Monitoring system for an industrial process using one or more multidimensional variables

• US 20030109951A1
• Filed: 06/13/2002
• Published: 06/12/2003
• Est. Priority Date: 03/10/2000
• Status: Active Grant

• Current Assignee: Smiths Detection Incorporated
• Original Assignee: Smiths Detection Incorporated
• Inventors: Steinthal, Michael Gregory, Hsiung, Chang-Meng B., Vicic, Michael Allen, Zhang, Shou-Hua, Sunshine, Steven A., Roy, Ajoy Kumar, Munoz, Bethsabeth
• Granted Patent: US 6,985,779 B2
• Time in Patent Office: Days
• US Class Current: 700/108
• CPC Class Codes: G05B 15/02 electric
• CPC Class Codes: G05B 19/042 using digital processors G05B19/05 takes precedence
• CPC Class Codes: G05B 19/4093 characterised by part programming, e.g. entry of geometrical information as taken from a technical drawing, combining this with machining and material information to obtain control information, named part programme, for the NC machine
• CPC Class Codes: G05B 19/41855 by local area network [LAN], network structure
• CPC Class Codes: G05B 19/41865 characterised by job scheduling, process planning, material flow
• CPC Class Codes: G05B 19/41875 characterised by quality surveillance of production
• CPC Class Codes: G05B 2219/31265 Control process by combining history and real time data
• CPC Class Codes: G05B 2219/31337 Failure information database
• CPC Class Codes: G05B 2219/31435 Paging support with display board, status monitoring and report compiling
• CPC Class Codes: G05B 2219/31457 Factory remote control, monitoring through internet
• CPC Class Codes: G05B 2219/32129 Select program for specified machine from library, file server
• CPC Class Codes: G05B 2219/32194 Quality prediction
• CPC Class Codes: G05B 2219/32196 Store audit, history of inspection, control and workpiece data into database
• CPC Class Codes: G05B 2219/32201 Build statistical model of past normal proces, compare with actual process
• CPC Class Codes: G05B 2219/32404 Scada supervisory control and data acquisition
• CPC Class Codes: G05B 2219/33209 Protocol, mailbox, email, mail system
• CPC Class Codes: G05B 2219/35095 Features library
• 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 23/0235 based on a comparison with predetermined threshold or range, e.g. "classical methods", carried out during normal operation; threshold adaptation or choice; when or how to compare with the threshold
• CPC Class Codes: G05B 23/0243 model based detection method, e.g. first-principles knowledge model
• 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: G05B 23/0286 : Modifications to the monitored process, e.g. stopping operation or adapting control
• CPC Class Codes: G05B 23/0294 : Optimizing process, e.g. process efficiency, product quality
• CPC Class Codes: Y02A 90/10 : Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
• CPC Class Codes: Y02P 90/02 : Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
• CPC Class Codes: Y02P 90/80 : Management or planning

Abstract

A system for monitoring an industrial process and taking action based on the results of process monitoring. Actions taken may include process control, paging, voicemail, and input for e-enterprise systems. The system includes an input module for receiving a plurality of parameters from a process for manufacture of a substance or object. The system also includes a library module. The library module includes a plurality of computer aided processes. Any one of the computer aided processes is capable of using each of the plurality of parameters to compare at least two of the plurality of parameters against a training set of parameters. The training set of parameters is generally predetermined. The computer aided process is also capable of determining if the at least two of the plurality of parameters are within a predetermined range of the training set of parameters. Additionally, the system includes an output module for outputting a result based upon the training set and the plurality of parameters.

Claims

1. A system for monitoring an industrial process, the system comprising a computer program product, the product comprising;

a code directed to accessing a process controller;

a code directed to an input module coupled to code directed to the process controller, the input module code being adapted to input a plurality of parameters from a process for manufacture of a substance;

a code directed to a computer aided process module coupled to the process controller, the computer aided process module code being adapted to compare at least two of the plurality of parameters against a predetermined training set of parameters, and being adapted to determine if the at least two of the plurality of parameters are within a predetermined range of the training set of parameters; and

a code directed to an output module coupled to the process controller, the output module being adapted to output a result based upon the determining step.

2. The system of claim 1 wherein the substance is selected from a petroleum product, a chemical product, a food product, a health product, a cleaning product, a biological product, and other fluid or objects.

3. The system of claim 1 wherein the plurality of parameters are selected from an intrinsic element or an extrinsic element of the process.

4. The system of claim 1 wherein the input module code, the computer aided process module code, and the output module code are provided in a single computer software program.

