CN116164844A - Multiband ultraviolet-infrared composite flame detector, control method thereof and electronic equipment - Google Patents
Multiband ultraviolet-infrared composite flame detector, control method thereof and electronic equipment Download PDFInfo
- Publication number
- CN116164844A CN116164844A CN202310127560.2A CN202310127560A CN116164844A CN 116164844 A CN116164844 A CN 116164844A CN 202310127560 A CN202310127560 A CN 202310127560A CN 116164844 A CN116164844 A CN 116164844A
- Authority
- CN
- China
- Prior art keywords
- flame
- ultraviolet
- mems thermopile
- signal processing
- processing unit
- 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.)
- Pending
Links
- 239000002131 composite material Substances 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012545 processing Methods 0.000 claims abstract description 89
- 230000005855 radiation Effects 0.000 claims abstract description 47
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 18
- 238000000605 extraction Methods 0.000 claims abstract description 15
- 230000003287 optical effect Effects 0.000 claims description 21
- 239000000463 material Substances 0.000 claims description 9
- 230000010354 integration Effects 0.000 claims description 4
- 239000002184 metal Substances 0.000 claims description 4
- 238000004806 packaging method and process Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 12
- 230000008569 process Effects 0.000 description 9
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 6
- 238000004590 computer program Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 6
- 230000000295 complement effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 229910044991 metal oxide Inorganic materials 0.000 description 5
- 150000004706 metal oxides Chemical class 0.000 description 5
- 238000001228 spectrum Methods 0.000 description 5
- 230000004913 activation Effects 0.000 description 4
- 238000002485 combustion reaction Methods 0.000 description 4
- 230000010485 coping Effects 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 229910002092 carbon dioxide Inorganic materials 0.000 description 3
- 239000001569 carbon dioxide Substances 0.000 description 3
- 238000011176 pooling Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000004377 microelectronic Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/0014—Radiation pyrometry, e.g. infrared or optical thermometry for sensing the radiation from gases, flames
- G01J5/0018—Flames, plasma or welding
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/02—Constructional details
- G01J5/03—Arrangements for indicating or recording specially adapted for radiation pyrometers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/10—Radiation pyrometry, e.g. infrared or optical thermometry using electric radiation detectors
- G01J5/12—Radiation pyrometry, e.g. infrared or optical thermometry using electric radiation detectors using thermoelectric elements, e.g. thermocouples
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
Abstract
The invention discloses a multiband ultraviolet-infrared composite flame detector, a control method thereof and electronic equipment, relating to the technical field of flame detectors, comprising the following steps: the system comprises a signal processing unit, a MEMS thermopile ultraviolet sensor, at least two MEMS thermopile infrared sensors and an alarm unit, wherein the MEMS thermopile ultraviolet sensor, the at least two MEMS thermopile infrared sensors and the alarm unit are respectively connected with the signal processing unit; the signal processing unit is used for receiving the corresponding wave band radiation signals transmitted by the MEMS thermopile ultraviolet sensor and the at least two MEMS thermopile infrared sensors, carrying out feature extraction processing based on the corresponding wave band radiation signals and a convolution learning algorithm, and controlling the alarm unit to carry out alarm prompt processing when the extracted actual feature value is matched with flame condition features in a pre-stored flame feature database, so that the flame identification accuracy can be effectively improved, false alarm can be effectively avoided, and the application range is wide.
Description
Technical Field
The invention relates to the technical field of flame detectors, in particular to a multiband ultraviolet-infrared composite flame detector, a control method thereof and electronic equipment.
Background
The principle of the photosensitive flame detector is as follows: the substances release a great deal of heat radiation when burned, generating continuous or discontinuous ultraviolet and infrared radiation of different wavelengths which are not recognizable by human eyes, wherein the carbon dioxide (CO) 2 ) The method comprises the steps of radiating and propagating in space in the form of electromagnetic waves, detecting ultraviolet radiation and infrared radiation in the environment by using an ultraviolet/infrared sensor, and judging that flame is generated when the ultraviolet/infrared sensor detects carbon dioxide radiation and reaches a certain threshold value.
Most of the existing ultraviolet-infrared composite flame detectors are integrated by two infrared sensors with different detection wave bands and one ultraviolet sensor. According to the first aspect, an infrared photosensitive tube or a pyroelectric infrared sensor is mostly used as the infrared sensor, output signals of the two infrared sensors are easy to be physically interfered by surrounding environments, a corresponding signal acquisition circuit is needed to be designed, in the second aspect, a plurality of artificial source radiation spectrums have peaks overlapped with flame radiation spectrums, an existing ultraviolet-infrared composite flame detector can identify an artificial light source as flame, a false alarm occurs, in the third aspect, flame judgment of the ultraviolet-infrared composite flame detector is realized by logically judging a threshold value of a radiation signal through a singlechip, and the threshold value of the judgment mode is fixed and cannot cope with flames of different combustibles.
In summary, the existing ultraviolet-infrared composite flame detector has the defects of less information collection, easy environmental interference and higher false alarm rate, and cannot cope with complex use environments in practical application.
