CN105588816A - Method for rapidly detecting melamine content in adulterated milk based on near infrared spectra - Google Patents

Method for rapidly detecting melamine content in adulterated milk based on near infrared spectra Download PDF

Info

Publication number
CN105588816A
CN105588816A CN201510941145.6A CN201510941145A CN105588816A CN 105588816 A CN105588816 A CN 105588816A CN 201510941145 A CN201510941145 A CN 201510941145A CN 105588816 A CN105588816 A CN 105588816A
Authority
CN
China
Prior art keywords
melamine
near infrared
content
milk
milk 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.)
Pending
Application number
CN201510941145.6A
Other languages
Chinese (zh)
Inventor
王铁军
史寒琴
惠建明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
New Hope Double Happiness Dairy (suzhou) Co Ltd
Original Assignee
New Hope Double Happiness Dairy (suzhou) Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by New Hope Double Happiness Dairy (suzhou) Co Ltd filed Critical New Hope Double Happiness Dairy (suzhou) Co Ltd
Priority to CN201510941145.6A priority Critical patent/CN105588816A/en
Publication of CN105588816A publication Critical patent/CN105588816A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G01N21/31Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
    • G01N21/35Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
    • G01N21/3577Investigating 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
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G01N21/31Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
    • G01N21/35Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
    • G01N21/359Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light

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 method for rapidly detecting the melamine content in adulterated milk based on near infrared spectra. The method includes the following steps that several parts of milk samples of the same mass are adulterated with melamine in sequence according to different mass ratios respectively to obtain several parts of adulterated milk samples; the near infrared spectra of the several parts of adulterated milk samples are collected; vector normalization is carried out on the collected spectra; a quantitative model of the melamine contents in the adulterated milk samples and the near infrared spectra of the adulterated milk samples is established according to a support vector regression analysis method; the near infrared spectrum of a milk sample to be detected is collected, and the melamine content in the milk sample to be detected is predicted by adopting the quantitative model. The method for rapidly detecting the melamine content in the adulterated milk based on the near infrared spectra is safe, reliable, rapid and accurate and has high practical application value.

