CN105823752B - The method that near infrared spectroscopy quickly differentiates edible oil type - Google Patents
The method that near infrared spectroscopy quickly differentiates edible oil type Download PDFInfo
- Publication number
- CN105823752B CN105823752B CN201610162211.4A CN201610162211A CN105823752B CN 105823752 B CN105823752 B CN 105823752B CN 201610162211 A CN201610162211 A CN 201610162211A CN 105823752 B CN105823752 B CN 105823752B
- Authority
- CN
- China
- Prior art keywords
- edible oil
- acid content
- oil sample
- near infrared
- sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000008157 edible vegetable oil Substances 0.000 title claims abstract description 135
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000004497 NIR spectroscopy Methods 0.000 title claims abstract description 17
- IPCSVZSSVZVIGE-UHFFFAOYSA-N hexadecanoic acid Chemical compound CCCCCCCCCCCCCCCC(O)=O IPCSVZSSVZVIGE-UHFFFAOYSA-N 0.000 claims abstract description 94
- 235000021314 Palmitic acid Nutrition 0.000 claims abstract description 48
- WRIDQFICGBMAFQ-UHFFFAOYSA-N (E)-8-Octadecenoic acid Natural products CCCCCCCCCC=CCCCCCCC(O)=O WRIDQFICGBMAFQ-UHFFFAOYSA-N 0.000 claims abstract description 47
- LQJBNNIYVWPHFW-UHFFFAOYSA-N 20:1omega9c fatty acid Natural products CCCCCCCCCCC=CCCCCCCCC(O)=O LQJBNNIYVWPHFW-UHFFFAOYSA-N 0.000 claims abstract description 47
- QSBYPNXLFMSGKH-UHFFFAOYSA-N 9-Heptadecensaeure Natural products CCCCCCCC=CCCCCCCCC(O)=O QSBYPNXLFMSGKH-UHFFFAOYSA-N 0.000 claims abstract description 47
- ZQPPMHVWECSIRJ-UHFFFAOYSA-N Oleic acid Natural products CCCCCCCCC=CCCCCCCCC(O)=O ZQPPMHVWECSIRJ-UHFFFAOYSA-N 0.000 claims abstract description 47
- 239000005642 Oleic acid Substances 0.000 claims abstract description 47
- QXJSBBXBKPUZAA-UHFFFAOYSA-N isooleic acid Natural products CCCCCCCC=CCCCCCCCCC(O)=O QXJSBBXBKPUZAA-UHFFFAOYSA-N 0.000 claims abstract description 47
- WQEPLUUGTLDZJY-UHFFFAOYSA-N n-Pentadecanoic acid Natural products CCCCCCCCCCCCCCC(O)=O WQEPLUUGTLDZJY-UHFFFAOYSA-N 0.000 claims abstract description 47
- ZQPPMHVWECSIRJ-KTKRTIGZSA-N oleic acid Chemical compound CCCCCCCC\C=C/CCCCCCCC(O)=O ZQPPMHVWECSIRJ-KTKRTIGZSA-N 0.000 claims abstract description 47
- OYHQOLUKZRVURQ-HZJYTTRNSA-N Linoleic acid Chemical compound CCCCC\C=C/C\C=C/CCCCCCCC(O)=O OYHQOLUKZRVURQ-HZJYTTRNSA-N 0.000 claims abstract description 43
- OYHQOLUKZRVURQ-IXWMQOLASA-N linoleic acid Natural products CCCCC\C=C/C\C=C\CCCCCCCC(O)=O OYHQOLUKZRVURQ-IXWMQOLASA-N 0.000 claims abstract description 43
- 235000020778 linoleic acid Nutrition 0.000 claims abstract description 43
- 238000001228 spectrum Methods 0.000 claims abstract description 35
- 238000005457 optimization Methods 0.000 claims abstract description 23
- 238000002329 infrared spectrum Methods 0.000 claims abstract description 22
- 241000894007 species Species 0.000 claims description 42
- 239000003921 oil Substances 0.000 claims description 13
- 235000019198 oils Nutrition 0.000 claims description 13
- 235000019483 Peanut oil Nutrition 0.000 claims description 11
- 235000019484 Rapeseed oil Nutrition 0.000 claims description 11
- 235000019486 Sunflower oil Nutrition 0.000 claims description 11
- 239000010495 camellia oil Substances 0.000 claims description 11
- 239000000312 peanut oil Substances 0.000 claims description 11
- 239000003549 soybean oil Substances 0.000 claims description 11
- 235000012424 soybean oil Nutrition 0.000 claims description 11
- 239000002600 sunflower oil Substances 0.000 claims description 11
- 239000002245 particle Substances 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000000691 measurement method Methods 0.000 claims description 4
- 230000032050 esterification Effects 0.000 claims description 3
- 238000005886 esterification reaction Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 239000002253 acid Substances 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 239000006228 supernatant Substances 0.000 claims description 2
- 238000005259 measurement Methods 0.000 claims 1
- 239000000047 product Substances 0.000 claims 1
- 238000001514 detection method Methods 0.000 abstract description 4
- 230000001737 promoting effect Effects 0.000 abstract description 2
- 239000000523 sample Substances 0.000 description 69
- 238000011156 evaluation Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 238000003556 assay Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 239000006101 laboratory sample Substances 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 230000000050 nutritive effect Effects 0.000 description 1
- 150000002943 palmitic acids Chemical class 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 230000007115 recruitment Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
- G01N21/17—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
- G01N21/3577—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing liquids, e.g. polluted water
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 invention discloses a kind of methods that near infrared spectroscopy quickly differentiates edible oil type, include the following steps:Choose the edible oil sample of unknown type to be identified;Acquire the atlas of near infrared spectra of edible oil sample;The atlas of near infrared spectra of edible oil sample is pre-processed, the pre-processed spectrum figure of edible oil sample is obtained;According to the pre-processed spectrum figure of edible oil sample, palmitic acid quantitative model, oleic acid quantitative model, linoleic acid quantitative model is used to predict the palmitic acid content, oleic acid content, linoleic acid content of edible oil sample respectively successively;According to the palmitic acid content, oleic acid content, linoleic acid content of obtained edible oil sample, type discriminating is carried out to edible oil sample using optimization qualitative model.Near infrared spectroscopy provided by the invention quickly differentiates that the method safety of edible oil type is quick, detection is convenient, differentiates that accuracy rate is high, has stronger practical value and promotional value.
Description
Technical field
The present invention relates to rapid detection technical fields, and in particular to a kind of near infrared spectroscopy quickly differentiates edible oil type
Method.
Background technology
Edible oil contains the important nutritional ingredient there are many needed by human body, is also essential in our diet lives
, studies have shown that being rich in a large amount of palmitic acids, oleic acid content, linoleic acid in part edible oil, have in different types of edible oil
Different palmitic acid, oleic acid content, linoleic acid composition;In addition, since palmitic acid, oleic acid, linoleic content essentially dictate
The nutritive value of edible oil, therefore usually as the important component index of evaluation edible oil quality, while being also to determine its business valence
The important evidence of value.As edible oil price constantly improves, many illegal businessmans pretend to be low value oil to seek exorbitant profit
High value oil puts goods on the market, or low value oil is mixed in high value oil, and serious infringement consumer and legal production and sales enterprise
The interests of industry.Therefore, it is necessary to study a kind of methods of quick discriminating edible oil type, to safeguarding consumer and lawful operation person
Interests maintain edible oil market normal order to be of great significance.
Invention content
Shortcoming present in view of the above technology, the present invention provides one kind safely and fast, detection is convenient, differentiates accurate
The method that the true high near infrared spectroscopy of rate quickly differentiates edible oil type.
The technical solution adopted by the present invention to solve the technical problems is:A kind of near infrared spectroscopy quickly differentiates edible oil
The method of type, includes the following steps:Step 1: sample is chosen:Choose the edible oil sample of unknown type to be identified;Step
Two, spectra collection:The atlas of near infrared spectra of the edible oil sample for the unknown type chosen in acquisition step one;Step 3: spectrum
Pretreatment:The atlas of near infrared spectra of the edible oil sample of the unknown type acquired in step 2 is pre-processed, is obtained unknown
The pre-processed spectrum figure of the edible oil sample of type;Step 4: content prediction:According to the food of the unknown type obtained in step 3
With the pre-processed spectrum figure of oil samples, palmitic acid quantitative model, oleic acid quantitative model, linoleic acid quantitative model difference are used successively
Predict palmitic acid content, oleic acid content, the linoleic acid content of the edible oil sample of the unknown type;Step 5: type differentiates:
According to palmitic acid content, oleic acid content, the linoleic acid content of the edible oil sample of the unknown type obtained in step 4, adopt
Type discriminating is carried out to the edible oil sample of the unknown type with optimization qualitative model.
