Cable processing station, cable machine with cable processing stations, and computer-implemented method

Description

[0001] The invention relates to a cable processing station, a cable machine with cable processing stations and a computer-implemented method according to the independent claims.

[0002] Optical cable inspection systems are well known. They are used for quality control in cable processing, for randomly inspecting finished cable systems consisting of a cable end and a cable connection element, such as a connector for electrically or optically connecting a cable to a terminal device.

[0003] US20020036770A1 describes such an inspection device, with which the fastening state of an electrical cable through a crimped piece of the terminal metal fitting can be assessed. The terminal metal fitting inspection device comprises an illumination lamp, a CCD camera for capturing an image, a dark box, and a control unit. The control unit assesses the good or bad crimping state of at least a portion of the crimped piece based on a dark area in an inspection area of ​​the image. A similar method is known from EP 0 702 227 A1.

[0004] The disadvantage of these known solutions is that errors are detected so that the defective parts can be sorted out, but this does not involve a fundamental change in the cable processing process.

[0005] EP 3 146 600 B1 shows a crimping device with an image recording device which monitors a positioning process of a cable prior to a crimping process relative to a connecting element in that the image recording device detects the position of a cable end of the cable and transmits it to the control device of the crimping device.

[0006] The disadvantage of these known solutions is that an incorrect cable type cannot be detected in the crimping device. Furthermore, the crimping tool must remain open for a long period of time to capture an image of the connector. This leads to a relatively long downtime in the process.

[0007] DE 10 2016 122 728 A1 comprises a measuring system-guided cable positioning system comprising a cable processing device with an image processing system for recording an image of a cable end and a feeding device for feeding the cable to the cable processing device, wherein a position of the cable in a processing area of ​​the cable processing device can be determined based on the recorded image of the cable end.

[0008] The disadvantage of this known solution is that the cable can only be positioned within the processing area of ​​the cable processing device using the feeder. Another disadvantage is that no material zones on the cable are detected.

[0009] The object of the present invention is therefore to create a cable processing station that avoids at least one of the aforementioned disadvantages and, in particular, enables rapid adjustment of the cable processing process after deviations from an ideal cable processing process have been detected. Furthermore, a cable processing machine is to be created that has a high degree of cable processing reliability. Furthermore, a computer-implemented method for controlling at least one cable processing station is to be created, which corrects production errors in the cable processing station and thus improves the cable processing process.

[0010] The problem is solved by the features of the independent claims. Advantageous further developments are set forth in the figures and in the dependent patent claims.

[0011] A cable processing station according to the invention for processing a cable end of a cable, in particular an electrical or optical cable, comprising at least one first tool for processing the cable and a control device for controlling the at least first tool. Furthermore, the cable processing station according to the invention comprises at least one first imaging sensor device for detecting at least one image of at least one cable end of the cable, as well as an image processing system.The image processing system is connected to the control device for exchanging control-specific parameters and is configured to recognize a first cable-specific image parameter and at least one second cable-specific image parameter from the at least one detected image, and to create at least one control-specific parameter based on the first cable-specific image parameter and the second cable-specific image parameter and to transmit it to the control device for controlling the first tool.

[0012] In other words, the at least one control-specific parameter is created based on a combination of the at least one first cable-specific image parameter and the second cable-specific image parameter. The first tool can be automatically controlled or regulated based on the at least one control-specific parameter, enabling rapid tracking of the cable processing process in the cable processing station. A control-specific parameter is suitable for creating a control data record with at least one control command, at least for the first tool of the cable processing station, in the control device.

[0013] The first cable-specific image parameter, for example, is the electrical conductor detected in the image, also typically referred to as the cable core or cable core. The second cable-specific image parameter, for example, is the cable insulation detected in the image, also typically referred to as the sheathing of the electrical conductor. The combination of the detection of the at least one first cable-specific image parameter and the second cable-specific image parameter subsequently leads to a specific cable type in the image processing system, which can be processed with the cable processing station or is intended for processing in the cable processing station. The control data sets relevant for this cable type can be automatically retrieved by the control device in order to process the cable end with the first tool.For example, a cable processing station is a stripping station for stripping the cable end or a crimping press for crimping a cable connection element onto the electrical conductor, or others, wherein the first tool is a cable conveyor, a stripping knife, or a crimping tool. Furthermore, the cable processing station can comprise a sealing element fitting device, with which a seal can be applied to the cable end or the electrical conductor. The first tool can be a means for applying the seal to the cable, typically a gripper mechanism or a pneumatic fitting device. The tools are typically each driven by a drive such that they can carry out the intended process steps. The respective tool drives are electrically connected to the control device for exchanging the control-specific parameters.

[0014] A stationary camera or a line sensor can be used as the first imaging sensor device, which can be moved relative to the cable using a typical raster method. A stationary camera can be positioned at the cable processing station to save space. A movable line sensor can detect a larger cable end on the cable. Alternatively, the camera can be arranged on a movement device at the cable processing station so that it can be moved, for example pivotably, from the first tool of the cable processing station to another tool of the cable processing station. The camera can, in particular, detect several images of the cable end of the cable in order to make a larger selection of detected images available to the image processing system. The camera can thereby detect images of the cable orfrom the cable end from different perspectives and, in particular, detect at least one image of a front view of the cable axis in order to record the layer structure of the cable. This allows, for example, a twist (twist) of the electrical conductor to be identified in the detected image. The camera mentioned here typically has a zoomable lens and various commercially available filter elements and is configured to detect three-dimensional images.

[0015] Furthermore, a further imaging sensor device can be arranged at the cable processing station, so that the at least one detected image can consist of several partial images and / or can be detected from several recording angles to the cable end of the cable in order to improve the image quality or the recording quality of the detected images.

