CN111105587A - Intelligent flame detection method and device, detector and storage medium - Google Patents
Intelligent flame detection method and device, detector and storage medium Download PDFInfo
- Publication number
- CN111105587A CN111105587A CN201911405386.3A CN201911405386A CN111105587A CN 111105587 A CN111105587 A CN 111105587A CN 201911405386 A CN201911405386 A CN 201911405386A CN 111105587 A CN111105587 A CN 111105587A
- Authority
- CN
- China
- Prior art keywords
- signal
- dynamic
- ultraviolet
- infrared
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 52
- 238000005070 sampling Methods 0.000 claims abstract description 53
- 238000013139 quantization Methods 0.000 claims abstract description 30
- 238000000034 method Methods 0.000 claims abstract description 15
- 239000006185 dispersion Substances 0.000 claims description 21
- 230000005284 excitation Effects 0.000 claims description 17
- 238000005096 rolling process Methods 0.000 claims description 16
- 230000008030 elimination Effects 0.000 claims description 13
- 238000003379 elimination reaction Methods 0.000 claims description 13
- 230000007613 environmental effect Effects 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 2
- 230000035945 sensitivity Effects 0.000 description 16
- 238000004891 communication Methods 0.000 description 12
- 238000004590 computer program Methods 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 239000000779 smoke Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000012943 hotmelt Substances 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
Landscapes
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Photometry And Measurement Of Optical Pulse Characteristics (AREA)
- Fire-Detection Mechanisms (AREA)
Abstract
The invention discloses an intelligent flame detection method, an intelligent flame detection device, a detector and a storage medium, wherein the method comprises the following steps: acquiring an infrared dynamic signal and an ultraviolet dynamic signal at sampling time of a certain period, and quantizing the signals respectively to obtain an infrared dynamic signal quantization value and an ultraviolet dynamic signal quantization value; calculating the average intensity of dynamic signals and the discreteness of the dynamic signals in the mt time window according to the infrared dynamic signal quantized value and the ultraviolet dynamic signal quantized value, and counting the discreteness; obtaining a dynamic signal characteristic value according to the average intensity of the dynamic signal in the mt time window and the discreteness of the dynamic signal; if the discrete count is greater than or equal to the effective count threshold and the difference value between the dynamic signal characteristic value and the background noise signal characteristic value is greater than or equal to the identification signal characteristic value threshold, identifying the flame and outputting a flame alarm signal. The invention can realize the purposes of eliminating background noise interference in a self-adaptive way, preventing false alarm and improving the reliability of flame detection alarm.
Description
Technical Field
The invention relates to an intelligent flame detection method, an intelligent flame detection device, a detector and a storage medium, and belongs to the technical field of flame detection.
Background
The flame detectors which are widely applied at present comprise a temperature-sensitive detector (glass ball or hot-melt metal), a smoke-sensitive detector and a point-type flame detector, and the temperature-sensitive detector and the smoke-sensitive detector are generally suitable for occasions with lower clearance height and smaller spacing space; the point-type flame detector is generally suitable for environments with large space and large dust, has two types of infrared flame detectors and ultraviolet flame detectors, and has obvious defects at the same time: the flame detector is usually installed at the top of a building space, the sensitivity of the flame detector is preset before installation, and people are difficult to approach the flame detector to adjust the detection sensitivity of the flame detector when the flame detector is changed due to application environment or the preset sensitivity of the flame detector is not suitable after the flame detector is installed and put into use, so that false alarm is easily caused.
Disclosure of Invention
In view of the above, the present invention provides an intelligent flame detection method, apparatus, system, intelligent flame detector and storage medium, which obtains a signal characteristic value according to a certain operation rule by obtaining an infrared signal and an ultraviolet signal with a specific wavelength released by flame; a certain time or a plurality of times in day and night can be selected as a sampling point, the background noise signal characteristic value in the day is obtained and is used as a detection signal threshold between the sampling point and the next sampling point, and the dynamic signal characteristic value exceeding the threshold in a certain range is finally judged as a fire alarm signal, so that the purposes of self-adaptively eliminating background noise interference, preventing false alarm and improving the detection flame alarm reliability are realized.
A first object of the present invention is to provide an intelligent flame detection method.
A second object of the present invention is to provide an intelligent flame detection device.
It is a third object of the present invention to provide an intelligent flame detector.
It is a fourth object of the present invention to provide a storage medium.
The first purpose of the invention can be achieved by adopting the following technical scheme:
an intelligent flame detection method, the method comprising:
acquiring an infrared dynamic signal and an ultraviolet dynamic signal at sampling time of a certain period, and quantizing the signals respectively to obtain an infrared dynamic signal quantization value and an ultraviolet dynamic signal quantization value;
calculating the average intensity of dynamic signals and the discreteness of the dynamic signals in the mt time window according to the infrared dynamic signal quantized value and the ultraviolet dynamic signal quantized value, and counting the discreteness; wherein m is a rolling time window coefficient, and t is sampling time of a certain period;
obtaining a dynamic signal characteristic value according to the average intensity of the dynamic signal in the mt time window and the discreteness of the dynamic signal;
if the discrete count is greater than or equal to the effective count threshold, carrying out background noise elimination processing;
after background noise elimination processing is carried out, if the difference value between the dynamic signal characteristic value and the background noise signal characteristic value is greater than or equal to the identification signal characteristic value threshold, flame is identified, and a flame alarm signal is output.
