METHOD AND SYSTEM FOR DETECTING ABNORMAL OPERATION IN A HYDROCRACKER

• US 20080082308A1
• Filed: 09/27/2007
• Published: 04/03/2008
• Est. Priority Date: 09/28/2006
• Status: Active Grant

• Current Assignee: Fisher-Rosemount Systems Incorporated (Emerson Electric Company)
• Original Assignee: Fisher-Rosemount Systems Incorporated (Emerson Electric Company)
• Inventors: Miller, John P., Kant, Ravi, Nguyen, Tautho H.
• Granted Patent: US 8,010,292 B2
• Time in Patent Office: Days
• US Class Current: 703/12
• CPC Class Codes: G05B 23/021 adopting a different treatment of each operating region or a different mode of the monitored system, e.g. transient modes; different operating configurations of monitored 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

Abstract

A system and method for detecting abnormal operation of a hydrocracker includes a model to model the hydrocracker. The model may be configurable to include one or more regression models corresponding to different operating regions of the portion of the hydrocracker. The system and method may also determine if a monitored temperature difference variable deviates significantly from the temperature difference variable predicted by the model. If there is a significant deviation, this may indicate an abnormal operation.

Claims

1. A method of detecting an abnormal operation of a hydrocracker, comprising:

collecting first data sets for the hydrocracker while the hydrocracker is in an operating region, the first data sets generated from a temperature difference variable between a first cross section in a reactor of the hydrocracker and a second cross section in the reactor of the hydrocracker in the operating region and from a load variable of the hydrocracker in the operation region;

generating a regression model of the hydrocracker in the operating region using the first data sets;

generating a prediction of first data generated from the temperature difference variable as a function of second data generated from the load variable using the regression model; and

determining if a corresponding signal generated from the temperature difference variable deviates from the prediction of the first data generated from the temperature difference variable to detect an abnormal situation within the hydrocracker.

2. The method of claim 1, wherein generating a regression model of the hydrocracker in the operating region comprises generating the regression model of the hydrocracker in the operating region to model the temperature difference variable as a function of the load variable.

3. The method of claim 1, wherein the temperature difference variable comprises a temperature difference between a weighted average temperature at the first cross section in the reactor of the hydrocracker and a weighted average temperature at the second cross section in the reactor of the hydrocracker.

4. The method of claim 1, wherein collecting the first data sets comprise at least one of collecting samples of the temperature difference variable and samples of the load variable, collecting processed samples of the temperature difference variable and processed samples of the load variable, and collecting statistical data generated from samples of the temperature difference variable and statistical data generated from samples of the load variable.

5. The method of claim 1, wherein generating a prediction of the first data generated from the temperature difference variable as a function of second data generated from the load variable using the first regression model comprises generating a prediction of a sample of the temperature difference variable as a function of a sample of the load variable using the first regression model.

6. The method of claim 1, wherein generating a prediction of the first data generated from the temperature difference variable as a function of second data generated from the load variable using the first regression model comprises generating a prediction of a mean of the temperature difference variable as a function of a mean of the load variable using the first regression model.

7. The method of claim 1, wherein determining if a corresponding signal generated from the temperature difference variable deviates from the prediction of the first data generated from the temperature difference variable to detect an abnormal situation within the hydrocracker comprises determining if the corresponding signal generated from the temperature difference variable deviates from the prediction of the first data generated from the temperature difference variable by a threshold.

8. The method of claim 7, wherein the threshold is at least one of a percentage of the prediction of the temperature difference variable and a number of standard deviations of the prediction of the temperature difference variable.

9. The method of claim 8, further comprising modeling the standard deviation of the prediction of the temperature difference variable as a function of the load variable.

10. The method of claim 8, further comprising calculating the standard deviation of the prediction of the temperature difference variable from a variance of residuals in the first data sets.

11. A method of detecting an abnormal operation of a hydrocracker, comprising:

collecting a plurality of first data sets for the hydrocracker while the hydrocracker is in an operating region, each of the plurality of first data sets generated from a corresponding temperature difference variable between cross sections in a reactor of the hydrocracker in the operating region and from a load variable of the hydrocracker in the operating region;

generating a regression model of the hydrocracker in the operating region for each temperature difference variable using the plurality of first data sets;

generating a prediction of first data generated from each of the temperature difference variables as a function of second data generated from the load variable using the regression models; and

determining if a corresponding signal generated from at least one of the temperature difference variables deviates from the prediction of the first data generated from the corresponding temperature difference variable to detect an abnormal situation within the hydrocracker.

12. The method of claim 11, wherein the temperature difference variables comprise differences between weighted average temperatures at cross sections in the reactor of the hydrocracker.

13. The method of claim 11, wherein determining if a corresponding signal generated from at least one of the temperature difference variables deviates from the prediction of the first data generated from the corresponding temperature difference variable to detect an abnormal situation within the hydrocracker comprises determining if the corresponding signal generated from the at least one of the temperature difference variables deviates from the prediction of the first data generated from the corresponding temperature difference variable by a threshold.

