CN111044503A - Coal quality measurement method based on information fusion of laser-induced breakdown spectroscopy and near infrared spectroscopy - Google Patents
Coal quality measurement method based on information fusion of laser-induced breakdown spectroscopy and near infrared spectroscopy Download PDFInfo
- Publication number
- CN111044503A CN111044503A CN201911290420.7A CN201911290420A CN111044503A CN 111044503 A CN111044503 A CN 111044503A CN 201911290420 A CN201911290420 A CN 201911290420A CN 111044503 A CN111044503 A CN 111044503A
- Authority
- CN
- China
- Prior art keywords
- data
- libs
- nir
- coal quality
- quantitative analysis
- 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
- 239000003245 coal Substances 0.000 title claims abstract description 105
- 238000002536 laser-induced breakdown spectroscopy Methods 0.000 title claims abstract description 105
- 238000004497 NIR spectroscopy Methods 0.000 title claims abstract description 103
- 238000000691 measurement method Methods 0.000 title claims abstract description 13
- 230000004927 fusion Effects 0.000 title claims abstract description 11
- 238000004445 quantitative analysis Methods 0.000 claims abstract description 48
- 238000000034 method Methods 0.000 claims abstract description 30
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims abstract description 21
- 229910052799 carbon Inorganic materials 0.000 claims abstract description 21
- 230000003595 spectral effect Effects 0.000 claims abstract description 21
- 238000001514 detection method Methods 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims abstract description 5
- 238000010606 normalization Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 14
- 238000010438 heat treatment Methods 0.000 claims description 11
- 238000012795 verification Methods 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000000491 multivariate analysis Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 2
- 238000012706 support-vector machine Methods 0.000 claims description 2
- 238000010200 validation analysis Methods 0.000 claims 1
- 238000010183 spectrum analysis Methods 0.000 abstract description 4
- 230000008901 benefit Effects 0.000 abstract description 3
- 230000008878 coupling Effects 0.000 abstract description 2
- 238000010168 coupling process Methods 0.000 abstract description 2
- 238000005859 coupling reaction Methods 0.000 abstract description 2
- 230000005855 radiation Effects 0.000 abstract description 2
- 238000002790 cross-validation Methods 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005251 gamma ray Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000003904 radioactive pollution Methods 0.000 description 1
- 239000003039 volatile agent Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/71—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light thermally excited
- G01N21/718—Laser microanalysis, i.e. with formation of sample plasma
-
- 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
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
-
- 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
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/22—Fuels, explosives
- G01N33/222—Solid fuels, e.g. coal
-
- 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
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Abstract
The invention relates to a coal quality measurement method based on information fusion of laser-induced breakdown spectroscopy and near infrared spectroscopy, which utilizes the advantages that both LIBS and NIR detection processes have no need or only need of simple sample pretreatment, collects LIBS data containing coal sample element information and NIR data containing coal sample molecular information at the same time, and then establishes a quantitative analysis model of volatile components and calorific value by utilizing LIBS and NIR spectral coupling data based on the characteristics that the volatile components and the calorific value are related to elements and molecules; based on the characteristic that ash content mainly consists of inorganic elements, a quantitative analysis model of the ash content is established by utilizing LIBS data; establishing a quantitative analysis model of the moisture by utilizing NIR data based on the characteristic that the moisture can strongly absorb near infrared radiation; finally, the content of the fixed carbon is calculated based on the contents of the volatile components, the ash content and the moisture content obtained by the spectral analysis.
Description
Technical Field
The invention relates to the field of coal quality detection and analysis, in particular to a coal quality measuring method based on information fusion of laser-induced breakdown spectroscopy and near infrared spectroscopy.
Background
The rapid and accurate measurement of the coal quality is a basic guarantee for promoting the clean and efficient utilization level of the coal, and the wide application of the coal quality is limited by radioactive pollution, high selling price and maintenance cost of the existing coal quality online measurement technology based on the gamma ray/neutron activation principle in the market at present. Because of the advantages of safety, simple operation, no need of pretreatment and nondestructive detection of samples, the application of Laser-Induced Breakdown Spectroscopy (LIBS) and Diffuse-reflected Near infrared Spectroscopy (NIR) in the field of coal detection is widely concerned and researched.
