CN104502309A - Method for discriminating multiple waste plastic kinds by adopting near infrared spectrum characteristic wavelength - Google Patents
Method for discriminating multiple waste plastic kinds by adopting near infrared spectrum characteristic wavelength Download PDFInfo
- Publication number
- CN104502309A CN104502309A CN201410854322.2A CN201410854322A CN104502309A CN 104502309 A CN104502309 A CN 104502309A CN 201410854322 A CN201410854322 A CN 201410854322A CN 104502309 A CN104502309 A CN 104502309A
- Authority
- CN
- China
- Prior art keywords
- waste
- used plastics
- kinds
- spectrum
- characteristic wavelength
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/20—Identification of molecular entities, parts thereof or of chemical compositions
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Chemical & Material Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Theoretical Computer Science (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Separation, Recovery Or Treatment Of Waste Materials Containing Plastics (AREA)
Abstract
The invention relates to a method for discriminating a plastic article and provides a method for discriminating multiple waste plastic kinds. The subsequent treatment calculated amount is reduced, the calculating time is saved, a sample can be directly discriminated and analyzed without being pretreated, and the operation and implementation in the industry are facilitated. Thus, according to the technical scheme adopted by the invention, the method for discriminating multiple waste plastic kinds by adopting a near infrared spectrum characteristic wavelength comprises the following steps: 1, acquiring original spectrums of multiple waste plastic standard samples by adopting a Fourier near-infrared spectroscopy; 2, performing K-M transformation on the acquired original spectrums; 3, performing principal component analysis on the spectrum data subjected to the K-M transformation, and extracting characteristic spectrums; 4, performing Fisher discrimination and establishing a discrimination model; and 5, discriminating and classifying unknown kinds of plastic by adopting the discrimination model established in the step 4, namely, a discriminant. The method is mainly applied to discrimination of the plastic article.
Description
Technical field
The present invention relates to plastic article discrimination method, particularly relate to the method adopting several waste or used plastics kind of characteristic wavelength of near-infrared spectrum identification
Technical background
At present, the total production of global plastic product is more than 1,000,000 tons.Cause the pollution that a global environmental problem and waste or used plastics bring to environment thus.Waste or used plastics is difficult to natural degradation, simultaneously to physical environment without affinity, therefore national governments are all actively promoting the recycling of waste or used plastics.
Now, the approach that waste or used plastics pollution problem is solved roughly has three kinds: recycling, landfill disposal and development degradation plastic.From the aspect of environmental protection, the recycling of waste or used plastics can either eliminate environmental pollution, can also obtain the valuable energy and resource simultaneously, bring obvious environmental and social benefits.Meanwhile, rational technology can also produce certain economic benefit, thus carries out recycling to waste or used plastics and meets China national conditions.
The recovery and treatment method of waste and old mixed plastic mainly contains four kinds: melting regeneration, heating power utilize, converting and modification recovery chemicals.But in the recycling process of its waste or used plastics, also encounter a lot of distinct issues, mainly contain following some:
(1) there will be secondary pollution and the corrosion to equipment in heat-obtaining process of burning, and supervene a large amount of harmful gas and black smoke.And the technology of China at present about burning heat-obtaining is also immature, and need a large amount of funds to support burning facility.
(2) Problem of Failure of catalyzer in catalytic pyrolysis process, because waste plastics heat conductivility is poor, and the part be mixed into can not make the catalyst surface coking and deactivation when fuel oil is produced in cracking by thermal decomposition material, the hydrogen chloride that PVC pyrolytic process produces in addition can cause catalyst poisoning equally.
(3) reclaim chemical products, the sorting problem of waste or used plastics before simple regeneration.
The identification of waste or used plastics, sorting are the bottlenecks that present stage restriction technics of reclaim of plastic waste utilizes.If do not added, distinguishing just mixes different types of plastics utilizes, and is just easy to cause that properties of product decline, processing procedure efficiency is low, and technical complexity increases, and even occurs waste product, produces secondary pollution.Therefore, waste or used plastics is identified that with being separated be the top priority of technics of reclaim of plastic waste.
The present invention introduces near-infrared spectrum technique in technics of reclaim of plastic waste field, utilizes the spectral information of near infrared spectrum comprehensive and abundant to carry out qualitative discrimination analysis to waste or used plastics.
In the Master's thesis " the useless mixed plastic Study of recognition based near infrared spectrum " to deliver for 2013, application near infrared spectrum to carry out discriminator to 6 kinds of waste or used plastics method was once described Liu Hong Sha, it first takes the level and smooth and Wavelet Denoising Method pre-service of S-G to original spectrum, but this spectral manipulation process is comparatively loaded down with trivial details, the characteristic wavelength extracted is also more, considerably increase the calculated amount of whole process, too increase the computing time of whole process simultaneously, make the complexity that its operating process in practical application becomes.
Summary of the invention
For overcoming the deficiencies in the prior art, provide the method identifying several waste or used plastics kind, reduce the calculated amount of subsequent treatment, save computing time, sample directly can carry out discriminatory analysis without pre-service, is convenient to operate in the industry and implement.For this reason, the technical scheme that the present invention takes is, adopts the method for several waste or used plastics kind of characteristic wavelength of near-infrared spectrum identification, comprises the steps:
Step 1: the original spectrum gathering several waste or used plastics standard model with Fourier transform near infrared instrument;
Step 2: the original spectrum of the waste or used plastics standard model collected in above-mentioned steps 1 is carried out K-M conversion;
Step 3: the spectroscopic data in above-mentioned steps 2 after K-M conversion process is carried out principal component analysis (PCA), extracts characteristic spectrum;
Step 4: the characteristic spectrum extracted through principal component analysis (PCA) in above-mentioned steps 3 is carried out Fisher and differentiate process, set up discrimination model;
Step 5: the discrimination model set up in application above-mentioned steps 4 and discriminant, carries out discriminator to the plastics of unknown kind.
The wavelength coverage of the original spectrum collected in step 1 is 1100-2500nm.
Fisher can be replaced to differentiate with BP neural network model in step 4 and set up discrimination model.
Fisher can be replaced to differentiate with PNN neural network model in step 4 and set up discrimination model.
Several plastics identified comprise PS, ABS, PP, PVC, PE, PET.
Compared with the prior art, technical characterstic of the present invention and effect:
The present invention carries out principal component analysis (PCA) to the near infrared spectrum of 86 pieces of waste or used plastics samples after K-M conversion as standard model collection, 18 characteristic wavelengths extracted can represent most information of original spectrum, reduce the calculated amount of subsequent treatment, save computing time.The BP neural network model adopted and PNN neural network model analytic process simply, are conveniently implemented in industrial operation.
Accompanying drawing explanation
Fig. 1 the inventive method schematic flow sheet.
Embodiment
The invention discloses a kind of method adopting near infrared light spectrum discrimination 6 kinds of waste or used plastics kinds, the present invention adopts Fourier transform near infrared instrument to gather the original spectrum of 6 kinds of waste or used plastics standard models, by original spectrum is K-M conversion and principal component analysis (PCA) extract characteristic wavelength, set up discrimination model with the reflectivity that characteristic wavelength is corresponding again, apply the discrimination model established and discriminatory analysis is carried out to unknown sample.Extract the characteristic wavelength of most information that can represent original spectrum, reduce the calculated amount of subsequent treatment, save computing time.Meanwhile, the requirement of near-infrared spectral analysis technology to sample is low, and sample directly can carry out discriminatory analysis without pre-service, is convenient to operate in the industry and implement.
In order to solve deficiency of the prior art, the present invention by extracting characteristic wavelength to the K-M of original spectrum conversion and principal component analysis (PCA), then is that discrimination model is set up in input with characteristic wavelength, applies the discrimination model established and carries out discriminatory analysis to unknown sample.Adopt identification waste or used plastics process computation amount of the present invention less, decrease spectroscopic data treatment capacity and processing time.
Technical scheme of the present invention is as follows:
1. adopt a method for several waste or used plastics kind of near infrared light spectrum discrimination, several plastics of described method identification comprise PS, ABS, PP, PVC, PE, PET, it is characterized in that described recognition methods comprises the following steps:
Step 1: the original spectrum gathering 6 kinds of waste or used plastics standard models with Fourier transform near infrared instrument;
Step 2: the original spectrum of the waste or used plastics standard model collected in above-mentioned steps 1 is carried out infrared spectrum K-M conversion;
Step 3: the spectroscopic data in above-mentioned steps 2 after K-M conversion process is carried out principal component analysis (PCA), extracts characteristic spectrum;
Step 4: the characteristic spectrum extracted through principal component analysis (PCA) in above-mentioned steps 3 is carried out Fisher and differentiate process, set up discrimination model;
Step 5: the model set up in application above-mentioned steps 4 carries out discriminator to the plastics of unknown kind.
2., according to the method for near infrared light spectrum discrimination 6 kinds of waste or used plastics kinds affiliated in 1, it is characterized in that the wavelength coverage of the original spectrum collected in step 1 is 1100-2500nm.
3., according to the method for near infrared light spectrum discrimination 6 kinds of waste or used plastics kinds affiliated in 1, it is characterized in that Fisher can be replaced to differentiate with BP neural network model in step 4 set up discrimination model.
4., according to the method for near infrared light spectrum discrimination 6 kinds of waste or used plastics kinds affiliated in 1, it is characterized in that Fisher can be replaced to differentiate with PNN neural network model in step 4 set up discrimination model.
The useless mixed plastic of useless mixed plastic and the society's recovery obtained after electric appliance and electronic product is disassembled and various electric wire are mainly discarded in the source of the present invention's discarded mixed plastic raw material used.
Waste and old mixed plastic raw material of the present invention is mainly derived from the useless mixed plastic of useless mixed plastic and the society's recovery obtained after discarded electric appliance and electronic product is disassembled and various electric wire, comprise these 6 kinds of plastics of PE, PP, PS, PVC, ABS and PET, wherein PE, PP, PVC and PET are mainly from various discarded household plastic goods, PS and ABS provides primarily of TCL extensive and profound in meaning (Tianjin) environmental protection Development Co., Ltd, is external import waste household appliances (televisor, refrigerator, washing machine and air-conditioning etc.).In 101 the waste or used plastics samples collected, the plastic sample being elected to be standard model collection has 86 pieces, wherein, PP plastic sample has 15 pieces, and PE plastic sample has 18 pieces, and PVC plastic sample has 10 pieces, ABS plastic sample has 15 pieces, and PET sample has 11 pieces, and PS plastic sample has 17 pieces.Unknown plastic sample as forecast set has 15 pieces, and wherein PET sample has 10 pieces, and PE plastic sample has 13 pieces, and PVC plastic sample has 11 pieces, and PS plastic sample has 15 pieces, and PP plastic sample has 12 pieces, and ABS plastic sample has 13 pieces.
Embodiment 1:
Waste or used plastics surface cleaned and uses 360# sand paper to polish, being then cut into the fritter of 2mm*2mm size respectively, finally it being numbered and measuring with diffuse reflectance under room temperature 20-25 DEG C of condition.
The near infrared spectrum of FT S6000 type Fourier infrared spectrograph to sample that the present invention adopts Bio-rad company of the U.S. to produce gathers, and spectral wavelength ranges between 1100-2500nm, and carries out K-M conversion to the original spectrum of the standard model collected.
MATLAB is adopted to carry out principal component analysis (PCA) to the near infrared spectrum of 86 pieces of waste or used plastics samples after K-M conversion as standard model collection, obtain principal component scores and loading factor, the contribution rate of accumulative total of front 4 major components arrives 96.62%, the characteristic information of the former spectrum overwhelming majority can be represented, wherein the contribution rate of first principal component is 75.68%, therefore based on the loading factor of first principal component, the loading factor considering front 4 major components selects 18 characteristic wavelengths, be 1216.46, 1394.44, 1660.65, 1699.85, 1731.64, 1752.72, 1765.85, 1789.00, 1821.69, 1906.08, 2131.80, 2147.70, 2209.05, 2254.14, 2296.07, 2320.75, 2376.05, 2478.27.
By 18 the characteristic wavelength data importing IBM SPSS Statistics19 softwares of the plastics of 86 standard model collection extracted, set up Fisher discrimination model.The Fisher discrimination model set up has carried out correct classification to 96.5% in initial packet case, has carried out correct classification to 89.5% in cross validation grouping case.Apply the Fisher discrimination model established again and discriminance analysis is carried out to 74 unknown samples, only have 3 to differentiate mistake to the identification and classification of unknown sample.
Embodiment 2:
With reference to the method for embodiment 1, using the input as BP neural network model of 18 characteristic wavelength data of the plastics of 86 standard model collection of extracting, BP neural network model is trained, the neural number of the BP neural network model input layer drawn is trained to be 18, the neural number of hidden layer is 20, the neural number of output layer is 6, target error 0.01, the transport function of hidden layer adopts two tangent S type transport function tansig, output layer adopts purelin function, select learning function trainlm, frequency of training is 100.With the BP neural network model trained, prediction classification is carried out to unknown sample collection again.BP neural network model is to the differentiation rate of accuracy reached of standard model collection to 98.84%, and the predictablity rate for unknown sample collection is 73.33%, substantially can reach the requirement to waste or used plastics classification.
Embodiment 3:
With reference to the method for embodiment 1, using the input as PNN neural network model of 18 characteristic wavelength data of the plastics of 86 standard model collection of extracting, PNN neural network model is trained, the dispersion constant of training the PNN neural network model obtained is 0.1, and the maximum neuron number in middle layer is 86.With the PNN network model trained, prediction classification is carried out to unknown sample collection again.The classification accuracy of PNN network training model to training set reaches 100%, is 97.67% to the classification accuracy of forecast set, reaches the requirement to waste or used plastics classification.
Above-mentionedly only several concrete case study on implementation in the present invention to be illustrated; but can not as protection scope of the present invention; every according to the change of the equivalence done by design spirit in the present invention or to modify or equal proportion zooms in or out, all should think and fall into protection scope of the present invention.
Claims (5)
1. adopt a method for several waste or used plastics kind of characteristic wavelength of near-infrared spectrum identification, it is characterized in that, comprise the steps:
Step 1: the original spectrum gathering several waste or used plastics standard model with Fourier transform near infrared instrument;
Step 2: the original spectrum of the waste or used plastics standard model collected in above-mentioned steps 1 is carried out K-M conversion;
Step 3: the spectroscopic data in above-mentioned steps 2 after K-M conversion process is carried out principal component analysis (PCA), extracts characteristic spectrum;
Step 4: the characteristic spectrum extracted through principal component analysis (PCA) in above-mentioned steps 3 is carried out Fisher and differentiate process, set up discrimination model;
Step 5: the discrimination model set up in application above-mentioned steps 4 and discriminant, carries out discriminator to the plastics of unknown kind.
2. the method adopting several waste or used plastics kind of characteristic wavelength of near-infrared spectrum identification as claimed in claim 1, it is characterized in that, the wavelength coverage of the original spectrum collected in step 1 is 1100-2500nm.
3. the method adopting several waste or used plastics kind of characteristic wavelength of near-infrared spectrum identification as claimed in claim 1, is characterized in that, Fisher can be replaced to differentiate with BP neural network model and set up discrimination model in step 4.
4. the method adopting several waste or used plastics kind of characteristic wavelength of near-infrared spectrum identification as claimed in claim 1, is characterized in that, Fisher can be replaced to differentiate with PNN neural network model and set up discrimination model in step 4.
5. the method adopting several waste or used plastics kind of characteristic wavelength of near-infrared spectrum identification as claimed in claim 1, it is characterized in that, several plastics of identification comprise PS, ABS, PP, PVC, PE, PET.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410854322.2A CN104502309A (en) | 2014-12-31 | 2014-12-31 | Method for discriminating multiple waste plastic kinds by adopting near infrared spectrum characteristic wavelength |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410854322.2A CN104502309A (en) | 2014-12-31 | 2014-12-31 | Method for discriminating multiple waste plastic kinds by adopting near infrared spectrum characteristic wavelength |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104502309A true CN104502309A (en) | 2015-04-08 |
Family
ID=52943727
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410854322.2A Pending CN104502309A (en) | 2014-12-31 | 2014-12-31 | Method for discriminating multiple waste plastic kinds by adopting near infrared spectrum characteristic wavelength |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104502309A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105139022A (en) * | 2015-07-21 | 2015-12-09 | 天津大学 | Plastic identification model establishment method via near-infrared hyper-spectral image technology |
| CN105738313A (en) * | 2016-03-10 | 2016-07-06 | 齐齐哈尔大学 | Method for identifying animal blood on basis of near-infrared spectrum technologies and application of method |
| CN106018324A (en) * | 2016-08-15 | 2016-10-12 | 中国计量大学 | Plastic identification apparatus and method based on near-infrared spectroscopy analysis |
| 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 |
| TWI622006B (en) * | 2016-08-31 | 2018-04-21 | 楊琛 | A valuable item trading system and method thereof |
| CN107999399A (en) * | 2017-12-27 | 2018-05-08 | 华侨大学 | Building waste on-line sorting system and method based on the detection of dot matrix EO-1 hyperion |
| CN110441254A (en) * | 2019-08-07 | 2019-11-12 | 中国计量大学 | A kind of near-infrared frequency comb spectrometer of plastics for identification |
| CN110658174A (en) * | 2019-08-27 | 2020-01-07 | 厦门谱识科仪有限公司 | Intelligent identification method and system based on surface enhanced Raman spectrum detection |
| CN110980036A (en) * | 2020-01-06 | 2020-04-10 | 沙洲职业工学院 | Intelligent garbage classification device and classification method thereof |
| CN112098357A (en) * | 2020-08-21 | 2020-12-18 | 南京农业大学 | Strawberry sensory quality grade evaluation method based on near infrared spectrum |
| EP3842787A1 (en) * | 2019-12-23 | 2021-06-30 | Sick Ag | Spectral sensor |
| CN113095388A (en) * | 2021-04-01 | 2021-07-09 | 福建师范大学 | Solid waste plastic material identification method based on double-layer classification algorithm |
| CN114235740A (en) * | 2021-11-12 | 2022-03-25 | 华南理工大学 | XGboost model-based waste plastic spectrum identification method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002090299A (en) * | 2000-09-11 | 2002-03-27 | Opt Giken Kk | Method for distinguishing grade of high-molecular material |
| CN102175637A (en) * | 2010-12-30 | 2011-09-07 | 中国药品生物制品检定所 | Method for detecting plastics |
| CN102230888A (en) * | 2011-06-16 | 2011-11-02 | 浙江大学 | Method for detecting content of plasticizing agent |
-
2014
- 2014-12-31 CN CN201410854322.2A patent/CN104502309A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002090299A (en) * | 2000-09-11 | 2002-03-27 | Opt Giken Kk | Method for distinguishing grade of high-molecular material |
| CN102175637A (en) * | 2010-12-30 | 2011-09-07 | 中国药品生物制品检定所 | Method for detecting plastics |
| CN102230888A (en) * | 2011-06-16 | 2011-11-02 | 浙江大学 | Method for detecting content of plasticizing agent |
Non-Patent Citations (2)
| Title |
|---|
| 张毅民 等: "基于近红外的Fisher判别法鉴别废塑料", 《工程塑料应用》 * |
| 黄扬明 等: "废旧塑料的红外鉴别技术及其应用", 《塑料》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105139022A (en) * | 2015-07-21 | 2015-12-09 | 天津大学 | Plastic identification model establishment method via near-infrared hyper-spectral image technology |
| CN105738313A (en) * | 2016-03-10 | 2016-07-06 | 齐齐哈尔大学 | Method for identifying animal blood on basis of near-infrared spectrum technologies and application of method |
| CN105738313B (en) * | 2016-03-10 | 2019-04-02 | 齐齐哈尔大学 | A kind of method and application identifying animal blood based on near-infrared spectrum technique |
| CN106018324A (en) * | 2016-08-15 | 2016-10-12 | 中国计量大学 | Plastic identification apparatus and method based on near-infrared spectroscopy analysis |
| TWI622006B (en) * | 2016-08-31 | 2018-04-21 | 楊琛 | A valuable item trading system and method thereof |
| 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 |