Further, before acquiring the infrared dynamic signal and the ultraviolet dynamic signal at a certain period of sampling time, the method further includes:
selecting a certain time or a plurality of times of day and night as sampling points to obtain an infrared signal and an ultraviolet signal, and quantizing the infrared signal and the ultraviolet signal respectively to obtain an infrared signal quantization value and an ultraviolet signal quantization value;
calculating the average intensity, the infrared signal discreteness and the ultraviolet signal discreteness of the infrared signal and the ultraviolet signal in the mt time window according to the infrared signal quantified value and the ultraviolet signal quantified value;
obtaining a background noise signal characteristic value of the current day according to the signal average intensity and the signal discreteness in the mt time window, and using the background noise signal characteristic value as a detection signal threshold from the sampling point to the next sampling point;
judging whether the intelligent flame detector fails or not according to the characteristic value of the background noise signal, and outputting a failure alarm signal if the intelligent flame detector fails; and if the intelligent flame detector is judged to be effective, executing subsequent operation.
Further, according to the background noise signal characteristic value, whether the intelligent flame detector is invalid or not is judged, and the method specifically comprises the following steps:
and respectively comparing the background noise signal characteristic value with a preset minimum value and a preset maximum value, if the background noise signal characteristic value is greater than the preset maximum value or less than the preset minimum value, judging that the intelligent flame detector is invalid, and if the background noise signal characteristic value is greater than or equal to the preset minimum value and less than or equal to the preset maximum value, judging that the intelligent flame detector is valid.
Further, before acquiring the infrared dynamic signal and the ultraviolet dynamic signal at a certain period of sampling time, the method further includes:
and when the environmental factors of the application environment exceed a certain change range and change, receiving the sampling time, the rolling time window coefficient, the effective counting threshold, the identification signal characteristic value threshold and the background noise signal characteristic value which are reset by the remote terminal in a certain period.
Further, the average intensity of the dynamic signal and the dispersion of the dynamic signal within the mt time window are calculated according to the quantized value of the infrared dynamic signal and the quantized value of the ultraviolet dynamic signal, as follows:
p＝[A1,A2]
d＝d1+d2
wherein p represents the average intensity of the dynamic signal in the mt time window, A1 represents the average intensity of the infrared dynamic signal in the mt time window, and A2 represents the average intensity of the ultraviolet dynamic signal in the mt time window; d represents the dispersion of dynamic signals within the mt time window, d1 represents the dispersion of infrared dynamic signals within the mt time window, and d2 represents the dispersion of ultraviolet dynamic signals within the mt time window.
The second purpose of the invention can be achieved by adopting the following technical scheme:
an intelligent flame detection device, the device comprising:
the signal acquisition module is used for acquiring the infrared dynamic signal and the ultraviolet dynamic signal at sampling time of a certain period, and quantizing the signals respectively to obtain an infrared dynamic signal quantization value and an ultraviolet dynamic signal quantization value;
the calculation module is used for calculating the average intensity of the dynamic signals and the discreteness of the dynamic signals in the mt time window according to the infrared dynamic signal quantized value and the ultraviolet dynamic signal quantized value, and counting the discreteness; wherein m is a rolling time window coefficient, and t is sampling time of a certain period;
the characteristic value acquisition module is used for acquiring a dynamic signal characteristic value according to the average intensity of the dynamic signal in the mt time window and the discreteness of the dynamic signal;
the background noise processing module is used for eliminating the background noise if the discrete count is greater than or equal to the effective count threshold;
and the output module is used for identifying flame and outputting a flame alarm signal if the difference value between the dynamic signal characteristic value and the background noise signal characteristic value is greater than or equal to the identification signal characteristic value threshold after background noise elimination processing.
The third purpose of the invention can be achieved by adopting the following technical scheme:
an intelligent flame detector comprises an infrared sensor, an ultraviolet sensor, an excitation and signal processing circuit and a remote terminal, wherein the infrared sensor and the ultraviolet sensor are respectively connected with the excitation and signal processing circuit, and the excitation and signal processing circuit is connected with the remote terminal through a remote communication interface;
the excitation and signal processing circuit is used for exciting the infrared sensor and the ultraviolet sensor and executing the intelligent flame detection method;
and the remote terminal is used for adjusting the sampling time, the rolling time window coefficient, the discrete counting and the identification signal characteristic value threshold of a certain period and sending the values to the excitation and signal processing circuit.
Further, the device also comprises a photosensitive sensor which is connected with the excitation and signal processing circuit;
the photosensitive sensor is used for identifying the change of day and night light of the application environment.
The third purpose of the invention can be achieved by adopting the following technical scheme:
an intelligent flame detector comprises a processor and a memory for storing a processor executable program, and when the processor executes the program stored in the memory, the intelligent flame detection method is realized.
The fourth purpose of the invention can be achieved by adopting the following technical scheme:
a storage medium storing a program which, when executed by a processor, implements the intelligent flame detection method described above.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention obtains the infrared dynamic signal and the ultraviolet dynamic signal in a certain period of sampling time, quantizes the signals, effectively reduces the background noise interference of continuous sampling, can greatly prolong the service life of the ultraviolet sensor, calculates the average intensity of the dynamic signal and the discreteness of the dynamic signal according to the quantized value of the infrared dynamic signal and the quantized value of the ultraviolet dynamic signal, counts the discreteness which is more than or equal to an effective counting threshold, eliminates the background noise, compares the difference between the characteristic value of the dynamic signal and the characteristic value of the background noise signal with the characteristic value threshold of the identification signal, realizes accurate flame detection and improves the reliability of flame detection and alarm.
2. The invention can select a certain time or a plurality of times of day and night as the sampling point to obtain the characteristic value of the background noise signal of the day, and the characteristic value is used as the detection signal threshold between the sampling point and the next sampling point, thereby completing the self-adaptive adjustment of the characteristic value of the background noise signal, effectively eliminating the background noise interference formed by the visible light spectrum, self-adaptively adjusting the detection sensitivity in a certain change range and effectively inhibiting the false alarm phenomenon.
3. The sampling time, the rolling time window coefficient, the effective counting threshold, the identification signal characteristic value threshold and the background noise signal characteristic value of a certain period are reset in a manual intervention remote communication control mode, so that the sensitivity of the identification flame after background noise interference is eliminated is improved or reduced, the specific requirement of environment change is better met, and the 'hand-in-hand' uncovering setting processing on the sensitivity of the detector is not required to be implemented by erecting a shed frame for high-altitude operation.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.
Fig. 1 is a block diagram showing the structure of an intelligent flame detector according to embodiment 1 of the present invention.
Fig. 2 is a flowchart of artificial intelligence and communication control processing software according to embodiment 1 of the present invention.
Fig. 3 is a flowchart of an intelligent flame detection method according to embodiment 1 of the present invention.
Fig. 4 is a flowchart of adaptive background noise signal characteristic values according to embodiment 1 of the present invention.
Fig. 5 is a block diagram showing the structure of an intelligent flame detection device according to embodiment 2 of the present invention.
Fig. 6 is a block diagram of a structure in which a second obtaining module, a third calculating module, a fourth calculating module, and a determining module are sequentially connected in embodiment 2 of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer and more complete, the technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the protection scope of the present invention.
Example 1:
as shown in fig. 1, the present embodiment provides an intelligent flame detector, which includes an infrared sensor 101, an ultraviolet sensor 102, a photosensitive sensor 103, an excitation and signal processing circuit 104 and a remote terminal 105, wherein the infrared sensor 101, the ultraviolet sensor 102 and the photosensitive sensor 103 are respectively connected to the excitation and signal processing circuit 104, and the excitation and signal processing circuit 104 is connected to the remote terminal 105 through a remote communication interface.
The infrared sensor 101 is used for detecting the flame and acquiring an infrared signal with a specific wavelength released by the flame.
The ultraviolet sensor 102 is used for detecting flame and can acquire an ultraviolet signal with a specific wavelength released by the flame.
The visible light spectrum contains abundant infrared and ultraviolet signals to form environment background noise signals, the background noise signals can generate interference output to the sensor, and the intelligent flame detector can eliminate the background noise.
The photosensitive sensor 103 is used for identifying the change of day and night light of the application environment.
The excitation and signal processing circuit 104 is a core of the intelligent flame detector, and is used for exciting the infrared sensor 101 and the photosensitive sensor 103 (feeding the infrared sensor 101 and the photosensitive sensor 103), respectively receiving small pyroelectric signals of the infrared sensor 101, amplifying, filtering and comparing the small pyroelectric signals, and extracting quantitative signals and reaction signals of the photosensitive sensor 103; periodically energizing the ultraviolet sensor 102 to acquire signals that may be present; a telecommunications interface is provided.
The remote terminal 105 can adopt a handheld terminal (such as a remote controller) or a desktop terminal, adopts a wired or wireless communication mode to carry out remote communication control on the intelligent flame detector, sets identification and judgment related factors, and can adopt the manual intervention remote communication control mode when the change of the environmental factors exceeds the self-adaptive adjustment range of the intelligent flame detector, so that the detection sensitivity of the intelligent flame detector can adapt to the change requirement of the environmental factors; among these, environmental factors include, but are not limited to: day and night, season, weather, light caused by structural changes in the environment, temperature difference changes, and the like.
The excitation and signal processing circuit 104 is embedded with artificial intelligence and communication control processing software, and the processing flow of the software in general case is as shown in fig. 2, and specifically includes:
1) initializing after the intelligent flame detector is electrified, and presetting sampling time t, rolling time window coefficient m and effective counting threshold n of a certain period0An identification signal characteristic value threshold Ns and a background noise signal characteristic value N0(ii) a Wherein, mt time window is a rolling time window which is m times t, and is continuously rolled in a certain time step.
2) And reading the infrared signal and the ultraviolet signal, quantizing to obtain an infrared signal quantized value s1 and an ultraviolet signal quantized value s2, and filtering.
3) Calculating the average intensity (density) of the infrared signal and the ultraviolet signal in the mt time window as follows:
where A1 represents the average intensity of the infrared signal within the mt time window and A2 represents the average intensity of the ultraviolet signal within the mt time window.
4) Calculating the discreteness of the infrared signal and the ultraviolet signal in the mt time window and calculating the discreteness count n of the statistical conformity condition items; wherein, the discreteness of the infrared signal and the ultraviolet signal is calculated according to the following formula:
where d1 represents the infrared signal dispersion within the mt time window and d2 represents the ultraviolet signal dispersion within the mt time window.
