Corrugated cardboard production unit and method for inspecting the flatness of corrugated cardboard sheets

Abstract

The invention relates to a corrugated cardboard production unit (2) and to a method for monitoring such a corrugated cardboard production unit (2). The sheets (6) are placed so as to lie partly one over the other on a conveyor belt (10) extending in the longitudinal direction (8) such that the end-face edge (26) of a leading sheet (6) rests on a trailing sheet (6). A defined region of a conveyor device (4) of the corrugated cardboard production unit (2) is specified as a test region (12), and images (I) of the test region (12) are captured using a camera (22). When viewed in the longitudinal direction (8), the camera (22) is oriented upstream and diagonally to the test region (12) and thus towards the end-face edge (26) of a sheet (6) located in the test region (12). On the basis of at least one of the captured images (I), the course of the end-face edge (26) is analyzed for a deviation from the flatness of the sheet (6) by means of an automatic image analysis.

Description

[0001] Description

[0002] Corrugated board plant and method for checking the flatness of corrugated board sheets

[0003] The invention relates to a corrugated board plant and a method for checking the flatness of sheets of corrugated board.

[0004] Corrugated board lines are well known and are used to produce individual sheets of corrugated board. During sheet production, the goal is to achieve the best possible flatness of each sheet, as this is a crucial criterion for quality and further processing. Flatness refers to a sheet being flat and without any warping. A deviation from this flatness in the form of a curve is also referred to as "warp."

[0005] According to EP 1 473 147 A1, undesired curvature of arches is detected using a camera-based system. The height levels of various points on an arch are recorded and evaluated. The inspection of the arches for deviations from flatness is also referred to below as "warp detection."

[0006] Camera-based systems for monitoring a corrugated board line or for inspecting the corrugated boards produced are well known. Markers are applied to the corrugated board. For example, a luminescent marker system is described in DE 10 2015 204 407 A1. Detecting a deviation from the flatness requires a high degree of accuracy in order to obtain reliable information about such a deviation with such a camera-based monitoring system.

[0007] Based on this, the invention is based on the object of ensuring a reliable automatic check of the flatness of the sheets produced in a corrugated board plant with little effort.

[0008] The object is achieved according to the invention by a method for monitoring the flatness of sheets of corrugated cardboard, wherein a) the sheets are placed partially on top of one another on a conveyor belt extending in a longitudinal direction and are conveyed in the longitudinal direction so that a leading edge of a leading sheet rests on a trailing sheet, b) a defined area of ​​a conveyor device of the corrugator is specified as the inspection area, c) at least one camera is provided with which images of the inspection area are taken, wherein d) the camera is positioned in front of the inspection area viewed in the longitudinal direction and is oriented obliquely towards the inspection area and thus towards the leading edge of a sheet located in the inspection area,e) on the basis of at least one of the recorded images, the profile of the front edge is analyzed by means of an automatic image evaluation with regard to a deviation of a respective sheet from a flat position of this sheet.,

[0009] The object is further achieved according to the invention by a corrugated board plant in which

[0010] - at least one conveyor device extending in a longitudinal direction is arranged for conveying sheets of corrugated cardboard, wherein the sheets are placed partially on top of each other on the conveyor belt during operation, so that a front edge of a leading sheet rests on a trailing sheet, - a defined area of ​​the conveyor device is specified as the test area,

[0011] - at least one camera is arranged which is designed to take images of the test area, wherein

[0012] - the camera is positioned in front of the test area when viewed in the longitudinal direction and is oriented diagonally towards the test area and thus towards the front edge of a sheet located in the test area,

[0013] - an evaluation unit is arranged which is designed to analyse the course of the front edge with regard to a deviation from a flat position of the sheet on the basis of at least one of the recorded images by means of an automatic image evaluation.

[0014] The advantages and preferred embodiments listed below with regard to the method are also to be applied analogously to the corrugated board plant and vice versa.

[0015] With the corrugator and the process, it is particularly important that the camera is positioned diagonally in front of the inspection area, so that the camera's view is directed from the front onto a respective overlapping end edge of the respective sheet. The conveyor system is preferably equipped with lighting so that the end edges or a corresponding shadow cast make the end edges clearly visible in the image. This enables reliable, automatic image analysis of the course and thus the profile of the end edge. Based on the course of the end edge in the transverse direction, i.e. perpendicular to the longitudinal direction, any curvatures and bulges that have formed on the end edge of the respective sheet can be immediately detected and evaluated as a characteristic value for a deviation from the flatness.

[0016] For warp detection, preferably only the evaluation of the profile of the front edge, described in detail below, is used. The evaluation unit is configured and designed accordingly and comprises, in particular, a processor, typically a data memory, and, in particular, one or more suitable algorithms with the aid of which the automatic image evaluation is carried out.

