CN102135496A - Infrared spectrum quantitative analysis method and infrared spectrum quantitative analysis device based on multi-scale regression - Google Patents
Infrared spectrum quantitative analysis method and infrared spectrum quantitative analysis device based on multi-scale regression Download PDFInfo
- Publication number
- CN102135496A CN102135496A CN2010106013539A CN201010601353A CN102135496A CN 102135496 A CN102135496 A CN 102135496A CN 2010106013539 A CN2010106013539 A CN 2010106013539A CN 201010601353 A CN201010601353 A CN 201010601353A CN 102135496 A CN102135496 A CN 102135496A
- Authority
- CN
- China
- Prior art keywords
- infrared spectrum
- quantitative analysis
- spectrum
- model
- spectrum quantitative
- 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
Images
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
- Spectrometry And Color Measurement (AREA)
Abstract
The invention relates to an infrared spectrum quantitative analysis method and an infrared spectrum quantitative analysis device based on multi-scale regression. The infrared spectrum quantitative analysis device comprises a spectrometer connected with a data signal wire, a preprocessor, a wavelet decomposition and reconfiguration processor, and a partial least-squares regression model integrator; and the infrared spectrum comprises a mid-infrared and near-infrared spectrum, with the wavelength range of 780nm to 5000nm. By wavelet decomposition and reconfiguration transformation, the multi-model establishment is realized; the difficulty of extracting the spectrum signal information by a single-model method is overcome; by independently determining factor quantity on different sub-models, the aim of sufficiently extracting effective information can be realized, and the prediction precision and stability of infrared spectrum analysis model can be improved.
Description
Technical field
The present invention relates to a kind of IR spectrum quantitative analysis method and apparatus, particularly based on the IR spectrum quantitative analysis method and apparatus of multiple dimensioned recurrence.
Background technology
Owing to both contained useful information in the spectral signal that spectrometer obtains, other various stochastic errors (background and noise) are also superposeing simultaneously.Therefore, when utilizing partial least-square regression method to carry out quantitative test, be difficult to obtain the higher model of precision of prediction.At this problem of precision of prediction that improves the partial least squares regression model, number of research projects is carried out, mainly comprise preprocessing procedures and variable STUDY ON SCREENING at present, these methods have been successfully used to the elimination of spectral background correction, noise removing, no information variable.Yet when utilizing said method to carry out information extraction, regular meeting face useful information extract insufficient or the information extracted in comprise noisy problem.Therefore, need invent a kind of the needs extracts spectral information, but classify by the information that spectrum is comprised, then sorted spectral information is carried out modeling and forecasting respectively, carry out integrated to the model result of each inhomogeneous spectral information at last, so both the inaccurate of withdrawing spectral information can be avoided, the predictablity rate of spectral model can be improved again net result.
Wavelet transformation successfully has been applied in the pre-service of spectral signal, comprises that data compression, level and smooth filter are made an uproar, baseline correction, overlapped signal is resolved and analyze field such as image processing.Different with other preprocess method, wavelet transformation has " time-frequency advantage ".By wavelet transform process, a spectral signal can be divided into several subsignals of different frequency, and after these subsignals were reconstructed, the information that reconstruct spectrum is comprised was almost identical with original spectrum.At last, by to the sub-spectral signal of the reconstruct under different frequency modeling and forecasting respectively, and carry out integrated to predicting the outcome.
In this patent, invented a kind of IR spectrum quantitative analysis method and apparatus that combines partial least-square regression method based on wavelet decomposition with reconstruct.Overcome the difficult point of single model method to withdrawing spectral information, when the spectroscopic data of Analysis of Complex, utilize method and apparatus among the present invention can directly utilize under each yardstick reconstruct spectrum to set up a plurality of offset minimum binary submodels, these submodel factor numbers can be selected more flexibly effectively according to the quantity of information that sub-spectrum comprises, and reach the purpose of the useful information under each yardstick of abundant extraction.
Summary of the invention
In the application Infrared Spectrum Technology component to be measured is carried out in the express-analysis process, in order to solve the inaccurate problem of withdrawing spectral information.The invention provides a kind of IR spectrum quantitative analysis method and apparatus based on multiple dimensioned recurrence.The characteristics of the multiresolution analysis of the wavelet transformation that this method and apparatus makes full use of have realized making full use of and reasonable distribution of infrared spectrum information.
