Discrete manufacturing hybrid cloud solution architecture

• US 10,416,660 B2
• Filed: 08/31/2017
• Issued: 09/17/2019
• Est. Priority Date: 08/31/2017
• Status: Active Grant

• Current Assignee: Rockwell Automation Technologies Incorporated (Allen-Bradley Co., Inc.)
• Original Assignee: Rockwell Automation Technologies Incorporated (Allen-Bradley Co., Inc.)
• Inventors: Maturana, Francisco P.
• Primary Examiner(s): Kasenge, Charles R
• Application Number:
  US15/692,213
• Publication Number:
  US 20190064787A1
• Time in Patent Office: 747 Days
• CPC Class Codes: G05B 2223/06 Remote monitoring
• CPC Class Codes: G05B 23/0227 Qualitative history assessment, whereby the type of data acted upon, e.g. waveforms, images or patterns, is not relevant, e.g. rule based assessment; if-then decisions
• CPC Class Codes: G05B 23/0283 Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL] preventive maintenance, i.e. planning maintenance according to the available resources without monitoring the system G06Q10/06
• CPC Class Codes: G05B 23/0294 Optimizing process, e.g. process efficiency, product quality
• CPC Class Codes: G06F 9/5072 Grid computing

Abstract

A hybrid data collection and analysis infrastructure combines edge-level and cloud-level computing to perform high-level monitoring and control of industrial systems and processes. Edge devices located on-premise at one or more plant facilities can collect data from multiple industrial devices on the plant floor and perform local edge-level analytics on the collected data. In addition, the edge devices maintain a communication channel to a cloud platform executing cloud-level data collection and analytic services. As necessary, the edge devices can pass selected sets of data to the cloud platform, where the cloud-level analytic services perform higher level analytics on the industrial data. The hybrid architecture operates in a bi-directional manner, allowing the cloud-level and edge-level analytics to send control instructions to industrial devices based on results of the edge-level and cloud-level analytics.

Claims

1. An edge device, comprising:

a memory that stores executable components;

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

a collection services component configured to collect industrial data from data tags of an industrial device and to generate a compressed data file containing the industrial data, wherein the data tags from which the industrial data is collected are defined by an edge-level data manifest file;

a queue processing component configured to package the compressed data file with header information based on message queuing information maintained in a message queuing data store to yield a compressed data packet and to send the compressed data packet to a cloud analytics system executing on a cloud platform; and

an edge analytics component configured to perform an edge-level analytic procedure on a first subset of the industrial data to yield a first analytic result, wherein the edge-level analytic procedure is defined by an edge-level metrics manifest file,

wherein

the edge analytics component is configured to send a first command to the industrial device based on the first analytic result,

the queue processing component is further configured to receive a second analytic result from the cloud analytics system, wherein the second analytic result is generated based on a cloud-level analytic procedure performed by the cloud analytics system that identifies a pattern in a trend of a second subset of the industrial data indicative of a loss of position accuracy of an actuator, and

the edge analytics component is further configured to send a second command to the industrial device based on the second analytic result.

2. The edge device of claim 1, wherein the pattern is a first pattern, and the edge-level analytic procedure is configured to identify a second pattern in the first subset of the industrial data indicative of an equipment anomaly, and to configure the first command to alter a controlled industrial process in response to identification of the second pattern.

3. The edge device of claim 2, wherein the edge-level analytic procedure is configured to identify, as the equipment anomaly based on the second pattern, a pneumatic air leak.

4. The edge device of claim 2, wherein the edge analytics component is further configured to send notification data to the cloud analytics system in response to identification of the second pattern.

5. The edge device of claim 1, wherein the edge analytics component is configured to generate the second command to alter a controlled industrial process to compensate for the loss of the position accuracy.

6. The edge device of claim 5, wherein the second command is configured to at least one of modify a machine cycle of the controlled industrial process to favor a different actuator or slow an actuation time of the actuator.

7. The edge device of claim 1, wherein the accuracy of actuator is an electro-pneumatic actuator.

8. The edge device of claim 1, wherein the cloud-level analytic procedure performs a comparison of the trend of the second subset of the industrial data with a model of performance degradation of the actuator, and generates the second command based on a result of the comparison.

