ADAPTIVE CONTROLLER AND EXPERT SYSTEM FOOD PROCESSING

• US 20080274240A1
• Filed: 05/03/2007
• Published: 11/06/2008
• Est. Priority Date: 05/03/2007
• Status: Abandoned Application

• Current Assignee: American Air Liquide Incorporated (L'Air Liquide SA)
• Original Assignee: American Air Liquide Incorporated (L'Air Liquide SA)
• Inventors: Paganessi, Joseph E., Germouni, Omar, Yuan, James T.C.
• Application Number:
  US11/744,077
• Publication Number:
  US 20080274240A1
• Time in Patent Office: Days
• US Class Current: 426/231
• CPC Class Codes: G01N 33/02 Food
• CPC Class Codes: G05B 13/028 using expert systems only
• CPC Class Codes: G06N 3/042 Knowledge-based neural networks; Logical representations of neural networks

Abstract

A method and apparatus for controlling efficacy of a food processing system. The method includes, responsive to receiving set points from an automatic expert system, operating an adaptive controller to perform steps including comparing the set points from the automatic expert system to process variables for the food processing system. The steps also include generating an error signal indicating a difference between the compared process variables and the set points and adjusting control settings for the food processing system using the error signal and one or more control parameters. The adaptive controller is configured to automatically modify the control parameters in response to a detected change in at least one of the set points and the process variables.

Claims

1. A method of controlling efficacy of a food processing system, the method comprising:

responsive to receiving set points from an automatic expert system, operating an adaptive controller to perform steps comprising;

comparing the set points from the automatic expert system to process variables for the food processing system;

generating an error signal indicating a difference between the compared process variables and the set points; and

adjusting control settings for the food processing system using the error signal and one or more control parameters, wherein the adaptive controller is configured to automatically modify the control parameters in response to a detected change in at least one of the set points and the process variables.

2. The method of claim 1, wherein the one or more control parameters includes a gain, a time constant, and a delay for the adaptive controller.

3. The method of claim 2, wherein the gain for the adaptive controller is calculated as a function of a relationship between one or more manipulated variables and one or more control variables.

4. The method of claim 1, wherein adjusting the control settings for the food processing system comprises performing at least three step changes to the control settings.

5. The method of claim 4, wherein the at least three step changes correspond to an upper operating range, middle operating range, and lower operating range for the control settings for the food processing system.

6. The method of claim 1, wherein the process variables include a pressure variable, temperature variable, solubility variable, fluid density variable, and residence time variable for the food processing system.

7. The method of claim 1, wherein the control settings modify at least one of a food flow rate, a reagent flow rate, and a heating fluid flow rate.

8. The method of claim 1, wherein the automatic expert system is configured to provide subsequent set points to the adaptive controller only after the process variables for the food processing system have reached a steady state and quality variables become available through an instrumented system downstream of the food processing system.

9. An adaptive controller configured to control efficacy of a food processing system, the controller comprising:

a computer readable storage medium including a plurality of instructions;

a processor, which, when executing the plurality of instructions, is configured to;

receive set points from an automatic expert system;

compare the set points from the automatic expert system to process variables for the food processing system, wherein comparing comprises generating an error signal indicating a difference between the process variables and the set points; and

adjust control settings for the food processing system using the error signal and one or more control parameters, wherein the adaptive controller is configured to automatically modify the control parameters in response to a detected change in at least one of the set points and the process variables.

10. The adaptive controller of claim 9, wherein the one or more control parameters includes a gain, a time constant, and a delay for the adaptive controller.

11. The adaptive controller of claim 10, wherein the gain for the adaptive controller is calculated as a function of a relationship between one or more manipulated variables and one or more control variables.

12. The adaptive controller of claim 9, wherein adjusting the control settings for the food processing system comprises performing at least three step changes to the control settings.

13. The adaptive controller of claim 12, wherein the at least three step changes correspond to an upper operating range, middle operating range, and lower operating range for the control settings for the food processing system.

14. The adaptive controller of claim 9, wherein the process variables include a pressure variable, temperature variable, solubility variable, fluid density variable, and residence time variable for the food processing system.

15. The adaptive controller of claim 9, wherein the control settings modify at least one of a food flow rate, a reagent flow rate, and a heating fluid flow rate.

16. The adaptive controller of claim 9, wherein the automatic expert system is configured to provide subsequent set points to the adaptive controller only after the process variables for the food processing system have reached a steady state and quality variables become available through an instrumented system downstream of the food processing system.

17. A method for generating set points used by an adaptive controller for controlling efficacy of a food processing system, the method comprising:

receiving process variables from the food processing system;

comparing the process variables from the food processing system to quality control metrics derived from the food processing system;

based upon a comparison of the process variables and the quality control metrics, generating the set points used by the adaptive controller for controlling the food processing system; and

providing the set points to the adaptive controller.

18. The method of claim 17, wherein the process variables include a pressure variable, temperature variable, solubility variable, fluid density variable, and residence time variable for the food processing system.

