CN115372311A - Method and system for predicting slash pine microfiber filament angle by near infrared spectrum technology - Google Patents
Method and system for predicting slash pine microfiber filament angle by near infrared spectrum technology Download PDFInfo
- Publication number
- CN115372311A CN115372311A CN202211000719.6A CN202211000719A CN115372311A CN 115372311 A CN115372311 A CN 115372311A CN 202211000719 A CN202211000719 A CN 202211000719A CN 115372311 A CN115372311 A CN 115372311A
- Authority
- CN
- China
- Prior art keywords
- slash pine
- angle
- near infrared
- microfiber
- wood
- 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
- 235000011334 Pinus elliottii Nutrition 0.000 title claims abstract description 124
- 241000142776 Pinus elliottii Species 0.000 title claims abstract description 124
- 229920001410 Microfiber Polymers 0.000 title claims abstract description 98
- 239000003658 microfiber Substances 0.000 title claims abstract description 98
- 238000002329 infrared spectrum Methods 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000005516 engineering process Methods 0.000 title claims abstract description 15
- 239000002023 wood Substances 0.000 claims abstract description 111
- 238000012795 verification Methods 0.000 claims abstract description 42
- 238000012937 correction Methods 0.000 claims abstract description 32
- 210000001724 microfibril Anatomy 0.000 claims abstract description 28
- 238000005259 measurement Methods 0.000 claims abstract description 22
- 238000011156 evaluation Methods 0.000 claims abstract description 6
- 239000000843 powder Substances 0.000 claims description 20
- 238000001228 spectrum Methods 0.000 claims description 13
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 7
- 238000004497 NIR spectroscopy Methods 0.000 claims description 6
- 230000002452 interceptive effect Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000002790 cross-validation Methods 0.000 claims description 3
- 235000013312 flour Nutrition 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000006872 improvement Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 241000894007 species Species 0.000 description 3
- 238000010200 validation analysis Methods 0.000 description 3
- RSWGJHLUYNHPMX-UHFFFAOYSA-N Abietic-Saeure Natural products C12CCC(C(C)C)=CC2=CCC2C1(C)CCCC2(C)C(O)=O RSWGJHLUYNHPMX-UHFFFAOYSA-N 0.000 description 2
- 235000005205 Pinus Nutrition 0.000 description 2
- 241000218602 Pinus <genus> Species 0.000 description 2
- KHPCPRHQVVSZAH-HUOMCSJISA-N Rosin Natural products O(C/C=C/c1ccccc1)[C@H]1[C@H](O)[C@@H](O)[C@@H](O)[C@@H](CO)O1 KHPCPRHQVVSZAH-HUOMCSJISA-N 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000009395 breeding Methods 0.000 description 2
- 230000001488 breeding effect Effects 0.000 description 2
- 210000004027 cell Anatomy 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 210000000020 growth cone Anatomy 0.000 description 2
- 238000009659 non-destructive testing Methods 0.000 description 2
- 239000005416 organic matter Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- KHPCPRHQVVSZAH-UHFFFAOYSA-N trans-cinnamyl beta-D-glucopyranoside Natural products OC1C(O)C(O)C(CO)OC1OCC=CC1=CC=CC=C1 KHPCPRHQVVSZAH-UHFFFAOYSA-N 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 241000208125 Nicotiana Species 0.000 description 1
- 235000002637 Nicotiana tabacum Nutrition 0.000 description 1
- 241000218641 Pinaceae Species 0.000 description 1
- 235000011613 Pinus brutia Nutrition 0.000 description 1
- 238000007605 air drying Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 239000006227 byproduct Substances 0.000 description 1
- 210000002421 cell wall Anatomy 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 230000007614 genetic variation Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000012770 industrial material Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 108700005457 microfibrillar Proteins 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The application discloses a method and a system for predicting slash pine microfiber filament angle by using near infrared spectrum technology: obtaining a slash pine sample wood core; obtaining original near infrared spectrum data and a micro-fiber angle measuring value of a slash pine sample wood core based on the slash pine sample wood core, and dividing the micro-fiber angle data and the original near infrared spectrum data into a correction set and an external verification set, wherein the property parameters of samples in the correction set are uniformly distributed; constructing a slash pine wood microfiber angle near-infrared prediction model based on the correction set; and substituting the external verification set near infrared spectrum data into the slash pine wood microfiber angle near infrared prediction model to obtain a predicted value, and finishing the evaluation of the slash pine microfiber angle prediction model prediction level by comparing the difference between the external verification set microfiber angle predicted value and the measured value. By establishing a prediction model of the angle of the slash pine microfibrils, the measurement of the angle property data of the slash pine microfibrils in a multi-site area becomes possible.
