专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明公开

EP4375768A1 VERFAHREN UND MASCHINENSTEUERUNG ZUM STEUERN EINER MASCHINE 审中-公开
公开(公告)号：EP4375768A1
公开(公告)日：2024-05-29
申请号：EP22209688.5
申请日：2022-11-25
申请人： Siemens Aktiengesellschaft
发明人： Swazinna, Phillip
IPC分类号： G05B13/02
CPC分类号： G05B13/027
摘要： Es wird eine Vielzahl von Trainingsdatensätzen (TD) eingelesen, die jeweils einen Maschinenzustand, eine Steueraktion sowie einen resultierenden Folgezustand spezifizieren. Für einen jeweiligen Maschinenzustand wird aus den Trainingsdatensätzen eine Trainings-Aktionstrajektorie (TAT) abgeleitet, wird mittels eines Steuerungsagenten (POL) eine Aktionstrajektorie (AT) prädiziert und wird eine Abweichung (DA) der prädizierten Aktionstrajektorie (AT) von der Trainings-Aktionstrajektorie (TAT) ermittelt. Die Abweichung (DA) wird dabei über mehrere Trajektorien-Zeitschritte akkumuliert. Der Steuerungsagent wird dann darauf trainiert, die ermittelten Abweichungen (DA) zu reduzieren. Darüber hinaus wird ein Performanzbewerter (PEV) bereitgestellt, der für eine Aktionstrajektorie (AT) einen Trajektorien-Performanzwert (RET) ermittelt. Zum Steuern der Maschine (M) wird dann ein aktueller Betriebszustand (BS) der Maschine erfasst, wird mittels des trainierten Steuerungsagenten (POL) eine Vielzahl von vom erfassten Betriebszustand ausgehenden Test-Aktionstrajektorien (TTA) prädiziert, wird für die Test-Aktionstrajektorien jeweils ein Trajektorien-Performanzwert (RET) durch den Performanzbewerter (PEV) ermittelt und wird abhängig von den ermittelten Trajektorien-Performanzwerten (RET) eine performanzoptimierende Aktionstrajektorie (PA) aus den Test-Aktionstrajektorien (TTA) selektiert. Anhand der selektierten Aktionstrajektorie (PA) wird die Maschine gesteuert.

2. 发明授权

EP4191348B1 CONTROL DEVICE, CONTROL SYSTEM, AND CONTROL METHOD FOR WIRE STRAIGHTENER 有权
公开(公告)号：EP4191348B1
公开(公告)日：2024-05-22
申请号：EP22209312.2
申请日：2022-11-24
IPC分类号： G05B13/04 , B21F1/02 , B21C51/00 , G05B13/02
CPC分类号： G05B13/048 , G05B13/0265 , B21F1/02 , B21F1/026 , B21C51/00

3. 发明公开

EP4369115A1 METHOD AND SYSTEM FOR PHYSICS AWARE CONTROL OF HVAC EQUIPMENT 审中-公开
公开(公告)号：EP4369115A1
公开(公告)日：2024-05-15
申请号：EP23206117.6
申请日：2023-10-26
申请人： Tata Consultancy Services Limited
发明人： NAGARATHINAM, SRINARAYANA , CHATI, YASHOVARDHAN SUSHIL , VASAN, ARUNCHANDAR , POONI VENKAT, MALINI
IPC分类号： G05B13/02 , F24F11/64 , G06N3/08
CPC分类号： G05B2219/261420130101 , G06N3/08 , G05B13/027 , F24F11/64
摘要： Use of Physics Informed Neural networks (PINNs) to control building systems is non-trivial, as basic formalism of PINNs is not readily amenable to control problems. Specifically, exogenous inputs (e.g., ambient temperature) and control decisions (e.g., mass flow rates) need to be specified as functional inputs to the neural network, which may not be known a priori. The input feature space could be very high dimensional depending upon the duration (monthly, yearly, etc.) and the (min-max) range of the inputs. The disclosure herein generally relates to Heating, Ventilation, and Air-Conditioning (HVAC) equipment, and, more particularly, to method and system for physics aware control of HVAC equipment. The system generates a neural network model based on a plurality of exogeneous variables from the HVAC. The generated neural network model is then used to generate the one or more control signal recommendations, which are further used to control operation of the HVAC.

