A1 EP 3969230 A1 EP3969230 A1 EP 3969230A1 EP 19724411 A EP19724411 A EP 19724411A EP 3969230 A1 EP3969230 A1 EP 3969230A1
Authority
EP
European Patent Office
Prior art keywords
per
quality
program
data
parameters
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
EP19724411.4A
Other languages
German (de)
English (en)
Inventor
Volker Kreidler
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.)
Big Data In Manufacturing GmbH
Original Assignee
Big Data In Manufacturing GmbH
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 Big Data In Manufacturing GmbH filed Critical Big Data In Manufacturing GmbH
Publication of EP3969230A1 publication Critical patent/EP3969230A1/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
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Program-controlled manipulators
    • B25J9/16—Program controls
    • B25J9/1628—Program controls characterised by the control loop
    • B25J9/163—Program controls characterised by the control loop learning, adaptive, model based, rule based expert control
    • 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
    • G05B2219/32194—Quality prediction
    • 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
    • G05B2219/33—Director till display
    • G05B2219/33321—Observation learning
    • 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
    • G05B2219/39—Robotics, robotics to robotics hand
    • G05B2219/39271—Ann artificial neural network, ffw-nn, feedforward neural network
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/80—Management or planning

Definitions

  • the invention relates to the products and process as per the first portion of the independent claims.
  • NC numerical control
  • CNC computerized numerical control
  • a CNC machine alters a blank piece of material such as metal, plastic, wood, ceramic, or any composite thereof to meet precise specifications by following programmed instructions and without a manual operator.
  • PTL1 discloses a closed-loop control process for a machining tool based on a numerical control program.
  • the NC program (1) is generated offline by an NC programming
  • An essential software component of CNC controller commonly referred to as the interpolator (2) computes the most important commanded points for the programmed tool path.
  • Another software task of the controller is known as the position controller and, based on the path, periodically calculates commanded axes positions, velocity and acceleration along each of the axes.
  • the generated commanded position is transmitted to a drive or current controller which periodically and precisely computes the required electrical current.
  • all commanded values are reliably and periodically updated periodically at varying time intervals.
  • the interpolator task of today’s CNC-controller is being executed every 4 msec/250Hz, the position task at 1 msec/1.000 Hz, the drives control task works at a frequency of 50 microsec/2.000 Hz.
  • each CNC machine is equipped with position sensors that constantly measure the current position of each axis. From these sensor values (3), further variables such as speed,
  • the drives provide the real current values and current acceleration for the execution of the drives control loop.
  • measurements (4) are typically taken by means of conventional coordinate measuring machines (CMM) to inspect the piece’s geometrical and surface quality.
  • CMM coordinate measuring machines
  • the measurements can be defined in terms of tolerance, such as may apply to parallelism, perpendicularity, angularity, position, concentricity, or circularity.
  • tolerance such as may apply to parallelism, perpendicularity, angularity, position, concentricity, or circularity.
  • NC program is static and does not change during series
  • Figure 1 shows a conventional CNC machining process.
  • Figure 2 illustrates Data-Preparation and Pre-Processing
  • Figure 3 illustrates the model-generation process
  • Figure 4 illustrates the quality root cause analysis. It identifies the NC- program-parameters impacting the part tolerances.
  • Figure 5 illustrates the prediction of part quality based on the digitally
  • Figure 6 illustrates the online adaption of NC-program-parameters in order to accomplish the required part quality.
  • Figure 7 illustrates the root cause analysis of all NC-parameters which influence the cycle time of the manufacturing process.
  • Figure 8 illustrates the online adaption of the relevant NC-program
  • Figure 9 illustrates the applied Artificial Intelligence methods.
  • Figure 10 illustrates the data-driven modelling
  • Figure 11 illustrates how Machine Learning generates the digital model.
  • Figure 12 illustrates how Machine Learning optimizes the input
  • Figure 13 illustrates the methodological components of the Machine
  • Figure 14 illustrates two methodological types of root cause analytics.
  • Figure 15 illustrates two methodological types of machine learning. Description of embodiments
  • the input data used is being prepared and pre-processed for the subsequent Quality and Productivity Analytic applications.
  • the input data include:
  • phase 2 the machine learning model is generated and parameterized.
  • the input data (configuration data of the machine, controllers and drives, NC program, dynamically generated setpoint data, sensor data and the output data are correlated.)
  • the output data are the quality data measured by a measuring machine such as parallelism, rectangularity, centricity, concentricity or circularity accuracy.
  • the manufacturing tolerances specified in all production processes are quantitatively evaluated during the workpiece measurement and it is determined whether these tolerances are in the defined window or outside, i.e. whether reject parts were produced by tolerance violation.
