Automatically optimized combustion control

• US 5,993,194 A
• Filed: 06/21/1996
• Issued: 11/30/1999
• Est. Priority Date: 06/21/1996
• Status: Expired due to Term

• Current Assignee: Jerome H. Lemelson, John H. Hiett, Robert D. Pedersen
• Original Assignee: Jerome H. Lemelson, John H. Hiett, Robert D. Pedersen
• Inventors: Lemelson, Jerome H., Hiett, John H., Pedersen, Robert D.
• Primary Examiner(s): Jones, Larry
• Application Number:
  US08/668,383
• Time in Patent Office: 1,257 Days
• Field of Search: 431/75, 431/14, 431/76, 431/78.79, 395/22, 395/24, 395/900, 382/1, 382/100, 356/45, 356/418, 358/100, 364/148.02, 706/23, 706/16
• US Class Current: 431/14
• CPC Class Codes: F23N 2223/52 Fuzzy logic
• CPC Class Codes: F23N 2229/20 Camera viewing
• CPC Class Codes: F23N 5/082 using electronic means
• CPC Class Codes: Y02T 50/60 Efficient propulsion technologies, e.g. for aircraft

Abstract

Systems and methods are disclosed that optimize the combustion process in various reactors, furnaces, and internal combustion engines. Video cameras are used to evaluate the combustion flame grade. Depending on the desired form, standard or special video devices, or beam scanning devices, are used to image the combustion flame and by-products. The video device generates and outputs image signals during various phases of, and at various locations in, the combustion process. Other forms of sensors monitor and generate data signals defining selected parameters of the combustion process, such as air flow, fuel flow, turbulence, exhaust and inlet valve openings, etc. In a preferred form, a neural networks initially processes the image data and characterizes the combustion flame. A fuzzy logic controller and associated fuzzy logic rule base analyzes the image data from the neural network, along with other sensor information. The fuzzy logic controller determines and generates control signals defining adjustments necessary to optimize the combustion process.

Claims

1. A method for monitoring and controlling parameters of a combustion process comprising the acts of:

(a) directing a scanning device at the combustion process;

(b) activating the scanning device to scan the combustion process and generate a scanning output signal that varies in accordance with variations in the combustion process;

(c) operating additional sensors to monitor other parameters of the combustion process and to generate sensor outputs that vary in accordance with variations in the combustion process;

(d) inputting the scanning output signal to a computer processor having at least a part thereof configured as a neural network;

(e) operating the neural network to process the scanning output signal and to generate a combustion classification signal defining a parameter of the combustion process;

(f) inputting the combustion classification signal and the sensor outputs to a decision analysis computer having at least a part thereof configured as a fuzzy logic controller with associated fuzzy inference rules defining combustion control actions depending on various combinations of sensor outputs and flame grade classification;

(g) operating the decision analysis computer to;

(i) analyze the combustion classification signal and sensor outputs in accordance with the fuzzy inference rules to determine appropriate combustion control actions to optimize the combustion process depending on various combinations of the sensor outputs and combustion classification signals; and

(ii) generate combustion control signals defining adjustments to at least one combustion parameter; and

(i) applying the combustion control signals to adjust at least one combustion parameter.

2. The method of claim 1 wherein the scanning device is a video camera.

3. The method of claim 2 wherein the video camera is CCD camera.

4. The method of claim 1 wherein the scanning device is a beam scanner.

5. The method of claim 1 wherein the scanning device is laser scanner and an associated detector.

6. The method of claim 1 further comprising:

(a) directing at least one additional scanning device at the combustion process;

(b) activating the additional scanning device to scan the combustion process and generate an additional scanning output signal that varies in accordance with variations in the combustion process;

(c) inputting the additional scanning output signal to a scanning computer processor configured to analyze scanning data; and

(d) operating the scanning computer processor to analyze the scanning data and to generate scanning output signals characterizing a parameter of the combustion process;

(e) inputting the scanning output signal to the decision analysis computer;

(f) operating the decision analysis computer to additionally analyze the scanning output signal.

7. The method of claim 6 wherein the additional scanning device is infrared camera.

8. The method of claim 6 wherein the additional scanning device is a spectral photodetector.

9. The method of claim 8 wherein the scanning computer processor is a spectral analyzer.

10. The method of claim 1 wherein the act of operating additional sensors to monitor other parameters of the combustion process and to generate sensor outputs that vary in accordance with variations in the combustion process, includes the acts of:

(a) positioning a temperature sensor so that it can sense the temperature of at least one parameter of the combustion process;

(b) activating the temperature sensor; and

(c) generating an output signal indicative the sensed temperature.

