公开(公告)号：US20230126849A1

公开(公告)日：2023-04-27

申请号：US18145984

申请日：2022-12-23

Applicant: CARTESIAM

Inventor： François de Grimaudet de Rochebouët ,  Mohamed Ali Moussa

IPC: G06F17/15 ,  G06F17/17 ,  G06F18/2413

Abstract: A method can be implemented on a microcontroller that includes at least one memory. The microcontroller is configured to receive sets of multivariable data from at least one sensor and the memory is configured to store a predefined number of categories. A category is associated with a mean and a covariance matrix. The method can be used to the detection of anomalies from the sets of multivariable data.

公开(公告)号：US20220245046A1

公开(公告)日：2022-08-04

申请号：US17660548

申请日：2022-04-25

Applicant: Cartesiam

Inventor： Francois De Rochebouet ,  He Huang

IPC: G06F11/32 ,  G06F9/50 ,  G06F11/30 ,  G06K9/62

Abstract: A learning method detects anomalies and is implemented on a microcontroller including at least one memory, the microcontroller being configured to receive data sets coming from at least one sensor, the memory being configured to store a maximum number of categories, a category including at least a signature and an occurrence.

公开(公告)号：US11885849B2

公开(公告)日：2024-01-30

申请号：US17483014

申请日：2021-09-23

Applicant: Cartesiam

Inventor： He Huang ,  Francois De Grimaudet De Rochebouet

IPC: G01R31/34 ,  G06N20/00 ,  G01R19/165

CPC classification number: G01R31/343 ,  G01R19/165 ,  G06N20/00

Abstract: A method can be used for supervising the operation of a machine powered with electric current. The method includes operating the machine in a normal operation mode, repeatedly performing a learning phase for learning the normal operation machine of the machine to create a knowledge base, autonomously switching from the learning phase into a supervision phase when the knowledge base is considered to have been created, and repeatedly performing the supervision phase.

公开(公告)号：US20220011154A1

公开(公告)日：2022-01-13

申请号：US17277126

申请日：2019-09-12

Applicant: CARTESIAM

Inventor： François DE GRIMAUDET DE ROCHEBOUET

IPC: G01H1/00 ,  G06N20/00 ,  G05B23/02 ,  G01M7/02

Abstract: A method for monitoring the operation of a machine that generates vibrations, includes a learning phase in which a knowledge base containing vibrational signatures representative of the operation of the machine is generated, and a monitoring phase in which the vibrations of the machine are compared to the knowledge base so as to detect an anomaly in the machine.

公开(公告)号：US12188812B2

公开(公告)日：2025-01-07

申请号：US17277126

申请日：2019-09-12

Applicant: CARTESIAM

Inventor： François De Grimaudet De Rochebouet

IPC: G01H1/00 ,  G01M7/02 ,  G05B23/02 ,  G06N20/00

Abstract: A method for monitoring the operation of a machine that generates vibrations, includes a learning phase in which a knowledge base containing vibrational signatures representative of the operation of the machine is generated, and a monitoring phase in which the vibrations of the machine are compared to the knowledge base so as to detect an anomaly in the machine.

公开(公告)号：US20220091188A1

公开(公告)日：2022-03-24

申请号：US17483014

申请日：2021-09-23

Applicant: Cartesiam

Inventor： He Huang ,  Francois De Grimaudet De Rochebouet

IPC: G01R31/34 ,  G01R19/165 ,  G06N20/00

Abstract: A method can be used for supervising the operation of a machine powered with electric current. The method includes operating the machine in a normal operation mode, repeatedly performing a learning phase for learning the normal operation machine of the machine to create a knowledge base, autonomously switching from the learning phase into a supervision phase when the knowledge base is considered to have been created, and repeatedly performing the supervision phase.

公开(公告)号：US11868197B2

公开(公告)日：2024-01-09

申请号：US17660548

申请日：2022-04-25

Applicant: Cartesiam

Inventor： Francois De Rochebouet ,  He Huang

IPC: G06F11/00 ,  G06F11/07 ,  G06F9/50 ,  G06F11/30 ,  G06F11/32 ,  G06F18/22

CPC classification number: G06F11/0751 ,  G06F9/5016 ,  G06F11/3013 ,  G06F11/3072 ,  G06F11/3089 ,  G06F11/327 ,  G06F18/22

Abstract: A learning method detects anomalies and is implemented on a microcontroller including at least one memory, the microcontroller being configured to receive data sets coming from at least one sensor, the memory being configured to store a maximum number of categories, a category including at least a signature and an occurrence.

公开(公告)号：US11341016B2

公开(公告)日：2022-05-24

申请号：US16880133

申请日：2020-05-21

Applicant: CARTESIAM

Inventor： François De Rochebouet ,  He Huang

IPC: G06F11/00 ,  G06F11/32 ,  G06F9/50 ,  G06F11/30 ,  G06K9/62

Abstract: A learning method detects anomalies and is implemented on a microcontroller including at least one memory, the microcontroller being configured to receive data sets coming from at least one sensor, the memory being configured to store a maximum number of categories, a category including at least a signature and an occurrence.

公开(公告)号：US20200371890A1

公开(公告)日：2020-11-26

申请号：US16880133

申请日：2020-05-21

Applicant: CARTESIAM

Inventor： François DE ROCHEBOUET ,  He HUANG

IPC: G06F11/32 ,  G06F11/30 ,  G06F9/50 ,  G06K9/62

Abstract: A learning method detects anomalies and is implemented on a microcontroller including at least one memory, the microcontroller being configured to receive data sets coming from at least one sensor, the memory being configured to store a maximum number of categories, a category including at least a signature and an occurrence.