[0016] Preferably, an AI module is provided, which is connected to the at least one first imaging sensor device and is configured to capture the first cable-specific image parameter and at least the second cable-specific image parameter from the at least one detected image. An AI (artificial intelligence) module can be trained, for example, with external or separate image data or parameters (material, structure, color, shape, etc.) for the respective cable type. For this purpose, the AI ​​module can have a computing unit for easy training. This AI module can thus be used in a wide range of applications, improving the accuracy, particularly when analyzing many different cable types. Furthermore, the evaluation speed in the image processing system can be improved. The AI ​​module works flexibly with different cable types and also with different cable connection elements.

[0017] The AI ​​module preferably comprises at least one neural network configured to analyze the at least one detected image. For example, the neural network can be trained using the at least one detected image. The neural network can be trained with image parameters to enable improved future testing of the process steps in the cable processing station, depending on the quality of the training images or reference images or reference contours, toward the ideal cable processing process. Furthermore, the AI ​​module enables the cable processing process, or the multiple process steps occurring therein, to be carried out largely independently of an operator, since the neural network assumes the operator's tasks.The downtime at the cable processing station is thus minimized because, for example, when changing the order from a first cable processing process to a further cable processing process, no learning process of the neural network is necessary and no adjustment steps on the cable processing machine by the operator are required.

[0018] Further preferably, the AI ​​module performs a semantic segmentation of the at least one detected image in order to assign at least one cable-specific image parameter to each pixel of the detected image, as well as to transfer the first analyzed cable-specific image parameter and at least the second analyzed cable-specific image parameter to the image processing system. Such image processing is disclosed, for example, in Liang-Chieh Chen et al. "Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation," Google Inc., 2018, arXiv:1802.02611, wherein the detected image is processed. A background signal is assigned to a pixel of the detected image as a cable-specific parameter if no cable end or cable is present for this pixel of the detected image.

[0019] In an alternative embodiment, the image processing system is configured to perform a segmentation of the at least one detected image. The detected image is processed in such a way that it is, for example, filtered or analyzed, so that the analyzed image has a higher image quality, particularly in those areas where the cable end is visible, and thus a first analyzed cable-specific image parameter and a second analyzed cable-specific image parameter can be determined more effectively. Advantageously, the image processing system comprises a computing unit that simply executes at least the aforementioned analyses or computational steps.

[0020] Alternatively or additionally, the image processing system is configured to divide the at least one detected image of the cable end into at least two material-specific regions based on the first cable-specific image parameter and the second cable-specific image parameter. A material-specific region differs from another material-specific region in the recorded image in that they comprise at least different materials. This makes it easy to divide the cable end into at least two regions so that the image processing system can, for example, detect unwanted cable insulation residues or other foreign bodies at the cable end. Furthermore, this simple subdivision makes it easy to detect unwanted cut wires in the cable shielding on the dielectric of a coaxial cable, thus preventing subsequent short circuits or defective high-frequency connections on the processed cable.

[0021] The image processing system is preferably configured to divide the at least one detected image of the cable end into at least two material-specific regions based on the first analyzed, cable-specific image parameter and the second analyzed, cable-specific image parameter. This allows for improved detection of the previously described unwanted cable insulation residues or other foreign bodies at the cable end, since the detected image is, for example, filtered to obtain analyzed cable-specific image parameters. Furthermore, by distinguishing material-specific regions in the image, a cable shield or cable foil folded back on the cable can be detected. As a result, subsequent interruptions in the cable processing can be prevented, and at the same time, the end products can be manufactured with higher quality, such as the service life of the processed cable.

[0022] Preferably, the first material-specific region comprises at least the electrical conductor of the cable, and the second material-specific region comprises at least the cable insulation or cable shielding (e.g., in the case of a coaxial cable or a high-voltage cable). These material-specific regions can be analyzed by the image processing system with regard to their surface area and their edge structure, also referred to as contour, in order to analyze, for example, boundary areas between the first material-specific region and the second material-specific region. For example, the image processing system is configured to detect, measure, and / or calculate the surface area, the surface circumference or the surface diameter, or the edge structures of the respective material-specific regions.For example, during the process step of stripping the cable insulation, and the associated removal process step, a cable strand of the electrical conductor is cut, and after the cable insulation is removed, a single cable strand protrudes or sticks out from the electrical conductor. With the detection of the aforementioned material-specific areas by the AI ​​module and / or the image processing system, it is now possible to determine in the analyzed image whether this is a protruding cable strand or a piece of cable insulation. A piece of cable insulation at the tip of the electrical conductor can, if necessary, be tolerated for subsequent process steps when attaching a cable connection element.With known comparable methods, such as a shadow image method, it is not possible to distinguish the material of the protruding object from the material of the other objects in the detected image, so that false error messages occur, which lead to the discarding of a usable cable.

[0023] For example, the stripping knife is a rotary knife, with the control device configured to provide a control-specific parameter to automatically adjust (e.g., to set deeper) the cutting depth of the rotary knife when processing the cable, such as a coaxial cable. This allows the rotary knife to repeat the cutting process if at least one individual electrical conductor was not cut when cutting the shielding layer and was detected as a material-specific area (material zone) on the dielectric. Such individual conductors that are not cut can be critical because they could cause a short circuit in the connector at a later point in the life cycle of the finished cable.This post-processing of the unfinished cable end also has the advantage that a cable that has already been cut to length does not have to be disposed of, thus reducing the consumption of raw materials.

[0024] Furthermore, for example in the case of a sheathed cable with multiple electrical wires or a shielded multi-conductor cable with filler, the alignment of the electrical wires is detected and analyzed using the image processing system in such a way that an end-face image can be measured. With the analyzed alignment of the electrical conductors, a rotating module, as a first tool, is controlled in a second step using the control-specific parameters of the control device. This rotating module aligns the electrical wires horizontally in the sheathed cable. To calculate the rotation angle for the rotating module, the measured alignment is calculated using the known twist of the electrical wires in the computing unit. This means that in a subsequent process step, the sheath or filler can be cut using a forming knife, as an additional tool, without damaging the electrical wires contained therein.The control device includes further control-specific parameters for the previously described subsequent process step and is configured to control the form knife in the subsequent process step.

[0025] Preferably, a database is provided which is connected to the image processing system, wherein the database has at least one storage unit and reference images for different cable ends are stored in the at least one storage unit. At least one, advantageously several, reference images for different cable types are stored in the storage unit of the database, which reference images can be processed in the cable processing station and can be retrieved by the image processing system. At the start of a cable processing process, an order with order data for the cable to be processed is typically transmitted to the control device of the cable processing station, which can access the database and its contents. The image processing system compares the detected or analyzed images with the reference images from the database and / or with the information on the current order.The reference images, for example, feature segmented areas that are easily comparable with the detected or analyzed image. This allows the cable processing process to be carried out without an operator. The order data for the cables or cable types to be processed includes, among other things, control data sets and / or control-specific parameters for controlling the first tool, as well as corresponding control tolerances, cable-specific image parameters, and / or material-specific areas including tolerance values. This allows those processed cables that are within the respective tolerances to be further processed. This reduces scrap at defective cable ends and increases productivity at the cable processing station.

[0026] Alternatively or additionally, a database is provided which is connected to the image processing system, wherein the database has at least one storage unit and in which at least one storage unit reference contours for different cable ends and / or sealing elements and / or cable connection elements are stored. In the storage unit of the database, at least one, advantageously several, reference contours for different cable types are stored, which can be processed in the cable processing station and can be called up by the image processing system. At the start of a cable processing process, an order with order data for the cable to be processed is typically transmitted to the control device of the cable processing station, which can access the database and its contents. The image processing system compares the detected oranalyzed images with the reference contours from the database and / or with the information on the current order. The order data for the cables or cable types to be processed includes, among other things, control data sets and / or control-specific parameters for controlling the first tool, as well as corresponding control tolerances, as well as cable-specific image parameters and / or material-specific ranges including tolerance values, so that those processed cables that are within the respective tolerances can be further processed. This reduces scrap at defective cable ends and increases productivity at the cable processing station.

[0027] Advantageously, the reference contours are stored individually as contour vectors. The contour vector is easily assigned to the detected or analyzed image, while the data volume of a contour vector is small compared to that of a reference image, thus accelerating data processing.

[0028] Advantageously, the database stores control-specific parameters and / or control data sets with which the at least one first tool can be controlled or regulated. The control-specific parameters and / or control data sets can be transmitted to the control device, allowing it to easily control the drive of the at least one first tool.

[0029] Alternatively or additionally, the database is connected to the AI ​​module, with reference images of different cable ends stored in at least one storage unit of the database. The image processing system compares the detected or analyzed images with the reference images from the database without requiring an operator.

[0030] Alternatively or additionally, the database is connected to the AI ​​module, with reference contours for different cable ends stored in at least one storage unit of the database. The image processing system compares the detected or analyzed images with the reference contours from the database without requiring an operator. The reference contours can be stored in the database as contour vectors, as previously mentioned.

[0031] Alternatively or additionally, at least one target value for at least one cable-specific image parameter is stored in the database's storage unit. These target values ​​can be target values ​​for the stripped length of the cable end and / or the width or thickness of the electrical conductor and typically include tolerance values ​​for the respective target values ​​for the respective cable type. Furthermore, these target values ​​include symmetry values ​​or ratio values, such as a ratio of the stripped length to the thickness of the electrical conductor or to the cable type currently in the cable processing process.

[0032] Alternatively or additionally, at least one target value for at least one material-specific area is stored in the database's storage unit. These target values ​​can include target values ​​for the area size, the area circumference or the area diameter, or the edge structure of the respective material-specific area, or a combination of the aforementioned values ​​and have corresponding tolerance values. For example, the image processing system can retrieve these target values ​​individually or in bulk and compare them with the detected material-specific area.

[0033] Advantageously, the computing unit is configured to create at least one deviation value from a comparison of the at least one target value and a measured cable-specific image parameter, which can be easily processed further.

[0034] Preferably, the image processing system is configured to capture at least the first cable-specific image parameter and / or at least the first analyzed cable-specific image parameter from the detected image of the cable end using an image measurement method. The image measurement method comprises at least one image measurement algorithm, which is disclosed, for example, in S. and Abe, K., "Topological Structural Analysis of Digitized Binary Images by Border Following", CVGIP 30 1, pp. 32-46 (1985). This allows the edge structures of the material-specific regions to be calculated. The edge structures can be divided into contour points and then mathematically filtered using a direction vector to obtain only the measurement points of the cut edges. In a further step, the median, the 10% quantile, and the 90% quantile of the measurement points along the longitudinal axis of the cable can be statistically evaluated.The statistical scatter of the measurement points at the cutting edge along the cable's longitudinal axis can be used to derive an attribute of the cutting quality in the cable processing process. Furthermore, a cable-specific parameter can include, for example, the stripping length at the cable end and thus be a length measurement.

[0035] The image measurement algorithm is alternatively or additionally configured to geometrically measure the detected image in a first step to determine the first cable-specific image parameter and the second cable-specific image parameter. The detected image is processed in such a way that, in a first step, the stripped length at the cable end is determined as the first cable-specific image parameter by measuring the length between the end of the electrical conductor and the cable insulation in the detected image. At the same time, the second cable-specific image parameter is determined by identifying the boundary area to or the beginning of the cable insulation.Based on the design of the detected boundary area for the cable insulation, for example, the position of the cable in the cable processing station can be determined and / or the correct stripping of the cable insulation from the cable end and / or the correct positioning of a sealing element at the cable end can be determined or verified. Alternatively or additionally, the image measurement algorithm is configured to detect contamination or production residues in the detected image, thus fulfilling another quality criterion for an ideal cable processing process.