Description
Technical Field
The application belongs to the field of near infrared spectrum prediction, and particularly relates to a method and a system for predicting slash pine microfiber filament angles by using a near infrared spectrum technology.
Background
Slash pine (Pinus elliottii Engelm) is a tree of the genus Pinus of the family pinaceae, native to the southeast united states, and one of the most important coniferous tree species in the genus Pinus of the world. The slash pine has been introduced in China for over 70 years, is a main tree species of industrial raw material forests in collective forest areas in south China, has rapid growth, strong adaptability and high wood utilization value, can be used as various industrial materials, building materials and pulp materials, and can also produce forest by-products such as high-quality rosin, rosin and the like, so that the slash pine is widely planted as a main tree species of industrial artificial forests in subtropical and tropical areas of the world.
Near Infrared Spectroscopy (NIRS) is a green nondestructive testing technology, can rapidly, simply and accurately perform nondestructive testing on organic matter samples in various states, such as powder, solid, liquid and other organic matter samples, and is widely applied to the fields of papermaking, agriculture, food, tobacco and the like. In recent years, the near infrared spectrum technology has also gained attention of forestry workers, and is gradually applied to detection of timber properties.
The microfibril angle (MFA) is an angle between the direction of microfibrils in the S2 layer of the wood cell wall and the principal axis of the cell, and the smaller the microfibril angle, the greater the cell tensile strength, which is one of the determinants of the mechanical properties of wood, and affects the elastic modulus and anisotropic shrinkage of wood, and is also related to the wood density. The microfiber filament angle is an important parameter for evaluating indexes of the wood, such as pressure resistance, tensile strength, bending resistance and the like, and has great influence on wood drying and shrinkage, so that the microfiber filament angle also has influence on the physical and mechanical properties of the wood. Studies have shown that the microfibril angle is inversely proportional to the wood strength, i.e. the smaller the value of the microfibril angle, the higher the wood strength. Therefore, the measurement of the microfibril angle of the slash pine wood is of great significance to the quality inspection and effective use of the slash pine wood.
The traditional wood microfibril angle detection method is a microscope technology method, but microfibrils are arranged in a three-dimensional mode, and a two-dimensional microfibril angle is observed in a microscope, so that the microfibril angle measured by the method is poor in accuracy, low in efficiency and high in technical requirements on experimental operators. In order to improve the production efficiency, an efficient and accurate slash pine microfiber filament angle prediction method is sought, and the method has important significance for slash pine material genetic improvement.
Disclosure of Invention
In order to solve the technical problems, the application provides a method and a system for predicting the wood microfiber angle of slash pine by using a near infrared spectrum technology, and the rapid and accurate determination of the wood microfiber angle of slash pine large-scale breeding groups is completed by establishing a prediction model of the slash pine microfiber angle.
In order to achieve the above object, the present application provides the following solutions:
a method for predicting slash pine microfiber filament angle by using near infrared spectrum technology comprises the following steps:
obtaining a slash pine sample wood core;
obtaining original near infrared spectrum data and a micro-fiber angle measurement value of the slash pine sample wood core based on the slash pine sample wood core, and dividing the micro-fiber angle data and the original near infrared spectrum data into a correction set and an external verification set, wherein the property parameters of the correction set samples are uniformly distributed;
constructing a slash pine wood microfiber angle near-infrared prediction model based on the correction set;
and substituting the external verification set near infrared spectrum data into the slash pine wood microfiber angle near infrared prediction model to obtain a predicted value, and finishing the evaluation of the slash pine microfiber angle prediction model prediction level by comparing the difference between the external verification set microfiber angle predicted value and the measured value.
Preferably, the method of obtaining a microfibrillar angle measurement of the wood core of the slash pine sample comprises:
the slash pine sample wood core was measured by a silverscan wood measurement system to obtain the microfiber angle measurement.
Preferably, the method of obtaining said raw near infrared spectral data comprises:
crushing the wood core of the slash pine sample into fine wood powder;
screening the wood powder fine powder, and selecting the wood powder fine powder of 40-60 meshes meeting the preset requirement as a sample to be detected;
and performing spectrum scanning on the sample to be detected by using a Fourier near infrared spectrometer to obtain the original near infrared spectrum data.
Preferably, when the Fourier near-infrared spectrometer is used for carrying out spectrum scanning on the sample to be detected, the Fourier near-infrared spectrometer needs to be set to be 15000-4000cm -1 And scanning the samples to be detected within the range, wherein the resolution ratio is 8, each sample to be detected is scanned for 5 times, and the sample loading is repeated for 5 times to obtain an average value.
Preferably, the method for constructing the slash pine wood microfiber filament angle near-infrared prediction model comprises the following steps:
importing the original near infrared Spectrum data of the correction set into chemometrics software PerkinElmer Spectrum Quant10, and performing data processing on the original near infrared Spectrum data by adopting a second derivative;
and associating the measured values of the microfibril angle of the correction set with the near infrared spectrum data to complete fitting based on a method combining a partial least square method and a leave-one-out interactive verification method, and constructing the near infrared prediction model of the microfibril angle of the slash pine wood.
Preferably, in the process of building the slash pine wood microfiber angle near-infrared prediction model, abnormal samples in the slash pine wood microfiber angle near-infrared prediction model are removed according to the residual influence graph and the residual distribution graph, so that the prediction accuracy of the model is improved.
Preferably, in the process of constructing the slash pine microfiber angle near-infrared prediction model, the optimal principal component number is determined based on the minimum root mean square error of interactive verification.
Preferably, the external validation of the near-infrared prediction model of slash pine microfiber filament angle is accomplished by the steps comprising:
obtaining a near-infrared original spectrogram based on the original near-infrared spectrum data of the external verification set;
inputting the external verification set near-infrared spectrogram into the slash pine microfiber angle near-infrared prediction model to obtain a predicted value; comparing the linear relation and the residual value of the predicted value and the measured value of the external verification set microfiber filament angle;
and obtaining the actual measurement capability of the slash pine wood microfiber angle near-infrared prediction model based on the linear relation and the residual value.
On the other hand, the invention also discloses a system for predicting the micro-fiber angle of the slash pine by using the near infrared spectrum technology, which comprises a slash pine sample wood core acquisition module, a data acquisition and division module, a model construction module and an external verification module;
the slash pine sample wood core obtaining module is used for obtaining slash pine sample wood cores;
the data acquisition and division module is used for acquiring original near infrared spectrum data and a micro-fiber angle measurement value of the slash pine sample wood core based on the slash pine sample wood core, and dividing the micro-fiber angle measurement value and the original near infrared spectrum data into a correction set and an external verification set, wherein the property parameters of samples in the correction set are uniformly distributed;
the model construction module is used for constructing a slash pine wood microfiber filament angle near-infrared prediction model based on the correction set;
and the external verification module is used for substituting the external verification set near infrared spectrum data into the slash pine wood micro-fiber angle near infrared prediction model to obtain a predicted value, and finishing the evaluation of the prediction level of the slash pine micro-fiber angle prediction model by comparing the difference between the predicted value and the measured value of the external verification set micro-fiber angle.
The beneficial effect of this application does: the method for predicting the wood microfibril angle of the slash pine by using the near infrared spectrum technology greatly saves manpower, material resources and time, enables the measurement of the wood property data of the slash pine microfibril in a multi-site region to be possible, and has important significance for summarizing the genetic variation rule of the wood property characters of large-scale breeding populations and improving the efficiency of wood property genetic improvement work. The method and the device have wide popularization space and use value.
Drawings
In order to more clearly illustrate the technical solution of the present application, the drawings needed to be used in the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for a person skilled in the art to obtain other drawings without any inventive exercise.
FIG. 1 is a flow chart of a method for predicting slash pine microfiber filament angle using near infrared spectroscopy in an embodiment of the present application;
FIG. 2 is a raw spectrum of a sample of slash pine core according to an embodiment of the present application;
FIG. 3 is a graph of the normal pp of the microfiber filament angles of a calibration set sample according to an embodiment of the present invention;
FIG. 4 is a diagram showing the modeling result of the microfiber angle before abnormal samples are removed from the slash pine microfiber angle near-infrared prediction model in the embodiment of the present application;
FIG. 5 is a graph showing the effect of the residual error of the slash pine microfiber filament angle near-infrared prediction model according to an embodiment of the present invention;
FIG. 6 is a graph of the slash pine microfiber filament angle near-infrared prediction model residual error distribution according to a first embodiment of the present invention;
FIG. 7 is a graph showing the results of correcting the microfiber filament angle of slash pine wood according to the present invention;
FIG. 8 is a graph of cross-validation root mean square error RMSECV as a function of principal component count for a microfiber angle near infrared prediction model in accordance with an embodiment of the present application;
FIG. 9 is a graph of the results of an external validation set of microfiber filament angle predictions according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, the present application is described in further detail with reference to the accompanying drawings and the detailed description.