5. The system of claim 1 wherein the computer aided module code includes an algorithm selected from PCA, HCA, KNN CV KNN Prd, SIMCA CV, SIMCA Prd, Canon Prd, Fisher CV, and SCREAM.

6. The system of claim 1 further comprising a code directed to normalizing coupled to the process controller, the normalizing code being adapted to normalize each of the plurality of parameters before input into the computer aided process module.

7. The system of claim 1 wherein the training step of parameters are preprocessed in at least two of the computer aided processes.

8. The system of claim 1 wherein the result is an affirmative response or a negative response, where the response is displayed on a terminal.

9. The system of claim 1 wherein the computer aided process is selected from a library comprising a plurality of processes.

10. The system of claim 9 wherein the plurality of processes includes at least a comparing process, a contrasting process, and a functional process.

11. A system for monitoring an industrial process for the manufacture of materials or objects, the system comprising a computer code product, the product comprising:

a code directed to an input module, the input module code being adapted to input a plurality of process parameters from a process for manufacture of a substance or object;

a code directed to a library module coupled to the input module code, the library module code including a plurality of computer aided processes, each of the computer aided processes being capable of determining an output based upon a predetermined training set of the plurality of process parameters;

a code directed to an output module coupled to the library module code, the output module code being adapted to output a result based upon the predetermined training set and the plurality of process parameters;

wherein each of the computer aided processes compares at least two of the plurality of process parameters against a portion of the training set of parameters and determines if the at least two of the plurality of process parameters are within a predetermined range of the portion of the training set of parameters.

12. A system for monitoring a process, the system comprising a computer program product, the product comprising:

a code directed to storing a first model in memory;

a code directed to acquiring data from a process;

a code directed to applying the first model to the data to identify a first predicted descriptor characteristic of a state of the process; and

a code directed to consulting a first knowledge based system to provide an output based upon the first predicted descriptor.

13. The product of claim 12 wherein the model is constructed from a mathematical equation describing a physical law.

14. The product of claim 12 further comprising preprocessing the data prior to applying the model.

15. The product of claim 12 wherein the output is communicated to the process to adjust an operational parameter of the process.

16. The product of claim 12 wherein the output is communicated to an operator to permit monitoring of the state of the process.

17. The product of claim 12 wherein the output is resident on a server and accessible to a user over a network of computers utilizing a browser software program.

18. The product of claim 17 wherein the input is acquired from the process over a network of computers

19. The product of claim 12 wherein the input is acquired from the process over a network of computers.

20. The product of claim 12 wherein the output is communicated over a network of computers to an associated system, the associated system including at least one of a legacy system, an e-enterprise system, and a desktop application.

21. The product of claim 12 wherein the first knowledge based system is an expert system.

22. The product of claim 12 further comprising:

a code directed to acquiring initial data from a source at a first time;

a code directed to converting the initial data into electronic form;

a code directed to loading the initial data into memory;

a code directed to retrieving the initial data from memory;

a code directed to acquiring subsequent data from the source at a second time;

a code directed to assigning a first descriptor to the initial data and a second descriptor to the subsequent data;

a code directed to constructing the model based upon the initial data, the subsequent data, the first descriptor, and the second descriptor; and

a code directed to storing the model in memory.

23. The product of claim 22 wherein the model is constructed from at least one of a univariate statistical technique, a multivariate statistical technique, a time series analysis, and a neural-based approach.

24. The product of claim 22 wherein the model is constructed from one of a group of different algorithms or models stored in a library.

25. The product of claim 22 wherein the source is in communication with the process, the initial data and the subsequent data reflecting prior operation of the process.

26. The product of claim 22 wherein the source is in communication with a second process similar to the process, the initial data and the subsequent data reflecting operation of the second process.

27. The product of claim 22 further comprising:

a code directed to constructing a second model;

a code directed to storing the second model in memory;

a code directed to applying the second model to the process data to identify a second predicted descriptor characteristic of the process data; and

a code directed to consulting the knowledge based system to produce the output based on the first predicted descriptor and the second predicted descriptor.

28. The product of claim 27 wherein the second model is constructed based upon the initial data, the subsequent data, the first descriptor, and the second descriptor, such that comparison of the first descriptor and the second descriptor represents a cross-validation.

29. The product of claim 27 wherein the second model is constructed from operation of a second process similar to the process, such that comparison of the first descriptor to the second descriptor represents an external validation.

30. The product of claim 27 wherein the knowledge based system is an expert system.

31. The product of claim 12 further comprising code configured to receive key preliminary information and to communicate the key preliminary information downstream to the code applying the first model, such that the first predicted descriptor reflects the key preliminary information.

