CN108780037A - Spectroscopic analysis methods, device, electronic equipment and computer readable storage medium - Google Patents
Spectroscopic analysis methods, device, electronic equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN108780037A CN108780037A CN201880001146.4A CN201880001146A CN108780037A CN 108780037 A CN108780037 A CN 108780037A CN 201880001146 A CN201880001146 A CN 201880001146A CN 108780037 A CN108780037 A CN 108780037A
- Authority
- CN
- China
- Prior art keywords
- spectral
- components
- spectral analysis
- measured
- analysis model
- 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
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000004611 spectroscopical analysis Methods 0.000 title claims abstract description 7
- 238000010183 spectrum analysis Methods 0.000 claims abstract description 163
- 230000003595 spectral effect Effects 0.000 claims abstract description 87
- 238000001228 spectrum Methods 0.000 claims abstract description 34
- 238000004458 analytical method Methods 0.000 claims abstract description 27
- 238000013507 mapping Methods 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims description 57
- 239000000203 mixture Substances 0.000 claims description 46
- 239000000126 substance Substances 0.000 claims description 37
- 238000013135 deep learning Methods 0.000 claims description 21
- 230000007613 environmental effect Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims 1
- 239000013014 purified material Substances 0.000 claims 1
- 239000004615 ingredient Substances 0.000 abstract 5
- 238000000691 measurement method Methods 0.000 abstract 1
- 230000004913 activation Effects 0.000 description 7
- 238000001237 Raman spectrum Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000001069 Raman spectroscopy Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 210000002364 input neuron Anatomy 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000004304 visual acuity Effects 0.000 description 1
Classifications
-
- 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
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/65—Raman scattering
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/28—Investigating the spectrum
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/28—Investigating the spectrum
- G01J3/44—Raman spectrometry; Scattering spectrometry ; Fluorescence spectrometry
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2201/00—Features of devices classified in G01N21/00
- G01N2201/12—Circuits of general importance; Signal processing
- G01N2201/129—Using chemometrical methods
- G01N2201/1293—Using chemometrical methods resolving multicomponent spectra
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Spectrometry And Color Measurement (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
This application involves spectral measurement methods field, a kind of spectroscopic analysis methods, device, electronic equipment and computer readable storage medium are disclosed.In the application, spectroscopic analysis methods include：Obtain the spectrogram of measured object；According to the spectrum analysis model being obtained ahead of time, spectrum analysis is carried out to the spectrogram of measured object, determines the ingredient of measured object and the accounting of each ingredient；Wherein, spectrum analysis model is to be trained acquisition to a large amount of spectroscopic datas in spectrum samples data set；Spectrum analysis model is used to define spectrogram and ingredient and the mapping relations of each ingredient accounting.The spectroscopic analysis methods, can analyze the accounting of the Multiple components for including in measured object and each ingredient, and effectively reduce influence of the spectral shift to analysis result.
Description
Technical Field
The present disclosure relates to the field of spectral measurement technologies, and in particular, to a spectral analysis method, an apparatus, an electronic device, and a computer-readable storage medium.
Background
Spectroscopic analysis refers to a method of identifying a substance based on its spectrum and determining its chemical composition and relative content to obtain the molecular structure of the substance.
The current spectral analysis is based on the modes of searching, peak searching, chemometrics and the like, and carries out single substance spectral recognition or mixture analysis on a measured object. Specifically, the analysis process is as follows:
the method comprises the steps of firstly finding out the position of a main peak value (a peak value capable of reflecting the characteristics of a measured object) contained in a spectrum to be analyzed through spectrum peak finding, then finding out substances possibly contained in the spectrum to be analyzed through a table look-up mode, removing the substances which are not possible to contain according to unreasonable peak value positions, finally carrying out correlation coefficient calculation on the rest substances, selecting the substances with larger correlation coefficients, and determining the selected substances with larger correlation coefficients as the identified substances.
However, the inventors found that at least the following problems exist in the prior art: the existing spectral analysis method can only carry out single-substance spectral recognition or mixture analysis on a measured object, and when the measured object consisting of a plurality of substances is analyzed, specific substances contained in the measured object and the proportion of each substance cannot be determined.
In addition, in the conventional spectrum analysis method, the analysis result is greatly influenced by the spectrum shift, so that the demand on the spectrum analysis equipment is high, and in order to reduce the influence of the spectrum shift on the analysis result, the calibration coefficient of the spectrum analysis equipment needs to be confirmed periodically so as to ensure that the data output by analysis can be standardized.
Due to different parameters such as resolution, spectral range and the like of the existing spectral analysis equipment, the same database cannot be shared among different spectral analysis equipment.
In addition, as the spectrum data in the spectrum database increases, the time consumed in the analysis process also increases linearly, which undoubtedly increases the calculation amount of the analysis process, thereby seriously affecting the analysis speed.
Disclosure of Invention
The present application provides a spectral analysis method, an apparatus, an electronic device and a computer-readable storage medium to solve the above technical problems.
One embodiment of the present application provides a spectral analysis method, including: obtaining a spectrogram of a measured object; performing spectral analysis on a spectrogram of a measured object according to a spectral analysis model obtained in advance, and determining components of the measured object and the ratio of each component; the spectral analysis model is obtained by training a large amount of spectral data in a spectral sample data set; the spectral analysis model is used for defining the mapping relation between the spectrogram and the components and the proportion of each component.
One embodiment of the present application provides a spectral analysis arrangement comprising: the device comprises an acquisition module and a determination module; the acquisition module is used for acquiring a spectrogram of a measured object; the determining module is used for performing spectral analysis on a spectrogram of the measured object according to a spectral analysis model obtained in advance, and determining components of the measured object and the ratio of each component; the spectral analysis model is obtained by training a large amount of spectral data in a spectral sample data set; the spectral analysis model is used for defining the mapping relation between the spectrogram and the components and the proportion of each component.
