EP0562506A2 - Verfahren und Vorrichtung zum Sortieren von Schüttgut - Google Patents

Verfahren und Vorrichtung zum Sortieren von Schüttgut Download PDF

Info

Publication number
EP0562506A2
EP0562506A2 EP93104640A EP93104640A EP0562506A2 EP 0562506 A2 EP0562506 A2 EP 0562506A2 EP 93104640 A EP93104640 A EP 93104640A EP 93104640 A EP93104640 A EP 93104640A EP 0562506 A2 EP0562506 A2 EP 0562506A2
Authority
EP
European Patent Office
Prior art keywords
measurement data
classification
parts
classification parameters
bulk material
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.)
Withdrawn
Application number
EP93104640A
Other languages
German (de)
English (en)
French (fr)
Other versions
EP0562506A3 (enrdf_load_stackoverflow
Inventor
Norbert Dr. Stelte
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Bodenseewerk Geratetechnik GmbH
Original Assignee
Bodenseewerk Geratetechnik GmbH
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 Bodenseewerk Geratetechnik GmbH filed Critical Bodenseewerk Geratetechnik GmbH
Publication of EP0562506A2 publication Critical patent/EP0562506A2/de
Publication of EP0562506A3 publication Critical patent/EP0562506A3/xx
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • 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
    • 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
    • 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
    • B07C5/36—Sorting apparatus characterised by the means used for distribution
    • B07C5/363—Sorting apparatus characterised by the means used for distribution by means of air
    • B07C5/365—Sorting apparatus characterised by the means used for distribution by means of air using a single separation means
    • B07C5/366—Sorting apparatus characterised by the means used for distribution by means of air using a single separation means during free fall of the articles