[0036] Preferably, the first cable-specific image parameter and / or the second cable-specific image parameter is selected from at least one of the group consisting of the color, structure, or shape of the electrical conductor, the cable insulation, a cable shield, and / or a sealing element. This allows different colors, structures, and shapes to be identified in the at least one detected image.

[0037] Color recognition, for example, enables rapid differentiation between the electrical conductor and the cable insulation. Furthermore, color recognition can be used to identify the material of the electrical conductor and, for example, to differentiate between electrical conductors made of copper and aluminum. Furthermore, coatings such as tin plating on the electrical conductor can also be identified. For example, if the color of the sealing element is identified using the first cable-specific image parameter and the edge structure of the sealing element is identified or inspected using the second cable-specific image parameter, interruptions in the cable processing can be prevented, while simultaneously preventing the consumption or waste of cable connection elements and / or cable material.

[0038] For example, structure recognition enables a distinction to be made between an electrical conductor consisting of individual cable strands and a solid electrical conductor. Furthermore, structure recognition detects different cable insulation materials. Furthermore, structure recognition enables the identification of a faulty cable and / or sealing element and / or cable connection element. For example, a faulty sealing element that has been incorrectly positioned at the cable end can be detected. In particular, the faulty sealing element can be detected before it is positioned at the cable end, preventing further processing of this cable. This allows potential rejects to be identified promptly, preventing further cable processing steps involving a faulty sealing element.

[0039] Shape recognition, for example, makes it possible to distinguish between imperfectly cut or poorly cut cable insulation after stripping the sheath at the cable end. Shape recognition also makes it possible to distinguish between an untwisted cable end and a twisted cable end, as well as, for example, the protrusion of one or more conductor wires from the desired orientation of the cable end. For example, when applying a sealing element to the cable end, it may happen that at least one conductor wire is positioned at the cable end in such a way that a leaky area is created at the cable end, which later causes corrosion damage to the processed cable.As previously explained, the image processing system and / or the AI ​​module independently detects the different material-specific areas belonging to the electrical conductor, the cable insulation, and the sealing element, thus preventing the production of defective cables. The aforementioned detections can be performed individually or in various combinations during and after processing the cable end with the first tool.

[0040] The AI ​​module is preferably configured to capture at least one further cable-specific image parameter from the at least one detected image. Thus, the at least one control-specific parameter is based on at least one further piece of information about the cable end or on a process parameter in the cable processing process. This process parameter can, for example, include an insertion position of the cable end in the first tool. The further cable-specific image parameter is detected in the same way as the image parameters described above. Alternatively or additionally, the image processing system is configured to capture the at least one further cable-specific image parameter from the at least one detected image.

[0041] In particular, a cable connection element for the cable end of the cable is to be assigned to the additional cable-specific image parameter. For example, the insertion position of the cable end within the cable connection element can be calculated by evaluating the lengths of the material-specific area of ​​the cable end and the material-specific area of ​​the cable connection element relative to each other. In particular, the previously described image measurement algorithm can be used to calculate how the area of ​​the electrical conductor and the area of ​​the cable insulation are divided. Likewise, the distance the tip of the electrical conductor extends beyond the foremost fastening zone on the cable connection element can be measured by calculating the length of the foremost material-specific area of ​​the electrical conductor.

[0042] Preferably, the control device is configured to stop and / or prevent a process step of the at least one first tool based on the at least one control-specific parameter. By sorting out faulty cable ends, no faulty cables are produced. Process reliability is thus increased, and consequential damage to the devices containing the processed cables is prevented.

[0043] The computer-implemented method according to the invention for automatically determining and generating control data sets and / or control-specific parameters for controlling at least one cable processing station which processes at least one cable end of a cable, wherein at least one image of the at least one cable end of the cable is detected with a first imaging sensor device, and at least one control data set and / or one control-specific parameter is automatically generated and stored, and an image processing system is present which receives the at least one detected image and recognizes a first cable-specific image parameter and at least one second cable-specific image parameter, and creates the at least one control data set and / or the at least one control-specific parameter on the basis of the first cable-specific image parameter and the second cable-specific image parameter.

[0044] The at least one control-specific parameter and / or at least one control data set is created based on a combination of the at least one first cable-specific image parameter and the second cable-specific image parameter. The combination of the at least one first cable-specific image parameter and the second cable-specific image parameter subsequently leads, in the image processing system, to a specific cable type, which is processed in particular with the cable processing station described here or is intended for processing in the cable processing station. The first tool is subsequently controlled or regulated based on the at least one control-specific parameter in such a way that rapid tracking of the cable processing process at the cable processing station is possible.

[0045] The control data set and / or the control-specific parameter control or regulate at least the movement or work activity of at least the first tool. The first tool can, for example, be movable from an initial state to a final state and / or activated or deactivated. These movements typically include control tolerances.

[0046] Preferably, at least one control-specific parameter is transmitted to the control device, whereby at least the first tool can be controlled or regulated directly and automatically.

[0047] Preferably, at least one control data record is transmitted to a storage unit. This allows this at least one control data record to be easily stored in the storage unit and stored for a longer period of time for later access.

[0048] Preferably, the first cable-specific image parameter and at least the second cable-specific image parameter are captured from the at least one detected image using an AI module, with the AI ​​module analyzing and processing the at least one detected image. The AI ​​module operates flexibly and automatically, recognizing different cable types and also different cable connection elements.