Preferably, the edible oil sample for the unknown type chosen in the step 1 be tea-seed oil, sunflower oil, soybean oil,
Any one in rapeseed oil, peanut oil.
Preferably, the spectra collection condition in the step 2 is as follows:The collecting temperature of edible oil sample is 60 ± 2 DEG C,
Near infrared ray ranging from 1350~1800 nm, scanning times 32 times, resolution ratio 3.5cm-1, measurement method is transmission,
Each edible oil sample takes the average value measured three times as the atlas of near infrared spectra finally acquired.
Preferably, the atlas of near infrared spectra of the edible oil sample of the unknown type of acquisition is carried out successively in the step 3
Standard normal variable changes and goes the combination algorithm pretreatment of trend technology, obtains the pretreatment light of the edible oil sample of unknown type
Spectrogram.
Preferably, the palmitic acid quantitative model, oleic acid quantitative model, the method for building up of linoleic acid quantitative model are as follows:
The edible oil sample of several different Known Species is collected, the edible oil sample of the difference Known Species includes:Tea-seed oil, sunflower
Oil, soybean oil, rapeseed oil and peanut oil;Acquire the atlas of near infrared spectra of the edible oil sample of several different Known Species, spectrum
Acquisition method carries out successively as described in step 2, and to the atlas of near infrared spectra of the edible oil sample of several different Known Species
Standard normal variable changes and goes the combination algorithm pretreatment of trend technology, obtains the edible oil sample of several different Known Species
Pre-processed spectrum figure;Palmitic acid content, oleic acid content, the linoleic acid of the edible oil sample of several different Known Species of measuring
Content;Established respectively using partial least-square regression method the edible oil sample of different Known Species pre-processed spectrum figure and its
The quantitative model of palmitic acid content, oleic acid content, linoleic acid content obtains palmitic acid quantitative model, oleic acid quantitative model, sub- oil
Sour quantitative model;Wherein, it is desirable that the root-mean-square error of palmitic acid quantitative model, oleic acid quantitative model and linoleic acid quantitative model is equal
≤ 10%, related coefficient is >=95%.
Preferably, palmitic acid content, oleic acid content, the sub- oil of the edible oil sample of several different Known Species of measuring
The method of acid content is as follows:Esterification method as defined in GB/T 17376-2008 eats Known Species according to national standards
Oil samples are pre-processed, and stand 24 hours after pretreatment, and the upper layer for taking out the edible oil sample of processed Known Species is clear
1 μ L of liquid are moved in gas chromatograph, are obtained gas chromatogram after 65~75 minutes after operation, are finally calculated according to gas chromatogram
Obtain the palmitic acid content, oleic acid content, linoleic acid content of the edible oil sample of different Known Species.
Preferably, the method for building up for optimizing qualitative model in the step 5 is as follows:Collect several different Known Species
Edible oil sample, it is described difference Known Species edible oil sample include:Tea-seed oil, sunflower oil, soybean oil, rapeseed oil and peanut
Oil;Palmitic acid content, oleic acid content, the linoleic acid content of the edible oil sample of several different Known Species of measuring;If will
Palmitic acid content, oleic acid content, linoleic acid content in the edible oil sample of dry different Known Species is as the defeated of qualitative model
Enter variable, the qualitative model of the edible oil sample of different Known Species is established by support vector machine classification method, and use grain
Subgroup optimization algorithm in qualitative model penalty factor and kernel functional parameter g optimize, obtain optimization qualitative model.
Preferably, using particle swarm optimization algorithm in qualitative model penalty factor and kernel functional parameter g optimize
When, the range that penalty factor and kernel functional parameter g is arranged is 2-10~210, ranging from the 2~8 of setting validation-cross parameter V.
Compared with prior art, the present invention advantage is:Near infrared spectroscopy provided by the invention quickly differentiates food
It can be to unknown by the palmitic acid quantitative model, oleic acid quantitative model and linoleic acid quantitative model of foundation with the method for oily type
Palmitic acid content, oleic acid content, linoleic acid content in the edible oil sample of type carry out fast prediction;Mould is calibrated by optimization
Type can carry out type discriminating to the edible oil sample of the unknown type of known palmitic acid content, oleic acid content, linoleic acid content;
The method that the near infrared spectroscopy quickly differentiates edible oil type, safely and fast, detection it is convenient, differentiate that accuracy rate is high, have compared with
Strong practical value and promotional value.