[0017] In contrast to the height measurement known from the prior art, which involves looking at the respective sheet from above and measuring the distance to a reference height, this type of edge evaluation is possible using simple means and with high reliability with regard to the desired "warp" detection. Therefore, a height measurement is notably omitted.

[0018] Another significant advantage of the described process and corrugator is that the camera simultaneously provides a wealth of additional information, allowing the camera to be used for additional monitoring tasks—both automatic and manual—and is also preferred. Overall, this edge evaluation measure minimizes the overall monitoring and system overhead for controlling the corrugator during corrugated board production.

[0019] For example, by identifying a particular front edge, the individual identification of a particular arch, especially a particular arch end, is already implicitly enabled and provided. With pure height detection, additional identification of a particular arch is required in order to reliably assign the measured distance profile to a particular arch.

[0020] According to a first embodiment, individual images are taken with the camera, and according to a second embodiment, image sequences are created and further processed in the manner of a stream. The conveyor device is in particular a section of the corrugated board plant in the area of ​​the so-called dry end. Specifically, the conveyor device is part of a storage system, which is arranged downstream of a cross cutter which cuts the produced continuous corrugated board into individual sheets. The sheets are deposited in the storage system on one or more conveyor belts, also referred to as storage belts, and then conveyed further, for example to a stacking device. The individual sheets are deposited and conveyed overlapping one another. They therefore lie on top of one another like scales. This is also referred to below as a scaled arrangement.

[0021] Frequently, several conveyor belts are provided, arranged side by side and, in particular, one above the other. In such a case, at least one camera is installed on each conveyor belt. The at least one camera is aimed at a specific section of the conveyor system, and specifically at the conveyor belt, which forms the inspection area of ​​the conveyor system. This means that the camera images a section of the conveyor system in each captured image. The camera is adjusted such that at least part of the captured image captures the inspection area.

[0022] According to a preferred embodiment, edge extraction is performed to identify the respective front edge, and an extracted front edge is obtained. Therefore, a suitable executable program / algorithm is installed in the evaluation unit, with the aid of which the edge extraction is carried out automatically. Such algorithms for detecting and extracting edges in a recorded image are generally known and are also referred to as edge detection filters. For example, the points with a specified brightness change in the recorded image, specifically a grayscale image, are determined. Such algorithms allow reliable identification of the profile of the front edge.

[0023] In the next step, the extracted front edge is evaluated, preferably with regard to its deviation from flatness. For this purpose, the profile of the front edge is evaluated, particularly with regard to maximum values, minimum values, deviations from a mean value, curvature behavior, etc.

[0024] For this purpose, the extracted front edge is conveniently approximated using a curve fit and thus a mathematical function. This mathematical function is then evaluated with regard to the deviation from flatness. Specifically, the aforementioned parameters, at least some of them, are analyzed using a functional analysis, such as by calculating derivatives, etc.

[0025] For example, the curve fit is a higher-order polynomial fit. A so-called spline interpolation is preferably used. This is particularly suitable for warp detection, since very strong curvatures can occur in the arcs, for example, due to grooving, which can be well approximated by spline interpolation.

[0026] According to a preferred embodiment, the sheets are further analyzed for twisting, preferably based on the identified and extracted front edge. The sheets are usually oriented parallel to the longitudinal direction and have edges and structures running in the longitudinal direction, for example the outer edges, a creasing or a longitudinal cutting edge. The front edge is typically designed as a transverse edge that runs transversely to such longitudinal edges of the sheet and is therefore also oriented transversely to the longitudinal direction of the conveyor belt when properly deposited on the conveyor belt. When analyzing whether the sheets are twisted, the image analysis is now automatically used to check in particular whether the front edge runs transversely to the longitudinal direction. For this purpose, for example, the length of the front edge, i.e. its extension in the transverse direction, is measured using automatic image analysis and compared with a target value.The target value is derived from the (known) width of the respective sheet and the imaging geometry of the camera. The width of the sheet is preferably read from the system control system for evaluation. In the case of a twist, the measured edge length is less than the target value. The difference to the target value is preferably also used to determine the degree of twist. If a twist is identified, especially a twist that exceeds a limit, a warning message is issued. According to a preferred development, the degree of twist is also determined when a twist is identified.

[0027] Finally, in a preferred embodiment, the previously identified rotation is automatically taken into account during warp detection. After an identified rotation, an image correction is therefore first performed to compensate for the rotation. For this purpose, the image is rotated, for example, so that the previously measured twist of the sheet is compensated and thus reversed. This measure enables a reliable evaluation of the extracted front edge.

[0028] In order to ensure the simplest possible design for detecting deviations from the flatness, a height measurement is omitted. A height measurement typically involves measuring the distance from a reference level to, in particular, several surface areas of the sheet. This omission minimizes the technical complexity of the equipment.

