公开(公告)号：US20230102717A1

公开(公告)日：2023-03-30

申请号：US17484031

申请日：2021-09-24

Applicant: Rockwell Automation Technologies, Inc.

Inventor： Jordan C. Reynolds ,  John J. Hagerbaumer ,  Troy W. Mahr ,  Thomas K. Jacobsen ,  Giancarlo Scaturchio

IPC: G05B19/418 ,  G05B19/05 ,  G05B23/02 ,  G06N20/00

Abstract: Various embodiments of the present technology generally relate to solutions for integrating machine learning models into industrial automation environments. More specifically, embodiments of the present technology include systems and methods for implementing machine learning models within industrial control code to improve performance, increase productivity, and add capability to existing control programs. In an embodiment, a system comprises an interface component configured to display a graphical representation of a machine learning asset in an industrial automation environment, wherein the graphical representation includes a visual indicator representative of an output from the machine learning asset. The interface component is further configured to adjust the visual indicator based on the output from the machine learning asset. In addition, a process control component is configured to control an industrial process in the industrial automation environment based at least in part on the output from the machine learning asset.

公开(公告)号：US20230100475A1

公开(公告)日：2023-03-30

申请号：US17484900

申请日：2021-09-24

Applicant: ROCKWELL AUTOMATION TECHNOLOGIES, INC.

Inventor： Scott D. Braun ,  Todd A. Wiese

IPC: G06F3/06 ,  H04L12/66 ,  H04L12/10

Abstract: A system includes drives that are communicatively coupled to a gateway communication device via single pair Ethernet (SPE) conductors. The gateway communication device may operate as router or a scanner to facilitate communication between the drives and components of an industrial automation system that are accessible via an Ethernet network.

公开(公告)号：US20230098504A1

公开(公告)日：2023-03-30

申请号：US17449479

申请日：2021-09-30

Applicant: Rockwell Automation Technologies, Inc.

Inventor： Roberto S. Marques ,  Yutao Wang ,  William H. Martin ,  Chirag L. Malkan ,  Mason Khan ,  Steven T. Haensgen

IPC: G05B19/418 ,  H04L12/10

Abstract: A multidrop system configured to be installed within a motor control center (MCC) of an industrial automation system includes a trunkline. The trunkline includes multiple multidrop make and break devices connected through a trunkline cable. Each of the multidrop make and break device includes a first network component, and a second network component. The first network component is configured to form a first subnet over the trunkline. The second network component is configured to couple a MCC withdrawable unit and form a second subnet over a branchline that connects one or more nodes within the MCC withdrawable unit. The multidrop make and break device is configured to couple the MCC withdrawable unit to, and decouple the MCC withdrawable unit from, the second network component without disrupting the first subnet.

公开(公告)号：US20230097885A1

公开(公告)日：2023-03-30

申请号：US17484461

申请日：2021-09-24

Applicant: Rockwell Automation Technologies, Inc.

Inventor： Jordan C. Reynolds ,  John J. Hagerbaumer ,  Troy W. Mahr ,  Thomas K. Jacobsen ,  Giancarlo Scaturchio

IPC: G05B13/04 ,  G05B13/02

Abstract: Various embodiments of the present technology generally relate to solutions for integrating machine learning models into industrial automation environments. More specifically, embodiments of the present technology include systems and methods for implementing machine learning models within industrial control code to improve performance, increase productivity, and add capability to existing control programs. In an embodiment, a system comprises: a storage component configured to maintain a set of model control schemes for controlling an industrial process, a control component configured to control the industrial process with a control program running a model control scheme, wherein the model control scheme is configured to optimize a first parameter of the industrial process, and a model management component configured to change the model control scheme to optimize a second parameter of the industrial process that is distinct from the first parameter.

公开(公告)号：US20230097533A1

公开(公告)日：2023-03-30

申请号：US17484691

申请日：2021-09-24

Applicant: Rockwell Automation Technologies, Inc.

Inventor： Jordan C. Reynolds ,  John J. Hagerbaumer ,  Troy W. Mahr ,  Jeffrey S. Sperling ,  Thomas K. Jacobsen ,  Giancarlo Scaturchio

IPC: G05B19/418 ,  G06N20/20

Abstract: Various embodiments of the present technology generally relate to solutions for integrating machine learning models into industrial automation environments. More specifically, embodiments include systems and methods for implementing machine learning models within industrial control code to improve performance, increase productivity, and add capability to existing programs. In an embodiment, a system comprises: a control component configured to run a closed-loop industrial process comprises a first machine learning model; a measurement component configured to measure a gap between outcome data predicted by the first machine learning model and actual outcome data; a determination component configured to determine, based on the gap, that the first machine learning model has degraded; and a management component configured to replace the first machine learning model with a second machine learning model, wherein the second machine learning model is trained based at least in part on the actual outcome data.