The first embodiment is as follows:
as shown in fig. 1, an embodiment of the present application is a method for predicting the angle of microfibrils of slash pine by near infrared spectroscopy:
in the embodiment, the slash pine core sample used in the model building process is taken from a slash pine artificial test forest in the Baiyunshan forest farm in Jian city in the middle of Jiangxi province, and is realized by adopting the following steps:
1. method for determining and sampling slash pine sample wood core
In the embodiment, the slash pine core samples used in the modeling are taken from the white cloud mountain forest farm in Jian city in the middle of Jiangxi province, 20 families are selected for research in slash pine artificial forests of 112 families which grow in 28 years according to the preservation rate results of different families, and 4-6 sample trees are selected from each family, and the total number of the sample trees is 100. Sampling at the position of 1.3m of the chest height of a selected sample wood by using a growth cone with an inner diameter opening of 12mm, wherein the growth cone is required to take a complete wood core from the south phloem to the north phloem, and 100 wood cores are taken in the total cone. And numbering the sample cores taken out in sequence, putting the sample cores into a wood groove capable of preventing the sample cores from deforming, and taking the sample cores back to a laboratory for air drying.
2. Determination of microfiber filament angle data
Dividing 100 slash pine sample wood cores into a south section and a north section from a pith position, wherein the south slash pine sample wood core is used for a SillviScan microfiber silk angle, and the north slash pine sample wood core is reserved for near infrared spectrum scanning. The measurement of the microfibril angle of the wood core of the slash pine sample was measured by an X-ray diffractometer of silverscan with a scanning step of 0.1mm.
3. Method for collecting original near infrared spectrum of slash pine sample wood core
(1) Preparing a slash pine sample: 100 northbound wood cores of the sample wood are crushed into fine wood powder by a crusher, the fine powder is sieved by a 40-60-mesh sieve, the fine wood powder meeting the preset requirements is selected as a sample to be tested, and the sample is filled into a self-sealing bag for later use. Before scanning, a sample to be detected is placed in a laboratory where a near-infrared spectrometer is located for more than 24 hours, and the purpose is to enable the environmental conditions of the sample to be detected and an instrument to be consistent, and reduce errors.
(2) Scanning of slash pine samples: in this study, a Fourier near infrared spectrometer was used, manufactured by Perkinelmer, USA. Before scanning the sample, the instrument is started to preheat for 30min, and after the sample is stabilized, scanning is carried out. When collecting original near infrared spectrum, blank calibration is carried out by a white board, and then a sample to be measured is placed in a sampling glass bottle at 15000-4000cm -1 The sample to be tested is scanned within the range, the resolution is 8, the indoor temperature is about 27 ℃, and the air humidity is 40-60%. Each sample was scanned 5 times, the sample was loaded 5 times repeatedly and the average was taken and the original near infrared spectral data was collected. The rotary sample table is adopted to scan the wood powder fine powder so as to increase the scanning area and reduce the error. And scanning by adopting a diffuse reflection spectrum to analyze the wood powder with different fineness. The near infrared original spectrum of the slash pine wood flour sample can be obtained as shown in FIG. 2.
4. Establishing a slash pine wood microfiber angle near-infrared prediction model:
(1) The method comprises the steps of taking 27 samples from 100 slash pine sample cores by adopting a random selection method to serve as an external verification set, taking the rest 73 samples as a modeling correction set, wherein specific statistical information of microfiber angle data corresponding to each sample set is shown in table 1, so that the microfiber angle distribution range corresponding to the correction set and the external verification set is wide, the coverage is strong, and the microfiber angle range corresponding to the correction set samples is larger than that of the external verification set. As can be seen from Table 1, the coefficient of variation is less than 20%, which indicates that the microfibril angle character belongs to weak variation and has strong internal stability, so that the microfibril angle of slash pine wood has strong screening potential and is necessary to research and analyze.
TABLE 1
(2) FIG. 3 is a normal analysis diagram of the microfiber filament angle of the calibration set sample, wherein the closer the calibration set sample is to the trend line, the better the normal distribution effect of the sample is. As can be seen from FIG. 3, the microfiber angles of the calibration set samples are uniformly distributed near the trend line, which indicates that the calibration set samples are all in accordance with normal distribution. The analysis shows that the sample of the slash pine wood microfiber filament angle has larger representativeness and meets the requirements of modeling samples.
(3) The raw near infrared spectra collected were imported into the chemometrics software PerkinElmer Spectrum Quant10, and the data pre-processed using the second derivative. Based on the combination of Partial Least Squares (PLS) and interactive verification, the measured values of the microfibril angle obtained by SiliviScan measurement are associated with the near infrared spectrum data of the correction set for fitting, and the near infrared prediction model of the microfibril angle of the slash pine wood is obtained through regression analysis and is shown in figure 4. And judging whether the sample of the correction set belongs to an abnormal value or not according to the residual influence graph and the residual distribution graph, and if the sample has larger influence or more deviated residual, determining the sample as the abnormal value sample. And eliminating the No. 2 and No. 36 samples according to the residual difference influence graph of the micro-fiber angle in the figure 5 and the residual difference distribution graph of the micro-fiber angle in the figure 6. Table 2 shows the difference in prediction ability before and after the removal of abnormal samples by the slash pine wood microfiber angle near infrared prediction model. Comparing the two properties before and after removing the abnormal value, determining a coefficient R 2 With an improvement of 0.0229, the corrected root mean square error RMSEC decreased by 0.1389. After the abnormal sample is removed, the accuracy of the model is effectively improved.
TABLE 2
The final near-infrared prediction model of the slash pine wood microfiber filament angle obtained after removing the abnormal samples is shown in fig. 7. As shown in FIG. 8, selection interaction verificationThe coefficient R of the model is determined when the number of principal components is 10 2 0.9117, the corrected root mean square error is 0.7662, and the cross-validation root mean square error is 1.5784. The correction decision coefficient of the model is high, the corrected root mean square error and the interactive verification root mean square error are low, and the prediction effect of the model is good.
(4) And (3) verification of the model: after the slash pine wood microfiber filament angle near-infrared prediction model was built, it was externally validated with 27 samples of the external validation set to examine the predictive power of the model. The method comprises the steps of predicting an external verification set sample which does not participate in modeling by using a slash pine wood microfiber angle near-infrared correction model, comparing a linear relation and a residual value between a predicted value and a test value, and checking the actual measurement capability of the model as shown in figure 9. Table 3 shows the results of the individual plant property detection corresponding to the external verification set samples by the slash pine wood microfiber angle near-infrared calibration model. The result shows that the maximum error between the predicted value and the measured value of the microfiber filament angle is 1.24, and the coefficient R is determined 2 At 0.8002, the predicted rms error is 1.024, which is relatively close in value to the corrected rms error. The model has high prediction capability and can be used for detecting unknown samples.
TABLE 3
Example two:
the invention also provides a system for predicting the slash pine microfiber filament angle by using the near infrared spectrum technology, which comprises a slash pine sample wood core acquisition module, a data acquisition and division module, a model construction module and an external verification module;
the slash pine sample wood core obtaining module is used for obtaining slash pine sample wood cores;
the data acquisition and division module is used for acquiring original near infrared spectrum data and a micro-fiber angle measurement value of the slash pine sample wood core based on the slash pine sample wood core, and dividing the micro-fiber angle measurement value and the original near infrared spectrum data into a correction set and an external verification set, wherein the property parameters of samples in the correction set are uniformly distributed;
a method of obtaining microfibril angle data for a wood core of a slash pine sample comprising:
measuring the wood core of the slash pine sample by an X-ray diffractometer of SillviScan to obtain a measured value of the microfiber angle;
crushing a slash pine sample wood core into fine wood powder;
screening the wood powder fine powder, and selecting the wood powder fine powder which meets the preset requirement and has 40-60 meshes as a sample to be detected;
performing spectrum scanning on a sample to be detected by using a Fourier near infrared spectrometer to obtain original near infrared spectrum data;
when the Fourier near-infrared spectrometer is used for carrying out spectrum scanning on the sample to be detected, the Fourier near-infrared spectrometer needs to be set to be 15000-4000cm -1 And scanning the samples to be detected within the range, wherein the resolution is 8, each sample to be detected is scanned for 5 times, and the sample loading is repeated for 5 times to obtain an average value.
The model construction module is used for constructing a slash pine wood microfiber filament angle near-infrared prediction model based on the correction set;
importing the original near infrared Spectrum data of the correction set into a chemometrics software PerkinElmer Spectrum Quant10, and performing data processing on the original near infrared Spectrum data by adopting a second derivative;
and (3) associating the microfiber filament angle measured values of the correction set with near infrared spectrum data to complete fitting based on a method combining a partial least square method and a leave-one-out interactive verification method, and constructing a slash pine wood microfiber filament angle near infrared prediction model.
And the external verification module is used for substituting the external verification set near infrared spectrum data into the slash pine wood microfiber angle near infrared prediction model to obtain a predicted value, and finishing the evaluation of the prediction level of the slash pine microfiber angle prediction model by comparing the difference between the predicted value and the measured value of the external verification set microfiber angle.
The above-described embodiments are merely illustrative of the preferred embodiments of the present application, and do not limit the scope of the present application, and various modifications and improvements made to the technical solutions of the present application by those skilled in the art without departing from the spirit of the present application should fall within the protection scope defined by the claims of the present application.
Claims (9)
1. A method for predicting the microfibril angle of slash pine by using a near infrared spectrum technology is characterized by comprising the following steps of:
obtaining a slash pine sample wood core;
obtaining original near infrared spectrum data and a micro-fiber angle measurement value of the slash pine sample wood core based on the slash pine sample wood core, and dividing the micro-fiber angle measurement value and the original near infrared spectrum data into a correction set and an external verification set, wherein the property parameters of samples in the correction set are required to be uniformly distributed;
constructing a slash pine wood microfiber filament angle near-infrared prediction model based on the correction set;
and substituting the external verification set near infrared spectrum data into the slash pine wood microfiber angle near infrared prediction model to obtain a predicted value, and finishing the evaluation of the slash pine microfiber angle prediction model prediction level by comparing the difference between the predicted value and the measured value of the external verification set microfiber angle.
2. The method of claim 1, wherein obtaining a determination of the microfibril angle of the slash pine core sample comprises:
measuring the slash pine sample wood core by a SillviScan wood measurement system to obtain the microfiber filament angle measurement.
3. The method of claim 1, wherein the method of obtaining the raw near infrared spectra data comprises:
crushing the wood core of the slash pine sample into fine wood powder;
screening the wood flour fine powder, and selecting the wood flour fine powder which meets the preset requirement and has 40-60 meshes as a sample to be detected;
and performing spectrum scanning on the sample to be detected by using a Fourier near infrared spectrometer to obtain the original near infrared spectrum data.
4. A method of predicting slash pine microfiber filament angle using near infrared spectroscopy according to claim 3,
when the Fourier near-infrared spectrometer is used for carrying out spectrum scanning on the sample to be detected, the Fourier near-infrared spectrometer needs to be set to be 15000-4000cm -1 And scanning the samples to be detected within the range, wherein the resolution is 8, scanning each sample to be detected for 5 times, repeatedly loading the samples for 5 times, and taking an average value.
5. The method of claim 1, wherein the method of constructing the slash pine wood microfiber angle near infrared correction model comprises:
importing the original near infrared Spectrum data of the correction set into chemometrics software PerkinElmer Spectrum Quant10, and performing data processing on the original near infrared Spectrum data by adopting a second derivative;
and associating the measured values of the microfibril angle of the correction set with the near infrared spectrum data to complete fitting based on a method combining a partial least square method and a leave-one-out interactive verification method, and constructing the near infrared prediction model of the microfibril angle of the slash pine wood.
6. The method for predicting slash pine microfiber filament angle by using near infrared spectrum technology as claimed in claim 5, wherein during the building process of the slash pine wood microfiber filament angle near infrared prediction model, abnormal samples in the slash pine microfiber filament angle near infrared prediction model are removed according to the residual error influence map and the residual error distribution map, so that the prediction accuracy of the model is improved.
7. The method of claim 5, wherein the optimal number of principal components is determined based on the minimum root mean square error of cross-validation during the construction of the NIR prediction model of the angle of the slash pine microfibrils.
8. The method of claim 1, wherein externally validating the near infrared prediction model of slash pine microfiber filament angle is accomplished by using near infrared spectroscopy, comprising the steps of:
obtaining a near-infrared original spectrogram based on the original near-infrared spectrum data of the external verification set;
inputting the external verification set near-infrared spectrogram into the slash pine microfiber angle near-infrared prediction model to obtain a predicted value; comparing the linear relation and the residual value of the predicted value of the external verification set microfiber angle with the measured value thereof;
and obtaining the actual measurement capability of the slash pine wood microfiber filament angle near-infrared prediction model based on the linear relation and the residual value.
9. A system for predicting slash pine microfiber angles by using a near infrared spectrum technology is characterized by comprising a slash pine sample wood core acquisition module, a data acquisition and division module, a model construction module and an external verification module;
the slash pine sample wood core obtaining module is used for obtaining slash pine sample wood cores;
the data acquisition and division module is used for acquiring original near infrared spectrum data and a micro-fiber angle measurement value of the slash pine sample wood core based on the slash pine sample wood core, and dividing the micro-fiber angle measurement value and the original near infrared spectrum data into a correction set and an external verification set, wherein the property parameters of samples in the correction set are uniformly distributed;
the model construction module is used for constructing a slash pine wood microfiber filament angle near-infrared prediction model based on the correction set;
and the external verification module is used for substituting the external verification set near infrared spectrum data into the slash pine wood microfiber angle near infrared prediction model to obtain a predicted value, and finishing the evaluation of the prediction level of the slash pine microfiber angle prediction model by comparing the difference between the predicted value and the measured value of the external verification set microfiber angle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211000719.6A CN115372311B (en) | 2022-08-19 | 2022-08-19 | Method and system for predicting wet land loose microfibril angle by near infrared spectrum technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211000719.6A CN115372311B (en) | 2022-08-19 | 2022-08-19 | Method and system for predicting wet land loose microfibril angle by near infrared spectrum technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115372311A true CN115372311A (en) | 2022-11-22 |
| CN115372311B CN115372311B (en) | 2023-06-23 |
Family
ID=84065022
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211000719.6A Active CN115372311B (en) | 2022-08-19 | 2022-08-19 | Method and system for predicting wet land loose microfibril angle by near infrared spectrum technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115372311B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104132910A (en) * | 2014-08-15 | 2014-11-05 | 华南农业大学 | Method for predicating length of pinus taeda wood fibers by using near infrared spectrum technology |
| CN104142311A (en) * | 2014-08-15 | 2014-11-12 | 华南农业大学 | Method for predicting yield of rosin in loblolly pine by using near infrared spectrum technology |
| CN104155264A (en) * | 2014-08-15 | 2014-11-19 | 华南农业大学 | Method for predicting content of turpentine in loblolly pine gum by using near infrared spectroscopy |
| CN105158195A (en) * | 2015-09-29 | 2015-12-16 | 中国林业科学研究院林产化学工业研究所 | Method for rapidly determining holocellulose content of pulping material based on near-infrared spectrum technology |
| CN105181639A (en) * | 2015-09-29 | 2015-12-23 | 中国林业科学研究院林产化学工业研究所 | Method for quickly determining content of pentosan in broad-leaved wood based on near infrared spectrum technology |
| CN105223102A (en) * | 2015-09-29 | 2016-01-06 | 中国林业科学研究院林产化学工业研究所 | A kind of method utilizing Near Infrared Spectroscopy for Rapid slurrying material basic density |
| CN105352909A (en) * | 2015-09-29 | 2016-02-24 | 中国林业科学研究院林产化学工业研究所 | Method for rapid determination of pulping material extraction matter content on basis of near infrared spectroscopy technology |
| CN106442382A (en) * | 2016-07-15 | 2017-02-22 | 中国林业科学研究院热带林业研究所 | Method for rapid prediction of Eucapyptus urophylla * E. tereticornis wood basic density |
| WO2018010352A1 (en) * | 2016-07-11 | 2018-01-18 | 上海创和亿电子科技发展有限公司 | Qualitative and quantitative combined method for constructing near infrared quantitative model |
-
2022
- 2022-08-19 CN CN202211000719.6A patent/CN115372311B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104132910A (en) * | 2014-08-15 | 2014-11-05 | 华南农业大学 | Method for predicating length of pinus taeda wood fibers by using near infrared spectrum technology |
| CN104142311A (en) * | 2014-08-15 | 2014-11-12 | 华南农业大学 | Method for predicting yield of rosin in loblolly pine by using near infrared spectrum technology |
| CN104155264A (en) * | 2014-08-15 | 2014-11-19 | 华南农业大学 | Method for predicting content of turpentine in loblolly pine gum by using near infrared spectroscopy |
| CN105158195A (en) * | 2015-09-29 | 2015-12-16 | 中国林业科学研究院林产化学工业研究所 | Method for rapidly determining holocellulose content of pulping material based on near-infrared spectrum technology |
| CN105181639A (en) * | 2015-09-29 | 2015-12-23 | 中国林业科学研究院林产化学工业研究所 | Method for quickly determining content of pentosan in broad-leaved wood based on near infrared spectrum technology |
| CN105223102A (en) * | 2015-09-29 | 2016-01-06 | 中国林业科学研究院林产化学工业研究所 | A kind of method utilizing Near Infrared Spectroscopy for Rapid slurrying material basic density |
| CN105352909A (en) * | 2015-09-29 | 2016-02-24 | 中国林业科学研究院林产化学工业研究所 | Method for rapid determination of pulping material extraction matter content on basis of near infrared spectroscopy technology |
| WO2018010352A1 (en) * | 2016-07-11 | 2018-01-18 | 上海创和亿电子科技发展有限公司 | Qualitative and quantitative combined method for constructing near infrared quantitative model |
| CN106442382A (en) * | 2016-07-15 | 2017-02-22 | 中国林业科学研究院热带林业研究所 | Method for rapid prediction of Eucapyptus urophylla * E. tereticornis wood basic density |
Non-Patent Citations (2)
| Title |
|---|
| 孙柏玲 等: "近红外光谱法在慈竹微纤丝角和纤维长度分析中的应用" * |
| 赵荣军 等: "基于近红外光谱技术预测径/弦切面粗皮桉木材微纤丝角" * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115372311B (en) | 2023-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108680515B (en) | Single-grain rice amylose quantitative analysis model construction and detection method thereof | |
| CN106706553A (en) | Method for quick and non-destructive determination of content of amylase in corn single grains | |
| CN109211829A (en) | A method of moisture content in the near infrared spectroscopy measurement rice based on SiPLS | |
| CN108732127B (en) | Method for detecting mixing proportion of each component in cut tobacco | |
| CN104142311B (en) | A kind of method of near-infrared spectrum technique prediction torch pine pine resin yield | |
| CN111855590A (en) | Remote sensing inversion model and method for rice leaf starch accumulation | |
| CN104155264A (en) | Method for predicting content of turpentine in loblolly pine gum by using near infrared spectroscopy | |
| CN111829965A (en) | Remote sensing inversion model and method for starch accumulation amount of rice overground part | |
| CN106383094A (en) | Method for fast testing contents of chemical ingredients in Eucalyptus urophylla*E. tereticornis wood | |
| CN102937575B (en) | Watermelon sugar degree rapid modeling method based on secondary spectrum recombination | |
| CN104596979A (en) | Method for measuring cellulose of reconstituted tobacco by virtue of near infrared reflectance spectroscopy technique | |
| CN108627468A (en) | A kind of prediction technique of feeding Boehmeria nivea leaves crude fiber content | |
| CN111855593A (en) | Remote sensing inversion model and method for starch content of rice leaf | |
| CN104596975A (en) | Method for measuring lignin of reconstituted tobacco by paper-making process by virtue of near infrared reflectance spectroscopy technique | |
| CN104255118A (en) | Rapid lossless testing method based on near infrared spectroscopy technology for paddy rice seed germination percentage | |
| CN104899424A (en) | Microscopic feature based method for objectively testing ripeness and leaf structure of flue-cured tobacco leaves | |
| CN104316492A (en) | Method for near-infrared spectrum measurement of protein content in potato tuber | |
| CN104132865A (en) | Method for predicting density of wood of loblolly pine by utilizing near-infrared spectrum technology | |
| CN109540837A (en) | The method that near-infrared quickly detects Boehmeria nivea leaves wood fibre cellulose content | |
| CN110470629A (en) | A kind of Near-Infrared Quantitative Analysis method of moisture and oil content in tea seed | |
| CN113655027A (en) | Method for rapidly detecting tannin content in plant by near infrared | |
| CN106706554A (en) | Method for rapidly and nondestructively determining content of straight-chain starch of corn single-ear grains | |
| CN103411895A (en) | Near infrared spectrum identification method of adulteration of pearl powder | |
| CN113176227A (en) | Method for rapidly predicting adulteration of dendrobium huoshanense in dendrobium hunan | |
| CN106323796B (en) | Method for determining content of chemical components of lignocellulose plant by using thermogravimetric analyzer |
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 |