Disclosure of Invention
The invention aims to provide a multiband ultraviolet-infrared composite flame detector, a control method thereof and electronic equipment, which solve the problems that the existing ultraviolet-infrared composite flame detector has the defects of less information quantity collection, easy environmental interference and higher false alarm rate and cannot cope with complex use environments in practical application
In a first aspect, the present invention provides a multi-band ultraviolet-infrared composite flame detector comprising:
the system comprises a signal processing unit, a MEMS thermopile ultraviolet sensor, at least two MEMS thermopile infrared sensors and an alarm unit, wherein the MEMS thermopile ultraviolet sensor, the at least two MEMS thermopile infrared sensors and the alarm unit are respectively connected with the signal processing unit;
the signal processing unit is used for receiving corresponding wave band radiation signals transmitted by the MEMS thermopile ultraviolet sensor and at least two MEMS thermopile infrared sensors, carrying out feature extraction processing based on the corresponding wave band radiation signals and a convolution learning algorithm, and controlling the alarm unit to carry out alarm prompt processing when the extracted actual feature value is matched with flame condition features in a pre-stored flame feature database.
Under the condition of adopting the technical scheme, the multiband ultraviolet and infrared composite flame detector provided by the embodiment of the invention comprises: the system comprises a signal processing unit, and a MEMS thermopile ultraviolet sensor, at least two MEMS thermopile infrared sensors and an alarm unit which are respectively connected with the signal processing unit. The signal processing unit is used for receiving a corresponding wave band radiation signal transmitted by the MEMS thermopile ultraviolet sensor and at least two MEMS thermopile infrared sensors, carrying out feature extraction processing based on the corresponding wave band radiation signal and a convolution learning algorithm, controlling the alarm unit to carry out alarm prompt processing when the extracted actual feature value is matched with flame condition features in a pre-stored flame feature database, effectively and stably acquiring ultraviolet and infrared radiation signals, effectively improving flame identification accuracy, effectively avoiding false alarm, simultaneously adopting a complementary metal oxide semiconductor-micro electro mechanical system integrated process for batch manufacturing of the MEMS thermopile ultraviolet sensor and the MEMS thermopile infrared sensors, having low cost and wide application range, and being capable of coping with complex use environments in practical applications.
In one possible implementation, the MEMS thermopile ultraviolet sensor and at least two of the MEMS thermopile infrared sensors are configured using different filters corresponding to the same type and kind of thermopile chip integration.
In one possible implementation manner, the MEMS thermopile ultraviolet sensor and the MEMS thermopile infrared sensor comprise a MEMS thermopile sensing chip, an application specific integrated circuit chip and the optical filters corresponding to corresponding wave bands, and the MEMS thermopile ultraviolet sensor or the MEMS thermopile infrared sensor is obtained by metal packaging the MEMS thermopile sensing chip, the application specific integrated circuit chip and the optical filters corresponding to corresponding wave bands;
the special integrated circuit chip is used for amplifying, filtering and analog-to-digital conversion respectively on the voltage signals generated by the MEMS thermopile sensing chip, and the optical filters corresponding to the corresponding wave bands are used for allowing light rays of the corresponding wave bands to pass through.
In one possible implementation, the at least two MEMS thermopile infrared sensors comprise three MEMS thermopile infrared sensors.
In one possible implementation, the band of light allowed to pass through by the corresponding optical filter in the MEMS thermopile ultraviolet sensor is 185 nm to 260 nm; the wave bands of the light which the optical filters corresponding to the three MEMS thermopile infrared sensors allow light to pass through are respectively 2.7 microns, 4.35 microns and 4.8 microns.
In one possible implementation manner, the alarm unit includes a buzzer, a warning lamp and a display subunit respectively connected with the signal processing unit, where the signal processing unit is used to control the alarm unit to perform alarm prompt processing, and includes:
the signal processing unit is used for controlling the buzzer and the warning lamp to give an alarm and controlling the display subunit to display the material and the size information of the flame.
In a second aspect, the present invention further provides a control method of a multiband ultraviolet-infrared composite flame detector, applied to any one of the multiband ultraviolet-infrared composite flame detectors in the first aspect, the control method comprising:
the signal processing unit receives corresponding wave band radiation signals transmitted by the MEMS thermopile ultraviolet sensor and at least two MEMS thermopile infrared sensors;
the signal processing unit performs feature extraction based on the corresponding band radiation signals and a convolution learning algorithm;
and when the extracted actual characteristic value is matched with the flame condition characteristic in the pre-stored flame characteristic database, the signal processing unit controls the alarm unit to carry out alarm prompt processing.
In one possible implementation manner, after the signal processing unit performs feature extraction based on the corresponding band radiation signal and a convolution learning algorithm, the method further includes:
the signal processing unit performs back propagation when the extracted actual characteristic value is not matched with flame condition characteristics in a pre-stored flame characteristic database, and obtains a deviation value of the actual characteristic value and the flame condition characteristics;
and the signal processing unit updates the weight value based on the deviation value, and circulates the step of matching the extracted actual characteristic value with the flame condition characteristic in the pre-stored flame characteristic database until the extracted actual characteristic value is matched with the flame condition characteristic in the pre-stored flame characteristic database.