19. The method of claim 17, wherein the quality control metrics include at least one of a pH metric and microbiological data provided by an instrumented system downstream of the food processing system.

20. The method of claim 19, wherein the microbiological data includes a bacteria kills metric.

21. The method of claim 17, further comprising:

providing subsequent set points to the adaptive controller only after the process variables for the food processing system have reached a steady state and quality variables become available through an instrumented system downstream of the food processing system.

22. The method of claim 17, wherein comparing the process variables to quality control metrics and generating the set points comprises:

providing the process variables and quality control metrics to a neural network configured to perform the comparison of the process variables and quality control metrics and generate the set points based upon the comparison.

23. The method of claim 22, wherein the neural network includes a plurality of perceptrons arranged as a multilayer network of perceptrons, wherein back-propagation of signals in the multilayer network of perceptrons is used to perform the comparison of the process variables and quality control metrics and generation of the set points based upon the comparison, wherein the quality control metrics includes microbiological data.

24. The method of claim 23, wherein the microbiological data includes bacteria kills.

25. An automatic expert system configured to generate set points used by an adaptive controller for controlling efficacy of a food processing system, comprising:

a computer readable storage medium including a plurality of instructions;

a processor, which, when executing the plurality of instructions, is configured to;

receive process variables from the food processing system;

compare the process variables from the food processing system to quality control metrics derived from the food processing system;

based upon a comparison of the process variables and the quality control metrics, generate the set points used by the adaptive controller for controlling the food processing system; and

provide the set points to the adaptive controller.

26. The automatic expert system of claim 25, wherein the process variables include a pressure variable, temperature variable, solubility variable, fluid density variable, and residence time variable for the food processing system.

27. The automatic expert system of claim 25, wherein the quality control metrics include at least one of a pH metric, and microbiological data provided by an instrumented system downstream of the food processing system.

28. The automatic expert system of claim 27, wherein the microbiological data includes a bacteria kills metric.

29. The automatic expert system of claim 25, wherein the processor is further configured to:

provide subsequent set points to the adaptive controller only after the process variables for the food processing system have reached a steady state and quality variables become available through an instrumented system downstream of the food processing system.

30. The automatic expert system of claim 25, wherein the processor comprises a neural network which is configured to receive the process variables and quality control metrics, wherein the neural network performs the comparison of the process variables and quality control metrics and generates the set points based upon the comparison.

31. The automatic expert system of claim 30, wherein the neural network includes a plurality of perceptrons arranged as a multilayer network of perceptrons, wherein back-propagation of signals in the multilayer network of perceptrons is used to perform the comparison of the process variables and quality control metrics and generation of the set points based upon the comparison.

32. A food processing system, comprising:

a chamber in which food processing is performed;

a plurality of sensors configured to provide process variables for the food processing system;

an automatic expert system configured to;

receive the process variables for the food processing system;

receive quality control metric for the food processing system;

compare the process variables from the food processing system to quality control metrics derived from the food processing system; and

based upon a comparison of the process variables and the quality control metrics, generate the set points used by the adaptive controller for controlling the food processing system; and

an adaptive controller configured to;

receive the set points from the automatic expert system;

compare the set points to the process variables for the food processing system, wherein comparing comprises generating an error signal indicating a difference between the process variables and the set points; and

adjust control settings for the food processing system using the error signal and one or more control parameters, wherein the adaptive controller is configured to automatically modify the control parameters in response to a detected change in at least one of the set points and the process variables.

33. The food processing system of claim 32, wherein the one or more control parameters includes a gain, a time constant, and a delay for the adaptive controller.

34. The food processing system of claim 33, wherein the gain for the adaptive controller is calculated as a function of a relationship between one or more manipulated variables and one or more control variables.

35. The food processing system of claim 32, wherein the process variables include a pressure variable, temperature variable, solubility variable, fluid density variable, and residence time variable for the food processing system.

36. The food processing system of claim 32, wherein the control settings modify at least one of a food flow rate, a reagent flow rate, and a heating fluid flow rate for the chamber in which the food processing system is performed.

37. The food processing system of claim 32, wherein the automatic expert system is configured to provide subsequent set points to the adaptive controller only after the process variables for the food processing system have reached a steady state and quality variables become available through an instrumented system downstream of the food processing system.

38. The food processing system of claim 32, wherein the quality control metrics include at least one of a pH metric and microbiological data provided by an instrumented system downstream of the food processing system.

39. The food processing system of claim 38, wherein the microbiological data includes a bacteria kills metric.

40. The food processing system of claim 32, wherein the automatic expert system comprises a neural network which is configured to receive the process variables and quality control metrics, wherein the neural network performs the comparison of the process variables and quality control metrics and generates the set points based upon the comparison.

41. The food processing system of claim 40, wherein the neural network includes a plurality of perceptrons arranged as a multilayer network of perceptrons, wherein back-propagation of signals in the multilayer network of perceptrons is used to perform the comparison of the process variables and quality control metrics and generation of the set points based upon the comparison.