Flame detection system

• US 20060017578A1
• Filed: 07/20/2004
• Published: 01/26/2006
• Est. Priority Date: 07/20/2004
• Status: Active Grant

• Current Assignee: MSA Technology, LLC (MSA Safety, Inc.)
• Original Assignee: General Monitors, Inc. (MSA Safety, Inc.)
• Inventors: Shubinsky, Gary D., Baliga, Shankar, Huseynov, Javid J., Boger, Zvi
• Granted Patent: US 7,202,794 B2
• Time in Patent Office: Days
• US Class Current: 340/578
• CPC Class Codes: G08B 17/10 Actuation by presence of smoke or gases , e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means
• CPC Class Codes: G08B 17/12 Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
• CPC Class Codes: G08B 29/26 by updating and storing reference thresholds
• CPC Class Codes: G08B 31/00 Predictive alarm systems characterised by extrapolation or other computation using updated historic data

Abstract

A flame detection system includes a plurality of sensors for generating a plurality of respective sensor signals. The plurality of sensors includes a set of discrete optical radiation sensors responsive to flame as well as non-flame emissions. An Artificial Neural Network may be applied in processing the sensor signals to provide an output corresponding to a flame condition.

Claims

1. A flame detection system, comprising:

a plurality of discrete optical radiation sensors;

means for joint time-frequency signal pre-processing outputs from the plurality of discrete optical radiation sensors to provide pre-processed signals; and

an Artificial Neural Network for processing the pre-processed signals and providing an output indicating a flame condition.

2. The system of claim 1, wherein the flame condition comprises one of the presence of flame, the absence of flame or false alarm.

3. The system of claim 1, wherein the flame condition is one of the presence or absence of flame.

4. The system of claim 1, wherein the plurality of optical radiation sensors comprises an array of discrete sensors.

5. The system of claim 4, wherein the array of discrete sensors are mounted in a unitary housing structure.

6. The system of claim 1, wherein the plurality of discrete optical radiation sensors comprises a 4.9 um sensor, a 2.2 um sensor, a 4.3 um sensor and a 4.45 um sensor.

7. The system of claim 1, wherein the Artificial Neural Network comprises a two-layer Artificial Neural Network.

8. The system of claim 1, wherein said pre-processing means establishes a correlation between frequency and time domain of the outputs from the discrete optical sensors.

9. The system of claim 8, wherein said means for establishing a correlation comprises an electronic signal processor adapted to perform one of Discrete Fourier Transform, Short-Time Fourier Transform with a shifting time window or a Discrete Wavelet Transform.

10. The system of claim 1, further comprising a temperature sensor for sensing a temperature of the system, and said Artificial Neural Network is further responsive to signals indicative of the sensed temperature to provide said output.

11. The system of claim 1, further comprising a vibration sensor for sensing a vibration level experienced by the system, and said Artificial Neural Network is further responsive to signals indicative of the sensed vibration level to provide said output.

12. A flame detection system, comprising:

a plurality of discrete optical radiation sensors; and

an Artificial Neural Network for processing a plurality of signals indicative of outputs from the plurality of sensors and providing an output indicating a flame condition.

13. The system of claim 12, wherein the flame condition comprises one of the presence of flame, the absence of flame or false alarm.

14. The system of claim 12, wherein the flame condition is one of the presence or absence of flame.

15. The system of claim 12, wherein the plurality of optical radiation sensors comprises an array of discrete sensors.

16. The system of claim 15, wherein the array of discrete sensors are mounted in a unitary housing structure.

17. The system of claim 12, wherein the plurality of discrete optical radiation sensors comprises a 4.9 um sensor, a 2.2 um sensor, a 4.3 um sensor and a 4.45 um sensor.

18. The system of claim 12, wherein the Artificial Neural Network comprises a two-layer Artificial Neural Network.

19. The system of claim 12, further comprising means for establishing a correlation between frequency and time domain of the outputs from the discrete optical sensors.

20. The system of claim 19, wherein said means for establishing a correlation comprises an electronic signal processor adapted to perform one of Discrete Fourier Transform, Short-Time Fourier Transform with a shifting time window or a Discrete Wavelet Transform.

21. The system of claim 12, further comprising a temperature sensor for sensing a temperature of the system, and said Artificial Neural Network is further responsive to signals indicative of the sensed temperature to provide said output.

22. A flame detection system, comprising:

a plurality of discrete sensors for generating a plurality of respective sensor signals, said plurality of sensors including a set of optical radiation sensors responsive to flame emissions; and

a digital signal processor including an Artificial Neural Network (ANN) for processing the sensor signals to provide an output corresponding to a flame condition.

23. The system of claim 22, wherein the flame condition comprises one of the presence of flame, the absence of flame or false alarm.

24. The system of claim 22, wherein the flame condition comprises one of the presence of flame or the absence of flame.

25. The system of claim 22, wherein the plurality of discrete sensors comprises an array of sensors mounted in a common housing structure.

