Smoke detection

• US 9,171,453 B2
• Filed: 01/23/2014
• Issued: 10/27/2015
• Est. Priority Date: 01/23/2014
• Status: Active Grant

• Current Assignee: UT-Battelle LLC
• Original Assignee: UT-Battelle LLC
• Inventors: Warmack, Robert J. Bruce, Wolf, Dennis A., Frank, Steven Shane
• Primary Examiner(s): WU, DANIEL J
• Application Number:
  US14/162,547
• Publication Number:
  US 20150206423A1
• Time in Patent Office: 642 Days
• Field of Search: 340/514, 340/577, 340/584, 340/628, 340/632, 700/299
• US Class Current: 1/1
• CPC Class Codes: G08B 17/00 Fire alarms; Alarms responsive to explosion
• 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 17/117 by using a detection device for specific gases, e.g. combustion products, produced by the fire G08B17/103, G08B17/11 take precedence
• CPC Class Codes: G08B 29/188 Data fusion; cooperative systems, e.g. voting among different detectors
• CPC Class Codes: G08B 29/20 Calibration, including self-calibrating arrangements
• CPC Class Codes: G08B 3/10 using electric transmission; using electromagnetic transmission
• CPC Class Codes: G08B 5/36 using visible light sources

Abstract

Various apparatus and methods for smoke detection are disclosed. In one embodiment, a method of training a classifier for a smoke detector comprises inputting sensor data from a plurality of tests into a processor. The sensor data is processed to generate derived signal data corresponding to the test data for respective tests. The derived signal data is assigned into categories comprising at least one fire group and at least one non-fire group. Linear discriminant analysis (LDA) training is performed by the processor. The derived signal data and the assigned categories for the derived signal data are inputs to the LDA training. The output of the LDA training is stored in a computer readable medium, such as in a smoke detector that uses LDA to determine, based on the training, whether present conditions indicate the existence of a fire.

Claims

1. A method of training a classifier for a smoke detector, comprising:

inputting sensor data from a plurality of tests into a processor, the sensor data indicative of environmental conditions during the tests;

using the processor to process the sensor data from the tests to generate derived signal data corresponding to the test data for respective tests;

assigning the derived signal data into categories comprising at least one fire group and at least one non-fire group;

performing linear discriminant analysis (LDA) training using the processor and the derived signal data and the assigned categories for the derived signal data as input to the LDA training, the output of the LDA training generating a centroid in linear discriminant coordinates for each of the categories, a plurality of coefficients for transforming derived signal data into linear discriminant (LD) coordinates, and a mean of group means; and

storing the plurality of coefficients, the plurality of centroids, and the mean of group means in a computer readable medium.

2. A method according to claim 1 wherein the categories comprise plural fire groups, the fire groups including a flaming fire group, a non-flaming fire group, and a grease fire group.

3. A method according to claim 2 wherein the at least one non-fire group comprises a normal group and a nuisance non-fire indicating group.

4. A method according to claim 1 wherein the inputted sensor data from the plurality of tests comprises data from individual tests broken down into time intervals for the test and the act of assigning comprises assigning derived signal data for the time intervals to the categories.

5. The method of claim 1 wherein the sensor data includes data from an aerosol sensor and one or more sensors selected from the group consisting of a temperature sensor, a carbon monoxide sensor, a Taguchi sensor, and a carbon monoxide sensor.

6. The method of claim 1 wherein the sensor data from each test is a time-series of sensor data over time periods and wherein the act of processing the sensor data comprises:

generating a first baseline based on a moving average over n previous measurements of the sensor data; and

calculating a difference between a present measurement of the sensor data and the first baseline.

7. The method of claim 6 wherein the act of processing the sensor data further comprises:

generating a second baseline based on a moving average over n′

previous measurements of the sensor data, n′

being different from n; and

calculating a difference between a present measurement of the sensor data and the second baseline.

8. The method of claim 1, wherein using the processor to process the sensor data from the tests includes:

adding data to account for sensor variance;

removing sensor data to account for faulty sensor data; and

generating new data by interpolating between measurements of the sensor data.

9. The method of claim 1, wherein the act of assigning the derived signal data into categories comprises assigning the derived signal data for the respective time periods into the categories.

10. The method of claim 1, wherein the act of storing comprises storing the plurality of coefficients, the plurality of centroids, and the mean of group means in a computer readable medium of a smoke detector.

11. The method of claim 10, further comprising:

receiving smoke alarm sensor data from at least one sensor of the smoke detector, the smoke alarm sensor data indicative of the present environmental conditions;

processing the smoke alarm sensor data to provide data in a plurality of data channels;

mapping the data from the plurality of data channels into linear discriminant space using the plurality of stored coefficients;

determining the nearest centroid of the plurality of stored centroids to the mapping of the data from the plurality of data channels in linear discriminant space; and

signaling an alarm condition if the nearest centroid is in a fire group category.