One embodiment of the present application provides an electronic device comprising at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method of spectral analysis as referred to in any of the method embodiments of the present application.
An embodiment of the present application provides a computer-readable storage medium having stored thereon computer instructions for causing a computer to perform a method of spectral analysis as referred to in any of the method embodiments of the present application.
Compared with the prior art, the spectral analysis model for defining the mapping relation between the spectrogram and the components and the ratio of each component is obtained by training a large amount of spectral data in the spectral sample data set, and when the components and the ratio of the components of the measured object need to be analyzed, the spectral analysis model is used for carrying out spectral analysis on the spectrogram of the measured object, so that a plurality of components contained in the measured object and the ratio of each component can be quickly analyzed. In addition, because the spectrum analysis model is obtained by training a large amount of spectrum data, and predetermined offset is added to the training data in the training process, the influence of the spectrum offset on an analysis result can be effectively reduced, the accuracy of the result is ensured, and in addition, the sharing of the databases is realized by training the databases with different resolutions and spectrum ranges.
Drawings
One or more embodiments are illustrated by way of example in the accompanying drawings, which correspond to the figures in which like reference numerals refer to similar elements and which are not to scale unless otherwise specified.
FIG. 1 is a flow chart of a method of spectral analysis in a first embodiment of the present application;
FIG. 2 is a schematic illustration of the training of a spectral analysis model in a first embodiment of the present application;
FIG. 3 is a flow chart of a method of spectral analysis in a second embodiment of the present application;
FIG. 4 is a flow chart of a method of spectral analysis in a third embodiment of the present application;
FIG. 5 is a schematic block diagram of a spectral analysis apparatus according to a fourth embodiment of the present application;
fig. 6 is a block diagram of an electronic device in a fifth embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, some embodiments of the present application will be described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
A first embodiment of the present application relates to a spectral analysis method, and a specific flow chart is shown in fig. 1.
In step 101, a spectrogram of a measured object is obtained.
In step 102, a spectrogram of the object to be measured is spectrally analyzed according to the spectral analysis model.
In step 103, the components of the object to be measured and the ratio of each component are determined.
Specifically, in this embodiment, the method for determining the components and the ratios of the components of the measured object may specifically be: inputting the spectral data in the spectrogram of the object to be measured into a spectral analysis model, then obtaining a spectral analysis result output by the spectral analysis model, extracting the components and the proportion of each component from the spectral analysis result, and determining the extracted components and the proportion of each component as the components and the proportion of each component of the object to be measured.
In this embodiment, the spectrum analysis model is obtained by training a large amount of spectrum data in the spectrum sample data set.
In addition, the spectral analysis model obtained by training in this embodiment is mainly used to define the mapping relationship between the spectrogram and the components and the ratios of the components, that is, after the spectral data in the spectrogram to be analyzed is input to the spectral analysis model, the spectral analysis model outputs the components corresponding to the spectrogram and the ratios of the components through analysis.
In addition, in this embodiment, the spectral data included in the spectral sample data set may specifically be spectral data of a pure object alone, or spectral data of a mixture alone, or both.
For ease of understanding, the acquisition of the spectral analysis model is specifically described below:
if the spectral analysis model is only used for analyzing and determining the components of the pure object, only the spectral data set of the pure object with known components needs to be constructed, and then the spectral data in the spectral data set of the pure object is trained based on a deep learning algorithm to obtain the spectral analysis model for analyzing the components of the pure object.
If the spectral analysis model is only used for analyzing and determining the components and the proportions of the components of the mixture, only the spectral data set of the mixture with known components and proportions of the components needs to be constructed, and then the spectral data in the spectral data set of the mixture is trained based on a deep learning algorithm to obtain the spectral analysis model.
If the spectral analysis model can analyze and determine the components of the pure substances and the components and the proportions of the components of the mixture, the spectral analysis model needs to be trained respectively according to the spectral data in the two data sets, so as to obtain the spectral analysis model which can analyze and determine the components of the pure substances and the components and the proportions of the components of the mixture.
With respect to constructing the spectral data set of the purified object with known composition, the operation of training the spectral data in the spectral data set of the purified object based on the deep learning algorithm to obtain the spectral analysis model for analyzing the composition of the purified object may specifically include the following steps:
first, spectral data of a pure object with known composition (which may be spectral data of the pure object with known composition stored in a historical database) is acquired, random noise data and/or abscissa and ordinate offset data (which may be reasonably added by those skilled in the art according to actual conditions) are added to the spectral data of the pure object, and a spectral data set of the pure object with known composition is constructed.
And then, repeatedly training the spectral data in the spectral data set of the pure object based on a deep learning algorithm until a spectral analysis model is obtained.
The method for constructing the spectral data set of the mixture with known components and component ratios includes training spectral data in the spectral data set of the mixture based on a deep learning algorithm, and specifically includes the following steps:
firstly, spectral data of known different substances are randomly added to the constructed spectral data set of the pure substance with known components according to different proportions, and a spectral data set of a mixture with known components and ratios of the components is constructed.
And then, repeatedly training the spectral data in the spectral data set of the mixture based on a deep learning algorithm until a spectral analysis model is obtained.
It should be noted that the above is only an example, and does not limit the technical solution and the scope of protection of the present application, and those skilled in the art can perform the setting according to the needs, and the present invention is not limited herein.
In addition, the above-mentioned repeatedly training the spectral data in the spectral data set until obtaining the spectral analysis model specifically means that training is completed when B can be output by repeatedly training a large amount of spectral data, for example, for a pure object a (component B), by training for many times, as long as a spectrogram of the pure object a is input plus different noises and offsets, even different spectral resolutions and ranges.
The operation of obtaining the spectral analysis model is performed before the spectral analysis of the spectrogram of the object to be measured and the determination of the components and the ratios of the components of the object to be measured. Moreover, the spectral analysis model obtained by training may be directly stored in the spectral analysis device, may also be stored in the remote server, or both may be stored, and the synchronization is updated at regular time according to a certain synchronization mechanism, and a specific implementation manner, which may be reasonably set by a person skilled in the art as needed, is not limited herein.
In order to make a clearer and more complete understanding about the training of the spectral analysis model in the technical solution of the present application, the following raman spectral analysis is specifically described as an example, and a specific training schematic diagram is shown in fig. 2.
The spectral analysis model shown in fig. 2 was trained so that the range of the spectral data stored in the database was 200cm-1～3000cm-1The spectral data are 1400 points, each point is 2cm apart-1The library is trained by taking the spectral data of ten thousand pure objects as an example.
Specifically, L1 to L9 in fig. 2 are an Input Layer (i.e., Input Layer), a first full-link Layer (i.e., sense Layer), a first Batch-wise Layer (i.e., Batch Normalization Layer), a second full-link Layer (i.e., sense Layer), a drop Layer (i.e., drop Layer), a second Batch-wise Layer (i.e., Batch Normalization Layer), a third full-link Layer (i.e., sense Layer), a Filter Layer (i.e., Threshold Filter Layer), and an output Layer, respectively.
Before training, the original 1400 points (i.e. 1400 × 1 tensor) need to be extended to 10000 points (i.e. 10000 × 1 tensor), i.e. a training spectrum sample data set is constructed.
Specifically, a tensor input of 1400 × 1 is defined as an input to L1. Wherein, the Batch Size is obtained after processing the input data.
After passing through L1, the input 1400 × 1 tensor is transmitted to L2, and in L2, the input 1400 × 1 tensor is compiled based on a ReLU (corrected linear unit) activation function to determine whether an offset vector needs to be added.
The specific formula is as follows:
output＝activation(dot(input，kernel)+bias)，
it should be noted that in the above formula, activation is an activation function, kernel is a weight matrix of the layer, bias is a bias vector, and output is the result.
In addition, it should be noted that the principle of the ReLU activation function is to set a negative number to 0, keep a positive number, and by default, not add an offset vector. The formula can be used by those skilled in the art according to the known technical means, and is not described herein in detail.
In L4, a tensor shape with an output of 3200 × 1 is defined, and the first step of continuation is completed. The other parameters are similar to those in L2 and are not described in detail here.
L5 is mainly used to randomly disconnect input neurons by ratio (rate) every time parameters are updated during training (i.e. to put the output tensor part position 0), to prevent overfitting, where the ratio parameter of the layer is set to 0.5.
In L7, a tensor shape with an output of 10000 × 1 is defined, the second continuation is completed, and the Sigmoid activation function is used to activate the data, and other parameters are similar to those in L2, and are not described here again.
After the above operation is completed, data is input to L8, the composition components of the input sample are determined from the tensor values of the output, the outputs of each component larger than the threshold are represented by "1", and the others are represented by "0", and the above structure is transferred to L9 and output by L9.
In addition, it should be noted that the main role of L3 and L6 in fig. 2 is to normalize the activation values of the outputs of L2 and L4 on the training of each batch, so that the average value of the output data is close to 0 and the standard deviation is close to 1.
After the operation is completed, initial sample data needing training can be obtained, and then the training is performed on the sample data based on a deep learning algorithm, which specifically comprises the following steps:
it should be noted that the raman spectrum of a substance is composed of a plurality of gaussian peaks (or lorentz peaks) with different peak heights, the peak width depends on the resolving power of the raman spectrometer, and the peak position depends on the chemical bonds contained in the substance molecules. The raman spectra of different substances mainly show the difference of peak positions and peak height ratios, and the raman spectrum of a mixture can be considered as a linear superposition of the raman spectra of purities forming the mixture.
According to the characteristics of the raman spectrum, the obtained pure raman spectrum data of 10000 substances are divided into A, B, C groups and D groups (in practical application, a data set can be reasonably divided according to the amount of the spectrum data for training, and is not limited here), and the data sets participating in the training are respectively generated according to the following combination modes:
training data for one substance (total 10000):
and A set: substances No. 1 to 2500;
and B, gathering: substances 2501 to 5000;
and C, gathering: materials No. 5001 to 7500;
d, gathering: 7501 to 10000 th substance.
Training data for both substances (15000 total):
the A sets and the B sets correspond to each other one by one, and 2500 mixtures are obtained by adopting random concentration mixing;
the A sets and the C sets correspond to each other one by one, and 2500 mixtures are obtained by adopting random concentration mixing;
the A sets and the D sets correspond to each other one by one, and 2500 mixtures are obtained by adopting random concentration mixing;
the B sets and the C sets correspond to each other one by one, and 2500 mixtures are obtained by adopting random concentration mixing;
the B sets and the D sets correspond to each other one by one, and 2500 mixtures are obtained by adopting random concentration mixing;
the C sets and the D sets correspond one to one, and 2500 mixtures are obtained by mixing random concentrations.
Training data for three substances (total 10000):
a + B + C, one-to-one correspondence, adopting random concentration mixing to obtain 2500 mixtures;
b + C + D, one-to-one correspondence, adopting random concentration mixing to obtain 2500 mixtures;
a + B + D, one-to-one correspondence, adopting random concentration mixing to obtain 2500 mixtures;
a + C + D, one-to-one correspondence, adopting random concentration mixing to obtain 2500 mixtures.
Training data for four substances (total 10000):
a + B + C + D, one-to-one correspondence, adopting random concentration mixing to obtain 2500 mixtures;
from the total of the substances, 4 substances were randomly extracted and mixed at random concentrations, and 7500 times (in practical applications, the mixing here can be set by those skilled in the art according to needs, and is not limited here) were performed to obtain 7500 mixtures.
Finally, the generated 45000 groups of data are divided into a Batch (sample size used by 1 iteration) as input data according to each 1000 pieces of data, and then training is carried out for a certain number of times based on a deep learning algorithm until loss (training loss value) and val _ loss (average training loss value) are stable and reduced to 10-6Hereinafter, the spectral analysis model may be considered to be available at this time.
It should be noted that the above is only an example, and does not limit the technical solution and the scope of protection of the present application, and those skilled in the art can perform the setting according to the needs, and the present invention is not limited herein.
As can be easily found from the above description, the spectral analysis method provided in this embodiment obtains the spectral analysis model for defining the mapping relationship between the spectrogram and the components and the ratios of the components by training a large amount of spectral data in the spectral sample data set, and performs spectral analysis on the spectrogram of the object to be measured by using the spectral analysis model when the components and the ratios of the components of the object to be measured need to be analyzed, so as to quickly analyze the components and the ratios of the components contained in the object to be measured. In addition, because the spectrum analysis model is obtained by training a large amount of spectrum data, and predetermined offset is added to the training data in the training process, the influence of the spectrum offset on an analysis result can be effectively reduced, the accuracy of the result is ensured, and in addition, the sharing of the databases is realized by training the databases with different resolutions and spectrum ranges.
A second embodiment of the present application relates to a method of spectral analysis. The embodiment is further improved on the basis of the first embodiment, and the specific improvement is as follows: when the components of the object to be measured and the ratio of each component are determined, whether the spectrum analysis result carries a label for successful analysis is judged, and corresponding operation is performed according to the judgment result, wherein the specific flow is shown in fig. 3.
Specifically, in the present embodiment, steps 301 to 306 are included, wherein steps 301, 302 and 306 are substantially the same as steps 101 to 103 in the first embodiment, and are not repeated herein, and differences are mainly introduced below, and technical details not described in detail in the present embodiment may be referred to the spectrum collision analysis method provided in the first embodiment, and are not repeated herein.
In step 303, it is determined whether the spectrum analysis result carries a label that is successfully analyzed.
Specifically, if the spectrum analysis result carries a label that is successfully analyzed, step 306 is performed, otherwise, step 304 is performed.
It should be noted that, when determining that the spectrum analysis result carries the label of successful analysis and performing determination of the components and the ratios of the components of the object to be measured in step 306, specifically, the components and the ratios of the components extracted from the spectrum analysis result are determined as the components and the ratios of the components of the object to be measured.
In addition, in this embodiment, the label used for indicating whether the spectral analysis operation is successful or not may be an attribute that is separately set, for example, after the analysis is completed, the output spectral analysis result carries the contents of "success" or "failure", or "YES" or "NO", so as to determine whether the spectral analysis operation is successful or not.
In addition, a field for identifying success or failure may not be separately set, the output of a successfully identified substance is directly set to be "1", and the output of a successfully unidentified substance is set to be "0", so that after the spectrogram of the measured object is analyzed according to the spectral analysis model, if all the output spectral analysis results are "1", it is determined that the spectral analysis operation is successful, otherwise, the operation is failed. And, based on this way, it is also possible to determine whether the object to be measured is pure or a mixture (if the number of "1" is plural, it is a mixture, and otherwise it is pure, on the premise that the success of the spectral analysis operation is determined).
It should be noted that the above is only an example, and does not limit the technical solution and the scope of protection of the present application, and those skilled in the art can perform the setting according to the needs, and the present invention is not limited herein.
In step 304, a new spectral analysis model is acquired.
Specifically, the new spectral analysis model obtained in this embodiment is obtained by training spectral data of other known components and pure substances of the ratios of the components and/or spectral data of a mixture of known components and the ratios of the components, which are obtained from the network, based on a deep learning algorithm.
How to train the spectral data to obtain the process of the spectral analysis mode based on the deep learning algorithm is described in detail in the first embodiment of the present application, and is not described herein again.
In step 305, a spectrogram of the object to be measured is spectrally analyzed according to the new spectral analysis model.
Through the above description, compared with the prior art, in the spectral analysis method provided in this embodiment, when the components and the proportions of the components of the object to be measured cannot be determined by using the existing spectral analysis model, based on the deep learning algorithm, the spectral analysis device or the remote server trains the spectral data of a large number of pure objects with known components and proportions of the components in the network and/or the spectral data of a mixture with known components and proportions of the components to obtain a new spectral analysis model to analyze the spectrogram of the object to be measured, thereby further improving user experience.
In addition, it is worth mentioning that in practical applications, if the components of the object to be measured and the ratios of the components cannot be determined by using a newly obtained spectral analysis model, the analysis can be performed by using the conventional stoichiometric method.
Through the cooperation of the three modes, the accuracy and the timeliness of the analysis result can be ensured as far as possible by the spectral analysis operation, and the user experience can be greatly improved.
In addition, in order to ensure that the device or the server can acquire the spectrum data from the network, so that the spectrum data in the network can be trained based on the deep learning algorithm to obtain a new spectrum analysis model, before the acquired spectrum data is trained based on the deep learning algorithm, it is necessary to determine that the network can be accessed.
If the network cannot be accessed, when the label which is successfully analyzed is carried in the spectrum analysis result, the existing stoichiometric method is directly used for analysis.
It should be noted that the above is only an example, and does not limit the technical solution and the scope of protection of the present application, and those skilled in the art can perform the setting according to the needs, and the present invention is not limited herein.
A third embodiment of the present application relates to a spectral analysis method. The embodiment is further improved on the basis of the first or second embodiment, and the specific improvement is as follows: after the components and the ratio of each component of the object to be measured are determined, the components and the ratio of each component of the object to be measured and the environmental information of the object to be measured are stored. For convenience of explanation, the following description will be made specifically for the modification made on the first embodiment, and a specific flow is shown in fig. 4.
Specifically, in the present embodiment, steps 401 to 404 are included, wherein steps 401 to 403 are substantially the same as steps 101 to 103 in the first embodiment, and are not repeated herein, and differences are mainly introduced below, and technical details not described in detail in the present embodiment may be referred to the spectrum collision analysis method provided in the first embodiment, and are not repeated herein.
In step 404, the components of the object to be measured, the ratio of each component, and the environmental information of the object to be measured are stored.
Compared with the prior art, according to the spectral analysis method provided in this embodiment, after the components and the proportions of the components of the object to be measured are determined, the components and the proportions of the components of the object to be measured obtained through analysis and the environment information where the object to be measured is located, which is obtained through the spectral analysis device, are stored (for example, stored in a memory inside the spectral analysis device or uploaded to a cloud server), so that a tester can conveniently perform subsequent operations according to the data obtained through analysis after completing spectral analysis of the object to be measured, such as updating the data in the spectral sample data set.
It should be noted that the environmental information of the object to be measured in this embodiment may specifically include GPS (Global Positioning System) information of the location of the object to be measured, and image information of the surrounding environment, that is, other related information, so that a manager or a management center can conveniently manage the spectral analysis device and operation arbitrarily.
In addition, the environmental information of the detected object is acquired and stored, so that whether dangerous events exist around the detected object or not is conveniently screened, operators are informed to deal with the dangerous events in time, and the operators and equipment are prevented from being damaged.
In addition, it is worth mentioning that, in practical application, after determining the components and the ratios of the components of the object to be measured, the result may be displayed on a display interface of the spectrum analysis device or transmitted to other devices for subsequent processing.
It should be noted that the above is only an example, and does not limit the technical solution and the scope of protection of the present application, and those skilled in the art can perform the setting according to the needs, and the present invention is not limited herein.
A fourth embodiment of the present application relates to a spectral analysis apparatus, and a specific structure is shown in fig. 5.
As shown in fig. 5, the spectral analysis apparatus mainly includes an acquisition module 501 and a determination module 502.
The obtaining module 501 is configured to obtain a spectrogram of a measured object. The determining module 502 is configured to perform spectral analysis on the spectrogram of the object to be measured according to a spectral analysis model obtained in advance, and determine components of the object to be measured and proportions of the components.
In this embodiment, the spectrum analysis model is obtained by training a large amount of spectrum data in the spectrum sample data set.
In addition, the spectral analysis model obtained by training in this embodiment is mainly used to define the mapping relationship between the spectrogram and the components and the ratio of each component.
In addition, it should be noted that, since the present embodiment is a virtual device embodiment corresponding to the method embodiment, technical details that are not described in detail in the present embodiment may be referred to a spectrum analysis method provided in any embodiment of the present application, and details are not described herein again.
As can be seen from the above description, the spectrum analysis apparatus provided in this embodiment obtains a spectrum analysis model for defining a mapping relationship between a spectrogram and components and ratios of the components by training a large amount of spectrum data in a spectrum sample data set, and performs spectrum analysis on the spectrogram of a measured object by using the spectrum analysis model when the components and ratios of the components of the measured object need to be analyzed, so as to quickly analyze a plurality of components contained in the measured object and the ratios of the components. In addition, the spectral analysis model is obtained by training a large amount of spectral data, so that the influence of spectral shift on an analysis result can be effectively reduced, and the accuracy of the result is ensured.
In addition, it should be noted that the above-described embodiments of the apparatus are merely illustrative, and do not limit the scope of the present application, and in practical applications, a person skilled in the art may select some or all of the modules to implement the purpose of the embodiments according to actual needs, and the present invention is not limited herein.
A fifth embodiment of the present application relates to an electronic device, and a specific structure is shown in fig. 6.
The electronic device in this embodiment may be a spectrum analyzer, such as a portable spectrum analyzer similar to a laptop, a small handheld spectrum analyzer, or an intelligent terminal device installed with a spectrum analysis application program, such as a mobile phone, a tablet computer, and the like, which is not illustrated here, nor is it limited specifically.
Specifically, the electronic device may include one or more processors 601, and a memory 602 and a communication component 603 communicatively connected to at least one processor 601, where one processor 601 is taken as an example in fig. 6.
In this embodiment, each functional module in the spectrum analysis apparatus related to the above embodiments is disposed on the processor 601, and the processor 601, the memory 602, and the communication component 603 may be connected to each other through a bus or in other manners, which is exemplified by being connected through a bus in fig. 6.
The memory 602 is used as a computer readable storage medium for storing software programs, computer executable programs, and modules, such as program instructions/modules corresponding to the spectral analysis method described in any of the method embodiments of the present application. The processor 601 performs the spectral analysis methods involved in any of the method embodiments of the present application by running software programs, instructions and modules stored in the memory 602 and controlling the communication component 603 to receive and/or transmit data.
In addition, it should be noted that the memory 602 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application program required by at least one function; the data storage area can establish an analysis result database for storing the components of the object to be detected, the ratio of each component, the environmental information of the object to be detected and the like. In addition, the memory 602 may include a high-speed Random Access Memory (RAM), a read/write memory (RAM), and the like. In some embodiments, the memory 602 may optionally include memory located remotely from the processor 601, which may be connected to the terminal device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
In addition, in practical applications, the memory 602 may store instructions executed by the at least one processor 601, where the instructions are executed by the at least one processor 601, so as to enable the at least one processor 601 to execute the spectral analysis method according to any embodiment of the present application, and control each functional module in the spectral analysis apparatus to perform each operation in the spectral analysis method.
In addition, it is worth mentioning that, with the development of the cloud computing technology, in order to further improve the processing capability of the electronic device, the electronic device in this embodiment may also be a cloud-end intelligent electronic device, that is, a processor of the electronic device for performing processing operation is located in a cloud end.
Specifically, the cloud intelligent electronic device enables the intelligent computing capacity of the cloud to be a convenient service, so that the research and development cost and the operation cost of the intelligent electronic device are greatly reduced, and the spectrum analysis model can be obtained through more convenient and rapid training by utilizing the strong computing capacity of the cloud.
It should be noted that the two types of electronic devices mentioned above are only specific examples in this embodiment, and do not limit the technical solution and the scope of protection of this application, and in practical applications, those skilled in the art can implement the method based on the implementation flow of the spectral analysis method according to the development of existing machine devices, and the implementation flow is not limited herein.
A sixth embodiment of the present application relates to a computer-readable storage medium, which is a computer-readable storage medium having stored therein computer instructions that enable a computer to perform the spectral analysis method referred to in any of the method embodiments of the present application.
Those skilled in the art can understand that all or part of the steps in the method of the foregoing embodiments may be implemented by a program to instruct related hardware, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, etc.) or a processor (processor) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific examples for carrying out the present application, and that various changes in form and details may be made therein without departing from the spirit and scope of the present application in practice.
Claims (11)
1. A method of spectral analysis comprising:
obtaining a spectrogram of a measured object;
performing spectral analysis on the spectrogram of the measured object according to a spectral analysis model obtained in advance, and determining components of the measured object and the ratio of each component;
the spectral analysis model is obtained by training a large amount of spectral data in a spectral sample data set;
the spectral analysis model is used for defining the mapping relation between the spectrogram and the components and the proportion of each component.
2. The spectral analysis method according to claim 1, wherein before the spectral analysis of the spectrogram of the object to be measured based on the spectral analysis model obtained in advance and the determination of the components and the ratios of the components of the object to be measured, the spectral analysis method further comprises:
establishing a spectral data set of a pure object with known components, and training spectral data in the spectral data set of the pure object based on a deep learning algorithm to obtain the spectral analysis model;
and/or constructing a spectral data set of a mixture with known components and the ratio of each component, and training spectral data in the spectral data set of the mixture based on a deep learning algorithm to obtain the spectral analysis model.
3. The method for spectral analysis according to claim 2, wherein the constructing a spectral dataset of a clean object with known composition, and training the spectral data in the spectral dataset of the clean object based on a deep learning algorithm, specifically comprises:
obtaining spectral data of the purified material of known composition;
adding random noise data and/or horizontal and vertical coordinate offset data to the spectral data of the pure object to construct a spectral data set of the pure object with known components;
and repeatedly training the spectral data in the spectral data set of the pure object based on a deep learning algorithm until the spectral analysis model is obtained.
4. The method of claim 3, wherein the constructing a spectral dataset of a mixture of known components and ratios of components, and training the spectral data in the spectral dataset of the mixture based on a deep learning algorithm, comprises:
randomly adding known spectral data of different substances into the constructed spectral data set of the pure substance with known components according to different proportions to construct a spectral data set of a mixture with known components and the proportions of the components;
and repeatedly training the spectral data in the spectral data set of the mixture based on a deep learning algorithm until the spectral analysis model is obtained.
5. The spectral analysis method according to any one of claims 1 to 4, wherein the spectral analysis of the spectrogram of the object to be measured according to a spectral analysis model obtained in advance to determine the components and the ratios of the components of the object to be measured specifically includes:
inputting the spectral data in the spectrogram of the measured object into the spectral analysis model;
acquiring a spectral analysis result output by the spectral analysis model, and extracting components and the ratio of each component from the spectral analysis result;
and determining the extracted components and the ratios of the components as the components of the object to be detected and the ratios of the components.
6. The method for spectrum analysis according to claim 5, wherein the determining the extracted components and ratios of the components as the components and ratios of the components of the object to be measured specifically comprises:
judging whether the spectrum analysis result carries a label which is successfully analyzed;
if the spectrum analysis result carries the label of successful analysis, determining the extracted components and the ratios of the components as the components of the object to be detected and the ratios of the components;
if the spectrum analysis result does not carry the label of successful analysis, acquiring the spectrum data of the pure object with known components and the proportion of each component existing in the network and/or the spectrum data of the mixture with known components and the proportion of each component, training the acquired spectrum data based on a deep learning algorithm to obtain a new spectrum analysis model, performing spectrum analysis on the spectrogram of the object to be measured according to the new spectrum analysis model, and determining the components of the object to be measured and the proportion of each component.
7. The spectral analysis method of claim 6, wherein prior to training the acquired spectral data based on a deep learning algorithm, the spectral analysis method further comprises:
it is determined that the network can be accessed.
8. The spectral analysis method according to any one of claims 1 to 7, wherein after determining the components and the ratios of the components of the object to be measured, the spectral analysis method further comprises:
and storing the components of the object to be measured, the ratio of each component and the environmental information of the object to be measured.
9. A spectroscopic analysis device comprising: the device comprises an acquisition module and a determination module;
the acquisition module is used for acquiring a spectrogram of the measured object;
the determining module is used for performing spectral analysis on the spectrogram of the measured object according to a spectral analysis model obtained in advance, and determining components of the measured object and the ratio of each component;
the spectral analysis model is obtained by training a large amount of spectral data in a spectral sample data set;
the spectral analysis model is used for defining the mapping relation between the spectrogram and the components and the proportion of each component.
10. An electronic device, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method of spectral analysis according to any one of claims 1 to 8.
11. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out a spectral analysis method according to any one of claims 1 to 8.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2018/082239 WO2019195971A1 (en) | 2018-04-09 | 2018-04-09 | Spectral analysis method, apparatus, electronic device, and computer-readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108780037A true CN108780037A (en) | 2018-11-09 |
Family
ID=64029135
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201880001146.4A Pending CN108780037A (en) | 2018-04-09 | 2018-04-09 | Spectroscopic analysis methods, device, electronic equipment and computer readable storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108780037A (en) |
| WO (1) | WO2019195971A1 (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110057757A (en) * | 2018-01-18 | 2019-07-26 | 深圳市理邦精密仪器股份有限公司 | Identification, identification network establishing method and the device of hemoglobin and its derivative |
| CN110532901A (en) * | 2019-08-12 | 2019-12-03 | 北京邮电大学 | Deep learning intelligence spectroscopic analysis methods and system based on multi-target detection |
| CN111289455A (en) * | 2020-03-25 | 2020-06-16 | 欧梯恩智能科技(苏州)有限公司 | Distributed peculiar smell evaluation method and device, terminal and readable storage medium |
| CN113281291A (en) * | 2021-05-14 | 2021-08-20 | 深圳市八六三新材料技术有限责任公司 | Method and device for analyzing components of essence and computer readable storage medium |
| CN113358594A (en) * | 2020-06-30 | 2021-09-07 | 北京领主科技有限公司 | Substance component analysis system, method, device and medium based on spectrum detection |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111272669A (en) * | 2020-01-23 | 2020-06-12 | 深圳市大拿科技有限公司 | Health assessment method based on fecal information detection and related equipment |
| CN112287426B (en) * | 2020-09-21 | 2024-05-17 | 广东众图科技有限公司 | Method and device for adjusting components of building structure and electronic equipment |
| CN114530216A (en) * | 2020-11-23 | 2022-05-24 | 中移物联网有限公司 | Spectral analysis method, device and readable storage medium |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1412539A (en) * | 2002-11-22 | 2003-04-23 | 中国人民解放军第二军医大学 | Chemical information modification method for quickly quantitatively analyzing complex mixture and spectrograph |
| CN1888860A (en) * | 2006-07-24 | 2007-01-03 | 中国林业科学研究院木材工业研究所 | Establishment of chemical composition content model in plant fiber material and content determining method |
| CN101419159A (en) * | 2008-11-24 | 2009-04-29 | 杨季冬 | Spectrum peak complete-superposing two-component mixture simultaneous determination spectral analysis method |
| CN103119448A (en) * | 2010-09-17 | 2013-05-22 | Abbvie公司 | Raman spectroscopy for bioprocess operations |
| CN104792752A (en) * | 2015-04-03 | 2015-07-22 | 江南大学 | Method for determining content of pigments in mixed pigment solutions by adopting three-dimensional fluorescence spectroscopy combined with PARAFAC (parallel factor analysis) algorithm |
| CN105548079A (en) * | 2015-12-28 | 2016-05-04 | 浙江中烟工业有限责任公司 | Method for determining cut tobacco composition based on near infrared spectrum |
| CN105651705A (en) * | 2015-01-14 | 2016-06-08 | 青海春天药用资源科技利用有限公司 | Method for nondestructively detecting content of counterfeit ingredients in cordyceps sinensis powder/tablets |
| CN105758836A (en) * | 2016-02-18 | 2016-07-13 | 安徽芯核防务装备技术股份有限公司 | Raman spectrum real-time and quantitive analysis method based on area method |
| CN106124449A (en) * | 2016-06-07 | 2016-11-16 | 中国科学院合肥物质科学研究院 | A kind of soil near-infrared spectrum analysis Forecasting Methodology based on degree of depth learning art |
| US20170140524A1 (en) * | 2015-11-17 | 2017-05-18 | Kla-Tencor Corporation | Single image detection |
| CN107145846A (en) * | 2017-04-26 | 2017-09-08 | 贵州电网有限责任公司输电运行检修分公司 | A kind of insulator recognition methods based on deep learning |
| CN107316046A (en) * | 2017-03-09 | 2017-11-03 | 河北工业大学 | A kind of method for diagnosing faults that Dynamic adaptiveenhancement is compensated based on increment |
| CN107491784A (en) * | 2017-08-09 | 2017-12-19 | 云南瑞升烟草技术（集团）有限公司 | Tobacco leaf near infrared spectrum quantitative modeling method and application based on deep learning algorithm |
| CN107679577A (en) * | 2017-10-12 | 2018-02-09 | 理光图像技术（上海）有限公司 | image detecting method based on deep learning |
| CN107796766A (en) * | 2017-10-18 | 2018-03-13 | 盐城工学院 | A kind of smelly pin salt place of production discrimination method, device and computer-readable recording medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09133629A (en) * | 1995-11-08 | 1997-05-20 | Kdk Corp | Treatment method for spectrum in spectral measurement and determination method using it |
| CN101299022A (en) * | 2008-06-20 | 2008-11-05 | 河南中医学院 | Method for evaluating Chinese medicine comprehensive quality using near infrared spectra technique |
| CN107561033A (en) * | 2017-09-21 | 2018-01-09 | 上海理工大学 | Key substance is qualitative in mixture based on tera-hertz spectra and method for quantitatively determining |
-
2018
- 2018-04-09 CN CN201880001146.4A patent/CN108780037A/en active Pending
- 2018-04-09 WO PCT/CN2018/082239 patent/WO2019195971A1/en active Application Filing
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1412539A (en) * | 2002-11-22 | 2003-04-23 | 中国人民解放军第二军医大学 | Chemical information modification method for quickly quantitatively analyzing complex mixture and spectrograph |
| CN1888860A (en) * | 2006-07-24 | 2007-01-03 | 中国林业科学研究院木材工业研究所 | Establishment of chemical composition content model in plant fiber material and content determining method |
| CN101419159A (en) * | 2008-11-24 | 2009-04-29 | 杨季冬 | Spectrum peak complete-superposing two-component mixture simultaneous determination spectral analysis method |
| CN103119448A (en) * | 2010-09-17 | 2013-05-22 | Abbvie公司 | Raman spectroscopy for bioprocess operations |
| CN105651705A (en) * | 2015-01-14 | 2016-06-08 | 青海春天药用资源科技利用有限公司 | Method for nondestructively detecting content of counterfeit ingredients in cordyceps sinensis powder/tablets |
| CN104792752A (en) * | 2015-04-03 | 2015-07-22 | 江南大学 | Method for determining content of pigments in mixed pigment solutions by adopting three-dimensional fluorescence spectroscopy combined with PARAFAC (parallel factor analysis) algorithm |
| US20170140524A1 (en) * | 2015-11-17 | 2017-05-18 | Kla-Tencor Corporation | Single image detection |
| CN105548079A (en) * | 2015-12-28 | 2016-05-04 | 浙江中烟工业有限责任公司 | Method for determining cut tobacco composition based on near infrared spectrum |
| CN105758836A (en) * | 2016-02-18 | 2016-07-13 | 安徽芯核防务装备技术股份有限公司 | Raman spectrum real-time and quantitive analysis method based on area method |
| CN106124449A (en) * | 2016-06-07 | 2016-11-16 | 中国科学院合肥物质科学研究院 | A kind of soil near-infrared spectrum analysis Forecasting Methodology based on degree of depth learning art |
| CN107316046A (en) * | 2017-03-09 | 2017-11-03 | 河北工业大学 | A kind of method for diagnosing faults that Dynamic adaptiveenhancement is compensated based on increment |
| CN107145846A (en) * | 2017-04-26 | 2017-09-08 | 贵州电网有限责任公司输电运行检修分公司 | A kind of insulator recognition methods based on deep learning |
| CN107491784A (en) * | 2017-08-09 | 2017-12-19 | 云南瑞升烟草技术（集团）有限公司 | Tobacco leaf near infrared spectrum quantitative modeling method and application based on deep learning algorithm |
| CN107679577A (en) * | 2017-10-12 | 2018-02-09 | 理光图像技术（上海）有限公司 | image detecting method based on deep learning |
| CN107796766A (en) * | 2017-10-18 | 2018-03-13 | 盐城工学院 | A kind of smelly pin salt place of production discrimination method, device and computer-readable recording medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110057757A (en) * | 2018-01-18 | 2019-07-26 | 深圳市理邦精密仪器股份有限公司 | Identification, identification network establishing method and the device of hemoglobin and its derivative |
| CN110532901A (en) * | 2019-08-12 | 2019-12-03 | 北京邮电大学 | Deep learning intelligence spectroscopic analysis methods and system based on multi-target detection |
| CN111289455A (en) * | 2020-03-25 | 2020-06-16 | 欧梯恩智能科技(苏州)有限公司 | Distributed peculiar smell evaluation method and device, terminal and readable storage medium |
| CN113358594A (en) * | 2020-06-30 | 2021-09-07 | 北京领主科技有限公司 | Substance component analysis system, method, device and medium based on spectrum detection |
| CN113281291A (en) * | 2021-05-14 | 2021-08-20 | 深圳市八六三新材料技术有限责任公司 | Method and device for analyzing components of essence and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019195971A1 (en) | 2019-10-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108780037A (en) | Spectroscopic analysis methods, device, electronic equipment and computer readable storage medium | |
| CA2501003C (en) | Sample analysis to provide characterization data | |
| Murphy et al. | Fluorescence spectroscopy and multi-way techniques. PARAFAC | |
| CN111798932B (en) | Pollutant monitoring data processing method and device, storage medium and terminal | |
| EP3517937B1 (en) | Mixture detection method and device | |
| CN112129741B (en) | Insulating oil aging analysis method and device, computer equipment and storage medium | |
| CN108780048A (en) | A kind of method, detection device and the readable storage medium storing program for executing of determining detection device | |
| CN111351757B (en) | Method and system for predicting quantitative measures of oil doping of edible oil samples | |
| CN112633341A (en) | Interface testing method and device, computer equipment and storage medium | |
| CN114218993A (en) | Online chromatograph control method and device, storage medium and server | |
| CN113051183A (en) | Test data recommendation method and system, electronic device and storage medium | |
| CN114218244B (en) | Online chromatograph database updating method, data identification method and device | |
| CN113567605A (en) | Method and device for constructing automatic interpretation model of mass chromatogram and electronic equipment | |
| CN111289459A (en) | Method, device, equipment and storage medium for detecting component concentration of mixed substance | |
| CN109253981B (en) | Method and device for establishing quantitative analysis model based on infrared spectrum | |
| CN116008248A (en) | Fuel Raman spectrum measuring method and system | |
| CN114564532A (en) | Visualization service platform, system and method based on surveying and mapping data | |
| CN117373565A (en) | Library construction method, identification method and device for ion mobility spectrometry-mass spectrometry | |
| Hu et al. | The Bridge between Screening and Assessment: Establishment and Application of Online Screening Platform for Food Risk Substances | |
| US7904410B1 (en) | Constrained dynamic time warping | |
| Ray et al. | Inferring the shape of data: a probabilistic framework for analysing experiments in the natural sciences | |
| CN113127858A (en) | Anomaly detection model training method, anomaly detection method and anomaly detection device | |
| CN112907145A (en) | Model interpretation method and electronic device | |
| Knapp et al. | A question of scale: modeling biomass, gain and mortality distributions of a tropical forest | |
| CN107664623B (en) | Method for extracting spectral characteristics of substance |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181109 |
|
| RJ01 | Rejection of invention patent application after publication |