  • the machine learning therefore establishes the correlation between the input data and the actual production tolerances.
  • the resulting quality data of the workpieces can in one case be predicted from the input data, in the other case can be identified from the measured manufacturing tolerances, which input parameters for the result was responsible at what impact.
  • the input data can also online being adapted during machining in order to produce 100% good workpieces.
  • Figure 4 illustrates an example where a given tolerance - here, in terms of circularity - was violated with a deviation of 15 pm, the affected contours of the workpiece (6) being circled in the drawing.
  • the proposed method (10 - Figure 2) pinpoints among the parameters of the NC program (1) the interpolation method, commanded feed rate, and tool data as causing this circularity defect with at an impact ratio of 53 % to 19 % to 28 %.
  • the NC programmer will readily apprehend that the deviation may be reduced by adapting said parameters.
  • the conventional approach does not have a root-cause model between input- and output variables and a very time- consuming trial and error process must be executed. To reach an optimum is practically impossible.
  • the machine learning system may adapt parameters of the
  • NC program (1)“online” to minimize any quality breaches, striving for zero- defect production.
  • Figure 6 Since the machine learning system has generated a root cause model between all input- and dynamically generated commanded values, resulting real values and the resulting part quality the system can also be applied to achieve Zero-Defect
  • the computational model of the process may be trained for optimization goals other than quality of the workpiece, for instance, the cycle time or net process time required by the tool for machining the workpiece.
  • the network establishes any correlations between, for instance, parameters of the NC program and resulting cycle time.
  • the method identifies commanded feed rate, commanded acceleration, commanded jerk, commanded drives current and commanded power consumption of the spindle as influential at a ratio of 21 %, 27%, 19%, 21 % and 12%. Knowledge of these correlations will allow the NC programmer to adjust said parameters to eliminate wasteful expenditure of resources.
  • embodiments may fine-tune the identified parameters of the NC program online in order to minimize cycle time.
  • the system is trying to achieve the minimum cycle time.
  • Pre-processing the data is essential for good results.
  • Correlation Analysis prunes the feature space by finding relevant or redundant features, while Autoencoders do the same by compressing and reconstructing input vectors.
  • Principal Component Analysis also simplifies the data for the later stages by finding the features which best represent the data with minimal loss in information.
  • a Fast Fourier Transformation converts cyclic data (might be a subset of the original features) into its spectral representation which yields information about the main frequencies observed in the data. A change in frequency often is the result of an anomaly/error in real use cases and even small changes in the spectrum can be detected via the later stages.
  • the pre-processed data is then feed into a Machine Learning model
  • the output of the trained model when presented with new data can be used for root cause analysis, optimizing input parameters or predictive maintenance.
  • the training step is using a model specific algorithm to learn the relation between the input data (sensors, parameters, ...) and the output (quality measurements, cycle times, error cases).
  • the goal is a model which can produce accurate predictions about the output when presented with new input data, reducing for example the need for manual measurements.
  • the process of model creation usually consists of three steps.
  • a naive model tries to predict a known output value based on the corresponding input. By comparing the prediction with the actual value, it creates an error measure which it uses to update itself to minimize this error. This process is repeated for all datapoints in the training set or until the prediction is optimal.
  • the system can also search for better combinations of input parameters given the environmental features and a metric to optimize (like no defects, shortest cycle time, most throughput).
  • correlation analysis yields insight about the weight of impact each input dimension (sensors, parameters, ...) has on the output. Additionally, after analyzing a datapoint as anomalous, the feature relevance can be computed to find the root cause of the problem.
  • the process of model creation usually consists of three steps.
  • a naive model tries to predict a known output value based on the corresponding input. By comparing the prediction with the actual value, it creates an error measure which it uses to update itself to minimize this error. This process is repeated for all datapoints in the training set or until the prediction is optimal.
  • the learned model can then be used to detect anomalies, classify errors or predict attributes. With new data, the model can also be updated to improve the precision or learn new classes.
  • Irregular behavior can also be traced back and attributed to individual features/sensors by calculating the distances between the model’s representation of normal behavior and current sensor values.
  • the invention is applicable, among others, throughout the CNC-controller and robot-based discrete manufacturing industry. Reference signs list
  • NPL1 SMID, Peter. CNC programming handbook: a comprehensive guide to practical CNC programming. Industrial Press Inc., 2003.

