CN108830253B - Screening model establishing method, spectrum screening device and method - Google Patents
Screening model establishing method, spectrum screening device and method Download PDFInfo
- Publication number
- CN108830253B CN108830253B CN201810680944.6A CN201810680944A CN108830253B CN 108830253 B CN108830253 B CN 108830253B CN 201810680944 A CN201810680944 A CN 201810680944A CN 108830253 B CN108830253 B CN 108830253B
- Authority
- CN
- China
- Prior art keywords
- spectrum
- gas
- sub
- sample
- target
- 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
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Signal Processing (AREA)
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
Abstract
The application discloses a screening model establishing method, a spectrum screening device and a spectrum screening method. The screening model establishing method is applied to the logging gas screening and comprises the following steps: inputting the obtained Z original samples into a preset classification model for training to obtain a first screening model; selecting V original samples from the Z original samples as a target sub-sample set to correct the first screening model to obtain a sub-model corresponding to the target sub-sample set; calculating a set of stable change values for each subset of targets; averaging the stable change value sets corresponding to the target sub-sample sets to obtain an integrated stable value matrix; screening an integrated stable value according to preset conditions, and constructing a correction spectrum; and inputting the corrected spectrum and the concentration of the gas to be detected corresponding to the corrected spectrum as a correction sample into the first screening model to obtain a second screening model. The scheme of this embodiment can accurately screen out the spectrum that the gas relevancy that awaits measuring is big.
Description
Technical Field
The application relates to the technical field of oil and gas exploration, in particular to a screening model establishing method, a spectrum screening device and a spectrum screening method.
Background
Logging has long been an important technique in petroleum engineering, and has played an important role in the fields of oil and gas exploration and development and service engineering. Among various logging technologies, the gas logging technology can detect gas separated from drilling fluid, and therefore, the gas logging technology is widely applied to the field of oil and gas exploration.
In gas logging technology, there are many methods that can be used to detect gas. The traditional detection method adopts a hydrogen flame chromatography technology, a thermal conductivity chromatography technology, an infrared spectrum technology and the like, and the detection results of the technologies are often not ideal due to the long detection period, few detection indexes and easy interference when the methods detect the gas. In the prior art, gas raman spectroscopy is often used to detect gases.
In the prior art, when gas is analyzed by adopting gas Raman spectroscopy, Raman spectrum information of mixed gas separated from drilling fluid is directly analyzed. Because the gas components separated from the drilling fluid are very complex and contain a plurality of interference gas components which do not need to be analyzed, when the Raman spectrum analysis is carried out, the Raman spectrum information of the interference gas components can cause serious interference to the analysis result of the gas to be detected, and the quantitative analysis precision of the gas Raman spectrum is greatly deteriorated.
Disclosure of Invention
In order to overcome the above disadvantages in the prior art, the present application aims to provide a screening model establishing method applied to logging gas screening, the method including: obtaining Z original samples, and inputting the Z original samples into a preset classification model for training to obtain a first screening model; each original sample comprises Raman spectrum information of a gas to be detected in a group of mixed gases and concentration information of various gases to be detected in the group of mixed gases, wherein the Raman spectrum information comprises sub-spectra corresponding to a plurality of wavelengths;
selecting V original samples from the Z original samples as a target sub-sample set, and correcting the first screening model according to the target sub-sample set to obtain a sub-model corresponding to the target sub-sample set;
taking one of the target subsample sets as a target sample, respectively changing the spectrum of the target sample according to a plurality of preset wavelengths, and obtaining a stable change value set corresponding to the plurality of preset wavelengths according to the processed spectrum and the submodel corresponding to the target subsample set, wherein the stable change value set comprises a stable change value corresponding to each gas to be detected;
repeating the action of selecting the target sub-sample set to obtain a stable change value set corresponding to the plurality of target sub-sample sets;
averaging the stable change value sets corresponding to the target sub-sample sets to obtain an integrated stable value matrix;
screening an integrated stable value according to a preset condition, and constructing a corrected spectrum from sub-spectra corresponding to the integrated stable value meeting the preset condition in the original sample;
and inputting the corrected spectrum and the concentration of the gas to be detected corresponding to the corrected spectrum as a correction sample into a first screening model to obtain a second screening model.
Optionally, the step of taking one of the target sub-sample sets as a target sample, performing change processing on the spectrum of the target sample for a plurality of preset wavelengths, and obtaining a stable change value set corresponding to the plurality of preset wavelengths according to the processed spectrum and the sub-model corresponding to the target sub-sample set includes:
sequentially taking a sub-spectrum of one wavelength in the spectrum of the multiple wavelengths of the target sample as a target sub-spectrum;
increasing the intensity of a target sub-spectrum by a first preset value to obtain a processed first spectrum, decreasing the intensity of the target sub-spectrum by a second preset value to obtain a processed second spectrum, and respectively inputting the first spectrum and the second spectrum into sub-models corresponding to the target sample to respectively obtain a first prediction result of the first spectrum and a second prediction result of the second spectrum; the first prediction result and the second prediction result both comprise the predicted concentrations of the plurality of gases to be detected;
and subtracting the predicted concentration of the same gas to be detected in the first prediction result and the second prediction result respectively to obtain a stable change value of each gas to be detected in the target sample corresponding to the wavelength.
Optionally, the obtaining of the original sample comprises:
mapping the Raman spectrum information of the gas to be detected to a nonlinear space to obtain the wavelength of the Raman spectrum information of each gas to be detected;
and filtering sub-spectra corresponding to the wavelengths of the Raman spectrum information of the gas to be detected in the Raman spectrum information of the mixed gas.
Optionally, the method further comprises the step of,
and inputting the Raman spectrum information of the mixed gas and the concentration of the gas to be detected in the mixed gas into a second screening model, and adjusting the second screening model.
It is another object of the present invention to provide a spectral screening apparatus, comprising:
the training module is used for obtaining Z original samples and inputting the Z original samples into a preset classification model for training to obtain a first screening model; each original sample comprises Raman spectrum information of a gas to be detected in a group of mixed gases and concentration information of various gases to be detected in the group of mixed gases, wherein the Raman spectrum information comprises sub-spectra corresponding to a plurality of wavelengths;
the calculation module selects V original samples from the Z original samples as a target sub-sample set, and corrects the first screening model according to the target sub-sample set to obtain a sub-model corresponding to the target sub-sample set;
taking one of the target subsample sets as a target sample, respectively changing the spectrum of the target sample according to a plurality of preset wavelengths, and obtaining a stable change value set corresponding to the plurality of preset wavelengths according to the processed spectrum and the submodel corresponding to the target subsample set, wherein the stable change value set comprises a stable change value corresponding to each gas to be detected;
repeating the action of selecting the target sub-sample set to obtain a stable change value set corresponding to the plurality of target sub-sample sets;
averaging the stable change value sets corresponding to the target sub-sample sets to obtain an integrated stable value matrix;
the reconstruction module screens an integrated stable value according to preset conditions, and constructs a corrected spectrum from sub-spectra corresponding to the integrated stable value meeting the preset conditions in the original sample; and the correction module is used for inputting the corrected spectrum and the concentration of the gas to be detected corresponding to the corrected spectrum into the first screening model as a correction sample to obtain a second screening model.
Optionally, the computing module is further configured to: the step of taking one of the target sub-sample sets as a target sample, respectively performing change processing on the spectrum of the target sample according to a plurality of preset wavelengths, and obtaining a stable change value set corresponding to the plurality of preset wavelengths according to the processed spectrum and the sub-model corresponding to the target sub-sample set comprises:
sequentially taking a sub-spectrum of one wavelength in the spectrum of the multiple wavelengths of the target sample as a target sub-spectrum;
increasing the intensity of a target sub-spectrum by a first preset value to obtain a processed first spectrum, decreasing the intensity of the target sub-spectrum by a second preset value to obtain a processed second spectrum, and respectively inputting the first spectrum and the second spectrum into sub-models corresponding to the target sample to respectively obtain a first prediction result of the first spectrum and a second prediction result of the second spectrum; the first prediction result and the second prediction result both comprise the predicted concentrations of the plurality of gases to be detected;
and subtracting the predicted concentration of the same gas to be detected in the first prediction result and the second prediction result respectively to obtain a stable change value of each gas to be detected in the target sample corresponding to the wavelength.
Optionally, the apparatus further comprises a preliminary screening module configured to:
mapping the Raman spectrum information of the gas to be detected to a nonlinear space to obtain the wavelength of the Raman spectrum information of each gas to be detected;
and filtering sub-spectra corresponding to the wavelengths of the Raman spectrum information of the gas to be detected in the Raman spectrum information of the mixed gas.
Optionally, the correction module is further configured to,
and inputting the Raman spectrum information of the mixed gas and the concentration of the gas to be detected in the mixed gas into a second screening model, and adjusting the second screening model.
It is another object of the present invention to provide a method of spectral screening, the method comprising,
inputting the Raman spectrum information to be screened into a second screening model established by any one of the screening model establishing methods to obtain the screened spectrum.
Optionally, the method further comprises:
collecting Raman spectrum information of unknown gas;
and filtering sub-spectra corresponding to the wavelengths of the Raman spectrum information of the gas to be detected in the Raman spectrum information of the unknown gas to obtain filtered Raman spectrum information, and taking the filtered Raman spectrum information as the Raman spectrum information to be screened.
Compared with the prior art, the method has the following beneficial effects:
according to the scheme provided by the embodiment of the application, in the process of measuring the logging gas, according to the influence degree of the sub-spectra with various wavelengths on the prediction result in the mixed gas Raman spectrum, the spectrum is reconstructed according to the influence degree, and a new sample is formed to correct the screening model. Thereby, it is made possible to more accurately screen out a spectrum important for predicting the concentration of the gas to be measured.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a first schematic flow chart of a model building method according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart illustrating a second method for building a model according to an embodiment of the present disclosure;
FIG. 3 is a flowchart of a stable value calculation method according to an embodiment of the present disclosure;
FIG. 4 is a block diagram of a spectrum screening apparatus according to an embodiment of the present disclosure;
FIG. 5 is a schematic flow chart of a spectral screening method provided in an embodiment of the present application;
FIG. 6 is a graph illustrating the results of an uncorrected screening model for a test gas according to an embodiment of the present application;
fig. 7 shows the predicted result of the final screening model for a gas to be tested according to the embodiment of the present application.
Icon: 111-a training module; 112-a calculation module; 113-a reconstruction module; 114-a correction module; 115-preliminary screening module.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings or orientations or positional relationships that the products of the present invention are conventionally placed in use, and are used only for convenience in describing the present application and simplifying the description, but do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present application. Furthermore, the terms "first," "second," "third," and the like are used solely to distinguish one from another and are not to be construed as indicating or implying relative importance.
Furthermore, the terms "horizontal", "vertical", "overhang" and the like do not imply that the components are required to be absolutely horizontal or overhang, but may be slightly inclined. For example, "horizontal" merely means that the direction is more horizontal than "vertical" and does not mean that the structure must be perfectly horizontal, but may be slightly inclined.
In the description of the present application, it is further noted that, unless expressly stated or limited otherwise, the terms "disposed," "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present application can be understood in a specific case by those of ordinary skill in the art.
As shown in fig. 1, the following method for establishing a screening model according to the preferred embodiment of the present application includes:
and step S111, respectively collecting the Raman spectrum information of the Z groups of mixed gases to obtain the Raman spectrum of each group of mixed gases.
In Z mixed gas group, each mixed gas group comprises Y gases, the Y gases comprise N gases to be detected, and the N gases to be detected are respectively represented as: g1，...，Gn...，GNThe concentration of the Y gases in each set of mixed gases is known, GnRepresents the nth gas to be detected, 0<n<And N is added. The Raman spectrum of each group of mixed gases comprises p wavelength sub-spectra, and the wavelengths of the p wavelength sub-spectra are respectively expressed as lambda1，...，λi，...,λp，1<i<p。
Step S112, respectively taking the Raman spectrum information of the gas with detection corresponding to each group of mixed gas in the group Z of mixed gas and the concentration information of each gas to be detected in the group of mixed gas as original training samples to carry out modeling so as to obtain a first screening model; the first screening model may be an LS-SVR model.
Between step S112 and step S111, a preliminary screening step of raman spectrum information may be further included, where the preliminary screening step of raman spectrum is: each original sample comprises Raman spectrum information of a gas to be detected in a group of mixed gases and concentration information of various gases to be detected in the group of mixed gases, wherein the Raman spectrum information comprises sub-spectra corresponding to a plurality of wavelengths; the original training sample can also be composed of spectrum information of raman spectrum information of gases to be detected which are screened out, and concentration information of gases to be detected, that is, for a sub-spectrum with a certain wavelength, if the raman spectrum information of any gas to be detected in the mixed gas does not have the sub-spectrum with the wavelength, the sub-spectrum with the wavelength in the mixed gas is filtered out.
For example, the raman spectrum information in a certain mixed gas includes a wavelength λ1，λ2，λ3The Raman spectrum information of various gases to be detected in the mixed gas only contains the wavelength lambda1，λ2The wavelength of the mixed gas Raman spectrum information is lambda3Filtering out the Raman spectrum information.
The step can filter out the spectrum irrelevant to the Raman spectrum information of the gas to be detected in the Raman spectrum information of the mixed gas.
Step S113, selecting V samples from Z original samples as target sub-sample set MtRemoving the target subsample set MtThe outer samples are all used as a syndrome sample set and a syndrome sample set MySet M of target subsamplestAnd syndrome sample set MyAnd inputting the first screening model, and correcting the first screening model to obtain the sub-models corresponding to the target sub-sample set.
In this embodiment, the target sub-sample set and the syndrome sample set are selected to correct the first screening model, so that a sub-model with higher precision can be obtained. In selecting the target subsample set, the target subsample set (i.e. the training subset) may be selected according to a random sampling technique, for example according to the monte carlo method.
Step S114:
as shown in fig. 2, in step S1141, a group of samples is selected from the target subset as a target sample MtxAnd sequentially taking the sub-spectrum of one wavelength in a plurality of preset wavelengths in the target sample as a target sub-spectrum. Increasing the intensity of the target sub-spectrum by a first preset value to obtain a first spectrum Mx(ii) a Attenuating the intensity of the target sub-spectrumObtaining a second spectrum M by a second preset valuex'; x represents the order of the selected target subsample set, Mt, i.e. the selected target subsample set, MtIs the second most.
In this embodiment, the first preset value and the second preset value are set according to actual conditions, and the first preset value and the second preset value may be equal in value.
For example, the values of the first preset value and the second preset value may be set to 15%, and at this time, a stable variation value may be obtained.
Noting the increased wavelength as λiThe predicted concentration of the nth gas is CinThe attenuation wavelength is denoted as λiThe predicted concentration of the nth gas is Cin'. Sub-spectra are spectra for each wavelength.
Step S1142, the first spectrum MxInputting a sub-model corresponding to the target sub-sample set to obtain a first spectrum MxFirst predicted result A ofxThe second spectrum Mx' inputting a sub-model corresponding to the target sub-sample set to obtain a pair of second spectra Mx' second prediction result Ax'；
Wherein A isxComprising a vector of N elements, AxThe element (C) includes a result of predicting the concentration of each gas in the mixed gasi1，...，Cin，...，CiN。Ax' is a vector comprising N elements, AxIn the formula, N elements represent the results of predicting the concentrations of the gases Ci1'，Ci2'，...，CiN'. Wherein C isi1Represents gas G1Predicted concentration of (C)inRepresents gas GnPredicted concentration of (C)iNRepresents gas GNThe predicted concentration of (c). Ci1' denotes G in the gas mixture1Predicted concentration of (C)in' denotes G in the gas mixturenPredicted concentration of (C)iNDenotes G in the mixed gasNThe predicted concentration of (c).
Step S1143, the first prediction is performedThe result is subtracted from the predicted concentration of the corresponding gas in the second prediction result to obtain the relative wavelength lambda of the predicted concentration of each gas to be detectediA stable value of the sub-spectrum of (a).
Of the x-th target sample, the number of samples,
gas G1Corresponding to wavelength λiThe stable change values of the sub-spectra of (a) are:
SVxi1＝Ci1-Ci1'；
gas GnCorresponding to wavelength λiThe stable change values of the sub-spectra of (a) are:
SVxin＝Cin-Cin'；
gas GNCorresponding to wavelength λiThe stable change values of the sub-spectra of (a) are:
SVxiN＝CiN-CiN'. The embodiment can obtain the corresponding stable variation value of the sub-spectrum by changing the sub-spectrum with the same wavelength in the target sample.
For example, when the target subsample set is selected for the first time, the wavelength is changed to λ1Of the sub-spectra of (a), selecting V samples from the Z sets of original samples as a target set of sub-samples MtTaking the samples except the target subsample set as a syndrome subsample set MySet M of target subsamplestAnd syndrome sample set MyAnd inputting the first screening model, and correcting the first screening model to obtain a sub-model, wherein the sub-model is the sub-model corresponding to the target sub-sample set.
Noting the increased wavelength as λiAt sub-spectral intensity of (a), the predicted concentration of the nth gas is CinThe attenuation wavelength is denoted as λiAt sub-spectral intensity of (a), the predicted concentration of the nth gas is Cin'。
Selecting a set of samples from the target subset of samples as target samples Mt1A target sample Mt1Medium wavelength is lambda1The intensity of the sub-spectrum is increased to obtain a first spectrum M corresponding to the target sub-sample set1(ii) a The first spectrum Mt1Medium wavelength is lambda1Is reduced to obtain a second spectrum M1'；
The first spectrum M1Inputting the sub-model corresponding to the target sub-sample set to obtain a first spectrum M1Predicted result of (A)1The second spectrum M1' inputting the sub-model corresponding to the target sub-sample set to obtain the second spectrum M1' prediction result A1'；
A1Including a concentration vector C11，...，C1n，...，C1N. Wherein, in the mixed gas, C11Represents gas G1Concentration of (C)1nRepresents gas GnBy analogy, C1NRepresents gas GNThe concentration of (c). A. the1' includes the element C11'，...,C1n'，...，C1N'. Wherein, C11' denotes G in the gas mixture1Concentration of `, C1n' denotes G in the gas mixturenConcentration of `, C1N' denotes G in the gas mixtureN' of the formula (I).
At a wavelength of λ1Subtracting the corresponding gas concentration prediction results after the sub-spectral intensities are respectively increased and decreased to obtain the output gas concentration relative to the wavelength lambda1The stable variation value of the sub-spectrum of (a). The stable variation value is the difference between the predicted concentration obtained by increasing the first preset intensity of the sub-spectrum of a certain wavelength of a certain gas to be detected in the target sample and the predicted concentration obtained by decreasing the second preset intensity of the sub-spectrum of the wavelength.
Gas G1Corresponding wavelength lambda1The stable change values of the sub-spectra of (a) are:
SV111＝C11-C11'；
gas GnCorresponding wavelength lambda1The stable change value of the sub-spectrum is:
SV11n＝C1n-C1n'；
gas GNCorresponding wavelength lambda1The stable change values of the sub-spectra of (a) are:
SV11N＝C1N-C1N'。
when changing sub-spectra of other wavelengths, the method for calculating the stable change value of the corresponding wavelength of each gas to be detected in the mixed gas takes the reference wavelength as lambda1The calculation method in sub-spectra of (a).
Sequentially changing the intensity of the sub-spectrum of each wavelength in the selected target sample to respectively obtain the stable change values corresponding to the sub-spectra of the corresponding wavelength, thereby obtaining the wavelength of which is sequentially changed to be lambda1，...，λi，...，λpAnd when the intensity of the sub-spectrum is high, each gas to be detected corresponds to the stable change value set of the sub-spectrum of each wavelength.
Steady variation value of the first wavelength: SVx11，...，SVx1N
Steady variation value of the second wavelength: SVx21，...，SVx2N
...
Stable change value of p-th wavelength: SVxp1，...，SVxpN
The steady change values for each gas to be detected for different wavelengths in a target subset form a matrix J1:
SVx11，...，SVx1N
SVx21，...，SVx2N
...
SVxp1，...，SVxpN
step S115, repeating the step S113 and the step S114X times to obtain an integrated stable value of each gas to be detected in X sub-models, wherein the intensity of the spectrum with the wavelength p is corresponding to the gas GnThe integrated stable value calculation method comprises the following steps:
ESVpn＝(SV1pn+...+SVxpn)/X
please refer to fig. 4 for a specific calculation flow of the integrated stable value.
The integrated stability value of each gas to be detected in the X submodels is as follows:
integrated stability value of gas to be detected in the first submodel:
ESV11，...，ESV1N
integrated stability value of gas to be detected in the second submodel:
ESV21，...，ESV2N
...
integrated stability value of gas to be detected in xth submodel:
ESVX1，...，ESVXN
the integrated stability value of each gas to be detected in the X submodels is represented by a matrix K as:
ESV11，...，ESV1N
ESV21，...，ESV2N
...
ESVX1，...，ESVXN
step S116, sorting all integrated stable values in the matrix K according to absolute value, wherein the larger the absolute value is, the corresponding wavelength lambda is showniThe more important the sub-spectrum of (a) is, the more important the sub-spectrum of each wavelength is obtained.
Screening an integrated stable value according to a preset condition, and constructing a corrected spectrum by using a sub-spectrum corresponding to the integrated stable value meeting the preset condition in an original sample;
in practice, the spectrum of wavelengths with the absolute value of the integrated stable value within a predetermined range may be screened out.
For example, in raman spectrum information of a certain sample, the wavelength is λ1，λ4，λ9，λ11，λ12The integrated stable value corresponding to the sub-spectrum satisfies the preset condition, i.e. the wavelength is lambda1，λ4，λ9，λ11，λ12If the integrated stable value corresponding to the sub-spectrum is within the preset range, the wavelength is lambda1，λ4，λ9，λ11，λ12The corresponding sub-spectra are screened out as the corrected spectrum.
And step S117, inputting the corrected spectrum and the concentration of the gas to be detected corresponding to the corrected spectrum into a first screening model as a correction sample to obtain a second screening model.
The invention sets the threshold value (preset range) of the integrated stable value to ensure that the ESV with the absolute value larger than the threshold valuexnAnd the spectral wavelength variable corresponding to the wavelength and the concentration of the gas to be detected are used as correction target samples. And correcting the first screening model of the target sample to obtain a corrected second screening model. In the scheme provided by the embodiment, the sub-spectrum which has a large influence on the analysis of the logging gas can be accurately screened from the Raman spectrum information of the mixed gas.
In an embodiment, in order to further improve the accuracy of the second filtered model, a second filtered model modification may be performed during the use, where the second filtered model modification step is: and inputting the Raman spectrum information of the mixed gas and the concentration of the gas to be detected of the mixed gas into the second screening model, and adjusting the second screening model.
As shown in fig. 3, another embodiment of the present application further provides a spectral screening apparatus, which includes a training module 111, a calculation module 112, a reconstruction module 113, and a correction module 114.
It is another object of the present invention to provide a spectral screening apparatus, comprising:
the training module 111 is used for obtaining Z original samples and inputting the Z original samples into a preset classification model for training to obtain a first screening model; each original sample comprises Raman spectrum information of a gas to be detected in a group of mixed gases and concentration information of various gases to be detected in the group of mixed gases, wherein the Raman spectrum information comprises sub-spectra corresponding to a plurality of wavelengths;
in this embodiment, the model training module 111 is configured to execute step S111, and please refer to corresponding steps in this embodiment for a detailed description of this step.
A calculating module 112, configured to select V original samples from the Z original samples as a target sub-sample set, and modify the first screening model according to the target sub-sample set to obtain a sub-model corresponding to the target sub-sample set;
taking one of the target subsample sets as a target sample, respectively changing the spectrum of the target sample according to a plurality of preset wavelengths, and obtaining a stable change value set corresponding to the plurality of preset wavelengths according to the processed spectrum and the submodel corresponding to the target subsample set, wherein the stable change value set comprises a stable change value corresponding to each gas to be detected;
repeating the action of selecting the target sub-sample set to obtain a stable change value set corresponding to the plurality of target sub-sample sets;
averaging the stable change value sets corresponding to the target sub-sample sets to obtain an integrated stable value matrix;
in this embodiment, the calculation module 112 is configured to execute step S112 to step S115. For a detailed description of this step, refer to the corresponding step in the model building method.
The reconstruction module 113 is used for screening an integrated stable value according to a preset condition, and constructing a modified spectrum from the sub-spectrum corresponding to the integrated stable value meeting the preset condition in the original sample;
in this embodiment, the reconstruction module 113 is configured to execute step S116. For a detailed description of this step, refer to the corresponding step in the model building method.
And the correction module 114 is used for inputting the corrected spectrum and the concentration of the gas to be detected corresponding to the corrected spectrum into the first screening model as a correction sample to obtain a second screening model.
In this embodiment, the correction module 114 is configured to execute step S117. For a detailed description of this step, refer to the corresponding step in the model building method.
Optionally, the calculation module 112 is further configured to: the step of taking one of the target sub-sample sets as a target sample, respectively performing change processing on the spectrum of the target sample according to a plurality of preset wavelengths, and obtaining a stable change value set corresponding to the plurality of preset wavelengths according to the processed spectrum and the sub-model corresponding to the target sub-sample set comprises:
sequentially taking a sub-spectrum of one wavelength in the spectrum of the multiple wavelengths of the target sample as a target sub-spectrum;
increasing the intensity of a target sub-spectrum by a first preset value to obtain a processed first spectrum, decreasing the intensity of the target sub-spectrum by a second preset value to obtain a processed second spectrum, and respectively inputting the first spectrum and the second spectrum into sub-models corresponding to the target sample to respectively obtain a first prediction result of the first spectrum and a second prediction result of the second spectrum; the first prediction result and the second prediction result both comprise predicted concentrations of a plurality of gases to be detected.
In this embodiment, the calculating module 112 is used for executing each sub-step (step S1141-step S1143) of the step S114, and for a detailed description of the step, reference is made to a corresponding step in the model building method.
Optionally, the apparatus further comprises a preliminary screening module 115, the preliminary screening module 115 being configured to:
mapping the Raman spectrum information of the gas to be detected to a nonlinear space to obtain the wavelength of the Raman spectrum information of each gas to be detected;
and filtering sub-spectra corresponding to the wavelengths of the Raman spectrum information of the gas to be detected in the Raman spectrum information of the mixed gas.
For a detailed description of this step, please refer to the corresponding primary screening step of raman spectrum information in the model building method.
Optionally, the correction module 114 is further configured to input the raman spectrum information of the mixed gas and the concentration of the gas to be detected in the mixed gas into the second screening model, and adjust the second screening model.
For a detailed description of this step, refer to the corresponding second screening model modification step in the model building method.
As shown in fig. 5, another embodiment of the present application also provides a spectrum screening method, including:
step S121, obtaining Raman spectrum information of each gas to be detected, namely mapping the logging gas to a nonlinear space, and obtaining the wavelength of the Raman spectrum information of each gas to be detected. In this embodiment, the best mode isThe small two-times support vector machine maps the logging gas to a nonlinear space. For example, if the concentration of gas G to be measured1，G2，...,GnThe concentration of (c). At this time, G1，G2，...GnThe respective raman spectral information is represented in a nonlinear space.
Collecting Raman spectrum information of unknown gas;
step S122, filtering sub-spectra corresponding to the wavelengths of the Raman spectrum information of the gas to be detected in the Raman spectrum information of the unknown gas to obtain filtered Raman spectrum information, and taking the filtered Raman spectrum information as the Raman spectrum information to be screened.
And S123, inputting the Raman spectrum information to be screened into the corrected second screening model for screening to obtain the screened spectrum.
Fig. 6 and 7 show the results of the first specific experiment, where fig. 6 shows the results of the first screening model for predicting the content of methane in the mixed gas G, and fig. 7 shows the results of the second screening model for predicting the content of methane in the mixed gas G.
In summary, according to the scheme provided by the embodiment of the application, in the process of measuring logging gas, according to the influence degree of sub-spectra with various wavelengths in the mixed gas raman spectrum on the prediction result, the spectrum is reconstructed according to the influence degree, and a new sample is formed to correct the screening model. Thereby, it is made possible to more accurately screen out a spectrum important for predicting the concentration of the gas to be measured.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to 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 is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A screening model establishing method is applied to well logging gas screening, and comprises the following steps:
obtaining Z original samples, and inputting the Z original samples into a preset classification model for training to obtain a first screening model; each original sample comprises Raman spectrum information of a gas to be detected in a group of mixed gases and concentration information of various gases to be detected in the group of mixed gases, wherein the Raman spectrum information comprises sub-spectra corresponding to a plurality of wavelengths;
selecting V original samples from the Z original samples as a target sub-sample set, and correcting the first screening model according to the target sub-sample set to obtain a sub-model corresponding to the target sub-sample set;
taking one of the target subsample sets as a target sample, respectively changing the spectrum of the target sample according to a plurality of preset wavelengths, and obtaining a stable change value set corresponding to the plurality of preset wavelengths according to the processed spectrum and the submodel corresponding to the target subsample set, wherein the stable change value set comprises a stable change value corresponding to each gas to be detected;
repeating the action of selecting the target sub-sample set to obtain a stable change value set corresponding to the plurality of target sub-sample sets;
averaging the stable change value sets corresponding to the target sub-sample sets to obtain an integrated stable value matrix;
screening an integrated stable value according to a preset condition, and constructing a corrected spectrum from sub-spectra corresponding to the integrated stable value meeting the preset condition in the original sample;
and inputting the corrected spectrum and the concentration of the gas to be detected corresponding to the corrected spectrum as a correction sample into a first screening model to obtain a second screening model.
2. The method for establishing a screening model according to claim 1, wherein the step of taking one of the target sub-sample sets as a target sample, performing variation processing on the spectrum of the target sample with respect to a plurality of preset wavelengths, and obtaining a stable variation value set corresponding to the plurality of preset wavelengths according to the processed spectrum and the sub-model corresponding to the target sub-sample set comprises:
sequentially taking a sub-spectrum of one wavelength in the spectrum of the multiple wavelengths of the target sample as a target sub-spectrum;
increasing the intensity of a target sub-spectrum by a first preset value to obtain a processed first spectrum, decreasing the intensity of the target sub-spectrum by a second preset value to obtain a processed second spectrum, and respectively inputting the first spectrum and the second spectrum into sub-models corresponding to the target sample to respectively obtain a first prediction result of the first spectrum and a second prediction result of the second spectrum; the first prediction result and the second prediction result both comprise the predicted concentrations of the plurality of gases to be detected;
and subtracting the predicted concentration of the same gas to be detected in the first prediction result and the second prediction result respectively to obtain a stable change value of each gas to be detected in the target sample corresponding to the wavelength.
3. The screening model building method according to claim 1, wherein the obtaining step of the original sample is:
mapping the Raman spectrum information of the gas to be detected to a nonlinear space to obtain the wavelength of the Raman spectrum information of each gas to be detected;
and filtering sub-spectra corresponding to the wavelengths of the Raman spectrum information of the gas to be detected in the Raman spectrum information of the mixed gas.
4. The screening model creation method of claim 1, further comprising,
and inputting the Raman spectrum information of the mixed gas and the concentration of the gas to be detected in the mixed gas into a second screening model, and adjusting the second screening model.
5. A spectral screening apparatus, comprising:
the training module is used for obtaining Z original samples and inputting the Z original samples into a preset classification model for training to obtain a first screening model; each original sample comprises Raman spectrum information of a gas to be detected in a group of mixed gases and concentration information of various gases to be detected in the group of mixed gases, wherein the Raman spectrum information comprises sub-spectra corresponding to a plurality of wavelengths;
the calculation module selects V original samples from the Z original samples as a target sub-sample set, and corrects the first screening model according to the target sub-sample set to obtain a sub-model corresponding to the target sub-sample set;
taking one of the target subsample sets as a target sample, respectively changing the spectrum of the target sample according to a plurality of preset wavelengths, and obtaining a stable change value set corresponding to the plurality of preset wavelengths according to the processed spectrum and the submodel corresponding to the target subsample set, wherein the stable change value set comprises a stable change value corresponding to each gas to be detected;
repeating the action of selecting the target sub-sample set to obtain a stable change value set corresponding to the plurality of target sub-sample sets;
averaging the stable change value sets corresponding to the target sub-sample sets to obtain an integrated stable value matrix;
the reconstruction module screens an integrated stable value according to preset conditions, and constructs a corrected spectrum from sub-spectra corresponding to the integrated stable value meeting the preset conditions in the original sample; and the correction module is used for inputting the corrected spectrum and the concentration of the gas to be detected corresponding to the corrected spectrum into the first screening model as a correction sample to obtain a second screening model.
6. The spectral screening apparatus of claim 5, wherein the calculation module is further configured to: the step of taking one of the target sub-sample sets as a target sample, respectively performing change processing on the spectrum of the target sample according to a plurality of preset wavelengths, and obtaining a stable change value set corresponding to the plurality of preset wavelengths according to the processed spectrum and the sub-model corresponding to the target sub-sample set comprises:
sequentially taking a sub-spectrum of one wavelength in the spectrum of the multiple wavelengths of the target sample as a target sub-spectrum;
increasing the intensity of a target sub-spectrum by a first preset value to obtain a processed first spectrum, decreasing the intensity of the target sub-spectrum by a second preset value to obtain a processed second spectrum, and respectively inputting the first spectrum and the second spectrum into sub-models corresponding to the target sample to respectively obtain a first prediction result of the first spectrum and a second prediction result of the second spectrum; the first prediction result and the second prediction result both comprise the predicted concentrations of the plurality of gases to be detected;
and subtracting the predicted concentration of the same gas to be detected in the first prediction result and the second prediction result respectively to obtain a stable change value of each gas to be detected in the target sample corresponding to the wavelength.
7. Spectral screening apparatus according to claim 5, further comprising a preliminary screening module for:
mapping the Raman spectrum information of the gas to be detected to a nonlinear space to obtain the wavelength of the Raman spectrum information of each gas to be detected;
and filtering sub-spectra corresponding to the wavelengths of the Raman spectrum information of the gas to be detected in the Raman spectrum information of the mixed gas.
8. The spectral screening apparatus of claim 5, wherein the correction module is further configured to,
and inputting the Raman spectrum information of the mixed gas and the concentration of the gas to be detected in the mixed gas into a second screening model, and adjusting the second screening model.
9. A method of spectral screening, comprising,
inputting the Raman spectrum information to be screened into a second screening model established by the screening model establishing method according to any one of claims 1 to 4, and obtaining the screened spectrum.
10. The method for spectral screening of claim 9, further comprising:
collecting Raman spectrum information of unknown gas;
and filtering sub-spectra corresponding to the wavelengths of the Raman spectrum information of the gas to be detected in the Raman spectrum information of the unknown gas to obtain filtered Raman spectrum information, and taking the filtered Raman spectrum information as the Raman spectrum information to be screened.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810680944.6A CN108830253B (en) | 2018-06-27 | 2018-06-27 | Screening model establishing method, spectrum screening device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810680944.6A CN108830253B (en) | 2018-06-27 | 2018-06-27 | Screening model establishing method, spectrum screening device and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108830253A CN108830253A (en) | 2018-11-16 |
| CN108830253B true CN108830253B (en) | 2021-11-26 |
Family
ID=64137839
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810680944.6A Active CN108830253B (en) | 2018-06-27 | 2018-06-27 | Screening model establishing method, spectrum screening device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108830253B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109508440B (en) * | 2018-11-28 | 2023-01-03 | 武汉轻工大学 | Method, device and equipment for constructing spectral analysis model and storage medium |
| CN110163276B (en) * | 2019-05-15 | 2021-03-26 | 浙江中烟工业有限责任公司 | Screening method of near infrared spectrum modeling sample |
| CN109975230B (en) * | 2019-05-16 | 2021-09-17 | 北京印刷学院 | On-line detection system and method for concentration of atmospheric pollutants |
| CN113588572B (en) * | 2021-08-04 | 2024-03-19 | 广州市华南自然资源科学技术研究院 | Intelligent management system for farmland heavy metal online detection correction model |
| CN113804577B (en) * | 2021-09-09 | 2022-09-06 | 湖北工业大学 | Screening method of environment-friendly insulating gas adsorbent |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103854305A (en) * | 2014-03-19 | 2014-06-11 | 天津大学 | Module transfer method based on multiscale modeling |
| CN105765381A (en) * | 2013-09-24 | 2016-07-13 | 维萨拉公司 | Method and system for gas concentration measurement of gas dissolved in liquids |
| CN106680241A (en) * | 2017-01-13 | 2017-05-17 | 北京化工大学 | Novel spectrum multi-analysis classification and identification method and application thereof |
| CN106778893A (en) * | 2016-12-28 | 2017-05-31 | 东北大学 | A kind of EO-1 hyperion Method of Sample Selection based on dimensionality reduction with cluster |
| CN107091818A (en) * | 2017-06-28 | 2017-08-25 | 武汉米字能源科技有限公司 | A kind of many air chamber complex component gas analysis systems and method |
| CN107092921A (en) * | 2017-03-10 | 2017-08-25 | 佛山市南海区广工大数控装备协同创新研究院 | The hyperspectral image classification method filtered based on K arest neighbors |
| CN107110776A (en) * | 2014-11-11 | 2017-08-29 | 光谱传感器公司 | Target analysis analyte detection and quantization in sample gas with complex background composition |
| CN107727638A (en) * | 2017-11-02 | 2018-02-23 | 嘉兴镭光仪器科技有限公司 | A kind of laser Raman spectroscopy gas analyzer with resonator enhancing |
| CN107818298A (en) * | 2017-09-27 | 2018-03-20 | 厦门大学 | General Raman spectral characteristics extracting method for machine learning material recognition |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8571281B2 (en) * | 2010-07-13 | 2013-10-29 | Carestream Health, Inc. | Dental shade mapping |
| JP2017026599A (en) * | 2015-07-22 | 2017-02-02 | パナソニックＩｐマネジメント株式会社 | Hydrogen gas inspection method and hydrogen gas inspection device |
| KR102396249B1 (en) * | 2015-10-14 | 2022-05-09 | 삼성전자주식회사 | Method and apparatus for user authentication using Raman spectrum |
-
2018
- 2018-06-27 CN CN201810680944.6A patent/CN108830253B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105765381A (en) * | 2013-09-24 | 2016-07-13 | 维萨拉公司 | Method and system for gas concentration measurement of gas dissolved in liquids |
| CN103854305A (en) * | 2014-03-19 | 2014-06-11 | 天津大学 | Module transfer method based on multiscale modeling |
| CN107110776A (en) * | 2014-11-11 | 2017-08-29 | 光谱传感器公司 | Target analysis analyte detection and quantization in sample gas with complex background composition |
| CN106778893A (en) * | 2016-12-28 | 2017-05-31 | 东北大学 | A kind of EO-1 hyperion Method of Sample Selection based on dimensionality reduction with cluster |
| CN106680241A (en) * | 2017-01-13 | 2017-05-17 | 北京化工大学 | Novel spectrum multi-analysis classification and identification method and application thereof |
| CN107092921A (en) * | 2017-03-10 | 2017-08-25 | 佛山市南海区广工大数控装备协同创新研究院 | The hyperspectral image classification method filtered based on K arest neighbors |
| CN107091818A (en) * | 2017-06-28 | 2017-08-25 | 武汉米字能源科技有限公司 | A kind of many air chamber complex component gas analysis systems and method |
| CN107818298A (en) * | 2017-09-27 | 2018-03-20 | 厦门大学 | General Raman spectral characteristics extracting method for machine learning material recognition |
| CN107727638A (en) * | 2017-11-02 | 2018-02-23 | 嘉兴镭光仪器科技有限公司 | A kind of laser Raman spectroscopy gas analyzer with resonator enhancing |
Non-Patent Citations (3)
| Title |
|---|
| "Raman-Spectroscopic investigation of sulfate ion concentration change in a continuously stirred tank reactor during the preparation of a cathode material precursor";IlBok Lee;《Electrochimica Acta》;20170820;第246卷;第864-869页 * |
| "气体监测中光学分析方法研究";勤奋的四川瞭望;《https://www.douban.com/note/571606732/》;20160721;第1-2页 * |
| "近红外光纤水气传感器的关键技术研究";王强;《中国博士学位论文全文数据库 信息科技辑》;20161115;第I140-1页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108830253A (en) | 2018-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108830253B (en) | Screening model establishing method, spectrum screening device and method | |
| Andersen et al. | Variable selection in regression—a tutorial | |
| Olivieri et al. | MVC2: A MATLAB graphical interface toolbox for second-order multivariate calibration | |
| JP6089345B2 (en) | Multicomponent regression / multicomponent analysis of temporal and / or spatial series files | |
| CN103534578B (en) | Determine spectral device and the method for composition present in sample | |
| Jiang et al. | Comparison of algorithms for wavelength variables selection from near-infrared (NIR) spectra for quantitative monitoring of yeast (Saccharomyces cerevisiae) cultivations | |
| US7251037B2 (en) | Method to reduce background noise in a spectrum | |
| US7248370B2 (en) | Method to reduce background noise in a spectrum | |
| Yu et al. | A comparison of several trilinear second-order calibration algorithms | |
| CN109060760B (en) | Analysis model establishing method, gas analysis device and method | |
| CN102608061B (en) | Improved method for extracting Fourier transformation infrared spectrum characteristic variable of multi-component gas by aid of TR (Tikhonov regularization) | |
| JP2013537307A (en) | Monitor, detect, and quantify compounds in gaseous sample streams | |
| Olivieri et al. | The effect of data matrix augmentation and constraints in extended multivariate curve resolution–alternating least squares | |
| US11592398B2 (en) | Augmented Raman analysis of a gas mixture | |
| Galvao et al. | An application of subagging for the improvement of prediction accuracy of multivariate calibration models | |
| Tang et al. | On-line multi-component alkane mixture quantitative analysis using Fourier transform infrared spectrometer | |
| CN109060702A (en) | Infrared spectroscopy quantitative analysis of nonlinear method | |
| Wang et al. | Estimation of soil organic matter by in situ Vis-NIR spectroscopy using an automatically optimized hybrid model of convolutional neural network and long short-term memory network | |
| CN107966499B (en) | Method for predicting crude oil carbon number distribution by near infrared spectrum | |
| Nespeca et al. | Multivariate filters combined with interval partial least square method: A strategy for optimizing PLS models developed with near infrared data of multicomponent solutions | |
| Mohseni et al. | Second-order advantage obtained from standard addition first-order instrumental data and multivariate curve resolution-alternating least squares. Calculation of the feasible bands of results | |
| Pierce et al. | Pixel-level data analysis methods for comprehensive two-dimensional chromatography | |
| CN103398971A (en) | Chemometrics method for determining cetane number of diesel oil | |
| WO2016120762A1 (en) | Automatic quantitative regression | |
| CN111896497A (en) | Spectral data correction method based on predicted value |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220215 Address after: 100027 Chaoyangmen North Street, Chaoyang District, Chaoyang District, Beijing Patentee after: SINOPEC Group Patentee after: SINOPEC OILFIELD SERVICE Corp. Patentee after: Sinopec Jingwei Co.,Ltd. Patentee after: Southwest measurement and control company of Sinopec Jingwei Co.,Ltd. Patentee after: Southwest logging branch of Sinopec Jingwei Co.,Ltd. Address before: 621000 No.28, Pingzheng 1st lane, Fucheng District, Mianyang City, Sichuan Province (Wuyi Mingdu 5f-1-56) Patentee before: GEOLOGIC LOGGING COMPANY OF SOUTHWEST PETROLEUM BUREAU, SINOPEC |