The moisture content of coal obtained by LIBS analysis is less accurate, NIR spectroscopy is more difficult to analyze elements and ash mainly composed of inorganic minerals, and the absorption band of NIR spectroscopy has overlapping and shifting phenomena affecting quantitative analysis. Coal quality has different relativity with elements and molecular structures, such as the correlation of volatile components and calorific value with the elements and the molecular structures, and the accuracy of single spectrum analysis is lower.
Disclosure of Invention
Aiming at the technical problems in the prior art, the invention mainly aims to provide a coal quality measuring method based on information fusion of laser-induced breakdown spectroscopy and near infrared spectroscopy.
In order to achieve the purpose, the invention adopts the following technical scheme:
a coal quality measurement method based on information fusion of laser-induced breakdown spectroscopy and near infrared spectroscopy comprises the following steps:
step S1, collecting coal samples with known coal quality indexes, carrying out Laser Induced Breakdown Spectroscopy (LIBS) detection and near infrared spectroscopy (NIR) detection on the coal samples, collecting LIBS and NIR data, and dividing the coal samples into verification sets and calibration sets;
step S2, preprocessing the LIBS and the NIR data to reduce interference of spectral noise on subsequent quantitative analysis;
step S3, carrying out normalization processing on the preprocessed LIBS and NIR data, respectively establishing primary quantitative analysis models of heating value, volatile component, ash content and moisture by utilizing the LIBS and the NIR data of the calibration set after the normalization processing based on a multivariate analysis method, and screening out the optimal input data for establishing the quantitative analysis models;
step S4, establishing a quantitative analysis model of each coal quality according to the optimal input data; wherein the optimal input data refers to LIBS data with high correlation coefficient, NIR data and LIBS combined NIR data;
s5, predicting the calorific value, the volatile component, the ash content and the moisture content of the coal quality indexes of the coal sample of the verification set by using the established quantitative analysis model of each coal quality, and comparing the prediction results of the quantitative analysis model established by different spectral data on each coal quality of the verification set to obtain the optimal quantitative analysis model of the corresponding coal quality indexes;
and step S6, calculating the fixed carbon content according to the prediction result of the optimal quantitative analysis model corresponding to the corresponding coal quality index.
Further, in step S1, the acquiring LIBS and NIR data refers to acquiring multiple sets of LIBS and NIR data for each coal sample, and then averaging the multiple sets of LIBS and NIR data respectively.
Further, in the preprocessing step, a channel normalization preprocessing method is adopted for the LIBS data; and (3) adopting a standard normal transformation preprocessing method for the NIR data.
Further, in step S3, the normalization process is a decimal scaling normalization:
x'＝x/10p
wherein x is original data, x 'is normalized data, and p satisfies max (| x' |) < 1.
Further, in step S3, the screening of the optimal input data for establishing the quantitative analysis model includes:
and selecting LIBS and NIR spectral band data with high correlation coefficients as input data of the quantitative analysis model of each coal quality by taking the LIBS and the NIR data of the calibration set and the correlation coefficients of the PLS latent variables as evaluation indexes.
In step S3, the multivariate analysis method is a quantitative analysis method capable of processing a high-dimensional data matrix, such as partial least squares method or support vector machine regression.
Further, in step S5, the quantitative analysis model predicts the performance of each coal quality indicator of the verification coal sample by using the predicted root mean square error, the average absolute error, and the average relative error as evaluation indicators.
Furthermore, in the optimal quantitative analysis model, LIBS is combined with NIR data for analyzing the calorific value of the coal quality index, LIBS is combined with NIR data for analyzing the volatile component of the coal quality index, LIBS data is used for analyzing the ash content of the coal quality index, and NIR data is used for analyzing the moisture content of the coal quality index.
Further, the fixed carbon content is calculated by the following formula:
FCad＝100％-(Mad+Aad+Vad)
therein, FCadDenotes the fixed carbon content, MadDenotes the moisture content, AadDenotes the ash content, VadRepresents the volatile content.
A coal quality analysis and measurement model based on information fusion of laser-induced breakdown spectroscopy and near infrared spectroscopy comprises:
the input module comprises a heating value input submodule, a volatile component input submodule, an ash content input submodule and a moisture input submodule; the system comprises a heating value input submodule, a volatile component input submodule, an ash content input submodule and a moisture input submodule, wherein the heating value input submodule is used for inputting LIBS & NIR data, the volatile component input submodule is used for inputting the LIBS & NIR data, the ash content input submodule is used for inputting the LIBS data, and the moisture content input submodule is used for inputting the NIR data;
and the processing module is connected with the input module, obtains the calorific value, the volatile component, the ash content and the moisture content of the coal quality index according to a multivariate analysis method based on the received LIBS data, the NIR data and the LIBS & NIR data, and calculates the fixed carbon content of the coal quality index according to the obtained volatile component, the ash content and the moisture content of the coal quality index.
And the output module is connected with the processing module and outputs the coal quality index heat productivity, volatile components, ash content, moisture content and fixed carbon content obtained by the model.
Compared with the prior art, the invention has at least the following beneficial effects:
aiming at the characteristic that different coal quality indexes have different correlations with elements and molecules in coal, the LIBS and NIR detection process has the advantage of no need or only simple sample pretreatment, LIBS data containing coal sample element information and NIR data containing coal sample molecule information are collected simultaneously, and then a quantitative analysis model of the volatile components and the calorific value is established by utilizing LIBS and NIR spectrum coupling data based on the characteristic that the volatile components and the calorific value are both related to the elements and the molecules; based on the characteristics that ash content mainly consists of inorganic elements and an LIBS spectrum contains a large number of inorganic element emission spectral lines, a quantitative analysis model of the ash content is established by utilizing LIBS data; establishing a quantitative analysis model of the moisture by utilizing NIR data based on the characteristic that the moisture can strongly absorb near infrared radiation; finally, the content of the fixed carbon is calculated based on the contents of the volatile components, the ash content and the moisture content obtained by the spectral analysis.
Drawings
FIG. 1 is a schematic flow chart of a coal quality measuring method according to the present invention.
FIG. 2 is a graph comparing the results of analyzing volatile contents using LIBS, NIR and LIBS & NIR data in examples of the present invention.
FIG. 3 is a graph comparing heating value results analyzed using LIBS, NIR and LIBS & NIR data in an embodiment of the invention.
FIG. 4 is a graph comparing the results of analyzing ash content using LIBS, NIR and LIBS & NIR data in examples of the present invention.
FIG. 5 is a comparison graph of moisture content analysis using LIBS, NIR and LIBS & NIR data in an example of the invention.
FIG. 6 is a graph of a fit of fixed carbon content values calculated in an example of the present invention to a reference value.
Detailed Description
The present invention will be described in further detail below.
The invention provides a coal quality analysis and measurement model based on information fusion of laser-induced breakdown spectroscopy and near infrared spectroscopy, which comprises the following components:
the input module comprises a heating value input submodule, a volatile component input submodule, an ash content input submodule and a moisture input submodule. The heating value input submodule is used for inputting LIBS & NIR data, the volatile component input submodule is used for inputting the LIBS & NIR data, the ash content input submodule is used for inputting the LIBS data, and the moisture content input submodule is used for inputting the NIR data.
And the processing module is connected with the input module, obtains the calorific value, the volatile component, the ash content and the moisture content of the coal quality index according to a multivariate analysis method based on the received LIBS data, the NIR data and the LIBS & NIR data, and calculates the fixed carbon content of the coal quality index according to the obtained volatile component, the ash content and the moisture content of the coal quality index. In the embodiment, a coal quality quantitative analysis model is established by using the partial least square method, and the processes of calculating the calorific value, the volatile component, the ash content and the moisture content are as follows:
X＝TPt+E (1)
C＝UQt+F (2)
wherein X represents LIBS, NIR or LIBS & NIR data matrix, C represents calorific value, volatile component, ash or water data matrix, P and Q are load matrix of X and C respectively, and E and F are error matrix of X and C respectively.
The principal components T and U of X and C can be obtained by the expressions (1) and (2), respectively, and the correlation is maximized by taking into account the linear relationship between T and U when performing the calculation. Assuming that T and U are vectors in a certain column of the principal component matrices T and U, respectively, the equation representing the linear relationship between them is:
u＝vt+e (3)
where v is the coefficient and e is the error vector.
And the output module is connected with the processing module and outputs the coal quality index heat productivity, volatile components, ash content, moisture content and fixed carbon content obtained by the model.
Next, the coal quality measurement method according to the present invention will be described in detail based on the coal quality analysis measurement model. The invention provides a coal quality measuring method based on information fusion of laser-induced breakdown spectroscopy and near infrared spectroscopy, which comprises the following steps:
and step S1, collecting coal samples with known coal quality indexes, carrying out Laser Induced Breakdown Spectroscopy (LIBS) detection and near infrared spectroscopy (NIR) detection on the coal samples, collecting LIBS and NIR data, and dividing the coal samples into verification sets and calibration sets.
The coal quality index refers to the volatile content, ash content, moisture content, fixed carbon content and calorific value of the coal sample. In this example, 45 coal samples with known coal quality indicators were collected. Under the atmospheric environment condition, LIBS detection system is used for collecting LIBS data of the coal samples, and NIR detection system arranged in diffuse reflection mode is used for collecting NIR data of the coal samples, so that element composition information and molecular structure information of the fire coal can be obtained simultaneously. Multiple sets of LIBS and NIR data were collected for each coal sample, and then averaged separately. Randomly selecting 10 coal samples from 45 coal samples to form a verification set, and forming the remaining 35 coal samples into a calibration set.
Step S2, LIBS and NIR data are preprocessed to reduce interference of spectral noise to subsequent quantitative analysis.
LIBS data was pre-processed using channel normalization and NIR data was pre-processed using Standard normal transformation (SNV). Channel normalization refers to dividing the intensity of a spectral line by the total intensity of the spectrum of the channel in which the spectral line is located.
And step S3, carrying out normalization processing on the preprocessed LIBS and NIR data, wherein in the embodiment, a Partial Least Squares (PLS) method is selected as the multivariate analysis method based on the multivariate analysis method, a primary quantitative analysis model of heat productivity, volatile components, ash content and moisture content is respectively established by utilizing the LIBS and the NIR data of the calibration set after the normalization processing, and the optimal input data for establishing the quantitative analysis model is screened out.
In the embodiment, the LIBS data and the NIR data after pretreatment are respectively normalized to-1 to 1 order of magnitude by decimal scaling normalization so as to eliminate the influence of order difference on the subsequent establishment of a quantitative analysis model by using LIBS & NIR spectral data, wherein the decimal scaling normalization method comprises the following steps:
x'＝x/10p(4)
wherein x is LIBS or NIR raw data, x 'is LIBS or NIR data normalized to the magnitude of-1, and p satisfies max (| x' |) < 1.
Based on PLS, respectively establishing a calorific value, volatile component, ash content and moisture quantitative analysis model by using calibration set LIBS and NIR spectral data after normalization processing, and selecting a spectral band with high correlation coefficient as input data of each coal quality quantitative analysis model by using the correlation coefficient of the calibration set LIBS and the NIR spectral data and PLS latent variable as evaluation indexes.
S4, establishing a quantitative analysis model of each coal quality according to the optimal input data, and optimizing by a cross validation method to obtain the optimal latent variable number of PLS in the quantitative analysis model; wherein the optimal input data refers to LIBS data with high correlation coefficient, NIR data and LIBS combined NIR data.
In the optimization of the cross validation method, a decision coefficient R is adopted2And cross-validation root mean square error as an evaluation index.
And step S5, predicting the calorific value, the volatile component, the ash content and the moisture content of the coal quality indexes of the coal sample of the verification set by using the established quantitative analysis model of each coal quality, and comparing the prediction results of the quantitative analysis model established by different spectral data on each coal quality of the verification set to obtain the optimal quantitative analysis model of the corresponding coal quality indexes.
The performance of each coal quality quantitative analysis model takes a Root Mean Square Error (RMSEP) Prediction, an Average Absolute Error (AAE), and an Average Relative Error (ARE) as evaluation indexes.
The established quantitative analysis model of each coal quality is used for predicting and verifying the volatile components, the calorific value, the ash content and the moisture content of the collected coal sample, and the obtained results are shown in figures 2 to 5. As can be seen from FIGS. 2 and 3, the combination of NIR data with LIBS (LIBS) and LIBS (LIBS) is compared with the results of the analysis with LIBS or NIR spectral data&NIR) spectral data to predict R of volatiles20.981 max, RMSEP 0.672%, AAE 0.514%, ARE 1.457% min; by LIBS&NIR predicting R of calorific value20.953 highest and RMSEP 0.192MJ/kg, AAE 0.168MJ/kg and ARE 0.679% lowest; thus, LIBS&NIR is suitable for analysis of volatile and calorific values. As can be seen from FIG. 4, R obtained when grey is predicted using LIBS data20.977 high with RMSEP 0.774%, AAE 0.675%, and ARE 9.367% minimum, so the best spectral information to analyze ash is LIBS; as can be seen from FIG. 5, R is obtained by predicting moisture using NIR spectral data20.976 max and RMSEP 0.308%, AAE 0.224%, and ARE 3.345% min, so the most suitable spectral information for analyzing moisture is NIR.
And step S6, calculating the fixed carbon content according to the prediction result of the optimal quantitative analysis model corresponding to the corresponding coal quality index. The fixed carbon content is calculated using the following formula:
FCad＝100％-(Mad+Aad+Vad) (5)
therein, FCadDenotes the fixed carbon content, MadDenotes the moisture content, AadDenotes the ash content, VadRepresents the volatile content.
FIG. 6 is a graph of fitting the fixed carbon content value calculated based on the above-mentioned fixed carbon content calculation formula to the reference value, wherein R is the content of volatile components, ash and moisture obtained by the spectral analysis in this example, to the reference value2＝0.904，RMSEP＝0.681％，AAE＝0.580％，ARE＝1.271％。
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (10)
1. A coal quality measurement method based on information fusion of laser-induced breakdown spectroscopy and near infrared spectroscopy is characterized by comprising the following steps:
step S1, collecting coal samples with known coal quality indexes, carrying out Laser Induced Breakdown Spectroscopy (LIBS) detection and near infrared spectroscopy (NIR) detection on the coal samples, collecting LIBS and NIR data, and dividing the coal samples into verification sets and calibration sets;
step S2, preprocessing the LIBS and the NIR data to reduce interference of spectral noise on subsequent quantitative analysis;
step S3, carrying out normalization processing on the preprocessed LIBS and NIR data, respectively establishing primary quantitative analysis models of heating value, volatile component, ash content and moisture by utilizing the LIBS and the NIR data of the calibration set after the normalization processing based on a multivariate analysis method, and screening out the optimal input data for establishing the quantitative analysis models;
step S4, establishing a quantitative analysis model of each coal quality according to the optimal input data; wherein the optimal input data refers to LIBS data with high correlation coefficient, NIR data and LIBS combined NIR data;
s5, predicting the calorific value, the volatile component, the ash content and the moisture content of the coal quality indexes of the coal sample of the verification set by using the established quantitative analysis model of each coal quality, and comparing the prediction results of the quantitative analysis model established by different spectral data on each coal quality of the verification set to obtain the optimal quantitative analysis model of the corresponding coal quality indexes;
and step S6, calculating the fixed carbon content according to the prediction result of the optimal quantitative analysis model on the corresponding coal quality index.
2. The measurement method according to claim 1, wherein the step S1 of collecting LIBS and NIR data includes collecting multiple sets of LIBS and NIR data for each coal sample, and averaging the multiple sets of LIBS and NIR data.
3. The measurement method according to claim 1, wherein in the preprocessing step, a channel normalization preprocessing method is applied to the LIBS data; and (3) adopting a standard normal transformation preprocessing method for the NIR data.
4. The measurement method according to claim 1, wherein in step S3, the normalization process is a fractional scaling normalization:
x'＝x/10p
wherein x is original data, x 'is normalized data, and p satisfies max (| x' |) < 1.
5. The measuring method according to claim 1 or 4, wherein in the step S3, the screening out the best input data for establishing the quantitative analysis model is:
and selecting LIBS and NIR spectral band data with high correlation coefficients as input data of the quantitative analysis model of each coal quality by taking the LIBS and the NIR data of the calibration set and the correlation coefficients of the PLS latent variables as evaluation indexes.
6. The measurement method according to claim 1, wherein in step S3, the multivariate analysis method is a quantitative analysis method such as partial least squares or support vector machine regression that can deal with a high-dimensional data matrix.
7. The measurement method according to claim 1, wherein in the step S5, the quantitative analysis model predicts the performance of each coal quality indicator of the validation coal sample by using a predicted root mean square error, a mean absolute error and a mean relative error as evaluation indicators.
8. The measurement method of claim 1, wherein in the optimal quantitative analysis model, LIBS is used for analyzing calorific value of the coal quality index in combination with NIR data, LIBS is used for analyzing volatile components of the coal quality index in combination with NIR data, LIBS is used for analyzing ash content of the coal quality index, and NIR is used for analyzing moisture content of the coal quality index.
9. The measurement method according to claim 1, wherein the fixed carbon content is calculated using the following formula:
FCad＝100％-(Mad+Aad+Vad)
therein, FCadDenotes the fixed carbon content, MadDenotes the moisture content, AadDenotes the ash content, VadRepresents the volatile content.
10. A coal quality analysis and measurement model based on information fusion of laser-induced breakdown spectroscopy and near infrared spectroscopy is characterized by comprising the following components:
the input module comprises a heating value input submodule, a volatile component input submodule, an ash content input submodule and a moisture input submodule; the system comprises a heating value input submodule, a volatile component input submodule, an ash content input submodule and a moisture input submodule, wherein the heating value input submodule is used for inputting LIBS & NIR data, the volatile component input submodule is used for inputting the LIBS & NIR data, the ash content input submodule is used for inputting the LIBS data, and the moisture content input submodule is used for inputting the NIR data;
and the processing module is connected with the input module, obtains the calorific value, the volatile component, the ash content and the moisture content of the coal quality index according to a multivariate analysis method based on the received LIBS data, the NIR data and the LIBS & NIR data, and calculates the fixed carbon content of the coal quality index according to the obtained volatile component, the ash content and the moisture content of the coal quality index.
And the output module is connected with the processing module and outputs the coal quality index heat productivity, volatile components, ash content, moisture content and fixed carbon content obtained by the model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911290420.7A CN111044503A (en) | 2019-12-16 | 2019-12-16 | Coal quality measurement method based on information fusion of laser-induced breakdown spectroscopy and near infrared spectroscopy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911290420.7A CN111044503A (en) | 2019-12-16 | 2019-12-16 | Coal quality measurement method based on information fusion of laser-induced breakdown spectroscopy and near infrared spectroscopy |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111044503A true CN111044503A (en) | 2020-04-21 |
Family
ID=70236573
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911290420.7A Pending CN111044503A (en) | 2019-12-16 | 2019-12-16 | Coal quality measurement method based on information fusion of laser-induced breakdown spectroscopy and near infrared spectroscopy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111044503A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111504981A (en) * | 2020-04-26 | 2020-08-07 | 上海交通大学 | Method for determining chemical components and moisture content in powder material |
| CN111624192A (en) * | 2020-06-04 | 2020-09-04 | 杭州岚达科技有限公司 | Multi-source spectrum fused gentiana rigescens species identification method and system |
| CN111965166A (en) * | 2020-07-03 | 2020-11-20 | 华南理工大学 | Rapid measurement method for biomass briquette characteristic index |
| CN112161968A (en) * | 2020-09-02 | 2021-01-01 | 滨州医学院 | Donkey-hide gelatin brand identification method based on data fusion |
| CN112763453A (en) * | 2021-01-11 | 2021-05-07 | 江苏闪码光机电科技有限公司 | Multi-factor real-time online detection device and method for ore bulk cargo in continuous conveying |
| CN112949169A (en) * | 2021-02-04 | 2021-06-11 | 长春大学 | Coal sample test value prediction method based on spectral analysis |
| CN114112976A (en) * | 2021-12-16 | 2022-03-01 | 山西大学 | XRF-NIRS combined coal calorific capacity high-repeatability detection method |
| CN114813635A (en) * | 2022-06-28 | 2022-07-29 | 华谱智能科技(天津)有限公司 | Method for optimizing combustion parameters of coal stove and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204630927U (en) * | 2015-05-26 | 2015-09-09 | 江西农业大学 | The navel orange place of production, south, a kind of Jiangxi device for quickly identifying |
| CN206483713U (en) * | 2017-01-22 | 2017-09-12 | 杨宝祥 | Mineral dry separation system |
| CN108303410A (en) * | 2018-04-23 | 2018-07-20 | 南京信息工程大学 | Trace element and its isotope automatic checkout system |
| CN109669023A (en) * | 2018-12-05 | 2019-04-23 | 浙江大学 | A kind of soil attribute prediction technique based on Multi-sensor Fusion |
| US20190323955A1 (en) * | 2017-07-21 | 2019-10-24 | Serguei Koulikov | Optical absorption spectroscopy based gas analyzer systems and methods |
-
2019
- 2019-12-16 CN CN201911290420.7A patent/CN111044503A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204630927U (en) * | 2015-05-26 | 2015-09-09 | 江西农业大学 | The navel orange place of production, south, a kind of Jiangxi device for quickly identifying |
| CN206483713U (en) * | 2017-01-22 | 2017-09-12 | 杨宝祥 | Mineral dry separation system |
| US20190323955A1 (en) * | 2017-07-21 | 2019-10-24 | Serguei Koulikov | Optical absorption spectroscopy based gas analyzer systems and methods |
| CN108303410A (en) * | 2018-04-23 | 2018-07-20 | 南京信息工程大学 | Trace element and its isotope automatic checkout system |
| CN109669023A (en) * | 2018-12-05 | 2019-04-23 | 浙江大学 | A kind of soil attribute prediction technique based on Multi-sensor Fusion |
Non-Patent Citations (4)
| Title |
|---|
| ROSS S. BRICKLEMYER ET AL: "Comparing vis–NIRS， LIBS， and Combined vis–NIRS-LIBS for Intact Soil Core Soil Carbon Measurement", 《SOIL SCIENCE SOCIETY OF AMERICA JOURNAL》 * |
| 张励维: "基于LIBS的气力输送煤粉成分快速检测研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
| 杨旭 等: "《数据科学导论》", 31 January 2017 * |
| 陈鹏强: "煤质内部成分的近红外光谱定量检测和分析研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111504981A (en) * | 2020-04-26 | 2020-08-07 | 上海交通大学 | Method for determining chemical components and moisture content in powder material |
| CN111624192A (en) * | 2020-06-04 | 2020-09-04 | 杭州岚达科技有限公司 | Multi-source spectrum fused gentiana rigescens species identification method and system |
| CN111624192B (en) * | 2020-06-04 | 2022-12-16 | 杭州岚达科技有限公司 | Multi-source spectrum fused gentiana rigescens species identification method and system |
| CN111965166A (en) * | 2020-07-03 | 2020-11-20 | 华南理工大学 | Rapid measurement method for biomass briquette characteristic index |
| CN112161968A (en) * | 2020-09-02 | 2021-01-01 | 滨州医学院 | Donkey-hide gelatin brand identification method based on data fusion |
| CN112763453A (en) * | 2021-01-11 | 2021-05-07 | 江苏闪码光机电科技有限公司 | Multi-factor real-time online detection device and method for ore bulk cargo in continuous conveying |
| CN112949169A (en) * | 2021-02-04 | 2021-06-11 | 长春大学 | Coal sample test value prediction method based on spectral analysis |
| CN112949169B (en) * | 2021-02-04 | 2023-04-07 | 长春大学 | Coal sample test value prediction method based on spectral analysis |
| CN114112976A (en) * | 2021-12-16 | 2022-03-01 | 山西大学 | XRF-NIRS combined coal calorific capacity high-repeatability detection method |
| CN114813635A (en) * | 2022-06-28 | 2022-07-29 | 华谱智能科技(天津)有限公司 | Method for optimizing combustion parameters of coal stove and electronic equipment |
| CN114813635B (en) * | 2022-06-28 | 2022-10-04 | 华谱智能科技(天津)有限公司 | Method for optimizing combustion parameters of coal stove and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111044503A (en) | Coal quality measurement method based on information fusion of laser-induced breakdown spectroscopy and near infrared spectroscopy | |
| CN102313722B (en) | Proximate analyzing method for coal quality based on multivariate linear regression | |
| US10175661B2 (en) | System, method and apparatus for determining properties of product or process streams | |
| Laxalde et al. | Characterisation of heavy oils using near-infrared spectroscopy: optimisation of pre-processing methods and variable selection | |
| Fidêncio et al. | Determination of organic matter in soil using near-infrared spectroscopy and partial least squares regression | |
| JP2016507113A5 (en) | System and method for determining characteristics of a product or process stream | |
| CN107703097B (en) | Method for constructing model for rapidly predicting crude oil property by using near-infrared spectrometer | |
| CN105300923A (en) | Correction method of measuring point free temperature compensation model during process of online application of near infrared spectrum analyzer | |
| CN104390927B (en) | The quick determination method of ash content in coal sample | |
| Guo et al. | Rapid quantitative analysis of adulterated rice with partial least squares regression using hyperspectral imaging system | |
| CN100443883C (en) | Method for detecting hydrgenated tail-oil paraffin composition using near-infrared spectrum | |
| CN1116878A (en) | Method for prediction of physical property data of hydrocarbon products | |
| CN105954228A (en) | Method for measuring content of sodium metal in oil sand based on near infrared spectrum | |
| CN109521002B (en) | Fuel characteristic measuring method for solid fuel particle flow | |
| de Souza et al. | PAT soft sensors for wide range prediction of key properties of diesel fuels and blending components for the oil industry | |
| CN116429724A (en) | Method for detecting pollution degree of composite insulator material based on infrared hyperspectral analysis | |
| CN104568811A (en) | Novel rapid detection method of calorific values in coal samples | |
| CN112949169B (en) | Coal sample test value prediction method based on spectral analysis | |
| Zhu et al. | Online discriminant model of blood spot eggs based on spectroscopy | |
| CN104181125A (en) | Method for rapidly determining Kol-bach value of beer malt | |
| CN115236024A (en) | Training method, determination method and device for model for determining content of total acids and total esters in wine | |
| Liu et al. | Feasibility of nondestructive detection of apple crispness based on spectroscopy and machine vision | |
| CN111965166A (en) | Rapid measurement method for biomass briquette characteristic index | |
| CN111257265A (en) | Rapid detection method for penetration index of asphalt for steel bridge deck pavement | |
| CN111044504A (en) | Coal quality analysis method considering uncertainty of laser-induced breakdown spectroscopy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200421 |