4. 发明授权

EP4115009B1 VERFAHREN UND VORRICHTUNG ZUR ÜBERWACHUNG EINER MASCHINENANLAGE ZUR HERSTELLUNG ODER BEHANDLUNG VON SYNTHETISCHEN FASERN 有权
公开(公告)号：EP4115009B1
公开(公告)日：2024-05-01
申请号：EP21709649.4
申请日：2021-03-02
IPC分类号： D01D13/00 , G05B13/02
CPC分类号： D01D13/00 , G05B13/0265 , G07C3/005

5. 发明授权

EP3948437B1 PREDICTIVE CLASSIFICATION OF FUTURE OPERATIONS 有权
公开(公告)号：EP3948437B1
公开(公告)日：2024-04-24
申请号：EP20713391.9
申请日：2020-02-04
IPC分类号： G05B13/02 , G05B13/04 , G05B23/02 , G06N3/04 , G06N3/045 , G06N3/048
CPC分类号： G05B23/024 , G05B23/0283 , G06N3/048 , G06N3/045

6. 发明公开

EP4318341A3 SYSTEM FOR FORECASTING AIRCRAFT ENGINE DETERIORATION USING RECURRENT NEURAL NETWORKS 审中-实审
公开(公告)号：EP4318341A3
公开(公告)日：2024-03-20
申请号：EP23217317.9
申请日：2020-03-23
申请人： RTX Corporation
发明人： NAGARAJA, Sharath B. , GRECO, Matthew R.
IPC分类号： G06T7/00 , F02C9/28 , G05B13/02 , G05B23/02 , G06Q10/00
摘要： A method for forecasting aircraft engine deterioration includes creating a first fused data set (130) corresponding to a first actual aircraft engine (20). The first fused data set (130) includes at least one as manufactured parameter of the actual aircraft engine, expected operating parameters of the first actual aircraft engine, and actual operating parameters of the actual aircraft engine. The actual operating parameters of the actual aircraft engine include internal aircraft sensor data (110), and external flight tracking data (114). The method further includes predicting an expected engine deterioration of the first actual engine based on the expected operating parameters and the actual operating parameters of the first actual aircraft engine by applying the first fused data set to a forecasting model. The forecasting model is a recurrent neural network based algorithm, and the recurrent neural network based algorithm is trained via a plurality of second fused data sets corresponding to actual aircraft engines.

7. 发明公开

EP4336281A1 METHOD FOR VALIDATING OR VERIFYING A TECHNICAL SYSTEM 审中-公开
公开(公告)号：EP4336281A1
公开(公告)日：2024-03-13
申请号：EP22195125.4
申请日：2022-09-12
申请人： Robert Bosch GmbH
发明人： Barsim, Karim Said Mahmoud , Gerwinn, Sebastian , Schiegg, Martin , Reeb, David , Patel, Kanil
IPC分类号： G05B19/042 , G05B17/02 , G05B13/02
摘要： Method for verifying and/or validating whether a technical system (40) fulfills a desired criterion, wherein the technical system (40) emits output signals based on input signals supplied to the technical system (40), wherein the method comprises the steps of:
• Obtaining models ( M 1 , M 2 ,M C ) for a plurality of components ( S 1 ,S 2 ,S C ) comprised by the technical system (40), wherein a connection between the obtained models characterizes which component passes which signal to which other component;
• Obtaining a plurality of validation measurements, wherein a validation measurement comprises a measurement input and a measurement output, wherein the measurement output is obtained from a component ( S 1 , S 2 ,S C ) of the technical system (40) for the measurement input if the measurement input is provided to the component (S 1 ,S 2 ,S C );
• For each component ( S 1 ,S 2 ,S C ), training a machine learning model ( V 1 ,V 2 ,V C ) to predict outputs of the respective component ( S 1 ,S 2 ,S C ) based on inputs of the respective component, wherein at least parts of the validation measurements are used as training dataset and wherein the machine learning model ( V 1 ,V 2 ,V C ) corresponds to the model ( M 1 ,M 2 ,M C ) obtained for the component;
• Obtaining first test outputs ( q M,C ) from a last model ( M C ) based on test inputs (q°), wherein the first test outputs ( q M,C ) are obtained by propagating the test inputs ( q 0 ) through the connection of models;
• Determining, second test outputs ( q V,C ) from the machine learning model ( V C ) corresponding to the last model and based on the test inputs ( q 0 ) of the models ( M 1 ,M 2 ,M C ), wherein the second test outputs ( q V,C ) are obtained by propagating the test inputs ( q 0 ) through a connection of the machine learning models ( V 1 ,V 2 ,V C ), wherein the connection of the machine learning models ( V 1 ,V 2 ,V C ) is according to the connection of the models ( M 1 , M 2 ,M C ) the respective machine learning models ( V 1 ,V 2 ,V C ) correspond to;
• Determine a deviation (d), wherein the deviation (d) characterizes a difference between first test outputs ( q M,C ) determined from the last model ( M C ) and second test outputs ( q V,C ) determined by the machine learning model ( V C ) corresponding to the last model ( M C );
• Verifying and/or validating whether the technical system (40) fulfills the criterion, wherein verifying and/or validating is characterized by determining a fraction of the first test outputs ( q M,C ) that fulfill an offset criterion, wherein the offset criterion is determined by offsetting the criterion by the determined deviation (d).

8. 发明公开

EP4336279A1 METHOD FOR VALIDATING OR VERIFYING A TECHNICAL SYSTEM 审中-公开
公开(公告)号：EP4336279A1
公开(公告)日：2024-03-13
申请号：EP22195191.6
申请日：2022-09-12
申请人： Robert Bosch GmbH
发明人： Patel, Kanil , Reeb, Davi , Gerwinn, Sebastian , Schiegg, Martin , Barsim, Karim Said Mahmoud
IPC分类号： G05B13/02 , G05B13/04
摘要： Method for verifying and/or validating whether a technical system (40) fulfills a desired criterion, wherein the technical system (40) emits output signals based on input signals supplied to the technical system (40), wherein the method comprises the steps of:
a. Obtaining models ( M 1 ,M 2 ,M C ) for a plurality of components ( S 1 ,S 2 ,S C ) comprised by the technical system (40), wherein a connection between the obtained models characterizes which component passes which signal to which other component;
b. Obtaining a plurality of validation measurements, wherein a validation measurement comprises a measurement input and a measurement output ( p 1 , p 2 ,p C -1 , p C ), wherein the measurement output is obtained from a component ( S 1 , S 2 , S C ) of the technical system (40) for the measurement input if the measurement input is provided to the component ( S 1 , S 2 , S C );
c. For each component ( S 1 , S 2 , S C ), training a machine learning model ( V 1 , V 2 , V C ) to predict measurement outputs ( p 1 , p 2 , p C -1 , p C ) of the respective component ( S 1 , S 2 , S C ) based on inputs of the respective component, wherein at least parts of the validation measurements are used as training dataset and wherein the machine learning model ( V 1 , V 2 , V C ) corresponds to the model ( M 1 , M 2 , M C ) obtained for the component;
d. Obtaining first test outputs ( q M,C ) from a last model ( M C ) based on test inputs (q°), wherein the first test outputs ( q M,C ) are obtained by propagating the test inputs (q°) through the connection of models;
e. Determining, second test outputs ( q V,C ) from the machine learning model ( V C ) corresponding to the last model and based on the test inputs ( q 0 ) of the models ( M 1 ,M 2 ,M C ), wherein the second test outputs ( q V,C ) are obtained by propagating the test inputs ( q 0 ) through a connection of the machine learning models ( V 1 ,V 2 ,V C ), wherein the connection of the machine learning models ( V 1 ,V 2 ,V C ) is according to the connection of the models ( M 1 ,M 2 ,M C ) the respective machine learning models ( V 1 ,V 2 ,V C ) correspond to;
f. Determining a discrepancy (d), wherein the discrepancy (d) characterizes a difference between a distribution of first test outputs ( q M,C ) determined from the last model ( M C ) and a distribution of second test outputs ( q V,C ) determined by the machine learning model ( V C ) corresponding to the last model ( M C );
g. Verifying and/or validating whether the technical system (40) fulfills the criterion, wherein verifying and/or validating is characterized by maximizing a probability of a distribution of measurement outputs ( p C ) of a last component ( S C ) of the technical system (40) to not fulfill the criterion with respect to the distribution of measurement outputs ( p C ) and under a constraint stipulating that a discrepancy of the distribution of measurement outputs ( p C ) and the distribution of first test outputs ( q M,C ) may not exceed the discrepancy (d) determined in step f.

9. 发明授权

EP3843257B1 SETTING SUPPORT DEVICE 有权
公开(公告)号：EP3843257B1
公开(公告)日：2024-03-13
申请号：EP19852210.4
申请日：2019-08-07
发明人： FUJIOKA, Takumi , EGI, Mamoru
IPC分类号： G05B13/02 , B25J9/16 , G05B19/404

10. 发明授权

EP4252087B1 BETRIEB EINES MEHRACHSSYSTEMS 有权
公开(公告)号：EP4252087B1
公开(公告)日：2024-02-21
申请号：EP21823253.6
申请日：2021-11-29
发明人： WEISSBACHER, Joachim
IPC分类号： G05B19/414 , G05B13/02 , H02P5/747 , H02P5/69

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式