11. The method of claim 10 wherein the act of positioning a temperature sensor so that it can sense the temperature of at least one parameter of the combustion process includes the act of mounting the sensor proximate the combustion flame.

12. The method of claim 10 wherein the act of positioning a temperature sensor so that it can sense the temperature of at least one parameter of the combustion process includes the act of mounting the sensor proximate the combustion exhaust.

13. The method of claim 1 wherein the act of operating additional sensors to monitor other parameters of the combustion process and to generate sensor outputs that vary in accordance with variations in the combustion process, includes the acts of:

(a) positioning a pressure sensor so that it can sense the pressure of at least one parameter of the combustion process;

(b) activating the pressure sensor; and

(c) generating an output signal indicative the sensed pressure.

14. The method of claim 13 wherein the act of positioning the pressure sensor so that it can sense the pressure of at least one parameter of the combustion process includes the act of mounting the sensor in the combustion exhaust.

15. The method of claim 13 wherein the act of positioning the pressure sensor so that it can sense the pressure of at least one parameter of the combustion process includes the act of mounting the sensor proximate the combustion flame.

16. The method of claim 1 wherein the act of operating the neural network to process the scanning output signal and to generate a combustion classification signal defining the combustion process includes the acts of:

(a) processing the scanning output signal in first and second hidden layers of parallel processing elements, which elements are weighted and trained to recognize different flame classification grades; and

(b) generating an output signal that defines a flame grade classification for the combustion process at the time it was scanned.

17. The method of claim 16 wherein the act of processing the scanning output signal includes analyzing the combustion flame core.

18. The method of claim 16 wherein the act of processing the scanning output signal includes analyzing the combustion fireball.

19. The method of claim 16 wherein the act of processing the scanning output signal includes analyzing the combustion flame propagation over a period of time.

20. The method of claim 1 wherein the act of operating the decision analysis computer to analyze the combustion classification signal and sensor outputs and to generate combustion control signals and includes the acts of:

(a) programming the decision analysis computer as a fuzzy logic controller with associated fuzzy inference rules established to monitor and adjust a ratio of air to fuel for the combustion process within a predetermined range;

(b) operating the decision analysis computer to evaluate the combustion classification and sensor outputs in accordance with the programmed fuzzy inference rules to determine whether the ratio of air to fuel needs to be changed to optimize combustion process while also minimizing pollutants, and if so, the amount that the ratio needs to be changed; and

(c) operating the decision analysis computer to generate combustion control signals defining required changes to the air-to-fuel ratio.

21. The method of claim 20 wherein the act of operating the decision analysis computer to generate combustion control signals defining required changes to the air-to-fuel ratio includes generating signals that alter the flow of air so that it is maintained within a range of defined by a preset minimum and a preset maximum.

22. The method of claim 20 wherein the act of operating the decision analysis computer to generate combustion control signals defining required changes to the air-to-fuel ratio includes generating signals that alter the flow of fuel so that it is maintained within a range defined by a preset minimum and a preset maximum.

23. The method of claim 20 wherein the act of operating the decision analysis computer to generate combustion control signals defining required changes to the air-to-fuel ratio includes generating signals that maintain the air-to-fuel ration with a range defined by a preset minimum and a preset maximum.

24. The method of claim 23 wherein both the flow of air and the flow of fuel are changed within defined minimum and maximum values.

25. The method of claim 1 further comprising the acts of mounting the scanning device on a moveable implement, and controlling the moveable implement so that the scanning device scans different parts of the combustion process.

26. The method of claim 1 wherein the acts of directing and activating the scanning device to scan the combustion process and generate a scanning output signal includes the acts of:

(a) directing a laser beam at particles of matter produced in the combustion process;

(b) photoelectrically detecting spectral radiation generated as the laser beam scans the particles of matter; and

(c) generating the scanning output signal so that it varies in accordance with detected variations in the spectral radiation as the laser beam scans the particles of matters.

27. The method of claim 1 wherein the acts of directing and activating the scanning device to scan the combustion process and generate a scanning output signal includes the acts of:

(a) directing a laser beam at particles of matter produced in the combustion process;

(b) photoelectrically detecting fluorescent radiation generated as the laser beam scans the particles of matter; and

(c) generating the scanning output signal so that it varies in accordance with detected variations in the fluorescent radiation as the laser beam scans the particles of matters.

28. The method in accordance with claim 1 wherein acts (a) through (g) are conducted intermittently.

29. The method of claim 1 wherein the act of operating the decision analysis computer to analyze the combustion classification signal and sensor outputs and to generate combustion control signals and includes the acts of:

(a) programming the decision analysis computer as a fuzzy logic controller with associated fuzzy inference rules established to monitor and adjust a ratio of air to fuel for the combustion process within a predetermined range designed to both optimize combustion efficiency and minimize resulting pollutants;

(b) operating the decision analysis computer to evaluate the combustion classification and sensor outputs in accordance with the programmed fuzzy inference rules to determine whether the ratio of air to fuel needs to be changed to optimize combustion process while also minimizing pollutants, and if so, the amount that the ratio needs to be changed; and

(c) operating the decision analysis computer to generate combustion control signals defining required changes to the air-to-fuel ratio.

30. The method of claim 29 wherein the act of operating the decision analysis computer to generate combustion control signals defining required changes to the air-to-fuel ratio includes generating signals that control a device for treating pollutants.

31. The method of claim 30 wherein the act of generating signals that control a device for treating pollutants includes generating signals to control a catalytic converter.

32. The method of claim 30 wherein the act of generating signals that control a device for treating pollutants includes generating signals to control a plasma generator.

33. The method of claim 30 wherein the act of generating signals that control a device for treating pollutants includes generating signals to control an ultrasonic generator.

34. The method of claim 30 wherein the act of generating signals that control a device for treating pollutants includes generating signals to control an electrostatic precipitator.

35. A method for controlling a combustion process in a reaction chamber comprising:

(a) scanning the combustion flame and generating scanning signals that vary with variations in the combustion flame;

(b) detecting spectral radiation emitted by the combustion process, and generating variable spectral information signals which vary with time,

(c) inputting the scanning signals and spectral information signals to a decision analysis computer having at least a part thereof configured as a fuzzy logic controller with associated fuzzy inference rules defining combustion control actions depending on various combinations of sensor outputs and flame grade classification;

(d) operating the decision analysis computer to;

(i) analyze the scanning signals and spectral information signals in accordance with the fuzzy inference rules to determine appropriate combustion control actions to optimize the efficiency of the combustion process and reduce pollutants; and

(ii) generate combustion control signals defining adjustments to at least one combustion parameter; and

(e) applying the combustion control signals to adjust at least one combustion parameter.

36. A method in accordance with claim 35 wherein the act of detecting spectral radiation emitted by the combustion process includes detecting spectral radiation emitted from matter burning in the combustion process.

37. A method in accordance with claim 35 wherein the act of detecting spectral radiation emitted by the combustion process includes detecting spectral radiation emitted from matter that is not burning in the combustion process.

38. A system for monitoring and controlling parameters of a combustion process taking place within a combustion chamber, comprising:

(a) a scanning device mounted proximate to the combustion chamber in a manner so that it is capable of scanning the combustion process, the scanning device including a detection circuit coupled to an output circuit, and configured to generate electrical scanning signals on the output circuit that vary with variations in the combustion process;

(b) a control circuit coupled to the scanning device and including an initiation circuit that activates the scanning device to begin scanning the combustion;

(c) a plurality of additional sensors configured to monitor other parameters of the combustion process, each sensor including an output circuit that generates sensor outputs that vary in accordance with variations in sensed parameters of the combustion process;

(d) a computer processor having (i) an input coupled to the output of the scanning device, (ii) logic configured as a neural network, and (iii) memory storing a program that, when executed by the network, processes the scanning output signal to generate a combustion classification signal defining a parameter of the combustion process;

(e) a decision analysis computer having (i) an input coupled to the computer processor that receives the combustion classification signals;

(ii) logic configured as a fuzzy controller;

(iii) memory storing a fuzzy inference rule program that, when executed by the fuzzy controller, analyzes the combustion classification signals and the sensor outputs to determine and generate combustion control signals defining combustion control actions that vary depending on various combinations of sensor outputs and flame grade classification;

(f) a plurality of combustion control devices configured to vary parameters of the combustion process, each combustion control device including a signal input; and

(g) wherein the decision analysis computer includes an output coupled to the inputs of the combustion control devices and is configured to communicate the combustion control signals from the fuzzy controller to the combustion control devices to adjust combustion parameters and optimize the combustion process.