TW202136744A - Waste plastic material determination device, material determination method, and material determination program - Google Patents
Waste plastic material determination device, material determination method, and material determination program Download PDFInfo
- Publication number
- TW202136744A TW202136744A TW110103638A TW110103638A TW202136744A TW 202136744 A TW202136744 A TW 202136744A TW 110103638 A TW110103638 A TW 110103638A TW 110103638 A TW110103638 A TW 110103638A TW 202136744 A TW202136744 A TW 202136744A
- Authority
- TW
- Taiwan
- Prior art keywords
- waste plastic
- judging
- spectrum
- aforementioned
- waste
- Prior art date
Links
- 239000000463 material Substances 0.000 title claims abstract description 210
- 239000002699 waste material Substances 0.000 title claims abstract description 144
- 239000004033 plastic Substances 0.000 title claims abstract description 140
- 229920003023 plastic Polymers 0.000 title claims abstract description 140
- 238000000034 method Methods 0.000 title claims description 24
- 238000001228 spectrum Methods 0.000 claims abstract description 105
- 238000005286 illumination Methods 0.000 claims abstract description 14
- 239000000284 extract Substances 0.000 claims abstract description 7
- 239000002985 plastic film Substances 0.000 claims description 30
- 238000012937 correction Methods 0.000 claims description 26
- 230000006870 function Effects 0.000 claims description 21
- 238000007781 pre-processing Methods 0.000 claims description 18
- 238000001514 detection method Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 15
- 238000003066 decision tree Methods 0.000 claims description 10
- 230000001678 irradiating effect Effects 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims 1
- 238000003379 elimination reaction Methods 0.000 claims 1
- 239000012634 fragment Substances 0.000 abstract 3
- 238000010586 diagram Methods 0.000 description 12
- 238000012216 screening Methods 0.000 description 12
- 238000002347 injection Methods 0.000 description 10
- 239000007924 injection Substances 0.000 description 10
- 238000012706 support-vector machine Methods 0.000 description 10
- 239000000203 mixture Substances 0.000 description 9
- 238000010187 selection method Methods 0.000 description 9
- XECAHXYUAAWDEL-UHFFFAOYSA-N acrylonitrile butadiene styrene Chemical compound C=CC=C.C=CC#N.C=CC1=CC=CC=C1 XECAHXYUAAWDEL-UHFFFAOYSA-N 0.000 description 6
- 229920000122 acrylonitrile butadiene styrene Polymers 0.000 description 6
- 239000004676 acrylonitrile butadiene styrene Substances 0.000 description 6
- 239000004698 Polyethylene Substances 0.000 description 5
- 239000004743 Polypropylene Substances 0.000 description 5
- 229920005669 high impact polystyrene Polymers 0.000 description 5
- 239000004797 high-impact polystyrene Substances 0.000 description 5
- 238000005192 partition Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 4
- 229910052782 aluminium Inorganic materials 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 239000002994 raw material Substances 0.000 description 4
- 239000007921 spray Substances 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 239000013502 plastic waste Substances 0.000 description 3
- 229910001220 stainless steel Inorganic materials 0.000 description 3
- 239000010935 stainless steel Substances 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- -1 Polypropylene Polymers 0.000 description 2
- 238000007635 classification algorithm Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 239000000470 constituent Substances 0.000 description 2
- 230000006866 deterioration Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000004064 recycling Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 229910052736 halogen Inorganic materials 0.000 description 1
- 125000001475 halogen functional group Chemical group 0.000 description 1
- 150000002367 halogens Chemical class 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 229910000953 kanthal Inorganic materials 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000000491 multivariate analysis Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000007747 plating Methods 0.000 description 1
- 229920000573 polyethylene Polymers 0.000 description 1
- 229920001155 polypropylene Polymers 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000012958 reprocessing Methods 0.000 description 1
- 239000011347 resin Substances 0.000 description 1
- 229920005989 resin Polymers 0.000 description 1
- 230000003746 surface roughness Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
- 125000000391 vinyl group Chemical group [H]C([*])=C([H])[H] 0.000 description 1
- 229920002554 vinyl polymer Polymers 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
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
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
-
- C—CHEMISTRY; METALLURGY
- C08—ORGANIC MACROMOLECULAR COMPOUNDS; THEIR PREPARATION OR CHEMICAL WORKING-UP; COMPOSITIONS BASED THEREON
- C08J—WORKING-UP; GENERAL PROCESSES OF COMPOUNDING; AFTER-TREATMENT NOT COVERED BY SUBCLASSES C08B, C08C, C08F, C08G or C08H
- C08J11/00—Recovery or working-up of waste materials
- C08J11/04—Recovery or working-up of waste materials of polymers
- C08J11/06—Recovery or working-up of waste materials of polymers without chemical reactions
-
- 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
- G01N21/27—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands using photo-electric detection ; circuits for computing concentration
- G01N21/274—Calibration, base line adjustment, drift correction
-
- 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
- G01N21/84—Systems specially adapted for particular applications
- G01N21/85—Investigating moving fluids or granular solids
-
- 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
- G01N21/84—Systems specially adapted for particular applications
- G01N2021/845—Objects on a conveyor
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
- Y02W30/00—Technologies for solid waste management
- Y02W30/50—Reuse, recycling or recovery technologies
- Y02W30/62—Plastics recycling; Rubber recycling
Landscapes
- Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Polymers & Plastics (AREA)
- Sustainable Development (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Medicinal Chemistry (AREA)
- Organic Chemistry (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Engineering & Computer Science (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Sorting Of Articles (AREA)
- Separation, Recovery Or Treatment Of Waste Materials Containing Plastics (AREA)
Abstract
Description
本揭示關於一種廢塑膠的材質判定裝置、材質判定方法、及材質判定程式。The present disclosure relates to a material judging device, material judging method, and material judging program for waste plastic.
為了在廢塑膠的再處理中進行物質回收,謀求以減少非對象物混入篩選後的產品的方式來提高純度。又,又,當原材料中含有高價物質時,謀求能夠以不遺漏任何高價物質的方式進行篩選。又,針對習知中由於無法分類而不得不進行熱回收的黑色塑膠,尋求為了物質回收而進行的效率較佳的材質判別及篩選。In order to recover materials in the reprocessing of waste plastics, we seek to improve the purity by reducing non-objects from being mixed into the screened products. In addition, when high-priced substances are contained in the raw materials, it is desired to be able to screen without missing any high-priced substances. In addition, for conventional black plastics that have to be heat-recovered because they cannot be sorted, a more efficient material identification and screening for material recovery is sought.
在專利文獻1中,記載將紅外光照射到篩選對象物上並接收來自篩選對象物的反射光,且使用基於反射光的頻譜並藉由圖案匹配的手法來判定篩選對象物的樹脂種類。
[先前技術文獻]
[專利文獻]In
[先前技術文獻] (專利文獻) 專利文獻1:日本特開2018-100903號公報[Prior Technical Literature] (Patent Document) Patent Document 1: Japanese Patent Application Publication No. 2018-100903
[發明所欲解決的問題]
然而,專利文獻1等記載的先前手法,在材質的判定精度上仍有改善的餘地。[The problem to be solved by the invention]
However, the previous methods described in
本揭示的目的在於提供一種廢塑膠的材質判定裝置、材質判定方法、及材質判定程式,其能夠提升廢塑膠的材質的判定精度。The purpose of the present disclosure is to provide a material judging device, material judging method, and material judging program for waste plastic, which can improve the judging accuracy of the material of waste plastic.
[解決問題的技術手段] 關於本發明的實施形態的一個觀點的廢塑膠的材質判定裝置,具備:照射部,其將光照射到在搬送路徑上搬送的廢塑膠片;反射頻譜檢測部,其接收藉由前述照射部所照射的光的反射光並檢測前述反射光的頻譜;第一判定部,其判定藉由前述反射頻譜檢測部所檢測到的前述頻譜,是前述廢塑膠片還是前述搬送路徑的哪一方的頻譜;第二判定部,其自藉由前述第一判定部判定為前述廢塑膠片的頻譜中抽出特徵量;及,第三判定部,其基於藉由前述第二判定部所抽出的前述特徵量來判別前述廢塑膠片的材質。[Technical means to solve the problem] The device for judging the material of waste plastic in one aspect of the embodiment of the present invention includes: an irradiating part that irradiates light to the waste plastic sheet conveyed on the conveying path; Reflected light of the irradiated light and detect the spectrum of the reflected light; a first determination unit that determines whether the spectrum detected by the reflected spectrum detection unit is the spectrum of the waste plastic sheet or the transport path; The second judging section, which extracts the characteristic quantity from the spectrum of the waste plastic sheet judged by the first judging section; and, the third judging section, which is based on the characteristic quantity extracted by the second judging section Identify the material of the aforementioned waste plastic sheet.
[發明的效果] 依據本揭示,能夠提供一種廢塑膠的材質判定裝置、材質判定方法、及材質判定程式,其能夠提升廢塑膠的材質的判定精度。[Effects of the invention] According to the present disclosure, a material judging device, material judging method, and material judging program for waste plastic can be provided, which can improve the judging accuracy of the material of waste plastic.
以下,參照隨附圖式來說明實施形態。為了方便對於說明的理解,針對各圖式中的相同構成元件儘可能附加相同的符號,並省略重複的說明。Hereinafter, the embodiment will be described with reference to the accompanying drawings. In order to facilitate the understanding of the description, the same symbols are attached as much as possible to the same constituent elements in the various drawings, and repeated descriptions are omitted.
另外,在以下的說明中,x方向、y方向、z方向是互相垂直的方向。x方向和y方向是水平方向,z方向是垂直方向。x方向是輸送帶2的搬送路徑3的搬送方向。y方向是輸送帶2的搬送路徑3的寬度方向。又,以下為了方便說明,會有將z正方向側表示為上側,將z負方向側表示為下側的情況。In addition, in the following description, the x direction, the y direction, and the z direction are directions perpendicular to each other. The x direction and the y direction are horizontal directions, and the z direction is the vertical direction. The x direction is the conveying direction of the
參照圖1~圖3,說明關於實施形態的廢塑膠的材質判定裝置1的概略構成。圖1是表示關於實施形態的廢塑膠的材質判定裝置1的概略構成的立體圖。圖2是圖1所示的廢塑膠的材質判定裝置1的側面圖。圖3是圖1所示的廢塑膠的材質判定裝置1的平面圖。此處,說明的例示,是材質判定對象的廢塑膠為黑色廢塑膠的情況,且混合有2種類的材質S1、S2(在圖1~圖3以四角形和三角形的標記來表示)的構成。以下,會有將2種類的材質S1、S2的黑色廢塑膠片一起以符號S來表示的情況。1 to 3, the schematic configuration of the
此黑色廢塑膠的材質判定裝置1,作為其主要部,具備:作為供給部的一例之振動進料器8,其依序供給黑色廢塑膠片S1、S2;及,作為搬送部的一例之輸送帶2,其搬送藉由振動進料器8供給的黑色廢塑膠片S1、S2。例如藉由投入用漏斗等來將粉碎後的黑色廢塑膠片S1、S2供給至振動進料器8上。振動進料器8,使載置有黑色廢塑膠片S1、S2之載置面振動,藉此一邊防止黑色廢塑膠片S1、S2彼此重疊,一邊供給至輸送帶2。輸送帶2,其頂面具有搬送路徑3,以往振動進料器8遠離的方向來搬送黑色廢塑膠片S1、S2。This black plastic waste
又,材質判定裝置1,作為其主要部,具備:作為照射部的一例之照明10,其將紅外線照射在黑色廢塑膠片S1、S2上;作為反射頻譜檢測部的一例之中紅外線相機4,其檢測來自黑色廢塑膠片S1、S2的反射頻譜;及,判別裝置5,其基於藉由中紅外線相機4所檢測到的反射頻譜來識別(identify)黑色廢塑膠片S1、S2的材質。照明10,具有例如鹵鎢燈等的紅外線光源也就是燈10A(參照圖6),並自燈10A朝向黑色廢塑膠片S1、S2照射紅外線。又,照明10,以使來自黑色廢塑膠片S1、S2的反射光入射到中紅外線相機4中的方式設置,且相對於中紅外線相機4設置在輸送帶2的運行方向的上部兩側(或上部單側)。In addition, the
中紅外線相機4,例如圖1所示,能夠以1台來檢測遍及寬度方向的全部區域,能夠沿著寬度方向區分為複數個(例如318個)區域並接收來自黑色廢塑膠片S1、S2的中紅外線的反射光,以在各區域中分別地檢測反射光的頻譜。中紅外線相機4,例如以附有中紅外線的波長區域3μm以上的分光器之相機來構成。中紅外線相機4,以例如230Hz的掃描頻率來實行檢測,每1次的掃描會將318個頻譜資料傳送到判別裝置5。判別裝置5,基於自中紅外線相機4接收到的318個頻譜資料來將318個各區域的材質判定結果輸出到後述的噴射控制部6。The
進一步,材質判定裝置1,在輸送帶2的搬送方向的下游側設置有噴射噴嘴7,以在與搬送方向交叉的方向上橫向或斜向地噴射氣體。噴射噴嘴7,在輸送帶2的寬度方向上並列地設置有複數個(例如318個),並藉由噴射控制部6來控制各個噴嘴的動作。噴射控制部6,對應於自判別裝置5接收到的材質判定結果,自噴射噴嘴7噴射氣體、或不噴射氣體,藉此對黑色廢塑膠片S1、S2進行分類並使其落下到例如藉由分隔板9而被區分的複數個區域(例如回收用漏斗)中,以收集想要的材質的廢塑膠。也就是說,本實施形態中,噴射控制部6、噴射噴嘴7、及分隔板9作為收集裝置12而發揮功能,該收集裝置12基於由判別裝置5所產生的材質判定結果,自在輸送帶2的搬送路徑3上流動(移動)的廢塑膠片中收集想要的材質。Furthermore, the
針對材質判定裝置1的動作進行說明。例如若藉由投入用漏斗等來將粉碎後的黑色廢塑膠片S1、S2供給至振動進料器8,則振動進料器8,以對被供給的黑色廢塑膠片S1、S2加以振動並且以不會重疊的方式往下游搬送,以供給至輸送帶2上。The operation of the
已供給至輸送帶2的頂面的搬送路徑3上的黑色廢塑膠片S1、S2,一邊在x正方向側的搬送方向被搬送,一邊在中紅外線相機4的可照相的位置,藉由來自照明10的紅外線加以照射。中紅外線相機4,接收藉由照明10所發出的紅外線照射在黑色廢塑膠片S1、S2上而產生的反射光,並將受光結果(受光頻譜的資料)輸出到判別裝置5。The black plastic scrap pieces S1 and S2 that have been supplied to the
判別裝置5,基於從中紅外線相機4輸入的受光結果來識別黑色廢塑膠片S1、S2。另外,依據判別裝置5之材質判定手法的詳細,參照圖4~圖9敘述於後。判別裝置5,將材質識別結果輸出到噴射控制部6。The
噴射控制部6,自被配置有複數個的噴射噴嘴7之中,選擇對應於材質的噴射噴嘴7,並算準時機來傳送控制訊號,接受到控制訊號之噴射噴嘴7,使噴嘴口打開並噴射氣體。依據判別裝置5的判別結果而在適當的時機自噴射噴嘴7來噴射氣體,藉此能夠將是篩選對象的材質與不是篩選對象的材質加以分離並回收。The
在圖2、圖3的例子中,輸送帶2上的黑色廢塑膠片S1,受到來自接收到控制訊號之噴射噴嘴7的氣體而被吹飛並落下到依據每個材質而設置的收集裝置中而被回收。又,輸送帶2上的黑色廢塑膠片S2,沒有受到來自噴射噴嘴7的氣體,所以在與黑色廢塑膠片S1不同的收集裝置12中被回收。藉由這種噴射噴嘴7的噴射和停止,能夠將複數種材質的黑色廢塑膠片,依據每種材質進行分類並回收。In the examples shown in Figures 2 and 3, the black waste plastic piece S1 on the
參照圖4~圖9,針對依據判別裝置5之判別材質的手法進行說明。圖4是判別裝置5的功能方塊圖。With reference to FIGS. 4 to 9, the method of judging materials based on the
如圖4所示,判別裝置5,具有前處理部51、第一判定部52、第二判定部53、及第三判定部54。As shown in FIG. 4, the
前處理部51,其實行藉由中紅外線相機4所檢測到的黑色廢塑膠片S1、S2的反射頻譜的補正和加工等的前處理。前處理部51,例如使用在反射光明亮的條件下測量到的頻譜、及在陰暗條件下測量到的頻譜來補正所檢測的反射頻譜。「陰暗條件」,是指比「明亮條件」相對較暗的條件。又,前處理部51,其實行自補正後的反射頻譜切出規定的頻率的範圍之加工。The
第一判定部52,其判定藉由中紅外線相機4所檢測到的頻譜,是廢塑膠片S1、S2還是輸送帶2的搬送路徑3的哪一方的頻譜。第一判定部52,其使用學習完成的One Class SVM(Support Vector Machine)來實行判定。The
One Class SVM(單類支援向量機),是機械學習的分類演算法的一種也就是SVM的一種。SVM中,以各類的支援向量(學習資料中的位於與其他類最近的位置)作為基準,以這些歐式距離(Euclidean distance)成為最大的方式設定識別邊界。又,當特徵是非線性時,使用核函數(kernel)來將資料映到特徵空間。適當地選擇核函數,藉此即使是複雜的資料配置也可以劃出識別邊界。One Class SVM (Single Class Support Vector Machine) is a type of classification algorithm for machine learning, which is also a type of SVM. In SVM, various support vectors (located in the closest position to other classes in the learning materials) are used as a reference, and the recognition boundary is set in such a way that these Euclidean distances become the largest. Moreover, when the feature is non-linear, a kernel function is used to map the data to the feature space. Appropriate selection of the kernel function, so that even the complex data configuration can also draw the recognition boundary.
One Class SVM中,對於一種類的學習資料使用被稱為核技巧(kernel trick)的手法,以將資料映射到高維空間的特徵空間。此時,以自原點遠離配置的方式映射學習資料,所以與原本的學習資料不類似的資料會聚集在原點的附近。使用此性質來實行正常資料(輸送帶2)與異常資料(物體(廢塑膠片S1、S2))的區別。In One Class SVM, a technique called kernel trick is used for a kind of learning materials to map the materials to the feature space of high-dimensional space. At this time, the learning materials are mapped away from the origin, so materials that are not similar to the original learning materials will gather near the origin. Use this property to distinguish between normal data (conveyor belt 2) and abnormal data (objects (waste plastic pieces S1, S2)).
在第一判定部52中使用圖案識別能力優異的One Class SVM,藉此能夠高精度地識別反射頻譜是被廢塑膠片S1、S2反射的頻譜,還是被輸送帶2的搬送路徑3反射的頻譜。另外,在第一判定部52中,也可以適用One Class SVM以外的機械學習的教導式學習(supervised learning)的分類手法。The One Class SVM with excellent pattern recognition capability is used in the
第二判定部53,自藉由第一判定部52判定為廢塑膠片的頻譜中抽出特徵資料Score1、Score2(特徵量)。第二判定部53,使用學習完成的PLS(Partial Least Squares:偏最小二乘法)來實行判定。The
PLS是機械學習的教導式學習的迴歸演算法的一種,其在自解釋變數算出的主成分之中,僅在少數的主成分與目標變數之間實行迴歸分析。PLS中,以主成分與目標變數的共變異數(covariance)變大的方式進行計算。本實施形態中,基於判定為被廢塑膠片S1、S2反射的反射頻譜的解釋變數,使用PLS來算出2種類的特徵資料Score1、Score2。PLS is a kind of regression algorithm of teaching learning of mechanical learning. Among the principal components calculated by self-explanatory variables, regression analysis is performed between only a few principal components and target variables. In PLS, the calculation is performed so that the covariance of the principal component and the target variable becomes larger. In this embodiment, based on the interpretation variable of the reflection spectrum determined to be reflected by the waste plastic sheets S1 and S2, PLS is used to calculate the two types of feature data Score1 and Score2.
第二判定部53,藉由使用PLS,能夠自反射頻譜的高維的解釋變數收斂成少數的特徵量,所以能夠抽出更容易區別的適當的特徵資料Score1、Score2。另外,在第二判定部53中,也可以適用PLS以外的機械學習的多變量解析手法。The
第三判定部54,基於藉由第二判定部53所抽出的反射頻譜的2種特徵資料Score1、Score2,來判別對應於此頻譜之廢塑膠片S1、S2的材質。第三判定部54,使用學習完成的決策樹(decision tree)來實行判定。決策樹,是教導式學習的分類演算法的一種。決策樹,是以樹狀結構來表示將目標變數進行分類的規則,其頻繁地被利用於分類問題中。The
在第三判定部54,藉由使用決策樹,能夠自反射頻譜的2種特徵資料Score1、Score2來精度良好地判別廢塑膠片S1、S2的材質。另外,在第三判定部54中,也可以適用決策樹以外的機械學習的教導式學習的分類手法。In the
判別裝置5,能夠以在物理上含有CPU(Central Processing Unit,中央處理單元)、主記憶裝置也就是RAM(Random Access Memory,隨機存取記憶體)和ROM(Read Only Memory,唯讀記憶體)、通訊模組、輔助記憶裝置等來構成電腦系統。如圖4所示的判別裝置5的各功能,是藉由在CPU和RAM等之中讀入規定的電腦軟體(材質判定程式),以基於CPU的控制來使各種硬體進行動作,並且實行在RAM中的資料的讀出和寫入來實現。亦即,在電腦上實行關於本實施形態的材質判定程式,藉此判別裝置5可作為圖4的前處理部51、第一判定部52、第二判定部53、第三判定部54而發揮功能。The
本實施形態的材質判別程式,例如儲存在電腦所具備的記憶裝置內。另外,材質判別程式,也可以構成為其一部分或全部是藉由通訊電路等傳輸介質來傳送,並藉由電腦所具備的通訊模組等來接收並記錄(包含安裝)。又,材質判別程式,也可以構成為在其一部分或全部自被儲存在CD-ROM、DVD-ROM、快閃記憶體等可攜帶的記憶媒體中的狀態下,記錄到電腦內(包含安裝)。The material discrimination program of this embodiment is stored in a memory device provided in a computer, for example. In addition, the material determination program can also be constructed in which part or all of it is transmitted by a transmission medium such as a communication circuit, and received and recorded (including installation) by a communication module or the like of a computer. In addition, the material determination program can also be configured to be recorded in a computer (including installation) in a state where part or all of it is stored in a portable storage medium such as CD-ROM, DVD-ROM, flash memory, etc. .
判別裝置5,也可以是由類比電路、數位電路或類比數位混合電路所構成的電路。又,也可以具備可實行判別裝置5的各功能的控制之控制電路。各電路的構裝,也可以依據ASIC(Application Specific Integrated Circuit,特殊應用積體電路)、FPGA(Field Programmable Gate Array,現場可程式化邏輯閘陣列)等來構裝。The
同樣地,噴射控制部6,也能夠在物理上以含有CPU、RAM和ROM、通訊模組、輔助記憶裝置等來構成電腦系統,並藉由在CPU和RAM中讀入規定的電腦軟體來實現其功能。Similarly, the
圖5是關於實施形態的廢塑膠的材質判別處理的流程圖。藉由判別裝置5來實行圖5所示的流程圖的各處理。Fig. 5 is a flowchart of the material discrimination processing of waste plastics according to the embodiment. The
在步驟S01中,藉由前處理部51,取得由中紅外線相機4獲得的頻譜Sorg
(n,w)。此處,n是感測器數目(藉由中紅外線相機4在輸送帶2的寬度方向上進行區分的頻譜檢測區域的數目),在感測器數目是318個的情況下,使用0~317的整數來對應各檢測領域。w是頻譜的波長,本實施形態中被設定為在2700(nm)~5300(nm)之間以20(nm)的刻度而設定合計131個波長,使用0~130的整數來對應各波長。也就是說,Sorg
(n,w)表示沿著輸送帶2的寬度方向的第n個頻譜檢測區域中的波長w的頻譜的強度的數值。In step S01, the
在步驟S02中,藉由前處理部51來補正在步驟S01中所取得的Sorg
(n,w),並算出完成補正的Scor
(n,w)。藉由此補正,能夠吸收由下述影響所造成的頻譜強度的特性的差異:測定空間的水蒸氣和二氧化碳的濃度變化;測量對象的黑色廢塑膠片S1、S2的溫度;照明及中紅外線相機4的長年劣化;輸送帶2上的位置等。完成補正的Scor
(n,w),能夠藉由下述算式(1)來算出。In step S02, the preprocessing
[算式1]
此處,Wref
(n,w),是在反射光明亮的條件下測得的第一補正用頻譜。Dref
(n,w),是在反射光比上述明亮條件更暗的條件下測得的第二補正用頻譜。這些補正用頻譜Wref
(n,w)、Dref
(n,w),例如能夠在實行材質判別處理之前,當實行中紅外線相機4的校正時進行抽出。[Equation 1] Here, W ref (n, w) is the first correction spectrum measured under the condition of bright reflected light. D ref (n, w) is the second correction spectrum measured under the condition that the reflected light is darker than the above-mentioned bright condition. These correction frequency spectra W ref (n, w) and D ref (n, w) can be extracted when performing correction of the
圖6是表示補正用的頻譜Wref
(n,w)、Dref
(n,w)的抽出手法的圖。如圖6所示,在輸送帶2的搬送路徑3上的中紅外線相機4的照相區域中,設置用以取得補正用頻譜之校正板11,並藉由中紅外線相機4來實行反射光的頻譜的檢測,藉此能夠取得補正用的頻譜Wref
(n,w)、Dref
(n,w)。Fig. 6 is a diagram showing a method of extracting frequency spectra W ref (n, w) and D ref (n, w) for correction. As shown in FIG. 6, in the photographing area of the
當是在反射光明亮的條件下測量的第一補正用頻譜Wref (n,w)時,配置可反射全部的中紅外線區域的波長之校正板11(鋁、不銹鋼等),在點亮照明10的狀態下,對於全部的感測器(n=0、1、2、…、317),取得全波長(w=0(2700)、1(2720)、2(2740)、…、130(5300))的資料。In the case of the first correction spectrum W ref (n, w) measured under the condition of bright reflected light, a correction plate 11 (aluminum, stainless steel, etc.) that can reflect all the wavelengths of the mid-infrared region is arranged, and the illumination is turned on. In the state of 10, for all sensors (n=0, 1, 2, ..., 317), obtain the full wavelength (w=0 (2700), 1 (2720), 2 (2740), ..., 130 ( 5300)).
當是在反射光陰暗的條件下檢測的第二補正用頻譜Dref (n,w)時,配置可反射全部的中紅外線區域的波長之校正板11(鋁、不銹鋼等),在關掉照明10的狀態(或關閉相機的快門的狀態)下,對於全部的感測器(n=0、1、2、…、317),取得全波長(w=0(2700)、1(2720)、2(2740)、…、130(5300))的資料。 When the second correction spectrum D ref (n, w) is detected under the dark condition of reflected light, a correction plate 11 (aluminum, stainless steel, etc.) that can reflect all the wavelengths of the mid-infrared region is arranged, and the illumination is turned off. In the state of 10 (or the state of closing the shutter of the camera), for all the sensors (n=0, 1, 2, ..., 317), obtain the full wavelength (w=0(2700), 1(2720), 2(2740),...,130(5300)).
例如圖6的虛線的箭頭標記所示,當要取得補正用的頻譜Wref
(n,w)、Dref
(n,w)時所配置的校正板11,較佳為設置成可在輸送帶2的搬送路徑3上的中紅外線相機4的照相區域的位置與自中紅外線相機4的照相區域和照明10的照射範圍避開的待機位置之間移動。換句話說,校正板11,可固定在中紅外線相機4的視野內的規定位置、及視野外的規定位置,且較佳為可在兩方的規定位置之間移動。校正板11,較佳為以要承受來自照明10的光之主面的表面粗度大而成為粗糙的面的方式進行加工。藉此,能夠抑制反射光的光暈。For example, as shown by the dotted arrow mark in Fig. 6, when the correction frequency spectrum W ref (n, w) and D ref (n, w) are to be obtained, the
又,當要取得補正用頻譜時,也可以停止輸送帶2。此時,若校正板11的動作出了什麼狀況,造成校正板11沒有正確地配置在中紅外線相機4的照相區域的位置,則照明10的紅外線會造成在輸送帶2的搬送路徑3上的被紅外線照射的部分的溫度上升,而可能燒毀或起火。因此,較佳為當校正板11沒有被固定在中紅外線相機4的視野內時,以不會自照明10照射紅外線的方式設置互鎖(interlock)。In addition, when the spectrum for correction is to be acquired, the
另外,如圖6所示,照明10,具有紅外線光源也就是燈10A(護套加熱器、碳素燈、kanthal型燈等)、及可收集燈10A的熱之反射板10B。燈10A,以沿著輸送帶2的寬度方向(y方向)延伸的方式形成,並且配置成沿著y軸朝向環繞軸心的全方向放射紅外線。反射板10B,以燈10A作為基準被配置在與輸送帶2的搬送路徑3相反的一側,並沿著環繞燈10A的軸心的圓周方向彎曲而形成,藉此能夠收集自燈10A往與輸送帶2相反的一側放射的紅外線並往輸送帶2側反射而送出。反射板10B,例如由鋁、不銹鋼、或鋁鍍膜等構件而構成。In addition, as shown in FIG. 6, the
回到圖5,在步驟S03中,藉由前處理部51以自補正完成的頻譜Scor
(n,w)切出具有特徵之波長區域。圖7是表示自反射波頻譜切出具有特徵之波長區域的處理的一例的圖。圖7的橫軸表示頻譜的波長(nm),縱軸表示各波長中的頻譜的強度。圖7中表示ABS(Acrylonitrile Butadiene Styrene,丙烯腈-丁二烯-苯乙烯共聚物)、HIPS(High-impact polystyrene,耐衝擊聚苯乙烯)、PP(Polypropylene,聚丙烯)、PE(Polyethylene,聚乙烯)的各材質的頻譜的一例。再者,圖7的例子中,切出3250~3750(nm)和4400~4600(nm)的波長區域的頻譜。圖7的例子中,以網點圖樣來表示被切出的波長區域的範圍。Returning to FIG. 5, in step S03, the
回到圖5,在步驟S04中,藉由第一判定部52,使用在步驟S02中被補正且在步驟S03中被切出的具有特徵之波長區域的頻譜,來判定各頻譜是輸送帶2的帶子(搬送路徑3)還是搬送路徑3上的物體(廢塑膠片)。第一判定部52,在本實施形態中是利用完成學習的One Class SVM來實行判定。Returning to FIG. 5, in step S04, the first determining
在步驟S05中,藉由第二判定部53,使用學習完成的PLS以自在步驟S04中被判定為物體(廢塑膠)的頻譜中抽出2種類的特徵資料Score1、Score2。圖8是表示特徵資料的抽出例的圖。圖8的橫軸表示第一特徵資料(Score1),縱軸表示第二特徵資料(Score2)。圖8中表示圖7所例示的ABS、HIPS、PP、PE的4種類的材質的抽出例。如圖8所示,依據2種特徵資料Score1、Score2而可在二維空間上針對各材質標定出(plot)各自的區域並加以區分。另外,特徵資料的數目,也可以是2種類以外。In step S05, the
回到圖5,在步驟S06中,藉由第三判定部54,基於在步驟S5中所抽出的2種類的特徵資料Score1、Score2,使用學習完成的決策樹來實行材質的判別。圖9是表示使用決策樹來判別材質的例子的圖。本實施形態中,為了最終可識別4種類的材質(PE、PP、ABS、HIPS),如圖9所示,決策樹具有2階層的條件跳轉(conditional jump)。在第一階層中,使用條件跳轉的函數f1(Score1、Score2),將特徵資料Score1、Score2的組分成二個群組G1、G2。一方的群組G1,在第二階層中,使用條件跳轉的函數f2(Score1、Score2),進一步被分成二個群組G11、G12。另一方的群組G2,在第二階層中,使用條件跳轉的函數f3(Score1、Score2),進一步被分成二個群組G21、G22。此結果,特徵資料Score1、Score2的組,被分類成四個群組G11、G12、G21、G22,且各群組的材質分別地被判定為PE、PP、ABS、HIPS。Returning to FIG. 5, in step S06, the
這樣一來,關於本實施形態的廢塑膠的材質判定裝置1的判別裝置5,具備:第一判定部52,其判定藉由中紅外線相機4所檢測到的反射光的頻譜,是廢塑膠片S還是搬送路徑3的哪一方的頻譜,該反射光是藉由照明10照射到輸送帶2的搬送路徑3上的光的反射光;第二判定部53,其自藉由第一判定部52判定為廢塑膠片S的頻譜中抽出2種類的特徵資料Score1、Score2;及,第三判定部54,其基於藉由第二判定部53所抽出的特徵資料Score1、Score2來判別廢塑膠片S的材質S1、S2。In this way, the judging
藉由此構成,自反射頻譜的輸入資訊,經過三階段的判定處理和資料的檢索,能夠得到廢塑膠的材質的輸出資訊,該三階段的判定處理和資料的檢索包含:依據第一判定部52的判別物體來檢索黑色塑膠片S的頻譜、依據第二判定部53的抽出特徵量以自頻譜資訊加以維度縮減(Dimensionality Reduction)而成為特徵資料、及依據第三判定部54的分類處理。因此,本實施形態的廢塑膠的材質判定裝置1,能夠考慮多種條件來實行廢塑膠的材質的判定,且成為可經由多個階段細膩地實行,能夠提升廢塑膠的材質的判定精度。With this structure, the input information of the self-reflective spectrum can be obtained through three-stage determination processing and data retrieval to obtain the output information of the material of the waste plastic. The three-stage determination processing and data retrieval include: according to the first determination section The identification object of 52 is used to retrieve the frequency spectrum of the black plastic sheet S, the extracted feature amount of the
又,關於本實施形態的廢塑膠的材質判定裝置1的判別裝置5,具備前處理部51,該前處理部51使用在反射光明亮的條件下測得的第一補正用頻譜Wref
(n,w)、及在比此明亮條件相對更暗的條件下測得的第二補正用頻譜Dref
(n,w),來補正藉由中紅外線相機4所檢測到的反射頻譜Sorg
(n,w)。In addition, the
這種反射頻譜Sorg
(n,w),例如使用算式(1)並使用補正用的頻譜Wref
(n,w)、Dref
(n,w)來進行補正,藉此能夠抑制由於下述影響所造成的頻譜強度的特性的差異:測量對象的黑色廢塑膠片S1、S2的溫度;中紅外線相機4的長年劣化;輸送帶2上的位置等。因此,使用補正完成的頻譜Scor
(n,w),實行第一判定部52、第二判定部53、第三判定部54的學習和判斷,藉此能夠進一步提升廢塑膠的材質的判定精度。Such reflection spectrum S org (n,w) can be corrected by using equation (1) and the spectrum W ref (n,w) and D ref (n,w) for correction, thereby suppressing the following The difference in the characteristics of the spectrum intensity caused by the influence: the temperature of the black waste plastic sheets S1 and S2 of the measurement object; the long-term deterioration of the
又,前處理部51,進一步實行自補正後的頻譜Scor
(n,w)切出規定的波長的範圍之加工,將加工後的頻譜輸出至第一判定部52。In addition, the
藉由此構成,能夠自頻譜中抽出與廢塑膠的材質關聯性強的部分,並利用於第一判定部52、第二判定部53、第三判定部54的學習和判定,所以能夠減少阻礙學習和判定之雜訊的混入,以進一步提升廢塑膠的材質的判定精度。With this configuration, it is possible to extract the parts with strong relevance to the material of the waste plastic from the spectrum and use them for learning and judgment of the
另外,本實施形態中,前處理部51,也可以構成為實行反射頻譜Sorg
(n,w)的補正處理、及切出規定的頻率的範圍的處理之2個處理,也可以僅實行2個處理的其中一方。In addition, in the present embodiment, the
又,本實施形態中,以材質判定對象的廢塑膠是黑色廢塑膠S的情況作為例示來說明,但是也可以是例如紅色和藍色等其他顏色的廢塑膠。又,也可以使用混雜不同顏色的廢塑膠。In addition, in this embodiment, the case where the waste plastic targeted for material determination is black waste plastic S is described as an example, but it may be waste plastics of other colors such as red and blue. In addition, waste plastics mixed with different colors can also be used.
參照圖10~圖14,針對依據本實施形態的材質判定裝置1之想要的材質的廢塑膠的篩選手法進行說明。圖10是表示依據本實施形態的材質判定裝置1來進行的第一材質篩選手法的平面圖。圖10中,對應於在圖3所示的材質判定裝置1的平面圖,並簡略化地進行圖示。圖10以後,作為篩選手法的一例,以混合有5種類的材質(1)、(2)、(3)、(4)、(5)之塑膠混合體作為篩選對象進行說明。10-14, the screening method of the waste plastic of the desired material according to the
圖10的例子中例示,輸送帶2和收集裝置12,在輸送帶2的寬度方向(y方向)沒有被區分而形成為一系統的搬送路徑的構成。如圖2等所示般,藉由噴射噴嘴7的噴射和停止並以分隔板9作為邊界來分類廢塑膠,所以在收集裝置12中可將篩選對象大致分類為2種類。因此,為了將混雜有篩選對象的5種類的材質之塑膠混合體,個別地篩選成各種單一材質,必須在收集裝置12之中的一方的收集裝置12-1(例如自噴射噴嘴7噴射氣體以回收廢塑膠之裝置)重複地進行一次一種類的分類處理。也就是說,如圖10所示,首先僅自塑膠混合體中僅分類材質(1)並在收集裝置12-1中回收。此時,在另一方的收集裝置12-2中收集的剩下的塑膠混合體混雜有其他4種類的材質(2)~(5)。接著,將混雜有4種類之剩下的塑膠混合體再次投入材質判定裝置1中,並分類出(2)~(5)的任一種。此手續重複4次,藉此能夠分類出5種類的材質(1)~(5)的各種材質。In the example of FIG. 10, the
圖11是表示依據本實施形態的材質判定裝置1A來進行的第二材質篩選手法的平面圖。圖11以後,輸送帶2的搬送路徑3,在寬度方向被區分而形成第一系統和第二系統這二個系統。更詳細來說,投入口(振動進料器8)、輸送帶2、收集裝置12,個別地在寬度方向被分成2個。另外,振動進料器8和輸送帶2,其構成要素沒有被分成2個,而是在單一要素中以系統之間不會混雜的方式附加有分隔件等。例如能夠在寬度方向幾乎中央的位置沿著搬送方向設置分隔壁,以將輸送帶2的搬送路徑3區分成二個系統。FIG. 11 is a plan view showing a second material selection method performed by the
以下說明中,第一系統以附加字A來表示,第二系統以附加字B來表示。又,相當於圖10的收集裝置12-1的構件標記為「收集裝置A1」和「收集裝置B1」,相當於圖10的收集裝置12-2的構件標記為「收集裝置A2」和「收集裝置B2」。In the following description, the first system is represented by an additional word A, and the second system is represented by an additional word B. In addition, the components corresponding to the collection device 12-1 of FIG. 10 are labeled "collection device A1" and "collection device B1", and the components equivalent to the collection device 12-2 of FIG. 10 are labeled "collection device A2" and "collection device A2" and "collection device B1". Device B2".
圖11的例子中,在第一系統和第二系統中收集相同材質的廢塑膠片。例如圖11所示,將混雜有5種類的材質(1)~(5)之塑膠混合體,供給至第一系統和第二系統的各自的投入口A、B,在各系統中實行材質判定,並在收集裝置A1、B1中收集相同材質(1)的廢塑膠片。又,在收集裝置A2、B2中收集混雜有剩下的材質(2)~(5)之廢塑膠。In the example of FIG. 11, waste plastic pieces of the same material are collected in the first system and the second system. For example, as shown in Figure 11, a plastic mixture mixed with 5 types of materials (1) to (5) is supplied to the respective input ports A and B of the first system and the second system, and the material determination is performed in each system , And collect waste plastic pieces of the same material (1) in the collection devices A1 and B1. In addition, the waste plastics mixed with the remaining materials (2) to (5) are collected in the collection devices A2 and B2.
圖12是表示依據本實施形態的材質判定裝置1B來進行的第三材質篩選手法的平面圖。圖12的例子中,在第一系統中,收集第一材質的廢塑膠片,並且將剩下的廢塑膠片供給至第二系統;在第二系統中,收集第二材質的廢塑膠片。圖12的例子中,能夠將複數種的混合原材料分類成第一材質、第二材質、及其他材質的3種類。Fig. 12 is a plan view showing a third material selection method performed by the
圖12的例子中,將混雜有5種類的材質(1)~(5)之塑膠混合體,供給至第一系統的投入口A,在第一系統的輸送帶A實行材質判定,並在收集裝置A1中收集材質(1)的廢塑膠片。又,在收集裝置A2中,收集混雜有剩下的材質(2)~(5)之廢塑膠。In the example of Figure 12, a plastic mixture mixed with 5 types of materials (1) to (5) is supplied to the input port A of the first system, and the material is judged on the conveyor belt A of the first system and collected The waste plastic pieces of material (1) are collected in the device A1. In addition, the collection device A2 collects waste plastic mixed with the remaining materials (2) to (5).
接著,將在收集裝置A2中收集的混雜有剩下的材質(2)~(5)之廢塑膠,藉由搬送裝置13搬送到第二系統的投入口B,並供給至投入口B。在第二系統的輸送帶B實行材質判定,並在收集裝置B1中收集材質(2)的廢塑膠片。又,在收集裝置B2中,收集混雜有剩下的材質(3)~(5)之廢塑膠。Next, the waste plastic mixed with the remaining materials (2) to (5) collected in the collection device A2 is conveyed to the input port B of the second system by the conveying
圖13是表示依據本實施形態的材質判定裝置1C來進行的第四材質篩選手法的平面圖。圖13的例子中,在第一系統中,收集第一材質和微量的其他材質的廢塑膠片,並且將已收集的廢塑膠片供給至第二系統;在第二系統中,自第一材質和微量的其他材質的廢塑膠片中收集第一材質的廢塑膠片。圖13的例子中,能夠針對規定的一種材質的塑膠片進行高純度的篩選。Fig. 13 is a plan view showing a fourth material selection method performed by the material judging device 1C of the present embodiment. In the example of FIG. 13, in the first system, waste plastic pieces of the first material and a small amount of other materials are collected, and the collected waste plastic pieces are supplied to the second system; in the second system, from the first material Collect waste plastic pieces of the first material from a small amount of waste plastic pieces of other materials. In the example of FIG. 13, high-purity screening can be performed on a plastic sheet of a predetermined material.
圖13的例子中,將混雜有5種類的材質(1)~(5)之塑膠混合體,供給至第一系統的投入口A,在第一系統的輸送帶A實行材質判定,並在收集裝置A1中收集材質(1)和微量的(2)~(5)的廢塑膠片。又,在收集裝置A2中,收集混雜有剩下的材質(2)~(5)和微量的(1)之廢塑膠。In the example of Figure 13, a plastic mixture mixed with 5 types of materials (1) to (5) is supplied to the input port A of the first system, and the material is judged on the conveyor belt A of the first system and collected The device A1 collects material (1) and a small amount of waste plastic pieces (2) to (5). In addition, the collection device A2 collects waste plastic mixed with the remaining materials (2) to (5) and a small amount of (1).
接著,將在收集裝置A1中收集的混雜有材質(1)和微量的(2)~(5)之廢塑膠,藉由搬送裝置13搬送到第二系統的投入口B,並供給至投入口B。在第二系統的輸送帶B實行材質判定,並在收集裝置B1中再度篩選材質(1)並收集材質(1)的廢塑膠片。在此收集裝置B1中收集的材質(1),比在收集裝置A1中收集的材質(1)的純度更高。在收集裝置B2中,收集混雜有剩下的材質(1)~(5)之廢塑膠。Next, the waste plastic mixed with materials (1) and trace amounts of (2) to (5) collected in the collection device A1 is transported to the input port B of the second system by the
圖14是表示依據本實施形態的材質判定裝置1D來進行的第五材質篩選手法的平面圖。圖14的例子中,在第一系統中,排除第一材質和微量的其他材質的廢塑膠片,並且將排除後的剩下的廢塑膠片供給至第二系統;在第二系統中,自其他的廢塑膠片中,進一步排除第一材質和微量的其他材質的廢塑膠片,以收集不含第一材質之廢塑膠片。圖14的例子中,能夠自混雜原材料中更確實地篩選一種規定的材質的塑膠片。FIG. 14 is a plan view showing a fifth material screening method performed by the
圖14的例子中,將混雜有5種類的材質(1)~(5)之塑膠混合體,供給至第一系統的投入口A,在第一系統的輸送帶A實行材質判定,並在收集裝置A1中收集材質(1)和微量的(2)~(5)的廢塑膠片。又,在收集裝置A2中,收集混雜有剩下的材質(2)~(5)和少量的(1)之廢塑膠。In the example of Figure 14, a plastic mixture mixed with 5 types of materials (1) to (5) is supplied to the input port A of the first system, and the material is judged on the conveyor belt A of the first system, and then collected The device A1 collects material (1) and a small amount of waste plastic pieces (2) to (5). In addition, the collection device A2 collects waste plastic mixed with the remaining materials (2) to (5) and a small amount of (1).
接著,將在收集裝置A2中收集的混雜有材質(2)~(5)和少量的(1)之廢塑膠,藉由搬送裝置13搬送到第二系統的投入口B,並供給至投入口B。在第二系統的輸送帶B實行材質判定,並在收集裝置B1中再度篩選材質(1)並收集材質(1)和微量的材質(2)~(5)的廢塑膠片。又,在收集裝置B2中,收集混雜有剩下的材質(2)~(5)和微量的(1)之廢塑膠。Next, the waste plastic mixed with materials (2) to (5) and a small amount of (1) collected in the collection device A2 is transported to the inlet B of the second system by the
圖15是表示材質判定裝置1的操作畫面的一例的圖。圖15所示的操作畫面,例如在設置於材質判定裝置1的本體的表示裝置上表示。如圖15所示,在操作畫面中,列舉出篩選的塑膠的材質名稱,成為可個別地選擇在上述第一系統(在圖15中的「1次」和第二系統(在圖15中的「2次」)中各自地噴射並篩選的材質。表示有操作畫面之表示裝置,例如是觸控面板,藉由按下「噴射選擇」欄的「OFF」表示等的操作來切換成「ON」表示,藉此能夠設定為當該材質(圖15中的ABS)的情況,使噴射噴嘴7噴射氣體並分類到收集裝置中。又,操作畫面中,也能夠設置「投入原料面積比」欄,對應於材料判定處理的判定結果來表示混合在原材料中的各材質的比率。FIG. 15 is a diagram showing an example of the operation screen of the
以上,參照具體例並對於本實施型態進行說明。但是,本揭示不限定於這些具體例。這些具體例,也可由業者來施加適當的設計變化,只要具備本揭示的特徵,都包含在本揭示的範圍中。前述各具體例所具備的各構件及其配置、條件、形狀等,不限定於已例示的構件而能夠適當地變化。前述各具體例所具備的各構件,只要沒有產生技術上的矛盾,能夠適當地組合變化。In the above, this embodiment is described with reference to specific examples. However, this disclosure is not limited to these specific examples. These specific examples can also be appropriately changed by the manufacturer, and as long as they have the characteristics of the present disclosure, they are all included in the scope of the present disclosure. The members provided in the foregoing specific examples and their arrangement, conditions, shapes, and the like are not limited to the members already exemplified and can be changed as appropriate. As long as there is no technical contradiction, the components included in the foregoing specific examples can be appropriately combined and changed.
本國際申請,基於2020年2月13日申請的日本專利申請2020-022811號而主張優先權,此處在本國際申請中援引2020-022811號的全部內容。This international application claims priority based on Japanese Patent Application No. 2020-022811 filed on February 13, 2020, and the entire content of No. 2020-022811 is cited here in this international application.
1,1A,1B,1C,1D:廢塑膠的材質判定裝置
2:輸送帶
3:搬送路徑
4:中紅外線相機(反射頻譜檢測部)
5:判別裝置
6:噴射控制部
7:噴射噴嘴
8:振動進料器
9:分隔板
10:照明
10A:燈
10B:反射板
11:校正板
12,12-1,12-2,A1,A2,B1,B2:收集裝置
13:搬送裝置
51:前處理部
52:第一判定部
53:第二判定部
54:第三判定部
S,S1,S2:材質(廢塑膠片、黑色廢塑膠片)1, 1A, 1B, 1C, 1D: Material judging device for waste plastic
2: Conveyor belt
3: Transport path
4: Mid-infrared camera (reflection spectrum detection part)
5: Discrimination device
6: Injection control department
7: Jet nozzle
8: Vibrating feeder
9: Divider
10:
圖1是表示關於實施形態的廢塑膠的材質判定裝置的概略構成的立體圖。 圖2是圖1所示的廢塑膠的材質判定裝置的側面圖。 圖3是圖1所示的廢塑膠的材質判定裝置的平面圖。 圖4是判別裝置的功能方塊圖。 圖5是關於實施形態的廢塑膠的材質判別處理的流程圖。 圖6是表示補正用的頻譜的抽出手法的圖。 圖7是表示自反射波頻譜切出具有特徵之波長區域的處理的一例的圖。 圖8是表示特徵資料的抽出例的圖。 圖9是表示使用決策樹來判別材質的例子的圖。 圖10是表示依據本實施形態的材質判定裝置來進行的第一材質篩選手法的平面圖。 圖11是表示依據本實施形態的材質判定裝置來進行的第二材質篩選手法的平面圖。 圖12是表示依據本實施形態的材質判定裝置來進行的第三材質篩選手法的平面圖。 圖13是表示依據本實施形態的材質判定裝置來進行的第四材質篩選手法的平面圖。 圖14是表示依據本實施形態的材質判定裝置來進行的第五材質篩選手法的平面圖。 圖15是表示材質判定裝置的操作畫面的一例的圖。Fig. 1 is a perspective view showing a schematic configuration of a waste plastic material judging device according to an embodiment. Fig. 2 is a side view of the material judging device for waste plastic shown in Fig. 1. Fig. 3 is a plan view of the material judging device for waste plastic shown in Fig. 1. Fig. 4 is a functional block diagram of the discrimination device. Fig. 5 is a flowchart of the material discrimination processing of waste plastics according to the embodiment. Fig. 6 is a diagram showing a method of extracting a frequency spectrum for correction. FIG. 7 is a diagram showing an example of processing for cutting out characteristic wavelength regions from the reflected wave spectrum. Fig. 8 is a diagram showing an example of extraction of feature data. FIG. 9 is a diagram showing an example of using a decision tree to determine material. Fig. 10 is a plan view showing a first material selection method performed by the material judging device of the present embodiment. Fig. 11 is a plan view showing a second material selection method performed by the material judging device of the present embodiment. Fig. 12 is a plan view showing a third material selection method performed by the material judging device of this embodiment. Fig. 13 is a plan view showing a fourth material selection method performed by the material judging device of this embodiment. Fig. 14 is a plan view showing a fifth material selection method performed by the material judging device of the present embodiment. Fig. 15 is a diagram showing an example of an operation screen of the material judging device.
國內寄存資訊 (請依寄存機構、日期、號碼順序註記) 無Domestic hosting information (please note in the order of hosting organization, date and number) without
國外寄存資訊 (請依寄存國家、機構、日期、號碼順序註記) 無Foreign hosting information (please note in the order of hosting country, institution, date, and number) without
5:判別裝置 5: Discrimination device
51:前處理部 51: Pre-processing department
52:第一判定部 52: First Judgment Section
53:第二判定部 53: Second Judgment Department
54:第三判定部 54: Third Judgment Department
Claims (14)
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2020-022811 | 2020-02-13 | ||
JP2020022811A JP7419093B2 (en) | 2020-02-13 | 2020-02-13 | Waste plastic sorting equipment, sorting method, and sorting program |
Publications (1)
Publication Number | Publication Date |
---|---|
TW202136744A true TW202136744A (en) | 2021-10-01 |
Family
ID=77292398
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW110103638A TW202136744A (en) | 2020-02-13 | 2021-02-01 | Waste plastic material determination device, material determination method, and material determination program |
Country Status (5)
Country | Link |
---|---|
JP (1) | JP7419093B2 (en) |
KR (1) | KR20220137627A (en) |
CN (1) | CN115003425A (en) |
TW (1) | TW202136744A (en) |
WO (1) | WO2021161779A1 (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2023167533A (en) * | 2022-05-12 | 2023-11-24 | キヤノン株式会社 | identification device |
Family Cites Families (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005249624A (en) * | 2004-03-05 | 2005-09-15 | Japan Science & Technology Agency | Polymer group discriminating method by optical spectrum |
JP4962342B2 (en) * | 2008-02-12 | 2012-06-27 | 株式会社カネカ | Synthetic fiber nonwoven fabric production method and cloth-like and / or cotton-like fiber separation device |
JP5367145B1 (en) * | 2012-12-10 | 2013-12-11 | ダイオーエンジニアリング株式会社 | Black waste plastic material sorting device |
JP5920236B2 (en) * | 2013-02-05 | 2016-05-18 | 東洋ライス株式会社 | Color sorter and color sort method |
JP2016080402A (en) * | 2014-10-10 | 2016-05-16 | キヤノン株式会社 | Learning device, learning method and program |
JP2016091359A (en) * | 2014-11-06 | 2016-05-23 | 株式会社リコー | Information processing system, information processing device, information processing method, and program |
JP6528665B2 (en) * | 2015-12-08 | 2019-06-12 | 株式会社島津製作所 | Sample identification method and sample identification device |
JP2018100903A (en) | 2016-12-20 | 2018-06-28 | パナソニックIpマネジメント株式会社 | Resin determination method and apparatus |
JP6880909B2 (en) * | 2017-03-28 | 2021-06-02 | 宇部興産株式会社 | How to Sort Carbon Fiber Reinforced Composites from Waste Plastic Mixtures |
JP7137772B2 (en) * | 2017-11-07 | 2022-09-15 | 大日本印刷株式会社 | Inspection system, inspection method and manufacturing method of inspection system |
WO2019140245A1 (en) * | 2018-01-12 | 2019-07-18 | Tyton Biosciences, Llc | Methods for recycling cotton and polyester fibers from waste textiles |
JP6987698B2 (en) * | 2018-05-21 | 2022-01-05 | 大王製紙株式会社 | Sorting equipment, sorting methods and programs, and computer-readable recording media |
JP7150481B2 (en) * | 2018-05-30 | 2022-10-11 | 大王製紙株式会社 | Processing method and processing system for used paper packaging including contraindicated items |
JP7087735B2 (en) * | 2018-06-29 | 2022-06-21 | 株式会社リコー | Spectroscopic property acquisition device, image forming device, and management system for image forming device |
-
2020
- 2020-02-13 JP JP2020022811A patent/JP7419093B2/en active Active
-
2021
- 2021-01-26 KR KR1020227023966A patent/KR20220137627A/en unknown
- 2021-01-26 CN CN202180011546.5A patent/CN115003425A/en active Pending
- 2021-01-26 WO PCT/JP2021/002624 patent/WO2021161779A1/en active Application Filing
- 2021-02-01 TW TW110103638A patent/TW202136744A/en unknown
Also Published As
Publication number | Publication date |
---|---|
KR20220137627A (en) | 2022-10-12 |
CN115003425A (en) | 2022-09-02 |
JP2021128062A (en) | 2021-09-02 |
JP7419093B2 (en) | 2024-01-22 |
WO2021161779A1 (en) | 2021-08-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Rozenstein et al. | Development of a new approach based on midwave infrared spectroscopy for post-consumer black plastic waste sorting in the recycling industry | |
Bonifazi et al. | A hierarchical classification approach for recognition of low-density (LDPE) and high-density polyethylene (HDPE) in mixed plastic waste based on short-wave infrared (SWIR) hyperspectral imaging | |
EP2832458B1 (en) | Optical type granule sorting machine | |
Kroell et al. | Optical sensors and machine learning algorithms in sensor-based material flow characterization for mechanical recycling processes: A systematic literature review | |
CN112218729A (en) | Process and system for built-in inspection of product streams for detecting foreign objects | |
US20140367316A1 (en) | Methods and apparatus for identifying and sorting materials using terahertz waves | |
CN108738338A (en) | Method and apparatus for detecting the chaff interferent in sample | |
EP3450029A1 (en) | Classification method and apparatus | |
KR20160084810A (en) | Fish species determination device and fish species determination method | |
Zulkifley et al. | Robust identification of polyethylene terephthalate (PET) plastics through bayesian decision | |
TW202136744A (en) | Waste plastic material determination device, material determination method, and material determination program | |
KR101298109B1 (en) | Apparatus for color discrimination in visible light band and plastic classification system using thereof | |
JP2011226821A (en) | Identification device and identification method | |
Serranti et al. | Hyperspectral imaging and its applications | |
US9449255B2 (en) | Method and apparatus for the determination of classification parameters for the classification of bank notes | |
TW202132765A (en) | Material determination device for waste plastics | |
Jabłoński et al. | Vision-based assessment of viability of acorns using sections of their cotyledons during automated scarification procedure | |
JP2017161262A (en) | Granular matter appearance quality discrimination device | |
JP7345776B2 (en) | Agricultural product sorting equipment | |
JP2011117901A (en) | Plastic discrimination device and method therefor | |
de Lima Ribeiro et al. | Multi-sensor characterization for an improved identification of polymers in WEEE recycling | |
KR20230099007A (en) | Apparatus for sorting waste plastic and sorting maethod using the same | |
WO2023007824A1 (en) | Sorting device for waste plastic, and method for sorting waste plastic | |
EP4270304A1 (en) | Identification method for object-to-be-sorted, sorting method, sorting device, and identification device | |
WO2023017639A1 (en) | Sorting system for waste plastic and sorting method for waste plastic |