Definitions

  • Such methods are used, for example, to sort broken glass in the reprocessing of waste glass according to the color, for example green, brown and white or even only "colored” and white.
  • the broken glass is separated so that each broken glass can be examined individually.
  • the spectral absorption or transmission at two or more different wavelengths is measured on the individual pieces of glass. From this, measurement data can be obtained from which the color of the broken glass can be deduced.
  • Classification is based on the measurement data. Control signals for controlling effectors are generated in accordance with this classification. The effectors sort the broken glass.
  • DE-C-34 45 428 describes a glass sorting device in which the broken glass falls through a chute.
  • the broken glass falls through light barriers with a light source and various photoelectric receivers, which are made sensitive to different wavelengths with the help of filters.
  • the signals from the receivers are integrated.
  • effectors are controlled in the form of scrapers.
  • the broken glass falls on a conveyor belt and is guided by the wipers from the conveyor belt into various containers.
  • EP-A-0 426 893 also describes a method and an apparatus for sorting broken glass, in which the intensity of the light guided through the cullet is measured at two different wavelengths. The differences in the intensities of the light passing through at the two wavelengths serve as measurement data for characterizing the glass. A fraction is separated from the broken glass in which the difference is less than a first threshold value and the intensities are greater than a second threshold value. These broken glass are considered to be colorless glass. The threshold values represent the classification parameters.
  • a compressed air stream serves as the effector.
  • classification parameters In all cases, classification parameters must be set. The definition of these classification parameters creates problems.
  • the fractions formed by the sorting are more valuable, the cleaner the different colors of the glass are separated. This is especially true for colorless glass, where even small amounts of colored glass significantly reduce the value of the old glass.
  • the setting of the classification parameters is therefore very critical.
  • the measurement data e.g. the quotient of the transmissions at two different wavelengths, for a fraction of broken glass, e.g. of green glass, by no means uniform.
  • the measurement data can fluctuate within the fraction within more or less wide limits.
  • the measurement data can also depend on other influences, for example on the degree of contamination or on the ambient temperature or air humidity (moisture, frozen moisture or fogging of broken glass). Setting the classification parameters is therefore not easy.
  • the invention has for its object to sort bulk goods, e.g. Glass breakage to find optimal classification parameters.
  • the invention is further based on the object of designing a device for sorting bulk material so that the setting of the classification parameters, e.g. from threshold values of the measurement data, to optimal values based on objective criteria.
  • a “learning phase” is thus provided, during which the classification parameters are determined and set, and a “sorting phase”, in which the bulk material is sorted on the basis of the set classification parameters.
  • the classification parameters are set in the learning phase as follows:
  • the sorted goods only contain parts that are assigned to either class A or class B.
  • N different measurement data are determined for each part, for example light intensities for N different spectral ranges.
  • Measurement data can also be data which are derived from primary data, for example quotients or differences in the intensities of different spectral ranges. By using such derived measurement data, the number of data to be processed can be reduced.
  • N different data can be represented as a point in an N-dimensional parameter space. If measurement data are taken from a part several times or measurement data from different parts of a class, the points in the parameter space do not generally coincide because of the unavoidable measurement errors and other influences. Rather, the points form a distribution (point cloud) in the N-dimensional parameter space.
  • class B point cloud in the same Parameter space.
  • the point clouds belonging to the different classes A and B will generally occupy areas in the N-dimensional parameter space that partially overlap.
  • the next task to be solved is to determine classification parameters which define an (N-1) -dimensional area in the parameter space which divides the entire parameter space into an area A and an area B.
  • This "area” is to be laid out in such a way that as many points of class A as possible lie in area A and as many points of class B as possible in area B. If the point clouds of classes A and B overlap, there is an optimization problem. For this optimization problem, an optimization criterion in the form of a cost function must be specified.
  • the two areas A and B separated by the area can each be connected. However, this is not absolutely necessary.
  • the one-dimensional (N-1) "area" is a line that divides the area into areas A and B.
  • the line can be open or e.g. to be closed in a circle.
  • Area A is then e.g. within the circle.
  • Area B is outside the circle.
  • Area A can also be formed by the interior of several circles.
  • the zero-dimensional surface is formed by one or more points.
  • the points divide the line into sections, which are each assigned to areas A or B.
  • X is the share of class A points that lie in area B, i.e. are misordered.
  • y is the proportion of points B that are in area A, which is also mis-sorted.
  • the coefficients a and b are determined from economic considerations. For the color sorting of waste glass, for example, the current value of the purity of the white glass of false colors determines the parameter a. The loss of white glass in the event of incorrect sorting into the colored fraction determines the parameter b.
  • the N-dimensional parameter space is divided into N-dimensional cells.
  • the cell size is an empirical parameter. In the two-dimensional case, this is a checkerboard-like division.
  • the rest of the parameter space is first defined as area "B".
  • area A is gradually expanded by one of the six possible neighboring cells at the expense of area B. After each such change in area, the cost function is checked. The area change is maintained if this reduces the cost function.
  • the cost function increases due to the area change, the area change is reversed. If, in addition to area expansion, a reduction in the area and the occupation of non-neighboring areas are also included, the global minimum of the cost function can also be found in addition to local minima of the cost function.
  • a parameter space divided into areas A and B results.
  • the breakdown is such that the cost function becomes minimal.
  • a part to be sorted is assigned to class A if its measurement data point in area N falls in the N-dimensional parameter space.
  • a part to be sorted is assigned to class B if its measurement data point falls in area B in the N-dimensional parameter space.
  • the calculation process can be accelerated by methods described in the literature, such as evolution strategies and genetic algorithms.
  • an approach for the description of the interface between the areas A and B can be chosen from the outset, which is defined by a set of classification parameters.
  • the statistical function of the classification parameters varies the cost function down to its global minimum.
  • the procedure is analogous if more than two classes are to be separated from one another.
  • the computer contains a neural network to which the measurement data of a known fraction are connected one after the other and whose weights in a training process as long as an algorithm of the neural network can be changed until measurement data of the parts belonging to the fraction are assigned to the fraction with the required probability.
  • Embodiments of the invention are the subject of the dependent claims.
  • 10 denotes a slide onto which waste glass in the form of broken glass can be placed.
  • the slide is designed so that the broken glass is separated.
  • the broken glass therefore passes individually through a measuring station 12.
  • the measuring station 12 contains an illuminating device 14 on one side of the translucent slide 10 there.
  • the illuminating device 14 sends white light through the broken glass.
  • the light is received by a sensor head 16.
  • 18 with a lens protector to protect the lenses contained in the sensor head 16 is designated.
  • the signals received by the sensor head 16 are connected to a computing and control unit 20.
  • the computing and control unit 20 supplies signals at an output 22 to control an effector 24.
  • the effector here is a compressed air nozzle, through which the broken glass falling from the end of the chute 10 is either passed via a distribution chute 26 into a first container 28 when the Compressed air nozzle no compressed air is supplied, or via a distributor chute 30 into a second container 32.
  • distribution to three containers can also be carried out in the same way.
  • the measuring station 12 is shown schematically in FIG.
  • the lighting device 14 contains a white light source 34.
  • the light bundle from the light source 34 is guided via an optical system 36 through the cullet 40 which is moved along a path 38.
  • the light is detected by the sensor head 16.
  • the sensor head 16 contains two photoelectric sensors 42 and 44.
  • a filter 46 and 48 are arranged in front of each of the sensors 42 and 44.
  • the light from the lighting device is through a Optics 50 and 52 collected on the respective sensor 42 and 44.
  • the sensors 42 and 44 provide signals which are proportional to the transmission of the respective glass of the shard 40 at the wavelength determined by the filter 46 and 48, respectively. After normalization (not shown), the signals from sensors 42 and 44 are logarithmized by logarithmic means 54 and 56, respectively. This provides the transmittance of the glass at the different wavelengths multiplied by the thickness of the glass. By forming quotients, represented by block 58, the thickness of the glass falls out, since the light of both wavelengths has passed through the same thickness of glass.
  • the quotients obtained are measurement data which are characteristic of the color of the glass. This can be seen from Fig.3.
  • Fig. 3 shows the transmissions of different types of glass depending on the wavelength. It can be seen that the quotient of the transmittance at two different wavelengths is characteristic of the color of the glass if the wavelengths are chosen appropriately.
  • the quotient for green glass gives a value close to 0.5, for brown glass one Value close to zero, while the quotient for white glass is about one. If you put thresholds between these values and consider glass for which the quotient is less than 0.25 as "brown”, glass for which the quotient is between 0.25 and 0.75 as “green” and glass for which the quotient above 0.75 is “white”, then you can sort the glass based on these thresholds.
  • the thresholds represent "classification parameters".
  • This classification based on the area in which the quotient of the transmittance lies is indicated in FIG. 2 by block 66.
  • a control signal is generated depending on the classification. This is represented by block 68.
  • the control signal controls the effector 24. This is represented by block 70.
  • the effector 24 directs the relevant piece of broken glass into the container corresponding to its color.
  • the frequency distribution is for white glass assigned to class "A" and the frequency distribution for brown and green glass is assigned to class "B".
  • the frequency distribution can be represented by point clouds in a one-dimensional parameter space, the parameter being the quotient of the logarithms of the intensities at two specific wavelengths.
  • a "histogram”, as shown in FIG. 5, can be used to better illustrate such a frequency distribution.
  • a number of adjacent ranges of values of these quotients are defined.
  • a fraction of broken glass of known color, for example brown, is measured.
  • the number of pieces of broken glass in which the quotients of the transmittance are within a certain range are counted. This number is assigned to the area.
  • a step function or a histogram such as histogram 72 in FIG. 5 then results.
  • histograms 74 and 76 are shown schematically as a kind of Gaussian curve. However, the histogram can have a completely different shape. If you e.g. if the green and brown fractions are combined to form a "colored" fraction, this results in histogram 75 for the combined, colored fraction.
  • classification parameters are thresholds in a one-dimensional parameter space.
  • X is the proportion of class A points awarded in the Area B are located, so they are mis-sorted.
  • y is the proportion of points B that are in area A, which is also mis-sorted.
  • the coefficients a and b are determined from economic considerations. For the color sorting of waste glass, for example, the current value of the purity of the white glass of false colors determines the parameter a. The loss of white glass in the event of incorrect sorting into the colored fraction determines the parameter b.
  • the statistical evaluation can be used to automatically set the classification parameters on the device for sorting bulk goods. This is shown schematically in Figure 4.
  • the quotients of the logarithms of the intensities at two predetermined wavelengths are formed as measurement data.
  • the measurement data entered in this way are digitized and classified according to size by a computer.
  • This classification is a fine classification of the measurement data that has nothing to do with the classification of the glass types.
  • This classification corresponds approximately to the division of the abscissa in Fig. 5 and serves to reduce the storage space used and the computing effort.
  • the classification is represented by block 84 in FIG.
  • the computer adds up the number of measured variables of the same class and thus forms a frequency distribution. This would correspond to curve 72 in FIG. 5.
  • the formation of a Frequency distribution is represented in FIG. 4 by block 86.
  • the frequency distribution is saved. This is represented by block 88.
  • influencing variables that can influence the measurement data also flow into this automatic specification.
  • This can e.g. the temperature or the humidity.
  • the influence of such influencing variables can be determined, for example, by measuring one and the same batch of broken glass at different atmospheric humidities in the manner described. There are then sets of classification parameters that are assigned to different atmospheric humidities. In normal sorting operation of the system, the air humidity is then measured continuously and the associated parameter set is automatically set. It is possible to simply set the set of classification parameters that belong to a humidity that is closest to the current humidity. However, a parameter set can also be obtained by interpolation. The same procedure can be applied to other influencing factors.
  • the humidity measurement (or measurement of another influencing variable) is represented by block 96.
  • the device described can be modified in various ways. Instead of the logarithms of the transmissions and their quotients, other functions can be spectral Properties of the glass to be sorted are used as measurement data. The principle described can be applied to the sorting of other bulk goods according to other criteria.
  • a neural network can also be provided as "self-learning" signal processing. Such a neural network is shown in FIG. 6.
  • the neural network 100 denotes a neural network that works with the "back propagation" algorithm.
  • the neural network has five inputs 102, 104, 106, 108 and 110. On these inputs 102, 104, 106, 108 and 110 the transmissions I at three different wavelengths and the ratios of the logarithms of the transmissions at the measured data are first and the second or at the third and the second wavelength.
  • the neural network has three outputs 112, 114 and 116.
  • the output 112 is assigned to the glass color "green”
  • the output 114 is assigned to the glass color "brown”
  • the output 116 is assigned to the glass color "white”.
  • fractions are again measured, for example of waste glass present as a broken glass.
  • the measurement data for green glass are successively applied to inputs 102 to 110.
  • Output 112 is set to "high", or logic one.
  • Outputs 114 and 116 are set to "zero”.
  • the weights in the neural network are gradually changed in the sense that a "high” or “logic one” at output 112 and “logic zero” at outputs 114 and 116 by inputting "green""Measurement data is obtained.
  • the measurement data entered at the inputs 102 to 110 are approximated as possible by iteratively changing the weights. This algorithm is therefore called “back propagation”.
  • Measured data here are the variables applied to inputs 102 to 110.
  • Classification parameters are the weights of the neural network that arise after the training of the neural network.

Landscapes

  • Sorting Of Articles (AREA)
  • Spectrometry And Color Measurement (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)
EP93104640A 1992-03-27 1993-03-22 Verfahren und Vorrichtung zum Sortieren von Schüttgut Withdrawn EP0562506A2 (de)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE4210157 1992-03-27
DE4210157A DE4210157C2 (de) 1992-03-27 1992-03-27 Verfahren zum Sortieren von Glasbruch

Publications (2)

Publication Number Publication Date
EP0562506A2 true EP0562506A2 (de) 1993-09-29
EP0562506A3 EP0562506A3 (enrdf_load_stackoverflow) 1995-01-25

Family

ID=6455267

Family Applications (1)

Application Number Title Priority Date Filing Date
EP93104640A Withdrawn EP0562506A2 (de) 1992-03-27 1993-03-22 Verfahren und Vorrichtung zum Sortieren von Schüttgut

Country Status (4)

Country Link
US (1) US5333739A (enrdf_load_stackoverflow)
EP (1) EP0562506A2 (enrdf_load_stackoverflow)
JP (1) JPH0643092A (enrdf_load_stackoverflow)
DE (1) DE4210157C2 (enrdf_load_stackoverflow)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0602464A3 (de) * 1992-12-12 1994-12-21 Rwe Entsorgung Ag Verfahren zum Erkennen von Objekten und Vorrichtung zur Durchführung des Verfahrens.
GB2289942A (en) * 1994-06-03 1995-12-06 Brown & Williamson Tobacco Detecting and separating foreign objects from particulate matter stream
EP0661108A3 (de) * 1993-12-28 1997-02-12 Reemtsma H F & Ph Verfahren zum optischen Sortieren von Schüttgut.
WO1997005969A1 (en) * 1995-08-09 1997-02-20 Alcan International Limited Method of sorting pieces of material
FR2752178A1 (fr) * 1996-08-06 1998-02-13 Vauche P Sa Machine de tri de bouteilles plastiques et procede mis en oeuvre par la machine
EP0775533A3 (de) * 1995-11-24 1998-06-17 Elpatronic Ag Sortierverfahren
US6234317B1 (en) 1999-04-15 2001-05-22 Wolfgang Sommer Device for sorting raw, pre-treated or recycled bulk material
WO2004045781A1 (en) * 2002-11-20 2004-06-03 Qinetiq Limited Apparatus and method for sorting objects by colour
DE202006019722U1 (de) * 2006-12-29 2008-04-30 Krones Ag Vorrichtung zum Behandeln von Gefäßen
CN106865156A (zh) * 2017-04-05 2017-06-20 江先庆 一种刮板输送机中部槽磨损检测装置及其检测方法

Families Citing this family (31)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE4322865A1 (de) * 1993-07-09 1995-01-12 Bodenseewerk Geraetetech Gerät zur Messung der Farbe von Glas, insbesondere von Glasbruch
JPH07132269A (ja) * 1993-11-10 1995-05-23 Kanetsuu Eng Kk カレット色別自動選別機及び選別方法
DE4415959A1 (de) * 1994-05-06 1995-11-09 Hergeth Hubert A Maschine zum Ausscheiden von metallischen Fremdteilen in einem Textilfaserstrom
DE19511901A1 (de) * 1995-03-31 1996-10-02 Commodas Gmbh Vorrichtung und Verfahren zum Sortieren von Schüttgut
DE19736536A1 (de) * 1997-08-22 1999-02-25 Ais Sommer Gmbh Vorrichtung zur Sortierung von rohstofflichen, vorveredelten oder recycelten Schüttgütern, die aus einzelnen zu sortierenden Teilen bestehen, wobei die Klassifizierung der zu sortierenden Teile nach empirisch bestimmten Klassifikationsparametern erfolgt und das auszusortierende Schüttgut abgeleitet wird
US6144004A (en) 1998-10-30 2000-11-07 Magnetic Separation Systems, Inc. Optical glass sorting machine and method
US6155489A (en) * 1998-11-10 2000-12-05 Ncr Corporation Item checkout device including a bar code data collector and a produce data collector
US6332573B1 (en) 1998-11-10 2001-12-25 Ncr Corporation Produce data collector and produce recognition system
US6369882B1 (en) 1999-04-29 2002-04-09 Advanced Sorting Technologies Llc System and method for sensing white paper
US7019822B1 (en) 1999-04-29 2006-03-28 Mss, Inc. Multi-grade object sorting system and method
US6374998B1 (en) 1999-04-29 2002-04-23 Advanced Sorting Technologies Llc “Acceleration conveyor”
US6286655B1 (en) 1999-04-29 2001-09-11 Advanced Sorting Technologies, Llc Inclined conveyor
US6250472B1 (en) 1999-04-29 2001-06-26 Advanced Sorting Technologies, Llc Paper sorting system
ATE291969T1 (de) 1999-04-30 2005-04-15 Binder Co Ag Verfahren und vorrichtung zum sortieren von altpapier
US6431446B1 (en) 1999-07-28 2002-08-13 Ncr Corporation Produce recognition system and method
DE10011093A1 (de) * 2000-03-09 2001-10-04 Commodas Gmbh Sortiervorrichtung und Sortierverfahren für dreidimensionale, insbesondere Hohlkörper
US6497324B1 (en) 2000-06-07 2002-12-24 Mss, Inc. Sorting system with multi-plexer
US7041926B1 (en) 2002-05-22 2006-05-09 Alan Richard Gadberry Method and system for separating and blending objects
US7081217B2 (en) * 2002-06-13 2006-07-25 Dan Treleaven Method for making plastic materials using recyclable plastics
AT411875B (de) * 2002-06-19 2004-07-26 Profactor Produktionsforschung Sortieranlage
US7351929B2 (en) * 2002-08-12 2008-04-01 Ecullet Method of and apparatus for high speed, high quality, contaminant removal and color sorting of glass cullet
US7355140B1 (en) * 2002-08-12 2008-04-08 Ecullet Method of and apparatus for multi-stage sorting of glass cullets
US8436268B1 (en) 2002-08-12 2013-05-07 Ecullet Method of and apparatus for type and color sorting of cullet
US7326871B2 (en) * 2004-08-18 2008-02-05 Mss, Inc. Sorting system using narrow-band electromagnetic radiation
US7383695B2 (en) * 2004-11-12 2008-06-10 Culchrome Llc Method of analyzing mixed-color cullet to facilitate its use in glass manufacture
DE102008036069A1 (de) * 2008-08-04 2010-02-25 Csl Behring Gmbh Vorrichtung und Verfahren zur Detektion von Glasbruch in einem Durchlauf-Sterilisiertunnel
US20100230330A1 (en) * 2009-03-16 2010-09-16 Ecullet Method of and apparatus for the pre-processing of single stream recyclable material for sorting
KR101462920B1 (ko) * 2014-05-27 2014-11-26 이광훈 퇴적물 분류 속도가 향상된, 탄성파 탐사 자료에 의하여 해저면 퇴적물의 종류를 자동 분류하는 방법
DE102017119137A1 (de) * 2017-08-22 2019-02-28 Sesotec Gmbh Verfahren zur Detektion und Aussonderung von Sonderglas aus Recyclingglas
US10512942B2 (en) * 2017-10-30 2019-12-24 Optisort, Llc System and method for sorting objects
FR3159012A1 (fr) * 2024-02-02 2025-08-08 Saint Gobain Glass France Procédé et système de détermination du type de verre composant un élément verrier

Family Cites Families (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE1797327C2 (de) * 1964-09-25 1974-07-25 Kollmorgen Corp., Garden City, N.Y. (V.St.A.) Gerät zur Messung des optischen Reflexionsvermögens bzw. der Durchlässigkeit. Ausscheidung aus: 1622484
US3737239A (en) * 1971-07-16 1973-06-05 Hoffmann La Roche Machine color recognition
DE2722294A1 (de) * 1976-05-19 1977-12-01 Ultra Sort Corp Vorrichtung zum sortieren von gegenstaenden
US4132314A (en) * 1977-06-13 1979-01-02 Joerg Walter VON Beckmann Electronic size and color sorter
US4259020A (en) * 1978-10-30 1981-03-31 Genevieve I. Hanscom Automatic calibration control for color grading apparatus
DE3039979C2 (de) * 1980-10-23 1984-08-02 Matthias Ing.(grad.) 8097 Vogtareuth Heinhaus Anordnung zum optoelektronischen Klassieren von Festkörpern nach Farbe und/oder Strukturbeschaffenheit
US4476982A (en) * 1981-04-01 1984-10-16 Sunkist Growers, Inc. Method and apparatus for grading articles according to their surface color
IT1205622B (it) * 1982-12-21 1989-03-23 Illycaffe Spa Procedimento per effettuare una selezione in un materiale granuliforme e macchina per attuare il procedimento
DE3445428A1 (de) * 1984-12-13 1986-06-19 MAB Marlis Kellermann, 7521 Dettenheim Glas-sortieranlage
US4690284A (en) * 1985-10-04 1987-09-01 Cochlea Corporation Method of and apparatus for inspecting objects using multiple position detectors
DE3731402A1 (de) * 1987-06-11 1988-12-29 Mabeg Muell & Abfall Anlage zur trennung von abfallhohlglaesern, insbesondere von flaschen mindestens nach weiss- und buntglas
DE3804391A1 (de) * 1988-02-12 1989-08-24 Hubertus Exner Verfahren und vorrichtung zum sortieren von altglasbruchstuecken
US5085325A (en) * 1988-03-08 1992-02-04 Simco/Ramic Corporation Color sorting system and method
US5002397A (en) * 1988-04-13 1991-03-26 International Integrated Systems, Inc. System of fluid inspection and/or identification
EP0342354A3 (en) * 1988-04-15 1992-01-08 Tecnostral S.A. Industria E Tecnologia Color sorting apparatus
DE3817026A1 (de) * 1988-05-19 1989-11-23 Hecht Dieter Dipl Ing Fh Verfahren und einrichtung zum sortieren von altglas
US4919534A (en) * 1988-09-30 1990-04-24 Environmental Products Corp. Sensing of material of construction and color of containers
US4992949A (en) * 1989-01-27 1991-02-12 Macmillan Bloedel Limited Color sorting of lumber
DE3914360A1 (de) * 1989-04-29 1990-10-31 Hubertus Exner Verfahren und vorrichtung zum verteilen von kleinteilen, wie glasbruchstuecken
EP0426893B1 (de) * 1989-11-08 1994-09-21 Siemens Aktiengesellschaft Verfahren und Einrichtung zum Sortieren
FR2660880B1 (fr) * 1990-04-12 1994-10-28 Bsn Emballage Procede et dispositif de tri optique numerique d'une masse de particules, telle que, notamment du groisil.
GB2247312B (en) * 1990-07-16 1994-01-26 Univ Brunel Surface inspection

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0602464A3 (de) * 1992-12-12 1994-12-21 Rwe Entsorgung Ag Verfahren zum Erkennen von Objekten und Vorrichtung zur Durchführung des Verfahrens.
EP0661108A3 (de) * 1993-12-28 1997-02-12 Reemtsma H F & Ph Verfahren zum optischen Sortieren von Schüttgut.
GB2289942A (en) * 1994-06-03 1995-12-06 Brown & Williamson Tobacco Detecting and separating foreign objects from particulate matter stream
GB2289942B (en) * 1994-06-03 1998-11-11 Brown & Williamson Tobacco Method and apparatus for detecting and separating foreign objects from a particulate matter stream
WO1997005969A1 (en) * 1995-08-09 1997-02-20 Alcan International Limited Method of sorting pieces of material
US5813543A (en) * 1995-08-09 1998-09-29 Alcan International Limited Method of sorting pieces of material
EP0775533A3 (de) * 1995-11-24 1998-06-17 Elpatronic Ag Sortierverfahren
EP0824042A1 (fr) * 1996-08-06 1998-02-18 P. Vauche S.A. Machine de tri de bouteilles plastiques et procédé mis en oeuvre par la machine
FR2752178A1 (fr) * 1996-08-06 1998-02-13 Vauche P Sa Machine de tri de bouteilles plastiques et procede mis en oeuvre par la machine
US6234317B1 (en) 1999-04-15 2001-05-22 Wolfgang Sommer Device for sorting raw, pre-treated or recycled bulk material
WO2004045781A1 (en) * 2002-11-20 2004-06-03 Qinetiq Limited Apparatus and method for sorting objects by colour
DE202006019722U1 (de) * 2006-12-29 2008-04-30 Krones Ag Vorrichtung zum Behandeln von Gefäßen
CN106865156A (zh) * 2017-04-05 2017-06-20 江先庆 一种刮板输送机中部槽磨损检测装置及其检测方法
CN106865156B (zh) * 2017-04-05 2018-10-12 张惠雄 一种刮板输送机中部槽磨损检测装置及其检测方法

Also Published As

Publication number Publication date
JPH0643092A (ja) 1994-02-18
DE4210157A1 (de) 1993-09-30
US5333739A (en) 1994-08-02
EP0562506A3 (enrdf_load_stackoverflow) 1995-01-25
DE4210157C2 (de) 1994-12-22

Similar Documents

Publication Publication Date Title
EP0562506A2 (de) Verfahren und Vorrichtung zum Sortieren von Schüttgut
DE19751862C2 (de) Verfahren und Vorrichtung zum Identifizieren und Sortieren von bandgeförderten Objekten
DE69227603T2 (de) Verfahren und Gerät zur optischen Bestimmung der Annehmbarkeit von Produkten
DE60201684T2 (de) Verfahren zum sortieren von aus einem organischen material bestehenden gegenständen
DE69921021T2 (de) Verfahren zum Unterscheiden von Produkteinheiten und Vorrichtung dazu
EP2598860A1 (de) Verfahren, sensoreinheit und maschine zum detektieren von "zuckerspitzen"-defekten in kartoffeln
DD152870A1 (de) Verfahren und vorrichtung zum klassieren in bewegung befindlichen stueckgutes
CH639570A5 (de) Verfahren zum sortieren von pflanzlichen gegenstaenden, insbesondere von landwirtschaftlichen produkten.
EP0166899B1 (de) Verfahren zur Untersuchung von Kunststoffkörpern
EP2110187B1 (de) Verfahren zum Identifizieren, Klassifizieren und Sortieren von Gegenständen, Objekten und Materialien, sowie ein Erkennungssystem zur Durchführung dieses Verfahrens
DE2340008A1 (de) Reflektometer
EP3842788B1 (de) Nah-infrarot-spektralsensor zur objekterkennung mittels maschinenlernverfahren, und entsprechendes verfahren
DE102016114465A1 (de) Vorrichtung und Verfahren zur Legierungsanalyse von Schrottfragmenten aus Metall
DE4406228C2 (de) Verfahren um aus einem Strom von Gegenständen nicht-akzeptable Güter und Fremdgegenstände auszusortieren
DE4127903C2 (de) Anordnung und Verfahren zur Qualitäts- und Größensortierung von Produkten und Artikeln
DE102017119137A1 (de) Verfahren zur Detektion und Aussonderung von Sonderglas aus Recyclingglas
DE19601950C1 (de) Verfahren zur Erkennung von Materialsorten, insbesondere Kunststoffsorten
DE3045344C2 (enrdf_load_stackoverflow)
CH634411A5 (en) Method for determining suitable optical wavelengths, for distinguishing test objects optically, and appliance required therefor and application of the method
DE3514313C2 (de) Verfahren und Vorrichtung zur Inspektion und zum Sortieren von Glasbehältern
DE3401475C2 (enrdf_load_stackoverflow)
EP0483607A1 (de) Verfahren zum Feststellen einer Eigenschaft eines Faserverbandes
DE60126775T2 (de) Teilchendatenanalyse
DE19720121C2 (de) Verfahren zur quantitativen Bestimmung der Anteile verschiedenartiger Stoffe in Schüttgütern
DE68902952T2 (de) Produkt-diskriminationssystem und verfahren dazu.

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

AK Designated contracting states

Kind code of ref document: A2

Designated state(s): AT BE CH DE DK ES FR GB GR IE IT LI LU MC NL PT SE

PUAL Search report despatched

Free format text: ORIGINAL CODE: 0009013

AK Designated contracting states

Kind code of ref document: A3

Designated state(s): AT BE CH DE DK ES FR GB GR IE IT LI LU MC NL PT SE

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION HAS BEEN WITHDRAWN

18W Application withdrawn

Withdrawal date: 19950330

R18W Application withdrawn (corrected)

Effective date: 19950330

R18W Application withdrawn (corrected)

Effective date: 19950330