Description

A kind of method based on mixing pseudo-content of melamine near infrared spectrum fast detecting milk
Technical field
The present invention relates to milk detection technique field, be specifically related to a kind of method based on mixing pseudo-content of melamine near infrared spectrum fast detecting milk.
Background technology
Milk is one of the most ancient natural drink, is described as " white blood ", and the importance of human body is well imagined; Milk contains abundant mineral matter, calcium, phosphorus, iron, zinc, copper, manganese, molybdenum, and milk is human calcium's best source, and calcium phosphorus ration is very suitable, is beneficial to the absorption of calcium. On market, some illegal retailers, in order to reap staggering profits, add melamine in milk, just there will be discomfort once people has drunk, and even may have serious consequences now.
Summary of the invention
For the weak point existing in above-mentioned technology, the invention provides a kind of safe and reliable, method based on mixing pseudo-content of melamine near infrared spectrum fast detecting milk fast and accurately.
The technical solution adopted for the present invention to solve the technical problems is: a kind of method based on mixing pseudo-content of melamine near infrared spectrum fast detecting milk, comprise the steps: step 1, sample preparation: in the milk sample of the quality such as some parts, mix melamine by different quality than successively respectively, obtain some parts and mix pseudo-milk sample; Step 2, spectra collection: gather the some parts of near infrared spectrums of mixing pseudo-milk sample; Step 3, spectrum pretreatment: the spectrum gathering is carried out to vector normalized; Step 4, quantitative model are set up: set up the content of melamine mixed in pseudo-milk sample and the quantitative model of its near infrared spectrum by support vector regression analytical method; Step 5, milk sample content of melamine to be measured prediction: gather the near infrared spectrum of milk sample to be measured, adopt quantitative model to predict the content of melamine of milk sample to be measured.
The scope of preferably, mixing content of melamine in described step 1 is 0.5~10%.
Preferably, when described step 2 spectra collection, milk sample temperature is 20~30 DEG C.
Preferably, when described step 2 spectra collection, spectral region 1200~1800nm.
Preferably, support vector regression analytical method in described step 4 adopts e-SVR regression model and the radial basis kernel function in support vector regression to carry out regression modeling, and adopts cross validation to be optimized the punishment parameters C in regression model, kernel functional parameter γ and loss function P.
Preferably, the scope of described punishment parameters C and kernel functional parameter γ is 0.1~1000.
Preferably, while adopting cross validation to carry out parameter optimization, require to make the coefficient correlation of quantitative model be greater than 0.995, root-mean-square error is less than 0.0001.
Compared with prior art, its beneficial effect is in the present invention: the method based on mixing pseudo-content of melamine near infrared spectrum fast detecting milk provided by the invention, and safe and reliable, quick and precisely, there is good actual application value.
Detailed description of the invention
The invention provides a kind of method based on mixing pseudo-content of melamine near infrared spectrum fast detecting milk, comprise the steps:
Step 1, sample preparation: in the milk sample of the quality such as some parts, mix melamine respectively by different quality than successively, the scope of mixing content of melamine is 0.5~10%, obtain some parts and mix pseudo-milk sample;
Step 2, spectra collection: gather the some parts of near infrared spectrums of mixing pseudo-milk sample, when spectra collection, milk sample temperature is 20~30 DEG C, spectral region 1200~1800nm;
Step 3, spectrum pretreatment: the spectrum gathering is carried out to vector normalized;
Step 4, quantitative model is set up: set up and mixed content of melamine in pseudo-milk sample and the quantitative model of its near infrared spectrum by support vector regression analytical method, described support vector regression analytical method adopts e-SVR regression model and the radial basis kernel function in support vector regression to carry out regression modeling, and adopt cross validation to the punishment parameters C in regression model, kernel functional parameter γ and loss function P are optimized, while adopting cross validation to carry out parameter optimization, the scope of described punishment parameters C and kernel functional parameter γ is 0.1~1000, requirement makes the coefficient correlation of quantitative model be greater than 0.995, root-mean-square error is less than 0.0001,
Step 5, milk sample content of melamine to be measured prediction: gather the near infrared spectrum of milk sample to be measured, adopt quantitative model to predict the content of melamine of milk sample to be measured.

Claims (7)

1. the method based on mixing pseudo-content of melamine near infrared spectrum fast detecting milk, its featureBe, comprise the steps:
Step 1, sample preparation: in the milk sample of the quality such as some parts, press respectively different quality ratio successivelyMix melamine, obtain some parts and mix pseudo-milk sample;
Step 2, spectra collection: gather the some parts of near infrared spectrums of mixing pseudo-milk sample;
Step 3, spectrum pretreatment: the spectrum gathering is carried out to vector normalized;
Step 4, quantitative model are set up: set up and mixed in pseudo-milk sample by support vector regression analytical methodContent of melamine and the quantitative model of its near infrared spectrum;
Step 5, milk sample content of melamine to be measured prediction: the near infrared light that gathers milk sample to be measuredSpectrum, adopts quantitative model to predict the content of melamine of milk sample to be measured.
2. as claimed in claim 1 based on mixing pseudo-content of melamine near infrared spectrum fast detecting milkMethod, it is characterized in that, the scope of mixing content of melamine in described step 1 is 0.5~10%.
3. as claimed in claim 1 based on mixing pseudo-content of melamine near infrared spectrum fast detecting milkMethod, it is characterized in that, when described step 2 spectra collection, milk sample temperature is 20~30 DEG C.
4. as claimed in claim 1 based on mixing pseudo-content of melamine near infrared spectrum fast detecting milkMethod, it is characterized in that, when described step 2 spectra collection, spectral region 1200~1800nm.
5. as claimed in claim 1 based on mixing pseudo-content of melamine near infrared spectrum fast detecting milkMethod, it is characterized in that, support vector regression analytical method in described step 4 adopts support vector to returnE-SVR regression model and radial basis kernel function in returning are carried out regression modeling, and adopt cross validation to returningPunishment parameters C, kernel functional parameter γ and loss function P in model are optimized.
6. as claimed in claim 5 based on mixing pseudo-content of melamine near infrared spectrum fast detecting milkMethod, it is characterized in that, the scope of described punishment parameters C and kernel functional parameter γ is 0.1~1000.
7. as claimed in claim 6 based on mixing pseudo-content of melamine near infrared spectrum fast detecting milkMethod, it is characterized in that, adopt cross validation while carrying out parameter optimization, require to make the phase of quantitative modelClose coefficient and be greater than 0.995, root-mean-square error is less than 0.0001.
CN201510941145.6A 2015-12-16 2015-12-16 Method for rapidly detecting melamine content in adulterated milk based on near infrared spectra Pending CN105588816A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510941145.6A CN105588816A (en) 2015-12-16 2015-12-16 Method for rapidly detecting melamine content in adulterated milk based on near infrared spectra

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510941145.6A CN105588816A (en) 2015-12-16 2015-12-16 Method for rapidly detecting melamine content in adulterated milk based on near infrared spectra

Publications (1)

Publication Number Publication Date
CN105588816A true CN105588816A (en) 2016-05-18

Family

ID=55928560

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510941145.6A Pending CN105588816A (en) 2015-12-16 2015-12-16 Method for rapidly detecting melamine content in adulterated milk based on near infrared spectra

Country Status (1)

Country Link
CN (1) CN105588816A (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106338491A (en) * 2016-08-17 2017-01-18 中国计量大学 Fake milk powder discriminating unit
CN106706555A (en) * 2016-11-21 2017-05-24 无锡迅杰光远科技有限公司 Milk powder determination method and system based on near infrared spectroscopy technology
CN108303406A (en) * 2018-02-07 2018-07-20 武汉轻工大学 Camellia seed oil adulteration identification method based on Raman spectrum
CN108426855A (en) * 2017-02-15 2018-08-21 天津农学院 The method of doping urea milk is differentiated based on Two-dimensional Near-infrared Correlation Spectroscopy: Theory gray-scale statistical characteristics
CN109342359A (en) * 2018-10-25 2019-02-15 中国科学院上海技术物理研究所 A kind of rapid detection method of other micro constitutent concentration mixed in pair of pesticide
CN109738386A (en) * 2018-12-28 2019-05-10 山东益丰生化环保股份有限公司 A kind of method of cyanamide content near infrared detection industrial liquid cyanamide
CN115575344A (en) * 2022-09-22 2023-01-06 广西医科大学 Method for simultaneously detecting oyster producing area and glycogen content based on portable near-infrared spectrometer

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102590128A (en) * 2012-01-10 2012-07-18 上海市兽药饲料检测所 Method for discriminating adulterated raw and fresh milk by using near infrared spectrum
US20120229796A1 (en) * 2010-03-09 2012-09-13 Chemlmage Corporation System and method for detecting contaminants in a sample using near-infrared spectroscopy
CN103792198A (en) * 2014-02-24 2014-05-14 天津农学院 Intermediate infrared-near infrared correlation spectrum discriminating method for melamine-doped milk
CN105115938A (en) * 2015-07-29 2015-12-02 北京航空航天大学 Quantitative determination method for melamine adulteration in feedstuff

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120229796A1 (en) * 2010-03-09 2012-09-13 Chemlmage Corporation System and method for detecting contaminants in a sample using near-infrared spectroscopy
CN102590128A (en) * 2012-01-10 2012-07-18 上海市兽药饲料检测所 Method for discriminating adulterated raw and fresh milk by using near infrared spectrum
CN103792198A (en) * 2014-02-24 2014-05-14 天津农学院 Intermediate infrared-near infrared correlation spectrum discriminating method for melamine-doped milk
CN105115938A (en) * 2015-07-29 2015-12-02 北京航空航天大学 Quantitative determination method for melamine adulteration in feedstuff

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
A: "具分段损失函数的支持向量机回归及在投资决策中的应用", <控制理论与应用> *
A: "基于支持向量机的系统辨识及其在下肢康复器械驱动建模中的应用", <吉林大学学报(工学版)> *
A: "支持向量回归建立测定醇烯比的近红外光谱校正模型", <光谱学与光谱分析> *
A: "用近红外光谱检测牛奶中的三聚氰胺", <红外与毫米波学报> *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106338491A (en) * 2016-08-17 2017-01-18 中国计量大学 Fake milk powder discriminating unit
CN106706555A (en) * 2016-11-21 2017-05-24 无锡迅杰光远科技有限公司 Milk powder determination method and system based on near infrared spectroscopy technology
CN108426855A (en) * 2017-02-15 2018-08-21 天津农学院 The method of doping urea milk is differentiated based on Two-dimensional Near-infrared Correlation Spectroscopy: Theory gray-scale statistical characteristics
CN108303406A (en) * 2018-02-07 2018-07-20 武汉轻工大学 Camellia seed oil adulteration identification method based on Raman spectrum
CN108303406B (en) * 2018-02-07 2021-04-27 武汉轻工大学 Camellia seed oil adulteration detection method based on Raman spectrum
CN109342359A (en) * 2018-10-25 2019-02-15 中国科学院上海技术物理研究所 A kind of rapid detection method of other micro constitutent concentration mixed in pair of pesticide
CN109738386A (en) * 2018-12-28 2019-05-10 山东益丰生化环保股份有限公司 A kind of method of cyanamide content near infrared detection industrial liquid cyanamide
CN115575344A (en) * 2022-09-22 2023-01-06 广西医科大学 Method for simultaneously detecting oyster producing area and glycogen content based on portable near-infrared spectrometer

Similar Documents

Publication Publication Date Title
CN105588816A (en) Method for rapidly detecting melamine content in adulterated milk based on near infrared spectra
Ren et al. Quantitative analysis and geographical traceability of black tea using Fourier transform near-infrared spectroscopy (FT-NIRS)
CN104849232B (en) A kind of method of quick detection royal jelly moisture and protein content
Aksuner et al. Determination of essential and non-essential elements in various tea leaves and tea infusions consumed in Turkey
CN104316489B (en) A kind of adulterated method of near infrared spectrum detection Ganoderma extract
CN1804582A (en) Method for identifying reductive milk in fresh milk and commodity milk by using near infrared spectrum
CN105588828A (en) Method for quickly detecting butterfat content through Raman spectra
CN105044024A (en) Method for nondestructive testing of grape berries based on near infrared spectrum technology
CN112595692A (en) Establishment method of fruit total sugar content prediction model and fruit total sugar content prediction method
Tamasi et al. Investigation on possible relationships between the content of sulfate and selected metals in Chianti wines
Wang et al. Back propagation-artificial neural network model for prediction of the quality of tea shoots through selection of relevant near infrared spectral data via synergy interval partial least squares
CN105136735A (en) Rapid and lossless analysis method for content of ternary adulterated sesame oil
CN105973814A (en) Laser near-infrared rapid detecting method for milk freshness
Haruna et al. Intelligent evaluation of free amino acid and crude protein content in raw peanut seed kernels using NIR spectroscopy paired with multivariable calibration
Fu et al. Simultaneous recognition of species, quality grades, and multivariate calibration of antioxidant activities for 12 famous green teas using mid‐and near‐infrared spectroscopy coupled with Chemometrics
CN105466906A (en) Method for rapidly detecting the mixing content of pseudo-urea in milk
CN103487446B (en) A kind of based on the detection method of Alumen additive in the fried food of dielectric property
Xu et al. Classification of organic and ordinary kiwifruit by chemometrics analysis of elemental fingerprint and stable isotopic ratios
CN105588925B (en) A kind of adulterated method of quick discriminating detection milk
Liu et al. Determination of characteristic wave bands and detection of melamine in fishmeal by Fourier transform near infrared spectroscopy
Shang et al. Establishment and Application of Model for Determining Oil Content of CottonseedUsing Near Infrared Spectroscopy
CN108008060A (en) The assay method and reagent of hydroxyproline in a kind of feed
CN105067609B (en) A kind of heat pack and the detection box as made from the heat pack and the method for carrying out concocted white spirit using box is detected and quickly testing oneself
CN106324127B (en) The pueraria root powder true and false identifies and the method for maca assay
CN108593596A (en) The method that Normal juice content in coconut juice is quickly detected based on near-infrared spectrum technique

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20160518

RJ01 Rejection of invention patent application after publication