[0049] Alternatively or additionally, the first cable-specific image parameter and at least the second cable-specific image parameter are captured from the at least one detected image using the image processing system, with the image processing system analyzing and processing the at least one detected image. This allows cable-specific parameters to be provided quickly and easily for the subsequent process.

[0050] Preferably, a semantic segmentation of the at least one detected image is performed, and at least one cable-specific image parameter is assigned to each pixel of the detected image. The detected image is filtered or analyzed, for example, so that the analyzed image has a higher image quality, particularly in those areas where the cable end is visible, and thus a first analyzed cable-specific image parameter and a second analyzed cable-specific image parameter are determined.

[0051] The AI ​​module is advantageously trained using at least one cable-specific image parameter, which comprises a neural network. The neural network can be trained with cable-specific image parameters in order to generate improved future control data sets and / or control-specific parameters, depending on the quality of the training images or reference images, and to perform improved testing of the process steps in the cable processing station. Furthermore, the AI ​​module enables the cable processing process or the multiple process steps involved to be carried out largely independently of an operator, since the neural network takes over the operator's tasks.The downtime at the cable processing station is minimized because, for example, when changing the order from a first cable processing process to a further cable processing process, no learning process of the neural network is necessary and no adjustment steps on the cable processing machine by the operator are required.

[0052] Preferably, the at least one detected image of the cable end of the cable is divided into at least two material-specific regions based on the first cable-specific image parameter and the second cable-specific image parameter. One material-specific region differs from another material-specific region in that they comprise at least different materials. This allows the cable end of the cable to be easily divided into at least two regions so that the image processing system can, for example, detect unwanted cable insulation residues or other foreign bodies at the cable end. Furthermore, with this simple subdivision, unwanted cut wires of the cable shield on the dielectric of a coaxial cable can be easily detected, thus preventing a subsequent short circuit or inadequate high-frequency connections at the processed cable end.

[0053] Preferably, the at least one detected image of the cable end of the cable is divided into at least two material-specific regions based on the first analyzed cable-specific image parameter and the second analyzed cable-specific image parameter. This allows for improved detection of the previously described unwanted cable insulation residues or other foreign bodies at the cable end, since the detected image is, for example, filtered to obtain analyzed cable-specific image parameters. As a result, subsequent interruptions in the cable processing can be prevented, while simultaneously producing end products with higher quality, such as the service life of the processed cable.

[0054] Preferably, the first material-specific region is assigned to the electrical conductor of the cable, and the second material-specific region is assigned to the cable insulation. Subsequently, the material-specific regions are measured or analyzed, in particular with regard to their surface area and / or region length and / or their edge structure, in order, for example, to easily identify boundary regions between the first material-specific region and the second material-specific region. The position of the first tool and the associated control-specific parameter are calculated based on the size (length times width) of the material-specific region. Measuring the region length can be used to determine the position change of the stripping blade, referred to as the first tool.This process step is improved because the material-specific areas consist of several measuring points, so that there are not only measuring points where the cable insulation protrudes beyond the electrical conductor, but also measuring points on the detected or analyzed image where a change from the first material-specific area to the second material-specific area is detected.

[0055] During the measurement, an image measurement algorithm is used that geometrically measures the image. One of these image measurement algorithms is disclosed, for example, in S. and Abe, K., "Topological Structural Analysis of Digitized Binary Images by Border Following," CVGIP 30 1, pp. 32-46 (1985). This allows a large number of measurement points to be measured and the edge structures of the material-specific areas to be calculated. The edge structures can be divided into contour points and then mathematically filtered using a direction vector to obtain only the measurement points of the cut edges. In a further step, the median, the 10% quantile, and the 90% quantile of the measurement points along the cable's longitudinal axis are statistically evaluated. An attribute of the cutting quality in the cable processing process is derived from the statistical scatter of the measurement points at the cut edge along the cable's longitudinal axis.This allows you to determine the optimal time to replace the stripping blades.

[0056] Preferably, the at least one cable-specific image parameter is compared with a target value for this cable-specific image parameter, and at least one control-specific parameter is created based on this comparison. These target values ​​can be target values ​​for the stripping length of the cable end and / or the width or thickness of the electrical conductor and typically include tolerance values ​​for the respective target values ​​for each cable type. Furthermore, these target values ​​include symmetry values ​​or ratio values, such as a ratio of the stripping length to the thickness of the electrical conductor or to the cable type currently in the cable processing process. The control-specific parameters created from this can, for example, include the positions of the stripping blade when cutting into the cable insulation and / or the stripping length when stripping the cable insulation from the cable end.

[0057] Alternatively or additionally, the at least one cable-specific image parameter is compared with a target value for this cable-specific image parameter, and at least one control data set is created based on this comparison. A control set typically comprises several control-specific parameters for controlling one or more tools of the cable processing station. A single comparison of the at least one cable-specific image parameter with a corresponding target value allows a conclusion to be drawn about the cable type in the cable processing station, so that it can be automatically controlled and a cable processing process is carried out.

[0058] Alternatively or additionally, the at least one material-specific range is compared with a target value for this material-specific range, and based on this comparison, at least one control data set and / or one control-specific parameter is created. A control set typically comprises several control-specific parameters for controlling one or more tools of the cable processing station. A single comparison of the at least one material-specific range with a corresponding target value allows a conclusion to be drawn about the type and dimension of the cable material and, subsequently, the cable type in the cable processing station, so that the station can be automatically controlled and a cable processing process is carried out.

[0059] Preferably, after comparing the cable-specific image parameter with the corresponding target value, an average value is calculated in the image processing system, which is then compared with the respective tolerance value or target value, and a tracked control-specific parameter is subsequently created. The average value calculation enables the filtering of an erroneous value, such as an extraordinary deviation from the deviation value.

[0060] Alternatively or additionally, after comparing the material-specific range with the corresponding target value, an average value is calculated in the image processing system, which is compared with the respective tolerance value or target value and subsequently a tracked control-specific parameter is created.

[0061] Preferably, the image processing system compares the measured cable-specific image parameter with the corresponding target value, and a deviation value is generated from the comparison. This improves the subsequent cable processing process.

[0062] Advantageously, if there is a deviation in the comparison parameters, the cable in the cable processing process is disposed of so that no faulty cables remain in the cable processing process.

[0063] The cable processing machine according to the invention with at least two cable processing stations, wherein at least one cable processing station is designed as described herein and with which a computer-implemented method as described herein can be carried out, has an image processing system. The image processing system is connected to a central control device for exchanging control-specific parameters and / or control data sets. The image processing system is configured to create at least one control-specific parameter and / or control data set based on the first cable-specific image parameter and the second cable-specific image parameter and to transmit these to the central control device for controlling at least one of the tools of at least one of the two cable processing stations. This allows not only individual cable processing stations to be controlled fully automatically.The control-specific parameters and / or a control data set are forwarded to the central control unit instead of to the individual control units of the cable processing stations. This ensures a high level of cable processing reliability without requiring an operator to be assigned to the cable processing machine.

[0064] Preferably, the first imaging sensor device is configured to detect the at least one image of the cable end of the cable, wherein the cable end of the cable is in the unprocessed state by the cable processing station. Thus, based on the at least one detected image and in particular with the embodiments of the cable processing station as described above, at least one material-specific region can be determined, which can be used, for example, to determine the cable type. Furthermore, an initial inspection of the unprocessed cable can be performed, allowing damaged cable ends to be sorted out early.

[0065] Preferably, the first imaging sensor device is configured to detect a second image of the cable end of the cable, wherein the cable end of the cable is in the state processed by at least one cable processing station. This allows a first control-specific parameter for controlling the first tool to be established at an early stage, said parameter being based on the embodiments of the cable processing station described here.

[0066] Advantageously, the first imaging sensor device is designed to detect a separate image of the cable end at each existing cable processing station, with the cable end present in the state processed by the respective cable processing station. This allows an entire cable processing process with multiple cable processing stations to be quickly adjusted individually after deviations from an ideal cable processing process have been detected. At the same time, a high level of cable processing process reliability is ensured.

[0067] A computer program product according to the invention which can be loaded directly into the internal memory of the central control device of a cable processing machine described here and / or a control device of a cable processing station described here and comprises control-specific parameters and / or control data sets with which the steps according to one of the aforementioned methods are carried out when the computer program product is running on the cable processing station or cable processing machine according to the invention.

[0068] Further advantages, features and details of the invention will become apparent from the following description, in which embodiments of the invention are described with reference to the drawings.

[0069] The list of reference symbols, like the technical content of the patent claims and figures, is part of the disclosure. The figures are described coherently and comprehensively. Identical reference symbols indicate identical components; reference symbols with different indices indicate functionally identical or similar components.

[0070] They show: Fig. 1 shows a first embodiment of a cable processing station according to the invention in a schematic representation, Fig. 2 shows an image of a first cable end of the cable detected by the sensor device, Fig. 3 shows a segmented image according to the image in Fig. 2 , Fig. 4 a representation of a segmented image according to the image in Fig. 3with a first cable connection element, Fig. 5 a representation of a segmented image of a further cable end of a further cable with a further cable connection element, Fig. 6 a representation of a segmented image of a cable end of a high-voltage cable, Fig. 7 a representation of a further segmented image according to the image in Fig. 6 with a sleeve on the high-voltage cable, Fig. 8 a representation of a segmented image of a cable end of another high-voltage cable in front view, Fig. 9 a representation of another segmented image according to the image in Fig. 8 in side view with an adhesive tape on the high-voltage cable, Fig. 10 a representation of another segmented image according to the image in Fig. 9 in front view, Fig. 11 a first flow chart which discloses a method for controlling the cable processing station, Fig. 12 a cable processing machine according to the invention with a cable processing station according to Fig. 1in a perspective view, Fig. 13 the cable processing machine according to Fig. 12 , in a schematic representation, and Fig. 14 a further flow chart showing a method for controlling the cable processing machine according to Fig. 12 revealed.

[0071] Fig. 1shows a cable processing station 20 for processing a cable end 12 of an electrical cable 10, which comprises at least a first tool 22 for processing the cable 10 and a control device 40 for controlling the at least first tool 22. The cable 10 shown is illustrated with different cable ends 12a-12d, which can be processed in different process steps at the cable processing station 20 with at least the first tool 22. The cable 10 with the cable end 12a is unprocessed and has a cable insulation 13 that partially encloses the electrical conductor 14 and exits at the end face of the cable 10. After a further process step, the same cable 10 has the cable end 12b, wherein the electrical conductor 14 is exposed after stripping and the cable insulation 13 is removed in the region of the cable end 12b.After a further process step, the same cable 10 has the cable end 12c, wherein a sealing element 15 is arranged in the region of the cable end 12c. After a further process step, the same cable 10 has the cable end 12d, wherein a cable connection element 16 is arranged and crimped in the region of the cable end 12d. The first tool 22 of the cable processing station 20 and the cable 10 are movable relative to one another in the direction of movement 23, wherein the first tool 22 comprises, depending on the process step, a stripping blade for stripping the cable insulation 13, a fitting device for fitting the sealing element 14, and a crimping tool for crimping the cable connection element 16 onto the cable 10.The cable processing station 20 further comprises at least one first imaging sensor device 25 for detecting at least one image of the cable ends 12a-12d of the cable 10, as well as an image processing system 30. The first imaging sensor device 25 is a camera and has a zoomable lens and various commercially available filter elements 27. The image processing system 30 is electrically connected to the control device 40 for exchanging control-specific parameters and is configured to recognize a first cable-specific image parameter and at least one second cable-specific image parameter from the at least one detected image, and to create at least one control-specific parameter based on the first cable-specific image parameter and the second cable-specific image parameter and to transmit it to the control device 40 for controlling the first tool 22.For example, the electrical conductor 14 is detected as the first cable-specific image parameter, and the cable insulation 13 is detected as the second cable-specific image parameter. The image processing system 30 thus detects the specific cable type of the cable 10. The image processing system 30 has an AI module 32, which is connected to the at least one first imaging sensor device 25 and is configured to capture the first cable-specific image parameter and at least the second cable-specific image parameter from the at least one detected image. An AI (artificial intelligence) module can be trained, for example, with external or separate image data or parameters (material, structure, color, shape, etc.) for the respective cable type.For this purpose, the AI ​​module 32 has a computing unit 33 and a neural network 34 which is designed to analyze the at least one detected image, wherein the neural network 34 is trainable.

