Time-series analytics for control valve health assessment

• US 10,619,760 B2
• Filed: 10/24/2016
• Issued: 04/14/2020
• Est. Priority Date: 10/24/2016
• Status: Active Grant

• Current Assignee: Fisher Controls International LLC (Emerson Electric Company)
• Original Assignee: Fisher Controls International LLC (Emerson Electric Company)
• Inventors: Anderson, Shawn W.
• Primary Examiner(s): Lee, Paul D
• Application Number:
  US15/332,563
• Publication Number:
  US 20180112795A1
• Time in Patent Office: 1,268 Days
• Field of Search: 702185
• CPC Class Codes: F16K 37/0041 for measuring valve parameters F16K37/0033 takes precedence
• CPC Class Codes: F16K 37/0083 by measuring valve parameters
• CPC Class Codes: F16K 37/0091 by measuring fluid parameters
• CPC Class Codes: G05B 23/0221 Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods
• CPC Class Codes: G05B 23/0232 based on qualitative trend analysis, e.g. system evolution
• CPC Class Codes: G05B 23/0237 based on parallel systems, e.g. comparing signals produced at the same time by same type systems and detect faulty ones by noticing differences among their responses
• 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
• CPC Class Codes: G05B 23/0272 Presentation of monitored results, e.g. selection of status reports to be displayed; Filtering information to the user

Abstract

Securing communications from a process plant to a remote system includes a data diode disposed there between that allows data to egress from the plant but prevents ingress of data into the plant and its associated systems. Process plant data from the secure communications is then analyzed to detect conditions occurring at process plant entities in the process plant using various machine learning techniques. When the process plant entity is a valve, the mode of operation for the valve is determined and a different analysis is applied for each mode in which a valve operates. Additionally, the process plant data for each valve is compared to other valves in the same process plant, enterprise, industry, etc. Accordingly, the health of each of the valves is ranked relative to each other and the process plant data for each valve is displayed in a side-by-side comparison.

Claims

1. A method for detecting the health of a valve, the method comprising:

receiving, at a computing device, data corresponding to a valve disposed in a process plant and operating to control an industrial process, the valve data including respective valve parameter values of the valve for one or more valve parameters over a plurality of instances of time collected as the valve is operating in the process plant;

analyzing, by the computing device, the valve data to determine a value of a real-time overall device health parameter of the valve;

determining, by the computing device, a relative health indicator of the valve based on a comparison of the real-time overall device health parameter value of the valve and respective real-time overall device health parameter values of a plurality of valves;

detecting a condition of the valve based on the relative health indicator of the valve; and

transmitting a control signal to the process plant to adjust operation of the process plant based on the detected condition of the valve to shut down operation of the valve.

2. The method of claim 1, wherein:

determining the relative health indicator of the valve based on the comparison of the real-time overall device health parameter value of the valve in the respective real-time overall device health parameter values of the plurality of valves includes ranking the plurality of valves based on the respective real-time overall device health parameter values of the plurality of valves; and

providing an indication of the real-time overall device health parameter value of the valve and an indication of the ranking of the plurality of valves for at least one of;

display at a user interface, storage in a data storage entity, or use by an application.

3. The method of claim 1, wherein analyzing the valve data to determine the real-time overall device health parameter value of the valve includes:

combining the respective valve parameter values of the valve for the one or more valve parameters over the plurality of instances of time to generate one or more valve parameter metrics; and

determining the real-time overall device health parameter value of the valve based on the one or more valve parameter metrics.

4. The method of claim 3,

further comprising generating a statistical model based on historical valve parameter values for the one or more valve parameters;

and

wherein determining the real-time overall device health parameter value of the valve based on the one or more valve parameter metrics comprises applying the one or more valve parameter metrics to the statistical model.

5. The method of claim 3, further comprising:

transmitting an indication of the detected condition of the valve to a user interface.

6. The method of claim 1, wherein:

the detected condition of the valve is a first detected condition; and

the method further comprises;

combining the respective valve parameter values of the valve for the one or more valve parameters over the plurality of instances of time to generate one or more valve parameter metrics;

generating, based on historical valve parameter values for the one or more valve parameters, a statistical model for detecting a second condition of the valve;

detecting the second condition of the valve by applying the one or more valve parameter metrics to the statistical model; and

comparing the first detected condition to the second detected condition; and

transmitting the indication of the first detected condition of the valve to the user interface comprises transmitting the indication of the first detected condition of the valve to the user interface when the first detected condition differs from the second detected condition.

7. The method of claim 1, further comprising:

causing an alarm or an event to be generated at the process plant based on the detected condition of the valve.

8. The method of claim 1, wherein detecting the condition of the valve includes at least one of:

determining a performance metric of the valve, or detecting at least one of;

an error, dead band, dead time, mechanical wear or a leak at the valve.

9. The method of claim 1, further comprising:

generating indications of respective valve parameter values of the plurality of valves for the one or more valve parameters over the plurality of instances of time; and

providing, to a user interface for display in a time series depiction, the indications of the respective valve parameter values of the plurality of valves for the one or more valve parameters over the plurality of instances of time in conjunction with the respective valve parameter values of the valve for the one or more valve parameters over the plurality of instances of time.

10. The method of claim 1, wherein the valve data includes at least one of:

a drive signal to the valve, a valve travel, or a travel set point; and

wherein the valve data is analyzed while the valve data is collected.

11. A system for detecting the health of a plurality of valves, the system comprising:

a plurality of valves, at least some of which are operating within a process plant to control an industrial process; and

one or more computing devices including;

one or more processors;

a communication unit; and

one or more non-transitory computer-readable media coupled to the one or more processors and to the communication unit, the one or more non-transitory computer-readable media storing instructions thereon that, when executed by the one or more processors, cause the one or more computing devices to;

receive valve data corresponding to the plurality of valves, the valve data including respective valve parameter values, of each valve included in the plurality of valves, for one or more valve parameters over a plurality of instances of time collected as the valve is operating in the process plant;

analyze the respective valve parameter values of the each valve to determine a respective real-time overall device health parameter value for the each valve;

determine a respective relative health indicator for the each valve based on a comparison of the real-time overall device health parameter values of the plurality of valves;

detect a condition of at least one of the valves based on the relative health indicator of the at least one valve; and

transmit a control signal to the process plant to adjust operation of the process plant based on the detected condition of the at least one valve to shut down operation of the at least one valve.

12. The system of claim 11, wherein:

the respective relative health indicators of the plurality of valves are determined based on a ranking of the plurality of valves based on the real-time overall device health parameter values of the plurality of valves; and

an indication of the ranking of the plurality of valves is provided in conjunction with the relative health indicator of the each valve for at least one of;

display at a user interface, storage in a data storage entity, or use by an application.

13. The system of claim 11, wherein:

the analysis of the respective valve parameter values of the each valve includes a combination of the respective valve parameter values of the each valve over the plurality of instances of time to generate a valve parameter metric of the each valve; and

the value of the respective real-time overall device health parameter for the each valve is based on the valve parameter metric of the each valve.

14. The system of claim 13,

further comprising a statistical model generated based on historical valve parameter values for the one or more valve parameters;

and

the value of the respective real-time overall device health parameter for the each valve is determined by an application of the valve parameter metric of the each valve to the statistical model.

15. The system of claim 14, wherein each of the historical valve parameter values is associated with a corresponding device health score for a corresponding valve, and the statistical model is generated further based on the corresponding device health scores associated with the historical valve parameter values.

16. The system of claim 14, wherein the statistical model is generated using one or more machine learning techniques, the one or more machine learning techniques including at least one of:

linear regression, polynomial regression, logistic regression, nave Bayes, decision trees, random forests, boosting, nearest neighbors, or neural networks.

17. The system of claim 11, wherein the instructions are further executable to cause the one or more computing devices to:

transmit an indication of the detected condition of the at least one valve to a user interface.

18. The system of claim 11, wherein the detected condition of the at least one valve includes at least one of:

a performance metric, an error, a leak, dead band, or mechanical wear at the at least one valve.

19. The system of claim 11,

further comprising a data diode configured to prevent two-way communications between a network of the process plant and the one or more computing devices;

and

wherein the valve data is secured for transmission from the process plant to the one or more computing devices via the data diode.

20. The system of claim 19, wherein the one or more computing devices are included in a cloud computing system.

21. The system of claim 11, wherein the instructions are further executable to cause the one or more computing devices to:

generate indications of respective valve parameter values of the plurality of valves for the one or more valve parameters over the plurality of instances of time; and

provide, to a user interface for display in a time series depiction, the indications of the respective valve parameter values of the plurality of valves for the one or more valve parameters over the plurality of instances of time.