Landscapes

  • Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Mechanical Engineering (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Robotics (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Numerical Control (AREA)

Abstract

La qualité d'une pièce à usiner (6) ne peut être mesurée qu'une fois qu'elle a été usinée. Si la pièce à usiner (6) doit être rejetée en raison d'écarts, toute corrélation entre ces écarts et des paramètres du programme de commande numérique n'est pas apparente. Pour améliorer le résultat d'usinage, chaque paramètre candidat du programme de commande numérique doit donc être modifié dans une procédure d'essai et d'erreur longue et fastidieuse. Le comportement dynamique de l'interpolateur, du contrôleur de position et de l'entraînement peut ainsi être considéré comme "boîte noire", le fonctionnement détaillé de ces modules de commande restant largement non transparent. En outre, le programme de commande numérique est statique et ne change pas pendant la production en série. Même si le comportement des machines change pendant une période plus longue en raison du vieillissement, le programme de commande numérique reste inchangé, ce qui entraîne une dégradation du fluage de la qualité de la pièce à usiner. Il n'y a généralement pas d'adaptation pour modifier les conditions de production. Selon l'invention, des techniques d'apprentissage machine sont utilisées, par exemple, pour prédire la qualité de production, pour optimiser ou réduire le temps de cycle d'usinage sur machine à commande numérique par calculateur.
EP19724411.4A 2019-05-11 2019-05-11 Intelligence artificielle dans la fabrication discrète Pending EP3969230A1 (fr)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/EP2019/062104 WO2020228932A1 (fr) 2019-05-11 2019-05-11 Intelligence artificielle dans la fabrication discrète

Publications (1)

Publication Number Publication Date
EP3969230A1 true EP3969230A1 (fr) 2022-03-23

Family

ID=66554368

Family Applications (1)

Application Number Title Priority Date Filing Date
EP19724411.4A Pending EP3969230A1 (fr) 2019-05-11 2019-05-11 Intelligence artificielle dans la fabrication discrète

Country Status (2)

Country Link
EP (1) EP3969230A1 (fr)
WO (1) WO2020228932A1 (fr)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12443173B2 (en) * 2021-10-12 2025-10-14 Royal Engineered Composites, Inc. Systems and methods for composite fabrication with AI quality control modules
CN115018162B (zh) * 2022-06-09 2024-06-04 华中科技大学 一种工业精加工过程加工质量实时预测方法和系统
CN115328062B (zh) * 2022-08-31 2023-03-28 济南永信新材料科技有限公司 水刺布生产线智能控制系统
DE102023132049A1 (de) * 2023-11-17 2025-05-22 TRUMPF Werkzeugmaschinen SE + Co. KG Verfahren zum Nachregeln eines Fertigungsprozesses
EP4715501A1 (fr) * 2024-09-18 2026-03-25 Siemens Aktiengesellschaft Procédé et système de commande du fonctionnement d'une machine à commande numérique par calculateur pour l'usinage d'une pièce
CN119057859B (zh) * 2024-11-05 2025-02-14 江苏蓝米节能科技有限公司 一种多点协同优化的保温板切割方法及装置
CN121069890A (zh) * 2025-08-29 2025-12-05 浙江威电精密机械有限公司 一种慢走丝线切割加工参数智能匹配方法及系统