5) From equations (1) to (4), the average signal intensity and the signal dispersion in the mt time window can be obtained as follows:
p＝[A1,A2](5)
d＝d1+d2 (6)
where p represents the average intensity of the signal within the mt time window and d represents the dynamic signal dispersion within the mt time window.
6) Obtaining N according to the signal average intensity and the signal dispersion in the mt time windowd(p，d，mt)。
7) If the discrete count n is larger than or equal to the effective count threshold n0If yes, carrying out background noise elimination processing, and entering step 7); discrete count n < effective count threshold n0And returning to the step 2) to continue reading the infrared signals and the ultraviolet signals.
8) If N is presentd(p，d，mt)-N0(p, d, mt) is not less than Ns (p, d, mt), the flame is recognized, a flame alarm signal is output, and if N is greater than or equal to Ns (p, d, mt), the flame is detectedd(p，d，mt)-N0(p, d, mt) < Ns (p, d, mt), returning to the step 2), and continuing to read the infrared signals and the ultraviolet signals.
Further, the excitation and signal processing circuit 104 includes a processor and a memory, the memory stores a computer program, and when the processor executes the computer program stored in the memory, an intelligent flame detection method can be realized, the method is applied to actual detection, and is realized on the basis of the artificial intelligence and communication control processing software, as shown in fig. 3, and includes the following steps:
s301, acquiring an infrared dynamic signal and an ultraviolet dynamic signal at sampling time of a certain period, and quantizing the signals respectively to obtain an infrared dynamic signal quantization value and an ultraviolet dynamic signal quantization value, wherein in the step 2), S1 and S2 respectively represent the infrared dynamic signal quantization value and the ultraviolet dynamic signal quantization value; the infrared dynamic signal and the ultraviolet dynamic signal are obtained in a certain period of sampling time and are quantized, so that the background noise interference of continuous sampling is effectively reduced, and meanwhile, the service life of the ultraviolet sensor can be greatly prolonged.
S302, calculating the average intensity of the dynamic signals and the discreteness of the dynamic signals in the mt time window according to the quantized values of the infrared dynamic signals and the ultraviolet dynamic signals, and counting the discreteness, wherein in the steps 3) to 5), p represents the average intensity of the dynamic signals in the mt time window, A1 represents the average intensity of the infrared dynamic signals in the mt time window, and A2 represents the average intensity of the ultraviolet dynamic signals in the mt time window; d represents the dispersion of dynamic signals within the mt time window, d1 represents the dispersion of infrared dynamic signals within the mt time window, and d2 represents the dispersion of ultraviolet dynamic signals within the mt time window.
S303, obtaining a dynamic signal characteristic value N according to the average intensity of the dynamic signal in the mt time window and the discreteness of the dynamic signald(p, d, mt), see step 6 above).
And S304, judging whether the discreteness count is greater than or equal to the effective count threshold.
If the discrete count is greater than or equal to the valid count threshold, performing background noise elimination processing, and entering step S305; otherwise, return to step S301.
S305, judging the characteristic value N of the dynamic signald(p, d, mt) and the background noise signal characteristic value N0(p, d, mt) is greater than or equal to the identification signal characteristic threshold Ns (p, d, mt);
if the difference value between the dynamic signal characteristic value and the background noise signal characteristic value is greater than or equal to the identification signal characteristic value threshold, identifying the flame and outputting a flame alarm signal; otherwise, return to step S301.
Further, a background noise signal N0(p, d, mt) may vary due to environmental factors, including, but not limited to: day and night, season, meteorology, the light that the structural change in the environment arouses, the difference in temperature change etc. wherein day and night is relatively more obvious to light, temperature change in one day, and this embodiment can distinguish day and night through photosensitive sensor, also can adopt intelligent flame detector's internal clock to distinguish day and night.
Therefore, before the dynamic probing, i.e. before step S301, as shown in fig. 4, the following steps may be further included:
s401, selecting a certain time or a plurality of times in day and night as sampling points, acquiring infrared signals and ultraviolet signals, quantizing the infrared signals and the ultraviolet signals respectively to obtain infrared signal quantized values and ultraviolet signal quantized values, and referring to the step 2).
And S402, calculating the average intensity, the infrared signal dispersion and the ultraviolet signal dispersion of the infrared signal and the ultraviolet signal in the mt time window according to the infrared signal quantization value and the ultraviolet signal quantization value, and referring to the steps 3) to 5).
S403, obtaining a background noise signal characteristic value N of the day according to the signal average intensity and the signal discreteness in the mt time window0(p, d, mt), and memory retention is performed and used as the threshold of the detection signal from the sampling point to the next sampling point.
Through the processing of the steps S401 to S403, the adaptive adjustment of the characteristic value of the background noise signal is completed, and the background noise interference caused by the visible light spectrum is effectively eliminated, that is, the detection sensitivity is adaptively adjusted.
And S404, judging whether the intelligent flame detector is invalid or not according to the background noise signal characteristic value.
If the intelligent flame detector is judged to be invalid, outputting a failure alarm signal; if the intelligent flame detector is judged to be effective, the subsequent operation is executed, namely steps S301-S305.
Specifically, the background noise signal characteristic value is compared with a preset minimum value pre-min and a preset maximum value pre-max respectively, if the background noise signal characteristic value is larger than the preset maximum value pre-max or smaller than the preset minimum value pre-min, the intelligent flame detector is judged to be invalid, and if the background noise signal characteristic value is larger than or equal to the preset minimum value pre-min and smaller than or equal to the preset maximum value pre-max, the intelligent flame detector is judged to be valid.
Different application environments need to correspond to different detection sensitivities, when different time periods or internal stacking conditions of the same application environment change, the detection sensitivities of the intelligent flame detector may also be different, and the intelligent flame detector can automatically complete the sensitivity adjustment within a certain change range due to the environmental factors (the steps S401 to S403); when these environmental factors exceed a certain variation range, the sampling time t, the rolling time window coefficient m, and the effective counting threshold n of a certain period need to be reset (by using the remote terminal 105) through a manual intervention remote communication control mode0An identification signal characteristic value threshold Ns and a background noise signal characteristic value N0The sensitivity of flame identification after background noise interference is eliminated is improved or reduced, and the specific requirements of environmental changes are better met.
The background noise characteristic value can be transmitted to a background terminal in a remote communication control mode to form large background noise characteristic data of an application environment, so that analysis and optimization are facilitated, and the long-term stability and reliability of the flame detector are further improved; the applicable place of the intelligent flame detector can completely cover an indoor closed space, a semi-closed space, a light shed or an outdoor application environment.
It should be noted that although the method operations of the above-described embodiments are depicted in the drawings in a particular order, this does not require or imply that these operations must be performed in this particular order, or that all of the illustrated operations must be performed, to achieve desirable results. Rather, the depicted steps may change the order of execution. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions.
Example 2:
as shown in fig. 5, the present embodiment provides an intelligent flame detection device, which includes a first signal obtaining module 501, a first calculating module 502, a first characteristic value obtaining module 503, a background noise processing module 504, and an output module 505, where the specific functions of the modules are as follows:
the first signal obtaining module 501 is configured to obtain an infrared dynamic signal and an ultraviolet dynamic signal at a sampling time of a certain period, and quantize the infrared dynamic signal and the ultraviolet dynamic signal respectively to obtain an infrared dynamic signal quantization value and an ultraviolet dynamic signal quantization value.
The first calculating module 502 calculates the average intensity of the dynamic signal and the discreteness of the dynamic signal in the mt time window according to the quantized value of the infrared dynamic signal and the quantized value of the ultraviolet dynamic signal, and counts the discreteness; wherein m is a rolling time window coefficient, and t is a sampling time of a certain period.
The first characteristic value obtaining module 503 is configured to obtain a characteristic value of the dynamic signal according to the average intensity of the dynamic signal within the mt time window and the discreteness of the dynamic signal.
The background noise processing module 504 is configured to perform background noise elimination processing if the discreteness count is greater than or equal to the valid count threshold.
The output module 505 is configured to identify a flame and output a flame alarm signal if a difference between the dynamic signal characteristic value and the background noise signal characteristic value is greater than or equal to an identification signal characteristic value threshold after the background noise elimination processing is performed.
Further, as shown in fig. 6, before the first signal obtaining module 501, the method may further include:
the second signal obtaining module 601 is configured to select a certain time or several times around the clock as a sampling point, obtain the infrared signal and the ultraviolet signal, and quantize the infrared signal and the ultraviolet signal respectively to obtain an infrared signal quantization value and an ultraviolet signal quantization value.
And a second calculating module 602, configured to calculate, according to the infrared signal quantization value and the ultraviolet signal quantization value, an average intensity, an infrared signal dispersion, and an ultraviolet signal dispersion of the infrared signal and the ultraviolet signal within the mt time window.
The second eigenvalue obtaining module 603 is configured to obtain an eigenvalue of a background noise signal of the current day according to the average signal intensity and the signal dispersion within the mt time window, and use the eigenvalue as a detection signal threshold between the sampling point and a next sampling point.
The judging module 604 is configured to judge whether the intelligent flame detector fails according to the characteristic value of the background noise signal, and output a failure alarm signal if the intelligent flame detector fails; and if the intelligent flame detector is judged to be effective, executing subsequent operation.
Further, before the first signal obtaining module 501, the method may further include:
and the receiving module is used for receiving the sampling time, the rolling time window coefficient, the discrete counting, the identification signal characteristic value threshold and the background noise signal characteristic value which are reset by the remote terminal in a certain period when the environmental factors of the application environment exceed a certain change range.
The specific implementation of each module in this embodiment may refer to embodiment 1, which is not described herein any more; it should be noted that the system provided in this embodiment is only illustrated by the division of the functional modules, and in practical applications, the functions may be distributed by different functional modules according to needs, that is, the internal structure is divided into different functional modules to complete all or part of the functions described above.
It will be understood that the terms "first," "second," and the like as used in the above-described apparatus may be used to describe various modules, but these modules are not limited by these terms. These terms are only used to distinguish one module from another. For example, a first computing module may be referred to as a second computing module, and similarly, a second computing module may be referred to as a first computing module, both the first and second computing modules being computing modules, but not the same computing module, without departing from the scope of the present invention.