9. The edge device of claim 1, further comprising a user interface component configured to send a notification of the second analytic result to a client device,

wherein the edge analytics component is configured to send the second command to the industrial device in response to receipt of confirmation input from the client device.

10. A method for processing industrial data, comprising:

collecting, by a system comprising a processor, industrial data from data tags of an industrial device, wherein the data tags from which the industrial data is collected are identified by an edge-level data manifest file;

generating, by the system, a compressed data file containing the industrial data;

adding, by the system, header information to the compressed data file to yield a compressed data packet, wherein the header information is based on message queuing information maintained in a message queuing data store to yield a compressed data packet;

sending, by the system, the compressed data packet to a cloud analytics system executing on a cloud platform;

performing, by the system, an edge-level analytic procedure on a first subset of the industrial data to yield a first analytic result, wherein the edge-level analytic procedure is defined by an edge-level metrics manifest file;

sending, by the system, a first command to the industrial device based on the first analytic result;

receiving, by the system, a second analytic result from the cloud analytics system, wherein the second analytic result is generated based on a cloud-level analytic procedure performed by the cloud analytics system that identifies a pattern in a time-based trend of a second subset of the industrial data, the pattern indicative of a loss of position accuracy of an actuator; and

sending, by the system, a second command to the industrial device based on the second analytic result.

11. The method of claim 10, wherein

the pattern is a first pattern,

the performing of the edge-level analytic procedure comprises identifying a second pattern in the first subset of the industrial data corresponding to an equipment anomaly, and

the sending the first command comprises configuring the first command to alter a controlled industrial process in response to identification of the second pattern.

12. The method of claim 11, wherein the identifying of the second pattern comprises identifying, as the equipment anomaly, a pneumatic air leak.

13. The method of claim 11, further comprising sending a notification to the cloud analytic system in response to the identifying of the second pattern.

14. The method of claim 10, wherein the sending the second command comprises generating the second command to alter a controlled industrial process based on the loss of the position accuracy.

15. The method of claim 10, wherein the actuator is an electro-pneumatic actuator.

16. The method of claim 10, wherein the adding of the header information comprises adding at least a customer identifier associated with the industrial enterprise and priority information specifying a processing priority for the industrial data.

17. The method of claim 10, wherein the sending the second command comprises generating the second command to at least one of modify a machine cycle controlled by the industrial device to favor a different actuator or slow an actuator time of the actuator.

18. A non-transitory computer-readable medium having stored thereon instructions that, in response to execution, cause an edge device comprising a processor to perform operations, the operations comprising:

collecting industrial data from data tags of an industrial device, wherein the data tags from which the industrial data is collected are defined by an edge-level data manifest file;

generating a compressed data file containing the industrial data;

appending header information to the compressed data file to yield a compressed data packet, wherein the header information is based on message queuing information maintained in a message queuing data store to yield a compressed data packet;

sending the compressed data packet to a cloud analytics system executing on a cloud platform;

performing an edge-level analytic procedure on a first subset of the industrial data to yield a first analytic result, wherein the edge-level analytic procedure is defined by an edge-level metrics manifest file;

sending a first control instruction to the industrial device based on the first analytic result;

receiving a second analytic result from the cloud analytics system, wherein the second analytic result is generated based on a cloud-level analytic procedure performed by the cloud analytics system that identifies a pattern in a trend of a second subset of the industrial data, the pattern indicative of a loss of position accuracy of an actuator; and

sending a second control instruction to the industrial device based on the second analytic result.

19. The non-transitory computer-readable medium of claim 18, wherein

the pattern is a first pattern,

the performing the edge-level analytic procedure comprises identifying a second pattern in the first subset of the industrial data corresponding to an equipment anomaly, and

the sending the first control instruction comprises configuring the first command to alter a controlled industrial process in response to identification of the second pattern.

20. The non-transitory computer-readable medium of claim 19, wherein the identifying the second pattern comprises identifying, as the equipment anomaly, a pneumatic air leak.