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE1274217B (de) 1961-09-05 1968-08-01 Gen Electric Impulsfolgefrequenzwandler zur Vorgabe von Geschwindigkeitskomponenten bei einer digitalen Lageregelung
JP2019020959A (ja) * 2017-07-14 2019-02-07 ファナック株式会社 制御装置及び学習装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
DAHBI SAMYA ET AL: "Modeling of cutting performances in turning process using artificial neural networks", INTERNATIONAL JOURNAL OF ENGINEERING BUSINESS MANAGEMENT, vol. 9, 1 January 2017 (2017-01-01), XP093306760, ISSN: 1847-9790, Retrieved from the Internet <URL:https://journals.sagepub.com/doi/pdf/10.1177/1847979017718988> [retrieved on 20250820], DOI: 10.1177/1847979017718988 *

Also Published As

Publication number Publication date
WO2020228932A1 (fr) 2020-11-19

Similar Documents

Publication Publication Date Title
WO2020228932A1 (fr) Intelligence artificielle dans la fabrication discrète
JP6832327B2 (ja) 生産プロセス中に異常なワークピースを自動検出するためのデータ駆動方法
JP6940542B2 (ja) 把持力調整装置及び把持力調整システム
JP6898371B2 (ja) 加工条件調整装置及び加工条件調整システム
US11267059B2 (en) Control device of wire electric discharge machine and machine learning device
Vishnu et al. A data-driven digital twin of CNC machining processes for predicting surface roughness
US20250187125A1 (en) Method and Manufacturing Installation for Producing a Plurality of Workpieces
EP4566746A1 (fr) Procédé et système de détermination et de surveillance de paramètres de processus de fabrication additive automatisé
Haber et al. Intelligent process supervision for predicting tool wear in machining processes
US20220011727A1 (en) Control device for controlling a manufacturing plant as well as a manufacturing plant and method
JP7053518B2 (ja) 切削液量調整装置及び切削液量調整システム
JP6781242B2 (ja) 制御装置、機械学習装置及びシステム
CN110174871B (zh) 控制装置、机器学习装置以及系统
CN119549919B (zh) 用于控制器生产的数智化焊接方法
Martínez-Arellano et al. A data analytics model for improving process control in flexible manufacturing cells
KR20210100399A (ko) 인공 지능을 이용한 가공품질 예측 시스템 및 방법
US11579000B2 (en) Measurement operation parameter adjustment apparatus, machine learning device, and system
CN119057211A (zh) 一种铝材冲压机的视觉检测标记加工一体系统
Dimla Development of an innovative tool wear monitoring system for zero-defect manufacturing
EP4120955B1 (fr) Système d&#39;usinage dentaire pour générer des paramètres de processus d&#39;usinage
Djurdjanovic et al. Process and operations control in modern manufacturing
Reuter et al. Adaptive inspection planning using a digital twin for quality assurance
Basova et al. Maintenance of Operable Condition of a Flexible Production System Through the Development and Implementation of a Method for Cutting Tools and Workpieces Operational Control
Chacko Sustainable practices in manufacturing: harnessing deep learning techniques
Avramova et al. ADAPTIVE CONTROL SYSTEMS OF MILLING PROCESS BY CHANGING THE CUTTING PARAMETERS: A REVIEW.

Legal Events

Date Code Title Description
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: 20211208

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: 20230828

RAP3 Party data changed (applicant data changed or rights of an application transferred)

Owner name: BIG DATA IN MANUFACTURING GMBH