Remote industrial monitoring and analytics using a cloud infrastructure

• US 9,253,054 B2
• Filed: 04/16/2013
• Issued: 02/02/2016
• Est. Priority Date: 08/09/2012
• Status: Active Grant

• Current Assignee: Rockwell Automation Technologies Incorporated (Rockwell Automation, Inc.)
• Original Assignee: Rockwell Automation Technologies Incorporated (Rockwell Automation, Inc.)
• Inventors: Maturana, Francisco, Asenjo, Juan L.
• Primary Examiner(s): ZHANG, SHIRLEY X
• Application Number:
  US13/864,011
• Publication Number:
  US 20140047107A1
• Time in Patent Office: 1,022 Days
• Field of Search: 709/224, 709/217
• US Class Current: 1/1
• CPC Class Codes: G05B 15/02 electric
• CPC Class Codes: G05B 19/056 Programming the PLC
• CPC Class Codes: G05B 2219/13 Plc programming
• CPC Class Codes: G05B 2223/06 Remote monitoring
• CPC Class Codes: G05B 23/0264 Control of logging system, e.g. decision on which data to store; time-stamping measurements
• CPC Class Codes: H04L 43/04 Processing captured monitoring data, e.g. for logfile generation
• CPC Class Codes: H04L 67/125 involving control of end-device applications over a network

Abstract

A cloud-based infrastructure facilitates gathering, transmitting, and remote storage of control and automation data using an agent-based communication channel. The infrastructure collects the industrial data from an industrial enterprise and intelligently sorts and organizes the acquired data based on selected criteria. Message queues can be configured on the cloud platform to segregate the industrial data according to priority, data type, or other criteria. Behavior assemblies stored in customer-specific manifests on the cloud platform define customer-specific preferences for processing data stored in the respective message queues. An agent-based analytics framework in the cloud platform performs desired analytics on the data using distributed parallel processing.

Claims

1. A system for cloud-based analysis of industrial data, comprising:

a memory that stores computer-executable components; and

a processor, operatively coupled to the memory, that executes the computer-executable components, the computer-executable components comprising;

a receiving component configured to receive, at a cloud platform, industrial data from a cloud agent device that resides at an industrial enterprise and collects the industrial data from one or more industrial devices;

a cloud storage component configured to store the industrial data on the cloud platform; and

an analytics framework configured to perform an analysis on the industrial data based on an analysis application executed on the cloud platform, and to generate an output based on a result of the analysis,

wherein the analytics framework is configured to assign a first processing task associated with the analysis to at least one virtual server that executes on the cloud platform and to assign a second processing task associated with the analysis to the cloud agent device.

2. The system of claim 1, wherein the analytics framework comprises a set of virtual servers, including the at least one virtual server, residing on the cloud platform, wherein the set of virtual servers are configured to execute the analysis application.

3. The system of claim 2, wherein the analytics framework is further configured to distribute processing tasks defined by the analysis application across the set of virtual servers.

4. The system of claim 2, wherein the set of virtual servers execute a plurality of agents that facilitate execution of the analysis application to perform the analysis.

5. The system of claim 4, wherein the plurality of agents are configured to communicate with the cloud agent device residing at the industrial enterprise to initiate localized analytics processing by the cloud agent device, and to receive a result of the localized analytics from the cloud agent device.

6. The system of claim 1, wherein the analysis determines whether at least a subset of the industrial data meets a defined alarm criteria, and the output comprises an alarm output.

7. The system of claim 1, wherein the analysis application comprises a risk assessment application configured to generate a risk profile for an industrial system based on the analysis.

8. The system of claim 1, wherein the analysis application comprises a predictive analysis application configured to determine, based on the analysis, a probability of a future occurrence of at least one of a machine downtime event, a machine failure, an inventory shortage, a material shortage, or a failure to fulfill a work order.

9. The system of claim 1, wherein the analysis application is configured to identify, based on the analysis, a dependency between a first subset of the industrial data and a second subset of the industrial data.

10. The system of claim 1, wherein the industrial data comprises a first set of data associated with a first industrial enterprise and a second set of data associated with a second industrial enterprise, and the analysis application is configured to generate recommendation data for the first industrial enterprise based on a comparison of the first set of data and the second set of data, wherein the recommendation data defines at least one of a recommended device configuration, a recommended modification to an industrial process, or a recommended modification to a production schedule.

11. A method for processing industrial data, comprising:

receiving, by a system executing on a cloud platform and comprising at least one processor, industrial data from a cloud agent device that collects the industrial data from one or more industrial devices, wherein the cloud agent device resides at a plant location;

storing the industrial data on cloud-based storage;

executing, on the cloud platform, an analysis application that performs an analysis on the industrial data;

assigning a first processing task associated with the analysis to one or more virtual servers executing on the cloud platform;

assigning a second processing task associated with the analysis to the cloud agent device; and

generating output data based on a first result of the first processing task received from the one or more virtual servers and a second result of the second processing task received from the cloud agent device.

12. The method of claim 11, wherein the executing comprises executing the analysis application on a plurality of virtual servers, including the one or more virtual servers, deployed in the cloud platform.

13. The method of claim 12, wherein the executing comprises:

dividing an executable function defined by the analysis application into multiple executable fragments; and

distributing the multiple executable fragments across the plurality of virtual servers for execution.

14. The method of claim 11, further comprising sending the output data to a client device via the cloud platform.

15. The method of claim 11, further comprising:

identifying, based on the analysis, whether a subset of the industrial data satisfies a defined alarm criterion,

wherein the generating the output data comprises generating an alarm indication in response to the identifying.

16. The method of claim 11, wherein the generating comprises generating a risk profile for an industrial system based on the result of the analysis.

17. The method of claim 11, wherein the generating comprises generating predictive output data that identifies, based on the first result and the second result, a predicted occurrence of at least one of a machine downtime event, a machine failure, an inventory shortage, a material shortage, or a failure to fulfill a work order.

18. The method of claim 11, further comprising identifying, based on the first result and the second result, a dependency between a first subset of the industrial data and a second subset of the industrial data.

19. A non-transitory computer-readable medium having stored thereon computer-executable instructions that, in response to execution, cause a computing system to perform operations, the operations comprising:

receiving industrial data from a cloud agent device residing at an industrial enterprise, wherein the cloud agent device collects the industrial data from one or more industrial devices;

storing the industrial data on a cloud platform;

performing an analysis on the industrial data in accordance with an analysis application, wherein the performing the analysis comprises;

dividing an executable function defined by the analysis application into multiple executable fragments, and

distributing the multiple executable fragments across at least one virtual server executing on the cloud platform and the cloud agent device for execution; and

generating output data based on a result of the analysis.

20. The computer-readable medium of claim 19, further comprising identifying, based on the analysis, whether a subset of the industrial data satisfies a defined alarm criterion, wherein the generating the output data comprises generating an alarm indication in response to the identifying.