Predicted fault analysis

• US 9,323,234 B2
• Filed: 10/24/2011
• Issued: 04/26/2016
• Est. Priority Date: 06/10/2009
• Status: Active Grant

• Current Assignee: Fisher-Rosemount Systems Incorporated (Emerson Electric Company)
• Original Assignee: Fisher-Rosemount Systems Incorporated (Emerson Electric Company)
• Inventors: Zhou, Ling, Daly, Paul K., Havekost, Robert B., Blevins, Terrence L., Wojsznis, Wilhelm K., Nixon, Mark J., Worek, Christopher J., Muston, Paul R.
• Primary Examiner(s): DUNN, DARRIN D
• Application Number:
  US13/279,881
• Publication Number:
  US 20120083917A1
• Time in Patent Office: 1,646 Days
• Field of Search: 700/12, 700 28- 30, 700/100, 700/109
• US Class Current: 1/1
• CPC Class Codes: G05B 13/048 using a predictor
• CPC Class Codes: G05B 19/41875 characterised by quality surveillance of production
• CPC Class Codes: G05B 2219/32187 Correlation between controlling parameters for influence on quality parameters
• CPC Class Codes: G05B 2219/32194 Quality prediction
• CPC Class Codes: G05B 23/0283 Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL] preventive maintenance, i.e. planning maintenance according to the available resources without monitoring the system G06Q10/06
• CPC Class Codes: Y02P 90/02 Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Abstract

Example methods, apparatuses and systems to correlate candidate factors to a predicted fault in a process control system are disclosed. Techniques may include obtaining a value associated with a particular factor corresponding to a process, and predicting a fault based on the value. A set of candidate factors corresponding to the predicted fault may be determined, and a correlation between the predicted fault and at least one factor from the set may be displayed. Different sections of the display may respectively correspond to the predicted fault and to the at least one factor, and the correlation may be indicated by time aligning the different sections. Modifications to one displayed section may result in automatic modification of other sections to maintain the correlation. A user may select one or more candidate factors to be displayed, and may indicate a particular point of a particular section to obtain additional details.

Claims

1. A method of correlating candidate factors to a predicted fault in a process control system, comprising:

obtaining a value associated with a particular factor corresponding to a process controlled in the process control system;

predicting a fault corresponding to the process when at least one of;

a predicted quality of the process passes a first threshold, the predicted quality of the process determined based on the value associated with the particular factor, or

a variation of the value of the particular factor passes a second threshold;

determining a set of candidate factors corresponding to the predicted fault, the set of candidate factors including the particular factor;

displaying, on a user interface of a computing device in communicative connection with the process control system, a correlation of at least one candidate factor of the set of candidate factors and the predicted fault as a quality prediction graph that indicates an effect, on an overall quality of the process, of adjusting the at least one candidate factor, wherein displaying the correlation of the at least one candidate factor and the predicted fault comprises displaying a time-based correlation of the at least one candidate factor and the predicted fault, the time based correlation further comprising a time indicator marking a time at which the quality prediction graph calculates effects of applying corrective actions; and

automatically implementing adjustments to at least one candidate factor if the effects of applying the corrective actions to improve process quality are within specific thresholds.

2. The method of claim 1, further comprising receiving an indication of a selection of the at least one candidate factor, and wherein displaying the correlation of the at least one candidate factor and the predicted fault is based on the received indication.

3. The method of claim 1, wherein displaying the correlation of the at least one candidate factor and the predicted fault comprises displaying a correlation of more than one candidate factor of the set of candidate factors and the predicted fault.

4. The method of claim 1, further comprising simultaneously displaying the correlation, an indication of each member of the set of candidate factors corresponding to the predicted fault, and a respective contribution of the each member to the predicted fault.

5. The method of claim 1, wherein displaying, on the user interface, the time-based correlation of the at least one candidate factor and the predicted fault comprises:

simultaneously displaying, on the user interface, a first graphical representation corresponding to the predicted fault and a second graphical representation corresponding to the at least one candidate factor,

wherein a particular instance in time as indicated on the first graphical representation is aligned on the user interface with the particular instance in time as indicated on the second graphical representation.

6. The method of claim 5, further comprising indicating the particular instance in time by displaying a common indicator across the first graphical representation and the second graphical representation.

7. The method of claim 5, further comprising aligning the first graphical representation and the second graphical representation according to a common time scale.