| CN107999399A (en) * | 2017-12-27 | 2018-05-08 | 华侨大学 | Building waste on-line sorting system and method based on the detection of dot matrix EO-1 hyperion |
| CN110441254A (en) * | 2019-08-07 | 2019-11-12 | 中国计量大学 | A kind of near-infrared frequency comb spectrometer of plastics for identification |
| CN110658174A (en) * | 2019-08-27 | 2020-01-07 | 厦门谱识科仪有限公司 | Intelligent identification method and system based on surface enhanced Raman spectrum detection |
| CN110658174B (en) * | 2019-08-27 | 2022-05-20 | 厦门谱识科仪有限公司 | Intelligent identification method and system based on surface enhanced Raman spectrum detection |
| EP3842787A1 (en) * | 2019-12-23 | 2021-06-30 | Sick Ag | Spectral sensor |
| CN110980036A (en) * | 2020-01-06 | 2020-04-10 | 沙洲职业工学院 | Intelligent garbage classification device and classification method thereof |
| CN112098357A (en) * | 2020-08-21 | 2020-12-18 | 南京农业大学 | Strawberry sensory quality grade evaluation method based on near infrared spectrum |
| CN112098357B (en) * | 2020-08-21 | 2021-12-10 | 南京农业大学 | Strawberry sensory quality grade evaluation method based on near infrared spectrum |
| CN113095388A (en) * | 2021-04-01 | 2021-07-09 | 福建师范大学 | Solid waste plastic material identification method based on double-layer classification algorithm |
| CN113095388B (en) * | 2021-04-01 | 2023-06-30 | 福建师范大学 | Solid waste plastic material identification method based on double-layer classification algorithm |
| CN114235740A (en) * | 2021-11-12 | 2022-03-25 | 华南理工大学 | XGboost model-based waste plastic spectrum identification method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104502309A (en) | Method for discriminating multiple waste plastic kinds by adopting near infrared spectrum characteristic wavelength | |
| de Santana et al. | Random forest as one-class classifier and infrared spectroscopy for food adulteration detection | |
| Yang et al. | Rapid and Nondestructive On‐Site Classification Method for Consumer‐Grade Plastics Based on Portable NIR Spectrometer and Machine Learning | |
| CN103412557A (en) | Industrial fault detection and diagnostic method suitable for nonlinear process on-line monitoring | |
| US20220101277A1 (en) | End to end platform to manage circular economy of waste materials | |
| CN110980036A (en) | Intelligent garbage classification device and classification method thereof | |
| CN111965121B (en) | Rapid classification detection method for coal coke slag based on spectral analysis technology | |
| Lei et al. | Geographic origin identification of coal using near-infrared spectroscopy combined with improved random forest method | |
| CN103018181A (en) | Soft measurement method based on correlation analysis and ELM neural network | |
| CN105139022A (en) | Plastic identification model establishment method via near-infrared hyper-spectral image technology | |
| CN106426643A (en) | Method for sorting broken plastics in waste household appliances through near infrared absorption spectroscopy analysis device | |
| Yu et al. | Novel automatic model construction method for the rapid characterization of petroleum properties from near-infrared spectroscopy | |
| Bao et al. | Feature selection method for nonintrusive load monitoring with balanced redundancy and relevancy | |
| Dan | NIR spectroscopy oranges origin identification framework based on machine learning | |
| CN114112983A (en) | Python data fusion-based Tibetan medicine all-leaf artemisia rupestris L producing area distinguishing method | |
| Liu et al. | Incremental Support Vector Machine Combined with Ultraviolet‐Visible Spectroscopy for Rapid Discriminant Analysis of Red Wine | |
| CN114118222A (en) | Coal mill state early warning system and fault identification and diagnosis method | |
| CN113310943A (en) | Lotus root starch adulteration identification method based on machine learning | |
| CN105069462A (en) | Qualitative determination method for organic chemical based on spectral characteristic refinement and classifier cascading | |
| Farcomeni et al. | Non-parametric analysis of infrared spectra for recognition of glass and glass ceramic fragments in recycling plants | |
| CN114970596A (en) | Raman spectrum analysis-based fish meal adulteration rapid detection method | |
| CN114662576A (en) | Non-invasive storage battery car charging detection method and system based on supervised classification | |
| Zhu et al. | Analysis of extractives content of guangxi fast-growing eucalyptus and models optimization based on near-infrared technique | |
| Wang et al. | Determination of 1-Naphthol and 2-Naphthol Based on Fluorescence Spectrometry Combined with Improved FastICA-SVR | |
| CN110717235A (en) | Coking prediction method for settler of catalytic cracking unit |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150408 |