26. The system of claim 25, wherein the set of optical radiation sensors comprises a 4.9 um sensor, a 4.3 um sensor and a 4.45 um sensor.

27. The system of claim 22, wherein the plurality of sensors further comprises an immunity sensor sensitive to radiation in an optical spectrum from ultraviolet to infrared.

28. The system of claim 27, wherein said immunity sensor is sensitive to 2.2 micron wavelength radiation.

29. The system of claim 22, wherein the plurality of sensors comprises a temperature sensor for generating a temperature sensor signal indicative of a temperature.

30. The system of claim 22, wherein the Artificial Neural Network comprises a two-layer Artificial Neural Network.

31. The system of claim 22, wherein the digital signal processor further comprising a pre-processing means for processing the sensor signals to provide pre-processed signals for said ANN, wherein pre-processing means comprises means for establishing a correlation between frequency and time domain of the signals, said means performing one of Discrete Fourier Transform, Short-Time Fourier Transform with a shifting time window or a Discrete Wavelet Transform.

32. The system of claim 30, wherein the Artificial Neural Network comprises a hidden layer of artificial neurons which apply a set of hidden layer connection weights and a sigmoid function to said pre-processed signals to provide hidden layer output signals, and an output layer of output neurons which apply a set of output connection weights and a sigmoid function to said hidden layer output signals to provide flame neuron output values.

33. The system of claim 22, further comprising a decision processor responsive to outputs from the ANN to determine a flame detection state based on said sensor signals.

34. The system of claim 33, wherein the decision processor generates an alarm condition when a threshold limit is exceeded.

35. A method for detecting flames, comprising:

sensing optical radiation over a field of view with a plurality of discrete sensors and generating sensor signals indicative of the sensed radiation;

processing the sensor signals by a digital signal processor including an Artificial Neural Network (ANN) to provide outputs corresponding to a flame condition.

36. The method of claim 35, wherein the flame condition comprises one of the presence of flame, the absence of flame or false alarm.

37. The method of claim 35, wherein the plurality of optical radiation sensors comprises a 4.9 um sensor, a 2.2 um sensor, a 4.3 um sensor and a 4.45 um sensor.

38. The method of claim 35, wherein the artificial neural network comprises a two-layer Artificial Neural Network.

39. The method of claim 35, further comprising:

establishing a correlation between frequency and time domain of the sensor signals.

40. The method of claim 39, wherein said establishing a correlation comprises:

performing one of Discrete Fourier Transform, Short-Time Fourier Transform with a shifting time window or a Discrete Wavelet Transform.

41. A method for training an Artificial Neural Network (ANN) for a flame detection system, comprising:

exposing a plurality of discrete optical radiation sensors to a plurality of flame, non-flame, false alarm and background conditions to collect training data comprising known input vectors;

using the training data to train the ANN to develop an operating set of synaptic connection weights.

42. The method of claim 41, wherein said using the training data comprises:

(i) assuming a starting set of synaptic connection weights, computing a forward-pass computation through the ANN to provide output signals;

(ii) comparing the output signals to the known target vectors to determine discrepancy values between the output signals and the known target vectors;

(iii) propagating the discrepancy values through a back propagation (BP) algorithm to calculate updated synaptic connection weights;

(iv) using the updated synaptic connection weights as input to the forward pass computation of the ANN;

(v) repeating (ii), (iii) and (iv) until the operating set has been obtained.

43. The method of claim 41, wherein said plurality of flame, non-flame, false alarm and background conditions includes a set of indoor test conditions and a set of outdoor test conditions.

44. The method of claim 43, wherein said indoor test conditions include training on a butane flame and a propane flame source, and said outdoor test conditions include training on an n-heptane flame outdoors.

45. The method of claim 41 wherein said plurality of flame, non-flame, false alarm and background conditions includes exposure to a test lamp for a field test,

46. A flame detection system, comprising:

a plurality of discrete optical radiation sensors;

means for joint time-frequency signal pre-processing output from the plurality of discrete optical radiation sensors to provide pre-processed signals; and

a digital signal processor for processing the pre-processed signals and providing an output indicating a flame condition.

47. The system of claim 46, wherein the flame condition comprises one of the presence of flame, the absence of flame or false alarm.

48. The system of claim 46, wherein the flame condition is one of the presence or absence of flame.

49. The system of claim 46, wherein the plurality of optical radiation sensors comprises an array of discrete sensors.

50. The system of claim 46, wherein the plurality of discrete optical radiation sensors comprises a 4.9 um sensor, a 2.2 um sensor, a 4.3 um sensor and a 4.45 um sensor.

51. The system of claim 46, wherein the digital signal processor comprises an Artificial Neural Network.

52. The system of claim 46, wherein said pre-processing means establishes a correlation between frequency and time domain of the outputs from the discrete optical sensors.

53. The system of claim 52, wherein said pre-processing means is adapted to perform one of Discrete Fourier Transform, Short-Time Fourier Transform with a shifting time window or a Discrete Wavelet Transform.