Application of abnormal event detection (AED) technology to polymers process

• US 20080097637A1
• Filed: 03/16/2007
• Published: 04/24/2008
• Est. Priority Date: 03/21/2006
• Status: Active Grant

• Current Assignee: ExxonMobil Research & Engineering Company (Exxon Mobil Corporation)
• Original Assignee: ExxonMobil Research & Engineering Company (Exxon Mobil Corporation)
• Inventors: Nguyen, Anh, Vercher, Stephen, Woo, Stephen, Emigholz, Kenneth, Orsak, Steven, Alagappan, Perry
• Granted Patent: US 7,761,172 B2
• Time in Patent Office: Days
• US Class Current: 700/110
• CPC Class Codes: G05B 17/02 electric
• 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

The present invention is a method and system for detecting an abnormal event for process units of a Polymers Unit. The method compares the operation of the process units to statistical, engineering or heuristic models. The statistical models are developed by principle components analysis of the normal operation for these units. In addition, the engineering models are based on correlation analysis between variables or simple engineering calculations. If the difference between the operation of a process unit and the normal model result indicates an abnormal condition, then the cause of the abnormal condition is determined and corrected.

Claims

1. A method for abnormal event detection (AED) for Polymers Process comprising:

(a) comparing online measurements from the process units to a set of models for normal operation of the corresponding process units,

(b) determining if the current operation differs from expected normal operations so as to indicate the presence of an abnormal condition in a process unit,

(c) assisting the process operator to determine the underlying cause of an abnormal condition in the Polymers Process, and

(d) performing corrective action to return the unit to normal operation.

2. The method of claim 1 wherein said set of models correspond to equipment groups and operating modes, one model for each group which may include one or more operating mode.

3. The method of claim 1 wherein said set of models correspond to equipment groups and process operating modes, one model for each group and each mode.

4. The method of claim 2 wherein said equipment groups include all major material and energy interactions in the same group.

5. The method of claim 4 wherein said equipment groups include quick recycles in the same group.

6. The method of claim 5 wherein said set of models of normal operations include principle component models.

7. The method of claim 6 wherein set of models of normal operations includes engineering models.

8. The method of claim 1 wherein said set of models of normal operation for each process unit is either a Principle Components model, or an engineering model, or an heuristic model.

9. The method of claim 1 wherein said model of normal operation for each process unit is determined using principle components analysis (PCA), correlation-based engineering models, or heuristic models.

10. The method of claim 9 wherein said Polymers Process areas are decomposed into eleven abnormality monitors.

11. The method of claim 1 wherein said process units are divided into operational sections of the Polymer Process system.

12. The method of claim 11 wherein there are nine operational sections.

13. The method of claim 11 wherein the nine operational sections comprises of nine operation sections—

the catalyst preparation area (Cat Prep), reactors (RX), recycle gas compressors, recycle gas recovery system, the dryers, two granule areas and two extruders system.

14. The method of claim 9 wherein each of the abnormality monitors generates a continuous signal indicating the probability of an abnormal condition in the area.

15. The method of claim 9 wherein said models include process variables values measured by sensors.

16. The method of claim 9 wherein said principle components of models for different process units include some process variable values measured by the same sensor.

17. The method of claim 13 wherein said model further identifies the consistency or relationship between tags around a specific unit, catalyst, reactors, dryers, recycle area, and valves/flows, to indicate any early breakdown in the relationship pattern.

18. The method of claim 17 wherein said model further comprises suppressing model calculations to eliminate false positives on special cause operations.

19. The method of claim 9 wherein (a) determining said model begins with a rough model based on questionable data, (b) using said rough model to gather high quality training data, and improve the model, and (c) repeating step (b) to further improve the model.

20. The method of claim 19 wherein said training data includes historical data for the model of the processing unit.

21. The method of claim 20 wherein said model includes transformed variables.

22. The method of claim 21 wherein said transformed variables include reflux to feed ratio in distillation columns, log of composition in high purity distillation, pressure compensated temperature measurement, sidestream yield, flow to valve position, and reaction rate to exp (temperature).

23. The model of claim 19 wherein some pairs of measurements for two variables are brought into time synchronization by one of the variables using a dynamic transfer function.

24. The model of claim 20 wherein variables of process measurements that are affected by operating point changes in process operations are converted to deviation variables by subtracting the moving average.

25. The method of claim 20 wherein said model is corrected for noise.

26. The method of claim 25 wherein said model is corrected by filtering or eliminating noisy measurements of variables.

27. The method of claim 20 wherein the measurements of a variable are scaled.

28. The method of claim 27 wherein the measurements are scaled to the expected normal range of that variable.

29. The method of claim 4 where a list of abnormality monitors automatically identified, isolated, ranked and displayed for the operator.

30. The method of claim 9 where the operator is presented with diagnostic information at different levels of detail to aid in the investigation of the event.

31. The method of claim 20 wherein the number of principle components is chosen such that coefficients of the principle component become about equal in size.

32. The method of claim 4 wherein said Principle Components include process variables provided by online measurements.

33. The model of claim 32 wherein some measurement pairs are time synchronized to one of the variables using a dynamic filter.

34. The model of claim 32 wherein the process measurement variables affected by operating point changes in the process operations are converted to deviation variables.

35. The method of claim 32 wherein the number of principle components is selected by the magnitude of total process variation represented by successive components.

50. The method of claim 1 wherein said polymer process is a polyolefin process.

51. The method of claim 50 wherein said polyolefin process is a polyethylene or polypropylene process or a combination thereof.

36. A system for abnormal event detection (AED) for some of the Polymers Process units comprised of:

(a) a set of models for the process units describing operations of the process units,

(b) a display which indicates if the current operation differs from expected normal operations so as to indicate the presence of an abnormal condition in the process unit,

(c) a display which indicates the underlying cause of an abnormal condition in the Polymers process unit.

37. The system of claim 36 wherein said model for each process unit is either a Principle Components model or an engineering model or a heuristic model.

38. The system of claim 37 wherein a PP is partitioned into three operational sections with a Principle Components model for each section.

39. The system of claim 38 wherein said Principle Components include process variables provided by online measurements.

40. The system of claim 38 wherein said model further comprises suppressing model calculates to eliminate operator induced notifications and false positives.

41. The system of claim 37 wherein:

(a) deriving said model begins with obtaining an initial model based upon questionable data, (b) use of said initial model to refine the data and improve the model, and (c) iteratively repeating step (b) to improve the model.

42. The system of claim 41 wherein said training data set includes historical data of the processing unit for model development.

43. The system of claim 42 wherein said model includes transformed variables.

44. The system of claim 43 wherein said transformed variables include reflux to total product flow in distillation columns, log of composition and overhead pressure in distillation columns, pressure compensated temperature measurements, flow to valve position and bed differential temperature and pressure.

45. The system of claim 42 wherein some measurement pairs are time synchronized to one of the variables using a dynamic filter.

46. The system of claim 42 wherein the process measurement variables affected by operating point changes in the process operations are converted to deviation variables.

47. The system of claim 42 wherein the measurements of a variable are scaled prior to model identification.

48. The system of claim 47 wherein the measurements are scaled by the expected normal range of that variable.

49. The system of claim 42 wherein the number of principle components is selected by the magnitude of total process variation represented by successive components.

52. The system of claim 36 wherein said polymer process is a polyolefin process.

53. The system of claim 52 wherein said polyolefin process is a polyethylene or polypropylene process or a combination thereof.

54. The system of claim 36 wherein said set of models include the automatic detection of grade switches, grade transitional duration and the automatic suppression of models during transitional duration.

55. The system of claim 36 wherein said system includes the automatic switching of on-line models.

56. The system of claim 36 wherein said set of models include different models for different family of grades.