CN114018326A - Low-voltage transformer area environment multi-parameter detection method based on micro-system sensor array - Google Patents
Low-voltage transformer area environment multi-parameter detection method based on micro-system sensor array Download PDFInfo
- Publication number
- CN114018326A CN114018326A CN202111294437.7A CN202111294437A CN114018326A CN 114018326 A CN114018326 A CN 114018326A CN 202111294437 A CN202111294437 A CN 202111294437A CN 114018326 A CN114018326 A CN 114018326A
- Authority
- CN
- China
- Prior art keywords
- sensor array
- concentration
- micro
- current
- kernel function
- 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 38
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 12
- 230000007613 environmental effect Effects 0.000 claims abstract description 11
- 238000000605 extraction Methods 0.000 claims abstract description 10
- 238000013507 mapping Methods 0.000 claims abstract description 10
- 230000006870 function Effects 0.000 claims description 43
- 238000012706 support-vector machine Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 16
- 238000000034 method Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 9
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 claims description 6
- 239000013618 particulate matter Substances 0.000 claims description 6
- 229910052710 silicon Inorganic materials 0.000 claims description 6
- 239000010703 silicon Substances 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 238000007499 fusion processing Methods 0.000 claims description 5
- 230000004927 fusion Effects 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000004907 flux Effects 0.000 claims description 3
- 238000012886 linear function Methods 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 7
- 206010063385 Intellectualisation Diseases 0.000 abstract description 3
- 230000010354 integration Effects 0.000 abstract description 3
- 239000002245 particle Substances 0.000 description 12
- 238000009296 electrodeionization Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 7
- 230000009471 action Effects 0.000 description 5
- 239000004020 conductor Substances 0.000 description 5
- 150000002500 ions Chemical class 0.000 description 5
- 239000000779 smoke Substances 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000005684 electric field Effects 0.000 description 4
- 230000006698 induction Effects 0.000 description 4
- 238000004377 microelectronic Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000005284 excitation Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 206010000369 Accident Diseases 0.000 description 2
- 238000009792 diffusion process Methods 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 239000003574 free electron Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000002035 prolonged effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 239000011540 sensing material Substances 0.000 description 2
- WSFSSNUMVMOOMR-UHFFFAOYSA-N Formaldehyde Chemical compound O=C WSFSSNUMVMOOMR-UHFFFAOYSA-N 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000005674 electromagnetic induction Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002086 nanomaterial Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000011295 pitch Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A50/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE in human health protection, e.g. against extreme weather
- Y02A50/20—Air quality improvement or preservation, e.g. vehicle emission control or emission reduction by using catalytic converters
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Other Investigation Or Analysis Of Materials By Electrical Means (AREA)
Abstract
The invention discloses a low-voltage transformer area environment multi-parameter detection method based on a micro-system sensor array, which comprises the following steps: adopting a structural mapping algorithm to establish a one-to-one corresponding relation between the output current of the micro-system sensor array and each parameter, eliminating cross interference among the parameters and obtaining an accurate model for simultaneously detecting multiple parameters; wherein the plurality of parameters includes temperature, humidity, gas concentration, current, and magnetic field; the microsystem sensor array comprises a plurality of three-electrode structure ionization sensors; the cathodes of the ionization sensors with the three-electrode structures are manufactured on the same polar plate, and the extraction electrode and the collector have the same structure but different polar distances; and acquiring the output current of the micro-system sensor array, and obtaining the environmental multi-parameter value of the low-voltage transformer area through the accurate model matching. The invention has the advantages of high integration level, small volume, high intellectualization and digitization level, low cost and the like.
Description
Technical Field
The invention mainly relates to the technical field of environmental parameter measurement, in particular to a low-voltage transformer area environment multi-parameter detection method based on a micro-system sensor array.
Background
With the rapid development of microelectronic technology, micro and nano technology aiming at processing micro and nano structures and systems has come into play, and a new revolution is opened in the field of small machine manufacturing, resulting in the birth of Micro Electro Mechanical Systems (MEMS). The MEMS is the widening and extending of the microelectronic technology, and fuses the microelectronic technology and the precise mechanical processing technology, so that the system integrating the microelectronic technology and the mechanical technology is realized, the shape structure of micron or even below micron can be processed, and the MEMS device has the characteristics which can not be achieved by the traditional sensor, thereby having wide application prospect.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: aiming at the problems in the prior art, the invention provides the low-voltage transformer area environment multi-parameter detection method based on the micro-system sensor array, which has high automation degree and low cost.
In order to solve the technical problems, the technical scheme provided by the invention is as follows:
a low-voltage transformer area environment multi-parameter detection method based on a micro-system sensor array comprises the following steps:
adopting a structural mapping algorithm to establish a one-to-one corresponding relation between the output current of the micro-system sensor array and each parameter, eliminating cross interference among the parameters and obtaining an accurate model for simultaneously detecting multiple parameters; wherein the plurality of parameters includes temperature, humidity, gas concentration, current, and magnetic field; the microsystem sensor array comprises a plurality of three-electrode structure ionization sensors; the cathodes of the ionization sensors with the three-electrode structures are manufactured on the same polar plate, and the extraction electrode and the collector have the same structure but different polar distances;
and acquiring the output current of the micro-system sensor array, and obtaining the environmental multi-parameter value of the low-voltage transformer area through the accurate model matching.
Preferably wherein the gas comprises H2、C2H2And CH4The data fusion process of the mixed gas detection under the corresponding temperature interference is as follows: the structure mapping algorithm is a support vector machine, wherein a support vector machine model of mixed gas and temperature comprises an input layer, a kernel function layer and an output layer; using sensor array to output current vector I ═ IH2,IC2H2,IC2H4,IT]And a support vector Ik＝[IkH2,IkC2H2,IkC2H4,IkT]As an input layer, values phi 'are calculated by the concentrations of three components in the mixed gas and temperature'H2、φ'C2H2、φ'C2H4And T' is a model output layer; a kernel function layer is arranged between the input layer and the output layer, and the kernel function has various forms including a linear kernel function, a polynomial kernel function, an RBF kernel function and a tensor product kernel function; the support vector machine structure passes through a kernel function K (I, I)k) The operation maps the data of the input space to the high-dimensional feature space, and then the data are mapped by the Lagrangian multiplier a1k–a4kAnd the offset (b 1-b 4) to achieve data fitting.
Preferably, NO/SO under temperature interference2/O2The data fusion process of the detection of the mixed gas and the particulate matter of the/PM 1/PM2.5/PM4/PM10 is as follows: NO/SO detection for micro-system sensor array2/O2The support vector machine of the/PM 1/PM2.5/PM4/PM10 mixed gas, particulate matter and temperature is composed of an input layer, a kernel function layer and an output layer; the input layer comprises a current vector I ═ I formed by collector currents of sensors with different polar distances in the silicon micron column three-electrode sensor arrayT,INO,ISO2,IO2,IPM1,IPM2.5,IPM4,IPM10]And a support vector I formed by taking the calibration experimental data of the sensor array as a training samplek＝[IkT,IkNO,IkSO2,IkO2,IkPM1,IkPM2.5,IkPM4,IkPM10](ii) a The kernel function layer includes kernel functions K (I, I)k) Lagrange multiplier alpha1k-α8kAnd a threshold value bkN is the number of training samples; the kernel function layer maps the data of the input layer to a high-dimensional characteristic space through a kernel function, and determines a linear function through a Lagrange multiplier and a threshold value to realize data flux fusion; the output layer outputs the temperature, NO concentration and SO of the current vector I of the collector of the corresponding sensor array2Concentration, O2Concentration, PM1 concentration, PM2.5 concentration, PM4 concentration, and PM10 concentration.
Preferably, the temperature T ' and the NO concentration phi ' are obtained according to a support vector machine structure model 'NO、SO2Concentration phi'SO2、O2Concentration phi'O2And PM1 concentration phi'PM1And PM2.5 concentration phi'PM2.5And PM4 concentration phi'PM4And PM10 concentration phi'PM10The relationship to the collected current of the microsystem sensor array is as follows:
in the formula: alpha is alpha1k-α8kLagrange multiplier, k ═ 1,2,3 … 570; i isjCollecting electrode current value of a silicon micron column three-electrode sensor array, wherein j is 1,2,3 … 8; i iskjTraining sample data for a support vector machine, k being 1,2,3 … 570; j is 1,2,3 … 8.
Preferably, the structural algorithm comprises a neural network and a support vector machine.
The invention also discloses a low-voltage transformer area environment multi-parameter detection system based on the micro-system sensor array, which comprises the following components:
the first program module is used for establishing a one-to-one corresponding relation between the output current of the micro-system sensor array and each parameter by adopting a structural mapping algorithm, eliminating cross interference among the parameters and obtaining an accurate model for simultaneously detecting multiple parameters; wherein the plurality of parameters includes temperature, humidity, gas concentration, current, and magnetic field; the microsystem sensor array comprises a plurality of three-electrode structure ionization sensors; the cathodes of the ionization sensors with the three-electrode structures are manufactured on the same polar plate, and the extraction electrode and the collector have the same structure but different polar distances;
and the second program module is used for acquiring the output current of the micro-system sensor array and obtaining the environmental multi-parameter value of the low-voltage transformer area through the accurate model matching.
The invention further discloses a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the low-pressure stage area environment multi-parameter detection method based on a microsystem sensor array as described above.
The invention also discloses computer equipment which comprises a memory and a processor, wherein the memory is stored with a computer program, and the computer program is executed by the processor to execute the steps of the low-pressure platform area environment multi-parameter detection method based on the micro-system sensor array.
