CN105572096A - Rapid detection and identification method for adulteration of milk - Google Patents
Rapid detection and identification method for adulteration of milk Download PDFInfo
- Publication number
- CN105572096A CN105572096A CN201510941202.0A CN201510941202A CN105572096A CN 105572096 A CN105572096 A CN 105572096A CN 201510941202 A CN201510941202 A CN 201510941202A CN 105572096 A CN105572096 A CN 105572096A
- Authority
- CN
- China
- Prior art keywords
- milk
- pseudo
- sample
- enhanced raman
- surface enhanced
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/65—Raman scattering
- G01N21/658—Raman scattering enhancement Raman, e.g. surface plasmons
Landscapes
- Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Physics & Mathematics (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, Analyzing Materials By Fluorescence Or Luminescence (AREA)
Abstract
The invention discloses a rapid detection and identification method for adulteration of milk. The rapid detection and identification method comprises the following steps: (1) sample preparation: preparing a plurality of milk samples, dividing the milk samples into a standard sample set and a sample set, and sequentially doping goat milk into the equal-quality milk samples in the sample set according to different mass ratios, respectively, so as to obtain an adulteration set; (2) spectrum collection: respectively collecting surface enhanced Raman spectrums of the standard sample set and the adulteration set; (3) spectrum pretreatment: carrying out pretreatment on the collected surface enhanced Raman spectrums; (4) establishing of qualitative cognition models: establishing qualitative cognition models of the surface enhanced Raman spectrums of the standard sample set and the adulteration set by learning a vector quantization neural network; and (5) recognition of a to-be-detected milk sample: collecting the surface enhanced Raman spectrum of the to-be-detected milk sample, and recognizing the to-be-detected milk sample by virtue of the qualitative cognition models. The rapid detection and identification method is safe, reliable, rapid and accurate and has very good actual application value.
Description
Technical field
The present invention relates to milk detection technique field, be specifically related to a kind of quick detection recognition methods of mixing puppet for milk.
Background technology
Milk is one of the most ancient natural drink, is described as " white blood ", well imagines the importance of human body; Milk contains abundant mineral matter, calcium, phosphorus, iron, zinc, copper, manganese, molybdenum, and milk is the best source of human calcium, and calcium phosphorus ration is very suitable, is beneficial to the absorption of calcium.Now commercially, some illegal retailers, in order to reap staggering profits, add goat milk in milk, and people, once drink and just there will be discomfort, even may have serious consequences.
Summary of the invention
For the weak point existed in above-mentioned technology, the invention provides a kind of safe and reliable, mix pseudo-quick detection recognition methods for milk fast and accurately.
The technical solution adopted for the present invention to solve the technical problems is: a kind of quick detection recognition methods of mixing puppet for milk, comprises the steps:
Step one, sample preparation: get some parts of milk samples, be divided into standard specimen collection and sample sets, in the milk sample waiting quality sample collection, mix goat milk respectively by different quality than successively, obtains mixing pseudo-collection;
Step 2, spectra collection: gather standard specimen collection respectively and mix the pseudo-Surface enhanced raman spectroscopy collected;
Step 3, Pretreated spectra: pre-service is carried out to the Surface enhanced raman spectroscopy gathered;
Step 4, qualitative recognition model are set up: by learning vector quantization neural network standard specimen collection and the qualitative recognition model mixing the pseudo-Surface enhanced raman spectroscopy collected;
Step 5, milk sample identification to be measured: the Surface enhanced raman spectroscopy gathering milk sample to be measured, adopt qualitative recognition model to identify milk sample to be measured.
Preferably, the scope of mixing pseudo-goat milk content in described step one is 1 ~ 10%.
Preferably, when described step 2 Surface enhanced raman spectroscopy gathers, milk sample temperature is 20 ° ± 5C.
Preferably, when described step 2 Surface enhanced raman spectroscopy gathers, spectrum wave-number range 4000 ~ 650cm
-1.
Preferably, the preprocess method in described step 3 adopts vector normalization and Savitzky-Golay filtering 15 smoothly.
Preferably, the output neuron number in described step 4 learning vector quantization neural network is set to 2, and study digit rate adopts 0.01, and error target is set to 0.1, and train epochs is set to 1000, and weights learning function adopts " learn1v1 ".
Preferably, the accuracy of described standard specimen collection requires to be greater than 95%.
Preferably, the accuracy of mixing pseudo-collection described in requires to be greater than 90%.
Compared with prior art, its beneficial effect is in the present invention: quick detection recognition methods of mixing puppet for milk provided by the invention, safe and reliable, quick and precisely, has good actual application value.