Description of the drawings
Fig. 1 is the flow diagram for the method that near infrared spectroscopy of the present invention quickly differentiates edible oil type;
Fig. 2 is the atlas of near infrared spectra of edible oil sample of the present invention;
Fig. 3 is the pre-processed spectrum figure of edible oil sample of the present invention;
Fig. 4 is particle swarm optimization algorithm optimizing result figure of the present invention;
Fig. 5 is the prediction identification result figure of edible oil forecast set sample of the present invention.
Specific implementation mode
Present invention will be described in further detail below with reference to the accompanying drawings, to enable those skilled in the art with reference to specification text
Word can be implemented according to this.
As shown in Figure 1, the present invention provides a kind of methods that near infrared spectroscopy quickly differentiates edible oil type, including such as
Lower step:
Step 1: sample is chosen:The edible oil sample of unknown type to be identified is chosen, the unknown type of selection is eaten
Oil samples are any one in tea-seed oil, sunflower oil, soybean oil, rapeseed oil, peanut oil;
Step 2: spectra collection:The atlas of near infrared spectra of the edible oil sample for the unknown type chosen in acquisition step one,
Spectra collection condition is as follows:The collecting temperature of edible oil sample is 60 ± 2 DEG C, near infrared ray ranging from 1350~1800
Nm, scanning times 32 times, resolution ratio 3.5cm-1, measurement method is transmission, and each edible oil sample takes what is measured three times to be averaged
Value is as the atlas of near infrared spectra finally acquired;
Step 3: Pretreated spectra:To the atlas of near infrared spectra of the edible oil sample of the unknown type acquired in step 2
Standard normal variable variation is carried out successively and goes the combination algorithm pretreatment of trend technology, obtains the edible oil sample of unknown type
Pre-processed spectrum figure;
Step 4: content prediction:According to the pre-processed spectrum figure of the edible oil sample of the unknown type obtained in step 3,
Palmitic acid quantitative model, oleic acid quantitative model, linoleic acid quantitative model is used to predict the edible of the unknown type respectively successively
Palmitic acid content, oleic acid content, the linoleic acid content of oil samples;
Wherein, the palmitic acid quantitative model, oleic acid quantitative model, the method for building up of linoleic acid quantitative model are as follows:It receives
Collect the edible oil sample of several different Known Species, the edible oil sample of the difference Known Species includes:Tea-seed oil, sunflower
Oil, soybean oil, rapeseed oil and peanut oil;Acquire the atlas of near infrared spectra of the edible oil sample of several different Known Species, spectrum
Acquisition method carries out successively as described in step 2, and to the atlas of near infrared spectra of the edible oil sample of several different Known Species
Standard normal variable changes and goes the combination algorithm pretreatment of trend technology, obtains the edible oil sample of several different Known Species
Pre-processed spectrum figure;Palmitic acid content, oleic acid content, the linoleic acid of the edible oil sample of several different Known Species of measuring
Content;Established respectively using partial least-square regression method the edible oil sample of different Known Species pre-processed spectrum figure and its
The quantitative model of palmitic acid content, oleic acid content, linoleic acid content obtains palmitic acid quantitative model, oleic acid quantitative model, sub- oil
Sour quantitative model;It is required that palmitic acid quantitative model, oleic acid quantitative model and linoleic acid quantitative model root-mean-square error≤
10%, related coefficient is >=95%;
Step 5: type differentiates:Contained according to the palmitic acid of the edible oil sample of the unknown type obtained in step 4
Amount, oleic acid content, linoleic acid content carry out type mirror using optimization qualitative model to the edible oil sample of the unknown type
Not;
Wherein, the method for building up for optimizing qualitative model is as follows:The edible oil sample of several different Known Species is collected, it is described
The edible oil sample of different Known Species includes:Tea-seed oil, sunflower oil, soybean oil, rapeseed oil and peanut oil;Measuring is several
Palmitic acid content, oleic acid content, the linoleic acid content of the edible oil sample of different Known Species;By several different Known Species
The input variable of palmitic acid content, oleic acid content, linoleic acid content as qualitative model in edible oil sample, by support to
Amount machine sorting technique establishes the qualitative model of the edible oil sample of different Known Species, and using particle swarm optimization algorithm to qualitative
Penalty factor and kernel functional parameter g in model optimize, and obtain optimization qualitative model;Using particle swarm optimization algorithm pair
When penalty factor and kernel functional parameter g in qualitative model optimize, the range of penalty factor and kernel functional parameter g is set
It is 2-10~210, ranging from the 2~8 of setting validation-cross parameter V.
