Non-Intrusive Data Analytics in a Process Control System

• US 20150005903A1
• Filed: 06/28/2013
• Published: 01/01/2015
• Est. Priority Date: 06/28/2013
• Status: Active Grant

• Current Assignee: Fisher-Rosemount Systems Incorporated (Emerson Electric Company)
• Original Assignee: Fisher-Rosemount Systems Incorporated (Emerson Electric Company)
• Inventors: Worek, Christopher J., Blevins, Terrence L., Havekost, Robert B., Thiele, Dirk
• Granted Patent: US 10,018,997 B2
• Time in Patent Office: Days
• US Class Current: 700/44
• CPC Class Codes: B29B 7/283 measuring data of the driving system, e.g. torque, speed, power
• CPC Class Codes: B29B 7/728 Measuring data of the driving system, e.g. torque, speed, power, vibration B29B7/724 takes precedence
• CPC Class Codes: G05B 19/41885 characterised by modeling, simulation of the manufacturing system
• CPC Class Codes: G05B 2219/31357 Observer based fault detection, use model
• CPC Class Codes: G05B 2219/31472 Graphical display of process
• CPC Class Codes: Y02P 90/02 Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Abstract

An on-line data analytics device can be installed in a process control system as a standalone device that operates in parallel with, but non-intrusively with respect to, the on-line control system to perform on-line analytics for a process without requiring the process control system to be reconfigured or recertified. The data analytics device includes a data analytics engine coupled to a logic engine that receives process data collected from the process control system in a non-intrusive manner. The logic engine operates to determine further process variable values not generated within the process control system and provides the collected process variable data and the further process variable values to the data analytics engine. The data analytics engine executes statistically based process models, such as batch models, stage models, and phase models, to produce a predicted process variable, such as an end of stage or end of batch quality variable for use in analyzing the operation of the on-line process.

Claims

1. A system for use in analyzing an operation of process plant control equipment within a process plant while the process plant control equipment is operating on-line within the process plant to implement an industrial process, comprising:

a data collection device, coupled to the process plant control equipment to collect process variable data from the process plant control equipment as determined or measured within the industrial process while the industrial process is operating on-line;

a process logic engine communicatively coupled to the data collection device that operates on a computer processor to simulate a portion of the operation of the industrial process using the collected process variable data to produce one or more further process variable values; and

a process analytic engine communicatively coupled to the process logic engine, including;

one or more stored data analytic models that statistically model the operation of the process; and

a data analytics execution engine that executes a data analytic routine using the one or more data analytic models while the industrial process is operating on-line to determine a predicted process variable for the industrial process using some of the process variable data and the one or more further process variable values while the industrial process is operating on-line.

2. The system of claim 1, wherein the predicted process variable is a predicted process quality value.

3. The system of claim 1, wherein the process logic engine includes one or more process simulation models and a process simulation engine that executes on a processor to simulate the operation of the industrial process using the one or more process simulation models to produce the one or more further process variable values.

4. The system of claim 3, wherein the process simulation engine stores the collected process variable values as collected by the data collection device to simulate the operation of the industrial process.

5. The system of claim 1, wherein the industrial process is a batch process and the one or more data analytic models includes a batch model.

6. The system of claim 5, wherein the process logic engine includes a process model that determines the start or the stop of a batch defined by the batch model as one of the one or more further process variable values.

7. The system of claim 1, wherein the industrial process is a batch process and wherein the one or more data analytic models includes two or more stage models for modeling a particular batch process.

8. The system of claim 7, wherein the process logic engine includes a process model that determines the start or the stop of each of two or more stages associated with the two or more stage models as the one or more further process variable values.

9. The system of claim 1, wherein the industrial process is a batch process and wherein the one or more data analytic models includes two or more phase models for different phases of a batch for modeling a particular batch process.

10. The system of claim 9, wherein the process logic engine includes a process model that determines the start or the stop of each of two or more phases associated with the phase models as the one or more further process variable values.

11. The system of claim 1, wherein the data analytic models includes a projection to latent structures (PLS) model.

12. The system of claim 1, wherein the data collection device collects process variables in the form of measured process variables.

13. The system of claim 1, wherein the data collection device collects process variables in the form of control signals.

14. The system of claim 1, wherein the data collection device collects process variables in the form of alarms and alerts as generated within the industrial process.

15. The system of claim 1, further including a model builder engine that develops the one or more data analytic models from past process variable data collected from the industrial process for one or more previous industrial processes and further variable values as determined by the process logic engine for the one or more previous industrial processes.

16. The system of claim 1, wherein the process logic engine includes a process simulation engine that stores the current configuration of the process control equipment used in the industrial process.

17. The system of claim 1, wherein the process logic engine includes a logic builder engine the enables a user to develop one or more logic modules to be implemented on the process logic engine to determine the one or more further process variable values.

18. The system of claim 1, wherein the predicted process variable values comprise one of an end-of-stage product quality and an end-of-batch product quality.

19. The system of claim 1, wherein the data collection device is an OPC data collection device.

20. A computer implemented method of analyzing an operation of process plant control equipment within a process plant while the process plant control equipment is operating on-line within the process plant to implement an industrial process, comprising:

collecting process variable data from the process plant control equipment as determined or measured within the industrial process while the industrial process is operating on-line;

using at least some of the collected process variable data to simulate the operation of the industrial process on a computer processor device to produce one or more further process variable values;

storing one or more data analytic models that statistically model the operation of the process; and

using a computer processor to implement a data analytic routine using the one or more data analytic models, at least a portion of the collected process variable data and the one or more further process variable values while the industrial process is operating on-line to determine a predicted process variable for the industrial process.

21. The computer implemented method of claim 20, wherein determining a predicted process variable for the industrial process includes determining the predicted process variable as a predicted process quality value.

22. The computer implemented method of claim 20, wherein determining a predicted process variable for the industrial process includes determining the predicted process variable value as one of an end-of-stage product quality and an end-of-batch product quality.

23. The computer implemented method of claim 20, wherein collecting process variable data from the process plant control equipment as determined or measured within the industrial process while the industrial process is operating on-line includes collecting the process variable data without reconfiguring the process control equipment.

24. The computer implemented method of claim 20, wherein collecting process variable data from the process plant control equipment as determined or measured within the industrial process while the industrial process is operating on-line includes collecting process variable data via a communications firewall.

25. The computer implemented method of claim 20, wherein using at least some of the collected process variable data to simulate the operation of the industrial process includes using one or more process logic routines that operate on the at least some of the collected process variable data to produce the one or more further process variable values.

26. The computer implemented method of claim 20, wherein using at least some of the collected process variable data to simulate the operation of the industrial process on a computer processor device to produce one or more further process variable values includes simulating the operation of the industrial process using one or more process simulation models.

27. The computer implemented method of claim 20, wherein the industrial process is a batch process and wherein using a computer processor to implement a data analytic routine using one or more data analytic models includes using one more batch models, stage models or phase models as the one or more data analytic models.

28. The computer implemented method of claim 27, wherein using at least some of the collected process variable data to simulate the operation of the industrial process on a computer processor device to produce one or more further process variable values includes determining the start or the stop of a batch, a stage or a phase associated with a batch model, a stage model or a phase model, as one of the one or more further process variable values.

29. The computer implemented method of claim 20, wherein using a computer processor to implement a data analytic routine using the one or more data analytic models includes using a projection to latent structures (PLS) model as one of the one or more data analytic models.

30. The computer implemented method of claim 20, further including enabling a user to develop, using a computer processor, the one or more data analytic models from past process variable data collected from the industrial process for one or more previous industrial processes and further variable values as determined for the one or more previous industrial processes.

31. The computer implemented method of claim 20, further including enabling a user to develop one or more logic modules to be implemented on a computer processor to determine the one or more further process variable values.

32. A process control system for use in controlling an industrial process, comprising:

process plant control equipment including a controller and one or more field devices which implement an industrial process;

a data collection device, communicatively coupled to the process plant control equipment to collect process variable data from the process plant control equipment as determined or measured within the industrial process while the industrial process is operating on-line;

a process logic engine communicatively coupled to the data collection device that operates on a computer processor to simulate the operation of the industrial process using some of the collected process variable data to produce one or more further process variable values; and

a process analytic engine communicatively coupled to the process logic engine, including;

one or more stored data analytic models that statistically model the operation of the process; and

a data analytics execution engine that executes a data analytic routine using the one or more data analytic models while the industrial process is operating on-line to determine a predicted process variable for the industrial process using a portion of the collected process variable data and the one or more further process variable values while the industrial process is operating on-line.

33. The process control system of claim 32, wherein the process plant control equipment is coupled to a first communications network and the process logic engine and the process analytic engine are coupled to a second communications network, and further including one or more firewalls disposed between the first communications network and the second communications network.

34. The process control system of claim 33, wherein the data collection device is coupled to both the first and the second communications networks.

35. The process control system of claim 34, wherein the data collection device performs read-only operations on the first communications network without performing any write operations on the first communications network.

36. The process control system of claim 33, wherein the process plant control equipment includes a data historian, and wherein the data historian is connected to the first and the second communication networks and is adapted to store data generated by and received from devices coupled to the first communications network.

37. The process control system of claim 32, wherein the predicted process variable is a predicted process quality value.

38. The process control system of claim 32, wherein the process logic engine includes one or more process simulation models and a process simulation engine that executes on a processor to simulate the operation of the industrial process using the one or more process simulation models.

39. The process control system of claim 32, wherein the industrial process is a batch process and the one or more data analytic models includes a batch model and wherein the process logic engine includes a process model that determines the start or the stop of a batch defined by the batch model as one of the one or more further process variable values.

40. The process control system of claim 32, wherein the data analytic models includes a projection to latent structures (PLS) model.

41. The process control system of claim 32, further including a model builder engine that develops the one or more data analytic models from past process variable data collected from the industrial process for one or more previous industrial process times and further variable values as determined by the process logic engine for the one or more previous industrial process times.

42. The process control system of claim 41, wherein the process logic engine includes a logic builder engine the enables a user to develop one or more logic modules to be implemented on the process logic engine to determine the one or more further process variable values.