Adjustment of data collection rate based on anomaly detection

• US 7,657,333 B2
• Filed: 09/27/2007
• Issued: 02/02/2010
• Est. Priority Date: 09/27/2007
• Status: Active Grant

• Current Assignee: Rockwell Automation Technologies Incorporated (Allen-Bradley Co., Inc.)
• Original Assignee: Rockwell Automation Technologies Incorporated (Allen-Bradley Co., Inc.)
• Inventors: Balewski, Mark Joseph, Harris, Kendal R., Gach, Martin George, Hall, Kenwood H., Rischar, Charles Martin, Bradford, Jonathan D., Kretschmann, Robert J., Siorek, Timothy
• Primary Examiner(s): Patel; Ramesh B
• Application Number:
  US11/862,983
• Publication Number:
  US 20090089558A1
• Time in Patent Office: 859 Days
• Field of Search: 700/34, 700/46, 700 51- 53, 700/55, 700 73- 75, 707/10, 709/248, 713/375, 713/400
• US Class Current: 700/51
• CPC Class Codes: G05B 21/02 electric
• CPC Class Codes: Y02P 90/02 Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Abstract

Systems and methods that vary multiple data sampling rates, to collect sets of data with different levels of granularity for an industrial system. The data for such industrial system includes sets of data from the “internal” data stream(s) (e.g., history data collected from an industrial unit) and sets of data from an “external” (e.g., traffic data on network services) data stream(s), based in part on the criticality/importance criteria assigned to each collection stage. Each set of data can be assigned its own unique data collection rate. For example, a higher sample rate can be employed when collecting data from the network during an operation stage that is deemed more critical (e.g., dynamic attribution of predetermined importance factors) than the rest of the operation.

Claims

1. An industrial automation system, comprising:

a coordination component that synchronizes multiple data streams associated with the industrial automation system according to a common timestamp or sequence count generator, wherein each of the multiple data streams has a data sampling rate that defines a rate at which data is collected from the data stream; and

a sample rate adjustment component that varies the data sampling rate of at least one data stream of the multiple data streams based upon at least one of a predetermined criteria or a predicted required sampling rate.

2. The industrial automation system of claim 1, wherein the multiple data streams include at least one internal data stream and at least one external data stream, wherein the at least one internal data stream comprises internal data from one or more industrial devices and the at least one external data stream comprises network traffic.

3. The industrial automation system of claim 1 further comprising a recognition component that identifies one or more trends in the multiple data streams indicative of a relationship between an event and a cause of the event.

4. The industrial automation system of claim 1, wherein the coordination component weaves together data from the internal and external data streams to synchronize the data according to the common timestamp or sequence count generator.

5. The industrial automation system of claim 1, wherein the sample rate adjustment component further comprising an estimation component that employs an analytical model to automatically predict a required data sampling rate for a stage of an operation associated with the industrial automation system.

6. The industrial automation system of claim 1, wherein the predetermined criteria is at least one of a fault detection or level of granularity for data collection assigned to an operational stage of an industrial process.

7. The industrial automation system of claim 1 further comprising a matching component that subscribes industrial zones with predetermined triggering events of an industrial process.

8. The industrial automation system of claim 5, wherein the data sampling rate can be varied by industrial zone.

9. The industrial automation system of claim 1 further comprising an artificial intelligence component that infers at least one of when, where, or how to vary the data sampling rate based upon at least one of a probabilistic or a statistical model.

10. The industrial automation system of claim 9, wherein the inference is based on prior collected data.

11. The industrial automation system of claim 9, wherein the probabilistic or the statistical model is adjusted based upon user feedback.

12. The industrial automation system of claim 1, wherein the data sampling rate is increased based upon a predetermined fault criteria.

13. A method of collecting data within an industrial plant comprising:

collecting data from multiple internal and external data streams;

maintaining a sequence relationship between multiple internal and external data streams based upon at least one of a common time stamp generator or a common sequence count generator; and

adjusting rate of data collection for at least one of the multiple internal and external data streams based upon a predetermined criteria.

14. The method of claim 13, wherein the multiple internal and external data streams are associated with an industrial process defined by a plurality of functional blocks.

15. The method of claim 14, wherein the predetermined criteria comprises a plurality of triggering events that each correspond to execution of a rate of data collection granularity level associated with a particular functional block.

16. The method of claim 15 further comprising adjusting the rate of data collection based upon user feedback regarding efficiency of collecting data at the granularity level.

17. The method of claim 15 further comprising collecting data based on the plurality of triggering events.

18. The method of claim 15, wherein the predetermined criteria is a fault detection, and the rate of data collection is increased.

19. The method of claim 15, wherein maintaining a sequence relationship further comprising weaving together the multiple internal and external data streams to.

20. An industrial automation system comprising:

means for synchronizing multiple data streams associated with the industrial automation system according to a common timestamp or sequence count generator, wherein each of the multiple data streams has a data sampling rate that defines a rate at which data is collected from the data stream; and

means for adjusting the data sampling rate of at least one data stream of the multiple data streams based upon at least one of a predetermined criteria or a predicted required sampling rate.