公开(公告)号：US20230097452A1

公开(公告)日：2023-03-30

申请号：US17449598

申请日：2021-09-30

Applicant: Rockwell Automation Technologies, Inc.

Inventor： Julie Nguyen ,  Stephen A. Wenner ,  Eric Eilberg ,  Jessica E. Forguites ,  Mark G. Devonshire

IPC: H04L1/22 ,  H04L61/2517 ,  H04L41/12

Abstract: A method for generating a topology view of an industrial parallel redundancy protocol (PRP) network includes: detecting, by one or more processors, a plurality of nodes on the PRP network; determining, by the one or more processors, a first set of the plurality of nodes that connects to a first local area network (LAN); determining, by the one or more processors, a second set of the plurality of nodes that connects to a second LAN; determining, by the one or more processors, connections between the plurality of nodes; and generating, by the one or more processors, the topology view of the PRP network comprising a topology view of the first LAN and the second LAN according to the determined connections.

公开(公告)号：US20230091778A1

公开(公告)日：2023-03-23

申请号：US17482145

申请日：2021-09-22

Applicant: Rockwell Automation Technologies, Inc.

Inventor： Thong T. Nguyen ,  Paul D. Schmirler ,  Timothy T. Duffy ,  Kristopher J. Holley ,  Susan J. Lovas

IPC: G06T11/00 ,  G06N5/04 ,  G06N5/02 ,  G06F3/01

Abstract: A tangible, non-transitory, computer-readable medium includes instructions that, when executed by processing circuitry, are configured to cause the processing circuitry to receive sensory datasets associated with an industrial automation system, determine context information based on a sensory dataset and representative of an environmental condition, predict an intent of a user to complete a task associated with the industrial automation system based on the sensory datasets and the context information, present first output representative data via an extended reality device based on the intent and a setting, the setting including a data presentation format for presenting the sensory datasets, receive inputs indicative of changes to the data presentation format, present second output representative data via the extended reality device in response to receiving the inputs, and update the setting based on the inputs and historical data indicative of users changing the data presentation format of the first output representative data.

公开(公告)号：US20230089251A1

公开(公告)日：2023-03-23

申请号：US17482153

申请日：2021-09-22

Applicant: Rockwell Automation Technologies, Inc.

Inventor： Thong T. Nguyen ,  Paul D. Schmirler ,  Timothy T. Duffy ,  Kristopher J. Holley ,  Susan J. Lovas

IPC: G06K9/00 ,  G05B19/048 ,  G06T19/00

Abstract: A non-transitory computer-readable medium includes instructions that, when executed by processing circuitry, are configured to cause the processing circuitry to receive, from first sensors, first sensory datasets associated with an industrial automation system, receive, from second sensors, second sensory datasets associated with a machine configured to perform mechanical operations, determine a position of the machine relative to the industrial automation system based on the first sensory datasets and the second sensory datasets, determine output representative data associated with the industrial automation system based on the first sensory datasets and the second sensory datasets and in accordance with the position of the machine relative to the industrial automation system, instruct an extended reality device to present the output representative data, determine movement of components of the machine, and instruct the extended reality device to present feedback based on the movement of the components.

公开(公告)号：US11609137B2

公开(公告)日：2023-03-21

申请号：US16834057

申请日：2020-03-30

Applicant: Rockwell Automation Technologies, Inc.

Inventor： Aderiano M. da Silva ,  Michael Cromheecke ,  Robert Miklosovic

IPC: G01L5/26 ,  G01P3/44 ,  G01R19/00

Abstract: For estimating motor torque and velocity, a method estimates a velocity profile for a motor based on line-to-line voltages and phase currents for the motor. The velocity profile is estimated without a position input and a velocity input. The method further estimates a torque profile for the motor based on the line-to-line voltages, the phase currents, and a time interval of the velocity profile of motor velocities greater than a velocity threshold, and wherein the motor is operating over the time interval.

公开(公告)号：US20230082099A1

公开(公告)日：2023-03-16

申请号：US17471967

申请日：2021-09-10

Applicant: Rockwell Automation Technologies, Inc.

Inventor： Robert Schmidt ,  Thong Nguyen ,  Paul Schmirler ,  Jingbo Liu

IPC: G05B19/418

Abstract: Various embodiments of the present technology relate to digital twins of devices and assemblies. More specifically, some embodiments relate to the orchestration of digital twin models for representing industrial systems based on characteristics of digital twins. In an embodiment, a method of operating an orchestration engine in an industrial automation environment comprises identifying a targeted outcome for modeling the industrial automation environment, configuring a digital twin environment corresponding to the industrial automation environment based at least on the targeted outcome, and executing a process associated with the industrial automation environment using the digital twin environment.