Embodiment
The invention provides a kind of quick detection recognition methods of mixing puppet for milk, comprise the steps:
Step one, sample preparation: get some parts of milk samples, be divided into standard specimen collection and sample sets, in the milk sample waiting quality sample collection, mix goat milk respectively by different quality than successively, and the scope of mixing pseudo-goat milk content is 1 ~ 10%, obtains mixing pseudo-collection;
Step 2, spectra collection: gather standard specimen collection respectively and mix the pseudo-Surface enhanced raman spectroscopy collected, when Surface enhanced raman spectroscopy gathers, milk sample temperature is 20 ° ± 5C, spectrum wave-number range 4000 ~ 650cm
-1;
Step 3, Pretreated spectra: pre-service is carried out to the Surface enhanced raman spectroscopy gathered, preprocess method adopts vector normalization and Savitzky-Golay filtering 15 smoothly;
Step 4, qualitative recognition model are set up: by learning vector quantization neural network standard specimen collection and the qualitative recognition model mixing the pseudo-Surface enhanced raman spectroscopy collected, the accuracy of described standard specimen collection requires to be greater than 95%, described in mix pseudo-collection accuracy require to be greater than 90%;
Wherein, the output neuron number in described learning vector quantization neural network is set to 2, and study digit rate adopts 0.01, and error target is set to 0.1, and train epochs is set to 1000, and weights learning function adopts " learn1v1 ";
Step 5, milk sample identification to be measured: the Surface enhanced raman spectroscopy gathering milk sample to be measured, adopt qualitative recognition model to identify milk sample to be measured.
Claims (8)
1. mix a pseudo-quick detection recognition methods for milk, it is characterized in that, comprise the steps:
Step one, sample preparation: get some parts of milk samples, be divided into standard specimen collection and sample sets, in the milk sample waiting quality sample collection, mix goat milk respectively by different quality than successively, obtains mixing pseudo-collection;
Step 2, spectra collection: gather standard specimen collection respectively and mix the pseudo-Surface enhanced raman spectroscopy collected;
Step 3, Pretreated spectra: pre-service is carried out to the Surface enhanced raman spectroscopy gathered;
Step 4, qualitative recognition model are set up: by learning vector quantization neural network standard specimen collection and the qualitative recognition model mixing the pseudo-Surface enhanced raman spectroscopy collected;
Step 5, milk sample identification to be measured: the Surface enhanced raman spectroscopy gathering milk sample to be measured, adopt qualitative recognition model to identify milk sample to be measured.
2. mix pseudo-quick detection recognition methods for milk as claimed in claim 1, it is characterized in that, the scope of mixing pseudo-goat milk content in described step one is 1 ~ 10%.
3. mix pseudo-quick detection recognition methods for milk as claimed in claim 1, it is characterized in that, when described step 2 Surface enhanced raman spectroscopy gathers, milk sample temperature is 20 ° ± 5C.
4. mix pseudo-quick detection recognition methods for milk as claimed in claim 1, it is characterized in that, when described step 2 Surface enhanced raman spectroscopy gathers, spectrum wave-number range 4000 ~ 650cm
-1.
5. mix pseudo-quick detection recognition methods for milk as claimed in claim 1, it is characterized in that, the preprocess method in described step 3 adopts vector normalization and Savitzky-Golay filtering 15 smoothly.
6. mix pseudo-quick detection recognition methods for milk as claimed in claim 1, it is characterized in that, output neuron number in described step 4 learning vector quantization neural network is set to 2, study digit rate adopts 0.01, error target is set to 0.1, train epochs is set to 1000, and weights learning function adopts " learn1v1 ".
7. mix pseudo-quick detection recognition methods for milk as claimed in claim 1, it is characterized in that, the accuracy of described standard specimen collection requires to be greater than 95%.
8. as claimed in claim 1 mix pseudo-quick detection recognition methods for milk, it is characterized in that, described in mix pseudo-collection accuracy require to be greater than 90%.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510941202.0A CN105572096A (en) | 2015-12-16 | 2015-12-16 | Rapid detection and identification method for adulteration of milk |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510941202.0A CN105572096A (en) | 2015-12-16 | 2015-12-16 | Rapid detection and identification method for adulteration of milk |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105572096A true CN105572096A (en) | 2016-05-11 |
Family
ID=55882474
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510941202.0A Pending CN105572096A (en) | 2015-12-16 | 2015-12-16 | Rapid detection and identification method for adulteration of milk |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105572096A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090046284A1 (en) * | 2003-05-27 | 2009-02-19 | Honh Wang | Systems and methods for food safety detection |
CN101929951A (en) * | 2009-06-19 | 2010-12-29 | 西北农林科技大学 | Method for distinguishing milk doped with ewe's milk by near infrared spectrum |
CN103411950A (en) * | 2013-06-24 | 2013-11-27 | 吉林大学 | Method for detecting tripolycyanamide in milk based on surface-enhanced Raman activity chip |
CN104122250A (en) * | 2014-07-04 | 2014-10-29 | 华东理工大学 | Method for rapid detection of lactose in milk |
CN104568909A (en) * | 2015-02-10 | 2015-04-29 | 吕志伟 | Method for detecting content of dicyandiamide in milk based on surface enhanced Raman scattering technology |
-
2015
- 2015-12-16 CN CN201510941202.0A patent/CN105572096A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090046284A1 (en) * | 2003-05-27 | 2009-02-19 | Honh Wang | Systems and methods for food safety detection |
CN101929951A (en) * | 2009-06-19 | 2010-12-29 | 西北农林科技大学 | Method for distinguishing milk doped with ewe's milk by near infrared spectrum |
CN103411950A (en) * | 2013-06-24 | 2013-11-27 | 吉林大学 | Method for detecting tripolycyanamide in milk based on surface-enhanced Raman activity chip |
CN104122250A (en) * | 2014-07-04 | 2014-10-29 | 华东理工大学 | Method for rapid detection of lactose in milk |
CN104568909A (en) * | 2015-02-10 | 2015-04-29 | 吕志伟 | Method for detecting content of dicyandiamide in milk based on surface enhanced Raman scattering technology |
Non-Patent Citations (5)
Title |
---|
KHAN MOHAMMAD KHAN ET AL.: "Detection of urea adulteration in milk using near-infrared Raman spectroscopy", 《FOOD ANAL. METHODS》 * |
拜发分析系统销售(北京)有限公司: "针对羊奶中掺牛奶的快速检测方案", 《食品安全导刊 分析与检测》 * |
王二丹 等: "非线性化学群集成分分析法测定掺杂在羊奶中的牛奶和马奶含量", 《高等学校化学学报》 * |
王燕 等: "应用 LVQ神经网络建立基于拉曼光谱检测技术的肺癌诊断模型初探", 《第十七届全国光散射学术会议》 * |
闻新 等: "《MATLAB 神经网络仿真与应用,第一版》", 31 July 2003, 北京:科学出版社 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106501470B (en) | Utilize the method for gustatory system and electronic nose association evaluation mustard thick chilli sauce flavor grade | |
CN105588816A (en) | Method for rapidly detecting melamine content in adulterated milk based on near infrared spectra | |
CN108875913B (en) | Tricholoma matsutake rapid nondestructive testing system and method based on convolutional neural network | |
CN102087212B (en) | Pueraria lobata starch adulteration identification method based on principal component analysis | |
CN104849232B (en) | A kind of method of quick detection royal jelly moisture and protein content | |
CN104374738A (en) | Qualitative analysis method for improving identification result on basis of near-infrared mode | |
CN101957316B (en) | Method for authenticating Xiangshui rice by near-infrared spectroscopy | |
CN108960315A (en) | A kind of processed meat products quality intelligent evaluation system and method | |
CN106841083A (en) | Sesame oil quality detecting method based on near-infrared spectrum technique | |
CN103411906B (en) | The near infrared spectrum qualitative identification method of pearl powder and oyster shell whiting | |
CN105866056A (en) | Hybrid purity identification method based on near infrared spectroscopy | |
CN103837587A (en) | Method for quickly evaluating taste of bayberry juice through electronic tongue system | |
CN106153547A (en) | A kind of method of quick detection Protein Content in Milk | |
CN105588828A (en) | Method for quickly detecting butterfat content through Raman spectra | |
CN108426968A (en) | A kind of sorting technique of winter honey and Chinese tallow tree honey | |
CN116881705B (en) | Near infrared spectrum data processing system of calyx seu fructus physalis | |
CN103091281A (en) | Tea fermentation degree identification method based on intermediate infrared spectrum characteristic base | |
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 | |
CN107121408A (en) | The quick nondestructive discrimination method of edible vegetable oil kind | |
CN105466906A (en) | Method for rapidly detecting the mixing content of pseudo-urea in milk | |
Lang et al. | Study on identification of red jujube origin by multi-element analysis | |
CN105572096A (en) | Rapid detection and identification method for adulteration of milk | |
CN103335960A (en) | Rapid detection method of key indicators in cinobufagin extraction and concentration processes | |
CN107037039A (en) | A kind of Xinjiang walnut place of production is traced to the source research method |
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: 20160511 |
|
RJ01 | Rejection of invention patent application after publication |