[0029] In a preferred embodiment, several markers are fixedly attached in the area of ​​the conveyor belt, which are correlated with the inspection area and, in particular, delimit it. The camera also captures the markers, so that they are included in the recorded image. The markers can be passive or active markers. Active markers have active light elements, for example (LED) light sources. Passive markers lack such light elements. Passive markers are, for example, colored markings or reflective elements. These passive markers are attached to the edge of the conveyor belt, for example, like foils.

[0030] Alternatively or in addition to the markers, the inspection area is defined by a defined setting and configuration, for example, during commissioning of the system. This includes, for example, a defined orientation of the camera relative to the conveyor system.

[0031] Based on the markers, it is preferably also checked with the help of automatic image analysis whether the test area depicted in the recorded image is oriented according to a specified target orientation. This measure checks in particular any device-related adjustment, specifically the adjustment of the camera in relation to the conveyor belt. Changes in the camera position during operation, e.g. due to vibrations etc., and any associated misalignment are therefore detected. If such a deviation of the depicted test area from the target orientation is detected, an automatic correction is preferably carried out. If, for example, it is detected that the depicted test area is rotated or distorted compared to its target orientation, a corresponding image transformation is carried out which reverses this rotation / distortion. This preferably takes place before edge extraction and its analysis are carried out.

[0032] By positioning the camera diagonally in front of the inspection area, the recorded images regularly display a perspective, specifically a so-called vanishing point perspective. This means that parallel structures extending longitudinally converge towards an imaginary vanishing point. In a preferred development, it is now provided that - before the recorded image is checked for deviations of the sheets from a flat position - this vanishing point perspective is automatically corrected. This means that the recorded image is automatically processed by means of a corresponding image transformation so that edges that are actually parallel also run parallel to one another in the recorded image. In particular, this also means that the recorded perspective image is converted into a top view image.Such a correction is particularly important when the sheets deposited on the conveyor belt extend only across part of the conveyor belt's width and are positioned at the edges. The camera is generally preferably positioned centrally with respect to the conveyor belt. Due to the camera's location in front of the inspection area, the off-center arrangement of the sheets leads to a certain distortion, which, without appropriate correction of the vanishing point perspective, can lead to errors in edge detection and edge evaluation.

[0033] In corrugated board systems, several individual sheets are often arranged side by side on the conveyor belt. These individual sheets are also referred to as blanks. They are created, for example, by dividing a sheet lengthwise into different individual sheets. A preferred development now provides for automatic detection of these individual sheets. For this purpose, the captured image is evaluated with the aid of automatic image analysis for longitudinal structures, such as cutting edges or grooves running lengthwise. Here, too, automatic edge extraction is performed in a preferred embodiment.

[0034] In this case, the brightness contrasts are often less pronounced than at the front edges, making edge detection more difficult. In a preferred further development, information from a system control system is therefore used and taken into account for the automatic image analysis. This information is, in particular, information about where creasing or cutting is taking place. In particular, the position of the cutting blade is taken from the system control system and taken into account for the image analysis. This makes it possible to significantly limit the image area to be examined with regard to longitudinal structures. Further information is, for example, the width of a respective individual sheet, which is known and stored in the system control system.

[0035] If several such individual sheets are arranged next to one another on the conveyor belt, each of these adjacent individual sheets is preferably analyzed for deviations from the flatness, as described above. In a useful embodiment, the camera is also used for an optical monitoring system designed for optical, manual monitoring of the corrugated board plant by operating personnel. For this purpose, the images recorded by the camera are displayed on a monitoring monitor of the monitoring system, which is monitored by the operating personnel. This enables optical manual monitoring of the corrugated board plant and in particular of the conveying device, particularly in real time. The perspective arrangement of the camera at an angle in relation to the conveyor belt enables a good overall overview of the conveying device and the conveyed sheets.

[0036] For the intended inspection of the sheets for deviations from flatness, the camera has a high resolution, in the millimeter range. This means that neighboring pixels depicted in the image represent and resolve two real points on the conveyor system that are separated by only a few millimeters, specifically in the range of 1-5 mm.

[0037] The inspection area depicted in the image typically extends across the entire width of the conveyor belt. This typically ranges between 100 cm and 400 cm, and in particular between 250 and 350 cm. Furthermore, the inspection area has a longitudinal depth that is preferably less than 1 m, and in particular between 40 cm and 75 cm. Depending on the camera's positioning, the depth can also be greater.

[0038] According to the invention, a corrugated board system is further configured with the features of claim 15. This combination of features constitutes an independent invention. The right to file a divisional application in this regard remains reserved. The aspects described below in connection with this further invention also represent preferred developments of the previously described corrugated board system and the previously described method. According to this aspect, an enclosure is mounted in the region of the testing area, which enclosure at least partially covers the conveyor device, at least the conveyor belt, and spans it in the transverse direction transversely to the longitudinal direction. With the aid of this enclosure, the testing area is specifically shaded from the surroundings, so that the testing area is at least partially protected and shaded from light, especially from the side or from above.Furthermore, a lighting element is installed that provides a defined illumination of the inspection area, especially the front edge. This improves the visibility of the inspection area, especially the front edge, making automated image analysis more reliable and accurate.

