WO2021046851A1 - Procédé d'identification et de classification de déchets de cuisine - Google Patents

Procédé d'identification et de classification de déchets de cuisine Download PDF

Info

Publication number
WO2021046851A1
WO2021046851A1 PCT/CN2019/105843 CN2019105843W WO2021046851A1 WO 2021046851 A1 WO2021046851 A1 WO 2021046851A1 CN 2019105843 W CN2019105843 W CN 2019105843W WO 2021046851 A1 WO2021046851 A1 WO 2021046851A1
Authority
WO
WIPO (PCT)
Prior art keywords
samples
level
infrared
food waste
kitchen waste
Prior art date
Application number
PCT/CN2019/105843
Other languages
English (en)
Chinese (zh)
Inventor
袁增伟
张诗文
覃祖茂
盛虎
王婷
Original Assignee
南京大学（溧水）生态环境研究院
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 南京大学（溧水）生态环境研究院 filed Critical 南京大学（溧水）生态环境研究院
Priority to PCT/CN2019/105843 priority Critical patent/WO2021046851A1/fr
Publication of WO2021046851A1 publication Critical patent/WO2021046851A1/fr

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
    • G01N21/17—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

Definitions

  • the invention belongs to the environmental field, and particularly relates to a method for identifying and classifying kitchen waste.
  • Food waste is the general term for the leftover meals discarded by the food and beverage units such as households, hotels, restaurants, etc. At present, about 40% of the most urban waste in the world is kitchen waste, mainly including rice and flour food residues, vegetables, vegetable oil, animal oil, meat bones, fish bones, etc. Its chemical components are mainly starch, cellulose, protein, lipids and inorganic salts.
  • Kitchen waste has the following characteristics: First, the content of organic matter such as crude protein and crude fiber is relatively high (each accounted for 16.73% and 2.52% of the dry food waste), which is of great development and utilization value, but it is perishable and produces foul smell; High water content (water mass fraction greater than 80%), inconvenient to collect and transport, low calorific value, improper handling is likely to produce secondary pollutants such as leachate; third is oil (crude fat accounts for 28.82% of the dry food waste ) And salt substances (NaCl content as high as 1.239%) are higher than other domestic wastes, which have a greater impact on the quality of resource-based products and require proper disposal.
  • the present invention provides a method for identification and classification of kitchen waste.
  • the invention provides a method for identification and classification of kitchen waste, which establishes a near-infrared qualitative discrimination model for the main components of kitchen waste, and uses the established near-infrared qualitative discrimination model for the main components of kitchen waste to qualitatively classify kitchen waste; :
  • the level is composed of first-level letters + first-level numbers + second-level letters + second-level numbers; the first-level letters are determined by the chemical components with the largest content.
  • the first-level number is determined by the percentage of the chemical component with the highest content;
  • the second-level letter is determined by the chemical component with the highest content, and the second-level number is determined by the percentage of the chemical component with the highest content;
  • step (3) Prepare a near-infrared spectrometer and a near-infrared optical fiber probe, perform laboratory infrared analysis on the 10 samples configured in step (2), and combine the results of laboratory analysis to determine the optimal collection of near-infrared spectra of the modeling set samples Conditions, and through spectral preprocessing and data compression, establish a qualitative discrimination model for the five components of food waste, and eliminate the singularities of the model. Under the same conditions, use the near-infrared spectra of the calibration set samples, and call the qualitative discrimination model for the calibration set samples. Perform qualitative analysis to correct the model;
  • Test food waste samples compare the infrared spectrum of the sample with the infrared spectrum of 10 samples, the sample number with the closest spectrum is the number of the sample to be tested, which is the classification of the sample.
  • the chemical components include: starch, denoted as A; cellulose, denoted as B; protein, denoted as C; lipids, denoted as D; inorganic salt, denoted as E.
  • the first-level number and the second-level number retain ten digits of the percentage.
  • the near-infrared spectrum acquisition conditions include detector, white light source, gain, moving mirror speed, scanning range, scanning times, and resolution index.
  • the near-infrared spectroscopy preprocessing refers to processing the near-infrared spectroscopy data of the modeling set sample collected in step (1) through smoothing, trend removal correction, multivariate scattering correction (MSC), and vector normalization (SNV). ) And other machine learning algorithms, and finally get the optimal conditions of spectrum preprocessing and wavelength range.
  • the method for determining the number of samples any two of the five largest samples are selected, there are 10 selection methods, and the largest samples start from 100 to 10, and there are 10 kinds in total, so 100 samples are made.
  • the food waste identification and classification method provided by the present invention uses five common substances in kitchen waste as standard products, establishes a database of 100 standard products-atlas, and then uses a computer to compare the measured samples with the standard product atlases, thereby providing The classification of kitchen waste is convenient to guide the treatment of kitchen waste.
  • the level is composed of first-level letters + first-level numbers + second-level letters + second-level numbers; the first-level letters are determined by the chemical components with the largest content.
  • the first-level number is determined by the percentage of the chemical component with the largest content;
  • the second-level letter is determined by the chemical component with the largest content, and the second-level number is determined by the percentage of the chemical component with the largest content;
  • the chemical components include: starch, denoted as A; fiber Element, denoted as B; protein, denoted as C; lipid, denoted as D; inorganic salt, denoted as E.
  • the first-level and second-level numbers retain ten digits of percentage.
  • step (1) Coding Method for determining the number of samples: Choose two of the five most samples, and there are 10 selection methods. The most samples start from 100 to 10, and there are 10 types in total, so 100 samples are made.
  • step (3) Prepare a near-infrared spectrometer and a near-infrared optical fiber probe, perform laboratory infrared analysis on the 10 samples configured in step (2), and combine the results of laboratory analysis to determine the optimal collection of near-infrared spectra of the modeling set samples Conditions, and through spectral preprocessing and data compression, establish a qualitative discrimination model for the five components of food waste, and eliminate the singularities of the model. Under the same conditions, use the near-infrared spectra of the calibration set samples, and call the qualitative discrimination model for the calibration set samples. Perform qualitative analysis to calibrate the model; the near-infrared spectrum acquisition conditions include detector, white light source, gain, moving mirror speed, scanning range, scanning times, and resolution index.
  • the near-infrared spectroscopy preprocessing refers to the near-infrared spectroscopy data of the modeling set sample collected in step (1) through smoothing processing, trend removal correction, multiple scattering correction (MSC), vector normalization (SNV) and other machines Learning algorithm, and finally get the optimal conditions of spectrum preprocessing and wavelength range.
  • Test food waste samples compare the infrared spectrum of the sample with the infrared spectrum of 10 samples, the sample number with the closest spectrum is the number of the sample to be tested, which is the classification of the sample.

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

L'invention concerne un procédé pour l'identification et la classification de déchets de cuisine. Le procédé comprend l'établissement d'un modèle de discrimination qualitative dans le proche infrarouge pour les composants principaux de déchets de cuisine, et l'utilisation du modèle pour classifier qualitativement les déchets de cuisine. Le procédé décrit utilise cinq substances communes dans des déchets de cuisine en tant qu'articles standard, établit une base de données de 100 articles-atlas standard, et utilise ensuite un ordinateur pour comparer un échantillon mesuré à des atlas d'articles standard pour ainsi classer et classifier des déchets de cuisine, ce qui facilite le guidage du traitement des déchets de cuisine.
PCT/CN2019/105843 2019-09-14 2019-09-14 Procédé d'identification et de classification de déchets de cuisine WO2021046851A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/105843 WO2021046851A1 (fr) 2019-09-14 2019-09-14 Procédé d'identification et de classification de déchets de cuisine

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/105843 WO2021046851A1 (fr) 2019-09-14 2019-09-14 Procédé d'identification et de classification de déchets de cuisine

Publications (1)

Publication Number Publication Date
WO2021046851A1 true WO2021046851A1 (fr) 2021-03-18

Family

ID=74865953

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/105843 WO2021046851A1 (fr) 2019-09-14 2019-09-14 Procédé d'identification et de classification de déchets de cuisine

Country Status (1)

Country Link
WO (1) WO2021046851A1 (fr)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE19720121A1 (de) * 1997-05-14 1998-01-08 Stefan Dipl Phys Leppelmann Verfahren zur quantitativen Bestimmung der Anteile verschiedenartiger Stoffe in Schüttgütern
DE19751862A1 (de) * 1997-11-22 1999-05-27 Lutz Prof Dr Priese Verfahren und Vorrichtung zum Identifizieren und Sortieren von bandgeförderten Objekten
CN102830087A (zh) * 2011-09-26 2012-12-19 武汉工业学院 基于近红外光谱技术快速鉴别餐饮废弃油脂的方法
CN104931454A (zh) * 2015-06-23 2015-09-23 浙江理工大学 一种利用近红外光谱分析技术快速测定纺织品中莱卡纤维含量的方法
CN106022489A (zh) * 2016-07-15 2016-10-12 安徽东锦资源再生科技有限公司 废旧纤维制品成分与含量智能分拣系统及方法
CN106198423A (zh) * 2016-09-12 2016-12-07 电子科技大学 一种基于可见‑近红外光谱分析技术鉴别火腿肠等级的方法
CN106273067A (zh) * 2016-07-15 2017-01-04 安徽东锦资源再生科技有限公司 废旧纤维制品智能识别与分拣系统
CN205879775U (zh) * 2016-07-15 2017-01-11 安徽东锦资源再生科技有限公司 废旧聚酯纤维制品成分识别装置
CN108982409A (zh) * 2018-08-08 2018-12-11 浙江工业大学 一种基于近红外光谱快速检测大型褐藻木质纤维素三组分含量的方法
CN109211835A (zh) * 2018-10-11 2019-01-15 南京大学（溧水）生态环境研究院 一种基于光谱技术的厨余垃圾快速鉴定方法

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE19720121A1 (de) * 1997-05-14 1998-01-08 Stefan Dipl Phys Leppelmann Verfahren zur quantitativen Bestimmung der Anteile verschiedenartiger Stoffe in Schüttgütern
DE19751862A1 (de) * 1997-11-22 1999-05-27 Lutz Prof Dr Priese Verfahren und Vorrichtung zum Identifizieren und Sortieren von bandgeförderten Objekten
CN102830087A (zh) * 2011-09-26 2012-12-19 武汉工业学院 基于近红外光谱技术快速鉴别餐饮废弃油脂的方法
CN104931454A (zh) * 2015-06-23 2015-09-23 浙江理工大学 一种利用近红外光谱分析技术快速测定纺织品中莱卡纤维含量的方法
CN106022489A (zh) * 2016-07-15 2016-10-12 安徽东锦资源再生科技有限公司 废旧纤维制品成分与含量智能分拣系统及方法
CN106273067A (zh) * 2016-07-15 2017-01-04 安徽东锦资源再生科技有限公司 废旧纤维制品智能识别与分拣系统
CN205879775U (zh) * 2016-07-15 2017-01-11 安徽东锦资源再生科技有限公司 废旧聚酯纤维制品成分识别装置
CN106198423A (zh) * 2016-09-12 2016-12-07 电子科技大学 一种基于可见‑近红外光谱分析技术鉴别火腿肠等级的方法
CN108982409A (zh) * 2018-08-08 2018-12-11 浙江工业大学 一种基于近红外光谱快速检测大型褐藻木质纤维素三组分含量的方法
CN109211835A (zh) * 2018-10-11 2019-01-15 南京大学（溧水）生态环境研究院 一种基于光谱技术的厨余垃圾快速鉴定方法

Similar Documents

Publication Publication Date Title
Khaled et al. Emerging nondestructive approaches for meat quality and safety evaluation—A review
Wang et al. Spectral detection techniques for non-destructively monitoring the quality, safety, and classification of fresh red meat
Iqbal et al. Prediction of moisture, color and pH in cooked, pre-sliced turkey hams by NIR hyperspectral imaging system
Qiao et al. Pork quality and marbling level assessment using a hyperspectral imaging system
CN102519906B (zh) 多通道近红外光谱牛肉品质多参数同时检测方法
Cluff et al. Optical scattering with hyperspectral imaging to classify longissimus dorsi muscle based on beef tenderness using multivariate modeling
Kamruzzaman et al. Hyperspectral imaging in tandem with multivariate analysis and image processing for non-invasive detection and visualization of pork adulteration in minced beef
CN109211835B (zh) 一种基于光谱技术的厨余垃圾快速鉴定方法
CN107064047A (zh) 一种基于近红外光谱的富士苹果品质无损检测方法
CN102967578A (zh) 在线获取牛肉样本近红外光谱的方法及其在评价牛肉质量中的应用
CN105092579A (zh) 一种芒果品质无损检测设备
Prades et al. Methodology for cork plank characterization (Quercus suber L.) by near-infrared spectroscopy and image analysis
Yang et al. Wood veneer defect detection system based on machine vision
CN104502307A (zh) 一种快速检测长牡蛎糖原和蛋白质含量的方法
CN112505015A (zh) 一种拉曼光谱快速预判牛肉pH值的方法
WO2021046851A1 (fr) Procédé d'identification et de classification de déchets de cuisine
Guo et al. Rapid determination of minced beef adulteration using hyperspectral reflectance spectroscopy and multivariate methods
Feifei et al. Feature extraction method of hyperspectral scattering images for prediction of total viable count in pork meat
Li et al. Hyperspectral imaging technique for determination of pork freshness attributes
WO2021046854A1 (fr) Procédé de classification de déchets de cuisine sur la base de mégadonnées
Dong et al. Nondestructive method for analysis of the soybean quality
Lv et al. Identification of less-ripen, ripen, and over-ripen grapes during harvest time based on visible and near-infrared (Vis-NIR) spectroscopy
CN113866122A (zh) 一种鸡品种快速鉴别方法及其应用
Liu et al. Feasibility of nondestructive detection of apple crispness based on spectroscopy and machine vision
Adam Sensory and Instrumental Methods of Meat Evaluation: A Review

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19945295

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19945295

Country of ref document: EP

Kind code of ref document: A1