14. The method of claim 13, wherein determining if the corresponding signal generated from the at least one of the temperature difference variables deviates from the prediction of the first data generated from the corresponding temperature difference variable by a threshold comprises determining if the corresponding signal generated from each of the at least one of the temperature difference variables deviates from the prediction of the first data generated from the corresponding temperature difference variable by a threshold corresponding to the temperature difference variable.

15. The method of claim 13, wherein the threshold is at least one of a percentage of the prediction of first data generated from each of the temperature difference variables and a number of standard deviations of the prediction of first data generated from each of the temperature difference variables.

16. A method of facilitating detection of an abnormal operation of a hydrocracker, comprising:

collecting first data sets generated from a temperature difference variable between a first cross section in a reactor of the hydrocracker and a second cross section in the reactor of the hydrocracker while the hydrocracker is in a first operating region and generated from a load variable of the hydrocracker while the hydrocracker is in the first operating region;

generating a first regression model of the process in the first operating region using the first data sets;

determining a first range in which the first regression model is valid;

generating a model of the hydrocracker to include the first regression model;

collecting second data sets generated from the temperature difference variable between the first cross section in a reactor of the hydrocracker and the second cross section in the reactor of the hydrocracker while the hydrocracker is in a second operating region and generated from a load variable of the hydrocracker while the hydrocracker is in the second operating region;

generating a second regression model of the hydrocracker in the second operating region using the second data sets;

determining a second range in which the second regression model is valid; and

revising the model of the hydrocracker to include the first regression model for the first range and the second regression model for the second range.

17. The method of claim 16, further comprising:

prior to collecting the second data sets, receiving a data set outside of the first range; and

generating an indicator that the received data set is outside of a valid range of the hydrocracker model;

wherein collecting the second data sets comprises collecting the second data sets in response to receiving an authorization.

18. The method of claim 17, wherein the authorization comprises an authorization to train the model for the second operating region.

19. The method of claim 18, wherein the authorization comprises an authorization to begin monitoring the hydrocracker;

wherein generating the second regression model comprises generating the second regression model in response to receiving the authorization to begin monitoring the hydrocracker after receiving authorization to train the model.

20. The method of claim 17, further comprising revising the model in response to receiving the authorization.

21. The method of claim 17, wherein the authorization comprises a user authorization.

22. A system for detecting an abnormal operation in a hydrocracker in a process plant, comprising:

a configurable model of the hydrocracker in the process plant, the configurable model including a first regression model in a first range corresponding to a first operating region of the hydrocracker, the configurable model capable of being subsequently configured to include a second regression model in a second range corresponding to a second operating region different than the first operating region, wherein the configurable model is capable of generating a prediction of a temperature difference variable value as a function of a load variable value, wherein the temperature difference variable value is generated from a temperature difference between a first cross section in a reactor of the hydrocracker and a second cross section in the reactor of the hydrocracker; and

a deviation detector coupled to the configurable model, the deviation detector configured to determine if the temperature difference variable value differs from the predicted temperature difference variable value by comparing a difference between the temperature difference variable value and predicted temperature difference variable value to a threshold.

23. The system of claim 22 wherein, after the configuration model is configured to include the second regression model, the configurable model is capable of:

generating the prediction of the temperature difference variable value using the first regression model if the load variable value is in the first range,

generating the prediction of the temperature difference variable value using the second regression model if the load variable value is in the second range.

24. A system for detecting an abnormal operation in a hydrocracker in a process plant, comprising:

a configurable model of the hydrocracker in the process plant, the configurable model including a regression model in a range corresponding to an operating region of the hydrocracker, wherein the configurable model is capable of generating a prediction of a temperature difference variable value as a function of a load variable value, wherein the temperature difference variable value is generated from a temperature difference between a first cross section in a reactor of the hydrocracker and a second cross section in the reactor of the hydrocracker;

a deviation detector coupled to the configurable model, the deviation detector configured to determine if the temperature difference variable value differs from the predicted temperature difference variable value by comparing a difference between the temperature difference variable value and predicted temperature difference variable value to a threshold; and

an integration application stored on a computer readable memory and adapted to be executed on a processor to create a representation of the hydrocracker for use in viewing the temperature difference variable value and for use in viewing an indication of an abnormal operation of the hydrocracker in response to comparing the difference between the temperature difference variable value and the predicted temperature difference variable value to a threshold.

25. The system of claim 24 wherein the configurable model includes a plurality of regression models in the range corresponding to the operating region of the hydrocracker, wherein the configurable model is capable of generating a plurality predictions of temperature difference variable values each as a function of the load variable value, wherein each temperature difference variable value is generated from a corresponding temperature difference between cross sections in a reactor of the hydrocracker;

wherein the deviation detector is configured to determine if at least one of the temperature difference variable values differs from the corresponding predicted temperature difference variable value by comparing a difference between the at least one of the temperature difference variable values and the corresponding predicted temperature difference variable value to a threshold;

wherein the integration application is configured to create an indication of an abnormal operation of the hydrocracker if a difference between at least one of the temperature difference variable values and the corresponding predicted temperature difference variable value exceeds the threshold and generates an identification of the temperature difference variable causing the abnormal operation.