CN116718638A - Dangerous chemical detection method and system based on electronic nose Internet of things - Google Patents
Dangerous chemical detection method and system based on electronic nose Internet of things Download PDFInfo
- Publication number
- CN116718638A CN116718638A CN202310066028.4A CN202310066028A CN116718638A CN 116718638 A CN116718638 A CN 116718638A CN 202310066028 A CN202310066028 A CN 202310066028A CN 116718638 A CN116718638 A CN 116718638A
- Authority
- CN
- China
- Prior art keywords
- gas
- sample
- matrix
- electronic nose
- dangerous
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 105
- 239000000126 substance Substances 0.000 title claims abstract description 79
- 238000012360 testing method Methods 0.000 claims abstract description 86
- 238000000034 method Methods 0.000 claims abstract description 17
- 239000011159 matrix material Substances 0.000 claims description 93
- 239000000383 hazardous chemical Substances 0.000 claims description 10
- 230000003287 optical effect Effects 0.000 claims description 10
- 238000012937 correction Methods 0.000 claims description 5
- 238000010521 absorption reaction Methods 0.000 claims description 4
- 238000000862 absorption spectrum Methods 0.000 claims description 4
- 235000013405 beer Nutrition 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 230000006855 networking Effects 0.000 claims 2
- 239000007789 gas Substances 0.000 description 81
- 230000000694 effects Effects 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 description 2
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 2
- 239000002360 explosive Substances 0.000 description 2
- 239000001257 hydrogen Substances 0.000 description 2
- 229910052739 hydrogen Inorganic materials 0.000 description 2
- 239000001301 oxygen Substances 0.000 description 2
- 229910052760 oxygen Inorganic materials 0.000 description 2
- 231100000331 toxic Toxicity 0.000 description 2
- 230000002588 toxic effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 231100001261 hazardous Toxicity 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 231100000252 nontoxic Toxicity 0.000 description 1
- 230000003000 nontoxic effect Effects 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
-
- 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)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Electrochemistry (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a dangerous chemical detection method and a dangerous chemical detection system based on the Internet of things of an electronic nose, which belong to the technical field of gas detection, wherein the method comprises the following steps: constructing a gas detection model through a standard sample; inputting the test sample into a gas detection model to detect the gas component in the test sample; determining the concentration of dangerous chemicals through a gas detection model; under the condition that the concentration of dangerous chemicals is higher than an alarm threshold value, outputting a detection result; comparing the detection result of the test sample with the sample information of the known test sample, and correcting the alarm threshold; the method comprises the steps that a gas detection model is configured in an electronic nose detector, and air samples are collected through a plurality of electronic nose detectors; under the condition that a certain target electronic nose detector monitors that dangerous chemicals exist in the air, the target electronic nose detector reports self-position information to a cloud server; and the cloud server informs the staff to go to the position of the target electronic nose detector in time and maintains the related equipment.
Description
Technical Field
The invention belongs to the technical field of gas detection, and particularly relates to a dangerous chemical detection method and system based on the Internet of things of an electronic nose.
Background
In the industrial production process, some dangerous chemical leakage events often occur, and once toxic and harmful or flammable and explosive gas leaks, huge personnel and property losses can be caused, so that personal and property safety is seriously endangered.
In the prior art, whether gas leakage exists in production equipment at all positions is often checked by adopting a manual inspection mode, so that the labor cost is high, and the accuracy of manually judging whether leakage exists is low. In other prior art, whether gas leakage exists or not is detected through the gas pressure sensor, and the method can only be applied to equipment which can provide convenience for installation of the gas pressure sensor, and can give an alarm at the highest level as long as the gas leakage exists, so that false alarm can be caused on some non-toxic and harmless gas leakage, production stoppage and shutdown are caused, and unnecessary loss is brought to enterprises.
Disclosure of Invention
The invention provides a dangerous chemical detection method and system based on the Internet of things of an electronic nose, which are used for solving the technical problems of low detection accuracy in the prior art of detecting gas leakage by means of manual or air pressure sensors.
First aspect
The invention provides a dangerous chemical detection method based on an electronic nose internet of things, wherein the electronic nose internet of things comprises a plurality of electronic nose detectors with dispersed positions, and the dangerous chemical detection method comprises the following steps:
s101: constructing a gas detection model through a standard sample;
s102: inputting a test sample into the gas detection model to detect a gas component in the test sample, wherein the gas component, concentration, and gas of the test sample are known amounts;
s103: determining the concentration of the dangerous chemical through the gas detection model under the condition that the dangerous chemical exists in the test sample;
s104: under the condition that the concentration of the dangerous chemical is higher than an alarm threshold value, determining the test sample as a dangerous sample, and outputting a detection result;
s105: comparing the detection result of the test sample with the known sample information of the test sample, and correcting the alarm threshold;
s106: configuring the gas detection model in the electronic nose detectors, and collecting air samples through a plurality of the electronic nose detectors;
s107: when a certain target electronic nose detector monitors that dangerous chemicals exist in the air and the concentration of the dangerous chemicals is higher than the alarm threshold value, the target electronic nose detector reports the position information of the target electronic nose detector, the components and the concentration of the dangerous chemicals to a cloud server;
s108: and the cloud server informs a worker to go to the position of the target electronic nose detector in time and maintains related equipment.
Second aspect
The invention provides a dangerous chemical detection system based on an electronic nose internet of things, wherein the electronic nose internet of things comprises a plurality of electronic nose detectors with dispersed positions, and the dangerous chemical detection system comprises:
the construction module is used for constructing a gas detection model through a standard sample;
a component detection module for inputting a test sample into the gas detection model to detect a gas component in the test sample, wherein the gas component, concentration, and gas of the test sample are known amounts;
the concentration detection module is used for determining the concentration of the dangerous chemical through the gas detection model under the condition that the dangerous chemical exists in the test sample;
the output module is used for determining the test sample as a dangerous sample and outputting a detection result under the condition that the concentration of the dangerous chemical is higher than an alarm threshold value;
the correction module is used for comparing the detection result of the test sample with the known sample information of the test sample and correcting the alarm threshold value;
the collection module is used for configuring the gas detection model in the electronic nose detectors and collecting air samples through a plurality of the electronic nose detectors;
the reporting module is used for reporting the position information of the target electronic nose detector, the components and the concentration of the dangerous chemical to the cloud server when the target electronic nose detector monitors that the dangerous chemical exists in the air and the concentration of the dangerous chemical is higher than the alarm threshold value;
and the notification module is used for notifying a worker to go to the position of the target electronic nose detector in time by the cloud server and maintaining related equipment.
Compared with the prior art, the invention has at least the following beneficial technical effects:
according to the invention, an electronic nose internet of things is formed by a plurality of electronic nose detectors with dispersed positions, a gas detection model is configured in the electronic nose detectors, the components and the concentration of gas in the air are automatically analyzed, and when the electronic nose detectors at a certain position monitor that dangerous chemicals exist in the air and the concentration of the dangerous chemicals is higher than an alarm threshold value, the electronic nose detectors report the position information of the electronic nose detectors, the components and the concentration of the dangerous chemicals to a cloud server; the cloud server informs workers to go to corresponding electronic nose detectors in time and maintains related equipment. The detection accuracy is high, false alarm is avoided, and personal and property safety can be protected.
Drawings
The above features, technical features, advantages and implementation of the present invention will be further described in the following description of preferred embodiments with reference to the accompanying drawings in a clear and easily understood manner.
FIG. 1 is a schematic flow chart of a dangerous chemical detection method based on the Internet of things of an electronic nose;
fig. 2 is a schematic structural diagram of a dangerous chemical detection system based on the internet of things of an electronic nose.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description will explain the specific embodiments of the present invention with reference to the accompanying drawings. It is evident that the drawings in the following description are only examples of the invention, from which other drawings and other embodiments can be obtained by a person skilled in the art without inventive effort.
For simplicity of the drawing, only the parts relevant to the invention are schematically shown in each drawing, and they do not represent the actual structure thereof as a product. Additionally, in order to simplify the drawing for ease of understanding, components having the same structure or function in some of the drawings are shown schematically with only one of them, or only one of them is labeled. Herein, "a" means not only "only this one" but also "more than one" case.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
In this context, it should be noted that the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected, unless explicitly stated or limited otherwise; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
In addition, in the description of the present invention, the terms "first," "second," and the like are used merely to distinguish between descriptions and are not to be construed as indicating or implying relative importance.
In an embodiment, referring to fig. 1 of the specification, the invention provides a flow diagram of a dangerous chemical detection method based on the internet of things of an electronic nose.
The dangerous chemical detection method based on the electronic nose Internet of things is applied to a dangerous chemical detection system based on the electronic nose Internet of things.
The electronic nose internet of things comprises a plurality of electronic nose detectors with scattered positions, and in the practical application process, the electronic nose detectors can be arranged at all positions of a field to comprehensively monitor the whole field.
The method for detecting the dangerous chemical comprises the following steps:
s101: and constructing a gas detection model through a standard sample.
Wherein the gas composition of the standard sample is known, and the concentration is 100%.
Further, the standard sample may encompass some common toxic, hazardous, flammable, and explosive gas samples.
The standard sample is meant to be a strange, unknown gas sample, which can be compared with the standard sample to confirm the composition of the gas sample.
In a possible implementation manner, the step S101 specifically includes a substep S1011:
s1011: and obtaining a data matrix X of a plurality of standard samples, wherein the standard samples comprise m types of gas, and each type of gas comprises n standard samples.
It will be appreciated that there are a total of m×n standard samples, and that the provision of multiple samples in each type of gas is to improve the accuracy of the sample data.
S1012: the total sample matrix P is obtained by summing up,,i=1,2,…,m,j=1,2,…,n。
it should be noted that the number of the substrates,is a single sample matrix.
Alternatively, the single sample matrix is acquired by the optical sensor, the initial light intensity of the optical sensor may be set at different light intensity values, after which the single sample matrix is normalized by the received light intensity values.
S1013: calculating a single sample P according to the total sample matrix P i Mean matrix eta of column data of (a) i And the mean matrix eta of the total sample matrix P m :
wherein ,representing the eigenvalues of the ith class, jth standard sample.
S1014: calculating an intra-class divergence matrix Q of the total sample matrix P 1 And an inter-class divergence matrix Q 2 :
Wherein, the intra-class divergence matrix Q 1 Characterizing similarity between data samples of a certain class, inter-class divergence matrix Q 2 The degree of similarity between different classes of data samples is characterized.
It will be appreciated that if it is desired to obtain a more beneficial discriminative recognition effect, the intra-class divergence matrix Q should be maintained 1 As small as possible, and inter-class divergence matrix Q 2 As large as possible.
S1015: constructing an objective function phi (alpha), adding constraint conditions, and calculating a divergence matrix Q in the class 1 Minimum and Q of the inter-class divergence matrix 2 At maximum, the eigenvalue λ of the total sample matrix P is used to distinguish between the gas components:
wherein, the constraint condition is:
α·Q 2 ·α T =1
φ'(α)=α·Q 1 ·α T -λ(α·Q 1 ·α T -1)=0
when phi (alpha) takes the maximum value, the intra-class divergence matrix Q can be satisfied 1 Minimum, and inter-class divergence matrix Q 2 Maximum.
Therefore, the eigenvalue λ of the total sample matrix P is:
s1016: calculating a total sample feature recognition matrix P':
P’=λ·P
s1017: taking the average value of the characteristic values of each type of sample in the total sample characteristic recognition matrix P', and calculating a plurality of gas classification matrices Yi:
s1018: based on the gas classification matrix Y i And constructing the gas detection model.
In the present invention, based on the gas classification matrix Y i The built gas detection model can maintain the in-class divergence matrix Q 1 As small as possible, and inter-class divergence matrix Q 2 As large as possible, the similarity degree between certain types of data samples is high, and the discrete degree between different types of data samples is high, so that the gas detection model has good distinguishing effect.
S102: a test sample is input to the gas detection model to detect a gas component in the test sample.
Wherein the gas composition, concentration, gas of the test sample is a known amount.
In one possible implementation manner, the step S102 specifically includes:
s1021: a plurality of the test samples are obtained, wherein the gas composition, concentration, and whether the gas is harmful to the test samples are known amounts.
S1022: and extracting a characteristic matrix Z of the test sample.
S1023: calculating each feature recognition matrix Y i And determining the gas component in the test sample under the condition that the Euclidean distance between the gas component and the characteristic matrix Z of the test sample is smaller than the preset distance.
Note that the euclidean distance represents the degree of similarity between the two matrices. The larger the Euclidean distance between the two matrices, the lower the degree of similarity between the two matrices; conversely, the smaller the Euclidean distance between two matrices, the higher the degree of similarity between the two matrices.
In the present invention, once a certain feature recognition matrix Y i The Euclidean distance between the test sample and the characteristic matrix Z of the test sample is smaller than the preset distance, which means that a certain characteristic identification matrix Y i Is relatively similar to the feature matrix Z of the test sample, and the test sample can be considered to contain the feature recognition matrix Y i Corresponding gas components.
S103: and determining the concentration of the dangerous chemical through the gas detection model under the condition that the dangerous chemical exists in the test sample.
In one possible embodiment, the electronic nose detector includes a gas accommodating chamber and an optical sensor, and the S103 specifically includes:
s1031: constructing the gas detection model according to beer's law:
I(λ)=I 0 (λ)e -σ(λ)cL
wherein I (lambda) represents the intensity of light received by the optical sensor, I 0 (lambda) represents the initial light intensity, sigma (lambda) represents the absorption cross section of the substance to be measured, lambda represents the wavelength, c represents the concentration of the substance to be measured, and L represents the length of the gas-accommodating chamber.
S1032: the above formula is deformed, and then:
cσ(λ)L=ln[I 0 (λ)I(λ)]。
s1033: assuming that the test sample includes K gas components, K test points are obtained in the absorption spectrum, and then:
where k=1, 2, …, K.
S1034: solving K unknown c by K equations k To detect the concentration of each gas component in the test sample.
In the detection process, the inherent components such as oxygen and hydrogen contained in the air are removed at the initial stage of the recognition or substituted into the above formula as known amounts in the recognition process.
Further, the ratio of oxygen to hydrogen in the air can be used to verify whether the calculation result is accurate.
S104: and under the condition that the concentration of the dangerous chemical is higher than an alarm threshold value, determining the test sample as a dangerous sample, and outputting a detection result.
S105: and comparing the detection result of the test sample with the known sample information of the test sample, and correcting the alarm threshold.
In one possible implementation manner, the step S105 specifically includes:
s1051: comparing the detection result with the known sample information of the test sample, and evaluating the detection result, wherein the evaluation result comprises: the security is detected as a hazard type result, the hazard is detected as a security type result, the security is detected as a security type result, and the hazard is detected as a hazard type result.
S1052: let the number of times the security is predicted as a security class result be TX, the number of times the security is predicted as a risk class result be FY, the number of times the risk is predicted as a risk class result be TY, the number of times the risk is predicted as a security class result be FX, the proportion FY of the predicted errors of the security sample be rate And the dangerous sample is predicted to the correct ratio FX rate The method comprises the following steps:
s1053: and making the cost for predicting the safety as a dangerous result p, the cost for predicting the safety as two types of results q, and correcting the alarm threshold value so as to make:
it should be noted that the cost of predicting security as a dangerous class result and the cost of predicting danger as a safe class result can be evaluated by downtime or property loss.
When the safety prediction is dangerous, misjudgment is caused, unnecessary shutdown and production stopping are caused, and unnecessary property loss is caused for enterprises. The danger is predicted to be safe, and the false judgment brings about huge potential safety hazards, and once the danger occurs, unnecessary shutdown and production stopping are caused, so that unnecessary property loss is brought to enterprises.
If the alarm threshold is set too low, the probability of predicting the safety as dangerous becomes high, the probability of predicting the safety as dangerous becomes low, and even frequent shutdown and production stoppage are caused. If the alarm threshold is set too high, the probability of predicting the safety as dangerous becomes low, and the probability of predicting the safety as dangerous becomes high, which means that the potential safety hazard bringing huge personnel and property loss is increased, so that the alarm threshold needs to be corrected.
S106: and configuring the gas detection model in the electronic nose detector, and collecting air samples through a plurality of the electronic nose detectors.
S107: under the condition that a certain target electronic nose detector monitors that dangerous chemicals exist in the air and the concentration of the dangerous chemicals is higher than the alarm threshold value, the target electronic nose detector reports the position information of the target electronic nose detector, the components and the concentration of the dangerous chemicals to a cloud server.
S108: and the cloud server informs a worker to go to the position of the target electronic nose detector in time and maintains related equipment.
Compared with the prior art, the invention has at least the following beneficial technical effects:
according to the invention, an electronic nose internet of things is formed by a plurality of electronic nose detectors with dispersed positions, a gas detection model is configured in the electronic nose detectors, the components and the concentration of gas in the air are automatically analyzed, and when the electronic nose detectors at a certain position monitor that dangerous chemicals exist in the air and the concentration of the dangerous chemicals is higher than an alarm threshold value, the electronic nose detectors report the position information of the electronic nose detectors, the components and the concentration of the dangerous chemicals to a cloud server; the cloud server informs workers to go to corresponding electronic nose detectors in time and maintains related equipment. The detection accuracy is high, false alarm is avoided, and personal and property safety can be protected
Example 2
In an embodiment, referring to fig. 2 of the specification, the invention provides a structural schematic diagram of a dangerous chemical detection system based on the internet of things of an electronic nose.
The invention provides a dangerous chemical detection system 20 based on the Internet of things of an electronic nose.
The electronic nose internet of things comprises a plurality of electronic nose detectors with scattered positions.
The hazardous chemical detection system 20 includes:
a construction module 201 for constructing a gas detection model from a standard sample;
a component detection module 202 for inputting a test sample into the gas detection model to detect a gas component in the test sample, wherein the gas component, concentration, and gas of the test sample are known amounts;
a concentration detection module 203, configured to determine, when it is determined that the dangerous chemical exists in the test sample, a concentration of the dangerous chemical through the gas detection model;
an output module 204, configured to determine the test sample as a dangerous sample and output a detection result when the concentration of the dangerous chemical is higher than an alarm threshold;
a correction module 205, configured to compare a detection result of the test sample with known sample information of the test sample, and correct the alarm threshold;
an acquisition module 206 for configuring the gas detection model in the electronic nose detectors, and acquiring air samples by a plurality of the electronic nose detectors;
the reporting module 207 is configured to report, when a target electronic nose detector detects that dangerous chemicals exist in air and the concentration of the dangerous chemicals is higher than the alarm threshold, the target electronic nose detector to a cloud server, the location information of the target electronic nose detector, the components and the concentration of the dangerous chemicals;
and the notification module 208 is configured to notify the cloud server that the worker is going to the position of the target electronic nose detector in time, and repair the related device.
In one possible implementation, the construction module 201 is specifically configured to:
acquiring a data matrix X of a plurality of standard samples, wherein the plurality of standard samples comprise m types of gas, each type of gas comprises n standard samples, and the gas composition of the standard samples is known, and the concentration is 100%;
the total sample matrix P is obtained by summing up,i=1,2,…,m,j=1,2,…,n;
calculating a single sample P according to the total sample matrix P i Mean matrix eta of column data of (a) i And the mean matrix eta of the total sample matrix P m :
wherein ,representing the characteristic value of the ith standard sample of the ith class;
calculating an intra-class divergence matrix Q of the total sample matrix P 1 And an inter-class divergence matrix Q 2 :
Constructing an objective function phi (alpha), adding constraint conditions, and calculating a divergence matrix Q in the class 1 Minimum and Q of the inter-class divergence matrix 2 At maximum, the eigenvalue λ of the total sample matrix P is used to distinguish between the gas components:
wherein, the constraint condition is:
α·Q 2 ·α T =1
φ'(α)=α·Q 1 ·α T -λ(α·Q 1 ·α T -1)=0
therefore, the eigenvalue λ of the total sample matrix P is:
calculating a total sample feature recognition matrix P':
P’=λ·P
averaging the characteristic values of each type of sample in the total sample characteristic recognition matrix P', and calculating a plurality of gas classification matrices Y i :
Based on the gas classification matrix Y i And constructing the gas detection model.
In one possible implementation, the component detection module 202 is specifically configured to:
obtaining a plurality of test samples, wherein the gas composition, concentration and whether the gas is harmful to the test samples are known amounts;
extracting a feature matrix Z of the test sample;
calculating each feature recognition matrix Y i And determining the gas component in the test sample under the condition that the Euclidean distance between the gas component and the characteristic matrix Z of the test sample is smaller than the preset distance.
In one possible embodiment, the electronic nose detector includes a gas accommodating chamber and an optical sensor, and the concentration detection module 203 is specifically configured to:
constructing the gas detection model according to beer's law:
I(λ)=I 0 (λ)e -σ(λ)cL
wherein I (lambda) represents the intensity of light received by the optical sensor, I 0 (lambda) represents the initial light intensity, sigma (lambda) represents the absorption cross section of the measured substance, lambda represents the wavelength, c represents the concentration of the measured substance, and L represents the length of the gas-accommodating chamber;
the above formula is deformed, and then:
cσ(λ)L=ln[I 0 (λ)I(λ)]
assuming that the test sample includes K gas components, K test points are obtained in the absorption spectrum, and then:
wherein k=1, 2, …, K;
solving K unknown c by K equations k To detect the concentration of each gas component in the test sample.
In one possible implementation, the correction module 205 is specifically configured to:
comparing the detection result with the known sample information of the test sample, and evaluating the detection result, wherein the evaluation result comprises: detecting the safety as a dangerous result, detecting the danger as a safe result, detecting the safety as a safe result, and detecting the danger as a dangerous result;
let the number of times the security is predicted as a security class result be TX, the number of times the security is predicted as a risk class result be FY, the number of times the risk is predicted as a risk class result be TY, the number of times the risk is predicted as a security class result be FX, the proportion FY of the predicted errors of the security sample be rate And the dangerous sample is predicted to the correct ratio FX rate The method comprises the following steps:
and making the cost for predicting the safety as a dangerous result p, the cost for predicting the safety as two types of results q, and correcting the alarm threshold value so as to make:
the hazardous chemical detection system 20 provided by the present invention can implement each process implemented in the above method embodiments, and for avoiding repetition, a detailed description is omitted herein.
The virtual system provided by the invention can be a system, and can also be a component, an integrated circuit or a chip in a terminal.
Compared with the prior art, the invention has at least the following beneficial technical effects:
according to the invention, an electronic nose internet of things is formed by a plurality of electronic nose detectors with dispersed positions, a gas detection model is configured in the electronic nose detectors, the components and the concentration of gas in the air are automatically analyzed, and when the electronic nose detectors at a certain position monitor that dangerous chemicals exist in the air and the concentration of the dangerous chemicals is higher than an alarm threshold value, the electronic nose detectors report the position information of the electronic nose detectors, the components and the concentration of the dangerous chemicals to a cloud server; the cloud server informs workers to go to corresponding electronic nose detectors in time and maintains related equipment. The detection accuracy is high, false alarm is avoided, and personal and property safety can be protected.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the invention, which are described in detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (10)
1. The dangerous chemical detection method based on the electronic nose internet of things is characterized in that the electronic nose internet of things comprises a plurality of electronic nose detectors with dispersed positions, and the dangerous chemical detection method comprises the following steps:
s101: constructing a gas detection model through a standard sample;
s102: inputting a test sample into the gas detection model to detect a gas component in the test sample, wherein the gas component, concentration, and gas of the test sample are known amounts;
s103: determining the concentration of the dangerous chemical through the gas detection model under the condition that the dangerous chemical exists in the test sample;
s104: under the condition that the concentration of the dangerous chemical is higher than an alarm threshold value, determining the test sample as a dangerous sample, and outputting a detection result;
s105: comparing the detection result of the test sample with the known sample information of the test sample, and correcting the alarm threshold;
s106: configuring the gas detection model in the electronic nose detectors, and collecting air samples through a plurality of the electronic nose detectors;
s107: when a certain target electronic nose detector monitors that dangerous chemicals exist in the air and the concentration of the dangerous chemicals is higher than the alarm threshold value, the target electronic nose detector reports the position information of the target electronic nose detector, the components and the concentration of the dangerous chemicals to a cloud server;
s108: and the cloud server informs a worker to go to the position of the target electronic nose detector in time and maintains related equipment.
2. The method for detecting hazardous chemicals according to claim 1, wherein said S101 specifically comprises:
s1011: acquiring a data matrix X of a plurality of standard samples, wherein the plurality of standard samples comprise m types of gas, each type of gas comprises n standard samples, and the gas composition of the standard samples is known, and the concentration is 100%;
s1012: the total sample matrix P is obtained by summing up,
s1013: calculating a single sample P according to the total sample matrix P i Mean matrix eta of column data of (a) i And the mean matrix eta of the total sample matrix P m :
wherein ,representing the characteristic value of the ith standard sample of the ith class;
s1014: calculating an intra-class divergence matrix Q of the total sample matrix P 1 And an inter-class divergence matrix Q 2 :
S1015: constructing an objective function phi (alpha), adding constraint conditions, and calculating a divergence matrix Q in the class 1 Minimum and Q of the inter-class divergence matrix 2 At maximum, the eigenvalue λ of the total sample matrix P is used to distinguish between the gas components:
wherein, the constraint condition is:
α·Q 2 ·α T =1
φ'(α)=α·Q 1 ·α T -λ(α·Q 1 ·α T -1)=0
therefore, the eigenvalue λ of the total sample matrix P is:
s1016: calculating a total sample feature recognition matrix P':
P’=λ·P
s1017: averaging the characteristic values of each type of sample in the total sample characteristic recognition matrix P', and calculating a plurality of gas classification matrices Y i :
S1018: based on the gas classification matrix Y i And constructing the gas detection model.
3. The method for detecting hazardous chemicals according to claim 1, wherein S102 specifically comprises:
s1021: obtaining a plurality of test samples, wherein the gas composition, concentration and whether the gas is harmful to the test samples are known amounts;
s1022: extracting a feature matrix Z of the test sample;
s1023: calculating each feature recognition matrix Y i And determining the gas component in the test sample under the condition that the Euclidean distance between the gas component and the characteristic matrix Z of the test sample is smaller than the preset distance.
4. The method for detecting hazardous chemicals according to claim 1, wherein the electronic nose detector includes a gas containing chamber and an optical sensor, and the S103 specifically includes:
s1031: constructing the gas detection model according to beer's law:
I(λ)=I 0 (λ)e -σ(λ)cL
wherein I (lambda) represents the intensity of light received by the optical sensor, I 0 (lambda) represents the initial light intensity, sigma (lambda) represents the absorption cross section of the measured substance, lambda represents the wavelength, c represents the concentration of the measured substance, and L represents the length of the gas-accommodating chamber;
s1032: the above formula is deformed, and then:
cσ(λ)L=ln[I 0 (λ)/I(λ)]
s1033: assuming that the test sample includes K gas components, K test points are obtained in the absorption spectrum, and then:
wherein k=1, 2, …, K;
s1034: solving K unknown c by K equations k To detect the concentration of each gas component in the test sample.
5. The method for detecting hazardous chemicals according to claim 1, wherein S105 specifically comprises:
s1051: comparing the detection result with the known sample information of the test sample, and evaluating the detection result, wherein the evaluation result comprises: detecting the safety as a dangerous result, detecting the danger as a safe result, detecting the safety as a safe result, and detecting the danger as a dangerous result;
s1052: let the number of times the security is predicted as a security class result be TX, the number of times the security is predicted as a risk class result be FY, the number of times the risk is predicted as a risk class result be TY, the number of times the risk is predicted as a security class result be FX, the proportion FY of the predicted errors of the security sample be rate And the dangerous sample is predicted to the correct ratio FX rate The method comprises the following steps:
s1053: and making the cost for predicting the safety as a dangerous result p, the cost for predicting the safety as two types of results q, and correcting the alarm threshold value so as to make:
6. dangerous chemical detecting system based on electronic nose thing networking, its characterized in that, electronic nose thing networking includes the scattered electronic nose detector in a plurality of positions, dangerous chemical detecting system includes:
the construction module is used for constructing a gas detection model through a standard sample;
a component detection module for inputting a test sample into the gas detection model to detect a gas component in the test sample, wherein the gas component, concentration, and gas of the test sample are known amounts;
the concentration detection module is used for determining the concentration of the dangerous chemical through the gas detection model under the condition that the dangerous chemical exists in the test sample;
the output module is used for determining the test sample as a dangerous sample and outputting a detection result under the condition that the concentration of the dangerous chemical is higher than an alarm threshold value;
the correction module is used for comparing the detection result of the test sample with the known sample information of the test sample and correcting the alarm threshold value;
the collection module is used for configuring the gas detection model in the electronic nose detectors and collecting air samples through a plurality of the electronic nose detectors;
the reporting module is used for reporting the position information of the target electronic nose detector, the components and the concentration of the dangerous chemical to the cloud server when the target electronic nose detector monitors that the dangerous chemical exists in the air and the concentration of the dangerous chemical is higher than the alarm threshold value;
and the notification module is used for notifying a worker to go to the position of the target electronic nose detector in time by the cloud server and maintaining related equipment.
7. The hazardous chemical detection system according to claim 6, wherein the building block is specifically configured to:
acquiring a data matrix X of a plurality of standard samples, wherein the plurality of standard samples comprise m types of gas, each type of gas comprises n standard samples, and the gas composition of the standard samples is known, and the concentration is 100%;
the total sample matrix P is obtained by summing up,i=1,2,…,m,j=1,2,…,n;
calculating a single sample P according to the total sample matrix P i Mean matrix eta of column data of (a) i And the mean matrix eta of the total sample matrix P m :
wherein ,representing the characteristic value of the ith standard sample of the ith class;
calculating an intra-class divergence matrix Q of the total sample matrix P 1 And an inter-class divergence matrix Q 2 :
Constructing an objective function phi (alpha), adding constraint conditions, and calculating a divergence matrix Q in the class 1 Minimum and Q of the inter-class divergence matrix 2 At maximum, the eigenvalue λ of the total sample matrix P is used to distinguish between the gas components:
wherein, the constraint condition is:
α·Q 2 ·α T =1
φ'(α)=α·Q 1 ·α T -λ(α·Q 1 ·α T -1)=0
therefore, the eigenvalue λ of the total sample matrix P is:
calculating a total sample feature recognition matrix P':
P’=λ·P
averaging the characteristic values of each type of sample in the total sample characteristic recognition matrix P', and calculating a plurality of gas classification matrices Y i :
Based on the gas classification matrix Y i And constructing the gas detection model.
8. The hazardous chemical detection system according to claim 6, wherein the component detection module is specifically configured to:
obtaining a plurality of test samples, wherein the gas composition, concentration and whether the gas is harmful to the test samples are known amounts;
extracting a feature matrix Z of the test sample;
calculating each feature recognition matrix Y i And determining the gas component in the test sample under the condition that the Euclidean distance between the gas component and the characteristic matrix Z of the test sample is smaller than the preset distance.
9. The hazardous chemical detection system according to claim 6, wherein the electronic nose detector comprises a gas-containing chamber and an optical sensor, the concentration detection module being specifically configured to:
constructing the gas detection model according to beer's law:
I(λ)=I 0 (λ)e -σ(λ)cL
wherein I (lambda) represents the intensity of light received by the optical sensor, I 0 (lambda) represents the initial light intensity and sigma (lambda) represents the absorption of the substance to be measuredA cross section, lambda represents wavelength, c represents concentration of a measured substance, and L represents length of the gas accommodating cavity;
the above formula is deformed, and then:
cσ(λ)L=ln[I 0 (λ)I(λ)]
assuming that the test sample includes K gas components, K test points are obtained in the absorption spectrum, and then:
wherein k=1, 2, …, K;
solving K unknown c by K equations k To detect the concentration of each gas component in the test sample.
10. The hazardous chemical detection system according to claim 6, wherein the correction module is specifically configured to:
comparing the detection result with the known sample information of the test sample, and evaluating the detection result, wherein the evaluation result comprises: detecting the safety as a dangerous result, detecting the danger as a safe result, detecting the safety as a safe result, and detecting the danger as a dangerous result;
let the number of times the security is predicted as a security class result be TX, the number of times the security is predicted as a risk class result be FY, the number of times the risk is predicted as a risk class result be TY, the number of times the risk is predicted as a security class result be FX, the proportion FY of the predicted errors of the security sample be rate And the dangerous sample is predicted to the correct ratio FX rate The method comprises the following steps:
and making the cost for predicting the safety as a dangerous result p, the cost for predicting the safety as two types of results q, and correcting the alarm threshold value so as to make:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310066028.4A CN116718638A (en) | 2023-01-17 | 2023-01-17 | Dangerous chemical detection method and system based on electronic nose Internet of things |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310066028.4A CN116718638A (en) | 2023-01-17 | 2023-01-17 | Dangerous chemical detection method and system based on electronic nose Internet of things |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116718638A true CN116718638A (en) | 2023-09-08 |
Family
ID=87873963
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310066028.4A Pending CN116718638A (en) | 2023-01-17 | 2023-01-17 | Dangerous chemical detection method and system based on electronic nose Internet of things |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116718638A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117496660A (en) * | 2023-11-08 | 2024-02-02 | 营口天成消防设备有限公司 | Intelligent fire-fighting linkage control system based on unmanned aerial vehicle |
-
2023
- 2023-01-17 CN CN202310066028.4A patent/CN116718638A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117496660A (en) * | 2023-11-08 | 2024-02-02 | 营口天成消防设备有限公司 | Intelligent fire-fighting linkage control system based on unmanned aerial vehicle |
CN117496660B (en) * | 2023-11-08 | 2024-04-30 | 营口天成消防设备有限公司 | Intelligent fire-fighting linkage control system based on unmanned aerial vehicle |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US6804563B1 (en) | Multidimensional method and system for statistical process control | |
CN115099760B (en) | Intelligent dangerous article detection and early warning method based on computer machine vision | |
CN113783272B (en) | Safety control method based on super capacitor monitoring management system | |
EP3527513B1 (en) | Method and system to release a confined stowage unit for unloading or inspection | |
CN116181416A (en) | Multi-parameter advanced early warning system and method for rock burst | |
CN116718638A (en) | Dangerous chemical detection method and system based on electronic nose Internet of things | |
Maleki et al. | Simultaneous monitoring of multivariate process mean and variability in the presence of measurement error with linearly increasing variance under additive covariate model (research note) | |
CN117589375A (en) | Chemical safety detection method, system, terminal equipment and storage medium | |
Harrou et al. | Improved detection of incipient anomalies via multivariate memory monitoring charts: Application to an air flow heating system | |
CN112949735A (en) | Liquid hazardous chemical substance volatile concentration abnormity discovery method based on outlier data mining | |
CN110186854A (en) | A kind of foodsafety information detecting method | |
CN114429308A (en) | Enterprise security risk assessment method and system based on big data | |
CN116105802A (en) | Underground facility safety monitoring and early warning method based on Internet of things | |
CN106081958B (en) | A kind of derrick crane on-line monitoring system | |
CN115994431A (en) | Hydrogen detector space arrangement scheme optimization method and system based on risk evaluation | |
CN118152226B (en) | Double-open type moisture-proof cabinet humidity monitoring method based on intelligent sensor | |
CN114385603A (en) | Environmental data monitoring method and monitoring system | |
CN113804839B (en) | Disaster area environment multi-parameter fusion monitoring and explosion hazard diagnosis system and device | |
CN206833239U (en) | A kind of thermal power plant's control system fault detection system based on data-driven | |
CN106092916B (en) | Coal mine gas detection method | |
CN109145609B (en) | Data processing method and device | |
US7366639B2 (en) | Methods for establishing alerts and/or alert limits for monitoring mechanical devices | |
CN115601913A (en) | Combustible dangerous material fire risk early warning method and device | |
CN114490829A (en) | Fault identification method, device, equipment and storage medium | |
CN111017667B (en) | Elevator brake abnormity detection method, device and equipment and readable storage medium |
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 |