The device of realizing technique scheme comprises: grow up to be a useful person through spectrometer, pretreater, wavelet decomposition and reconfigurable processor, partial least squares regression mode set that data signal line links to each other.
Infrared and near infrared spectrum during described infrared spectrum comprises, promptly wavelength coverage is: 780 nm-50000 nm.
Described pretreater takes centralization and vector normalization that the original signal of spectrometer collection is handled.
Described wavelet decomposition and reconfigurable processor, the treatment step that specifically comprises is as follows: at first, in the wavelet decomposition process, need set decomposition scale and two parameters of wavelet basis; Secondly the approximate or details spectral component of decomposing under each yardstick of back is reconstructed, so just original spectral signal data battle array is transformed to several the sub-spectral signal data battle arrays identical with original spectrum signal data battle array dimension.
Described partial least squares regression mode set is grown up to be a useful person, its concrete operations are as follows: respectively to setting up corresponding partial least squares regression submodel (in each submodel through the sub-spectral signal data battle array that obtains after wavelet decomposition and the reconstruction processor processes, number of principal components can be selected different numerical value), utilize the submodel of having set up respectively test set sample index to be predicted, predicted the outcome accordingly respectively; At last predicting the outcome of each submodel is weighted, obtains the predicted value of final sample index.By comparing under different decomposition yardstick and the wavelet basis, the predicted root mean square error of model (Root Mean Square Error of Prediction, RMSEP) value is determined suitable decomposition scale, wavelet basis and model parameter and preservation, is used for the forecast analysis of follow-up fresh sample infrared spectrum.
Because the present invention adopts above technical scheme, obtains following effect:
By wavelet decomposition and restructuring transformation, realized the structure of multi-model, overcome the difficulty of single model method to the spectral signal information extraction; By different submodels are determined factor number separately, realized the abundant extraction of effective information, improved the precision of prediction and the robustness of Infrared spectroscopy model.
Description of drawings
The IR spectrum quantitative analysis method and apparatus synoptic diagram of the multiple dimensioned recurrence of Fig. 1;
Fig. 2 near infrared light spectrogram;
The multiple dimensioned partial least-square regression method operation chart of Fig. 3;
Fig. 4 decomposition scale is to the influence of multiple dimensioned partial least-square regression method
Fig. 5 wavelet decomposition and reconfigurable processor operation chart;
The predicted value of Fig. 6 infrared spectrum model and the correlogram of reference value.
Embodiment
Embodiment describes in conjunction with following embodiment.Near infrared spectrum with pears is an example, the pol index of pears inside is carried out the structure of multiple dimensioned regression model.
Fig. 1 is the IR spectrum quantitative analysis method and apparatus synoptic diagram of multiple dimensioned recurrence, and Fig. 2 is the near infrared light spectrogram, and spectral range is 750-1800 nm, and every spectrum comprises 1051 data points.All samples is divided into calibration set and test set according to the ratio of 2:1.
All samples is carried out wavelet decomposition, select the db4 wavelet basis here during decomposition, decomposition scale from 1 to 20, Figure 3 shows that multiple dimensioned partial least-square regression method operation chart, as can be seen from the figure spectrum is after wavelet decomposition reconstruct, obtain a series of sub-spectral signal matrixes identical with the original spectrum dimension, all sub-spectrum atlases differ greatly, and the useful information that each sub-spectrum matrix comprises also there are differences.Therefore during modeling, original spectrum can only be selected a number of principal components, and multiple dimensioned partial least-square regression method can be chosen different number of principal components by antithetical phrase spectrum matrix, makes information extraction more flexibly fully.
Figure 4 shows that the influence of decomposition scale to multiple dimensioned partial least-square regression method, dotted line represents to adopt the predicted root mean square error of traditional partial least-square regression method among the figure, solid line is represented the change curve of the predicted root mean square error of test set with the wavelet decomposition yardstick, as we know from the figure, when adopting 5 yardstick wavelet decomposition reconstruct, the predicted root mean square error minimum of test set.Thereby can determine the decomposition scale and the wavelet basis of wavelet decomposition and reconfigurable processor.
Figure 5 shows that wavelet decomposition and reconfigurable processor operation chart.Each sub-spectral signal matrix among the figure is set up calibration model respectively, corresponding number of principal components is respectively 7,4,5,3,2,4, and when handling without wavelet decomposition and reconfigurable processor, the number of principal components of model is 4, as seen adopts multiple dimensioned partial least-squares regressive analysis method to be more conducive to the extraction of spectral information.
Figure 6 shows that the correlogram of multiple dimensioned partial least squares regression model predication value of infrared spectrum and reference value.As we know from the figure, obtained the better prediction result.
Effect of the present invention is: by adopting multiple dimensioned PLS method infrared spectrum is carried out quantitative analysis, help to extract the useful information of spectral signal under the different frequency, obtain more accurate, stable predicting the outcome. Therefore, the method and apparatus of this invention is expected to become the infrared spectrum analysis method that a kind of extremely has application prospect.
Claims (1)
1. based on the IR spectrum quantitative analysis method and apparatus of multiple dimensioned recurrence, it is characterized in that: comprise that spectrometer, pretreater, wavelet decomposition and reconfigurable processor, partial least squares regression mode set that data signal line links to each other grow up to be a useful person;
Infrared and near infrared spectrum during described infrared spectrum comprises, promptly wavelength coverage is: 780 nm-50000 nm;
Described pretreater takes centralization and vector normalization that the original signal of spectrometer collection is handled.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010106013539A CN102135496A (en) | 2010-12-23 | 2010-12-23 | Infrared spectrum quantitative analysis method and infrared spectrum quantitative analysis device based on multi-scale regression |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010106013539A CN102135496A (en) | 2010-12-23 | 2010-12-23 | Infrared spectrum quantitative analysis method and infrared spectrum quantitative analysis device based on multi-scale regression |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102135496A true CN102135496A (en) | 2011-07-27 |
Family
ID=44295343
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010106013539A Pending CN102135496A (en) | 2010-12-23 | 2010-12-23 | Infrared spectrum quantitative analysis method and infrared spectrum quantitative analysis device based on multi-scale regression |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102135496A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102435556A (en) * | 2011-09-20 | 2012-05-02 | 湖南大学 | Accurate spectrum quantitative analysis method used for complex heterogeneous mixture system |
| CN103884670A (en) * | 2014-03-13 | 2014-06-25 | 西安交通大学 | Smoke component quantitative analysis method based on near infrared spectrum |
| CN104574341A (en) * | 2013-10-11 | 2015-04-29 | 中国林业科学研究院资源信息研究所 | Method and device for determining sugar degree of fruit |
| CN105842190A (en) * | 2016-03-17 | 2016-08-10 | 浙江中烟工业有限责任公司 | Near-infrared model transfer method based on spectral regression |
| CN109492707A (en) * | 2018-11-28 | 2019-03-19 | 武汉轻工大学 | Construction method, device, equipment and the storage medium of spectrum analysis model |
| CN114112978A (en) * | 2021-12-13 | 2022-03-01 | 大连理工大学 | Wavelet function calibration modeling method for detecting concentration of solution in crystallization process by using in-situ infrared spectroscopy |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101806729A (en) * | 2010-03-31 | 2010-08-18 | 中国人民解放军总后勤部油料研究所 | In-use lubricating oil quality rapid testing method |
| CN101915744A (en) * | 2010-07-05 | 2010-12-15 | 北京航空航天大学 | Near infrared spectrum nondestructive testing method and device for material component content |
-
2010
- 2010-12-23 CN CN2010106013539A patent/CN102135496A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101806729A (en) * | 2010-03-31 | 2010-08-18 | 中国人民解放军总后勤部油料研究所 | In-use lubricating oil quality rapid testing method |
| CN101915744A (en) * | 2010-07-05 | 2010-12-15 | 北京航空航天大学 | Near infrared spectrum nondestructive testing method and device for material component content |
Non-Patent Citations (2)
| Title |
|---|
| 《化工时刊》 20080202 殷俊等 小波变换_偏最小二乘法用于苯胺_苯酚和苯甲酸的同时测定 第43-44、52页 1 第22卷, 第2期 * |
| 褚小立等: "小波变换结合多维偏最小二乘方法用于近红外光谱定量分析", 《分析化学研究简报》, vol. 34, 30 September 2006 (2006-09-30), pages 175 - 178 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102435556A (en) * | 2011-09-20 | 2012-05-02 | 湖南大学 | Accurate spectrum quantitative analysis method used for complex heterogeneous mixture system |
| CN102435556B (en) * | 2011-09-20 | 2013-09-04 | 湖南大学 | Accurate spectrum quantitative analysis method used for complex heterogeneous mixture system |
| CN104574341A (en) * | 2013-10-11 | 2015-04-29 | 中国林业科学研究院资源信息研究所 | Method and device for determining sugar degree of fruit |
| CN104574341B (en) * | 2013-10-11 | 2017-09-05 | 中国林业科学研究院资源信息研究所 | A kind of determination method and apparatus of sugar degree |
| CN103884670A (en) * | 2014-03-13 | 2014-06-25 | 西安交通大学 | Smoke component quantitative analysis method based on near infrared spectrum |
| CN103884670B (en) * | 2014-03-13 | 2016-01-20 | 西安交通大学 | Based on the smoke components quantitative analysis method of near infrared spectrum |
| CN105842190A (en) * | 2016-03-17 | 2016-08-10 | 浙江中烟工业有限责任公司 | Near-infrared model transfer method based on spectral regression |
| CN105842190B (en) * | 2016-03-17 | 2018-12-11 | 浙江中烟工业有限责任公司 | A kind of method for transferring near infrared model returned based on spectrum |
| CN109492707A (en) * | 2018-11-28 | 2019-03-19 | 武汉轻工大学 | Construction method, device, equipment and the storage medium of spectrum analysis model |
| CN109492707B (en) * | 2018-11-28 | 2020-10-23 | 武汉轻工大学 | Method, device and equipment for constructing spectral analysis model and storage medium |
| CN114112978A (en) * | 2021-12-13 | 2022-03-01 | 大连理工大学 | Wavelet function calibration modeling method for detecting concentration of solution in crystallization process by using in-situ infrared spectroscopy |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109493287B (en) | Deep learning-based quantitative spectral data analysis processing method | |
| CN102135496A (en) | Infrared spectrum quantitative analysis method and infrared spectrum quantitative analysis device based on multi-scale regression | |
| CN110068544B (en) | Substance identification network model training method and terahertz spectrum substance identification method | |
| CN102305772A (en) | Method for screening characteristic wavelength of near infrared spectrum features based on heredity kernel partial least square method | |
| CN110907393B (en) | Method and device for detecting saline-alkali stress degree of plants | |
| CN107121407B (en) | The method that near-infrared spectrum analysis based on PSO-RICAELM identifies Cuiguan pear maturity | |
| CN113008805B (en) | Radix angelicae decoction piece quality prediction method based on hyperspectral imaging depth analysis | |
| CN102072767A (en) | Wavelength similarity consensus regression-based infrared spectrum quantitative analysis method and device | |
| CN104062262A (en) | Crop seed variety authenticity identification method based on near infrared spectrum | |
| CN107247033B (en) | Identify the method for Huanghua Pear maturity based on rapid decay formula life cycle algorithm and PLSDA | |
| CN104655583A (en) | Fourier-infrared-spectrum-based rapid coal quality recognition method | |
| CN105158200A (en) | Modeling method capable of improving accuracy of qualitative near-infrared spectroscopic analysis | |
| CN104255118B (en) | Rapid lossless testing method based on near infrared spectroscopy technology for paddy rice seed germination percentage | |
| CN105138834A (en) | Tobacco chemical value quantifying method based on near-infrared spectrum wave number K-means clustering | |
| CN116385784A (en) | Method and system for measuring and calculating chlorophyll content of rice under cadmium stress | |
| CN103743705A (en) | Rapid detection method for sorghum halepense and similar species | |
| CN114216877B (en) | Automatic detection and reconstruction method and system for spectral peak in tea near infrared spectral analysis | |
| CN115436343A (en) | Method and system for migration and standardization between heterogeneous laser induced breakdown spectroscopy | |
| CN117250161B (en) | Real-time monitoring system of soybean salt and alkali tolerance identification pond | |
| Yang et al. | A quality detection method of corn based on spectral technology and deep learning model | |
| Huang et al. | Optimal wavelength selection for hyperspectral scattering prediction of apple firmness and soluble solids content | |
| CN117538287A (en) | Method and device for nondestructive testing of phosphorus content of Huangguan pear | |
| Wang et al. | Monitoring model for predicting maize grain moisture at the filling stage using NIRS and a small sample size | |
| CN102072884A (en) | Wheat leaf sugar-nitrogen ratio rapid detection method based on spectrum technology | |
| CN105651727B (en) | The method that near-infrared spectrum analysis based on JADE and ELM differentiates apple shelf life |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20110727 |