EP4136590A1 - Procédé d'entraînement hybride pour algorithmes d'auto-apprentissage - Google Patents

Procédé d'entraînement hybride pour algorithmes d'auto-apprentissage

Info

Publication number
EP4136590A1
EP4136590A1 EP21713592.0A EP21713592A EP4136590A1 EP 4136590 A1 EP4136590 A1 EP 4136590A1 EP 21713592 A EP21713592 A EP 21713592A EP 4136590 A1 EP4136590 A1 EP 4136590A1
Authority
EP
European Patent Office
Prior art keywords
values
training
algorithm
self
physical variables
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
EP21713592.0A
Other languages
German (de)
English (en)
Inventor
Christian RIESS
Fabio DA COSTA FERREIRA
Daniel Wolf
Dietmar Tilch
Tobias Ehlgen
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.)
ZF Friedrichshafen AG
Original Assignee
ZF Friedrichshafen 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 ZF Friedrichshafen AG filed Critical ZF Friedrichshafen AG
Publication of EP4136590A1 publication Critical patent/EP4136590A1/fr
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/0895—Weakly supervised learning, e.g. semi-supervised or self-supervised learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning

Definitions

  • the invention relates to a method according to the preamble of claim 1.
  • the invention is based on the object of improving the training of self-learning algorithms. This object is achieved by a method according to claim 1. Preferred developments are contained in the subclaims and result from the following description.
  • a self-learning algorithm is an algorithm that belongs to the generic term of machine learning. It is based on a model that is trained by entering training data.
  • the model can be a neural network or a statistical model. Training a model refers to the adaptation of the model to training data.
  • the inventive method is used to train a self-learning algorithm.
  • the algorithm is designed, depending on one or more values - output values - one or more physical variables of a technical device, one or more values - dependent values - one or more physical variables of the technical Device to forecast.
  • a physical quantity is a property of a process or state that can be quantitatively determined on an object in physics - here: the device.
  • a physical quantity is quantitatively determined by the value of the quantity.
  • the technical device is preferably a transmission.
  • one or more values of one or more physical quantities of a plain bearing of the transmission can be predicted.
  • the dependent values are forecast by calculation.
  • the algorithm is thus designed to computationally determine one or more values of one or more physical variables of the device as a function of one or more values of one or more physical variables of the technical device.
  • the dependency of the values is a functional dependency with the output values as functional parameters and the dependent values as functional values.
  • the arithmetic determination of the dependent values is equivalent to a calculation of the functional dependency.
  • the algorithm is first subjected to basic training. This is to be understood as a training of the algorithm on values of physical quantities that were obtained by simulating at least part of the device. This implies that a simulation of the at least one part of the device is carried out.
  • the simulation preferably precedes the basic training.
  • the simulation determines initial values and dependent values. These serve the algorithm as training data. Preferably, only values obtained by simulation are used for the basic training.
  • the basic training is followed by advanced training.
  • the advanced training is to be understood as training the algorithm on measured values of the physical quantities. This implies that the values are measured on the device.
  • the advanced training is preferably carried out exclusively with measured values.
  • the algorithm is trained on measured output values and the values that are also measured and dependent on them. The measurements are preferably carried out before the advanced training.
  • the basic training is done through simulation, it is dependent on generalizing model assumptions that affect the accuracy of the predicted values. This deficiency is remedied by the subsequent build-up training.
  • the advanced training is based on measured values of the physical variables, the self-learning algorithm is calibrated to a specific physical instance of the device. A database consisting of real field data is only required for the advanced training. The training data of the basic training can be obtained arithmetically in any amount. The invention thus makes it possible to improve the accuracy of a self-learning algorithm without increasing the size of the database.
  • the advanced training is carried out after the basic training has been completed. This means that the basic training is completed at a point in time at which the advanced training is started.
  • the method according to the invention is preferably used in a method for detecting anomalies in the technical device mentioned above.
  • the output values are determined by measuring.
  • the dependent values are forecast using the algorithm.
  • the dependent values are determined by measuring.
  • Anomalies can be identified by comparing the predicted dependent values and the measured dependent values. It can be assumed that there is no anomaly if the predicted and measured values at least largely agree. If there are major deviations, this is due to an anomaly, such as damage.
  • damage to plain bearings can be detected in this way. Damage in plain bearings leads to an increase in temperature.
  • the temperature of the plain bearing is therefore preferably measured and forecast.
  • the measured and forecast values are compared with one another. If the values deviate significantly from one another, it can be assumed that the plain bearing is damaged.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Biomedical Technology (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

L'invention concerne un procédé d'entraînement d'un algorithme d'auto-apprentissage ; l'algorithme étant conçu pour prédire une ou plusieurs valeurs d'une ou de plusieurs variables physiques du dispositif en fonction d'une ou de plusieurs valeurs d'une ou de plusieurs variables physiques d'un dispositif technique ; l'algorithme étant soumis à un apprentissage de base avec des valeurs des variables physiques obtenues par simulation d'au moins une partie du dispositif. L'algorithme subit ensuite un apprentissage d'accumulation avec des valeurs mesurées des variables physiques.
EP21713592.0A 2020-04-15 2021-03-16 Procédé d'entraînement hybride pour algorithmes d'auto-apprentissage Pending EP4136590A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102020204715.4A DE102020204715A1 (de) 2020-04-15 2020-04-15 Hybrides Trainingsverfahren für selbstlernende Algorithmen
PCT/EP2021/056648 WO2021209209A1 (fr) 2020-04-15 2021-03-16 Procédé d'entraînement hybride pour algorithmes d'auto-apprentissage

Publications (1)

Publication Number Publication Date
EP4136590A1 true EP4136590A1 (fr) 2023-02-22

Family

ID=75143598

Family Applications (1)