Embodiment:
1, laboratory sample
Totally 133 parts of tea-seed oil, sunflower oil, soybean oil, rapeseed oil and five class edible oil sample of peanut oil are collected, using SPXY
Algorithm presses 3:1 ratio chooses 33 parts of 100 parts of edible oil calibration set sample and edible oil forecast set sample, and wherein edible oil corrects
Collect the foundation that sample is used for quantitative model and qualitative model, edible oil forecast set sample is used for the property of quantitative model and qualitative model
It is able to verify that;Wherein, distributed number such as the following table 1 of the forecast set sample and calibration set sample of five class edible oil samples.
Table 1
Type | Number | Forecast set | Calibration set | Subtotal |
Tea-seed oil | 1 | 6 | 15 | 21 |
Sunflower oil | 2 | 2 | 19 | 21 |
Soybean oil | 3 | 9 | 21 | 30 |
Rapeseed oil | 4 | 4 | 28 | 32 |
Peanut oil | 5 | 12 | 17 | 29 |
It is total | 33 | 100 | 133 |
2, experiment test
2.1 spectra collection
The atlas of near infrared spectra of 133 parts of edible oil samples is acquired using near infrared spectroscopy instrument, spectra collection condition is as follows:
Collecting temperature is 60 ± 2 DEG C, near infrared ray ranging from 1350~1800 nm, scanning times 32 times, and resolution ratio is
3.5cm-1, measurement method is transmission, and each edible oil sample takes the average value measured three times as the near infrared light finally acquired
The atlas of near infrared spectra of spectrogram, 133 parts of edible oil samples is as shown in Figure 2.
2.2 assay
Palmitic acid content, oleic acid content, the linoleic acid content of 133 parts of edible oil samples of measuring;Wherein, measuring
Method is as follows:Esterification method as defined in GB/T 17376-2008 pre-processes edible oil sample according to national standards, in advance
24 hours are stood after processing, and the 1 μ L of supernatant liquor for taking out processed edible oil sample are moved in gas chromatograph, wait for operation 65
Gas chromatogram is obtained after~75 minutes, the palmitic acid that 133 parts of edible oil samples are finally calculated according to gas chromatogram contains
Amount, oleic acid content, linoleic acid content.
3, Pretreated spectra
It is found by lot of experiments, carries out different pretreatments to spectrum before modeling, model performance is generated
Influence also differs widely, therefore preprocess method chooses the estimated performance and the scope of application for determining model;Using standard normal
Variable change and go trend technology combination algorithm can be used to eliminate the baseline drift of spectrum and the influence of light path to reach simplified
Model improves the purpose of its predictive ability;Fig. 3 is the pre-processed spectrum figure of 133 parts of edible oil samples.
4, the foundation of quantitative model
Established respectively using partial least-square regression method the pre-processed spectrum figure of edible oil sample and its palmitic acid content,
The quantitative model of oleic acid content, linoleic acid content obtains palmitic acid quantitative model, oleic acid quantitative model, linoleic acid quantitative model;
Model-evaluation index is as shown in table 2 below.
Table 2
5, the foundation of qualitative model
Using the palmitic acid content of 100 parts of edible oil calibration set samples, oleic acid content, linoleic acid content as qualitative model
Input variable establishes the qualitative model of edible oil calibration set sample by support vector machine classification method, and excellent using population
Change algorithm in qualitative model penalty factor and kernel functional parameter g optimize, obtain optimization qualitative model;Wherein, it uses
When particle swarm optimization algorithm optimizes penalty factor and kernel functional parameter g, parameter setting is as follows:Maximum evolutionary generation is set
It is 100, initial population number is set as 20, and Studying factors initial value is set as C1=1.5, C2=1.7, and evolutionary rate initial value is set as
0.6, evolutionary rate update coefficient of elasticity initial value is set as 1, and population recruitment speed coefficient of elasticity initial value is set as 1, validation-cross
Parameter V is set as 5, and the range of penalty factor and kernel functional parameter g are set as 2-10~210, optimization obtain when penalty factor=
When 204.7351 and kernel functional parameter g=23.7421, optimization qualitative model is to the discriminating accuracy rate of edible oil calibration set sample
100%;Wherein, particle swarm optimization algorithm optimizing result figure is as shown in Figure 4.
