Valve service detection through data analysis

• US 9,934,671 B1
• Filed: 10/24/2016
• Issued: 04/03/2018
• 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): Mullen, Thomas
• Application Number:
  US15/332,542
• Time in Patent Office: 526 Days
• Field of Search: 340679, 3406861, 340540, 340606, 340626, 340584, 700 83, 700108
• 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: G05B 2219/24015 Monitoring
• CPC Class Codes: G05B 2219/25297 Identify controlled element, valve, and read characteristics
• CPC Class Codes: G05B 23/0208 characterized by the configuration of the monitoring system
• 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: G08B 21/18 Status alarms G08B21/02 takes precedence
• CPC Class Codes: H04L 12/40019 Details regarding a bus master
• CPC Class Codes: H04L 2012/4026 Bus for use in automation systems
• CPC Class Codes: Y02P 90/02 Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

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 a mode of operation of a valve in a process plant, the method comprising:

receiving, at a computing device, data generated as a result of the valve operating within the process plant 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;

analyzing, by the computing device, the valve data to identify, from a plurality of modes of valve operation, a mode of operation of the valve, the plurality of modes of valve operation including two or more of;

full stroke cycling, continuous throttling, or periodic throttling; and

transmitting an indication of the identified mode of operation of the valve to at least one of a user interface or an application within the computing device or another computing device for analyzing operations in the process plant.

2. The method of claim 1, wherein the respective valve parameter values are a first set of valve parameters, and the method further comprises:

selecting, based on the identified mode of operation of the valve, a second set of valve parameters;

analyzing a second set of valve parameter values of the second set of valve parameters over the plurality of instances of time, thereby detecting a condition of the valve, the second set of valve parameter values included in the valve data; and

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

3. The method of claim 2, wherein analyzing the second set of valve parameter values over the plurality of instances in time thereby detecting the condition of the valve includes:

combining the second set of valve parameter values over the plurality of instances of time to generate one or more valve parameter metrics; and

detecting the condition 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 second set of valve parameters, the historical valve parameter values generated by one or more valves operating in the identified mode of operation of the valve;

and

wherein detecting the condition 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 4, wherein generating the statistical model includes generating the statistical model 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, naï

ve Bayes, decision trees, random forests, boosting, nearest neighbors, or neural networks.

6. The method of claim 2, further comprising:

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

7. The method of claim 2, wherein detecting the condition of the valve includes at least one of:

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

dead band, dead time, or a leak at the valve.

8. The method of claim 1, wherein analyzing the valve data to identify the mode of operation of the valve includes:

combining the respective valve parameter values of the valve over the plurality of instances of time to generate a valve parameter metric of the valve;

comparing the valve parameter metric of the valve to a plurality of statistical models respectively corresponding to the plurality of modes of valve operation, each statistical model corresponding to a respective mode of valve operation and generated based on respective historical valve parameter values of one or more valves operating in the respective mode of valve operation; and

identifying the mode of operation of the valve based on the comparison.

9. The method of claim 1, wherein analyzing the valve data including the respective valve parameter values to identify the mode of operation of the valve includes analyzing values corresponding to at least one of:

a travel set point, a valve travel measurement, an instrument drive signal, an actuator pressure, a travel cycle, a cycle counter, a travel accumulator, or a control signal over the plurality of instances of time to identify the mode of operation of the valve.

10. The method of claim 9, wherein analyzing the valve data to identify the mode of operation of the valve includes:

analyzing respective valve travel measurements of the valve over the plurality of instances of time during on-line operation of the process plant to determine an average valve travel per cycle;

determining the valve is operating in the full stroke cycling mode when the average valve travel per cycle exceeds a threshold number;

determining the valve is operating in the continuous throttling mode when the average valve travel per cycle does not exceed the threshold number; and

determining the valve is operating in the periodic throttling mode when the valve alternates between operating in the full stroke cycling mode and operating in the continuous throttling mode.

11. A system for detecting a mode of operation of a valve in a process plant, the system comprising:

a valve operating within the 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, via the communication unit, data generated as a result of the valve operating within the process plant to control the 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;

analyze the valve data to identify, from a plurality of modes of valve operation, a mode of operation of the valve, the plurality of modes of valve operation including two or more of;

full stroke cycling, continuous throttling, or periodic throttling; and

transmit, via the communication unit, an indication of the identified mode of operation of the valve to at least one of a user interface or an application within the one or more computing devices or within other computing devices for analyzing operations in the process plant.

12. The system of claim 11, wherein the respective valve parameter values are a first set of valve parameters, and the instructions are executable to further cause the computing device to:

select, based on the identified mode of operation of the valve, a second set of valve parameters;

analyze a second set of valve parameter values of the second set of valve parameters over the plurality of instances of time to detect a condition of the valve, the second set of valve parameter values included in the valve data; and

transmit, via the communication unit, an indication of the detected condition of the valve to the user interface.

13. The system of claim 12, wherein:

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

the condition of the valve is detected based on the valve parameter metric.

14. The system of claim 13,

further comprising a statistical model corresponding to the identified mode of operation of the valve and generated based on historical valve parameter values of valves operating in the identified mode of operation;

and

wherein the condition of the valve is detected based on an application of the valve parameter metric to the statistical model corresponding to the identified mode of operation of the valve.

15. 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, naï

ve Bayes, decision trees, random forests, boosting, nearest neighbors, or neural networks.

16. The system of claim 12, wherein the detected condition of the valve includes at least one of:

a performance metric indicating a level of performance of the valve, dead band, dead time, or a leak at the valve.

17. The system of claim 11, wherein the analysis of the valve data to identify the mode of operation of the valve includes:

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

a comparison of the valve parameter metric of the valve to a plurality of statistical models respectively corresponding to the plurality of modes of valve operation, each statistical model corresponding to a respective mode of valve operation and generated based on respective historical valve parameter values of one or more valves operating according to the respective mode of valve operation; and

an identification of the mode of operation of the valve based on the comparison.

18. The system of claim 17, wherein the plurality of statistical models are generated using one or more machine learning techniques.

19. The system of claim 11, wherein the valve data includes valve parameter values of the valve corresponding to at least one of:

a travel set point, a valve travel measurement, an actuator pressure, a travel cycle, a cycle counter, a travel accumulator, or a control signal.

20. The system of claim 19, wherein:

the analysis of the valve data includes an analysis of respective valve travel measurements of the valve over the plurality of instances of time during on-line operation of the process plant to determine an average valve travel per cycle;

the valve is determined to be operating in the full stroke cycling mode when the average valve travel per cycle exceeds a threshold number;

the valve is determined to be operating in the continuous throttling mode when the average valve travel per cycle does not exceed the threshold number; and

the valve is determined to be operating in the periodic throttling mode when the valve alternates between operating in the full stroke cycling mode and the continuous throttling mode.

21. The system of claim 11, wherein the one or more computing devices are included in a cloud computing system.

22. The system of claim 21, wherein the cloud computing system and the process plant are communicatively connected via a data diode, the data diode configured to prevent data traffic from ingressing into the process plant.