Application Number Title Priority Date Filing Date
EP21713592.0A Pending EP4136590A1 (fr) 2020-04-15 2021-03-16 Procédé d'entraînement hybride pour algorithmes d'auto-apprentissage

Country Status (4)

Country Link
US (1) US20230214660A1 (fr)
EP (1) EP4136590A1 (fr)
DE (1) DE102020204715A1 (fr)
WO (1) WO2021209209A1 (fr)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102022205152A1 (de) 2022-05-24 2023-11-30 Zf Friedrichshafen Ag Selbstlernender Algorithmus zur Prognose des Einstechens in einen Haufen
DE102023200020A1 (de) 2023-01-03 2024-07-04 Robert Bosch Gesellschaft mit beschränkter Haftung Verfahren zum Trainieren eines Algorithmus des maschinellen Lernens und Verfahren zum Einstellen mindestens eines in einem induktiven Härteverfahren mindestens eines Bauteils einstellbaren Prozessparameters

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200110181A1 (en) * 2018-10-04 2020-04-09 The Boeing Company Detecting fault states of an aircraft

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9811074B1 (en) * 2016-06-21 2017-11-07 TruPhysics GmbH Optimization of robot control programs in physics-based simulated environment
EP3628101B8 (fr) * 2017-04-28 2023-07-19 Better Therapeutics, Inc. Procédé et système de gestion d'interventions en matière de style de vie et de santé
US10773382B2 (en) * 2017-09-15 2020-09-15 X Development Llc Machine learning methods and apparatus for robotic manipulation and that utilize multi-task domain adaptation
US11416510B2 (en) * 2019-04-10 2022-08-16 Kpmg Llp Systems and methods for applying lifecycle processes to digital data objects utilizing distributed ledger technology and artificial intelligence
US11176692B2 (en) * 2019-07-01 2021-11-16 Sas Institute Inc. Real-time concealed object tracking
US11763160B2 (en) * 2020-01-16 2023-09-19 Avanseus Holdings Pte. Ltd. Machine learning method and system for solving a prediction problem
US11307586B2 (en) * 2020-02-17 2022-04-19 Toyota Motor Engineering & Manufacturing North America, Inc. Offroad travel assistance system for a vehicle
US12475280B2 (en) * 2020-03-23 2025-11-18 Ansys, Inc. Generative networks for physics based simulations

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200110181A1 (en) * 2018-10-04 2020-04-09 The Boeing Company Detecting fault states of an aircraft

Also Published As

Publication number Publication date
US20230214660A1 (en) 2023-07-06
DE102020204715A1 (de) 2021-10-21
WO2021209209A1 (fr) 2021-10-21

Similar Documents

Publication Publication Date Title
DE102017108169B4 (de) Produktionssystem, das einen Bestimmungswert einer Variablen in Bezug auf eine Produktabweichung festlegt
DE102018126434B4 (de) Testvorrichtung und Maschinenlernvorrichtung
AT520554B1 (de) Prüfstand und Verfahren zum Durchführen eines dynamischen Prüflaufs für einen Prüfaufbau
CN104792529A (zh) 基于状态空间模型的滚动轴承寿命预测方法
WO2021209209A1 (fr) Procédé d'entraînement hybride pour algorithmes d'auto-apprentissage
DE602005002818T2 (de) Verfahren zur Überwachung der Betriebsleistungen einer Industrieanlage
DE4338615A1 (de) Verfahren und Vorrichtung zur Führung eines Prozesses in einem geregelten System
CN105095963A (zh) 一种精确诊断与预测风洞设备故障的方法
DE102016117190A1 (de) Verfahren und Vorrichtung zum Überwachen eines Zustands wenigstens einer Windkraftanlage und Computerprogrammprodukt
WO2015082669A1 (fr) Procédé informatisé et système de surveillance et détermination d'état automatiques de sections entières d'une unité de processus
CN106610584A (zh) 一种基于神经网络与专家系统的再制造工序质量控制方法
WO1998015882A1 (fr) Procede et dispositif pour l'identification ou le calcul prealable de parametres d'un processus industriel variant dans le temps
EP3999925A1 (fr) Procédés et dispositifs permettant de déterminer une qualité de produit
CN106845826B (zh) 一种基于PCA-Cpk的冷连轧生产线服役质量状态评估方法
DE102017131241B4 (de) Überwachungsverfahren für eine Windkraftanlage, zugehörige Überwachungsvorrichtung sowie Windkraftanlage mit Überwachungsvorrichtung
WO2013087122A1 (fr) Procédé de génération d'un signal indiquant une oscillation dans un réseau de distribution d'énergie électrique
CN120598371B (zh) 一种发电厂汽轮机风险监控的模块化系统及实现方法
DE102017106919A1 (de) Verfahren zur Bestimmung einer Schädigungsmaßunsicherheit eines Kraftfahrzeugs
CN111367255A (zh) 一种多变量控制系统性能评价测试系统及方法
DE102019207319A1 (de) Lehrdatenerzeugungseinrichtung und Lehrdatenerzeugungsverfahren
CN106096170A (zh) 基于数据驱动的风电机组多变量故障预测方法
DE102021100566A1 (de) Verfahren zur Bereitstellung wenigstens einer Information über eine hydraulische Anlage
CN106503417A (zh) 一种基于状态评价的电力设备故障率计算方法
CN116205044A (zh) 一种复杂航天设备的实时健康分析方法和系统
DE102021206044A1 (de) Überwachung der produktion von werkstoffplatten, insbesondere holzwerkstoffplatten, insbesondere unter verwendung einer selbstorganisierenden karte

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

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: 20220919

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: 20251021