Compared with the prior art, the invention has the advantages that:
the invention can detect the environmental temperature, humidity, smoke dust and weak current through the micro-system sensor array, can judge whether the fire accident happens or not by detecting the environmental smoke concentration, and has the advantages of wide measuring range, high resolution, high response speed, high integration level and small volume; the current situation of on-line monitoring false alarm of the current power grid is actively improved, the intellectualization and the digitization of the power system are promoted, the updating of the detection standard of the power industry is promoted, the cost of comprehensive intelligent sensing materials and equipment of the domestic power system is reduced in a large proportion, and the maximization of the monitoring benefit of the equipment state is realized.
Drawings
FIG. 1 is a schematic structural diagram of a microsystem sensor array according to an embodiment of the present invention.
FIG. 2 is a diagram of the spatial point position of the long straight conductor according to the present invention.
FIG. 3 is a diagram illustrating the force deflection of the charged particles in the magnetic field according to the present invention.
FIG. 4 is a flow chart of an embodiment of the method of the present invention.
Detailed Description
The invention is further described below with reference to the figures and the specific embodiments of the description.
As shown in fig. 4, the method for detecting multiple parameters of the environment of the low-voltage distribution room based on the micro-system sensor array according to the embodiment of the present invention includes the steps of:
adopting a structural mapping algorithm to establish a one-to-one corresponding relation between the output current of the micro-system sensor array and each parameter, eliminating cross interference among the parameters and obtaining an accurate model for simultaneously detecting multiple parameters; wherein the plurality of parameters includes temperature, humidity, gas concentration, current, and magnetic field; the microsystem sensor array comprises a plurality of three-electrode structure ionization sensors; wherein cathodes 1 of a plurality of ionization sensors with three-electrode structures are manufactured on the same polar plate, and an extraction electrode 2 and a collector electrode 3 have the same structure but different polar distances, as shown in fig. 1;
and acquiring the output current of the micro-system sensor array, and obtaining the environmental multi-parameter value of the low-voltage transformer area through the accurate model matching.
The micro-system sensor array can detect the ambient temperature, humidity, smoke dust and weak current, can judge whether a fire accident occurs or not by detecting the concentration of the ambient smoke, and has the advantages of wide range, high resolution, high response speed, high integration level and small volume; the current situation of on-line monitoring false alarm of the current power grid is actively improved, the intellectualization and the digitization of the power system are promoted, the updating of the detection standard of the power industry is promoted, the cost of comprehensive intelligent sensing materials and equipment of the domestic power system is reduced in a large proportion, and the maximization of the monitoring benefit of the equipment state is realized.
Specifically, the theoretical basis of temperature detection is as follows: the three-electrode ionization type sensor is extremely sensitive to temperature (formulas (1) to (3)), has the characteristics of thermal emission and thermal ionization, and can detect the temperature, and particularly:
I＝I0eαd (1)
α＝APe-BPE (2)
wherein I is the sensor output current; i is0Is the initial discharge current; j is a function ofeIs the cathode emission current density; α is a first ionization coefficient of the gas; d is the distance of the alpha process; e is the cathode nanotip electric field strength; p is the gas pressure; a and B are constants related to the gas species and temperature; epsilon0Is the absolute permittivity; Φ is the electron work function before application of the electric field; e is the amount of charge carried by one electron; b isEIs the emission constant, whose value is related to the material and the surface condition; k is the boltzmann constant; collecting current IcIs part of I, then Ic(t); temperature rise, current IcAnd (4) increasing.
The theoretical basis of humidity detection is as follows: the collector current and the relative humidity of the three-electrode ionization type sensor show a monotonous rising trend, and the collector current of the sensor gradually increases along with the increase of the relative humidity. Wherein the relative humidity is measured as follows:
Pw＝RH×PS (4)
in the formula, PwIs the pressure, P, of the water vapor currently being measuredsIs the pressure of saturated steam, PsThe calculation of (c) uses the Wexler formula:
wherein T is the absolute temperature of water vapor, C0＝-6.044×103；C1＝1.893×101；C2＝-2.824×10-2；C3＝1.724×10-5；C4＝2.858。
In gas impact ionization, when the temperature and the excitation voltage are fixed, the water vapor impact ionization coefficient alpha is mainly determined by the water vapor pressure PwThe expression is:
the smoke detection theoretical basis is as follows: first ionization coefficient alpha and gas species and concentration
Related to, collecting current IcThe change of (2) can reflect the change of the gas type and concentration between the sensor electrodes, and can be used for detecting the gas concentration. In addition, when particles exist between the sensor electrodes, a part of positive ions collide with the particles to transfer charges, so that the particles are charged. Under the action of concentration gradient, the charged particles and the rest positive ions move to the extraction electrode through diffusion; after passing through the extraction hole, the collector moves in an accelerated manner under the action of a reverse electric field. Arrival and receptionAfter the collector, the collector collects charged particles and positive ions to generate collector current Ic。
Known gas discharge current Ic＝I0eαdThe equation (7), (8), and (9) are obtained by using α -APe-BP/E and the ideal gas state equation PV-nRT, which show that the change of the particle concentration causes the change of the discharge current. Wherein P is the gas pressure; v is the gas volume; r is the ideal gas constant.
The theoretical basis of current detection is as follows: the current is measured indirectly according to the law of electromagnetic induction. For the induced magnetic field generated by any infinitesimal current d l with the same direction current I in the current-carrying long straight wire, the infinitesimal dB direction is the same, and according to the BioSaval law, the induced magnetic field at the point A can be known as follows:
wherein θ is the angle between the connection line of A point and any point on the long straight conductor and the long straight conductor. Perpendicular AO along point A, AO length r0The distance of the wire element d l from point l is:
wherein theta is1、θ2Is L1、L2The angle theta value corresponding to the two ends of the wire L1、L2At infinite distance between two points, θ1＝0、θ2Pi, substituting formula (11) has:
equation (13) shows that when a current I passes through a conductor, magnetic induction B is generated around the conductor, and the magnetic induction B is proportional to the current I. It can be seen that the basic principle of the current sensor is: the magnetic induction B at a fixed position inside the current sensor is accurately measured, and the magnitude and direction of the measured current are obtained through signal processing, as shown in FIG. 2.
The theoretical basis of magnetic field detection is as follows: the three-electrode ionization type sensor is based on the discharge principle, when the three-electrode ionization type sensor is placed in a magnetic field, free electrons generate rotation and migration movement, namely larmor movement, due to the action of magnetic field force near a discharge area, the movement path of the three-electrode ionization type sensor is prolonged, the residence time between polar plates is prolonged, the collision frequency of the free electrons and gas molecules is increased, the ionization of the gas molecules near a discharge electrode is effectively enhanced, the concentration of charged particles is improved, and the discharge current density j is increased (formula 14). Meanwhile, according to the equation of motion of electrons and the equation of energy of electrons in the magnetic field (equations 15 and 16), the energy of electrons Q will also increase with the magnetic field. The increase in electron energy increases the probability of electron impact ionization, thereby producing more positive ions and increasing the collection current density jc.
Where μ is the charged particle mobility, N is the charged particle density, v is the charged particle velocity, E is the electric field strength, DMGFThe diffusion coefficient of the plasma under the action of a magnetic field, and B is magnetic induction intensity; m is electron mass, e is electron charge, veIs the electron motion velocity.
Meanwhile, electrons and positive ions generated by the interelectrode discharge are subjected to the action force of the magnetic field, as shown in fig. 3; for example, inwardly or outwardly under the influence of the magnetic field Bx, thereby influencing the collection current Ic.
The theoretical basis of simultaneous detection of multiple parameters is as follows: due to the nonlinear relation between the collecting current Ic and the polar distance d of the sensor, the output current values Ic of the sensors with different polar distances are different, and the sensors with different polar distances can be used for simultaneously detecting multiple parameters. The cathodes of a plurality of sensors are manufactured on the same polar plate, and the extraction electrode and the collector have the same structure but different polar distances.
Wherein d is1、d2、…、dnDifferent pole pitches of the sensor; function f0、f1、…、fnRespectively describe d1、
And temperature, humidity, gas to sensor output I1The influence of (a); a is0、a1、…、anAre respectively f0、f1、…、fnThe coefficient of (a); b0、b1、…、bnAre respectively g0、g1…、gnThe coefficient of (a); c. C0、c1、…、cnAre respectively h0、h1、…、hnThe coefficient of (a).
Through experimental calibration, a model of the multi-parameter to be measured and the output current of the sensor can be established, and measurement is realized.
In a specific embodiment, a one-to-one correspondence relationship between the output current of the sensor array and each parameter is established by adopting a structural mapping algorithm such as a neural network, a support vector machine and the like, so that cross interference among the parameters is eliminated, and an accurate model for simultaneously detecting multiple parameters is obtained.
In one embodiment, a three-electrode ionization sensor implements a single CH4、SO2、C2H2、H2、NO、CH2And detecting the O gas concentration, wherein the collecting current of the sensor is reduced along with the increase of the gas concentration. The lowest detection values are respectively CH4(2ppt)、SO2(15ppt)、C2H2(1ppm)、H2(20ppt)、NO(70ppt)、CH2O (50 ppt). The pulse power supply is used as the excitation of the sensor, so that the hysteresis problem of the sensor is solved, and the breakthrough of the sensor in the aspect of gas detection is realized. By optimizing the pulse excitation condition, the detection accuracy of the sensor can be further improved. Wherein, the three-electrode ionization type sensor with three different polar distances forms a sensor array, and realizes three components H2/C2H2/CH4Gas, NO/SO2Temperature and CH4/H2/C2H2/C2H4Simultaneous detection of/CO/temperature.
In one embodiment, in performing multi-sensor data fusion, a support vector machine model for a sensor array to detect a three-component gas mixture and temperature includes an input layer, a kernel function layer, and an output layer. Using sensor array to output current vector I ═ IH2,IC2H2,IC2H4,IT]And a support vector Ik＝[IkH2,IkC2H2,IkC2H4,IkT](k-1, 2, …, n) as an input layer, and phi 'is calculated by the concentrations of three components in the mixed gas and the temperatures'H2、φ'C2H2、φ'C2H4And T' is a model output layer. The kernel function layer is arranged between the input layer and the output layer, and the kernel function K (I, I)k) In many forms, e.g. linear kernel functionsPolynomial kernel function, RBF kernel function, tensor product kernel function, and the like. The support vector machine structure passes through a kernel function K (I, I)k) The operation maps the data of the input space to the high-dimensional feature space, and then the data are mapped by the Lagrangian multiplier a1k–a4k(k-1, 2, …,1248) and offset b1–b4The determined linear regression function achieves data fitting.
In one embodiment, the NO/SO is present under temperature disturbances2/O2The data fusion process of the detection of the mixed gas and the particulate matter of the/PM 1/PM2.5/PM4/PM10 is as follows:
NO/SO detection for sensor array2/O2The support vector machine for the mixed gas, the particulate matter and the temperature of the/PM 1/PM2.5/PM4/PM10 is composed of an input layer, a kernel function layer and an output layer. The input layer comprises a current vector I ═ I formed by collector currents of sensors with different polar distances in the silicon micron column three-electrode sensor arrayT,INO,ISO2,IO2,IPM1,IPM2.5,IPM4,IPM10]And a support vector I formed by taking the calibration experimental data of the sensor array as a training samplek＝[IkT,IkNO,IkSO2,IkO2,IkPM1,IkPM2.5,IkPM4,IkPM10]. The kernel function layer includes kernel functions K (I, I)k) Lagrange multiplier alpha1k-α8k(k is 1,2 … n) and a threshold value bk(k ═ 1,2 … 8), n is the number of training samples; the kernel function layer maps the data of the input layer to a high-dimensional characteristic space through a kernel function, and the data flux fusion is realized through a Lagrange multiplier and a threshold value to determine a linear function. The output layer outputs the temperature, NO concentration and SO of the current vector I of the collector of the corresponding sensor array2Concentration, O2Concentration, PM1 concentration, PM2.5 concentration, PM4 concentration, and PM10 concentration.
Obtaining the temperature T ' and NO concentration phi ' according to a support vector machine structure model 'NO、SO2Concentration phi'SO2、O2Concentration phi'O2And PM1 concentration phi'PM1And PM2.5 concentration phi'PM2.5And PM4 concentration phi'PM4And PM10 concentration phi'PM10The relationship to the current collected by the sensor array is:
in the formula: alpha is alpha1k-α8k(k ═ 1,2,3 … 570) is the lagrange multiplier; i isj(j ═ 1,2,3 … 8) for collector current values for silicon micron pillar three-electrode sensor arrays; i iskjAnd (k is 1,2,3 … 570, and j is 1,2,3 … 8) is the training sample data of the support vector machine. After the structural parameters of the support vector machine are optimized by the particle swarm optimization, the model is used for temperature and O2The concentration, PM1 concentration, PM4 concentration, and PM10 concentration have large errors. For NO concentration, SO2 concentration, PThe M2.5 concentration error is small, and the maximum quote errors are all less than 5%.
The embodiment of the invention also discloses a low-voltage transformer area environment multi-parameter detection system based on the micro-system sensor array, which comprises the following components:
the first program module is used for establishing a one-to-one corresponding relation between the output current of the micro-system sensor array and each parameter by adopting a structural mapping algorithm, eliminating cross interference among the parameters and obtaining an accurate model for simultaneously detecting multiple parameters; wherein the plurality of parameters includes temperature, humidity, gas concentration, current, and magnetic field; the microsystem sensor array comprises a plurality of three-electrode structure ionization sensors; the cathodes of the ionization sensors with the three-electrode structures are manufactured on the same polar plate, and the extraction electrode and the collector have the same structure but different polar distances;
and the second program module is used for acquiring the output current of the micro-system sensor array and obtaining the environmental multi-parameter value of the low-voltage transformer area through the accurate model matching.
The detection system of the invention corresponds to the detection method and has the advantages of the method.
The embodiment of the invention further discloses a computer readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, executes the steps of the low-pressure platform area environment multi-parameter detection method based on the micro-system sensor array. The embodiment of the invention also discloses computer equipment which comprises a memory and a processor, wherein the memory is stored with a computer program, and the computer program is executed by the processor to execute the steps of the low-pressure platform area environment multi-parameter detection method based on the micro-system sensor array.
All or part of the flow of the method of the embodiments may be implemented by a computer program, which may be stored in a computer-readable storage medium and executed by a processor, to implement the steps of the embodiments of the methods. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution media, and the like. The memory may be used to store computer programs and/or modules, and the processor may perform various functions by executing or executing the computer programs and/or modules stored in the memory, as well as by invoking data stored in the memory. The memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above-mentioned embodiments, and all technical solutions belonging to the idea of the present invention belong to the protection scope of the present invention. It should be noted that modifications and embellishments within the scope of the invention may be made by those skilled in the art without departing from the principle of the invention.
Claims (8)
1. A low-voltage transformer area environment multi-parameter detection method based on a micro-system sensor array is characterized by comprising the following steps:
adopting a structural mapping algorithm to establish a one-to-one corresponding relation between the output current of the micro-system sensor array and each parameter, eliminating cross interference among the parameters and obtaining an accurate model for simultaneously detecting multiple parameters; wherein the plurality of parameters includes temperature, humidity, gas concentration, current, and magnetic field; the microsystem sensor array comprises a plurality of three-electrode structure ionization sensors; the cathodes of the ionization sensors with the three-electrode structures are manufactured on the same polar plate, and the extraction electrode and the collector have the same structure but different polar distances;
and acquiring the output current of the micro-system sensor array, and obtaining the environmental multi-parameter value of the low-voltage transformer area through the accurate model matching.
2. The method of claim 1, wherein the gas comprises H, and wherein the gas comprises H2、C2H2And CH4The data fusion process of the mixed gas detection under the corresponding temperature interference is as follows: the structure mapping algorithm is a support vector machine, wherein a support vector machine model of mixed gas and temperature comprises an input layer, a kernel function layer and an output layer; using sensor array to output current vector I ═ IH2,IC2H2,IC2H4,IT]And a support vector Ik＝[IkH2,IkC2H2,IkC2H4,IkT]As an input layer, values phi 'are calculated by the concentrations of three components in the mixed gas and temperature'H2、φ'C2H2、φ'C2H4And T' is a model output layer; a kernel function layer is arranged between the input layer and the output layer, and the kernel function has various forms including a linear kernel function, a polynomial kernel function, an RBF kernel function and a tensor product kernel function; the support vector machine structure passes through a kernel function K (I, I)k) The operation maps the data of the input space to the high-dimensional feature space, and then the data are mapped by the Lagrangian multiplier a1k–a4kAnd the offset (b 1-b 4) to achieve data fitting.
3. The method of claim 1, wherein the method of detecting the environmental multiparameter of the low pressure area based on the microsystem sensor array is characterized in that NO/SO is generated under temperature disturbance2/O2The data fusion process of the detection of the mixed gas and the particulate matter of the/PM 1/PM2.5/PM4/PM10 is as follows: NO/SO detection for micro-system sensor array2/O2The support vector machine of the/PM 1/PM2.5/PM4/PM10 mixed gas, particulate matter and temperature is composed of an input layer, a kernel function layer and an output layer; the input layer comprises sensors with different polar distances in a silicon micron column three-electrode sensor arrayCollector current forming current vector I ═ IT,INO,ISO2,IO2,IPM1,IPM2.5,IPM4,IPM10]And a support vector I formed by taking the calibration experimental data of the sensor array as a training samplek＝[IkT,IkNO,IkSO2,IkO2,IkPM1,IkPM2.5,IkPM4,IkPM10](ii) a The kernel function layer includes kernel functions K (I, I)k) Lagrange multiplier alpha1k-α8kAnd a threshold value bkN is the number of training samples; the kernel function layer maps the data of the input layer to a high-dimensional characteristic space through a kernel function, and determines a linear function through a Lagrange multiplier and a threshold value to realize data flux fusion; the output layer outputs the temperature, NO concentration and SO of the current vector I of the collector of the corresponding sensor array2Concentration, O2Concentration, PM1 concentration, PM2.5 concentration, PM4 concentration, and PM10 concentration.
4. The low-pressure platform area environment multi-parameter detection method based on the micro-system sensor array as claimed in claim 3, wherein the temperature T ' and NO concentration phi ' are obtained according to a support vector machine structure model 'NO、SO2Concentration phi'SO2、O2Concentration phi'O2And PM1 concentration phi'PM1And PM2.5 concentration phi'PM2.5And PM4 concentration phi'PM4And PM10 concentration phi'PM10The relationship to the collected current of the microsystem sensor array is as follows:
in the formula: alpha is alpha1k-α8kLagrange multiplier, k ═ 1,2,3 … 570; i isjCollecting electrode current value of a silicon micron column three-electrode sensor array, wherein j is 1,2,3 … 8; i iskjTraining sample data for a support vector machine, k being 1,2,3 … 570; j is 1,2,3 … 8.
5. The method for detecting the environment multiparameter of the low-pressure platform area based on the micro-system sensor array as claimed in any one of claims 1 to 4, wherein the structural algorithm comprises a neural network and a support vector machine.
6. A low-pressure platform area environment multi-parameter detection system based on a micro-system sensor array is characterized by comprising:
the first program module is used for establishing a one-to-one corresponding relation between the output current of the micro-system sensor array and each parameter by adopting a structural mapping algorithm, eliminating cross interference among the parameters and obtaining an accurate model for simultaneously detecting multiple parameters; wherein the plurality of parameters includes temperature, humidity, gas concentration, current, and magnetic field; the microsystem sensor array comprises a plurality of three-electrode structure ionization sensors; the cathodes of the ionization sensors with the three-electrode structures are manufactured on the same polar plate, and the extraction electrode and the collector have the same structure but different polar distances;
and the second program module is used for acquiring the output current of the micro-system sensor array and obtaining the environmental multi-parameter value of the low-voltage transformer area through the accurate model matching.
7. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for the low-pressure stage area environment multi-parameter detection based on a microsystem sensor array according to any of claims 1 to 5.
8. Computer device comprising a memory and a processor, said memory having stored thereon a computer program, wherein said computer program, when being executed by the processor, is adapted to carry out the steps of the method for the multi-parameter sensing of an environment of a low pressure area based on an array of microsystems sensors according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111294437.7A CN114018326B (en) | 2021-11-03 | 2021-11-03 | Low-voltage transformer area environment multi-parameter detection method based on microsystem sensor array |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111294437.7A CN114018326B (en) | 2021-11-03 | 2021-11-03 | Low-voltage transformer area environment multi-parameter detection method based on microsystem sensor array |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114018326A true CN114018326A (en) | 2022-02-08 |
| CN114018326B CN114018326B (en) | 2024-04-16 |
Family
ID=80060321
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111294437.7A Active CN114018326B (en) | 2021-11-03 | 2021-11-03 | Low-voltage transformer area environment multi-parameter detection method based on microsystem sensor array |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114018326B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB1348562A (en) * | 1971-08-19 | 1974-03-20 | Plesishvtsev Nv Semashko Nn | Plasma source of charged particles |
| EP0981060A2 (en) * | 1998-08-20 | 2000-02-23 | Forschungszentrum Jülich Gmbh | Method and apparatus for near-surface detection of sub-surface current-density distribution |
| US20060155486A1 (en) * | 2004-10-07 | 2006-07-13 | Walsh Alicia M | Computer-implemented system and method for analyzing mixtures of gases |
| CN102095782A (en) * | 2011-02-16 | 2011-06-15 | 西安交通大学 | Gas on-line detection device based on micro-nano carbon nano tube film three-electrode |
| CN104614437A (en) * | 2015-02-15 | 2015-05-13 | 太原理工大学 | Electrode spacing optimization method for carbon nanotube three-electrode gas sensor |
| CN106248779A (en) * | 2016-08-03 | 2016-12-21 | 西安交通大学 | There is Jenner's metre hole thin film three electrode ionizing transducer array of temperature compensation function |
| CN108228538A (en) * | 2017-12-29 | 2018-06-29 | 航天科工智慧产业发展有限公司 | SO in a kind of city2The Forecasting Methodology of concentration value |
| US20180217086A1 (en) * | 2017-02-02 | 2018-08-02 | Sandia Corporation | Mixed-Potential Electrochemical Sensor |
| CN108445298A (en) * | 2018-03-28 | 2018-08-24 | 南京林业大学 | A kind of field coupling type induction conductivity sensor and its characteristic compensation device |
| CN110278648A (en) * | 2019-06-26 | 2019-09-24 | 中国人民解放军陆军装甲兵学院 | The influence research method of magnetic field configuration plasma depression effect |
| CN110287600A (en) * | 2019-06-26 | 2019-09-27 | 中国人民解放军陆军装甲兵学院 | Flowing and pressure investigation method of the magnetic controlled plasma in cylinder |
| CN112577864A (en) * | 2020-11-19 | 2021-03-30 | 西安交通大学 | Silicon micron column array three-electrode ionization type microsystem haze sensor and preparation method thereof |
| CN112684262A (en) * | 2020-11-19 | 2021-04-20 | 西安交通大学 | Silicon micron column array three-electrode ionization type MEMS electric field sensor and preparation method thereof |
| KR20210109400A (en) * | 2020-02-27 | 2021-09-06 | 주식회사 센서위드유 | Hazardous gas sensor platform with deep-learning technology to improve target gas detection and prediction in the in the mixed gas environment |
| CN113375716A (en) * | 2021-06-01 | 2021-09-10 | 国网重庆市电力公司电力科学研究院 | Self-powered power transmission line on-line monitoring system based on multi-sensor data fusion |
-
2021
- 2021-11-03 CN CN202111294437.7A patent/CN114018326B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB1348562A (en) * | 1971-08-19 | 1974-03-20 | Plesishvtsev Nv Semashko Nn | Plasma source of charged particles |
| EP0981060A2 (en) * | 1998-08-20 | 2000-02-23 | Forschungszentrum Jülich Gmbh | Method and apparatus for near-surface detection of sub-surface current-density distribution |
| US20060155486A1 (en) * | 2004-10-07 | 2006-07-13 | Walsh Alicia M | Computer-implemented system and method for analyzing mixtures of gases |
| CN102095782A (en) * | 2011-02-16 | 2011-06-15 | 西安交通大学 | Gas on-line detection device based on micro-nano carbon nano tube film three-electrode |
| CN104614437A (en) * | 2015-02-15 | 2015-05-13 | 太原理工大学 | Electrode spacing optimization method for carbon nanotube three-electrode gas sensor |
| CN106248779A (en) * | 2016-08-03 | 2016-12-21 | 西安交通大学 | There is Jenner's metre hole thin film three electrode ionizing transducer array of temperature compensation function |
| US20180217086A1 (en) * | 2017-02-02 | 2018-08-02 | Sandia Corporation | Mixed-Potential Electrochemical Sensor |
| CN108228538A (en) * | 2017-12-29 | 2018-06-29 | 航天科工智慧产业发展有限公司 | SO in a kind of city2The Forecasting Methodology of concentration value |
| CN108445298A (en) * | 2018-03-28 | 2018-08-24 | 南京林业大学 | A kind of field coupling type induction conductivity sensor and its characteristic compensation device |
| CN110278648A (en) * | 2019-06-26 | 2019-09-24 | 中国人民解放军陆军装甲兵学院 | The influence research method of magnetic field configuration plasma depression effect |
| CN110287600A (en) * | 2019-06-26 | 2019-09-27 | 中国人民解放军陆军装甲兵学院 | Flowing and pressure investigation method of the magnetic controlled plasma in cylinder |
| KR20210109400A (en) * | 2020-02-27 | 2021-09-06 | 주식회사 센서위드유 | Hazardous gas sensor platform with deep-learning technology to improve target gas detection and prediction in the in the mixed gas environment |
| CN112577864A (en) * | 2020-11-19 | 2021-03-30 | 西安交通大学 | Silicon micron column array three-electrode ionization type microsystem haze sensor and preparation method thereof |
| CN112684262A (en) * | 2020-11-19 | 2021-04-20 | 西安交通大学 | Silicon micron column array three-electrode ionization type MEMS electric field sensor and preparation method thereof |
| CN113375716A (en) * | 2021-06-01 | 2021-09-10 | 国网重庆市电力公司电力科学研究院 | Self-powered power transmission line on-line monitoring system based on multi-sensor data fusion |
Non-Patent Citations (2)
| Title |
|---|
| 施勇: "有限元法研究三电极管极式电除尘器电场特性", CNKI优秀硕士学位论文全文库, vol. 2012, no. 2 * |
| 郑博聪: "脉冲等离子体工艺中等离子体与表面相互作用数值研究", CNKI博士学位论文全文库, vol. 2019, no. 8 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114018326B (en) | 2024-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mitzner et al. | Development of a micromachined hazardous gas sensor array | |
| Li et al. | A novel surface acoustic wave-impedance humidity sensor based on the composite of polyaniline and poly (vinyl alcohol) with a capability of detecting low humidity | |
| CN107589155A (en) | A kind of capacitance type sensor and preparation method thereof | |
| CN107966481B (en) | A kind of Material Identification sensor and preparation method thereof based on composite capacitive structure | |
| JPH09210963A (en) | Solid gas sensor | |
| US20200116694A1 (en) | Zero-Power Wireless Chemical Sensor for Agricultural Pests and Disease Monitoring | |
| CN113514502A (en) | Multi-dimensional multi-parameter gas sensor, preparation method thereof and gas detection method | |
| CN102175343A (en) | Carbon nanotube film three-electrode gas temperature sensor and temperature measuring method thereof | |
| CN109813492A (en) | A kind of capacitive films vacuum meter | |
| CN100403021C (en) | Ionized gas sensor microarray structure based on micro-electronic fabrication technology | |
| Kawakita et al. | Detection of micro/nano droplet by galvanic-coupled arrays | |
| CN106248779B (en) | Three electrode ionizing transducer array of Jenner's metre hole film with temperature compensation function | |
| CN114018326B (en) | Low-voltage transformer area environment multi-parameter detection method based on microsystem sensor array | |
| CN102095783A (en) | Carbon nano tube film three-electrode sensor array and method for detecting concentration of mixed gas | |
| CN102095782B (en) | Gas on-line detection device based on micro-nano carbon nano tube film three-electrode | |
| CN208366907U (en) | Flexible ion transducer based on two tungsten selenides | |
| US6717413B1 (en) | Contact potential difference ionization detector | |
| EP3623804B1 (en) | Method of operating gas sensors and corresponding device, sensor and program product | |
| CN111912877B (en) | Organic gas detection and identification chip based on sensor array | |
| CN102095791B (en) | Method for detecting concentration of two-component gas based on carbon nano tube film three-electrode sensor | |
| CN102072784A (en) | Carbon nanotube film ionizing gas temperature sensor and temperature measuring method thereof | |
| CN109655859B (en) | Measuring instrument pair with multiple detectors for improving radon exhalation rate 218 Po collection efficiency measurement cavity and method | |
| CN207516298U (en) | A kind of capacitance type sensor | |
| US20080099330A1 (en) | Electrochemical sensor having suspended element counter electrode and deflection method for current sensing | |
| Il’in et al. | Design of the gas sensor prototype with CNTs-based sensitive element and application of the FFT technique for gas identification |
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 |