32. A method for monitoring a process, the method comprising:

storing a first model in a memory;

acquiring data from a process;

applying the first model to the data to identify a first predicted descriptor characteristic of a state of the process; and

consulting a first knowledge based system to provide an output based upon the first predicted descriptor.

33. The method of claim 32 wherein the model is constructed from a mathematical equation describing a physical law.

34. The method of claim 32 further comprising preprocessing the data prior to applying the model.

35. The method of claim 32 wherein the output is communicated to the process to adjust an operational parameter of the process.

36. The method of claim 32 wherein the output is communicated to a human operator to permit monitoring of the process.

37. The method of claim 32 wherein the output is resident on a server and accessible to a user through a browser software program.

38. The product of claim 37 wherein the input is acquired from the process over a network of computers

39. The product of claim 32 wherein the input is acquired from the process over a network of computers.

40. The method of claim 32 wherein the output is communicated over a network to an associated system, the associated system including at least one of a legacy system, an e-enterprise system, and a desktop application.

41. The method of claim 32 wherein the first knowledge based system is an expert system.

42. The method of claim 32 further comprising:

acquiring initial data from a source at a first time;

converting the initial data into electronic form;

loading the initial data into memory;

retrieving the initial data from memory;

acquiring subsequent data from the source at a second time;

assigning a first descriptor to the initial data and a second descriptor to the subsequent data;

constructing the model based upon the initial data, the subsequent data, the first descriptor, and the second descriptor; and

storing the model in memory.

43. The method of claim 42 wherein the model is constructed from one of a univariate statistical technique, a multivariate statistical technique, and a time series analysis.

44. The method of claim 42 wherein the model is constructed from one of a group of different algorithms stored in a library.

45. The method of claim 42 wherein the source is in communication with the process, the initial data and the subsequent data reflecting prior operation of the process.

46. The method of claim 42 wherein the source is in communication with a second process similar to the process, the initial data and the subsequent data reflecting operation of the second process.

47. The method of claim 42 further comprising:

constructing a second model;

storing the second model in memory;

applying the second model to the process data to identify a second predicted descriptor characteristic of the process data; and

consulting the first knowledge based system to produce the output based upon the first predicted descriptor and the second predicted descriptor.

48. The method of claim 47 wherein the second model is constructed based upon the initial data, the subsequent data, the first descriptor, and the second descriptor, such that comparison of the first descriptor and the second descriptor represents a cross-validation.

49. The method of claim 47 wherein the second model is constructed from operation of a second process similar to the process, such that comparison of the first descriptor to the second descriptor represents an external validation.

50. The method of claim 47 wherein the knowledge based system is an expert system.

51. The method claim 32 further comprising receiving key preliminary information and communicating the key preliminary information downstream to the first model, such that the first predicted descriptor reflects the key preliminary information.

52. A system for controlling a process, the system comprising:

a first field mounted device in communication with a process and configured to produce a first input; and

process manager receiving the first input and configured to apply a first model to the first input to identify a first predicted descriptor characteristic of a state of the process, and configured to consult a first knowledge based system to provide an output based upon the first predicted descriptor.

53. The system of claim 52 wherein the process manager is a server in communication with the first field mounted device via a computer network.

54. The product of claim 52 wherein the process manager is a server in communication with a user through a network of computers utilizing a browser software program.

55. The product of claim 54 wherein the process manager is in communication with the first field mounted device via the computer network.

56. The system of claim 52 further comprising a second field mounted device receiving the output and adjusting an operational parameter of the process according to the output.

57. The system of claim 52 further comprising an interface between the process manager and an associated system including at least one of a legacy system, an e-enterprise system, and a desktop application.

58. The system of claim 52 wherein the first knowledge based system is an expert system.

59. The system of claim 52 wherein the model is constructed utilizing one of a univariate statistical technique, a multivariate statistical technique, a time series analysis, and a neural-based technique.

60. The system of claim 52 further comprising a library configured to store one of a group of different algorithms utilized to construct the first model.

61. The system of claim 52 further comprising a library configured to store one of a group of different algorithms utilized to construct the first model.

62. The system of claim 52 further comprising:

a second model; and

a second knowledge based system, the process manager applying the second model to the data to identify a second predicted descriptor characteristic of the process data, the second knowledge based system submitting one of the first predicted descriptor and the second predicted descriptor to the first knowledge based system where the first predicted descriptor is different from the second predicted descriptor.