[0072] The AI ​​module 32 performs a semantic segmentation of the at least one detected image in order to assign at least one cable-specific image parameter to each pixel of the detected image, as well as to transfer the first analyzed cable-specific image parameter and at least the second analyzed cable-specific image parameter to the image processing system 30. The image processing system 30 is configured to divide the at least one detected image of the cable end 12a-12d into at least two material-specific regions based on the first analyzed cable-specific image parameter and the second analyzed cable-specific image parameter (see also Fig. 3 and 4). One material-specific region differs from another material-specific region in that they comprise at least different materials. Furthermore, a database 50 is present, which is electrically connected to the image processing system 30, wherein the database 30 has a storage unit 55. Reference images of different cable ends 12a-12d, different cable types, and / or sealing elements 15 and cable connection elements 16 are stored in the storage unit 55, which can be processed in the cable processing station 20 and can be retrieved by the image processing system 30. Furthermore, reference contours are stored in the storage unit 55 as contour vectors for different cable ends 12a-12d, different cable types, and / or sealing elements 15 and cable connection elements 16, which can be processed in the cable processing station 20 and can be retrieved by the image processing system 30.Furthermore, control-specific parameters and / or control data sets are stored in the database 50, with which at least the first tool 22 can be controlled or regulated. Furthermore, target values ​​for the cable-specific image parameters are stored in the memory unit 55 of the database 50. These target values ​​can be target values ​​for the stripped length of the cable end 12b and / or the width or thickness of the electrical conductor 14 and typically include tolerance values ​​for the respective target values. Furthermore, these target values ​​include symmetry values ​​or ratio values, such as a ratio of the stripped length to the thickness of the electrical conductor 14 or to the cable type currently being processed. Furthermore, further target values ​​relating to the subdivided material-specific regions are stored in the memory unit 55 of the database 50 and can be retrieved by the image processing system 30.These additional target values ​​can include target values ​​for the surface size, surface circumference or surface diameter or the edge structure of the respective material-specific area, or a combination of the aforementioned values ​​and have corresponding tolerance values.

[0073] The image processing system 30 is configured to acquire at least the first cable-specific image parameter and / or at least the first analyzed cable-specific image parameter from the respective detected image of the cable end 12a-12d of the cable 10 using an image measurement method. The first cable-specific image parameter and / or the second cable-specific image parameter are analyzed with respect to their color and / or structure and / or shape of the electrical conductor 14 and / or the cable insulation 13 and / or a cable shielding (see Fig. 5 ) and / or a sealing element 15.

[0074] The image measurement method comprises at least one image measurement algorithm with which the detected and / or segmented image can be processed. The image measurement algorithm is configured to geometrically measure the detected or segmented image in a first step in order to determine the first cable-specific image parameter and the second cable-specific image parameter, as well as to detect edge structures. The edge structures can be divided into contour points and then mathematically filtered using a direction vector in order to obtain only the measurement points of the cutting edges. In a further step, the median, the 10% quantile, and the 90% quantile of the measurement points along the longitudinal axis of the cable 10 can be statistically evaluated. From the statistical scatter of the measurement points at the cutting edge along the longitudinal axis of the cable 10, an attribute of the cutting quality in the cable processing process can be derived.

[0075] The image processing system 30 compares the cable-specific image parameters and / or the material-specific areas from the detected or analyzed images with the reference images or the respective target values ​​from the database 50 and creates control-specific parameters, which are transmitted to the control device 40. The control device 40 controls the drive 24 of the first tool 22 using the control-specific parameters.

[0076] Fig. 2 to Fig. 4 show a first embodiment of the previously described images. Using this example, the states of the cable end 12a-12d from the process steps and method steps described here are illustrated. Fig. 2shows a first image of the cable end 12b detected by the sensor device 25. The cable end 12b of the cable 10 has a colored (blue) cable insulation 13 and an electrical conductor 14 with several conductor wires, which have a copper-colored, twisted structure. Fig. 3shows the cable end 12b segmented using the AI ​​module 32, in which each pixel of the detected image is assigned at least one cable-specific image parameter. A background signal is assigned to a pixel of the detected image as a cable-specific parameter (e.g., black) if no cable end 12b or cable 10 is present for this pixel of the detected image. The cable insulation 13 is shown in monochrome, and the electrical conductor 14, with several conductor wires, has a hatching. The AI ​​module is trained accordingly and assigns a first material-specific area to the electrical conductor 14 and a second material-specific area to the cable insulation 13. Both the representation of the cable end 12b according to Fig. 2 as well as according to Fig. 3show that a conductor wire 14a deviates from the actual orientation of the electrical conductor 14. The image processing system 30 measures this area 18, as described herein, and compares the analyzed cable-specific image parameters with the target values ​​in the database 50. Fig. 4shows the cable end 12d of the cable 10 segmented using the AI ​​module 32, wherein the cable 10 has a cable connection element 16 designed as a plug. The cable connection element 16 is attached or crimped to the two crimping areas 16a, to the electrical conductor 14, and to the cable insulation 13 using a tool 22 designed as a crimping tool. The segmented image shows colors or hatching assigned to the aforementioned areas or components, which indicate their color and / or structure and / or shape and are recognized and measured by the image processing system 30 in order to be able to transfer a new control-specific parameter or control data set to the control device 40 if necessary.The aforementioned target values ​​may include values ​​for brushing on the conductor wires on the conductor 14 or the length of the protruding conductor wire 14a or a tolerance value for contamination residues on the conductor wire 14a and may also be stored in the storage unit 55 of the database 50.