[0039] A further advantage of the enclosure is that in addition to optical shading, it also provides other protection for the test area, for example against contamination.

[0040] In a preferred embodiment, the lighting element is dimmable, allowing the brightness to be adjusted. This allows the brightness to be adjusted to the ambient lighting conditions and also allows it to be adjusted during operation.

[0041] Alternatively or additionally, the light color can be adjusted. This allows the camera to specifically improve the visibility of structures in the inspection area. Especially when using passive markers, the light color can be adjusted to improve the visibility of the markers.

[0042] The lighting element is preferably attached to the housing, in particular on an inner side. In a preferred embodiment, the housing generally has at least one side wall and preferably two side walls as well as a top wall. The top wall preferably spans the conveyor belt across its entire width. In particular, it connects the two side walls. These are fastened to the conveyor device at the edges, for example. Overall, the housing - viewed in the longitudinal direction - is L-shaped and preferably U-shaped. By arranging it on an inner side and in particular on the inside of the top wall, targeted illumination of the area shaded by the housing is achieved.

[0043] In a preferred embodiment, the lighting element is mounted and / or shaded in such a way that the lighting element is not visible to the camera and / or that the light emitted by the ventilation element does not shine into the camera. Invisible here means that the lighting element is not recognizable in the image recorded by the camera. At the very least, the lighting element, specifically a cone of light emitted by the lighting element, is aligned in such a way that it does not shine into the camera. This ensures good recognizability of the illuminated inspection area, in particular without overexposure (high brightness) of partial areas in the image recorded by the camera. In order to achieve this shading of the lighting element in the direction of the camera, an aperture, for example, is arranged.

[0044] In order to provide the best possible shading of the test area, the enclosure is made of an optically non-transparent, opaque material.

[0045] The enclosure is preferably formed only in the area of ​​the test area, thus extending over only a portion of the conveyor system. Specifically, it is longitudinally adapted to the length of the test area and has a length that corresponds, for example, to between 0.5 and twice the length of the test area. Preferably, the length corresponds, for example, to 0.7 to 1.5 times the length of the test area.

[0046] The height of the enclosure is preferably in the range between 0.2 m and, for example, a maximum of 1 m and is preferably in the range less than 0.7 m or even less than 0.5 m - related to the height of the conveyor belt. Overall, this shades a comparatively narrow area of ​​the conveyor system and thus protects it as well as possible from ambient light. In a preferred embodiment, the lighting element extends transversely to the longitudinal direction and has several individually controllable areas. The individually controllable areas can therefore be used to specifically illuminate defined transverse areas. This is particularly useful if the entire width of the conveyor system is not used, i.e. if the sheets resting on it do not cover the entire width.

[0047] Specifically, the lighting element comprises multiple light elements. Individual LEDs are preferred as the light elements. The light elements can be controlled either individually or in groups to create the controllable areas.

[0048] The various options described above, such as dimming to adjust a suitable illuminance, adjusting the light color (especially through the use of RGB lamps), are preferably implemented during operation of the system, i.e. during the implementation of the process, and are carried out individually or in any combination.

[0049] An embodiment of the invention is explained in more detail below with reference to the figures, which show, in some cases highly simplified representations:

[0050] FIG 1 shows a conveyor device as part of a corrugated board plant in a lateral cross-sectional view,

[0051] FIG 2 a perspective view of a conveyor belt in the direction of a camera,

[0052] FIG 3 a schematic block diagram of parts of the corrugator,

[0053] FIG 4 shows a recorded image of a test area with an extracted front edge and

[0054] FIG. 5 shows the result of a curve fit, which reproduces the profile of the extracted front edge. FIG. 1 and FIG. 2 show, in highly simplified representations, a section of a corrugated board plant 2, a portion of a conveyor device 4, by means of which individual sheets 6 of corrugated board are conveyed and transported in a conveying direction. The conveying direction simultaneously defines a longitudinal direction 8 of the conveyor device 4. The conveyor device 4 has a conveyor belt 10, which is guided by a belt carrier 11.

[0055] The individual sheets 6 rest on the conveyor belt 10, overlapping each other by a portion in the longitudinal direction 8. They therefore rest on one another in a shingled manner. This overlapping arrangement is also referred to below as a shingled arrangement. During operation, the conveyor belt 10 runs continuously, so that the sheets 6 are continuously conveyed in the longitudinal direction 8. The conveyor belt 10 has a width transverse to the longitudinal direction 8 that is typically in the range between 100 cm and 400 cm and in particular in the range between 250 cm and 350 cm. This width defines the maximum corrugated board width that can be produced with the corrugator 2. In the exemplary embodiment, the width of the sheets 6 is significantly less than the width of the conveyor belt 10.

[0056] A predetermined sub-area is assigned to the conveyor system 4 as the inspection area 12. This is represented in Figure 2 by dashed lines. It is preferably a rectangular sub-area of ​​the conveyor system 4, specifically of the conveyor belt 10. In the exemplary embodiment, markers 14 are arranged at the corners of the inspection area 12, specifically at the edge of the conveyor belt 10. For example, they are integrated into an edge flange 16. They are generally fixedly mounted on the conveyor system 4. Alternatively, the inspection area 12 is defined by a defined configuration and orientation, e.g., of the camera 22.

[0057] The conveyor device 4 further generally comprises a support frame 18 (see FIG. 1 ), by means of which the conveyor device 4 is fastened, for example, to a floor and which is also designed to mechanically hold the conveyor belt 10. In the exemplary embodiment, only one conveyor belt 10 is shown. However, conveyor devices 4 frequently comprise several conveyor belts 10, which are arranged, for example, one above the other or next to one another. Typically, each conveyor belt 10 is arranged at an angle and conveys the sheets 6 to a higher level. A stacking device for stacking the individual sheets 6 is usually arranged downstream of the conveyor belt 10.

[0058] A camera system 20 is also assigned to each conveyor belt 10, which has at least one camera 22 and is formed by the latter in the exemplary embodiment. The camera 22 is positioned opposite the longitudinal direction 8 in front of the inspection area 12 and slightly above the conveyor belt 10. The camera 22 is oriented toward the inspection area 12, i.e., a detection range of the camera 22 is aligned with the inspection area 12.

[0059] The camera 22 is preferably a CCD camera with a suitable CCD sensor and a suitable pixel density. The resolution of the camera 22 is sufficiently high. Specifically, the resolution is in the millimeter range, i.e., two adjacent pixels in the captured image I represent a real distance (of the inspection area 12) in the range of a few millimeters, in particular in the range of 1-5 mm.

[0060] Typically, the conveyor device 4 has a lighting device 24 with at least one lighting element, with the aid of which at least a partial area and in particular the inspection area 12 is suitably illuminated. In the exemplary embodiment in Figure 1, several lighting elements are shown. The illumination of the inspection area 12 ensures that the images I recorded by the camera 22 (see, for example, FIG. 4) have a quality sufficient for the intended image analysis. Depending on the design of the markers 14, especially if they are designed as reflective elements or as luminescent elements, the lighting also ensures good recognizability of the markers 14 in the recorded image I. For example, a lighting element is positioned in the area of ​​the camera 22 and illuminates the markers 14 from there. However, active markers 14 are preferably used as markers 14, which have a luminous element, such as, for example,have an LED.

[0061] Due to the staggered arrangement of the individual sheets 6 and the illumination, a front edge 26 of each sheet 6 is clearly visible due to a high light-dark contrast (see in particular FIG. 2 and FIG. 4). FIG. 2 further shows that the sheets 6 are grooved and / or cut in the longitudinal direction 8. This is indicated for each individual sheet 6 by two dashed cutting lines 28. If each sheet 6 is completely severed, several individual sheets 6A, 6B, 6C are present, which are usually also referred to as a blank. The following explanations refer - unless otherwise stated - to a variant in which the respective sheets 6 are merely grooved and not divided into individual sheets 6A, 6B, 6C.

[0062] Normally, the sheets 6 are oriented in the longitudinal direction 8, ie typically the cutting lines 28 and / or their edge edges are oriented parallel to the longitudinal direction 8.

[0063] However, when the individual sheets 6 are deposited on the conveyor belt 10, it can sometimes happen that individual sheets 6 are rotated out of this desired position, as is shown in a simplified manner using one of the sheets 6.

[0064] A corrugated board machine 2 generally consists of several components. Using the corrugated board machine 2, continuous corrugated board is first produced from paper webs, which are then cut to produce the individual sheets 6. The structure and operation of such a corrugated board machine 2 are generally known and typically as follows:

[0065] The paper webs are unwound from a unwinder and fed to the other downstream components of the corrugator 2. To ensure uninterrupted operation, so-called splicers are provided, for example, which enable uninterrupted operation even when changing paper rolls. Using a so-called single-facer machine, a single-sided corrugated board web is first produced. One of the paper webs is corrugated using a corrugated roller and then glued to a first cover web on one side. This is usually fed to further machines for further processing via a so-called bridge, and a second cover web is usually glued onto the corrugated layer of the single-sided corrugated board web opposite the first cover web. For this purpose, the web is typically first fed to a so-called preheater. A gluing unit is provided for gluing.To ensure quality and trouble-free operation, heating devices, traction devices, and other belt guides are also preferred for guiding the paper webs and / or the resulting corrugated board web. The section of a corrugator up to the production of double-sided corrugated board is referred to as the wet end.

[0066] This is followed by the dry end. This is where the previously produced continuous corrugated board web is processed and cut to size. Typically, a so-called short cross cutter is provided first, which is used to remove the so-called start-up waste, for example, during a format change. Furthermore, the dry end, particularly downstream of the short cross cutter, features a cutting and creasing machine that cuts or at least creasing the corrugated board web lengthwise, thus inserting defined click areas.

[0067] Finally, a so-called cross cutter is arranged downstream, which cuts the corrugated cardboard web in the transverse direction to produce the individual sheets 6. Further downstream of the cross cutter is the storage system, which includes the previously described conveyor device 4. The stacking device for stacking the individual sheets 6 is typically arranged downstream of the conveyor device 4.

[0068] The special design of the corrugated board plant 2 as well as the method for monitoring the corrugated board plant, in particular with regard to monitoring whether there is a deviation from the flatness of the individual sheets 6, is explained in more detail below, particularly in connection with FIGS. 3, 4 and 5:

[0069] According to FIG. 3, the camera 22 is connected to an evaluation unit 30, which in the exemplary embodiment is also connected to a system controller 32. This is arranged, for example, in a monitoring room 34, which is equipped with a number of monitors 36 that are part of a manual optical monitoring system 38. The images recorded by the camera 22 are displayed on one of the monitors 36, in particular as a live stream, so that the system can be visually monitored by the operating personnel.

[0070] The system control 32, which can also be divided into several control units, controls the operation of the corrugated board system 2 and in particular also of the conveyor device 4. The evaluation unit 30 shown separately in FIG 3 can be part of the system control.

[0071] For warp detection, i.e., for evaluating whether the sheets 6 deviate from a flat position, images I (see FIG. 4) are continuously recorded using camera 22. These may be individual images or a stream.

[0072] The camera captures a total of 22 images at a suitable frame rate (refresh rate). The frame rate is, for example, in the range of 30 to 60 frames per second (30 Hz - 60 Hz). In principle, cameras with higher or lower frame rates can also be used.

[0073] The recorded images I, i.e., the corresponding electronic image data, are transmitted to the evaluation unit 30. The evaluation unit 30 is suitably configured to perform automatic image evaluation and image processing. For this purpose, the evaluation unit 30 has at least one suitable processor and one or more suitable algorithms, as well as a memory. The image processing and image evaluation process comprises, in particular, the following:

[0074] Steps on:

[0075] In step a, for example, a first image correction is carried out in which distortions caused by the camera lens are corrected.

[0076] In a step b, the markers 14 are detected and the test area 14 is determined in the recorded image I.

[0077] In a further step c, an initial evaluation is performed. For example, it is checked whether the test area 14 shown in the recorded image I is oriented according to a target orientation. If this is not the case, an image correction, for example, a rotation or distortion of the recorded image I, is preferably performed.

[0078] Furthermore, the identified test area 14 is preferably extracted, for example by cropping the image I to the test area 14 identified in the image I.

[0079] Finally, in this step c, the vanishing point perspective is preferably corrected. This involves, in particular, an image transformation so that the perspective representation determined by the camera position is transformed into a top view.

[0080] The above-mentioned steps a to c are preparatory steps for image processing prior to the actual warp check, which is carried out in the following steps:

[0081] In step d, for example, a respective sheet 6 is first generally detected and identified as such. This is done, for example, by detecting the displayed front edge 26.

[0082] In the subsequent step e, edge detection is performed using a suitable algorithm so that the profile of the front edge 26 in the recorded image I is identified and extracted. This is illustrated by way of example in FIG 4 using the lower front edge 26 by the bold line, which thus depicts the identified profile of the front edge 26 and thus forms an extracted front edge 26'.

[0083] FIG 4 generally shows the image I prepared according to steps a to c, in which the extracted front edge 26' is additionally shown.

[0084] In the subsequent step f, the identified profile of the front edge 26 is analyzed and evaluated with the support of suitable algorithms. For this purpose, a mathematical approximation of the extracted front edge 26' is performed in a first step, so that the profile of the front edge 26 is described by a mathematical function. The result of this mathematical approximation is shown as an example in Figure 5. The curve obtained by the mathematical approximation is plotted on the y-axis around a zero position. The x-axis represents the extension of the front edge 26 in the transverse direction.

[0085] Based on this mathematical function, a functional analysis is subsequently carried out in order to derive characteristic parameters for the profile of the front edge 26. These characteristic parameters are, in particular, maximum values, minimum values, distances between these maximum and minimum values, curvature values, a (for example, moving) mean value, and preferably also statistical parameters, such as (standard) deviation from the mean value. One or more of these parameters are used for the analysis. Target values ​​are specified for the various parameters. If these are exceeded, an inadmissible deviation from the flatness is detected and a corresponding error message is issued. In addition or alternatively, the parameters characterizing the profile are output and / or saved, in particular also in connection with the respective underlying image I recorded.In addition to this identification and evaluation of the flatness, the sheets 6 are preferably also monitored for further properties or defects during the automatic image evaluation on the basis of the image I recorded with the camera 22:.

[0086] For example, it is monitored whether the sheets 6 are oriented in their respective target orientation, i.e., typically whether they are aligned parallel to the longitudinal direction 8. The front edge 26 typically runs perpendicular to the longitudinal direction 8. To analyze the target orientation, the length of the front edge 26 in image 1 is measured using image analysis, for example. If this length is smaller than a target length, this indicates that the sheet 6 is twisted.

[0087] In the event that several individual sheets 6A, 6B, 6C are arranged next to one another, automatic identification of the individual sheets 6A, 6B, 6C is preferably also provided. Furthermore, the analysis and evaluation of the profile of the front edge 26 to detect a deviation from the flatness is carried out individually for each individual sheet 6A, 6B, 6C, as previously described in connection with sheet 6.

[0088] To identify the individual sheets 6A, 6B, 6C, the image analysis preferably evaluates the recorded image I with regard to the cutting lines 28 oriented in the longitudinal direction 8. This is again done using edge detection. Preferably, additional information is also used via the system control 32, for example, regarding the position of cutting knives used to create the cutting lines 28 and / or the width of the respective sheets 6 or individual sheets 6A, 6B, 6C. Based on this additional information, the analysis is focused on only limited image areas, thus reducing the computational effort and simultaneously improving the evaluation quality.

[0089] In connection with Figure 2, as a preferred further development but also as an independent invention, a housing 40 is formed in the region of the testing area 12. In the exemplary embodiment, this housing 40 is U-shaped and has two side walls 42 and a top wall 44 which connects the two side walls 42 to one another. The housing 40 spans the entire width of the conveyor device 4 in the testing area 12. In the exemplary embodiment, the housing 40 has a length in the longitudinal direction 8 that corresponds to the length of the testing area 12. On the inside of the top wall 44, a lighting element 46 is arranged which extends transversely across the conveyor belt 10. The lighting element 46 has, as individual lighting elements, in particular individual LEDs which are lined up next to one another in the transverse direction. The lighting element 46 is therefore a type of LED bar.The lighting element 46 is dimmable and is preferably dimmed during operation depending on the current lighting situation. Furthermore, in a preferred development, there is also the possibility of adjusting the color, which is preferably also selected appropriately during operation to clearly distinguish the desired structures within the inspection area 12 in the camera image. In particular, this improves the visibility of the front edge 26 and / or the markers 14. The lighting element 46 has individually controllable areas or segments, which are preferably arranged next to one another in the transverse direction. These areas are, in particular, groups of individual LEDs.

[0090] This configuration allows the inspection area 12 to be suitably illuminated depending on the current requirements and lighting situation, with the intensity and / or color being suitably adjusted for this purpose. For the desired edge detection, this results in, in particular, a better prominence of the shadow cast by the front edge 26. The enclosure 40 protects the inspection area 12 from externally incident scattered light and other sources of interference, as well as from contamination. A light cone emitted by the illumination element 46 is preferably oriented obliquely downward, and preferably in such a way that the shadow cast by the front edge 26 is as prominent as possible. List of Reference Symbols

[0091] 2 corrugated board lines

[0092] 4 Conveyor system

[0093] 6 sheets

[0094] 6 A, B, C single sheets

[0095] 8 Longitudinal direction

[0096] 10 Conveyor belt

[0097] 11 band carriers

[0098] 12 Test area

[0099] 14 markers

[0100] 16 flange

[0101] 18 Support structure

[0102] 20 camera system

[0103] 22 Camera

[0104] 24 Lighting device

[0105] 26 front edge

[0106] 26' extracted front edge

[0107] 28 Cutting line

[0108] 30 evaluation unit

[0109] 32 Plant control

[0110] 34 Monitoring room

[0111] 36 monitors

[0112] 38 manual monitoring system

[0113] 40 Enclosure

[0114] 42 side wall

[0115] 44 upper wall

[0116] 46 lighting element

[0117] I captured image

Claims

Claims 1. A method for monitoring the flatness of sheets (6) of corrugated cardboard in a corrugated cardboard plant (2), wherein a) the sheets (6) are placed partially superimposed on a conveyor belt (10) extending in a longitudinal direction (8), so that a front edge (26) of a leading sheet (6) rests on a trailing sheet (6), b) a defined area of ​​a conveyor device (4) of the corrugated cardboard plant (2) is specified as the inspection area (12), c) at least one camera (22) is provided, with which images (I) of the inspection area (12) are recorded, characterized in that d) the camera (22) is positioned leading to the inspection area (12) as viewed in the longitudinal direction (8) and is oriented obliquely towards the inspection area (12) and thus towards the front edge (26) of a sheet (6) located in the inspection area (12),e) on the basis of at least one of the recorded images (I), the profile of the front edge (26) is analyzed with regard to a deviation from a flat position of the sheet (6) by means of an automatic image evaluation.

2. Method according to the preceding claim, characterized in that an edge extraction is carried out to identify the front edge (26) and an extracted front edge (26') is obtained.

3. Method according to the preceding claim, characterized in that the course of the extracted front edge (26') is evaluated with regard to the deviation from a flat position.

4. Method according to the preceding claim, characterized in that for evaluation the extracted front edge (26') is approximated with a curve fit and a mathematical function contained therein is evaluated with regard to a deviation from a flat position.

5. Method according to one of the preceding claims, characterized in that the sheets (6) are checked for twisting, in particular on the basis of an evaluation of the front edge (26).

6. Method according to one of the preceding claims, characterized in that a measurement of a distance between surface areas of the respective sheet (6) with respect to a reference height is dispensed with.

7. Method according to one of the preceding claims, characterized in that markers (14) are fixedly attached in the region of the conveyor belt (10) and are correlated with the test area (12), the markers (14) also being detected by the camera (22) so that they are included in the recorded image (I).

8. Method according to the preceding claim, characterized in that the position of the markers (14) in the recorded image (I) is evaluated and it is checked whether the test area (12) depicted in the recorded image (I) is oriented according to a predetermined target orientation.

9. Method according to one of the preceding claims, characterized in that due to the arrangement of the camera (22) obliquely in front of the test area (12), the recorded image (I) has a vanishing point perspective and that a correction of the vanishing point perspective is carried out automatically.

10. Method according to one of the preceding claims, characterized in that a plurality of individual sheets (6A, 6B, 6C) are arranged next to one another on the conveyor belt (10) and an automatic individual sheet detection is carried out, wherein for this purpose preferably longitudinal structures are evaluated and in particular information from a system control (32) is also used. 11 . Method according to one of the preceding claims, characterized in that several individual sheets (6A, 6B, 6C) are arranged next to one another on the Conveyor belt (10) are arranged and for each individual sheet (6A, 6B, 6C) it is checked whether there is a deviation from the flatness. Method according to one of the preceding claims, characterized in that the camera (22) is simultaneously used for an optical monitoring system (38) for optical manual monitoring by operating personnel. Method according to one of the preceding claims, characterized in that the camera (22) has a resolution in the millimeter range. Corrugated cardboard plant (2), in which - at least one conveyor device (4) extending in a longitudinal direction (8) is arranged for conveying sheets (6) of corrugated cardboard, wherein the sheets (6) are placed partially superimposed on the conveyor belt (10) during operation, so that a front edge (26) of a leading sheet (6) rests on a trailing sheet (6), - a defined area of ​​the conveyor (4) is specified as the test area (12), - at least one camera (22) is arranged, which is designed to record images (11) of the test area (12), characterized in that - the camera (22) is positioned in front of the test area (12) when viewed in the longitudinal direction (8) and is oriented obliquely towards the test area (12) and thus towards the front edge (26) of a sheet (6) located in the test area (12), - an evaluation unit (26) is arranged, which is configured to analyze the profile of the front edge (26) with regard to a deviation from a flat position of the sheet (6) on the basis of at least one of the recorded images (I) by means of an automatic image evaluation. Corrugated cardboard plant (2), in particular according to the preceding claim, in which - at least one conveyor device (4) extending in a longitudinal direction (8) is arranged for conveying sheets (6) of corrugated cardboard, - a defined area of ​​the conveyor (4) is specified as the test area (12), - at least one camera (22) is arranged, which is designed to record images (11) of the test area (12), characterized in that - the camera (22) is directed towards the test area (12) to take images showing the test area, - a housing (40) covering the conveyor device (4) is mounted in the region of the test area (12), wherein a lighting element (46) is arranged which illuminates at least part of the test area (12).

16. Corrugated cardboard system (2) according to the preceding claim, in which one or more of the following features is / are implemented: a) the lighting element (46) is dimmable and / or the light color is adjustable, b) a light cone emanating from the lighting element (46) is oriented obliquely towards the inspection area (12), c) the lighting element (46) is attached to an inner side of the housing (40), d) the housing (40) has at least one side wall (42), preferably two side walls (42) and a top wall (44), e) the lighting element (46) is attached and / or shaded such that the lighting element (46) is not visible to the camera (22) and / or the light emitted by the lighting element (46) does not shine into the camera (22), f) the housing (40) is made of an opaque material,g) the housing (40) is formed only in the area of ​​the test area (12) and has a length in the longitudinal direction (8) which is particularly adapted to the length of the test area (12), for example in the range from 0.5 times to 2 times the length of the test area (12), h) the lighting element (46) extends transversely to the longitudinal direction (8) and has a plurality of individually controllable regions, in particular a plurality of individual LEDs, which can preferably be controlled individually or in groups.

Images