Method and system for assessing performance of control systems

• US 20080183424A1
• Filed: 01/25/2007
• Published: 07/31/2008
• Est. Priority Date: 01/25/2007
• Status: Active Grant

• Current Assignee: Tyco Fire & Security GmbH (Johnson Controls International plc)
• Original Assignee: Johnson Controls Technology Company (Johnson Controls International plc)
• Inventors: Seem, John E.
• Granted Patent: US 7,496,472 B2
• Time in Patent Office: Days
• US Class Current: 702/181
• CPC Class Codes: G05B 23/0216 Human interface functionality, e.g. monitoring system providing help to the user in the selection of tests or in its configuration
• CPC Class Codes: G05B 23/024 Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks

Abstract

A method and system is disclosed for scaling performance indicators of control applications in an environmental control system. The method and system include receiving more than one performance indicator from a first control application, wherein the first control application includes a modulating control output and receiving more than one performance indicator from a second control application, wherein the second control application includes a staged-control output. The method and system further include identifying a probability distribution, wherein the probability distribution is characteristic of a fault-free environmental control system and calculating probability distributions associated with the performance indicators of the first and second control applications. The method and system also include displaying the probability distributions of the first and second control applications on a common scale.

Claims

1. A method for scaling performance indicators of control applications in an environmental control system, the method comprising:

receiving more than one performance indicator from a first control application, wherein the first control application includes a modulating control output;

receiving more than one performance indicator from a second control application, wherein the second control application includes a staged-control output;

identifying a probability distribution function, wherein the probability distribution function is characteristic of a fault-free environmental control system;

calculating probability distributions associated with the performance indicators of the first and second control applications; and

displaying the probability distributions of the first and second control applications on a common scale.

2. A method for scaling performance indicators according to claim 1, wherein the step of calculating the probability distributions includes performing a logarithmic transformation of the performance indicators.

3. A method for scaling performance indicators according to claim 2, wherein the logarithmic transformation for the first control application is given by:

4. A method for scaling performance indicators according to claim 2, wherein the logarithmic transformation for the second control application is given by:

5. A method for scaling performance indicators according to claim 1, wherein the probability distribution function comprises a sample mean and standard deviation function.

6. A method for scaling performance indicators according to claim 1, wherein the probability distribution function comprises a kernel density function.

7. A method for scaling performance indicators according to claim 1, wherein the probability distribution function comprises a moments function.

8. A method for scaling performance indicators according to claim 1, wherein the performance indicators are exponentially weighted moving averages.

9. A method for scaling performance indicators according to claim 1, wherein the common scale comprises a plurality of dot plots ranging from good to poor performance.

10. A method for scaling performance indicators according to claim 1, wherein the control applications are associated with an HYAC system.

11. A method for scaling performance indicators according to claim 1, wherein the performance indicators represent error in the performance of the control application.

12. A method for analyzing performance of control applications in an environmental control system, the steps of the method comprising:

receiving more than one performance indicator from a first and a second control application;

determining probability distributions associated with the performance indicators of the first and second control applications; and

displaying the probability distributions of the first and second control applications on a common scale.

13. A method for analyzing performance of control applications according to claim 12, wherein the common scale comprises a plurality of dot plots ranging from good to poor performance.

14. A method for analyzing performance of control applications according to claim 12, wherein the step of displaying the probability distributions includes displaying on a rug plot.

15. A method for analyzing performance of control applications according to claim 12, wherein the performance indicators are exponentially weighted moving averages.

16. A method for analyzing performance of control applications according to claim 12, wherein the performance indicators represent error in the performance of the control application.

17. A method for analyzing performance of control applications according to claim 12, wherein the control applications are associated with an HYAC system.

18. A method for analyzing performance of control applications according to claim 12, further including performing a logarithmic transformation of the performance indicators.

19. A method for analyzing performance of control applications according to claim 18, wherein the logarithmic transformation for the first control application is given by:

20. A method for analyzing performance of control applications according to claim 18, wherein the logarithmic transformation for the second control application is given by:

21. A method for analyzing performance of control applications according to claim 12, wherein determining probability distributions associated with the performance indicators of the first and second control applications comprises utilizing a sample mean and standard deviation function.

22. A method for analyzing performance of control applications according to claim 12, wherein determining probability distributions associated with the performance indicators of the first and second control applications comprises utilizing a kernel density function.

23. A method for analyzing performance of control applications according to claim 12, wherein determining probability distributions associated with the performance indicators of the first and second control applications comprises utilizing a moments function.