6, optimize the verification of qualitative model
By the palmitic acid content, oleic acid content, linoleic acid content of 33 parts of edible oil forecast set samples qualitative mould as an optimization
The input variable of type, using the optimization qualitative model pair when penalty factor=204.7351 and kernel functional parameter g=23.7421
The type of 33 parts of edible oil forecast set samples carries out prediction discriminating, and by the true of prediction result and 33 parts of edible oil forecast set samples
Real Genre categories are compared one by one, are obtained optimization qualitative model and are differentiated that accuracy rate is to the type of edible oil forecast set sample
100%;Wherein, the prediction identification result figure of 33 parts of edible oil forecast set samples is as shown in Figure 5.
Although the embodiments of the present invention have been disclosed as above, but it is not limited in listed fortune in specification and embodiments
With it can be fully applied to various fields suitable for the present invention, for those skilled in the art, can be easily real
Now other modification, therefore without departing from the general concept defined in the claims and the equivalent scope, the present invention is not limited to
Specific details and legend shown and described herein.
Claims (5)
1. a kind of method that near infrared spectroscopy quickly differentiates edible oil type, which is characterized in that include the following steps:
Step 1: sample is chosen:Choose the edible oil sample of unknown type to be identified;
Step 2: spectra collection:The atlas of near infrared spectra of the edible oil sample for the unknown type chosen in acquisition step one;
Step 3: Pretreated spectra:The atlas of near infrared spectra of the edible oil sample of the unknown type acquired in step 2 is carried out
Pretreatment, obtains the pre-processed spectrum figure of the edible oil sample of unknown type;
Step 4: content prediction:According to the pre-processed spectrum figure of the edible oil sample of the unknown type obtained in step 3, successively
Predict the edible oil sample of the unknown type respectively using palmitic acid quantitative model, oleic acid quantitative model, linoleic acid quantitative model
Palmitic acid content, oleic acid content, the linoleic acid content of product;
The palmitic acid quantitative model, oleic acid quantitative model, the method for building up of linoleic acid quantitative model are as follows:
The edible oil sample of several different Known Species is collected, the edible oil sample of the difference Known Species includes:Tea-seed oil,
Sunflower oil, soybean oil, rapeseed oil and peanut oil;
Acquire the atlas of near infrared spectra of the edible oil sample of several different Known Species, institute in spectra collection method such as step 2
It states, and standard normal variable variation is carried out successively to the atlas of near infrared spectra of the edible oil sample of several different Known Species and is gone
Trend technology is combined algorithm pretreatment, obtains the pre-processed spectrum figure of the edible oil sample of several different Known Species;
Palmitic acid content, oleic acid content, the linoleic acid content of the edible oil sample of several different Known Species of measuring, method
It is as follows:Esterification method as defined in GB/T 17376-2008 carries out the edible oil sample of Known Species pre- according to national standards
Processing, stands 24 hours, and the 1 μ L of supernatant liquor for taking out the edible oil sample of processed Known Species move to gas phase after pretreatment
In chromatograph, gas chromatogram is obtained after 65~75 minutes after operation, is finally calculated known to difference according to gas chromatogram
Palmitic acid content, oleic acid content, the linoleic acid content of the edible oil sample of type;
Established respectively using partial least-square regression method the edible oil sample of different Known Species pre-processed spectrum figure and its
The quantitative model of palmitic acid content, oleic acid content, linoleic acid content obtains palmitic acid quantitative model, oleic acid quantitative model, sub- oil
Sour quantitative model;Wherein, it is desirable that the root-mean-square error of palmitic acid quantitative model, oleic acid quantitative model and linoleic acid quantitative model is equal
≤ 10%, related coefficient is >=95%;
Step 5: type differentiates:According to palmitic acid content, the oil of the edible oil sample of the unknown type obtained in step 4
Acid content, linoleic acid content carry out type discriminating using optimization qualitative model to the edible oil sample of the unknown type;Optimization
The method for building up of qualitative model is as follows:
The edible oil sample of several different Known Species is collected, the edible oil sample of the difference Known Species includes:Tea-seed oil,
Sunflower oil, soybean oil, rapeseed oil and peanut oil;
Palmitic acid content, oleic acid content, the linoleic acid content of the edible oil sample of several different Known Species of measuring;
Using in the edible oil sample of several different Known Species palmitic acid content, oleic acid content, linoleic acid content is as qualitative
The input variable of model establishes the qualitative model of the edible oil sample of different Known Species by support vector machine classification method,
And using particle swarm optimization algorithm in qualitative model penalty factor and kernel functional parameter g optimize, obtain optimizing qualitative
Model.
2. the method that near infrared spectroscopy as described in claim 1 quickly differentiates edible oil type, which is characterized in that the step
The edible oil sample for the unknown type chosen in rapid one is arbitrary in tea-seed oil, sunflower oil, soybean oil, rapeseed oil, peanut oil
It is a kind of.
3. the method that near infrared spectroscopy as described in claim 1 quickly differentiates edible oil type, which is characterized in that the step
Spectra collection condition in rapid two is as follows:The collecting temperature of edible oil sample is 60 ± 2 DEG C, and near infrared ray is ranging from
1350~1800 nm, scanning times 32 times, resolution ratio 3.5cm-1, measurement method is transmission, and each edible oil sample takes three times
The average value of measurement is as the atlas of near infrared spectra finally acquired.
4. the method that near infrared spectroscopy as described in claim 1 quickly differentiates edible oil type, which is characterized in that the step
Standard normal variable variation is carried out successively to the atlas of near infrared spectra of the edible oil sample of the unknown type of acquisition in rapid three and is gone
Trend technology is combined algorithm pretreatment, obtains the pre-processed spectrum figure of the edible oil sample of unknown type.
5. the method that near infrared spectroscopy as described in claim 1 quickly differentiates edible oil type, which is characterized in that use grain
Subgroup optimization algorithm in qualitative model penalty factor and kernel functional parameter g optimize when, penalty factor and core are set
The range of function parameter g is 2-10~210, ranging from the 2~8 of setting validation-cross parameter V.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610162211.4A CN105823752B (en) | 2016-03-22 | 2016-03-22 | The method that near infrared spectroscopy quickly differentiates edible oil type |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610162211.4A CN105823752B (en) | 2016-03-22 | 2016-03-22 | The method that near infrared spectroscopy quickly differentiates edible oil type |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105823752A CN105823752A (en) | 2016-08-03 |
CN105823752B true CN105823752B (en) | 2018-10-12 |
Family
ID=56524149
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610162211.4A Active CN105823752B (en) | 2016-03-22 | 2016-03-22 | The method that near infrared spectroscopy quickly differentiates edible oil type |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105823752B (en) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107036999A (en) * | 2016-11-15 | 2017-08-11 | 天津工业大学 | A kind of five yuan of ready-mixed oil quantitative analysis methods based near infrared spectrum and Chemical Measurement |
CN108267424B (en) * | 2018-02-07 | 2021-04-27 | 武汉轻工大学 | Method for rapidly identifying type of edible oil based on multiple characteristic components |
CN108362659B (en) * | 2018-02-07 | 2021-03-30 | 武汉轻工大学 | Edible oil type rapid identification method based on multi-source spectrum parallel fusion |
CN108388965B (en) * | 2018-03-01 | 2021-10-26 | 武汉轻工大学 | Method for detecting adulteration content of grease, terminal equipment and computer readable storage medium |
CN108680595B (en) * | 2018-04-27 | 2020-11-03 | 上海理工大学 | Low-field magnetic resonance edible oil type detection method |
CN108645841B (en) * | 2018-08-24 | 2020-11-03 | 武汉轻工大学 | Sesame oil multi-component adulteration detection method based on Raman spectrum wavelet fusion |
CN109142265B (en) * | 2018-08-24 | 2021-02-19 | 武汉轻工大学 | Method for rapidly identifying type of edible oil by near infrared spectrum wavelet fusion |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102830087A (en) * | 2011-09-26 | 2012-12-19 | 武汉工业学院 | Method for quickly identifying food waste oils based on near infrared spectroscopy |
CN103293118A (en) * | 2013-05-11 | 2013-09-11 | 江南大学 | Hogwash oil identification method based on near infrared reflectance spectroscopy |
CN103398970A (en) * | 2013-07-24 | 2013-11-20 | 骆驰 | Method for qualitatively and quantitatively analyzing edible oil and further detecting hogwash oil |
CN103528986A (en) * | 2012-07-04 | 2014-01-22 | 佛山市技术标准研究院 | Method for identifying drainage oil based on finger-print technology |
CN104316486A (en) * | 2014-10-15 | 2015-01-28 | 闽江学院 | Method for rapidly screening unqualified vegetable oil |
-
2016
- 2016-03-22 CN CN201610162211.4A patent/CN105823752B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102830087A (en) * | 2011-09-26 | 2012-12-19 | 武汉工业学院 | Method for quickly identifying food waste oils based on near infrared spectroscopy |
CN103528986A (en) * | 2012-07-04 | 2014-01-22 | 佛山市技术标准研究院 | Method for identifying drainage oil based on finger-print technology |
CN103293118A (en) * | 2013-05-11 | 2013-09-11 | 江南大学 | Hogwash oil identification method based on near infrared reflectance spectroscopy |
CN103398970A (en) * | 2013-07-24 | 2013-11-20 | 骆驰 | Method for qualitatively and quantitatively analyzing edible oil and further detecting hogwash oil |
CN104316486A (en) * | 2014-10-15 | 2015-01-28 | 闽江学院 | Method for rapidly screening unqualified vegetable oil |
Non-Patent Citations (3)
Title |
---|
基于近红外光谱的食用油品质检测技术研究;李慧;《北京工商大学》;万方学术论文库;20130712;正文第9-10页及20-30页 * |
粒子群最小二乘支持向量机结合偏最小二乘法用于芝麻油质量的鉴别;毕艳兰,任小娜,彭丹,杨国龙,张林尚,汪学德;《分析化学研究报告》;20130922;第41卷(第9期);第1366-1372页 * |
红外光谱分析技术在食用植物油品质检测中的应用研究;代秀迎;《江苏大学》;万方学术论文数据库;20110803;正文第13-14页及20-34页 * |
Also Published As
Publication number | Publication date |
---|---|
CN105823752A (en) | 2016-08-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105823752B (en) | The method that near infrared spectroscopy quickly differentiates edible oil type | |
Vasconcelos et al. | Study of adulteration of extra virgin olive oil with peanut oil using FTIR spectroscopy and chemometrics | |
US20180052144A1 (en) | Method And Technique For Verification Of Olive Oil Composition | |
CN102735642B (en) | Method for quickly and losslessly identifying virgin olive oil and olive-residue oil | |
Fadzlillah et al. | FTIR spectroscopy combined with chemometric for analysis of sesame oil adulterated with corn oil | |
Li et al. | Authentication of pure camellia oil by using near infrared spectroscopy and pattern recognition techniques | |
Sherazi et al. | Main fatty acid classes in vegetable oils by SB-ATR-Fourier transform infrared (FTIR) spectroscopy | |
CN102590129B (en) | Method for detecting content of amino acid in peanuts by near infrared method | |
CN103217411A (en) | Raman-spectrum-based method for detecting content of oleic acid, linoleic acid and saturated fatty acid in edible vegetable oil | |
CN102221533B (en) | Method for quantitatively detecting adulteration of peanut oil based on ultraviolet spectrum | |
Pan et al. | a simple and portable screening method for adulterated olive oils using the hand‐held FTIR spectrometer and chemometrics tools | |
Zarezadeh et al. | Olive oil classification and fraud detection using E-nose and ultrasonic system | |
Gandhi et al. | Detection of coconut oil in ghee using ATR-FTIR and chemometrics | |
Kasemsumran et al. | Partial least squares processing of near‐infrared spectra for discrimination and quantification of adulterated olive oils | |
CN106596464A (en) | Near-infrared autocorrelation spectrum detection method for melamine doped in milk powder | |
Lu et al. | Fluorescence hyperspectral image technique coupled with HSI method to predict solanine content of potatoes | |
Mobaraki et al. | Structural characterization of carbonyl compounds by IR spectroscopy and chemometrics data analysis | |
Yuan et al. | Identification and detection of adulterated Camellia Oleifera Abel. Oils by near infrared transmittance spectroscopy | |
CN104297201A (en) | Method for quickly, accurately and quantitatively detecting ratio of various oil components in blend oil | |
CN110398472A (en) | A kind of vegetable oil identification classification method based on two-dimensional correlation spectra quantization | |
Taous et al. | Geographical classification of authentic Moroccan Argan oils and the rapid detection of soya and sunflower oil adulteration with ATR-FTIR spectroscopy and chemometrics | |
Amsaraj et al. | Support vector machine-based rapid detection and quantification of butter yellow adulteration in mustard oil using NIR spectra | |
Jamwal et al. | Non-targeted fingerprinting approach for rapid quantification of mustard oil adulteration with linseed oil: An economically motivated adulteration | |
Song et al. | Detection of aflatoxin B1 in peanut oil using attenuated total reflection fourier transform infrared spectroscopy combined with partial least squares discriminant analysis and support vector machine models | |
CN107121408A (en) | The quick nondestructive discrimination method of edible vegetable oil kind |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |