CN108844941A - A kind of identification and classification method of the different grade phosphorus mines based on Raman spectrum and PCA-HCA - Google Patents
A kind of identification and classification method of the different grade phosphorus mines based on Raman spectrum and PCA-HCA Download PDFInfo
- Publication number
- CN108844941A CN108844941A CN201810540220.1A CN201810540220A CN108844941A CN 108844941 A CN108844941 A CN 108844941A CN 201810540220 A CN201810540220 A CN 201810540220A CN 108844941 A CN108844941 A CN 108844941A
- Authority
- CN
- China
- Prior art keywords
- sample
- pca
- hca
- phosphorus
- raman spectrum
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/65—Raman scattering
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/24—Earth materials
-
- 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
- G01N2201/06—Illumination; Optics
- G01N2201/061—Sources
- G01N2201/06113—Coherent sources; lasers
Abstract
The method for identifying the invention discloses the different grade phosphorus mines of Raman spectroscopy combination PCA-HCA a kind of and classifying, belongs to spectrum of use technical field.Including:The phosphorus ore sample for taking different grades obtains the Raman spectrum raw information of each sample using Raman spectrometer;The Raman spectrum raw information of acquisition is pre-processed, and establishes discrimination model to by pretreated raman spectroscopy by integrating main component analysis (PCA) and Hierarchical clustering analysis (HCA), realizes the classification of phosphorus ore sample to be measured.This process simplify the pre-treatment steps of sample; avoid cumbersome chemical process; shorten detection time; the advantages that with quick, accuracy is high, lossless; there is important impetus to the phosphorus ore for identifying different grades; new approaches are provided for quick under mine, real-time and on-line checking, to the production efficiency for improving phosphorus ore, cost of winning is reduced and environmental protection is significant.
Description
Technical field
The present invention relates to spectrum of use technical field more particularly to a kind of different product based on Raman spectrum and PCA-HCA
The identification and classification method of position phosphorus ore.
Background technique
Phosphorus ore is the important strategic resource in China, it is both the important raw mineral materials of a variety of phosphorus products, while being also food
The material base of safety and fine phosphorus chemical.China's phosphorus ore gross reserves is abundant, but rich ore is few, and 90% phosphorus ore grade is lower than
26%, average grade is only 16.85%, and most of ore needs to utilize by ore dressing.The grade of evaluation rock phosphate in powder is choosing
An important link during mine, in China, rock phosphate in powder grade refers to the content of P2O5 in rock phosphate in powder, is contained by effective P2O5
The measurement of amount carries out primary dcreening operation to phosphorus ore, can predict the commercial mining value and exploitation difficulty of phosphorus ore.
The method of current measurement rock phosphate in powder grade has a physical method and chemical method, including conventional chemical analysis method, infrared
Spectroscopic methodology, nuclear magnetic resonance method, X-ray, Plasma Mass Spectrometry (ICP-MS), ion-exchange, chromatography, mass spectrography etc..But
Wherein most methods need to carry out in the lab, and detection process is relatively cumbersome, and some methods need to answer sample
Miscellaneous pre-treatment cannot well adapt to now quickly detect a large amount of samples, the needs that on-site test is analyzed especially under mine.
One kind quickly and effectively identification of phosphorus ore grade and classification method are found, phosphate rock resource utilization efficiency is improved, to China's industry and agriculture
Industry sustainable development is of great significance.
Raman spectrum is a kind of emerging molecular fingerprint technology, and the physics, chemistry and deep structure of sample interior can be obtained
Information characterizes substance, and detection process is rapid and does not destroy sample.Compared with infrared spectroscopy, Raman spectrum vibration superposition
Effect is smaller, and bands of a spectrum are apparent, is easier to judge ore structures information by the ownership of characteristic peak in ore spectral information.
Summary of the invention
The technical problem to be solved in the present invention is that for the defects in the prior art, provide it is a kind of based on Raman spectrum and
The identification and classification method of the different grade phosphorus mines of PCA-HCA.
The technical solution adopted by the present invention to solve the technical problems is:
The present invention provides the identification and classification method of a kind of different grade phosphorus mines based on Raman spectrum and PCA-HCA, should
Method includes the following steps:
S1, the phosphorus ore powder sample for taking a variety of known grades, carry out compressing tablet process to it, obtain the corresponding pressure of different grades
Piece sample;
S2, several measurement points are chosen to each press sheet compression, carry out laser Raman spectroscopy measurement, respectively each measurement point
Raman spectrum;
S3, the raw information of the Raman spectrum of each measurement point is pre-processed, including smooth, baseline correction and single order are led
Number processing, obtains corresponding pretreatment spectrogram;
S4, using the phosphorus ore sample pretreatment spectrogram of the obtained various different grades of step S1-S3, establish database;
S5, principal component analysis and hierarchial-cluster analysis MATLAB program are write, database obtained in step S4 is carried out
PCA-HCA discrimination model is established in principal component analysis-hierarchial-cluster analysis;
S6, grade phosphorus mine sample to be measured is identified and is classified:Grade phosphorus mine sample to be measured is measured under the same conditions,
The spectrum of measurement is imported in PCA-HCA discrimination model after pretreatment, realizes the discriminant classification of phosphorus ore sample to be measured.
Further, confocal laser method for measuring Raman spectrum is used in step S2 of the invention, obtains each measurement point
Raman spectrum.
Further, 50 are not less than to the measurement point quantity that each press sheet compression is chosen in step S2 of the invention.
Further, the baseline correction method in being pre-processed in step S3 of the invention uses airPLS method baseline school
Just.
Further, principal component analysis-hierarchial-cluster analysis PCA-HCA discrimination model is built in step S5 of the invention
It is vertical:Differentiate that distance uses Euclidean distance, definition is:
Wherein, DIk, EuclideanIndicate n-dimensional space two o'clock XiAnd XkBetween Euclidean distance, n representation space dimension, j indicate
Point coordinate dimension, XijIndicate point XiJth tie up coordinate, XkjIndicate XkJth tie up coordinate;
Criterion uses knearest neighbour method, i.e., the Europe of grade phosphorus mine sample to be measured and which kind of known grade phosphorus mine sample
Formula distance is minimum, then is classified as same class.
Further, after carrying out principal component analysis in step S5 of the invention, further include to the homogeneity information of sample into
The method of row analysis:
The principal component for analyzing sample, establishes principal component analysis pca model, each measurement point of sample to its central point it is European away from
From the difference degree for representing each test point, the principal component of front three is come to content in sample, calculates separately its each measurement point
To the Euclidean distance of its central point, Euclidean distance distribution more disperses, and shows that the uniformity of phosphorus ore sample grade is poorer.
Further, it is smoothed in this method of the invention, the processing of the baseline correction of airPLS method and first derivative
Method be specially:
Firstly, Savitzky-Golay convolution method is used to carry out polynomial order to spectrum as 8 smoothing processings of 2 ranks;
Secondly, weighting penalized least-squares method airPLS again using adaptive iteration carries out baseline correction, removal fluorescence interference;Third,
The spectrum after smooth and baseline correction is handled using first derivative, obtains first derivative spectrum.
Further, the method for the PCA-HCA discrimination model established in this method of the invention is specially:
PCA analysis is carried out first, obtains retaining phosphorus ore raw spectroscopic data, and the master after the completion of classification by training set
Sample is carried out dimensionality reduction according to covariance matrix by ingredient;Secondly, HCA analysis is carried out, with sum of squares of deviations method, in conjunction with European
Phosphorus ore sample is divided into different types of cluster by distance.
The beneficial effect comprise that:Different grade phosphorus mines based on Raman spectrum and PCA-HCA of the invention
Identification and classification method, 1) measurement method of the present invention is easy to operate, realizes the different product based on Raman spectroscopy
The phosphorus ore of position quick and precisely identifies and classifies, while can measure phosphorus ore sample homogeneity, has to detection phosphorus ore grade important
Impetus reduces cost of winning and environmental protection is significant to the production efficiency for improving phosphorus ore.The present invention does not need to match
Any solution and chemical assay are made, operating procedure is enormously simplified, shortens detection time, future can be used for fast under mine
Speed, real-time and on-line checking also avoid operating unskilled or subjective factor bring measurement result not due to operator
The consequences such as accurate.2) disaggregated model is established using pretreated Raman spectrum combination PCA-HCA, there is classification accurately, quickly
Convenient feature.2) phosphorus ore grade is characterized using average characteristics Raman peak signature intensity, is weakened due to sample unevenness
Influence of the equal other influences factor to laser Raman spectroscopy measurement result, improve measurement method of the present invention reliability and
Accuracy.4) phosphorus ore grade uniformity is characterized using the distribution of the Euclidean distance of pattern detection point to center of a sample's point,
Improve the application range of measurement method of the present invention.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples, in attached drawing:
Fig. 1 is the Raman light of random 5 measurement points of phosphorus ore sample A, B, C and D of 4 kinds of grades described in the embodiment of the present invention
Spectrogram.
Fig. 2 is phosphorus ore sample A, B, C and D totally 80 groups of averaged spectrum (every kind of product of 4 kinds of grades described in the embodiment of the present invention
Position sample measures 100 points, and 5 points are averaged, and obtains 20 groups of averaged spectrums) carry out principal component analysis, the first two principal component PC1
With the shot chart of PC2.
Fig. 3 is that the PCA of known 4 kinds of phosphorus ore sample 80 groups of averaged spectrums of A, B, C and D described in the embodiment of the present invention is obtained
Divide and carries out the cluster tree graph that hierarchial-cluster analysis (HCA) is obtained.
Fig. 4 is the uniformity of known 4 kinds of grade phosphorus mine samples A, B, C and D described in the embodiment of the present invention (using European
Distance).
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.
In a specific embodiment of the invention, amount to the phosphorus ore sample of 4 kinds of grades of measurement, respectively high-grade sample A
(P2O5:31.25%) with B (P2O5:29.06%), middle grade sample C (P2O5:And low-grade sample D (P 22.08%)2O5:
3.29%).Wherein, sample A is from Guizhou Wengan area, and sample B, C and D are from Jinning, Yunnan area, the product of all samples
Place value passes through《The measurement phosphomoly adic acid quinoline volumetry of phosphoric acid anhydride in phosphorus ore content》(GB/T 1871.1-1995) measurement.
Measurement is copolymerized burnt micro Raman spectra system, laser wavelength 532nm using Nanobase XperRam200, and power is
100mW, spectral scanning range are 200~1950cm-1。
Specific step is as follows:
1) phosphorus ore sample A powder is taken to carry out tabletting;
2) the phosphorus ore sample in step 1) is placed on the objective table for being copolymerized burnt micro-Raman spectroscopy, chooses 100
Measurement point is the laser beam of 100mv using laser intensity, and the surface of sample, time for exposure are focused on by the object lens of 40X
20s, respectively each measurement point original Raman spectrum;
3) the Raman spectrum raw information of step 2) acquisition is pre-processed, including smoothing processing, airPLS method baseline
Correction and first derivative processing, obtain corresponding pretreatment spectrogram;
Smoothly locate firstly, Savitzky-Golay (SG) convolution method is used to carry out polynomial order to spectrum for 8 points of 2 ranks
Reason;Secondly, weighting penalized least-squares method (airPLS) again using adaptive iteration carries out baseline correction, removal fluorescence interference;
Third handles the spectrum after smooth and baseline correction using first derivative, obtains first derivative spectrum.
4) step 1)~3 are used) it is raman spectrum after the corresponding pretreatment of step measurement B, C and D phosphorus ore sample, with
Machine chooses 5 point mappings, such as schemes shown in (1);
Modeled segments:
5) principal component analysis and hierarchial-cluster analysis MATLAB program are write, 4) the middle Raman spectrum data obtained is carried out
PCA-HCA discrimination model is established in principal component analysis-hierarchial-cluster analysis.
PCA analysis is carried out first, phosphorus ore raw spectroscopic data is utmostly retained by training set and effect of classifying
Sample is carried out dimensionality reduction according to covariance matrix by the best principal component of fruit;Secondly, HCA analysis is carried out, with sum of squares of deviations method
(ward ' s linage rule) is divided into phosphorus ore sample not in conjunction with Euclidean distance (actual distance between m-dimensional space two o'clock)
Congener cluster.
Differentiate that distance uses Euclidean distance, criterion uses knearest neighbour method.Wherein, each sample measures 100 points,
Every 5 measurement point spectrum is averaged, and obtains 20 groups of averaged spectrums, and the phosphorus ore sample of 4 kinds of grades amounts to 80 groups of averaged spectrums.Number
1~20 counter sample A (P2O5:31.25%), 20~40 counter sample B (P2O5:29.06%), 40~60 counter sample C
(P2O5:22.08%), 60~80 counter sample D (P2O5:3.29%).Fig. 2 is that 80 groups of averaged spectrums carry out principal component analysis, preceding
The shot chart of two principal components PC1 and PC2;
Fig. 3 is that PCA score progress hierarchial-cluster analysis (HCA) of 4 kinds of phosphorus ore samples A, B, C and D, 80 groups of averaged spectrums obtains
The cluster tree graph arrived.80 groups of averaged spectrums have been divided into 5 groups, in addition to one 3.29% sample is individually assigned to one kind, remaining
79 groups of data are accurately classified, and classification accuracy has reached 98.75%.
In above scheme, the homogeneity information of sample can be analyzed simultaneously.It establishes in pca model, each test point of sample arrives
The Euclidean distance of its central point represents the difference degree of each sample point.Original spectral data is replaced using PCA score data
Most of primary data information (pdi) can not only be reflected by calculating Euclidean distance, and can compress the variable for participating in calculating Euclidean distance
Number.The coordinate of pattern detection point under model is established to the Euclidean distance of center of a sample's point by calculating first three principal component, it can be with
Reflect the uniformity of the Raman spectrum otherness and sample interior between its different sample point, the more dispersion of Euclidean distance distribution,
Show that the uniformity of phosphorus ore sample grade is poorer.
The Euclidean distance of each sample test point to its central point represents the difference degree of each sample point in model.It uses
Score data, which replaces original spectral data to calculate Euclidean distance, can not only reflect most of primary data information (pdi), and can compress
Participate in the variable number of calculating Euclidean distance.The lower 4 kinds of phosphorus ores pattern detection point of model is established by calculating its first three principal component
Coordinate can reflect in the Raman spectrum otherness and sample between its different sample point to the Euclidean distance of its center of a sample's point
The uniformity in portion.Fig. 4 is the uniformity of 4 kinds of grade phosphorus mine samples A, B, C and D, it can be seen that low-grade sample D (P2O5:
3.29%) SPECTRAL DIVERSITY between sample point is maximum, and other ratio of medium-high grade phosphorus ore SPECTRAL DIVERSITYs are all smaller, and uniformity is all preferable.
Identification and classified part:
6) it is the predictive ability of further verifying model, 20 groups is had neither part nor lot in the phosphorus ore sample B (10 groups) and C (10 of modeling
Group) carry out step 1) -3) treated, and spectrum imports in PCA-HCA discrimination model, realize the discriminant classification of phosphorus ore sample.Knot
Fruit shows have 9 groups correctly to be classified in 10 groups of phosphorus ore sample B, and only 1 group has been assigned to A group, 10 groups of phosphorus ore sample C quilts by mistake
Accurate classification, classification accuracy 95.00%.Show to combine PCA-HCA model to the different product of differentiation in time based on Raman spectrum
The phosphorus ore of position has good reliability and accuracy.
In conclusion the present invention provides a kind of, the different grade phosphorus mines based on Raman spectroscopy combination PCA-HCA reflect
Other and classification method.Compared to existing different grade phosphorus mine identifications compared with classification method, this method is easy to operate, avoids
Cumbersome chemical separation process, reduces sample detection time, good classification effect, while it is uniform to measure phosphorus ore sample
Property, there is important impetus to detection phosphorus ore grade;It can be quick, the real-time and on-line checking of phosphorus ore grade under realization mine
A kind of new approaches are provided, to the production efficiency for improving phosphorus ore, cost of winning is reduced and environmental protection is significant.
It should be understood that for those of ordinary skills, it can be modified or changed according to the above description,
And all these modifications and variations should all belong to the protection domain of appended claims of the present invention.
Claims (8)
1. a kind of identification and classification method of the different grade phosphorus mines based on Raman spectrum and PCA-HCA, which is characterized in that the party
Method includes the following steps:
S1, the phosphorus ore powder sample for taking a variety of known grades, carry out compressing tablet process to it, obtain the corresponding tabletting sample of different grades
Product;
S2, several measurement points are chosen to each press sheet compression, carry out laser Raman spectroscopy measurement, respectively each measurement point drawing
Graceful spectrum;
S3, the raw information of the Raman spectrum of each measurement point is pre-processed, including at smooth, baseline correction and first derivative
Reason, obtains corresponding pretreatment spectrogram;
S4, using the phosphorus ore sample pretreatment spectrogram of the obtained various different grades of step S1-S3, establish database;
S5, principal component analysis and hierarchial-cluster analysis MATLAB program are write, to database obtained in step S4 carry out it is main at
Divide analysis-hierarchial-cluster analysis, establishes PCA-HCA discrimination model;
S6, grade phosphorus mine sample to be measured is identified and is classified:Grade phosphorus mine sample to be measured is measured under the same conditions, will be surveyed
The spectrum of amount imports in PCA-HCA discrimination model after pretreatment, realizes the discriminant classification of phosphorus ore sample to be measured.
2. the identification and classification method of the different grade phosphorus mines according to claim 1 based on Raman spectrum and PCA-HCA,
It is characterized in that, using confocal laser method for measuring Raman spectrum in step S2, the Raman spectrum of each measurement point is obtained.
3. the identification and classification method of the different grade phosphorus mines according to claim 1 based on Raman spectrum and PCA-HCA,
It is characterized in that, being not less than 50 to the measurement point quantity that each press sheet compression is chosen in step S2.
4. the identification and classification method of the different grade phosphorus mines according to claim 1 based on Raman spectrum and PCA-HCA,
It is characterized in that, the baseline correction method in being pre-processed in step S3 uses the baseline correction of airPLS method.
5. the identification and classification method of the different grade phosphorus mines according to claim 1 based on Raman spectrum and PCA-HCA,
It is characterized in that, principal component analysis-hierarchial-cluster analysis PCA-HCA discrimination model foundation in step S5:Differentiate that distance uses
Euclidean distance, definition are:
Wherein, DIk, EuclideanIndicate n-dimensional space two o'clock XiAnd XkBetween Euclidean distance, n representation space dimension, j indicate point sit
Mark dimension, XijIndicate point XiJth tie up coordinate, XkjIndicate XkJth tie up coordinate;
Criterion uses knearest neighbour method, i.e., grade phosphorus mine sample to be measured and which kind of known grade phosphorus mine sample it is European away from
From minimum, then same class is classified as.
6. the identification and classification method of the different grade phosphorus mines according to claim 1 based on Raman spectrum and PCA-HCA,
It is characterized in that, further including the method analyzed the homogeneity information of sample after carrying out principal component analysis in step S5:
The principal component for analyzing sample, establishes principal component analysis pca model, the Euclidean distance generation of each measurement point of sample to its central point
The difference degree of each test point of table, the principal component of front three is come to content in sample, is calculated separately its each measurement point and is arrived it
The Euclidean distance of central point, Euclidean distance distribution more disperse, and show that the uniformity of phosphorus ore sample grade is poorer.
7. the identification and classification method of the different grade phosphorus mines according to claim 1 based on Raman spectrum and PCA-HCA,
It is characterized in that, being smoothed in this method, the method for the baseline correction of airPLS method and first derivative processing is specially:
Firstly, Savitzky-Golay convolution method is used to carry out polynomial order to spectrum as 8 smoothing processings of 2 ranks;Secondly,
It weights penalized least-squares method airPLS again using adaptive iteration and carries out baseline correction, removal fluorescence interference;Third, using one
Order derivative handles the spectrum after smooth and baseline correction, obtains first derivative spectrum.
8. the identification and classification method of the different grade phosphorus mines according to claim 1 based on Raman spectrum and PCA-HCA,
It is characterized in that, the method for the PCA-HCA discrimination model established in this method is specially:
First carry out PCA analysis, by training set obtain retain phosphorus ore raw spectroscopic data, and classify after the completion of it is main at
Point, sample is carried out by dimensionality reduction according to covariance matrix;Secondly, carry out HCA analysis, with sum of squares of deviations method, in conjunction with it is European away from
It is divided into different types of cluster from phosphorus ore sample.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810540220.1A CN108844941B (en) | 2018-05-30 | 2018-05-30 | Method for identifying and classifying different-grade phosphate ores based on Raman spectrum and PCA-HCA |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810540220.1A CN108844941B (en) | 2018-05-30 | 2018-05-30 | Method for identifying and classifying different-grade phosphate ores based on Raman spectrum and PCA-HCA |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108844941A true CN108844941A (en) | 2018-11-20 |
CN108844941B CN108844941B (en) | 2021-10-12 |
Family
ID=64211007
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810540220.1A Active CN108844941B (en) | 2018-05-30 | 2018-05-30 | Method for identifying and classifying different-grade phosphate ores based on Raman spectrum and PCA-HCA |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108844941B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110826615A (en) * | 2019-10-31 | 2020-02-21 | 南方电网科学研究院有限责任公司 | Method, device, equipment, medium and data acquisition system for classifying pollutants |
CN110989024A (en) * | 2019-12-17 | 2020-04-10 | 山东大学 | TBM tunnel fault broken zone forecasting system and method based on rock mineral analysis |
CN111398243A (en) * | 2020-04-02 | 2020-07-10 | 中南大学 | Optical fiber Raman system and method for on-line detection of grade of tungsten flotation concentrate |
CN112834481A (en) * | 2020-12-31 | 2021-05-25 | 宁波海关技术中心 | Raman spectrum enhanced measurement system and measurement method |
CN116559142A (en) * | 2023-05-11 | 2023-08-08 | 长光辰英(杭州)科学仪器有限公司 | Colony Raman spectrum rapid selection method based on HCA +' |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102053083A (en) * | 2010-11-09 | 2011-05-11 | 清华大学 | Method for on-line measurement of coal quality characteristics based on partial least squares method |
CN103398993A (en) * | 2013-08-14 | 2013-11-20 | 江南大学 | Method for detecting commercially available orange juice drink by combination of PCA-HCA (principal component analysis-hierarchical cluster analysis) and PLSR (partial least squares regression) through fluorescence spectroscopy |
CN104215591A (en) * | 2014-09-25 | 2014-12-17 | 暨南大学 | Damage-free visible-near infrared light spectrum detecting method |
CN104237403A (en) * | 2014-09-03 | 2014-12-24 | 上海应用技术学院 | Method for distinguishing chicken base |
CN105136738A (en) * | 2015-09-29 | 2015-12-09 | 中国林业科学研究院林产化学工业研究所 | Near-infrared-based method for identifying tree varieties ranging from eucalyptus-category tree varieties to acacia-mangium-category tree varieties |
CN106383103A (en) * | 2016-09-18 | 2017-02-08 | 中国科学院海洋研究所 | Time-resolved oil fluorescence identification method based on main component analysis |
WO2017197346A1 (en) * | 2016-05-13 | 2017-11-16 | Gas Sensing Technology Corp. | Gross mineralogy and petrology using raman spectroscopy |
CN107389813A (en) * | 2017-07-10 | 2017-11-24 | 北京中医药大学 | Rascal, dried orange peel, the dried immature fruit of citron orange and the method for Fructus Aurantii are differentiated based on chemical classification and UPLC Tof MS |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103604771A (en) * | 2013-12-02 | 2014-02-26 | 广东产品质量监督检验研究院 | Method for identifying type of water-based wall coating commonly used emulsions by utilizing near-infrared spectroscopy principal component analysis-Mahalanobis distance classification method |
CN106501208A (en) * | 2016-09-20 | 2017-03-15 | 广西中烟工业有限责任公司 | A kind of tobacco style similitude sorting technique based near infrared light spectrum signature |
CN107958267B (en) * | 2017-11-21 | 2021-04-27 | 东南大学 | Oil product property prediction method based on spectral linear representation |
-
2018
- 2018-05-30 CN CN201810540220.1A patent/CN108844941B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102053083A (en) * | 2010-11-09 | 2011-05-11 | 清华大学 | Method for on-line measurement of coal quality characteristics based on partial least squares method |
CN103398993A (en) * | 2013-08-14 | 2013-11-20 | 江南大学 | Method for detecting commercially available orange juice drink by combination of PCA-HCA (principal component analysis-hierarchical cluster analysis) and PLSR (partial least squares regression) through fluorescence spectroscopy |
CN104237403A (en) * | 2014-09-03 | 2014-12-24 | 上海应用技术学院 | Method for distinguishing chicken base |
CN104215591A (en) * | 2014-09-25 | 2014-12-17 | 暨南大学 | Damage-free visible-near infrared light spectrum detecting method |
CN105136738A (en) * | 2015-09-29 | 2015-12-09 | 中国林业科学研究院林产化学工业研究所 | Near-infrared-based method for identifying tree varieties ranging from eucalyptus-category tree varieties to acacia-mangium-category tree varieties |
WO2017197346A1 (en) * | 2016-05-13 | 2017-11-16 | Gas Sensing Technology Corp. | Gross mineralogy and petrology using raman spectroscopy |
CN106383103A (en) * | 2016-09-18 | 2017-02-08 | 中国科学院海洋研究所 | Time-resolved oil fluorescence identification method based on main component analysis |
CN107389813A (en) * | 2017-07-10 | 2017-11-24 | 北京中医药大学 | Rascal, dried orange peel, the dried immature fruit of citron orange and the method for Fructus Aurantii are differentiated based on chemical classification and UPLC Tof MS |
Non-Patent Citations (10)
Title |
---|
CEBI NUR等: "Detection of L-Cysteine in wheat flour by Raman microspectroscopy combined chemometrics of HCA and PCA", 《FOOD CHEMISTRY》 * |
严衍禄等: "《近红外光谱分析的原理、技术与应用》", 13 January 2013, 中国轻工业出版社 * |
刘燕德: "《光谱诊断技术在农产品品质检测中的应用》", 31 January 2017, 华中科技大学出版社 * |
司守奎等: "《数学建模算法与应用》", 30 April 2015, 国防工业出版社 * |
周天楠等: "《聚合物材料结构表征与分析实验教程》", 31 May 2016, 四川大学出版社 * |
李舰等: "《数据科学中的R语言》", 31 July 2015, 西安交通大学出版社 * |
王斌会: "《多元统计分析及R语言建模》", 31 March 2016, 暨南大学出版社 * |
王艳玲: "《文物检测仪器与应用》", 31 December 2016, 宁夏人民教育出版社 * |
蔡耀仪等: "基于拉曼光谱的复杂硫化矿快速分类方法研究", 《光谱学与光谱分析》 * |
陈思雨等: "基于共聚焦拉曼光谱技术的苹果轻微损伤早期判别分析", 《光谱学与光谱分析》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110826615A (en) * | 2019-10-31 | 2020-02-21 | 南方电网科学研究院有限责任公司 | Method, device, equipment, medium and data acquisition system for classifying pollutants |
CN110989024A (en) * | 2019-12-17 | 2020-04-10 | 山东大学 | TBM tunnel fault broken zone forecasting system and method based on rock mineral analysis |
CN110989024B (en) * | 2019-12-17 | 2021-10-08 | 山东大学 | TBM tunnel fault broken zone forecasting system and method based on rock mineral analysis |
CN111398243A (en) * | 2020-04-02 | 2020-07-10 | 中南大学 | Optical fiber Raman system and method for on-line detection of grade of tungsten flotation concentrate |
WO2021196416A1 (en) * | 2020-04-02 | 2021-10-07 | 中南大学 | Optical fiber raman system and method for online detection of tungsten flotation concentrate grades |
CN112834481A (en) * | 2020-12-31 | 2021-05-25 | 宁波海关技术中心 | Raman spectrum enhanced measurement system and measurement method |
CN112834481B (en) * | 2020-12-31 | 2023-09-05 | 宁波海关技术中心 | Raman spectrum enhancement measurement system and measurement method |
CN116559142A (en) * | 2023-05-11 | 2023-08-08 | 长光辰英(杭州)科学仪器有限公司 | Colony Raman spectrum rapid selection method based on HCA +' |
CN116559142B (en) * | 2023-05-11 | 2023-11-21 | 长光辰英(杭州)科学仪器有限公司 | Colony Raman spectrum rapid selection method based on HCA +' |
Also Published As
Publication number | Publication date |
---|---|
CN108844941B (en) | 2021-10-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108844941A (en) | A kind of identification and classification method of the different grade phosphorus mines based on Raman spectrum and PCA-HCA | |
CN104807787B (en) | A kind of Classification of Tea discrimination method based on LIBS | |
CN103487411B (en) | A kind of random forests algorithm is in conjunction with the method for Laser-induced Breakdown Spectroscopy identification type of steels | |
CN103488874B (en) | A kind of combination LIBS sorting technique to ferrous materials | |
CN102778442B (en) | Method for rapidly identifying type of balsam material liquid for cigarette | |
Longobardi et al. | Geographical origin discrimination of lentils (Lens culinaris Medik.) using 1H NMR fingerprinting and multivariate statistical analyses | |
CN108181263B (en) | Tobacco leaf position feature extraction and discrimination method based on near infrared spectrum | |
CN104198432B (en) | The method of application near-infrared spectrum technique Undamaged determination fire-resistant coating for steel structure brand | |
CN101900672B (en) | Method for quickly identifying class and viscosity grade of lubricating oil | |
CN106560697A (en) | Method for identifying producing area of Wuyi rock tea through combination of near infrared spectroscopy and trace element detection | |
CN102183500B (en) | White spirit identification method based on fluorescence characteristic parameter Euclidean distance | |
CN105843870B (en) | The analysis method and its application of repeatability and reproducibility | |
CN104697966A (en) | Method for quantitatively analyzing chromium and manganese in steel based on least square support vector machine algorithm combined with laser-induced breakdown spectroscopy | |
CN106680241A (en) | Novel spectrum multi-analysis classification and identification method and application thereof | |
CN102004088A (en) | Method for measuring coal property on line based on neural network | |
CN107132266A (en) | A kind of Classification of water Qualities method and system based on random forest | |
CN106596513A (en) | Tea leaf variety identification method based on laser induced breakdown spectroscopy | |
CN105717066A (en) | Near-infrared spectrum recognition model based on weighting association coefficients | |
CN106770607B (en) | A method of identifying genuine-fake cigarette using HS-IMR-MS | |
CN107402192A (en) | A kind of method of quick analysis essence and flavoring agent quality stability | |
CN111272686B (en) | Hyperspectral detection method for iron grade of iron ore concentrate powder | |
CN106645098B (en) | A kind of jade source area identification method of spectral normalization combination multivariate statistical model | |
CN103698353A (en) | Bird's nest identification method | |
CN111398208B (en) | Method for rapidly identifying jadeite in traditional process by utilizing near infrared technology | |
CN112485238B (en) | Method for identifying turmeric essential oil producing area based on Raman spectrum technology |
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 |