In one possible implementation manner, the signal processing unit controls the alarm unit to perform alarm prompt processing when the extracted actual characteristic value matches with a flame condition characteristic in a pre-stored flame characteristic database, and the method includes:
the signal processing unit is used for controlling the buzzer and the warning lamp to give an alarm and controlling the display subunit to display the material and the size information of the flame.
The beneficial effects of the control method of the multiband ultraviolet infrared composite flame detector provided in the second aspect are the same as those of the multiband ultraviolet infrared composite flame detector described in the first aspect or any possible implementation manner of the first aspect, and are not described in detail herein.
In a third aspect, the present invention also provides an electronic device, including: one or more processors; and one or more machine readable media having instructions stored thereon, which when executed by the one or more processors, cause the apparatus to perform the method of controlling a multi-band ultraviolet-infrared composite flame detector described in any of the possible implementations of the second aspect.
The beneficial effects of the electronic device provided in the third aspect are the same as the beneficial effects of the control method of the multiband ultraviolet infrared composite flame detector described in the second aspect or any possible implementation manner of the second aspect, and are not described herein.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:
FIG. 1 shows a schematic structural diagram of a multiband ultraviolet-infrared composite flame detector provided in an embodiment of the present application;
FIG. 2 illustrates a flow chart of a machine learning training flame signature database algorithm provided by an embodiment of the present application;
FIG. 3 is a schematic flow chart of a control method of a multiband ultraviolet-infrared composite flame detector according to an embodiment of the present application;
fig. 4 is a schematic hardware structure of an electronic device according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a chip according to an embodiment of the present invention.
Reference numerals:
101-a signal processing unit; 102-a MEMS thermopile ultraviolet sensor; 103-MEMS thermopile infrared sensor; 104-an alarm unit; an A-MEMS thermopile sensing chip; b-an application specific integrated circuit chip; a C-filter; d-packaging the tube seat; e-pipe cap; 1031. 1032, 1033-three MEMS thermopile infrared sensors; 1041-a buzzer; 1042-warning light; 300-an electronic device; 310-a processor; 340-communication lines; 320-a communication interface; 330-memory; 3101-a first processor; 3102-a second processor; 400-chip; 450-bus system.
Detailed Description
In order to clearly describe the technical solution of the embodiments of the present invention, in the embodiments of the present invention, the words "first", "second", etc. are used to distinguish the same item or similar items having substantially the same function and effect. For example, the first threshold and the second threshold are merely for distinguishing between different thresholds, and are not limited in order. It will be appreciated by those of skill in the art that the words "first," "second," and the like do not limit the amount and order of execution, and that the words "first," "second," and the like do not necessarily differ.
In the present invention, the words "exemplary" or "such as" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.
In the present invention, "at least one" means one or more, and "a plurality" means two or more. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a alone, a and B together, and B alone, wherein a, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b or c may represent: a, b, c, a and b, a and c, b and c, or a, b and c, wherein a, b, c can be single or multiple.
Fig. 1 shows a schematic structural diagram of a multiband ultraviolet-infrared composite flame detector provided in an embodiment of the present application, as shown in fig. 1 (a) and fig. 1 (b), where the multiband ultraviolet-infrared composite flame detector includes:
a signal processing unit 101, and one MEMS thermopile ultraviolet sensor 102, at least two MEMS thermopile infrared sensors 103 and an alarm unit 104 respectively connected to the signal processing unit.
The signal processing unit 101 is configured to receive the corresponding band radiation signals transmitted by the MEMS thermopile ultraviolet sensor 102 and the at least two MEMS thermopile infrared sensors 103, perform feature extraction processing based on the corresponding band radiation signals in combination with a convolution learning algorithm, and control the alarm unit 104 to perform alarm prompt processing when the extracted actual feature value matches with a flame condition feature in a pre-stored flame feature database.
The multiband ultraviolet-infrared composite flame detector provided by the embodiment of the invention comprises: the system comprises a signal processing unit, and a MEMS thermopile ultraviolet sensor, at least two MEMS thermopile infrared sensors and an alarm unit which are respectively connected with the signal processing unit. The signal processing unit is used for receiving a corresponding wave band radiation signal transmitted by the MEMS thermopile ultraviolet sensor and at least two MEMS thermopile infrared sensors, carrying out feature extraction processing based on the corresponding wave band radiation signal and a convolution learning algorithm, controlling the alarm unit to carry out alarm prompt processing when the extracted actual feature value is matched with flame condition features in a pre-stored flame feature database, effectively and stably acquiring ultraviolet and infrared radiation signals, effectively improving flame identification accuracy, effectively avoiding false alarm, simultaneously adopting a complementary metal oxide semiconductor-micro-electromechanical system (Complementary Metal Oxide Semiconductor-Micro Electronic Mechanical Systems, CMOS-MEMS) integrated process for batch manufacturing of the MEMS thermopile ultraviolet sensor and the MEMS thermopile infrared sensors, being low in cost and wide in application range, and being capable of coping with complex use environments in practical application.
In the application, the MEMS thermopile ultraviolet sensor and at least two MEMS thermopile infrared sensors are formed by applying different optical filters corresponding to the integration of thermopile chips of the same type and the same kind, the same type thermopile chips are adopted to manufacture the ultraviolet/infrared sensors, only one signal acquisition circuit is needed, the thermopile ultraviolet/infrared sensors have the advantages of being capable of measuring constant radiation quantity, free of bias voltage, free of chopper and the like, and the corresponding band optical filters can be provided to realize accurate measurement of spectrum radiation of different bands, so that the device is more suitable for flame radiation signal detection in complex environments.
Optionally, referring to fig. 1, the MEMS thermopile ultraviolet sensor 102 and the MEMS thermopile infrared sensor 103 include a MEMS thermopile sensing chip a, an application specific integrated circuit chip B, and the optical filter C corresponding to a corresponding wavelength band, and the MEMS thermopile ultraviolet sensor 102 or the MEMS thermopile infrared sensor 103 is obtained by metal packaging the MEMS thermopile sensing chip a, the application specific integrated circuit chip B, and the optical filter C corresponding to a corresponding wavelength band;
the special integrated circuit chip is used for amplifying, filtering and analog-to-digital (A/D) conversion processing on the voltage signals generated by the MEMS thermopile sensing chip, and the optical filters corresponding to the corresponding wave bands are used for allowing light rays of the corresponding wave bands to pass through.
The metal package may be a TO46 package, among others.
Optionally, referring to fig. 1, the multiband ultraviolet-infrared composite flame detector further includes a package stem D and a stem cap E.
Alternatively, referring to fig. 1, the at least two MEMS thermopile infrared sensors include three MEMS thermopile infrared sensors (1031, 1032, and 1033).
In the present application, the at least two MEMS thermopile infrared sensors may be two, three or four, and may be other number of infrared sensors, which is not limited in this application, where each infrared sensor works in its own band, the more infrared is, the more multiband radiation information can be collected, and the more accurate flame detection will be.
Optionally, a wave band of 185 nm to 260 nm which allows light to pass through by the corresponding optical filter in the MEMS thermopile ultraviolet sensor; the wave bands of the light which the optical filters corresponding to the three MEMS thermopile infrared sensors allow light to pass through are respectively 2.7 microns, 4.35 microns and 4.8 microns, and the four-band radiation signals can be transmitted to a computer in real time for feature extraction.
It should be noted that the artificial light source generally has a radiation peak near 4.8 microns and no flame, and the invention adds the radiation sensor of the wave band, so as to avoid false alarm caused by the artificial light source.
Optionally, referring to fig. 1, the alarm unit 104 includes a buzzer 1041, a warning lamp 1042, and a display subunit respectively connected to the signal processing unit 101, where the signal processing unit is configured to control the alarm unit to perform alarm prompting processing, and includes:
the signal processing unit is used for controlling the buzzer and the warning lamp to give an alarm and controlling the display subunit to display the material and the size information of the flame.
The warning light may be a Light Emitting Diode (LED) warning light, or may be other types of warning lights, which is not specifically limited in the embodiment of the present application.
In this application, the signal processing unit 101 is further configured to perform back propagation when the extracted actual feature value does not match the flame condition feature in the pre-stored flame feature database, and calculate a deviation value between the actual feature value and the flame condition feature; and the signal processing unit updates the weight value based on the deviation value, and circulates the step of matching the extracted actual characteristic value with the flame condition characteristic in the pre-stored flame characteristic database until the extracted actual characteristic value is matched with the flame condition characteristic in the pre-stored flame characteristic database.
Specifically, fig. 2 shows a flow chart of a flame characteristic database algorithm formed by machine learning training provided by the embodiment of the application, as shown in fig. 2, after initialization, in the forward propagation process, the input electric response data of four sensors (one MEMS thermopile ultraviolet sensor and three MEMS thermopile infrared sensors) are subjected to convolution and pooling treatment of a plurality of convolution layers, characteristic vectors are provided, the characteristic vectors are transmitted into a fully connected layer, and a classification and identification result is obtained, namely, four-band spectral information and target output are obtained, the output of each unit of a hidden layer and an output layer is further obtained, the error between an actual output value and a target value is obtained, and when the error e is in an allowable range, namely, when the output result accords with the flame combustion state, the flame is output and a fire early warning result is carried out. And when the result output by the convolutional neural network does not accord with the flame combustion state, back propagation is carried out. And calculating errors of actual output values and target values, calculating errors of neurons in a network layer when the error e is not in an allowable range, returning the errors layer by layer, calculating the errors of each layer, namely calculating an error gradient, and then updating the weight.
The error updating process of the convolution layer is as follows: and taking the error matrix as a convolution kernel, convoluting the input feature map to obtain a deviation matrix of the weight, and adding the deviation matrix with the weight of the original convolution kernel to obtain an updated convolution kernel. The process is continuously circulated by inputting four-band spectrum information of different flame states, and finally a flame characteristic database is obtained. According to the flame characteristic database, the flame state can be accurately, efficiently and conveniently judged. Namely, based on a machine learning algorithm, the characteristic data of various flames are extracted, a flame characteristic database is established, and the functions of accurately identifying flame materials and sizes are realized
In the present application, the value of the error e is generated when the computer calculates, and under the condition that high accuracy is required, the smaller the value of e is, the better the value of e is, which is not particularly limited, and the embodiment of the present application can be specifically adjusted according to the actual application scenario.