8. The method of claim 5, further comprising:

receiving a user indication to modify a view of the first graphical representation; and

based on the user indication, adjusting the view of the first graphical representation and a view of the second graphical representation, including preserving a time alignment between the view of the first graphical representation and the view of the second graphical representation displayed on the user interface.

9. The method of claim 5, further comprising displaying at least one detail corresponding to a point included on the first graphical representation or included on the second graphical representation, the displaying the at least one detail occurring in response to a user selection of the point or a user mouse-over of the point.

10. The method of claim 1, wherein obtaining the value associated with the particular factor corresponding to the process comprises obtaining a value of a particular measured variable corresponding to the process.

11. The method of claim 1, wherein obtaining the value associated with the particular factor corresponding to the process comprises obtaining a value of a calculation based on a value of a parameter corresponding to the process.

12. The method of claim 11, wherein obtaining the value of the calculation based on the value of the parameter comprises at least one of:

obtaining a value corresponding to a change to a mean value corresponding to the parameter,

obtaining a value corresponding to a change to a standard deviation corresponding to the parameter, or

obtaining a value corresponding to a shift of a frequency of oscillation of values of the parameter.

13. An apparatus for correlating candidate factors contributing to a predicted fault in a process control system, comprising:

a computing device in communicative connection a batch data receiver, the batch data receiver communicatively coupled to the process control system and configured to receive a value associated with a particular factor corresponding to a process controlled by the process control system, the computing device including a processor and a memory, and the memory storing computer-executable instructions that are executable by the processor to;

predict a fault occurring in the process control system when at least one of;

a predicted quality of the process passes a first threshold, the predicted quality of the process determined based on the value associated with the particular factor, or

a variation of the value of the particular factor passes a second threshold;

determine a set of candidate factors, the set of candidate factors including the particular factor;

cause a representation of a correlation between the predicted fault and at least one candidate factor of the set of candidate factors to be displayed on a user interface within a quality prediction graph that indicates an effect, on an overall quality of the process, of adjusting the at least one candidate factor, wherein displaying the correlation of the at least one candidate factor and the predicted fault comprises displaying a time-based correlation of the at least one candidate factor and the predicted fault, the time based correlation further comprising a time indicator marking a time at which the quality prediction graph calculates effects of applying corrective actions; and

automatically implementing adjustments to at least one candidate factor if the effects of applying the corrective actions to improve process quality are within specific thresholds.

14. The apparatus of claim 13, further comprising additional computer-executable instructions stored on the memory of the computing device and executable by the processor to receive an indication of a selection of the at least one candidate factor.

15. The apparatus of claim 13, wherein the at least one candidate factor comprises more than one candidate factor.

16. The apparatus of claim 13, wherein the representation of the correlation between the predicted fault and the at least one candidate factor comprises:

a first graph corresponding to the predicted fault; and

a second graph corresponding to the at least one candidate factor, the second graph caused to be simultaneously displayed on the user interface with the first graph,

wherein a time axis of the first graph and a time axis of the second graph are presented, on the user interface, in alignment across a displayed time interval.

17. The apparatus of claim 16, wherein the representation of the correlation further comprises an indicator of a particular instance in time, the indicator being displayed across the first graph and the second graph.

18. The apparatus of claim 17, wherein the indicator of the particular instance in time is moveable across the displayed time interval.

19. The apparatus of claim 16, further comprising additional computer-executable instructions stored on the memory of the computing device and executable by the processor to cause a presentation of a modification to the representation of the correlation between the predicted fault and at least one candidate factor displayed on the user interface, the modification including:

a first adjustment to one of the first graph or the second graph, the first adjustment based on a user indication and including a modification to the displayed time interval; and

a second adjustment to the other one of the first graph or the second graph, the second adjustment based on the first adjustment and corresponding to the modification of the displayed time interval.

20. The apparatus of claim 16, wherein:

the at least one candidate factor comprises more than one candidate factor,

the representation of the correlation between the predicted fault and the more than one candidate factor comprises the first graph corresponding to the predicted fault and a respective graph corresponding to each candidate factor of the more than one candidate factor, wherein each respective graph is caused to be simultaneously presented on the user interface with the first graph.

21. The apparatus of claim 13, wherein the particular factor is a particular measured variable.

22. The apparatus of claim 21, wherein the value associated with the particular measured variable is a value of the particular measured variable.

23. The apparatus of claim 21, wherein the value associated with the particular measured variable is a value of a calculation based on a value of the particular measured variable and comprising at least one of:

a calculation of a shift of a mean value, a calculation of a shift of a standard deviation, or a calculation of a shift of a frequency of oscillation.