12. The method of claim 11, wherein processing the smoke alarm sensor data to provide data in a plurality of data channels includes calculating a baseline moving average of the smoke alarm sensor data.

13. The method of claim 12, wherein processing the smoke alarm sensor data to provide data in a plurality of data channels includes subtracting the stored mean of group means from the baseline moving average of the smoke alarm sensor data.

14. A method of detecting a hazardous condition, comprising:

inputting sensor data from a plurality of tests into a processor, the sensor data indicative of environmental conditions during the test;

processing the sensor data from the plurality of tests, using the processor to generate derived signal data corresponding to the test data for respective tests;

assigning at least one group to the derived signal data for a respective test, the at least one group selected from a plurality of groups including a normal group, a flaming fire group, and a non-flaming group;

performing linear discriminant analysis (LDA) training using the derived signal data and the assigned at least one group for the respective tests as input to the LDA training, the output of the LDA training generating a plurality of transformation coefficients for transforming derived signal data into linear discriminant (LD) coordinates, a mean of group means, and a plurality of centroids in linear discriminant coordinates, wherein the plurality of centroids includes a different centroid for each of the plurality of groups;

storing the plurality of transformation coefficients, the mean group of means, and the plurality of centroids into a computer-readable memory of a smoke detector;

providing one or more sensors coupled to the smoke detector for sensing present environmental conditions and providing data corresponding to the sensed present environmental conditions, the data being provided in a plurality of data channels;

mapping the data from the plurality of data channels into linear discriminant space using the plurality of stored transformation coefficients;

determining the nearest centroid of the plurality of stored centroids to the data from the plurality of data channels mapped into linear discriminant space; and

signaling an alarm if the nearest centroid is associated with a centroid in a group corresponding to a hazardous condition.

15. The method of claim 14, wherein processing the sensor data from the plurality of tests includes calculating a baseline moving average for sensor data of the respective tests.

16. The method of claim 14, wherein processing the sensor data from the plurality of tests includes adding data to account for sensor variance.

17. The method of claim 14, wherein processing the sensor data from the plurality of tests includes removing sensor data to account for faulty sensor data.

18. The method of claim 14, wherein processing the sensor data from the plurality of tests includes generating new sensor data by interpolating between measurements of the sensor data.

19. The method of claim 14, wherein assigning the derived signal data into groups comprises dividing derived signal data for the respective test into time periods and assigning the derived signal data for the respective time periods into the groups.

20. The method of claim 19, wherein assigning the derived signal data into groups comprises assigning the derived signal data for the respective time periods into the groups based on sensor data exceeding a threshold.

21. The method of claim 19, wherein assigning the derived signal data into groups comprises excluding derived signal data that exceeds a threshold from any group.

22. The method of claim 14, wherein the sensor data from the plurality of tests includes data from sensors of the same type as the one or more sensors coupled to the smoke detector for sensing present environmental conditions.

23. A smoke detector, comprising:

a computer readable medium including linear discriminant analysis (LDA) training output data generated by;

inputting sensor data from a plurality of tests, the sensor data indicative of environmental conditions during the respective tests;

processing the sensor data to generate derived signal data for the respective tests;

assigning at least one group to the derived signal data for the respective tests, the at least one group selected from a plurality of groups, each group of the plurality of groups associated with a hazardous condition or a non-hazardous condition; and

performing LDA training using the derived signal data and the assigned at least one group for the respective tests as input to the LDA training, the output of the LDA training generating a plurality of transformation coefficients for transforming derived signal data into linear discriminant (LD) coordinates, a mean of group means, and a plurality of centroids in linear discriminant coordinates, wherein the plurality of centroids includes a different centroid for each group of the plurality of groups;

at least one sensor configured to observe present environmental conditions, the at least one sensor comprising an aerosol sensor;

a processor operatively connected to the computer readable memory and the at least one sensor, the processor configured to;

process data from the at least one sensor to provide data in a plurality of data channels indicative of the present environmental conditions;

map the data from the plurality of data channels into linear discriminant space using the plurality of transformation coefficients stored in the computer readable medium;

classify the present environmental conditions as belonging to one group of the plurality of groups based on the linear discriminant mapping of the data from the plurality of data channels; and

signal an alarm condition if the present environmental conditions are classified as belonging to a group associated with a hazardous condition; and

an alarm operatively connected to the processor, the alarm generating an audible alert, a visual alert, or a combination thereof in response to the alarm signal.

24. The smoke detector of claim 23, wherein the classification of the present environmental conditions as belonging to one group of the plurality of groups is based on the linear discriminant mapping of the plurality of data channels being outside a threshold in linear discriminant coordinates.