The four-band spectrum information is waveform information read by four sensors, namely radiation intensity information of four bands.
The flame combustion state can be the materials of small, medium and large fires and combustion, and the corresponding parameters are information acquired by four sensors, namely specific values measured by the four sensors at 185-260 nm, 2.7 microns, 4.35 microns and 4.8 microns respectively. For example, all wood fires, then all four sensors will have a value within a fixed small range.
In the application, the four sensors in the figure 1 (b) all use the sensor structure in the figure 1 (a), but the filters of the four sensors are different and are respectively 185-260 nanometers, 2.7 micrometers, 4.35 micrometers and 4.8 micrometers, and the sensors are not easily affected by the environment and are more stable, and the thermopile sensors with the same structure are more convenient to produce and can reduce the cost; the system side adopts a machine learning algorithm to distinguish flame states, can distinguish flames generated by different materials and flame sizes, is different from a singlechip threshold value to judge flames, can only judge flames to be in a state of being larger than a certain value of a sensor, can effectively and stably acquire ultraviolet and infrared radiation signals, effectively improves flame identification accuracy, effectively avoids false alarm, simultaneously, the MEMS thermopile ultraviolet sensor and the MEMS thermopile infrared sensor can be manufactured in batches by adopting a CMOS-MEMS integrated process, and the system side has the advantages of low cost, wide application range and capability of coping with complex use environments in practical application.
It should also be noted that the machine learning algorithm includes a convolution layer, a pooling layer, an activation function, and a full connection layer. The purpose of convolution operations is to extract different features of the input, and more layers of the network can iteratively extract more complex features from low-level features. The convolution layer extracts flame characteristics of different fire phases according to the electrical output information of the ultraviolet sensor and the infrared sensor. Because the input of the flame detector is provided with four signal channels, the convolution kernel is provided with four channels, each convolution kernel channel is convolved with the corresponding channel of the input layer, and the convolution result of each channel is added according to the bit to obtain the final characteristic. The characteristic extraction capability of the convolution layer can collect the obvious characteristic information in four sensors when flame is generated to the greatest extent, and accurately distinguish the flame state. The pooling layer is mainly used for sub-sampling the flame characteristic diagram learned by the convolution layer, and has the significance of reducing the input dimension of a subsequent network layer, reducing the size of a model, improving the calculation speed, improving the robustness of the characteristics and preventing over-fitting. After weighted summation, the input is calculated by using a function, namely an activation function, wherein the activation function introduces nonlinear characteristics into a convolution network, and the activation function plays an important role in model learning and understanding of very complex and nonlinear functions. The full connection layer spreads the feature map (matrix) obtained by the convolution of the last layer into one-dimensional vectors and provides input for the classifier. And finally, the classifier collates the characteristic information corresponding to different flame states, namely a flame characteristic database, so that the flame state can be judged when the flame detector is actually applied.
The multiband ultraviolet-infrared composite flame detector provided by the embodiment of the invention comprises: the system comprises a signal processing unit, and a MEMS thermopile ultraviolet sensor, at least two MEMS thermopile infrared sensors and an alarm unit which are respectively connected with the signal processing unit. The signal processing unit is used for receiving corresponding wave band radiation signals transmitted by the MEMS thermopile ultraviolet sensor and at least two MEMS thermopile infrared sensors, carrying out feature extraction processing based on the corresponding wave band radiation signals and a convolution learning algorithm, controlling the alarm unit to carry out alarm prompt processing when the extracted actual feature value is matched with flame condition features in a pre-stored flame feature database, effectively and stably acquiring ultraviolet and infrared radiation signals, effectively improving flame identification accuracy, effectively avoiding false alarm, simultaneously adopting a complementary metal oxide semiconductor-micro electro mechanical system integrated process for batch manufacturing of the MEMS thermopile ultraviolet sensor and the MEMS thermopile infrared sensors, having low cost and wide application range, being capable of coping with complex use environments in practical application, adopting a homotype thermopile chip to manufacture the ultraviolet/infrared sensor when the extracted actual feature value is matched with flame condition features in the pre-stored flame feature database, only needing a signal thermopile infrared sensor, having constant radiation detection accuracy, needing no bias voltage, being capable of being applied to realize accurate wave band detection, being applicable to the detection of the radiation of the corresponding wave band, and the like.
Fig. 3 shows a flow chart of a control method of a multiband ultraviolet-infrared composite flame detector provided in an embodiment of the present application, which is applied to the multiband ultraviolet-infrared composite flame detector shown in fig. 1, as shown in fig. 3, the control method of the multiband ultraviolet-infrared composite flame detector includes:
step 201: the signal processing unit receives corresponding wave band radiation signals transmitted by the MEMS thermopile ultraviolet sensor and at least two MEMS thermopile infrared sensors.
Step 202: and the signal processing unit performs feature extraction based on the corresponding band radiation signals and a convolution learning algorithm.
Step 203: and when the extracted actual characteristic value is matched with the flame condition characteristic in the pre-stored flame characteristic database, the signal processing unit controls the alarm unit to carry out alarm prompt processing.
Specifically, the signal processing unit is used for controlling the buzzer and the warning lamp to give an alarm and controlling the display subunit to display the material and the size information of the flame.
In the present application, the method further comprises: the signal processing unit performs back propagation when the extracted actual characteristic value is not matched with flame condition characteristics in a pre-stored flame characteristic database, and obtains a deviation value of the actual characteristic value and the flame condition characteristics;
and the signal processing unit updates the weight value based on the deviation value, and circulates the step of matching the extracted actual characteristic value with the flame condition characteristic in the pre-stored flame characteristic database until the extracted actual characteristic value is matched with the flame condition characteristic in the pre-stored flame characteristic database.
According to the control method of the multiband ultraviolet-infrared composite flame detector, provided by the embodiment of the invention, the signal processing unit receives the corresponding band radiation signals transmitted by the MEMS thermopile ultraviolet sensor and at least two MEMS thermopile infrared sensors, the signal processing unit performs feature extraction based on the corresponding band radiation signals and combines a convolution learning algorithm, and when the extracted actual feature value is matched with the flame condition feature in the pre-stored flame feature database, the signal processing unit controls the alarm unit to perform alarm prompt processing, ultraviolet and infrared radiation signals can be effectively and stably acquired, the flame recognition accuracy is effectively improved, false alarm is effectively avoided, meanwhile, the MEMS thermopile ultraviolet sensor and the MEMS thermopile infrared sensors can be manufactured in batches by adopting complementary metal oxide semiconductor-micro-electromechanical system integration processes, the cost is low, the application range is wide, and the complex use environment in practical application can be met.
The control method of the multiband ultraviolet infrared composite flame detector provided by the invention is applied to the multiband ultraviolet infrared composite flame detector shown in fig. 1, and is not repeated here.
The electronic device in the embodiment of the invention can be a device, a component in a terminal, an integrated circuit, or a chip. The device may be a mobile electronic device or a non-mobile electronic device. By way of example, the mobile electronic device may be a cell phone, tablet computer, notebook computer, palm computer, vehicle mounted electronic device, wearable device, ultra-mobile personal computer (ultra-mobile personal computer, UMPC), netbook or personal digital assistant (personal digital assistant, PDA), etc., and the non-mobile electronic device may be a server, network attached storage (Network Attached Storage, NAS), personal computer (personal computer, PC), television (TV), teller machine or self-service machine, etc., and embodiments of the present invention are not limited in particular.
The electronic device in the embodiment of the invention can be a device with an operating system. The operating system may be an Android operating system, an IOS operating system, or other possible operating systems, and the embodiment of the present invention is not limited specifically.
Fig. 4 shows a schematic hardware structure of an electronic device according to an embodiment of the present invention. As shown in fig. 4, the electronic device 300 includes a processor 310.
As shown in FIG. 4, the processor 310 may be a general purpose central processing unit (central processing unit, CPU), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present invention.
As shown in fig. 4, the electronic device 300 may further include a communication line 340. Communication line 340 may include a path to communicate information between the components described above.
Optionally, as shown in fig. 4, the electronic device may further include a communication interface 320. The communication interface 320 may be one or more. The communication interface 320 may use any transceiver-like device for communicating with other devices or communication networks.
Optionally, as shown in fig. 4, the electronic device may further comprise a memory 330. Memory 330 is used to store computer-executable instructions for performing aspects of the present invention and is controlled by the processor for execution. The processor is configured to execute computer-executable instructions stored in the memory, thereby implementing the method provided by the embodiment of the invention.
As shown in fig. 4, the memory 330 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (random access memory, RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (electrically erasable programmable read-only memory, EEPROM), a compact disc (compact disc read-only memory) or other optical disk storage, optical disk storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited thereto. Memory 330 may be a stand-alone device coupled to processor 310 via communication line 340. Memory 330 may also be integrated with processor 310.
Alternatively, the computer-executable instructions in the embodiments of the present invention may be referred to as application program codes, which are not particularly limited in the embodiments of the present invention.
In a particular implementation, as one embodiment, as shown in FIG. 4, processor 310 may include one or more CPUs, such as CPU0 and CPU1 in FIG. 4.
In a specific implementation, as an embodiment, as shown in fig. 4, the terminal device may include a plurality of processors, such as a first processor 3101 and a second processor 3102 in fig. 4. Each of these processors may be a single-core processor or a multi-core processor.
Fig. 5 is a schematic structural diagram of a chip according to an embodiment of the present invention. As shown in fig. 5, the chip 400 includes one or more (including two) processors 310.
Optionally, as shown in fig. 5, the chip further includes a communication interface 320 and a memory 330, and the memory 330 may include a read-only memory and a random access memory, and provides operation instructions and data to the processor. A portion of the memory may also include non-volatile random access memory (non-volatile random access memory, NVRAM).
In some implementations, as shown in FIG. 5, the memory 330 stores elements, execution modules or data structures, or a subset thereof, or an extended set thereof.
In the embodiment of the present invention, as shown in fig. 5, by calling the operation instruction stored in the memory (the operation instruction may be stored in the operating system), the corresponding operation is performed.
As shown in fig. 5, the processor 310 controls the processing operation of any one of the terminal devices, and the processor 310 may also be referred to as a central processing unit (central processing unit, CPU).
As shown in fig. 5, memory 330 may include read-only memory and random access memory and provides instructions and data to the processor. A portion of the memory 330 may also include NVRAM. Such as a memory, a communication interface, and a memory coupled together by a bus system that may include a power bus, a control bus, a status signal bus, etc., in addition to a data bus. But for clarity of illustration the various buses are labeled as bus system 450 in fig. 5.
As shown in fig. 5, the method disclosed in the above embodiment of the present invention may be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or by instructions in the form of software. The processor may be a general purpose processor, a digital signal processor (digital signal processing, DSP), an ASIC, an off-the-shelf programmable gate array (field-programmable gate array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.
In one aspect, a computer readable storage medium is provided, in which instructions are stored, which when executed, implement the functions performed by the terminal device in the above embodiments.
In one aspect, a chip for use in a terminal device is provided, the chip including at least one processor and a communication interface coupled to the at least one processor, the processor configured to execute instructions to implement the functions performed by the multi-band ultraviolet-infrared composite flame detector in the above embodiments.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present invention are performed in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, a terminal, a user equipment, or other programmable apparatus. The computer program or instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer program or instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired or wireless means. The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that integrates one or more available media. The usable medium may be a magnetic medium, e.g., floppy disk, hard disk, tape; optical media, such as digital video discs (digital video disc, DVD); but also semiconductor media such as solid state disks (solid state drive, SSD).
Although the invention is described herein in connection with various embodiments, other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the "a" or "an" does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage. Although the invention has been described in connection with specific features and embodiments thereof, it will be apparent that various modifications and combinations can be made without departing from the spirit and scope of the invention. Accordingly, the specification and drawings are merely exemplary illustrations of the present invention as defined in the appended claims and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the invention. It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. A multi-band ultraviolet-infrared composite flame detector, characterized in that the multi-band ultraviolet-infrared composite flame detector comprises:
the system comprises a signal processing unit, a MEMS thermopile ultraviolet sensor, at least two MEMS thermopile infrared sensors and an alarm unit, wherein the MEMS thermopile ultraviolet sensor, the at least two MEMS thermopile infrared sensors and the alarm unit are respectively connected with the signal processing unit;
the signal processing unit is used for receiving corresponding wave band radiation signals transmitted by the MEMS thermopile ultraviolet sensor and at least two MEMS thermopile infrared sensors, carrying out feature extraction processing based on the corresponding wave band radiation signals and a convolution learning algorithm, and controlling the alarm unit to carry out alarm prompt processing when the extracted actual feature value is matched with flame condition features in a pre-stored flame feature database.
2. The multi-band ultraviolet infrared composite flame detector of claim 1, wherein the MEMS thermopile ultraviolet sensor and at least two of the MEMS thermopile infrared sensors are configured using different filters corresponding to the same type and kind of thermopile chip integration.
3. The multi-band ultraviolet-infrared composite flame detector according to claim 2, wherein the MEMS thermopile ultraviolet sensor and the MEMS thermopile infrared sensor comprise MEMS thermopile sensing chips, application specific integrated circuit chips and the optical filters corresponding to respective bands, and the MEMS thermopile ultraviolet sensor or the MEMS thermopile infrared sensor is obtained by metal packaging the MEMS thermopile sensing chips, the application specific integrated circuit chips and the optical filters corresponding to respective bands;
the special integrated circuit chip is used for amplifying, filtering and analog-to-digital conversion respectively on the voltage signals generated by the MEMS thermopile sensing chip, and the optical filters corresponding to the corresponding wave bands are used for allowing light rays of the corresponding wave bands to pass through.
4. A multi-band ultraviolet infrared composite flame detector according to claim 3, wherein the at least two MEMS thermopile infrared sensors comprise three MEMS thermopile infrared sensors.
5. The multi-band ultraviolet-infrared composite flame detector according to claim 4, wherein the band of light allowed by the corresponding optical filter in the MEMS thermopile ultraviolet sensor is 185 nm to 260 nm; the wave bands of the light which the optical filters corresponding to the three MEMS thermopile infrared sensors allow light to pass through are respectively 2.7 microns, 4.35 microns and 4.8 microns.
6. The multi-band ultraviolet-infrared composite flame detector according to claim 1, wherein the alarm unit comprises a buzzer, a warning lamp and a display subunit respectively connected with the signal processing unit, and the signal processing unit is used for controlling the alarm unit to perform alarm prompt processing, and comprises:
the signal processing unit is used for controlling the buzzer and the warning lamp to give an alarm and controlling the display subunit to display the material and the size information of the flame.
7. A control method of a multiband ultraviolet-infrared composite flame detector, characterized in that it is applied to the multiband ultraviolet-infrared composite flame detector according to any one of claims 1 to 6, the control method comprising:
the signal processing unit receives corresponding wave band radiation signals transmitted by the MEMS thermopile ultraviolet sensor and at least two MEMS thermopile infrared sensors;
the signal processing unit performs feature extraction based on the corresponding band radiation signals and a convolution learning algorithm;
and when the extracted actual characteristic value is matched with the flame condition characteristic in the pre-stored flame characteristic database, the signal processing unit controls the alarm unit to carry out alarm prompt processing.
8. The method for controlling a multiband ultraviolet-infrared composite flame detector according to claim 7, further comprising, after the signal processing unit performs feature extraction based on the corresponding band radiation signal in combination with a convolution learning algorithm:
the signal processing unit performs back propagation when the extracted actual characteristic value is not matched with flame condition characteristics in a pre-stored flame characteristic database, and obtains a deviation value of the actual characteristic value and the flame condition characteristics;
and the signal processing unit updates the weight value based on the deviation value, and circulates the step of matching the extracted actual characteristic value with the flame condition characteristic in the pre-stored flame characteristic database until the extracted actual characteristic value is matched with the flame condition characteristic in the pre-stored flame characteristic database.
9. The method for controlling a multiband ultraviolet-infrared composite flame detector according to claim 7, wherein the signal processing unit controls the alarm unit to perform alarm prompt processing when the extracted actual characteristic value matches with a flame condition characteristic in a pre-stored flame characteristic database, comprising:
the signal processing unit is used for controlling the buzzer and the warning lamp to give an alarm and controlling the display subunit to display the material and the size information of the flame.
10. An electronic device, comprising: one or more processors; and one or more machine readable media having instructions stored thereon that, when executed by the one or more processors, cause performance of the method of controlling a multi-band ultraviolet-infrared composite flame detector of any of claims 7-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310127560.2A CN116164844A (en) | 2023-02-02 | 2023-02-02 | Multiband ultraviolet-infrared composite flame detector, control method thereof and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310127560.2A CN116164844A (en) | 2023-02-02 | 2023-02-02 | Multiband ultraviolet-infrared composite flame detector, control method thereof and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116164844A true CN116164844A (en) | 2023-05-26 |
Family
ID=86421561
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310127560.2A Pending CN116164844A (en) | 2023-02-02 | 2023-02-02 | Multiband ultraviolet-infrared composite flame detector, control method thereof and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116164844A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117518175A (en) * | 2023-11-09 | 2024-02-06 | 大庆安瑞达科技开发有限公司 | Method for rapidly finding fire source by infrared Zhou Saolei reaching wide area range |
-
2023
- 2023-02-02 CN CN202310127560.2A patent/CN116164844A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117518175A (en) * | 2023-11-09 | 2024-02-06 | 大庆安瑞达科技开发有限公司 | Method for rapidly finding fire source by infrared Zhou Saolei reaching wide area range |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Manno et al. | Deep learning strategies for automatic fault diagnosis in photovoltaic systems by thermographic images | |
| CN113853239B (en) | Intelligent identification and alarm method and system | |
| AU2010317664B2 (en) | Anomaly detection of radiological signatures | |
| Li et al. | Fall detection for elderly person care using convolutional neural networks | |
| US20220337788A1 (en) | System and method for remote detection and location of gas leaks | |
| JP6009016B2 (en) | Motion and gesture recognition by passive single-pixel thermal sensor system | |
| CN116164844A (en) | Multiband ultraviolet-infrared composite flame detector, control method thereof and electronic equipment | |
| US10996169B2 (en) | Multi-spectral fluorescent imaging | |
| CN108760053A (en) | A kind of volume temperature detection method and device | |
| Son et al. | Video based smoke and flame detection using convolutional neural network | |
| CN111666826A (en) | Method, apparatus, electronic device and computer-readable storage medium for processing image | |
| US11788886B2 (en) | Wearable device and method for measuring ultra-violet light with visible light sensor | |
| US20180350062A1 (en) | Gate-level mapping of integrated circuits using multi-spectral imaging | |
| CN114667546A (en) | System and method for hyper-spectral imaging and artificial intelligence assisted automatic identification of drugs | |
| JP4711131B2 (en) | Pixel group parameter calculation method and pixel group parameter calculation apparatus | |
| CA1202504A (en) | Method and apparatus for converting spectral and light intensity values | |
| US20220011165A1 (en) | Elevated temperature screening using pattern recognition in thermal images | |
| Chen et al. | Moisture contents and product quality prediction of Pu‐erh tea in sun‐drying process with image information and environmental parameters | |
| Sampaio et al. | Leveraging deep neural networks for automatic and standardised wound image acquisition | |
| CN109269984B (en) | Automatic turbidity classification system | |
| CN116206221B (en) | Water flare detection method and system | |
| CN108760595B (en) | Distributed gas turbidity monitoring point | |
| Sumriddetchkajorn et al. | Palm-size wide-band three-dimensional multispectral imaging camera | |
| CN108872029B (en) | Gas turbidity processing node | |
| Liang et al. | Rapid Identification of the Species of Bloodstain Based on Near Infrared Spectroscopy and Convolutional Neural Network-Support Vector Machine Algorithm |
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 |