CN109085136B - Method for measuring content of oxide components in cement raw material by near-infrared diffuse reflection spectrum - Google Patents
Method for measuring content of oxide components in cement raw material by near-infrared diffuse reflection spectrum Download PDFInfo
- Publication number
- CN109085136B CN109085136B CN201810890983.9A CN201810890983A CN109085136B CN 109085136 B CN109085136 B CN 109085136B CN 201810890983 A CN201810890983 A CN 201810890983A CN 109085136 B CN109085136 B CN 109085136B
- Authority
- CN
- China
- Prior art keywords
- cement raw
- raw material
- diffuse reflection
- spectrum
- sample
- 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.)
- Expired - Fee Related
Links
- 239000004568 cement Substances 0.000 title claims abstract description 110
- 238000001228 spectrum Methods 0.000 title claims abstract description 76
- 238000000034 method Methods 0.000 title claims abstract description 74
- 239000002994 raw material Substances 0.000 title claims description 86
- 238000012795 verification Methods 0.000 claims abstract description 35
- 238000002790 cross-validation Methods 0.000 claims abstract description 18
- 235000012054 meals Nutrition 0.000 claims abstract description 9
- 238000001055 reflectance spectroscopy Methods 0.000 claims abstract description 7
- 238000012937 correction Methods 0.000 claims description 56
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 claims description 26
- PNEYBMLMFCGWSK-UHFFFAOYSA-N aluminium oxide Inorganic materials [O-2].[O-2].[O-2].[Al+3].[Al+3] PNEYBMLMFCGWSK-UHFFFAOYSA-N 0.000 claims description 25
- 229910052593 corundum Inorganic materials 0.000 claims description 24
- 229910001845 yogo sapphire Inorganic materials 0.000 claims description 24
- 230000003595 spectral effect Effects 0.000 claims description 21
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N silicon dioxide Inorganic materials O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 claims description 19
- 238000004876 x-ray fluorescence Methods 0.000 claims description 15
- 229910052681 coesite Inorganic materials 0.000 claims description 12
- 229910052906 cristobalite Inorganic materials 0.000 claims description 12
- 239000000377 silicon dioxide Substances 0.000 claims description 12
- 229910052682 stishovite Inorganic materials 0.000 claims description 12
- 229910052905 tridymite Inorganic materials 0.000 claims description 12
- 238000009499 grossing Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 5
- 238000000227 grinding Methods 0.000 claims description 4
- 238000003825 pressing Methods 0.000 claims description 4
- 238000002203 pretreatment Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 2
- 238000010200 validation analysis Methods 0.000 abstract description 7
- 238000000985 reflectance spectrum Methods 0.000 abstract 2
- 239000000523 sample Substances 0.000 description 64
- ODINCKMPIJJUCX-UHFFFAOYSA-N calcium oxide Inorganic materials [Ca]=O ODINCKMPIJJUCX-UHFFFAOYSA-N 0.000 description 24
- 239000000292 calcium oxide Substances 0.000 description 24
- LIVNPJMFVYWSIS-UHFFFAOYSA-N silicon monoxide Chemical compound [Si-]#[O+] LIVNPJMFVYWSIS-UHFFFAOYSA-N 0.000 description 12
- 238000004519 manufacturing process Methods 0.000 description 6
- 238000007781 pre-processing Methods 0.000 description 6
- 238000002329 infrared spectrum Methods 0.000 description 4
- 229910052594 sapphire Inorganic materials 0.000 description 4
- 239000010980 sapphire Substances 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 238000002835 absorbance Methods 0.000 description 2
- 238000000862 absorption spectrum Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000009614 chemical analysis method Methods 0.000 description 2
- 229910000530 Gallium indium arsenide Inorganic materials 0.000 description 1
- 235000019738 Limestone Nutrition 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- BRPQOXSCLDDYGP-UHFFFAOYSA-N calcium oxide Chemical compound [O-2].[Ca+2] BRPQOXSCLDDYGP-UHFFFAOYSA-N 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000004927 clay Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005281 excited state Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000005283 ground state Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- LIKBJVNGSGBSGK-UHFFFAOYSA-N iron(3+);oxygen(2-) Chemical compound [O-2].[O-2].[O-2].[Fe+3].[Fe+3] LIKBJVNGSGBSGK-UHFFFAOYSA-N 0.000 description 1
- 239000006028 limestone Substances 0.000 description 1
- 239000002075 main ingredient Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000007430 reference method Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 229910052814 silicon oxide Inorganic materials 0.000 description 1
- 239000002893 slag Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
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
- G01N21/359—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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
- G01N23/22—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by measuring secondary emission from the material
- G01N23/223—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by measuring secondary emission from the material by irradiating the sample with X-rays or gamma-rays and by measuring X-ray fluorescence
-
- 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
- G01N2021/3595—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using FTIR
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2201/00—Features of devices classified in G01N21/00
- G01N2201/12—Circuits of general importance; Signal processing
- G01N2201/129—Using chemometrical methods
Landscapes
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
本发明公开了一种近红外漫反射光谱测定水泥生料氧化物成分含量的方法，采用X射线荧光法测定采集的水泥生料样品的主要氧化物成分含量，得到样品各成分的标准；将全部水泥生料样品分为校正集和验证集，获得其近红外漫反射光谱；对近红外漫反射光谱进行平滑处理，采用协同间隔偏最小二乘法建立校正模型，确定样品各成分含量与近红外漫反射光谱的关系；使用验证集样品对校正模型进行外部验证，通过校正集相关系数、交叉验证均方根误差、验证集相关系数和预测均方根误差综合判断模型性能，分析预测值与真实值之间的相关性。
The invention discloses a method for measuring the content of oxide components of cement raw meal by near-infrared diffuse reflection spectroscopy. Cement raw meal samples are divided into calibration set and verification set, and the near-infrared diffuse reflectance spectrum is obtained; the near-infrared diffuse reflectance spectrum is smoothed, and the collaborative interval partial least squares method is used to establish a calibration model to determine the relationship between the content of each component in the sample and the near-infrared diffuse reflectance. The relationship between reflection spectra; externally verify the calibration model using the validation set samples, comprehensively judge the performance of the model through the calibration set correlation coefficient, cross-validation root mean square error, validation set correlation coefficient and prediction root mean square error, and analyze the predicted value and the true value correlation between.
Description
Technical Field
The invention relates to a method for measuring the content of oxide components in cement raw materials by near-infrared diffuse reflection spectroscopy.
Background
The cement is an indispensable basic material in modern economic construction, and the quality of the cement is closely related to the safety of human life and property. In the cement production process, the proportion of various raw materials (clay, limestone, steel slag and the like) is directly proportionedDetermine the quality of the cement. The cement is mainly composed of CaO and SiO2、Al2O3And Fe2O3Etc. and therefore, the industrial production needs to control the proportioning of the raw materials by detecting the content of the oxides in the cement raw meal to ensure the quality of the cement.
The chemical analysis method and the X-ray fluorescence method are inspection methods generally adopted in the cement industry, the chemical analysis method has complex procedures and long time consumption, the X-ray fluorescence method needs to be provided with special sample preparation equipment, the cost is high, the radioactivity is high, the health is damaged, and although the measurement speed is relatively high (30-60min), the timeliness of industrial control is difficult to meet. Along with the annual increase of the automation level of a cement production line, the production scale is gradually increased, and the two detection methods cannot timely reflect the change of the content of the components of the cement raw materials, so that the raw material proportion adjustment is delayed, and the cement quality fluctuation is large. Therefore, a rapid and effective method for on-line detection and analysis of cement raw materials is urgently needed in the cement industry.
Disclosure of Invention
The invention provides a method for measuring the content of oxide components in cement raw meal by using near-infrared diffuse reflection spectroscopy, aiming at solving the problems, and the invention can quickly measure the main components of the cement raw meal, especially the oxide components (including but not limited to CaO and SiO) by combining the near-infrared diffuse reflection spectroscopy analysis technology with the cooperative interval partial least square method2、Al2O3、Fe2O3) And the content provides data and theoretical basis for ensuring the quality of the cement.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for measuring the content of oxide components in cement raw materials by near-infrared diffuse reflection spectroscopy comprises the following steps:
measuring the content of main oxide components of raw materials in an acquired cement sample (for modeling) by adopting an X-ray fluorescence method to obtain the standard of each component of the sample;
dividing all cement raw material samples into a correction set and a verification set, and respectively obtaining near infrared diffuse reflection spectrums of the cement raw material samples by adopting a Fourier near infrared spectrometer;
smoothing the near-infrared diffuse reflection spectrum of the cement raw material, selecting the wavelength of the near-infrared diffuse reflection spectrum by adopting a cooperative interval partial least square method, establishing a correction model, and determining the relation between the content of each component of the sample and the near-infrared diffuse reflection spectrum;
performing external verification on the correction model by using a verification set sample, comprehensively judging the performance of the model through a correlation coefficient of the correction set, a cross verification root-mean-square error, a correlation coefficient of the verification set and a prediction root-mean-square error, and analyzing the correlation between a predicted value and a true value;
and judging whether the prediction effect of the model meets the requirement, if so, determining the content of the main oxide components of the cement raw material to be detected by using the correction model, and if not, correcting the parameters of the model, and verifying again until the requirement is met.
In the invention, the main components of the cement raw material or the main oxide components of the cement raw material refer to calcium oxide CaO and silicon oxide SiO2Aluminum oxide Al2O3And/or iron (III) oxide Fe2O3。
Further, the method for measuring the content of the main oxide components in all cement raw material samples by using an X-ray fluorescence method comprises the following specific steps:
(a) deeply grinding a powdery cement raw material sample;
(b) putting the cement raw material sample obtained in the step (a) into a mould to be pressed into a cake shape;
(c) and (c) placing the cake-shaped sample pressed in the step (b) into an X-ray fluorescence analyzer, measuring the content of the main oxide component in the cement raw material sample, and taking the obtained content as a standard sample.
The X-ray fluorescence method is used as a standard reference method to obtain the standard content of the main oxide components of the cement sample used for modeling, and standard data are provided for the subsequent modeling by adopting a cooperative interval partial least square method.
The standard content of each oxide component of a modeling sample must be obtained by adopting a collaborative interval partial least square method for modeling, the X-ray fluorescence method is equivalent to a standard chemical method, the collaborative interval partial least square method is adopted for modeling, a spectrum is screened, noise and irrelevant information are removed, and the model prediction performance is better.
Further, the number of samples in the calibration set is greater than or equal to the number of samples in the verification set.
Further, the process of obtaining near infrared diffuse reflection spectra of the verification set and the correction set by using the Fourier near infrared spectrometer comprises the steps of putting a corresponding cement raw material sample on a window sheet, compacting by using a pressing die, putting the window sheet on a diffuse reflection kit of the Fourier near infrared spectrometer, and collecting the near infrared spectrum of the cement raw material sample by using the Fourier near infrared spectrometer.
Further, each sample is repeatedly loaded and scanned for N times, N is more than 2, the average spectrum of the N times is taken as the obtained spectrum data, and the spectrum area range is 10000-4000cm-1Resolution of 4cm-1。
Further, a relation curve of the reflection absorbance and the wave number of near infrared light is recorded to obtain a near infrared diffuse reflection spectrum, the spectrum comprises the substance type and the concentration information of the sample, and a model is established by combining the content of main oxide components of all cement raw material samples (for modeling) measured by an X-ray fluorescence method through a chemometrics method for predicting the concentration information of the sample to be measured to obtain the corresponding spectrum area range of each component.
Furthermore, the CaO has a spectral region range of 10000--1、9400-8800cm-1And 4600-4000cm-1，SiO2The spectrum region range is 9400-9200cm-1、7000-6800cm-1And 4400--1，Fe2O3The spectral region range of (1) is 8200-7600cm-1、6400-5800cm-1And 4600-4000cm-1，Al2O3The spectral region range is 8800-8600cm-1、4600-4400cm-1And 4400--1。
Further, wavelength selection is carried out on the near-infrared diffuse reflection spectrum by adopting a collaborative interval partial least square method, and then a correction model is established, wherein the method comprises the following steps:
(a) processing the near-infrared diffuse reflection spectrum of the cement raw material by utilizing a Savitzky-Golay smoothing pretreatment method;
(b) the spectral region of the near-infrared diffuse reflection spectrum of the cement raw material is averagely divided into a plurality of parts, and a plurality of parts with the minimum cross validation root mean square are selected to establish a cooperative interval partial least square model.
Further, in the step (b), the spectral region of the near infrared diffuse reflection spectrum of the cement raw material is divided into 10 parts, 20 parts, 30 parts, 40 parts and 50 parts on average.
Further, the specific step of determining the accuracy of the correction set model includes:
establishing a correction set prediction model for the sample spectrum data of the correction set by using a cooperative interval partial least square method to obtain a correlation coefficient of the correction set and a cross validation root mean square error of the correction set;
and predicting the spectrum of the sample in the verification set by using the correction set prediction model to obtain the correlation coefficient and the prediction root mean square error of the verification set.
Further, there is a linear relationship between the predicted value and the true value of the model.
Compared with the prior art, the invention has the beneficial effects that:
the invention adopts near infrared diffuse reflection spectrum combined with cooperative interval partial least square method to rapidly measure the main oxide components (CaO, SiO) of cement raw meal2、Al2O3、Fe2O3) The content determination method has the advantages of rapidness, simplicity and convenience, and no need of pretreatment of samples, only needs about a few minutes (including sample loading and content prediction) for determining one sample, can meet the timeliness of industrial cement production, can increase the representativeness of a modeling sample by increasing the sample number of cement raw material samples in practical application, and improves the prediction performance of a correction set model.
The invention adopts Savitzky-Golay smoothing preprocessing method to process the spectrum data, and adopts cooperative interval partial least square method to establish the correction set prediction model, which can eliminate the noise and useless information in the near infrared diffuse reflection spectrum of the cement raw material sample, and the finally established correction model has more accurate measuring result and practical application value.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application.
FIG. 1 is a graph of the original near infrared spectrum of 93 samples of cement raw material in this example;
FIG. 2 is a cross-validation root mean square error RMSECV versus number of principal factors for the correction set prediction model of this embodiment; (a) is CaO, (B) is SiO2(C) is Fe2O3And (D) is Al2O3；
FIG. 3 is a near infrared diffuse reflection absorption spectrum plot of wavenumber selection when a calibration set model was established for 76 cement raw material samples in this example; (a) is CaO, (B) is SiO2(C) is Fe2O3And (D) is Al2O3；
FIG. 4 is a correlation graph of predicted values and true values of 76 cement raw material samples in the calibration set in this example; (a) is CaO, (B) is SiO2(C) is Fe2O3And (D) is Al2O3；
FIG. 5 is a correlation graph of the predicted values and the true values of 17 cement raw material samples in the validation set of this example; (a) is CaO, (B) is SiO2(C) is Fe2O3And (D) is Al2O3；
Fig. 6 is a detailed process diagram of the present embodiment.
The specific implementation mode is as follows:
the invention is further described with reference to the following figures and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
In the present invention, terms such as "upper", "lower", "left", "right", "front", "rear", "vertical", "horizontal", "side", "bottom", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only terms of relationships determined for convenience of describing structural relationships of the parts or elements of the present invention, and are not intended to refer to any parts or elements of the present invention, and are not to be construed as limiting the present invention.
In the present invention, terms such as "fixedly connected", "connected", and the like are to be understood in a broad sense, and mean either a fixed connection or an integrally connected or detachable connection; may be directly connected or indirectly connected through an intermediate. The specific meanings of the above terms in the present invention can be determined according to specific situations by persons skilled in the relevant scientific or technical field, and are not to be construed as limiting the present invention.
As shown in FIG. 6, a near infrared diffuse reflection spectrum combined with a collaborative interval partial least square method for rapidly determining the main components (CaO, SiO) of cement raw meal2、Al2O3、Fe2O3) The method comprises the following steps:
(1) collecting a cement raw material sample;
(2) the main components (CaO, SiO) of all cement raw material samples are determined by adopting an X-ray fluorescence method2、Al2O3、Fe2O3) Content (c);
(3) dividing all cement raw material samples into a correction set and a verification set, and respectively obtaining near infrared diffuse reflection spectrums of the cement raw material samples by adopting a Fourier near infrared spectrometer;
(4) preprocessing the near-infrared diffuse reflection spectrum of the cement raw material by selecting a Savitzky-Golay smoothing preprocessing method; selecting the wavelength of the near-infrared diffuse reflection spectrum by adopting a cooperative interval partial least square method, and further establishing a correction model;
(5) performing external verification on the correction model by using a verification set sample, judging the performance of the model by using 4 parameter values of a correlation coefficient R of the correction set, a cross verification root mean square error RMSECV, a correlation coefficient Q of the verification set and a prediction root mean square error RMSEP, and analyzing the correlation between a predicted value and a true value;
(6) judging whether the model prediction effect meets the requirements, if so, performing (7), otherwise, correcting the model parameters, and re-verifying;
(7) determining the main components (CaO, SiO) of cement raw meal to be measured by using a calibration model2、Al2O3、Fe2O3) And (4) content.
The X-ray fluorescence method for measuring the main component content of all cement raw materials in the step (2) comprises the following steps:
(a) deeply grinding a powdery cement raw material sample;
(b) putting 100g of the cement raw material sample obtained in the step (a) into a mould to be pressed into a cake shape;
(c) putting the cake-shaped sample prepared in the step (b) into an X-ray fluorescence analyzer, and measuring the main components (CaO, SiO) in the cement raw material sample2、Al2O3、Fe2O3) Content (c);
the method for collecting the near-infrared diffuse reflection spectrum in the step (3) comprises the following steps:
(a) taking a cement raw material sample, putting the sample on a sapphire window sheet, compacting the sample by a pressing die, putting the sapphire window sheet on a diffuse reflection kit of a Fourier near-infrared spectrometer, and collecting the near-infrared spectrum of the cement raw material sample by using the Fourier near-infrared spectrometer: each sample is repeatedly loaded and scanned for 3 times, the average spectrum of 3 times is taken as the obtained spectrum data, and the spectrum area range is 10000-4000cm-1Resolution of 4cm-1And the number of scanning times is 64.
(b) The number of cement raw material samples is 93 parts, wherein 76 parts of spectral data are used for modeling of a correction set, and the rest 17 parts of spectral data of the samples are used for model inspection as a verification set.
The step (4) of selecting the wavelength of the near-infrared diffuse reflection spectrum by adopting a collaborative interval partial least square method so as to establish a correction model, comprising the following steps of:
(a) selecting a Savitzky-Golay smoothing pretreatment method to treat the near-infrared diffuse reflection spectrum of the cement raw material;
(b) evenly dividing the spectrum region of the near-infrared diffuse reflection spectrum of the cement raw material into 10 parts, 20 parts, 30 parts, 40 parts and 50 parts, and establishing a cooperative interval partial least square model by selecting 3 parts with the best combination effect (the minimum cross validation root mean square RMSECV);
the specific steps for determining the accuracy of the correction set model in step (5) are as follows:
(a) establishing a correction set prediction model for 76 sample spectral data of a correction set by using a cooperative interval partial least square method, finding that a good linear relation exists between a predicted value and a true value of the model, and obtaining a correlation coefficient R of the correction set and a cross validation root mean square error RMSECV of the correction set;
(b) and predicting the spectra of 17 samples in the verification set by using a correction set prediction model to obtain a correlation coefficient Q of the verification set and a prediction root mean square error RMSEP.
Note that the numbers are selected from the data in this embodiment, and the specific numbers may be changed or replaced according to specific situations in other embodiments.
The principle of the method or the information needing attention is as follows:
when a sample is irradiated by a near-infrared light source, molecules absorb radiation of certain frequencies to generate molecular vibration and transition of a rotation energy level from a ground state to an excited state, so that the reflected light intensity corresponding to the absorption areas is weakened; and recording a relation curve of the reflection absorbance and the wave number of the near infrared light to obtain a near infrared diffuse reflection spectrum, wherein the spectrum contains the species and the concentration information of the substances in the sample, and establishing a model for predicting the concentration information of the sample to be measured by a chemometrics method.
The method comprises the steps of measuring the content of main components of the cement raw material through a near-infrared diffuse reflection absorption spectrum of a cement raw material sample, increasing the number of samples of a correction set sample, expanding the range of data, and improving the prediction performance of a correction model.
The source of the calibration set cement raw material sample should contain all possible later determined sample types as much as possible, and in practical application, the calibration model established by the invention covers cement raw material samples of different raw material producing areas so as to ensure that the calibration set contains all possible later determined samples.
The measured near infrared diffuse reflection spectrum data of the cement raw material sample also contains other useless information and noise besides target information related to the content of main components, so that a proper spectrum preprocessing method is needed to eliminate the noise, and a proper fitting method is used to screen the spectrum to screen out the useless information.
The method adopts a Savitzky-Golay smoothing pretreatment method to carry out pretreatment on the near infrared diffuse reflection spectrum of the cement raw material, adopts a cooperative interval partial least square method to averagely divide the spectrum area range into 10 parts, 20 parts, 30 parts, 40 parts and 50 parts, selects 3 parts with the best combination effect (the minimum cross validation root mean square RMSECV) to establish a correction prediction model, and determines that the spectrum area range of CaO is 10000--1、9400-8800cm-1And 4600-4000cm-1，SiO2The spectrum region range is 9400-9200cm-1、7000-6800cm-1And 4400--1，Fe2O3The spectral region range of (1) is 8200-7600cm-1、6400-5800cm-1And 4600-4000cm-1，Al2O3The spectral region range is 8800-8600cm-1、4600-4400cm-1And 4400--1。
When a collaborative interval partial least square method is adopted for modeling, the selection of the optimal main factor number is very important, if the main factor number is too small, useful spectrum information can be lost, if the main factor number is too large, an overfitting phenomenon can occur, the optimal main factor number is selected through cross validation of root mean square error RMSECV, and finally the main factor number of CaO is determined to be 9, and SiO is determined to be2The number of major factors of (1) is 8, Fe2O3Has a main factor of 8, Al2O3The main factor of (A) is9。
Specific application examples are described below:
the apparatus and materials used in the examples were as follows:
a fourier near infrared spectrometer (MB3600, ABB, switzerland) equipped with a high sensitivity InGaAs detector, a diffuse reflection probe, a solid sample test kit, a fiber optic conversion assembly and online process monitoring software.
Samples of cement raw materials (supplied by Shandong Qufu Mizhong cement works).
The invention is described in detail below with reference to the figures and specific embodiments.
Example 1
This example describes a method for rapidly determining the main components (CaO, SiO) of cement raw meal by combining near-infrared diffuse reflectance spectroscopy with a collaborative interval partial least squares method2、Al2O3、Fe2O3) A method of content comprising the steps of:
(1) collecting a cement raw material sample;
collecting a powdery cement raw material sample on a production line of a middle-connected cement plant of Shandong Qufuu through an automatic sampler of a material taking port;
(2) the main components (CaO, SiO) of all cement raw material samples are determined by adopting an X-ray fluorescence method2、Al2O3、Fe2O3) Content, providing standard data for subsequent modeling by adopting a cooperative interval partial least square method;
deeply grinding a powdery cement raw material sample; putting 100g of ground cement raw material sample into a mould to be pressed into a cake shape; putting the pressed cake sample into an X-ray fluorescence analyzer, and measuring the main components (CaO, SiO) in the cement raw material sample2、Al2O3、Fe2O3) And (4) content.
(3) Dividing all cement raw material samples into a correction set and a verification set, and respectively obtaining near infrared diffuse reflection spectrums of the cement raw material samples by adopting a Fourier near infrared spectrometer;
93 parts of cement raw material samples, wherein 76 parts of spectral data are used for modeling of a correction set, and the rest 17 parts of sample spectral data are used for model inspection as a verification set;
taking a cement raw material sample, putting the sample on a sapphire window sheet, compacting the sample by a pressing die, putting the sapphire window sheet on a diffuse reflection kit of a Fourier near-infrared spectrometer, and collecting the near-infrared spectrum of the cement raw material sample by using the Fourier near-infrared spectrometer: each sample is repeatedly loaded and scanned for 3 times, the average spectrum of 3 times is taken as the obtained spectrum data, and the spectrum area range is 10000-4000cm-1Resolution of 4cm-1And the number of scanning times is 64.
The near infrared diffuse reflection spectrum of 93 samples of cement raw materials is shown in FIG. 1.
(4) Preprocessing the near-infrared diffuse reflection spectrum of the cement raw material by selecting a Savitzky-Golay smoothing preprocessing method; selecting the wavelength of the near-infrared diffuse reflection spectrum by adopting a cooperative interval partial least square method, and further establishing a correction model;
averagely dividing the spectral region of the near-infrared diffuse reflection spectrum of the cement raw material into 10 parts, 20 parts, 30 parts, 40 parts and 50 parts by adopting a cooperative interval partial least square method, and establishing a cooperative interval partial least square model by selecting 3 parts with the best combination effect (the minimum cross validation root mean square RMSECV);
the relationship between the number of main factors and the cross-validation root mean square error RMSECV is shown in FIG. 2, the number of main factors of CaO is 9, and SiO2The number of main factors of (1) is 8, Fe2O3The number of main factors of (1) is 8, Al2O3The number of main factors of (1) is 9; the spectral region selection is shown in FIG. 3, and the spectral region range of CaO is 10000-9400cm-1、9400-8800cm-1And 4600-4000cm-1，SiO2The spectrum region range is 9400-9200cm-1、7000-6800cm-1And 4400--1，Fe2O3The spectral region range of (1) is 8200-7600cm-1、6400-5800cm-1And 4600-4000cm-1，Al2O3The spectral region range is 8800-8600cm-1、4600-4400cm-1And 4400--1。
(5) Performing external verification on the correction model by using a verification set sample, judging the performance of the model by using 4 parameter values of a correlation coefficient R of the correction set, a cross verification root mean square error RMSECV, a correlation coefficient Q of the verification set and a prediction root mean square error RMSEP, and analyzing the correlation between a predicted value and a true value;
establishing a correction set prediction model for 76 sample spectral data of the correction set to obtain a correlation coefficient R and a cross validation root mean square error RMSECV of the correction set, wherein the result is shown in FIG. 4; the spectra of 17 samples in the verification set are predicted by using the correction set prediction model, and the correlation coefficient Q and the prediction root mean square error RMSEP of the verification set are obtained, and the result is shown in FIG. 5.
The correlation coefficient R of a correction set of CaO is 0.8203, the cross validation root mean square error RMSECV is 0.2689%, the correlation coefficient Q of the validation set is 0.9525, the prediction root mean square error RMSEP is 0.1878%, the average deviation is 0.14%, and the maximum deviation is 0.39%; SiO 22The correlation coefficient R of the correction set is 0.8857, the cross validation root mean square error RMSECV is 0.2383%, the correlation coefficient Q of the validation set is 0.9471, the prediction root mean square error RMSEP is 0.1737%, the average deviation is 0.13%, and the maximum deviation is 0.44%; al (Al)2O3The correlation coefficient R of the correction set of (1) is 0.9309, the cross-validation root mean square error RMSECV is 0.0808%, the correlation coefficient Q of the validation set is 0.9449, the predicted root mean square error RMSEP is 0.0932%, the average deviation is 0.07%, and the maximum deviation is 0.18%. Fe2O3The correlation coefficient R of the correction set is 0.6951, the cross validation root mean square error RMSECV is 0.0447%, the correlation coefficient Q of the validation set is 0.7967, the predicted root mean square error RMSEP is 0.0344%, the average deviation is 0.03%, and the maximum deviation is 0.09%.
(6) Judging whether the model prediction effect meets the requirements, if so, performing (7), otherwise, correcting the model parameters, and re-verifying;
(7) determining the main components (CaO, SiO) of cement raw meal to be measured by using a calibration model2、Al2O3、Fe2O3) And (4) content.
The main parameters of the prediction model of the main component content of the cement raw material sample are shown in the table 1:
TABLE 1 Cement raw material sample principal component content prediction model
| Name of ingredient | Number of major factors | R | RMSECV(％) | Q | RMSEP(％) |
| |
9 | 0.8203 | 0.2689 | 0.9525 | 0.1878 |
| |
8 | 0.8857 | 0.2383 | 0.9471 | 0.1737 |
| Fe2O3 | 8 | 0.6951 | 0.0447 | 0.7967 | 0.0344 |
| Al2O3 | 9 | 0.9338 | 0.0790 | 0.9360 | 0.0996 |
The absolute error of the prediction of the main component content of the cement raw material sample is shown in Table 2.
TABLE 2 Absolute error of prediction of main ingredient content of cement raw material sample
According to the detection method for rapidly determining the content of the main components of the cement raw material by combining the near-infrared diffuse reflection spectrum with the collaborative interval partial least square method, the absolute error of the prediction model meets the production requirements of the cement industry, and the established model has good prediction performance and can rapidly and accurately detect the content of the main components of the cement raw material.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (2)
1. A method for measuring the content of oxide components in raw cement by near-infrared diffuse reflection spectroscopy is characterized in that: the method comprises the following steps:
the method comprises the following steps of (A) measuring the content of main oxide components in all cement raw materials by using an X-ray fluorescence method, wherein the method comprises the following specific steps: (a) deeply grinding a powdery cement raw material sample; (b) putting the cement raw material sample obtained in the step (a) into a mould to be pressed into a cake shape; (c) placing the cake-shaped sample pressed in the step (b) into an X-ray fluorescence analyzer, measuring the content of main oxide components in the cement raw material sample, and taking the obtained content as a standard sample;
dividing all cement raw material samples into a correction set and a verification set, respectively obtaining near infrared diffuse reflection spectrums of the cement raw material samples by adopting a Fourier near infrared spectrometer, and determining the relation between each component of the samples and the near infrared diffuse reflection spectrums;
the process of obtaining the near-infrared diffuse reflection spectrum of the verification set and the correction set by the Fourier near-infrared spectrometer comprises the steps of putting a corresponding cement raw material sample on a window, compacting by a pressing die, putting the window on a diffuse reflection kit of the Fourier near-infrared spectrometer, and collecting the near-infrared diffuse reflection spectrum of the cement raw material sample by the Fourier near-infrared spectrometer; each sample is repeatedly loaded and scanned for N times, N is more than 2, the average spectrum of the N times is taken as the obtained spectrum data, and the spectrum range is 10000-4000cm-1Resolution of 4cm-1；
(III) smoothing the near-infrared diffuse reflection spectrum of the cement raw material, selecting the wavelength of the near-infrared diffuse reflection spectrum by adopting a cooperative interval partial least square method, and further establishing a correction model, wherein the method specifically comprises the following steps:
(a) processing the near-infrared diffuse reflection spectrum of the cement raw material by utilizing a Savitzky-Golay smoothing pretreatment method;
(b) evenly dividing the spectrum region of the near-infrared diffuse reflection spectrum of the cement raw material into a plurality of parts, and selecting a plurality of parts with the minimum cross validation root mean square to establish a cooperative interval partial least square model;
in the adoption ofWhen modeling is carried out by the collaborative interval partial least square method, if the number of main factors is too small, useful spectrum information is lost, if the number of main factors is too large, an overfitting phenomenon occurs, the optimal number of main factors is selected by cross validation of root mean square error RMSECV, and finally the number of main factors of CaO is determined to be 9, and SiO is determined2The number of major factors of (1) is 8, Fe2O3Has a main factor of 8, Al2O3The number of main factors of (1) is 9; the CaO spectral region range is 10000-9400cm-1、9400-8800cm-1And 4600-4000cm-1，SiO2The spectrum region range is 9400-9200cm-1、7000-6800cm-1And 4400--1，Fe2O3The spectral region range of (1) is 8200-7600cm-1、6400-5800cm-1And 4600-4000cm-1，Al2O3The spectral region range is 8800-8600cm-1、4600-4400cm-1And 4400--1；
And (IV) carrying out external verification on the correction model by using a verification set sample, comprehensively judging the performance of the model by using a correlation coefficient of the correction set, a cross verification root-mean-square error, a correlation coefficient of the verification set and a prediction root-mean-square error, and analyzing the correlation between a predicted value and a true value, wherein the method specifically comprises the following steps:
establishing a correction set prediction model for the sample spectrum data of the correction set by using a cooperative interval partial least square method to obtain a correlation coefficient of the correction set and a cross validation root mean square error;
predicting the spectrum of the sample in the verification set by using a correction set prediction model to obtain a correlation coefficient and a prediction root mean square error of the verification set;
a linear relation exists between the predicted value and the true value of the model;
and (V) judging whether the model prediction effect meets the requirement, if so, determining the main oxide components of the cement raw material to be detected by using the correction model, and if not, correcting the model parameters and verifying again until the requirement is met.
2. The method for measuring the content of the oxide components in the cement raw meal by using the near-infrared diffuse reflection spectrum as claimed in claim 1, which is characterized in that: the number of samples in the correction set is more than or equal to that in the verification set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810890983.9A CN109085136B (en) | 2018-08-07 | 2018-08-07 | Method for measuring content of oxide components in cement raw material by near-infrared diffuse reflection spectrum |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810890983.9A CN109085136B (en) | 2018-08-07 | 2018-08-07 | Method for measuring content of oxide components in cement raw material by near-infrared diffuse reflection spectrum |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109085136A CN109085136A (en) | 2018-12-25 |
| CN109085136B true CN109085136B (en) | 2021-02-23 |
Family
ID=64834177
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810890983.9A Expired - Fee Related CN109085136B (en) | 2018-08-07 | 2018-08-07 | Method for measuring content of oxide components in cement raw material by near-infrared diffuse reflection spectrum |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109085136B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110806400B (en) * | 2019-09-18 | 2022-01-14 | 天津农学院 | Correction method for reducing influence of soil moisture content on polycyclic aromatic hydrocarbon fluorescence working curve |
| CN111272696A (en) * | 2020-03-24 | 2020-06-12 | 山东大学 | A method for rapid detection of impurity essence in Pu'er tea |
| CN111781151A (en) * | 2020-07-06 | 2020-10-16 | 济南大学 | A method and system for rapidly detecting the content of cement raw meal components |
| CN111751320A (en) * | 2020-07-06 | 2020-10-09 | 济南大学 | Detection method and system of cement raw meal component content based on wave band selection |
| CN111751319A (en) * | 2020-07-06 | 2020-10-09 | 济南大学 | Method and system for rapid detection of component content of cement raw meal based on near-infrared spectroscopy |
| CN113419050A (en) * | 2021-07-20 | 2021-09-21 | 山东恒拓科技发展有限公司 | Method and device for soft measurement of cement raw material components |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2259766B (en) * | 1991-09-17 | 1995-08-23 | Schlumberger Services Petrol | A method to determine the phase composition of cement |
| JP4557483B2 (en) * | 2000-01-31 | 2010-10-06 | ダブリュー・アール・グレイス・アンド・カンパニー−コネチカット | Test method for hydratable cementitious composition |
| CN106198446A (en) * | 2016-06-22 | 2016-12-07 | 中国热带农业科学院热带作物品种资源研究所 | A method for the rapid determination of L-borneol content in Ainaxiang leaf powder by near-infrared spectroscopy |
| CN107589089A (en) * | 2017-10-30 | 2018-01-16 | 中国科学院合肥物质科学研究院 | The detecting system and its control method of raw ingredients of cement |
-
2018
- 2018-08-07 CN CN201810890983.9A patent/CN109085136B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN109085136A (en) | 2018-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109085136B (en) | Method for measuring content of oxide components in cement raw material by near-infrared diffuse reflection spectrum | |
| KR101498096B1 (en) | Apparatus and method for discriminating of geographical origin of agricutural products using hyperspectral imaging | |
| CN101221125A (en) | Method of Measuring Characteristic Parameters of Eutrophic Water Body Using Spectral Technology | |
| CN109540838B (en) | Method for rapidly detecting acidity in fermented milk | |
| CN104062256A (en) | Soft measurement method based on near infrared spectroscopy | |
| CN106770058A (en) | The quick special purpose device and its application method of the soil nitrate-N based on infrared spectrum | |
| CN104132720B (en) | Near infrared spectroscopy quickly detects the tablet weight of medicinal tablet | |
| CN103900990B (en) | The method of plutonium and nitric acid content in Rapid Simultaneous Determination organic facies | |
| CN108760647A (en) | A kind of wheat content of molds line detecting method based on Vis/NIR technology | |
| CN104596979A (en) | Method for measuring cellulose of reconstituted tobacco by virtue of near infrared reflectance spectroscopy technique | |
| CN104596975A (en) | Method for measuring lignin of reconstituted tobacco by paper-making process by virtue of near infrared reflectance spectroscopy technique | |
| CN103792205B (en) | The sensitive quick nondestructive analysis of the high flux near-infrared of tablet impurity and tensile strength | |
| CN104596976A (en) | Method for determining protein of paper-making reconstituted tobacco through ear infrared reflectance spectroscopy technique | |
| CN109374548A (en) | A kind of method that utilizes near-infrared rapid determination of nutrient composition in rice | |
| CN103308475A (en) | A method for simultaneous measurement of Pu(IV) and HNO3 content in post-treatment liquid | |
| CN111521580A (en) | A method for detecting freshness of fish fillets based on portable near-infrared spectrometer | |
| CN101487796A (en) | Method for measuring melamine content in solid example | |
| CN104596982A (en) | Method for measuring pectin of paper-making reconstituted tobacco by near-infrared diffuse reflection spectrum technology | |
| CN109799224A (en) | Quickly detect the method and application of protein concentration in Chinese medicine extract | |
| CN110231306A (en) | A kind of method of lossless, the quick odd sub- seed protein content of measurement | |
| CN111751320A (en) | Detection method and system of cement raw meal component content based on wave band selection | |
| CN110210005A (en) | A kind of spectrum wave number selection method of no reference value | |
| CN102262055B (en) | A method for measuring the residual amount of acrylamide monomer in polyacrylamide substances | |
| CN104568828A (en) | Method for determining tensile strength of reproduced tobacco leaves of papermaking method by near-infrared diffuse reflection spectrum | |
| CN109030410B (en) | Construction method of royal jelly near-infrared quantitative correction model and royal jelly detection method |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210223 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |