EP4045324A1 - Verfahren zum automatischen fehlermanagement an einer druckmaschine - Google Patents
Verfahren zum automatischen fehlermanagement an einer druckmaschineInfo
- Publication number
- EP4045324A1 EP4045324A1 EP20792961.3A EP20792961A EP4045324A1 EP 4045324 A1 EP4045324 A1 EP 4045324A1 EP 20792961 A EP20792961 A EP 20792961A EP 4045324 A1 EP4045324 A1 EP 4045324A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- error
- printing
- print image
- error type
- type database
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B41—PRINTING; LINING MACHINES; TYPEWRITERS; STAMPS
- B41F—PRINTING MACHINES OR PRESSES
- B41F33/00—Indicating, counting, warning, control or safety devices
- B41F33/0036—Devices for scanning or checking the printed matter for quality control
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B41—PRINTING; LINING MACHINES; TYPEWRITERS; STAMPS
- B41F—PRINTING MACHINES OR PRESSES
- B41F5/00—Rotary letterpress machines
- B41F5/24—Rotary letterpress machines for flexographic printing
Definitions
- the invention relates to a method for automatic error management on a printing machine, in which a repetitive print image is printed on a moving web of material.
- error management refers to the entirety of the actions with which printing errors are dealt with on the printing press during the printing process.
- error detection i.e. the determination that an error has occurred
- error diagnosis i.e. the assignment to a specific cause
- actual resolution of the error i.e. the resolution of the error.
- So-called inspection systems are used to carry out error management on a printing press. Such inspection systems are basically set up so that the operator can observe and monitor the print image as a still image on a monitor while the printing process is running.
- the print image is usually recorded with a line camera.
- the line camera In contrast to an area camera, the line camera only ever records a single line of images, since in this way a higher resolution and a higher readout speed can be achieved compared to an area camera.
- the two-dimensional image is then created due to the movement of the belt. However, since this movement is subject to constant fluctuations, the feed is synchronized with the help of an encoder so that no image distortion occurs.
- the inspection system can also be equipped with an area camera (other designation: matrix camera) which records a section of the printed image on the moving material web.
- an area camera other designation: matrix camera
- the selected section is preferably a prominent area of the print image in which printing errors have a particularly strong effect.
- the matrix camera is typically capable of zooming, so that faulty or problematic areas of the print image can be examined with high resolution. If the operator detects printing errors in the section shown (for example, errors in the color tone or register errors), he can readjust the machine parameters (for example the printing position, the longitudinal register or the side register) in order to correct the printing errors.
- the inspection system can also be equipped with an optical spectrometer.
- An optical spectrometer breaks down the light picked up by a point of light into its spectral components and evaluates the result in a computer system.
- Miniature spectrometers which are built into a compact housing and which can be placed in a suitable location within the printing press, are particularly suitable for the applications presented here.
- Such miniature spectrometers usually consist of an aperture (i.e. an entrance slit), an optical grating and an optical sensor.
- the grating is located behind the aperture and scatters the spectral components of the incident light at slightly different angles, so that the scattered light can be evaluated by the optical sensor as light intensity over the wavelength of the respective light components.
- the positions of the errors detected by the operator on the moving material web are stored in the inspection system. After completion of the printing process, it is then possible, for example with the help of a rewinder, to approach the defective area of the printed material web and separate it. It is also possible for the defective areas on the material web to be marked during printing and only then removed during subsequent processing.
- error detection algorithms are also known which automatically detect certain errors in the print image and subsequently support the operator in performing his tasks. For example, an error detection algorithm can be based on a reference image that is recorded at the beginning of the print job.
- the reference image can for example be recorded at the beginning of the printing process on the basis of the first print images (for example the first 50 images) with the line camera, the area camera and / or the optical spectrometer, these first images for creating the reference image (also called "golden image") be integrated.
- the fluctuation range of the image information can be determined for each individual pixel, so that tolerance limits for error detection can be set.
- the currently recorded image is then subtracted from the reference image during the printing process. If the difference obtained is outside the error tolerances, an error signal is generated and the defective image area is displayed on the monitor of the control panel.
- the desired print result can also be specified by the so-called digital proof, which is provided by the prepress stage.
- the image provided by the inspection system is compared with the digital proof.
- the digital image processing techniques already described in connection with the reference image can also be used for this comparison.
- the object of the invention is therefore to improve the automatic fault management in existing inspection systems.
- FIG. 1 shows an overall view of the printing machine according to the invention using the example of a flexographic printing machine
- FIG. 2 shows a detailed view of FIG. 1 with a line camera and a moving material web
- FIG. 3 shows an exemplary block diagram of the method according to the invention.
- FIG. 1 shows an overall view of the printing machine according to the invention using the example of a flexographic printing machine 101 with a line camera 102, a prepress 103, a control unit 104 and a control station 106.
- the control unit is installed at position 105 of the flexographic printing machine 101 and is shown separately for the sake of clarity.
- the flexographic printing machine 101 is a so-called central cylinder machine and accordingly has a central cylinder 107 around which the eight inking units are arranged in a star shape.
- Each of these inking units has a printing roller, an anilox roller and a doctor blade chamber, which are each mounted on anchors on the machine side.
- the inking unit 108 is designated as an example.
- the material web 109 In order to print the material web 109, it is pulled off the material roll 111 in the unwinding station 110 and guided to the pressure roller 112 via several deflection rollers.
- the pressure roller 112 applies the material web 109 to the central cylinder 107 for further transport, so that the material web 109 is guided past the inking units and the intermediate inking unit dryers (not shown in detail) in precise register.
- the flexographic printing machine is also equipped with an inspection system for error detection.
- an initial print image 118 (composite file) with the color separations from prepress 103 is stored in control unit 104, the prepress being connected to control unit 104 via line 117.
- the initial print image 118 is then compared with the actual print image recorded by the line camera 102, the line camera being connected to the control unit 104 via the line 116.
- FIG. 2 shows a detailed view of FIG. 1 with a line camera and a moving material web.
- the corresponding reference symbols from FIG. 1 have been adopted, so that reference is made to the description of FIG. 1 in this respect.
- the material web 107 running out of the bridge dryer 113 was printed by the inking units 108 and thus has a repetitive print image. For the sake of simplicity, however, the print image is not shown in FIG. 2.
- the line camera 102 records the print image and forwards it to the control unit 104 via the line 116.
- An error detection algorithm for detecting printing errors is implemented in the control unit 104.
- Machine states that can be assigned to the printing error such as: temperature of the impression cylinder, provided values, viscosity of the printing ink, etc.
- the error type database 311 is then able to output the error type 312 from the detected printing error.
- the defect type database 311 is trained by a large number of operators. The process is as follows:
- the starting point in the training phase is initially the same situation of a print job as in the execution phase.
- a print image 301 is also inspected by an error detection algorithm 302 in the training phase.
- the printing error is displayed to the operator together with feature information 303.
- the operator decides which type of error 304 is the basis of the printing error. It makes sense to assign the error types to several categories in the hierarchy. Examples of possible categories and types of errors are:
- the error type 304 entered by the operator is then uploaded from the terminal 305 with the feature information 303 to a cloud data storage medium 306.
- the advantage of the cloud data memory 306 is that a large number of operators worldwide can operate the cloud data memory 306.
- the data in the cloud data memory 306 are then analyzed and classified by a so-called support vector machine (abbreviated: SVM).
- SVM 307 is a mathematical method of pattern recognition that is implemented in a computer program.
- the principle of the SVM 307 is based on dividing a quantity of data into classes in such a way that as broad an area as possible remains free of data around the class boundaries (so-called “Large Margin Classifier”).
- Such an SVM is, for example, in the article by Christopher JC Burges entitled “A tutorial on Support Vector Machines for Pattern Recognition ", published in” Data Mining and Knowledge Discovery ", Volume 2/1998, pages 121-167
- the SVM 307 now identifies a region in the multi-dimensional feature space of the features 303 that has been sufficiently frequently assigned the same error type 304 by the operator, this results in a reproducible association between the features 303 and the error type 304 SVM 307 is stored in the database 311 in the training phase, so that the database 3011 in the execution phase is able to output the trained error type 312 based on the features 310.
- the training phase and the execution phase do not have to run one after the other, but can be carried out in parallel.
- the execution phase it is also possible to allow the operator to make an entry in order to enable corrections if the error type 312 output by the database 311 does not appear correct to the operator.
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Mechanical Engineering (AREA)
- Inking, Control Or Cleaning Of Printing Machines (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102019127996.8A DE102019127996A1 (de) | 2019-10-16 | 2019-10-16 | Verfahren zum automatischen Fehlermanagement an einer Druckmaschine |
| PCT/EP2020/078828 WO2021074180A1 (de) | 2019-10-16 | 2020-10-14 | Verfahren zum automatischen fehlermanagement an einer druckmaschine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP4045324A1 true EP4045324A1 (de) | 2022-08-24 |
Family
ID=72915818
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP20792961.3A Pending EP4045324A1 (de) | 2019-10-16 | 2020-10-14 | Verfahren zum automatischen fehlermanagement an einer druckmaschine |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US20240109283A1 (de) |
| EP (1) | EP4045324A1 (de) |
| DE (1) | DE102019127996A1 (de) |
| WO (1) | WO2021074180A1 (de) |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102011050733A1 (de) * | 2011-05-30 | 2012-12-06 | Eltromat Gmbh | Verfahren zur Steuerung eines Drucklaufes in einer Rotationsdruckmaschine |
| EP2886345A1 (de) * | 2013-12-23 | 2015-06-24 | Comexi Group Industries, S.A.U | Automatische Druckparametereinstellung und Steuerungsverfahren |
| US10331852B2 (en) * | 2014-01-17 | 2019-06-25 | Arterys Inc. | Medical imaging and efficient sharing of medical imaging information |
| DE102014004556A1 (de) * | 2014-03-31 | 2015-10-01 | Heidelberger Druckmaschinen Ag | Verfahren zur Prüfung der Zuverlässigkeit der Fehlererkennung eines Bildinspektionsverfahrens |
| JP6624125B2 (ja) * | 2017-03-13 | 2019-12-25 | コニカミノルタ株式会社 | 画像検査装置、画像形成システム及び画像圧縮方法 |
| IL254078A0 (en) * | 2017-08-21 | 2017-09-28 | Advanced Vision Tech A V T Ltd | Method and system for creating images for testing |
| DE102017216260A1 (de) * | 2017-09-14 | 2019-03-14 | Heidelberger Druckmaschinen Ag | Bildinspektion von Druckerzeugnissen mit Fehlerklassen |
-
2019
- 2019-10-16 DE DE102019127996.8A patent/DE102019127996A1/de active Pending
-
2020
- 2020-10-14 WO PCT/EP2020/078828 patent/WO2021074180A1/de not_active Ceased
- 2020-10-14 EP EP20792961.3A patent/EP4045324A1/de active Pending
- 2020-10-14 US US17/769,114 patent/US20240109283A1/en not_active Abandoned
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021074180A1 (de) | 2021-04-22 |
| US20240109283A1 (en) | 2024-04-04 |
| DE102019127996A1 (de) | 2021-04-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP0884178B1 (de) | Verfahren zur Regelung der Farbgebung beim Drucken mit einer Druckmaschine | |
| EP2011651B1 (de) | System zur Inspektion eines Druckbildes | |
| DE10319770A1 (de) | Verfahren zur Regelung der Farbdichte einer von einer Druckmaschine auf einem Druckträger aufgebrachten Farbe und Vorrichtung zur Regelung verschiedener für den Druckprozess einer Druckmaschine relevanter Parameter | |
| EP3680106B1 (de) | Mn-detektion im druckbild | |
| DE10131934B4 (de) | Messung und Regelung der Farbgebung im Rollendruck | |
| DE102019208257A1 (de) | Druckqualitätsanalyse mit neuronalen Netzen | |
| EP3871892B1 (de) | Makulaturoptimierte detektion | |
| DE102011014073A1 (de) | Verfahren zur Regelung eines Druckvorgangs | |
| EP1714786A2 (de) | Vorrichtung zur Inspektion von Druckerzeugnissen | |
| DE102016213111B4 (de) | Inspektionssystem mit mehreren Erfassungsbereichen | |
| DE10149158A1 (de) | Verfahren und Vorrichtung zur Ermittlung der Position einer bedruckten Papierbahn | |
| AT412675B (de) | Verfahren zur qualitätskontrolle an drucksachen | |
| WO2005104034A1 (de) | Verfahren zur beurteilung einer qualität einer von einer druckmaschine produzierten drucksache | |
| WO2004056570A1 (de) | Verfahren und vorrichtung zur echzeitkontrolle von druckbildern | |
| DE102007041673B4 (de) | Verfahren zur Gewinnung von Druckbild- oder Druckplatteninformationen | |
| EP4045324A1 (de) | Verfahren zum automatischen fehlermanagement an einer druckmaschine | |
| AT501210B1 (de) | Verfahren zur qualitätskontrolle an oberflächenvariablen drucksachen | |
| EP4045323A1 (de) | Verfahren zum automatischen fehlermanagement an einer druckmaschine | |
| DE69026488T2 (de) | Verfahren zur Qualitätsbeurteilung von Druckerzeugnissen | |
| WO2021074183A1 (de) | Verfahren zum automatischen fehlermanagement an einer druckmaschine | |
| DE102020129339A1 (de) | Verfahren zum automatischen Fehlermanagement an einer Druckmaschine | |
| DE102008033171A1 (de) | Verfahren und Vorrichtung zur Inline-Qualitätssicherung an Druckmaschinen | |
| DE102015203358B4 (de) | Verfahren zur Beurteilung von mehreren jeweils mindestens ein Druckbild aufweisenden Druckerzeugnissen hinsichtlich ihrer jeweiligen Weiterverarbeitungsfähigkeit | |
| DE4023314A1 (de) | Verfahren zur kontrolle und steuerung der qualitaet von druckerzeugnissen | |
| DE102009005292A1 (de) | Messvorrichtung zur teilweisen Erfassung bogenförmiger Bedruckstoffe |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| 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 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20220516 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) | ||
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
| 17Q | First examination report despatched |
Effective date: 20260210 |