Process plant monitoring based on multivariate statistical analysis and on-line process simulation

• US 20070005266A1
• Filed: 09/06/2006
• Published: 01/04/2007
• Est. Priority Date: 05/04/2004
• Status: Active Grant

• Current Assignee: Fisher-Rosemount Systems Incorporated (Emerson Electric Company)
• Original Assignee: Fisher-Rosemount Systems Incorporated (Emerson Electric Company)
• Inventors: Nixon, Mark, Blevins, Terrence, McMillan, Gregory
• Granted Patent: US 7,729,789 B2
• Time in Patent Office: Days
• US Class Current: 702/22
• CPC Class Codes: G05B 17/02 electric
• CPC Class Codes: G05B 19/0426 Programming the control sequence
• CPC Class Codes: G05B 19/41885 characterised by modeling, simulation of the manufacturing system
• CPC Class Codes: G05B 2219/23424 Select construction element from function library
• CPC Class Codes: G05B 2219/25067 Graphic configuration control system
• CPC Class Codes: G05B 2219/25428 Field device
• CPC Class Codes: G05B 2219/31467 Display of operating conditions of machines, workcells, selected programs
• CPC Class Codes: G05B 2219/31469 Graphical display of process as function of detected alarm signals
• CPC Class Codes: G05B 2219/31472 Graphical display of process
• CPC Class Codes: G05B 2219/31474 Icon display for quick access of detailed information
• CPC Class Codes: G05B 2219/32128 Gui graphical user interface
• CPC Class Codes: G05B 2219/32342 Real time simulation
• CPC Class Codes: G05B 23/0254 based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks
• CPC Class Codes: G05B 23/0267 Fault communication, e.g. human machine interface [HMI]
• CPC Class Codes: G06F 8/20 Software design
• CPC Class Codes: G06F 9/4488 Object-oriented
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 50/04 Manufacturing
• CPC Class Codes: H04L 2012/4026 Bus for use in automation systems
• CPC Class Codes: H04L 67/12 : specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
• CPC Class Codes: H04L 67/289 : Intermediate processing functionally located close to the data consumer application, e.g. in same machine, in same home or in same sub-network
• CPC Class Codes: H04L 67/51 : Discovery or management thereof, e.g. service location protocol [SLP] or web services
• CPC Class Codes: H04L 67/56 : Provisioning of proxy services store-and-forward switching systems in data switching networks H04L12/54
• CPC Class Codes: H04L 67/75 : Indicating network or usage conditions on the user display
• CPC Class Codes: Y02P 90/02 : Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
• CPC Class Codes: Y02P 90/30 : Computing systems specially adapted for manufacturing
• CPC Class Codes: Y02P 90/80 : Management or planning
• CPC Class Codes: Y10S 715/965 : for process control and configuration

Abstract

Disclosed are systems and methods for on-line monitoring of operation of a process in connection with process measurements indicative of the operation of the process. In some cases, the operation of the process is simulated to generate model data indicative of a simulated representation of the operation of the process and based on the process measurements. A multivariate statistical analysis of the operation of the process is implemented based on the model data and the process measurements. The output data from the multivariate statistical analysis may then be evaluated during the operation of the process to enable the on-line monitoring of the process involving, for instance, fault detection via classification analysis of the output data.

Claims

1. A system for on-line monitoring of operation of a process in a process plant having a process control system to control the process in connection with process measurements indicative of the operation of the process, the system comprising:

a process simulation module to model a plurality of physical devices within the process plant for generation of model data indicative of a simulated representation of the operation of the process;

an analysis module to implement a multivariate statistical analysis of the operation of the process based on the model data and the process measurements;

one or more computer-readable media to store respective configurations of the process simulation module and the analysis module; and

,

one or more computer-executable execution engines for implementation of the respective configurations of the process simulation module and the analysis module to enable the on-line monitoring of the process based on communications with the process control system during the operation of the process.

2. The system of claim 1, wherein the configuration of the analysis module comprises a principal component analysis (PCA) tool to generate output data indicative of differences between the model data and the process measurements.

3. The system of claim 1, wherein the configuration of the analysis module comprises a partial least squares (PLS) analysis tool to generate output data indicative of differences between the model data and the process measurements.

4. The system of claim 1, wherein the configuration of the analysis module comprises a principal component analysis (PCA) tool and a partial least squares (PLS) analysis tool utilized in combination to generate output data indicative of differences between the model data and the process measurements.

5. The system of claim 1, wherein the configuration of the analysis module further comprises an expert analysis tool comprising a rule stored on the one or more computer-readable media and configured to be applied to output data from the multivariate statistical analysis.

6. The system of claim 1, wherein the configuration of the analysis module further comprises a discriminant analysis tool comprising criteria stored on the one or more computer-readable media and configured to be applied to output data from the multivariate statistical analysis.

7. The system of claim 1, wherein the model data comprises process parameter data indicative of a future operational state of the process based on the process measurements, such that the implementation of the multivariate statistical analysis utilizes the process parameter data to evaluate the future operational state of the process.

8. The system of claim 1, wherein the model data comprises a non-measured process parameter indicative of the operation of the process and derived from the process measurements, and wherein the configuration of the analysis module is adapted to analyze the non-measured process parameter.

9. The system of claim 1, further comprising a process graphic stored in the one or more computer-readable media and adapted for use by the one or more execution engines in generating a user interface having a graphic display of the plurality of physical devices modeled by the process simulation module, wherein the graphic display is configured to provide a plurality of display elements representative of current operating conditions of the plurality of physical devices, respectively, in accordance with the multivariate statistical analysis.

10. The system of claim 9, wherein each display element of the plurality of display elements is individually selectable to configure the analysis module.

11. The system of claim 1, wherein the elements of the process control system comprises a process control module, which, in turn, comprises a plurality of process control routines stored in the one or more computer-readable media and configured to support transmission of the process measurements to the process simulation module and the analysis module during the operation of the process.

12. The system of claim 1, wherein the configuration of the analysis tool comprises a principal component analysis (PCA) tool comprising a plurality of model data sets, each model data set corresponding with a disturbance input provided to the process simulation module to simulate a respective abnormal operating situation.

13. The system of claim 1, wherein the implementation of the process simulation module and the analysis module is integrated within an on-line environment of the process control system.

14. The system of claim 13, further comprising a graphic display module stored on the one or more computer-readable media and adapted for implementation by the one or more execution engines to generate a depiction of the plurality of physical devices with information indicative of a fault condition identified by the multivariate statistical representation, the depiction being provided via a user interface integrated with an operator interface of the on-line environment of the process control system.

15. A method for on-line monitoring of operation of a process in connection with process measurements indicative of the operation of the process, the method comprising the steps of:

simulating the operation of the process to generate model data indicative of a simulated representation of the operation of the process and based on the process measurements;

implementing a multivariate statistical analysis of the operation of the process based on the model data and the process measurements; and

,

evaluating output data from the multivariate statistical analysis during the operation of the process to enable the on-line monitoring of the process.

16. The method of claim 15, wherein the multivariate statistical analysis comprises principal component analysis (PCA) of data indicative of the operation of the process.

17. The method of claim 15, wherein the multivariate statistical analysis comprises a partial least squares (PLS) analysis of data indicative of the operation of the process.

18. The method of claim 15, wherein the evaluating step comprises the step of determining whether a fault condition exists in the operation of the process via classification analysis of the output data.

19. The method of claim 18, wherein the classification analysis is based on one or more expert rules.

20. The method of claim 18, wherein the classification analysis comprises discriminant analysis of the output data.

21. The method of claim 18, wherein the model data comprises process parameter data indicative of a future operational state of the process based on the process measurements.

22. The method of claim 18, wherein the model data comprises a non-measured process parameter indicative of the operation of the process.

23. The method of claim 18, further comprising the steps of rendering a graphic display of the process, and displaying data indicative of the fault condition by modifying a portion of the graphic display associated with a portion of the process implicated by the fault condition.

24. A method for on-line monitoring of operation of a process in a process plant having a process control system to control the process in connection with process measurements indicative of the operation of the process, the method comprising the steps of:

executing a control routine via the process control system to generate a process parameter based on the process measurements;

implementing a multivariate statistical analysis of the operation of the process to generate statistical data based on the process parameter and the process measurements;

evaluating the statistical data from the multivariate statistical analysis during the operation of the process for a determination of whether a fault condition exists; and

,

generating a user interface display of a process graphic to enable the on-line monitoring of the process by depicting the fault condition determination in connection with a plurality of physical devices within the process plant.

25. The method of claim 24, wherein the multivariate statistical analysis comprises principal component analysis (PCA) of data indicative of the operation of the process.

26. The method of claim 25, wherein the principal component analysis (PCA) comprises multiway PCA based on process data indicative of historical operation of the process.

27. The method of claim 24, wherein the multivariate statistical analysis comprises a partial least squares (PLS) analysis of data indicative of the operation of the process.

28. The method of claim 27, wherein the partial least squares (PLS) analysis comprises multiway PLS analysis based on process data indicative of historical operation of the process.

29. The method of claim 24, wherein the evaluating step comprises determining whether the fault condition exists via classification analysis of the statistical data.

30. The method of claim 24, further comprising the step of simulating the operation of the process to generate model data indicative of the simulated operation of the process, such that the multivariate statistical analysis is based on a statistical comparison of the model data with the process parameter and the process measurements.