Example 3:
the present embodiment provides a storage medium, which is a computer-readable storage medium, and stores a computer program, and when the computer program is executed by a processor, the computer program implements the intelligent flame detection method of embodiment 1, as follows:
acquiring an infrared dynamic signal and an ultraviolet dynamic signal, and quantizing the signals respectively to obtain an infrared dynamic signal quantization value and an ultraviolet dynamic signal quantization value;
calculating the average intensity of dynamic signals and the discreteness of the dynamic signals in the mt time window according to the infrared dynamic signal quantized value and the ultraviolet dynamic signal quantized value, and counting the discreteness; wherein m is a rolling time window coefficient, and t is sampling time of a certain period;
obtaining a dynamic signal characteristic value according to the average intensity of the dynamic signal in the mt time window and the discreteness of the dynamic signal;
if the discrete count is greater than or equal to the effective count threshold, carrying out background noise elimination processing;
after background noise elimination processing is carried out, if the difference value between the dynamic signal characteristic value and the background noise signal characteristic value is greater than or equal to the identification signal characteristic value threshold, flame is identified, and a flame alarm signal is output.
Further, before acquiring the infrared dynamic signal and the ultraviolet dynamic signal at a certain period of sampling time, the method may further include:
selecting a certain time or a plurality of times of day and night as sampling points to obtain an infrared signal and an ultraviolet signal, and quantizing the infrared signal and the ultraviolet signal respectively to obtain an infrared signal quantization value and an ultraviolet signal quantization value;
calculating the average intensity, the infrared signal discreteness and the ultraviolet signal discreteness of the infrared signal and the ultraviolet signal in the mt time window according to the infrared signal quantified value and the ultraviolet signal quantified value;
obtaining a background noise signal characteristic value of the current day according to the signal average intensity and the signal discreteness in the mt time window, and using the background noise signal characteristic value as a detection signal threshold from the sampling point to the next sampling point;
judging whether the intelligent flame detector fails or not according to the characteristic value of the background noise signal, and outputting a failure alarm signal if the intelligent flame detector fails; and if the intelligent flame detector is judged to be effective, executing subsequent operation.
Further, according to the background noise signal characteristic value, whether the intelligent flame detector is invalid or not is judged, and the method specifically comprises the following steps:
and respectively comparing the background noise signal characteristic value with a preset minimum value and a preset maximum value, if the background noise signal characteristic value is greater than the preset maximum value or less than the preset minimum value, judging that the intelligent flame detector is invalid, and if the background noise signal characteristic value is greater than or equal to the preset minimum value and less than or equal to the preset maximum value, judging that the intelligent flame detector is valid.
Further, before acquiring the infrared dynamic signal and the ultraviolet dynamic signal at a certain period of sampling time, the method may further include:
and when the environmental factors of the application environment exceed a certain change range and change, receiving the sampling time, the rolling time window coefficient, the discrete counting, the identification signal characteristic value threshold and the background noise signal characteristic value of a certain period which are reset by the remote terminal.
The storage medium described in this embodiment may be a magnetic disk, an optical disk, a computer Memory, a Random Access Memory (RAM), a usb disk, a removable hard disk, or other media.
In summary, the invention applies the intelligent flame detection technology of remote communication control and self-adaptive elimination of background noise interference, can meet the application requirements of the flame detector in complex environment, can remotely and digitally set the detection sensitivity of the flame detector according to the change requirements of the application environment, and can also self-adaptively and automatically adjust the detection sensitivity in day and night environment, thus fundamentally solving the defect that the detection sensitivity of the flame detector is difficult to adjust after the flame detector is installed and used, can self-adaptively control the change of the environmental factors, can manually intervene to remotely control the flame detector when the change of the environmental factors exceeds the self-adaptive range, adjusts and sets the detection sensitivity of the flame detector, effectively inhibits the occurrence of the false alarm phenomenon of the flame detector, and is applicable to indoor closed space, semi-closed space, light shed or outdoor environment.
The above description is only for the preferred embodiments of the present invention, but the protection scope of the present invention is not limited thereto, and any person skilled in the art can substitute or change the technical solution and the inventive concept of the present invention within the scope of the present invention.
Claims (10)
1. An intelligent flame detection method, the method comprising:
acquiring an infrared dynamic signal and an ultraviolet dynamic signal at sampling time of a certain period, and quantizing the signals respectively to obtain an infrared dynamic signal quantization value and an ultraviolet dynamic signal quantization value;
calculating the average intensity of dynamic signals and the discreteness of the dynamic signals in the mt time window according to the infrared dynamic signal quantized value and the ultraviolet dynamic signal quantized value, and counting the discreteness; wherein m is a rolling time window coefficient, and t is sampling time of a certain period;
obtaining a dynamic signal characteristic value according to the average intensity of the dynamic signal in the mt time window and the discreteness of the dynamic signal;
if the discrete count is greater than or equal to the effective count threshold, carrying out background noise elimination processing;
after background noise elimination processing is carried out, if the difference value between the dynamic signal characteristic value and the background noise signal characteristic value is greater than or equal to the identification signal characteristic value threshold, flame is identified, and a flame alarm signal is output.
2. The intelligent flame detection method of claim 1, wherein before acquiring the infrared dynamic signal and the ultraviolet dynamic signal at a certain period of sampling time, the method further comprises:
selecting a certain time or a plurality of times of day and night as sampling points to obtain an infrared signal and an ultraviolet signal, and quantizing the infrared signal and the ultraviolet signal respectively to obtain an infrared signal quantization value and an ultraviolet signal quantization value;
calculating the average intensity, the infrared signal discreteness and the ultraviolet signal discreteness of the infrared signal and the ultraviolet signal in the mt time window according to the infrared signal quantified value and the ultraviolet signal quantified value;
obtaining a background noise signal characteristic value of the current day according to the signal average intensity and the signal discreteness in the mt time window, and using the background noise signal characteristic value as a detection signal threshold from the sampling point to the next sampling point;
judging whether the intelligent flame detector fails or not according to the characteristic value of the background noise signal, and outputting a failure alarm signal if the intelligent flame detector fails; and if the intelligent flame detector is judged to be effective, executing subsequent operation.
3. The intelligent flame detection method according to claim 2, wherein the determining whether the intelligent flame detector is disabled is based on the background noise signal characteristic value, and specifically comprises:
and respectively comparing the background noise signal characteristic value with a preset minimum value and a preset maximum value, if the background noise signal characteristic value is greater than the preset maximum value or less than the preset minimum value, judging that the intelligent flame detector is invalid, and if the background noise signal characteristic value is greater than or equal to the preset minimum value and less than or equal to the preset maximum value, judging that the intelligent flame detector is valid.
4. The intelligent flame detection method of claim 1, wherein before acquiring the infrared dynamic signal and the ultraviolet dynamic signal at a certain period of sampling time, the method further comprises:
and when the environmental factors of the application environment exceed a certain change range and change, receiving the sampling time, the rolling time window coefficient, the effective counting threshold, the identification signal characteristic value threshold and the background noise signal characteristic value which are reset by the remote terminal in a certain period.
5. The intelligent flame detection method of any one of claims 1-4, wherein the average intensity of the dynamic signal and the dispersion of the dynamic signal within the mt time window are calculated from the quantized values of the infrared dynamic signal and the ultraviolet dynamic signal, as follows:
p＝[A1,A2]
d＝d1+d2
wherein p represents the average intensity of the dynamic signal in the mt time window, A1 represents the average intensity of the infrared dynamic signal in the mt time window, and A2 represents the average intensity of the ultraviolet dynamic signal in the mt time window; d represents the dispersion of dynamic signals within the mt time window, d1 represents the dispersion of infrared dynamic signals within the mt time window, and d2 represents the dispersion of ultraviolet dynamic signals within the mt time window.
6. An intelligent flame detection device, the device comprising:
the signal acquisition module is used for acquiring the infrared dynamic signal and the ultraviolet dynamic signal at sampling time of a certain period, and quantizing the signals respectively to obtain an infrared dynamic signal quantization value and an ultraviolet dynamic signal quantization value;
the calculation module is used for calculating the average intensity of the dynamic signals and the discreteness of the dynamic signals in the mt time window according to the infrared dynamic signal quantized value and the ultraviolet dynamic signal quantized value, and counting the discreteness; wherein m is a rolling time window coefficient, and t is sampling time of a certain period;
the characteristic value acquisition module is used for acquiring a dynamic signal characteristic value according to the average intensity of the dynamic signal in the mt time window and the discreteness of the dynamic signal;
the background noise processing module is used for eliminating the background noise if the discrete count is greater than or equal to the effective count threshold;
and the output module is used for identifying flame and outputting a flame alarm signal if the difference value between the dynamic signal characteristic value and the background noise signal characteristic value is greater than or equal to the identification signal characteristic value threshold after background noise elimination processing.
7. An intelligent flame detector is characterized by comprising an infrared sensor, an ultraviolet sensor, an excitation and signal processing circuit and a remote terminal, wherein the infrared sensor and the ultraviolet sensor are respectively connected with the excitation and signal processing circuit;
the excitation and signal processing circuit is used for exciting the infrared sensor and the ultraviolet sensor and executing the intelligent flame detection method of any one of claims 1-5;
and the remote terminal is used for adjusting the sampling time, the rolling time window coefficient, the discrete counting and the identification signal characteristic value threshold of a certain period and sending the values to the excitation and signal processing circuit.
8. The intelligent flame detector of claim 7, further comprising a light sensitive sensor coupled to the excitation and signal processing circuitry;
the photosensitive sensor is used for identifying the change of day and night light of the application environment.
9. An intelligent flame detector, comprising a processor and a memory for storing a processor-executable program, wherein the processor, when executing the program stored in the memory, implements the intelligent flame detection method of any of claims 1-5.
10. A storage medium storing a program, wherein the program, when executed by a processor, implements the intelligent flame detection method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911405386.3A CN111105587B (en) | 2019-12-31 | 2019-12-31 | Intelligent flame detection method and device, detector and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911405386.3A CN111105587B (en) | 2019-12-31 | 2019-12-31 | Intelligent flame detection method and device, detector and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111105587A true CN111105587A (en) | 2020-05-05 |
| CN111105587B CN111105587B (en) | 2021-01-01 |
Family
ID=70424191
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911405386.3A Active CN111105587B (en) | 2019-12-31 | 2019-12-31 | Intelligent flame detection method and device, detector and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111105587B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111640278A (en) * | 2020-06-12 | 2020-09-08 | 无锡格林通安全装备有限公司 | Method for detecting cleanliness of window of multiband flame detector |
| CN111722546A (en) * | 2020-06-30 | 2020-09-29 | 广东美的厨房电器制造有限公司 | Control method and control device of sensor and cooking equipment |
| CN111986436A (en) * | 2020-09-02 | 2020-11-24 | 成都指码科技有限公司 | Comprehensive flame detection method based on ultraviolet and deep neural networks |
| CN113609769A (en) * | 2021-08-03 | 2021-11-05 | 无锡格林通安全装备有限公司 | Design method of multiband red ultraviolet hydrogen flame detector |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS62136603A (en) * | 1985-12-11 | 1987-06-19 | Sumitomo Bakelite Co Ltd | Filter for fire detector |
| US5552763A (en) * | 1993-11-10 | 1996-09-03 | Simplex Time Recorder Company | Fire alarm system with sensitivity adjustment |
| CN101493980A (en) * | 2009-03-05 | 2009-07-29 | 中国科学技术大学 | Rapid video flame detection method based on multi-characteristic fusion |
| CN201844880U (en) * | 2010-11-15 | 2011-05-25 | 上海翼捷工业安防技术有限公司 | Infrared and ultraviolet combined flame detector |
| CN103886344A (en) * | 2014-04-14 | 2014-06-25 | 西安科技大学 | Image type fire flame identification method |
| CN104318688A (en) * | 2014-10-31 | 2015-01-28 | 湘潭大学 | Multi-sensor fire early-warning method based on data fusion |
-
2019
- 2019-12-31 CN CN201911405386.3A patent/CN111105587B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS62136603A (en) * | 1985-12-11 | 1987-06-19 | Sumitomo Bakelite Co Ltd | Filter for fire detector |
| US5552763A (en) * | 1993-11-10 | 1996-09-03 | Simplex Time Recorder Company | Fire alarm system with sensitivity adjustment |
| CN101493980A (en) * | 2009-03-05 | 2009-07-29 | 中国科学技术大学 | Rapid video flame detection method based on multi-characteristic fusion |
| CN201844880U (en) * | 2010-11-15 | 2011-05-25 | 上海翼捷工业安防技术有限公司 | Infrared and ultraviolet combined flame detector |
| CN103886344A (en) * | 2014-04-14 | 2014-06-25 | 西安科技大学 | Image type fire flame identification method |
| CN104318688A (en) * | 2014-10-31 | 2015-01-28 | 湘潭大学 | Multi-sensor fire early-warning method based on data fusion |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111640278A (en) * | 2020-06-12 | 2020-09-08 | 无锡格林通安全装备有限公司 | Method for detecting cleanliness of window of multiband flame detector |
| CN111722546A (en) * | 2020-06-30 | 2020-09-29 | 广东美的厨房电器制造有限公司 | Control method and control device of sensor and cooking equipment |
| CN111986436A (en) * | 2020-09-02 | 2020-11-24 | 成都指码科技有限公司 | Comprehensive flame detection method based on ultraviolet and deep neural networks |
| CN111986436B (en) * | 2020-09-02 | 2022-12-13 | 成都视道信息技术有限公司 | Comprehensive flame detection method based on ultraviolet and deep neural networks |
| CN113609769A (en) * | 2021-08-03 | 2021-11-05 | 无锡格林通安全装备有限公司 | Design method of multiband red ultraviolet hydrogen flame detector |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111105587B (en) | 2021-01-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111105587B (en) | Intelligent flame detection method and device, detector and storage medium | |
| US8766807B2 (en) | Dynamic alarm sensitivity adjustment and auto-calibrating smoke detection | |
| CN103380661B (en) | Ambient light controls | |
| US20090060260A1 (en) | Intelligent image smoke/flame sensor and detection system | |
| CN104392577A (en) | Aerosol grain size sensing method based on dual-wavelength scattered signals and application of method to fire smoke detection | |
| US20120126975A1 (en) | Dynamic Alarm Sensitivity Adjustment and Auto-Calibrating Smoke Detection for Reduced Resource Microprocessors | |
| EP2357615B1 (en) | Video processing | |
| JP4327665B2 (en) | Electric blind control device | |
| US20140055280A1 (en) | Wireless communication monitoring device, wireless communication monitoring system, wireless communication monitoring method, and non-transitory computer-readable recording medium | |
| CN106913313B (en) | Sleep monitoring method and system | |
| KR20190109644A (en) | Apparatus and method for detecting greenhouse data collection error | |
| KR20200087339A (en) | Safety management apparatus for aging buildings based on internet of things | |
| EP3411678A1 (en) | A method and system to detect and quantify daylight that employs non-photo sensors | |
| JP2020071698A (en) | Fire detection device, fire detection method, and fire monitoring system | |
| CN111524311B (en) | Fire identification alarm judgment method | |
| CN113434538B (en) | Earthquake intensity assessment method and system based on population position data | |
| CN115359641B (en) | Regular false alarm judging method for photoelectric sensing equipment | |
| KR102271728B1 (en) | Empty house management system using logo projector and QR code | |
| EP3848917B1 (en) | Integrated fire alarm method and system | |
| US20230139436A1 (en) | Systems and methods for enhanced performance of camera devices | |
| Kim et al. | A fire alarm vision system based on IR image processing | |
| EP4111944A1 (en) | Estimating an actual light profile for an individual | |
| US10778957B2 (en) | Adjustable lighting in a stereo-optical counting device based on ambient lighting | |
| KR101858981B1 (en) | Intrusion detection apparatus by using co2 sensor | |
| KR20180063695A (en) | IoT System for detecting abnormal behavior using neural network theory |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |