CN112528806B - Single-cluster tea aroma type classification method and device based on bionic olfaction - Google Patents
Single-cluster tea aroma type classification method and device based on bionic olfaction Download PDFInfo
- Publication number
- CN112528806B CN112528806B CN202011402079.2A CN202011402079A CN112528806B CN 112528806 B CN112528806 B CN 112528806B CN 202011402079 A CN202011402079 A CN 202011402079A CN 112528806 B CN112528806 B CN 112528806B
- Authority
- CN
- China
- Prior art keywords
- tea
- correction
- classification model
- aroma type
- aroma
- 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.)
- Active
Links
- 241001122767 Theaceae Species 0.000 title claims abstract description 168
- 238000000034 method Methods 0.000 title claims abstract description 64
- 239000011664 nicotinic acid Substances 0.000 title claims abstract description 27
- 230000008786 sensory perception of smell Effects 0.000 title claims abstract description 19
- 238000012937 correction Methods 0.000 claims abstract description 83
- 238000013145 classification model Methods 0.000 claims abstract description 78
- 239000011159 matrix material Substances 0.000 claims abstract description 28
- 239000007789 gas Substances 0.000 claims description 31
- 238000012360 testing method Methods 0.000 claims description 28
- 238000005070 sampling Methods 0.000 claims description 25
- 238000007789 sealing Methods 0.000 claims description 21
- 238000012795 verification Methods 0.000 claims description 16
- UHOVQNZJYSORNB-UHFFFAOYSA-N Benzene Chemical compound C1=CC=CC=C1 UHOVQNZJYSORNB-UHFFFAOYSA-N 0.000 claims description 15
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 claims description 12
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 claims description 12
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 claims description 12
- 229910000037 hydrogen sulfide Inorganic materials 0.000 claims description 12
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 9
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 claims description 6
- 150000001335 aliphatic alkanes Chemical class 0.000 claims description 6
- 229910021529 ammonia Inorganic materials 0.000 claims description 6
- -1 aromatic alkane Chemical class 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 239000001257 hydrogen Substances 0.000 claims description 6
- 229910052739 hydrogen Inorganic materials 0.000 claims description 6
- 125000003118 aryl group Chemical group 0.000 claims description 5
- 238000005303 weighing Methods 0.000 claims description 5
- 238000003860 storage Methods 0.000 abstract description 11
- 238000001514 detection method Methods 0.000 description 15
- 238000002790 cross-validation Methods 0.000 description 11
- 238000004590 computer program Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 238000011031 large-scale manufacturing process Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 230000007423 decrease Effects 0.000 description 3
- 239000003205 fragrance Substances 0.000 description 3
- 235000012907 honey Nutrition 0.000 description 3
- 241000233805 Phoenix Species 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012821 model calculation Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- GSWAOPJLTADLTN-UHFFFAOYSA-N oxidanimine Chemical compound [O-][NH3+] GSWAOPJLTADLTN-UHFFFAOYSA-N 0.000 description 2
- 238000003908 quality control method Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 229910044991 metal oxide Inorganic materials 0.000 description 1
- 150000004706 metal oxides Chemical class 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Biology (AREA)
- Medicinal Chemistry (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Combustion & Propulsion (AREA)
- Signal Processing (AREA)
- Food Science & Technology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Sampling And Sample Adjustment (AREA)
Abstract
The application relates to a method, a device, computer equipment and a storage medium for classifying aroma types of single tea based on bionic olfaction. The method comprises the following steps: obtaining a correction sample set of single tea leaves; wherein the correction sample set comprises correction samples of a plurality of single tea leaves of different aroma types; collecting a time sequence sensing signal of the volatile gas of the correction sample and the sensor array by using an electronic nose with the sensor array; extracting a characteristic variable value from the time sequence sensing signal, and constructing a characteristic variable matrix after carrying out standardized pretreatment on the characteristic variable value; and constructing a single tea aroma type classification model according to the characteristic variable matrix and combining with the aroma type label of the correction sample. The method can be used for rapidly and efficiently classifying the aroma types of the tea samples of the single tea.
Description
Technical Field
The application relates to the technical field of quality detection, in particular to a single-cluster tea aroma type classification method, device, computer equipment and storage medium based on bionic smell.
Background
The single tea is one of the three-big high-aroma tea in the world, and is mainly produced in Chaozhou city of Guangdong province in China. 2018 data show that the planting area of the single-cluster tea in Chaozhou city reaches 19.3 mu, the total yield of the tea is 2.4 mu ton, and the yield exceeds 35 hundred million yuan. For example, the Chaozhou floral "phoenix Dancong tea" and the Honey flavored "LingTou Dancong tea" are two major products in the area, and geographic marker protection products were obtained in 2013. In order to improve the industrial benefit of the single tea, the quality control of the single tea is important in ensuring the quality of the aroma type in the modern and large-scale production process of the single tea.
The traditional classification of the aroma types of the single tea is mainly realized by a manual evaluation mode, and the method needs to perform damage detection on samples. Moreover, the result of the manual evaluation is influenced by subjective consciousness and physiological state of the panelist, which is unfavorable for obtaining the detection result with high precision and good repeatability. Aiming at the tea aroma type detection method, no technology and method capable of rapidly classifying single tea aroma types exist. Therefore, the method for quickly classifying the aroma types of the single tea is developed, the single tea aroma types are quickly classified, and the method has important production practice significance for improving the development level of the single tea industry.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a method, apparatus, computer device, and storage medium for classifying aroma types of single tea based on bionic olfaction, which can improve efficiency of classifying aroma types of single tea.
A method for classifying aroma types of single tea based on bionic olfaction comprises the following steps:
obtaining a correction sample set of single tea leaves; wherein the correction sample set comprises correction samples of a plurality of single tea leaves of different aroma types;
collecting a time sequence sensing signal of the volatile gas of the correction sample and the sensor array by using an electronic nose with the sensor array;
extracting a characteristic variable value from the time sequence sensing signal, and constructing a characteristic variable matrix after carrying out standardized pretreatment on the characteristic variable value;
and constructing a single-cluster tea aroma type classification model according to the characteristic variable matrix and combining with the aroma type label of the correction sample.
In one embodiment, the timing sense signal comprises a timing sense signal of an aromatic benzene component, an ammoxidation component, an ammonia component, a hydrogen component, an alkane component, a methane component, a hydrogen sulfide component, an ethanol component, a hydrogen sulfide component, and/or an aromatic alkane component.
In one embodiment, extracting feature variable values from the time-series sense signal includes:
and extracting the maximum value, the average value, the 85s stable value, the maximum value of the first derivative, the minimum value of the first derivative and/or the average value of the first derivative of the data curve of the time sequence sensing signal within the preset sampling time as a characteristic variable value.
In one embodiment, the method further comprises:
and analyzing the classification result of the single tea aroma type classification model by using a cross-validation method to determine an optimal single tea aroma type classification model.
In one embodiment, the cross-validation method is used to analyze the classification result of the single tea aroma type classification model to determine an optimal single tea aroma type classification model, including:
acquiring a first relation curve of root mean square error and the number of latent variables of a cross verification model of the single-cluster tea aroma type classification model;
obtaining a second relation curve of the average classifying error rate and the number of latent variables of a cross verification model of the single-cluster tea aroma type classification model;
and determining the number of target latent variables according to the first relation curve and the second relation curve, and determining an optimal single-cluster tea aroma type classification model according to the number of target latent variables.
In one embodiment, the method further comprises:
obtaining a test sample set of single tea leaves; wherein the test sample set comprises a plurality of test samples of single tea leaves of different aroma types;
classifying the aroma type of the test sample by using the single-tea aroma type classification model to verify the effectiveness of the single-tea aroma type classification model.
In one embodiment, a method of obtaining volatile gas from a calibration sample includes:
weighing 15g of each correction sample, respectively filling the correction samples into a 350mL beaker, and sealing the mouth of the beaker by using a sealing film; placing the beaker after the sealing treatment in a room temperature environment of 26+/-1 ℃ for standing for more than 60 minutes, and obtaining volatile gas of each correction sample from the headspace of the beaker after the gas saturation of the headspace of the beaker after the sealing treatment is stable.
In one embodiment, before the collecting the time-series sensing signal of the volatile gas of the calibration sample and the sensor array by the electronic nose with the sensor array, the method further comprises:
setting sampling parameters of the electronic nose; the sampling time is 100s, the sampling time interval is 1s, the automatic cleaning time of the sensor array unit is 60s, the zeroing time of the sensor array unit is 10s, and the air inlet speed of volatile matters is 240mL/min.
In one embodiment, the method further comprises:
and classifying the aroma types of the samples to be classified of the single-cluster tea leaves with unknown aroma types by using the constructed single-cluster tea aroma type classification model.
A single tea aroma type classification device based on bionic olfaction, the device comprising:
the correction sample acquisition module is used for acquiring a correction sample set of single tea leaves; wherein the correction sample set comprises correction samples of a plurality of single tea leaves of different aroma types;
the sensing signal acquisition module is used for acquiring time sequence sensing signals of the volatile gas of the correction sample and the sensor array by using an electronic nose with the sensor array;
the characteristic variable extraction module is used for extracting characteristic variable values from the time sequence sensing signals, and constructing a characteristic variable matrix after standardized pretreatment of the characteristic variable values;
the classification model construction module is used for constructing a single-cluster tea aroma type classification model according to the characteristic variable matrix and combining with the aroma type label of the correction sample.
A computer device comprising a memory, a processor and a computer program stored on the memory and operable on the processor, the processor executing the computer program to perform the steps of the method for classifying aroma types of single tea based on bionic olfaction.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method for classifying aroma types of single tea based on bionic olfaction described above.
According to the method, the device, the computer equipment and the storage medium for classifying the aroma types of the single tea based on bionic smell, the correction samples of the single tea are obtained, the time sequence sensing signals of the correction samples are collected by the electronic nose, the characteristic variable values are extracted from the time sequence sensing signals to construct a characteristic variable matrix, and the characteristic variable matrix is used for combining with the aroma type labels to construct a classification model of the aroma types of the single tea. The single-cluster tea aroma type classification model can realize the rapid classification of the sample aroma types under the condition of not damaging the samples, and meets the requirements of rapid and nondestructive detection of the single-cluster tea aroma types in large-scale production.
Drawings
FIG. 1 is a flow chart of a method for classifying aroma types of single tea based on bionic olfaction in one embodiment;
FIG. 2 is a technical framework diagram of a method for classifying aroma types of single tea based on bionic olfaction in an application example;
FIG. 3 is a graph of time series sensing signals of each tea sample in one example of application;
FIG. 4 is a thermodynamic diagram of a feature variable matrix containing 90 single tea samples in one example of application;
FIG. 5 is a trend graph of classification results of a classification model of single-cluster tea aroma types established by using a partial least squares algorithm according to the number of latent variables in an application example;
FIG. 6 is a block diagram of a single burst tea aroma type classification device based on bionic olfaction in one embodiment;
fig. 7 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order that the invention may be understood more fully, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended claims. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. These embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the experimental methods in the following examples, in which specific conditions are not noted, are generally performed under conventional conditions or under conditions suggested by the manufacturer. The various reagents commonly used in the examples are all commercially available products.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
In one embodiment, as shown in fig. 1, a method for classifying aroma types of single-cluster tea based on bionic olfaction is provided, which comprises the following steps:
step S10: obtaining a correction sample set of single tea leaves; wherein the calibration sample set includes calibration samples of a plurality of single tea leaves of different aroma types.
The single tea is one of three high-aroma tea in the world, and is an important part of quality control of the single tea in order to improve the industrial benefit of the single tea and ensure the aroma type of the single tea in the modern and large-scale production process of the single tea. Specifically, when the correction sample is selected, a sufficient number of samples can be selected as much as possible, and the samples are preferably undamaged, damped and polluted tea single-cluster tea samples with different aroma types. Preferably, the number of correction samples is not less than 60.
Step S20: the electronic nose with the sensor array is used for collecting time sequence sensing signals of volatile gas of correction samples and the sensor array.
Specifically, the electronic nose is an electronic system for identifying smell by using the response of the gas sensor array, the calibration samples have certain volatility, volatile gases formed by volatile substances in each calibration sample are collected by the electronic nose respectively, and the volatile gases act to generate time sequence sensing signals after contacting with the sensor array in the electronic nose.
In one embodiment, a method of obtaining volatile gas from a calibration sample includes: weighing 15g of each correction sample, respectively filling the correction samples into a 350mL beaker, and sealing the mouth of the beaker by using a sealing film; placing the beaker after the sealing treatment in a room temperature environment of 26+/-1 ℃ for standing for more than 60 minutes, and obtaining volatile gas of each correction sample from the headspace of the beaker after the gas saturation of the headspace of the beaker after the sealing treatment is stable.
By adopting the method for acquiring the volatile gas of the correction sample, the volatile gas with higher stability of each correction sample can be obtained, so that the accuracy of the acquisition of the subsequent time sequence sensing signals is improved, and the component characteristics of the sample can be reflected more accurately and comprehensively.
In one embodiment, before collecting the timing sensing signal of the volatile gas of the calibration sample acting with the sensor array using the electronic nose having the sensor array, further comprising: setting sampling parameters of an electronic nose; the sampling time is 100s, the sampling time interval is 1s, the automatic cleaning time of the sensor array unit is 60s, the zeroing time of the sensor array unit is 10s, and the air inlet speed of volatile matters is 240mL/min.
In this embodiment, before the volatile gas of the sample is collected by using the electronic nose, the sampling parameters of the electronic nose may be further set according to the requirements, so as to improve the accuracy of sampling. The sampling parameters can be adjusted according to sample class, accuracy requirements, etc. Preferably, the sampling time is 100s, the sampling time interval is 1s, the automatic cleaning time of the sensor array unit is 60s, the zeroing time of the sensor array unit is 10s, the air inlet speed of volatile matters is 240mL/min, and the sampling parameters can ensure that the volatile matters of a sample are fully contacted with the sensor array, so that the accuracy of subsequent calculation is improved.
In one embodiment, the timing sense signal comprises a timing sense signal of an aromatic benzene component, an ammoxidation component, an ammonia component, a hydrogen component, an alkane component, a methane component, a hydrogen sulfide component, an ethanol component, a hydrogen sulfide component, and/or an aromatic alkane component.
In this embodiment, the volatile components of the calibration sample of single tea leaves may include aromatic benzene components, ammonia oxide components, ammonia components, hydrogen components, alkane components, methane components, hydrogen sulfide components, ethanol components, hydrogen sulfide components, and aromatic alkanes components. Specifically, the electronic nose including the sensor array units capable of generating the time-series sensing signal by reacting with the volatile components may be selected to sample, for example, a PEN3.5 electronic nose apparatus manufactured by AIRSENSE corporation in germany may be used, and the time-series sensing signals of the sensor array units named W1C, W5S, W3C, W6S, W5C, W1S, W1W, W2S, W W and W3S may be obtained, and the sensor array units may be used to detect the time-series sensing signals of the aromatic benzene component, the ammonia component, the hydrogen component, the alkane component, the methane component, the hydrogen sulfide component, the ethanol component, the hydrogen sulfide component and the aromatic alkane component, respectively.
Step S30: and extracting characteristic variable values from the time sequence sensing signals, and constructing a characteristic variable matrix after carrying out standardized pretreatment on the characteristic variable values.
Specifically, the characteristic variable value refers to a variable value capable of reflecting basic characteristic information of a time series signal data curve. The dimension of extracting the feature variable value is not limited, and for example, a maximum value, an average value, an 85s stable value, a first derivative maximum value, a first derivative minimum value, and/or a first derivative average value may be extracted from the time-series sensing signal data within a preset sampling time as the feature variable value.
In one embodiment, extracting feature variable values from a time-series sense signal includes: and extracting the maximum value, the average value, the 85s stable value, the maximum value of the first derivative, the minimum value of the first derivative and/or the average value of the first derivative of the data curve of the time sequence sensing signal within the preset sampling time as the characteristic variable value.
In this embodiment, the data that more accurately and comprehensively reflects the basic features of the time-series sensing signals of each sample can be obtained by extracting the feature variable values from the dimensions.
Specifically, the mathematical expression of the characteristic variable value may be represented by the following formulas (1), (2), (3), (4), (5) and (6), respectively.
x Stable value ＝x t ,t＝85s (3)
Wherein x in formula (1), formula (2), formula (3), formula (4), formula (5), and formula (6) t Representing the reading of a single sensor array unit at time ts, dt represents the derivative of time t.
Further, the extracted feature variable value may be subjected to standardized preprocessing, the standardized preprocessing may be calculated by the following formula (7), and the mean value of the feature variable after the standardized preprocessing is 0 and the variance is 1.
Wherein,,
is the mean value of sample characteristic variables, s 2 Variance is the sample characteristic variable.
Step S40: and constructing a single tea aroma type classification model according to the characteristic variable matrix and combining with the aroma type label of the correction sample.
The standard for determining the fragrance type label is not limited, and can be determined by referring to national standard (GB/T23776-2018), for example. Specifically, a mathematical modeling method such as a partial least square discriminant analysis algorithm can be used for establishing a classification detection model for judging the fragrance type of the single-slave tea based on the characteristic variable matrix and the fragrance type label of each correction sample.
According to the method for classifying the aroma types of the single tea based on the bionic olfaction, the correction samples of the single tea are obtained, the time sequence sensing signals of the correction samples are collected by the electronic nose, the characteristic variable value is extracted from the time sequence sensing signals to construct the characteristic variable matrix, and the characteristic variable matrix is combined with the aroma type label to construct the classification model of the aroma types of the single tea. The single-cluster tea aroma type classification model can realize the rapid classification of the sample aroma types under the condition of not damaging the samples, and meets the requirements of rapid and nondestructive detection of the single-cluster tea aroma types in large-scale production.
In one embodiment, the method further comprises: and analyzing the classification result of the single-cluster tea aroma type classification model by using a cross-validation method to determine an optimal single-cluster tea aroma type classification model.
According to the embodiment, the detection result of the single-cluster tea aroma type classification model established based on the correction set sample is analyzed by using the cross verification method, the related parameters established by the model are adjusted based on the detection result, the modeling parameter with the optimal detection result is determined, and the optimal single-cluster tea aroma type classification model is determined based on the modeling parameter, so that the accuracy and precision of the single-cluster tea aroma type classification model in the follow-up actual classification process for unknown sample classification are improved.
In one embodiment, the cross-validation method is used to analyze the classification result of the classification model of single tea aroma type to determine an optimal classification model of single tea aroma type, comprising: acquiring a first relation curve of root mean square error and the number of latent variables of a cross verification model of a single tea aroma type classification model; obtaining a second relation curve of the average classifying error rate and the number of latent variables of a cross verification model of the single-cluster tea aroma type classification model; and determining the number of target latent variables according to the first relation curve and the second relation curve, and determining an optimal single-cluster tea aroma type classification model according to the number of target latent variables.
In this embodiment, a relationship curve between the root mean square error and the number of latent variables of a cross verification model of a single-cluster tea aroma type classification model is constructed by using a cross verification method as a first relationship curve, a relationship curve between the average classification error rate and the number of latent variables of the cross verification model of the single-cluster tea aroma type classification model is constructed as a second relationship curve, the first number of the latent variables when the root mean square error is minimum is determined by analyzing the first relationship curve, the second number of the latent variables when the average classification error rate is minimum is determined by analyzing the second relationship curve, and the target number of the latent variables is determined by integrating the first number of the latent variables and the second number of the latent variables. Preferably, the first number of latent variables is 4, the second number of latent variables is 4 and 5, and the target number of latent variables is 4.
In the embodiment, the relation curve between the root mean square error and the classification average error rate detected by the model construction method and the number of the latent variables can be used for more accurately determining the optimal target number of the latent variables constructed by the model, and the model calculation speed is increased due to the fact that the number of the latent variables is too small, but under fitting is easy to occur, and the accuracy is insufficient; the number of the latent variables is too large, the calculation speed of the model is reduced, the model is easy to be overfitted with correction set data, and the accuracy is not enough. Therefore, in the embodiment, the accuracy of subsequent classification detection can be improved while the classification speed is ensured by determining the number of the target latent variables and constructing the optimal single-cluster tea aroma type classification model based on the optimal number of the target latent variables.
In one embodiment, the method further comprises: obtaining a test sample set of single tea leaves; wherein the test sample set comprises a plurality of test samples of single tea leaves with different aroma types; and classifying the aroma types of the test samples by using the single-cluster tea aroma type classification model so as to verify the effectiveness of the single-cluster tea aroma type classification model.
Specifically, test samples of a certain number of tea leaves are collected, the electronic nose is used for collecting time sequence sensing signals of volatile gas of each test sample and a sensor array of the electronic nose, the test samples can be collected at the same time of collecting correction samples, and can also be collected before model verification, and the collection mode of the time sequence sensing signals of the test samples is similar to that of the correction samples and is not repeated here. And classifying the aroma types of the test samples through the time sequence sensing signals of the test samples and the single tea aroma type classification model constructed based on the correction samples, and verifying the effectiveness of the model according to classification results.
In one embodiment, the method further comprises: and classifying the aroma types of the samples to be classified of the single-cluster tea leaves with unknown aroma types by using the constructed single-cluster tea aroma type classification model.
Specifically, a sample to be classified of single-cluster tea leaves with unknown aroma types is obtained, a time sequence sensing signal of the sample to be classified, which is acquired by an electronic nose, is obtained, characteristic variable values are extracted from the time sequence sensing signal of the sample to be classified to construct a characteristic variable matrix, the characteristic variable matrix is input into the single-cluster tea aroma type classification model constructed based on the correction sample, and the single-cluster tea aroma type classification model outputs an aroma type label of the sample to be classified, so that the single-cluster tea aroma types are rapidly classified.
The specific manner of the acquisition of the time sequence sensing signal, the extraction of the characteristic variable value and the construction of the characteristic variable matrix of the sample to be classified can refer to the related operation of the correction sample, and will not be described herein.
The method for classifying the single-cluster tea samples with unknown aroma types by using the single-cluster tea aroma type classification model constructed by the method has the advantages of high classification precision, high speed and low cost, and in addition, the samples cannot be damaged, so that the requirements of rapid and nondestructive detection on the single-cluster tea aroma types in large-scale production can be met.
The method for classifying the aroma types of the single-cluster tea based on bionic smell according to the application is further described below with reference to an application example. As can be understood in conjunction with fig. 2, fig. 2 shows a technical framework diagram of a method for classifying aroma types of single-cluster tea based on bionic olfaction in an application example.
First, a raw sample set of single-cluster tea leaves is collected, and a time-series sensing signal and a sensory panel label (aroma type label) of each raw sample are collected. Specifically, 90 tea samples containing floral "phoenix Dancong tea" and honey-flavored "Ling Tou Dancong tea" were collected. And weighing 15g of tea leaves for each tea leaf sample, filling the tea leaves into a 350mL beaker, sealing the tea leaves, placing the tea leaves in an indoor environment at 26+/-1 ℃ for 60min, using an electronic nose to extract air on the top of the beaker for detection, and collecting time sequence sensing signals of the samples. The analysis sampling time of the electronic nose is set to be 100s, the sampling time interval is 1s, the automatic cleaning time of the sensor is 60s, the zeroing time of the sensor is 10s, and the air inlet speed is 240mL/min. When the gas is extracted and injected, volatile matters of the tea samples act on the sensor array unit, the sensor signals change according to the difference of volatile component information, and the time sequence sensing signals of the tea samples are shown in figure 3. And extracting maximum values, average values, 85s stable values, first derivative maximum values, first derivative minimum values and first derivative average values from the acquired 100s time sequence sensing signal data to form a characteristic variable matrix so as to describe volatile substance component information of the sample. The characteristic variable matrix thermodynamic diagram containing 90 single tea samples is shown in figure 4.
In this example, PEN3.5 type electronic nose device manufactured by AIRSENSE corporation, germany, which comprises 10 metal oxide sensors, the names and characteristics of which are shown in Table 1, was used.
TABLE 1 PEN3.5 electronic nose sensor array Unit characterization
The aroma type tag for the collected single tea clump samples was determined using the tea She Ganguan review method with reference to the national standard (GB/T23776-2018).
The method comprises the steps of dividing 90 tea samples into a correction sample set for modeling and a test sample set for verification according to a ratio of 2:1, wherein the correction sample set comprises 46 and 14 samples of floral and honey types for building a classification model, and the test sample set comprises 24 and 6 samples of floral and honey types for testing the performance of the classification model.
After the characteristic variable values of each correction sample in the correction sample set are subjected to standardized pretreatment, a characteristic variable matrix is formed, wherein the characteristic variable matrix comprises signal characteristic values of ten sensors named W1C, W5S, W3C, W6S, W5C, W1S, W1W, W2S, W2W, W3S in the sensor array unit. The signal characteristic values comprise a maximum value, an average value, an 85s stable value, a first derivative maximum value, a first derivative minimum value and a first derivative average value of the data curve of each sensor within 100 s. Thus, each sample can obtain a one-dimensional feature line vector with the length of 60, and the arrangement sequence is as follows: 1 to 10 are the maximum values of the sensors W1 5 3 6 11 2 2 3S, 11 to 20 are the average values of the sensors W1 5 3 6 11 2 2 3S, 21 to 30 are the 85S stable values of the sensors W1 5 3 6 11 2 2 3S, 31 to 40 are the maximum values of the first derivatives of the sensors W1 5 3 6 11 12 2 3S, 41 to 50 are the minimum values of the first derivatives of the sensors W1 5 3 6 11 2 2 3S, and 51 to 60 are the average values of the first derivatives of the sensors W1 5 3 6 11 12 2 3S.
And (3) establishing a single tea aroma type classification model by using a partial least square discriminant analysis algorithm on the characteristic variable matrix, observing a classification model result by using a ten-fold cross validation method, and selecting an optimal classification model.
Fig. 5 shows a trend graph of classification results of the single tea aroma type classification model established by using the partial least square algorithm as a function of the number of latent variables. The single tea aroma type classification model established based on the correction sample set is a correction model, the root mean square error of the correction model is continuously reduced along with the increase of the number of latent variables, and the fitting degree of the representative model to the modeling set data is higher. The root mean square error of the cross validation model decreases and then increases with the number of latent variables, and the minimum value 0.3509 is obtained when the number of the latent variables is 4. The classification average error rate of the correction model generally shows a descending trend along with the increase of the number of the latent variables, and the trend is the same as the change trend of the root mean square error of the correction model. The classification average error rate of the cross validation model decreases and then increases as the number of latent variables increases, and a minimum value 0.1258 is obtained when the number of latent variables is 4 and 5. For the classification model established by the partial least square method, the number of latent variables is too small, the calculation speed of the model is increased, but the model is easy to be under fitted, and the accuracy is insufficient. The number of the latent variables is too large, the calculation speed of the model is reduced, the model is easy to be overfitted with correction set data, and the accuracy is not enough. The optimization of the number of latent variables is a coupled optimization of both model calculation speed and accuracy. In the process of optimizing model parameters by cross validation of ten folds, as the number of the latent variables selected by the correction model increases, the root mean square error of the correction model decreases, which means that the fitting degree of the model to the sample data of the correction set increases, and by checking the Root Mean Square Error (RMSEC) of the cross validation model established by different numbers of the latent variables, when the Root Mean Square Error (RMSEC) is minimum, the corresponding number of the latent variables can be used as the optimal modeling parameters. Thus, the result shown in fig. 5 can determine that the model established when the number of latent variables is 4 is the optimal single tea aroma type classification model.
The test sample is brought into an optimal single-tea aroma type classification model, and the complete detection result of the single-tea aroma type classification model in the application example is calculated and obtained as shown in table 2. The accuracy of the established optimal classification model for classifying the test samples of the test sample set is 86.67%. Under the condition of not damaging the tea samples, the single-cluster tea samples with unknown aroma types are subjected to aroma type classification, so that 86.67% of classification accuracy can be obtained, and the fact that the single-cluster tea aroma types can be rapidly classified based on bionic smell is shown.
Table 2 complete detection results of tea aroma type classification model
It should be understood that, although the steps in the flowcharts are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, and the order of execution of the sub-steps or stages is not necessarily sequential, but may be performed in rotation or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
In one embodiment, as shown in fig. 6, there is provided a single tea aroma type classification device based on bionic olfaction, comprising: a correction sample acquisition module 10, a sensing signal acquisition module 20, a characteristic variable extraction module 30 and a classification model construction module 40, wherein:
a correction sample acquisition module 10 for acquiring a correction sample set of tea leaves of a single tea cluster; wherein the correction sample set comprises correction samples of a plurality of single tea leaves of different aroma types;
a sensing signal acquisition module 20 for acquiring a time sequence sensing signal of the volatile gas of the correction sample acting with the sensor array by using the electronic nose with the sensor array;
the feature variable extraction module 30 is configured to extract feature variable values from the time sequence sensing signal, perform standardized preprocessing on the feature variable values, and then construct a feature variable matrix;
the classification model construction module 40 is configured to construct a single tea aroma type classification model according to the feature variable matrix and the aroma type label of the correction sample.
In one embodiment, the sensing signal acquisition module 20 acquires time-series sensing signals of an ammonia oxide component, an ammonia component, a hydrogen component, an alkane component, a methane component, a hydrogen sulfide component, an ethanol component, a hydrogen sulfide component, and/or an aromatic alkane component.
In one embodiment, the feature variable extraction module 30 extracts, as the feature variable values, a maximum value, an average value, an 85s stable value, a first derivative maximum value, a first derivative minimum value, and/or a first derivative average value of the data curve of the time-series sensing signal for a preset sampling time.
In one embodiment, the classification model construction module 40 is further configured to analyze the classification result of the classification model of single tea aroma type by using a cross-validation method to determine an optimal classification model of single tea aroma type.
In one embodiment, classification model construction module 40 obtains a first relationship of root mean square error versus number of latent variables for cross-validation of a single cluster tea aroma type classification model; acquiring a second relation curve of the classifying average error rate and the number of latent variables of cross verification of the single-cluster tea aroma type classifying model; and determining the number of target latent variables according to the first relation curve and the second relation curve, and determining an optimal single-cluster tea aroma type classification model according to the number of target latent variables.
In one embodiment, the apparatus further comprises a classification model verification module 50 for obtaining a test sample set of tea leaves in a single cluster; wherein the test sample set comprises a plurality of test samples of single tea leaves with different aroma types; and classifying the aroma types of the test samples by using the single-cluster tea aroma type classification model so as to verify the effectiveness of the single-cluster tea aroma type classification model.
In one embodiment, the apparatus further comprises an unknown sample classification module 60 for classifying the aroma type of the sample to be classified of the single tea leaves of unknown aroma type using the constructed single tea aroma type classification model.
In one embodiment, the sensing signal acquisition module 20 weighs 15g of each correction sample, and respectively fills the correction samples into a 350mL beaker, and the sealing film is used for sealing the mouth of the beaker; placing the beaker after the sealing treatment in a room temperature environment of 26+/-1 ℃ for standing for more than 60 minutes, and obtaining volatile gas of each correction sample from the headspace of the beaker after the gas saturation of the headspace of the beaker after the sealing treatment is stable.
In one embodiment, the sensing signal acquisition module 20 is further configured to set sampling parameters of the electronic nose; the sampling time is 100s, the sampling time interval is 1s, the automatic cleaning time of the sensor array unit is 60s, the zeroing time of the sensor array unit is 10s, and the air inlet speed of volatile matters is 240mL/min.
For specific limitations of the classification device for single-tea aroma types based on bionic smell, reference may be made to the above limitation of the classification method for single-tea aroma types based on bionic smell, and no further description is given here. All or part of each module in the single-cluster tea aroma type classification device based on bionic smell can be realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing sample time sequence sensing signal data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by the processor is used for realizing a single-cluster tea aroma type classification method based on bionic smell.
It will be appreciated by those skilled in the art that the structure shown in fig. 7 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method for classifying tea aroma types based on bionic olfaction.
In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, which when executed by a processor implements the steps of the method for classifying aroma types of single-burst tea based on bionic olfaction described above.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
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 above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (7)
1. A method for classifying aroma types of single-cluster tea based on bionic olfaction, the method comprising:
obtaining a correction sample set of single tea leaves; wherein the correction sample set comprises correction samples of a plurality of single tea leaves of different aroma types;
collecting a time sequence sensing signal of the volatile gas of the correction sample and the sensor array by using an electronic nose with the sensor array; the method for acquiring the volatile gas of the correction sample comprises the following steps: weighing 15g of each correction sample, respectively filling the correction samples into a 350mL beaker, and sealing the mouth of the beaker by using a sealing film; placing the beaker after the sealing treatment in a room temperature environment of 26+/-1 ℃ for standing for more than 60 minutes, and obtaining volatile gas of each correction sample from the headspace of the beaker after the gas saturation of the headspace of the beaker after the sealing treatment is stable;
extracting a characteristic variable value from the time sequence sensing signal, and constructing a characteristic variable matrix after carrying out standardized pretreatment on the characteristic variable value;
constructing a single tea aroma type classification model according to the characteristic variable matrix and combining with an aroma type label of a correction sample;
acquiring a first relation curve of root mean square error and the number of latent variables of a cross verification model of the single-cluster tea aroma type classification model;
obtaining a second relation curve of the average classifying error rate and the number of latent variables of a cross verification model of the single-cluster tea aroma type classification model;
and determining the number of target latent variables according to the first relation curve and the second relation curve, and determining an optimal single-cluster tea aroma type classification model according to the number of target latent variables.
2. The method of claim 1, wherein the time-series sensing signal comprises a time-series sensing signal of an aromatic benzene component, an ammoxidation component, an ammonia component, a hydrogen component, an alkane component, a methane component, a hydrogen sulfide component, an ethanol component, a hydrogen sulfide component, and/or an aromatic alkane component.
3. The method of claim 1, wherein extracting feature variable values from the time-series sense signal comprises:
and extracting the maximum value, the average value, the 85s stable value, the maximum value of the first derivative, the minimum value of the first derivative and/or the average value of the first derivative of the data curve of the time sequence sensing signal within the preset sampling time as a characteristic variable value.
4. The method according to claim 1, wherein the method further comprises:
obtaining a test sample set of single tea leaves; wherein the test sample set comprises a plurality of test samples of single tea leaves of different aroma types;
classifying the aroma type of the test sample by using the single-tea aroma type classification model to verify the effectiveness of the single-tea aroma type classification model.
5. The method of claim 1, further comprising, prior to the collecting the timing sense signal of the volatile gas of the calibration sample with the sensor array using the electronic nose having the sensor array:
setting sampling parameters of the electronic nose; the sampling time is 100s, the sampling time interval is 1s, the automatic cleaning time of the sensor array unit is 60s, the zeroing time of the sensor array unit is 10s, and the air inlet speed of volatile matters is 240mL/min.
6. The method according to any one of claims 1 to 5, further comprising:
and classifying the aroma types of the samples to be classified of the single-cluster tea leaves with unknown aroma types by using the constructed single-cluster tea aroma type classification model.
7. A single tea aroma type classification device based on bionic olfaction, characterized in that the device comprises:
the correction sample acquisition module is used for acquiring a correction sample set of single tea leaves; wherein the correction sample set comprises correction samples of a plurality of single tea leaves of different aroma types;
the sensing signal acquisition module is used for acquiring time sequence sensing signals of the volatile gas of the correction sample and the sensor array by using an electronic nose with the sensor array; the volatile gas acquisition mode of the correction sample is as follows: weighing 15g of each correction sample, respectively filling the correction samples into a 350mL beaker, and sealing the mouth of the beaker by using a sealing film; placing the beaker after the sealing treatment in a room temperature environment of 26+/-1 ℃ for standing for more than 60 minutes, and obtaining volatile gas of each correction sample from the headspace of the beaker after the gas saturation of the headspace of the beaker after the sealing treatment is stable;
the characteristic variable extraction module is used for extracting characteristic variable values from the time sequence sensing signals, and constructing a characteristic variable matrix after standardized pretreatment of the characteristic variable values;
the classification model construction module is used for constructing a single tea aroma type classification model according to the characteristic variable matrix and combining with the aroma type label of the correction sample;
the classification model construction module is also used for acquiring a first relation curve of root mean square error and the number of latent variables of cross verification of the single tea aroma type classification model; acquiring a second relation curve of the classifying average error rate and the number of latent variables of cross verification of the single-cluster tea aroma type classifying model; and determining the number of target latent variables according to the first relation curve and the second relation curve, and determining an optimal single-cluster tea aroma type classification model according to the number of target latent variables.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011402079.2A CN112528806B (en) | 2020-12-02 | 2020-12-02 | Single-cluster tea aroma type classification method and device based on bionic olfaction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011402079.2A CN112528806B (en) | 2020-12-02 | 2020-12-02 | Single-cluster tea aroma type classification method and device based on bionic olfaction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112528806A CN112528806A (en) | 2021-03-19 |
| CN112528806B true CN112528806B (en) | 2023-06-16 |
Family
ID=74997395
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011402079.2A Active CN112528806B (en) | 2020-12-02 | 2020-12-02 | Single-cluster tea aroma type classification method and device based on bionic olfaction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112528806B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108593592A (en) * | 2018-04-19 | 2018-09-28 | 广东药科大学 | A kind of tuber of pinellia based on near-infrared spectrum technique mixes pseudo- discrimination method |
| WO2019211243A1 (en) * | 2018-05-04 | 2019-11-07 | Givaudan Sa | Interactive aroma dispensing system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106198446A (en) * | 2016-06-22 | 2016-12-07 | 中国热带农业科学院热带作物品种资源研究所 | The method of L-Borneol content near infrared spectrum quick test Herba Blumeae Balsamiferae leaf powder |
| CN107273421B (en) * | 2017-05-16 | 2020-10-23 | 浙江大学 | High-accuracy mode identification and detection method for aroma type and quality of tea |
| CN111855757B (en) * | 2020-07-21 | 2023-11-14 | 广西壮族自治区亚热带作物研究所（广西亚热带农产品加工研究所） | Liupu tea aged aroma and flavor identification method based on electronic nose |
-
2020
- 2020-12-02 CN CN202011402079.2A patent/CN112528806B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108593592A (en) * | 2018-04-19 | 2018-09-28 | 广东药科大学 | A kind of tuber of pinellia based on near-infrared spectrum technique mixes pseudo- discrimination method |
| WO2019211243A1 (en) * | 2018-05-04 | 2019-11-07 | Givaudan Sa | Interactive aroma dispensing system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112528806A (en) | 2021-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103134850B (en) | A kind of tea leaf quality method for quick based on characteristic perfume | |
| CN109032829A (en) | Data exception detection method, device, computer equipment and storage medium | |
| CN104238543B (en) | The bad pattern method of inspection and its device of the sensing data of time series form | |
| WO2016008398A1 (en) | Program performance test method and device | |
| CN105954412B (en) | For the sensor array optimization method of hickory nut freshness detection | |
| CN105223240A (en) | A kind of method utilizing detection by electronic nose crab freshness | |
| CN116777251B (en) | Full-flow-based monitoring and analyzing system for preparation process of medicament | |
| CN111427928A (en) | Data quality detection method and device | |
| CN108195895A (en) | A kind of tea leaf nitrogen content rapid detection method based on electronic nose and spectrophotometric color measurement instrument | |
| CN107132311A (en) | A kind of fast gas recognizer extracted based on frequency domain character | |
| CN115575322A (en) | Outgoing quality inspection method and system for direct-insertion LED lamp beads | |
| CN112528806B (en) | Single-cluster tea aroma type classification method and device based on bionic olfaction | |
| CN118091369A (en) | Chip testing method, system, device and computer readable storage medium | |
| CN112052496B (en) | Operation method of high arch dam valley amplitude deformation influence factor analysis system based on VAR model | |
| CN115376612B (en) | Data evaluation method and device, electronic equipment and storage medium | |
| CN111474293B (en) | Method and system for determining bacterial wilt solution | |
| CN114169903A (en) | Traditional Chinese medicine digital quality control tracing method capable of fusing nondestructive testing technology | |
| CN112782233B (en) | Gas identification method based on array gas sensor | |
| CN115659271A (en) | Sensor abnormality detection method, model training method, system, device, and medium | |
| CN110047562B (en) | Information structure and method for titer detection based on enzyme activity determination method | |
| Acutis et al. | Analytical method performance evaluation (AMPE) a software tool for analytical method validation | |
| CN118069949B (en) | Dynamic layout method and system based on component tree architecture | |
| CN117740755B (en) | Edible vegetable oil authenticity judging method, system, equipment and medium | |
| CN116878801B (en) | Structure state identification method, device and terminal under random excitation effect | |
| CN107664655A (en) | Method and device for phenetic analysis thing |
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 | ||
| CB02 | Change of applicant information |
Address after: No. 20, Jinying Road, Tianhe District, Guangzhou, Guangdong 510630 Applicant after: Institute of agricultural quality standards and monitoring technology, Guangdong Academy of Agricultural Sciences Address before: No. 20, Jinying Road, Tianhe District, Guangzhou, Guangdong 510630 Applicant before: AGRICULTURAL PUBLIC MONITORING CENTER, GUANGDONG ACADEMY OF AGRICULTURAL SCIENCES |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |