CN112649390A - Adhesive moisture content monitoring method based on near infrared spectrum - Google Patents
Adhesive moisture content monitoring method based on near infrared spectrum Download PDFInfo
- Publication number
- CN112649390A CN112649390A CN202011531316.5A CN202011531316A CN112649390A CN 112649390 A CN112649390 A CN 112649390A CN 202011531316 A CN202011531316 A CN 202011531316A CN 112649390 A CN112649390 A CN 112649390A
- Authority
- CN
- China
- Prior art keywords
- adhesive
- near infrared
- moisture content
- infrared spectrum
- prediction 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
- 239000000853 adhesive Substances 0.000 title claims abstract description 57
- 230000001070 adhesive effect Effects 0.000 title claims abstract description 57
- 238000002329 infrared spectrum Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000012544 monitoring process Methods 0.000 title claims abstract description 13
- 238000001514 detection method Methods 0.000 claims abstract description 16
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 13
- 239000011230 binding agent Substances 0.000 claims abstract description 6
- 238000007689 inspection Methods 0.000 claims description 15
- 238000012795 verification Methods 0.000 claims description 15
- 238000012360 testing method Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000004497 NIR spectroscopy Methods 0.000 claims description 4
- 238000002790 cross-validation Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 238000012847 principal component analysis method Methods 0.000 claims description 2
- 230000003595 spectral effect Effects 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 7
- 238000007781 pre-processing Methods 0.000 abstract description 3
- 238000000513 principal component analysis Methods 0.000 description 4
- 239000003380 propellant Substances 0.000 description 4
- 230000001419 dependent effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004449 solid propellant Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000005303 weighing Methods 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
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3554—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for determining moisture content
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention relates to a binder moisture content monitoring method based on near infrared spectrum, which comprises the following steps: preparing a calibration sample set; acquiring an original near infrared spectrum; respectively preprocessing the original near infrared spectrum of each standard sample to obtain a target near infrared spectrum; making target near infrared spectra of all standard samples into a data set, constructing a quantitative model, and detecting the quantitative model by using a detection set to obtain a prediction model of the moisture content of the adhesive; and (4) determining the adhesive to be determined by utilizing a prediction model of the water content in the adhesive to obtain a water content determination result. The invention can effectively carry out rapid and reliable quantitative detection on the moisture in the adhesive, has short detection time and high result accuracy, and is particularly suitable for continuous, real-time and on-line detection of components on an industrial adhesive production line.
Description
Technical Field
The invention relates to the field of adhesive detection, in particular to an adhesive moisture content monitoring method based on near infrared spectrum.
Background
The adhesive is a key component of the solid propellant, and the moisture content of the adhesive in the production of the propellant must be strictly controlled because the moisture in the adhesive has important influence on the energy performance, the combustion performance, the mechanical property and the technological performance of the propellant. At present, on-site sampling is periodically carried out on an adhesive production line once, then the sample is sent to a physicochemical detection center, the water content of the sample is analyzed by using a Karl Fischer method, and if the detection is unqualified, the production line is subjected to secondary treatment until the index requirement is met. Because the traditional detection method has the problems of time and labor consumption, low efficiency, poor accuracy and the like, and can not meet the development requirement of adhesive production, a determination method for rapidly, continuously analyzing and monitoring the water content in the adhesive in real time is needed, and the method plays an important role in ensuring the development and capacity improvement of the current propellant.
Disclosure of Invention
The invention provides a method for monitoring the moisture content of an adhesive based on near infrared spectroscopy, which solves the technical problems of time and labor consumption, low efficiency and lower accuracy in the conventional method for measuring the moisture content of the adhesive. The invention can effectively carry out rapid and reliable quantitative detection on the moisture in the adhesive, has short detection time and high result accuracy, and is suitable for continuous, real-time and on-line detection of components on an industrial adhesive production line.
In order to solve the technical problem, the invention provides a binder moisture content monitoring method based on near infrared spectrum, which comprises the following steps:
s1: adding water with different proportions into the adhesive with the same quality to prepare 30 modeling standard samples with the concentration in a gradient distribution manner;
s2: under the preset spectral resolution, performing near-infrared scanning on each modeling standard sample according to the preset scanning times to obtain an original near-infrared spectrum corresponding to each modeling standard sample;
s3: performing dimensionality reduction treatment on the original near infrared spectrum of each modeling standard sample by using a principal component analysis method to obtain a target near infrared spectrum corresponding to each standard sample;
s4: making target near infrared spectra of all modeling standard samples into a data set, constructing a quantitative model, and detecting the quantitative model by using a detection set to obtain a moisture content prediction model in the adhesive;
s5: and (4) determining the adhesive to be determined by utilizing a prediction model of the water content in the adhesive to obtain a water content determination result.
Further, the S4 includes the following steps:
s41: adopting a cross validation method to make target near infrared spectra of all modeling standard samples into data sets, wherein 5 data sets are used as inspection sets, and 25 data sets are used as test sets;
s42: and constructing the quantitative model, setting inspection parameters of the quantitative model, wherein the inspection parameters comprise iteration times, and inspecting the quantitative model by using the inspection set and the inspection parameters to obtain a prediction model of the moisture content in the adhesive.
Further, in S4, the prediction model of moisture content in the adhesive is verified by using the test set, if the verification is passed, the step S42 is executed, and if the verification is not passed, the step S41 is returned to.
Further, the step S42 includes the following steps:
s421: inputting the test set into a prediction model of the moisture content in the adhesive, and respectively calculating a correlation coefficient and a root mean square error:
the calculation formula of the correlation coefficient is as follows:
the calculation formula of the root mean square error is as follows:
wherein, R is2For correlation coefficients, RMSECV is the root mean square error, M is the number of samples in the test set,C i is the actual value of the number of the ith sample,is a predicted value of the number of the ith sample,is the average of all the actual values,Differ i is the difference between the chemically measured value and the predicted value for the ith sample;
s422: and judging whether the prediction model of the moisture content in the adhesive passes the verification according to the correlation coefficient and the root mean square error, if so, executing S42, and if not, executing S41.
According to the method for monitoring the moisture content of the adhesive based on the near infrared spectrum, the original near infrared spectrum is obtained through near infrared scanning of an adhesive sample, and then the original near infrared spectrum is preprocessed, so that disordered information such as noise in the original near infrared spectrum can be removed, and a target near infrared spectrum with higher quality is obtained; and then, a data set is made according to the target near infrared spectrum, a quantitative model is constructed, and the quantitative model is detected by using the detection set, so that a prediction model of the moisture content in the adhesive is obtained. The method can effectively and reliably quantitatively detect the moisture in the propellant adhesive, has short detection time and high result accuracy, and is particularly suitable for continuous, real-time and online detection of components on an industrial adhesive production line.
Detailed Description
The present invention is further illustrated by the following specific examples. The scope of the invention is not limited thereto but should include the full scope of the claims. Any changes or substitutions that may be easily made by those skilled in the art within the technical scope of the present disclosure are intended to be included within the scope of the present disclosure.
A binder moisture content monitoring method based on near infrared spectrum comprises the following steps:
s1: weighing adhesive standard samples with the same mass, and injecting 0-10 mu L of water into the samples one by adopting a microliter injector to prepare 30 modeling standard samples with the concentration in a gradient distribution;
s2: respectively placing 30 modeling samples to 40cm3The sample cell is used for near infrared scanning, the near infrared scanning uses near infrared spectrum (the specific model is Nicolet 6700), a transmission measurement module is adopted, and the scanning range is 4000cm-1~10000cm-1The scanning times are 128 times, and the resolution is 8cm-1Scanning each sample for 3 times to obtain a near infrared spectrum data set of each sample;
s3: performing dimensionality reduction on the original near infrared spectrum of each modeling standard sample by using a Principal Component Analysis (PCA) method to obtain a target near infrared spectrum corresponding to each standard sample;
the original near infrared spectrum contains a large amount of useless information related to non-target factors, including background noise, baseline drift and the like, besides useful chemical information, so that the original near infrared spectrum needs to be preprocessed, and the spectrum preprocessing method comprises the steps of eliminating constant offset, subtracting a straight line, vector normalization, minimum-maximum normalization, first derivative and second derivative, wherein the processing results of the obtained near infrared spectrum are different when the spectrum preprocessing method is used independently or independently; in the embodiment, the Principal Component Analysis (PCA) is used for dimensionality reduction, so that the component information with the largest influence factor on the determination of the moisture content in each original near infrared spectrum can be obtained, the processing effect is best, the target near infrared spectrum is obtained, and the optimal quantitative model can be obtained subsequently;
s4: making target near infrared spectra of all modeling standard samples into a data set, constructing a quantitative model, and detecting the quantitative model by using a detection set to obtain a moisture content prediction model in the adhesive;
wherein the S4 includes the following steps:
s41: adopting a cross validation method to make target near infrared spectra of all modeling standard samples into data sets, wherein 5 data sets are used as inspection sets, and 25 data sets are used as test sets;
s42: constructing the quantitative model, setting inspection parameters of the quantitative model, wherein the inspection parameters comprise iteration times, and inspecting the quantitative model by using the inspection set and the inspection parameters to obtain a prediction model of the moisture content in the adhesive;
wherein, in S4, the test set is used to verify the prediction model of moisture content in adhesive, if the verification is passed, the step 42 is executed, if the verification is not passed, the step S41 is returned, wherein, if the verification is passed, the test set is used to verify the prediction model of moisture content in adhesive, the prediction effect of the model can be evaluated, and if the verification is passed, it indicates that the accuracy of the prediction model of moisture content in adhesive of the present embodiment on the determination of moisture content in adhesive can reach the expectation, and if the verification is not passed, it indicates that the accuracy of the prediction model of moisture content in adhesive is not enough, the operation needs to be returned to S41 for rechecking until the prediction model reaching the expectation accuracy is obtained; through the verification steps, the accuracy of the prediction model of the moisture content in the adhesive can be effectively ensured;
wherein the S42 includes the following steps:
s421: inputting the test set into a prediction model of the moisture content in the adhesive, and respectively calculating a correlation coefficient and a root mean square error:
the calculation formula of the correlation coefficient is as follows:
the calculation formula of the root mean square error is as follows:
wherein, R is2For correlation coefficients, RMSECV is the root mean square error, M is the number of samples in the test set,C i is the actual value of the number of the ith sample,is a predicted value of the number of the ith sample,is the average of all the actual values,Differ i is the difference between the chemically measured value and the predicted value for the ith sample;
s422: judging whether the prediction model of the moisture content in the adhesive passes the verification according to the correlation coefficient and the root mean square error, if so, executing S42, otherwise, executing S41, wherein the correlation coefficient R2The fitting degree of the whole regression equation can be measured, the overall relation between the dependent variable and all independent variables is expressed, the change of the dependent variable is described by the change of the independent variables, the maximum value of the correlation coefficient is 1, and when the correlation coefficient is close to 1 month, the fitting degree of the regression equation to the predicted value is better; the root mean square error RMSECV reflects the accuracy of the prediction model, and when the root mean square error is smaller, the accuracy of the prediction model is higher, and the prediction capability is stronger; therefore, the goodness of the model is related to the correlation coefficient and the root mean square error;
s5: and (4) determining the adhesive to be determined by utilizing a prediction model of the water content in the adhesive to obtain a water content determination result.
The verification of the model for predicting the moisture content in the binder is shown in table 1:
table 1 verification of the prediction model for the moisture content in the binder
Model (model) | RMSECV/% | R2 value |
Moisture content of the adhesive | 0.0581 | 99.32 |
As can be seen from Table 1, R of the model was established2The value is close to 100, and the RMSECV value is close to 1, which shows that the quality of the established model is good and can be used for accurately predicting the concentration of an unknown sample.
Claims (4)
1. A binder moisture content monitoring method based on near infrared spectrum is characterized by comprising the following steps:
s1: adding water with different proportions into the adhesive with the same quality to prepare 30 modeling standard samples with the concentration in a gradient distribution manner;
s2: under the preset spectral resolution, performing near-infrared scanning on each modeling standard sample according to the preset scanning times to obtain an original near-infrared spectrum corresponding to each modeling standard sample;
s3: performing dimensionality reduction treatment on the original near infrared spectrum of each modeling standard sample by using a principal component analysis method to obtain a target near infrared spectrum corresponding to each standard sample;
s4: making target near infrared spectra of all modeling standard samples into a data set, constructing a quantitative model, and detecting the quantitative model by using a detection set to obtain a moisture content prediction model in the adhesive;
s5: and (4) determining the adhesive to be determined by utilizing a prediction model of the water content in the adhesive to obtain a water content determination result.
2. The method for monitoring the moisture content of an adhesive based on near infrared spectroscopy according to claim 1, wherein: the S4 includes the following steps:
s41: adopting a cross validation method to make target near infrared spectra of all modeling standard samples into data sets, wherein 5 data sets are used as inspection sets, and 25 data sets are used as test sets;
s42: and constructing the quantitative model, setting inspection parameters of the quantitative model, wherein the inspection parameters comprise iteration times, and inspecting the quantitative model by using the inspection set and the inspection parameters to obtain a prediction model of the moisture content in the adhesive.
3. The method for monitoring the moisture content of an adhesive based on near infrared spectroscopy according to claim 2, wherein: and in the step S4, the test set is used for verifying the prediction model of the moisture content in the adhesive, if the verification is passed, the step S42 is executed, and if the verification is not passed, the step S41 is returned.
4. The method for monitoring the moisture content of an adhesive based on near infrared spectroscopy according to claim 2, wherein: the S42 includes the following steps:
s421: inputting the test set into a prediction model of the moisture content in the adhesive, and respectively calculating a correlation coefficient and a root mean square error:
the calculation formula of the correlation coefficient is as follows:
the calculation formula of the root mean square error is as follows:
wherein, R is2For correlation coefficients, RMSECV is the root mean square error, M is the number of samples in the test set,C i is the actual value of the number of the ith sample,is a predicted value of the number of the ith sample,is the average of all the actual values,Differ i is the difference between the chemically measured value and the predicted value for the ith sample;
s422: and judging whether the prediction model of the moisture content in the adhesive passes the verification according to the correlation coefficient and the root mean square error, if so, executing S42, and if not, executing S41.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011531316.5A CN112649390A (en) | 2020-12-22 | 2020-12-22 | Adhesive moisture content monitoring method based on near infrared spectrum |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011531316.5A CN112649390A (en) | 2020-12-22 | 2020-12-22 | Adhesive moisture content monitoring method based on near infrared spectrum |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112649390A true CN112649390A (en) | 2021-04-13 |
Family
ID=75359276
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011531316.5A Pending CN112649390A (en) | 2020-12-22 | 2020-12-22 | Adhesive moisture content monitoring method based on near infrared spectrum |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112649390A (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018010352A1 (en) * | 2016-07-11 | 2018-01-18 | 上海创和亿电子科技发展有限公司 | Qualitative and quantitative combined method for constructing near infrared quantitative model |
CN110702635A (en) * | 2019-09-02 | 2020-01-17 | 内蒙合成化工研究所 | Method for online detection of high-energy adhesive component by near infrared spectrum |
CN111044483A (en) * | 2019-12-27 | 2020-04-21 | 武汉工程大学 | Method, system and medium for determining pigment in cream based on near infrared spectrum |
-
2020
- 2020-12-22 CN CN202011531316.5A patent/CN112649390A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018010352A1 (en) * | 2016-07-11 | 2018-01-18 | 上海创和亿电子科技发展有限公司 | Qualitative and quantitative combined method for constructing near infrared quantitative model |
CN110702635A (en) * | 2019-09-02 | 2020-01-17 | 内蒙合成化工研究所 | Method for online detection of high-energy adhesive component by near infrared spectrum |
CN111044483A (en) * | 2019-12-27 | 2020-04-21 | 武汉工程大学 | Method, system and medium for determining pigment in cream based on near infrared spectrum |
Non-Patent Citations (2)
Title |
---|
李丽洁 等: "《含氮化合物制备与表征实验》", 31 August 2015, 北京航空航天大学出版社, pages: 143 - 144 * |
高向阳: "《食品分析与检验》", 31 October 2006, 中国计量出版社, pages: 88 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104062257B (en) | A kind of based on the method for general flavone content near infrared ray solution | |
CN110687072B (en) | Calibration set and verification set selection and modeling method based on spectral similarity | |
CN107703097B (en) | Method for constructing model for rapidly predicting crude oil property by using near-infrared spectrometer | |
CN104062256B (en) | A kind of flexible measurement method based near infrared spectrum | |
CN105300923A (en) | Correction method of measuring point free temperature compensation model during process of online application of near infrared spectrum analyzer | |
CN108760647A (en) | A kind of wheat content of molds line detecting method based on Vis/NIR technology | |
CN104062258A (en) | Method for rapid determination of soluble solids in compound ass-hide glue pulp by near infrared spectroscopy | |
CN105334185A (en) | Spectrum projection discrimination-based near infrared model maintenance method | |
CN111272686B (en) | Hyperspectral detection method for iron grade of iron ore concentrate powder | |
CN102506731B (en) | Method for detecting reconstituted tobacco thickness in papermaking process by utilizing near infrared spectrums | |
CN115993344A (en) | Quality monitoring and analyzing system and method for near infrared spectrum analyzer | |
WO2020248961A1 (en) | Method for selecting spectral wavenumber without reference value | |
CN114611582B (en) | Method and system for analyzing substance concentration based on near infrared spectrum technology | |
CN109283153B (en) | Method for establishing quantitative analysis model of soy sauce | |
CN109540837B (en) | Method for rapidly detecting lignocellulose content of ramie leaves by near infrared | |
CN104316492A (en) | Method for near-infrared spectrum measurement of protein content in potato tuber | |
CN117269109B (en) | Method for detecting chloride ion content in concrete structure based on near infrared spectrum | |
CN111141809B (en) | Soil nutrient ion content detection method based on non-contact type conductivity signal | |
CN113655027A (en) | Method for rapidly detecting tannin content in plant by near infrared | |
CN109709060B (en) | Method for measuring asphalt softening point, penetration degree and mass loss | |
CN111896497A (en) | Spectral data correction method based on predicted value | |
CN106872398A (en) | A kind of HMX explosives moisture method for fast measuring | |
CN112649390A (en) | Adhesive moisture content monitoring method based on near infrared spectrum | |
CN116662751A (en) | Tobacco leaf moisture content detection method for removing abnormal samples based on principal component analysis and lever value method | |
CN105866065B (en) | Methenamine content analysis method in a kind of methenamine-acetum |
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 |