Scalable analytics architecture for automation control systems

Patent metadata

Field	Value
Publication number	US-10509396-B2
Application number	US-201715609323-A
Country	US
Kind code	B2
Filing date	May 31, 2017
Priority date	Jun 9, 2016
Publication date	Dec 17, 2019
Grant date	Dec 17, 2019

Abstract

A layered industrial analytics architecture enables the flow of information from intelligent assets into tools and engines that perform analytics and enable decision-making in substantially real-time. The analytics architecture comprises analytic nodes that are distributed across multiple layers of an industrial enterprise, and includes system features that optimize movement of data across this layered architecture. Each analytic node includes base architectural constructs that host various analytic, data acquisition, and storage elements. These base constructs can operate autonomously, or in conjunction with other instances of base constructs or other elements of the control system. The system design uses a multi-platform compatible implementation that allows the base elements to be deployed on various different computing platforms.

First claim

What is claimed is:

1. A system for performing scalable analytics on industrial data, comprising:
analytic node devices distributed across multiple levels of an industrial enterprise, wherein the analytic node devices comprise at least a first set of analytic node devices deployed at a first level of the industrial enterprise and a second set of analytic node devices deployed at a second level of the industrial enterprise, and wherein a first analytic node device of the analytic node devices comprises:
a memory that stores executable components; and
a processor, operatively coupled to the memory, that executes the executable components, the executable components comprising
an analytic component configured to perform one or more first analytic operations on a first set of industrial data collected from one or more industrial devices to yield first result data;
a presentation framework component configured to send the first result data to a client device; and
an application framework component configured to send at least a subset of the first result data to a second analytic node device of the analytic node devices in response to a determination that the subset of the first result data satisfies a criterion, defined by the analytic component, indicative of a relevance of the subset of the first result data to an industrial operation being executed by industrial devices being monitored by the second analytic node device,

wherein
the application framework component is further configured to receive at least one of a second set of industrial data or second result data from the second analytic node device,
the analytic component is further configured to perform one or more second analytic operations on the second set of industrial data or the second result data received from the second analytic node device, and
the application framework component is further configured to allow modular addition and modular removal of multiple analytic components that define respective multiple different analytic operations to be performed on the first set of industrial data.

2. The system of claim 1 , wherein the first level or the second level comprise at least one of a device level, a machine level, a system level, a plant level, or an enterprise level.

3. The system of claim 1 , wherein the presentation framework is configured to send the first result data to at least one of a thin client executing on the client device, a human-machine interface device, or an industrial control program development application.

4. The system of claim 1 , wherein the analytic component is configured to retrieve extrinsic data from a web-based data source, and to correlate industrial data received from multiple other analytic node devices with the extrinsic data to yield the first result data.

5. The system of claim 4 , wherein the extrinsic data comprises at least one of weather data, financial market data, production data, manufacturer product data, power grid data, commercial buying pattern data, or medical record data.

6. The system of claim 1 , wherein the criterion further indicates a relevance of the subset of the first result data to an analytic operation being performed by the second analytic node device.

7. The system of claim 1 , wherein an analytic node device of the analytic node devices is configured to execute on at least one of an industrial controller, a motor drive, an analytics card, an I/O module of an industrial controller, a cloud-based analytics system, a field gateway device, or an analytic computer.

8. The system of claim 1 , wherein the first analytic node device and the second analytic node device are configured to exchange and process the first result data and the second result data in connection with a collaborative analytics operation.

9. The system of claim 1 , wherein
the analytic component is configured to send instruction data to at least one of the one or more industrial devices based on at least one of the first result data or the second result data, and
the instruction data is configured to alter an industrial control operation executed by the one or more industrial devices.

10. The system of claim 1 , wherein the analytic node device is configured to add contextual information to the first result data to yield contextualized data, the contextual information comprising at least one of a time at which the first set of industrial data was generated, a quality indicator, an identity of a plant or a production area within a plant from which the first set of industrial data was received, a machine or process state at the time the first set of industrial data was generated, or personnel identifiers that identify plant employees on shift at the time the first set of industrial data was generated.

11. A method, comprising:
deploying analytic node devices across multiple levels of an industrial enterprise, wherein the deploying comprises deploying at least a first set of analytic node devices at a first level of the industrial enterprise and deploying a second set of analytic node devices at a second level of the industrial enterprise;
performing, by an analytic component of a first analytic node device of the analytic node devices, one or more first analytic operations on first industrial data collected from one or more industrial devices to yield first result data;
in response to determining that the first result data satisfies a notification criterion, sending, by a presentation framework component of the first analytic node device, the first result data to a client device;
in response to determining that a subset of the first result data satisfies a defined criterion indicating a relevance of the subset of the first result data to an industrial operation being executed by industrial devices being monitored by the second analytic node device, sending, by an application framework component of the first analytic node device, the subset of the first result data to a second analytic node device of the analytic node devices;
receiving, by the application framework component of the first analytic node device, at least one of second industrial data or second result data from the second analytic node; and
performing, by the analytic component or another analytic component of the first analytic node device, one or more second analytic operations on the second industrial data or the second result data received from the second analytic node device,
wherein the application framework component is configured to allow modular addition and modular removal of multiple analytic components that define respective multiple different analytic operations to be performed on the first industrial data.

12. The method of claim 11 , wherein the deploying comprises deploying the analytic nodes at two or more of a device level of the industrial enterprise, a machine level of the industrial enterprise, a system level of the industrial enterprise, a plant level of the industrial enterprise, or an enterprise level of the industrial enterprise.

13. The method of claim 11 , wherein the sending the first result data to a client device comprises sending the first result to at least one of a thin client executing on the client device, a human-machine interface device, or an industrial control program development application.

14. The method of claim 11 , further comprising correlating, by the first analytic node device, industrial data received from multiple other analytic node devices with extrinsic data to yield the first result data.

15. The method of claim 14 , wherein the correlating comprises correlating, with the industrial data, at least one of w

Assignees

• Rockwell Automation Tech Inc

Inventors

• Sandler Scott N
• Dyck John
• Pantaleano Michael J
• Hill Edward Alan
• Cahalane Ryan
• Burnham Nancy L
• Ptacek Petr
• Liberman Eugene
• Comeau David W
• Wise Jonathan
• Keller Michael R

Classifications

• G05B19/418 Primary

  Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] · CPC title

• G05B2219/31368

  MAP manufacturing automation protocol · CPC title

• G05B2219/31151

  Lan local area network · CPC title

• G05B19/41835 Primary

  characterised by program execution · CPC title

• Y02P90/86

  Cross-Sectional Technologies · mapped topic