[0077] Fig. 5 shows a further embodiment of the previously described images of a cable end 12d', comparable to the Fig. 4, wherein this cable 10' represents a coaxial cable as a cable type, to which a further plug is arranged as a cable connection element 16'. The cable connection element 16' is fastened or crimped to the two crimping areas 16a' on the electrical conductor 14' and to the cable insulation 13' using a tool designed as a crimping tool. The cable 10' further has a dielectric 15' and a cable shield 17'. The segmented image shows markings or hatchings assigned to the aforementioned areas or components, which indicate their color and / or structure and / or shape and are recognized and measured by the image processing system 30. The image processing system 30 measures the respective areas 18, as described here, in order to be able to create and transfer a new control-specific parameter or control data set to the control device 40 if necessary.

[0078] Figs. 6 and 7show a further embodiment of the previously described images of a cable end 12d", comparable to the Fig. 2 to Fig. 5, wherein the cable 10" represents a high-voltage cable as a cable type. The high-voltage cable or cable 10" has an electrical conductor 14", an inner cable insulation 13", and an outer cable insulation 13a", wherein a cable shield 17" and a film 17a" are arranged between the cable insulations 13", 13a". The segmented image shows markings or hatchings assigned to the aforementioned areas or components, which indicate their color and / or structure and / or shape and are recognized and measured by the image processing system 30. The image processing system 30 measures the respective areas 18", as described here, in order to create a new control-specific parameter or control data set and to transfer it to the control device 40. For example, with such high-voltage cables it is essential that the foil 17a" does not protrude from the outer cable insulation 13a", whereby the control-specific parameter orThe control data set for the stripping knife as the first tool ensures this and controls the stripping knife accordingly.

[0079] As shown in the further segmented image in the Fig. 7 shown, the high-voltage cable is according to Fig. 6equipped with a sleeve 19" and the cable shielding 17" folded over this sleeve 19". The folding back of the cable shielding 17" can be accomplished, for example, using a rotating brush as the first tool. The image processing system 30 measures, as described here, the area 18", which defines the overlap area of ​​the folded back cable shielding 17" over the sleeve 19", whereby the subsequently newly created control-specific parameter or control data set for the stripping blade and / or for the rotating brush ensures a sufficient overlap area and controls the stripping blade and / or the rotating brush. Instead of the sleeve 19", an adhesive tape can also be arranged on the outer cable insulation 13a", whereby the image processing system 30 detects whether the entire cable shielding is arranged under the adhesive tape (not shown).

[0080] Fig. 8 to 10show a further embodiment of the previously described images of a cable end 12d‴, comparable to the Fig. 6 and Fig. 7 , where the 10‴ cable represents a high-voltage cable as a cable type.

[0081] Fig. 8 shows the high-voltage cable or cable 10‴ in the unprocessed state in a front view, wherein the cable 10‴ has a first electrical conductor 14‴ and a second electrical conductor 14a‴, each comprising an inner cable insulation 13‴, 13a‴, as well as an outer cable insulation 13c"', wherein an insulating filler 13b‴ is arranged between the inner cable insulations 13"', 13c‴ and the outer cable insulation 13c‴. The insulating filler 13b‴ is sheathed by a cable shield 17‴. Fig. 9 and Fig. 10 show the cable 10‴ in a side view ( Fig. 9 ) and in front view ( Fig. 10 ) after the stripping process step, where in addition to the Fig. 8Among the elements shown, a sleeve 19‴ is shown, which sits on the outer cable insulation 13c‴ and wherein the cable shield 17‴ is folded around a sleeve 19‴. The cable shield 17‴ is fixed to the outer cable insulation 13c‴ with an adhesive strip 17b‴.

[0082] The segmented images in the Fig. 8 to Fig. 10show markings or hatchings assigned to the aforementioned areas or components, which indicate their color and / or structure and / or shape and are recognized and measured by the image processing system 30. The image processing system 30 measures, as described here, the respective areas 18"', 18a"' in order to create a new control-specific parameter or control data set and transfer it to the control device 40. For example, with such high-voltage cables, it is essential that the two electrical conductors are twist-free. The image processing system 30 checks this using a detected image from the imaging sensor device 25, which detects the frontal view of the unprocessed high-voltage cable 10‴ ( Fig. 8) and detects the positions of the two electrical conductors 14‴ and 14a‴. This forms the basis for the subsequent process step of stripping, because the position of the two electrical conductors 14‴ and 14a‴ (rotation, e.g., relative to the horizontal) can be corrected. Furthermore, the image processing system 30 measures the respective areas 18"', 18a‴ around the electrical conductors 14"', 14a''', which serve as the basis for control-specific parameters or control data sets for the subsequent process step of stripping for the stripping knife or the cable conveyor as the first tool in order to control these tools accordingly. Fig. 9 shows the power cable after stripping with electrical conductors 14‴ and 14a‴ spaced apart and Fig. 10shows the front view of the high-voltage cable after stripping with twisted and spaced-apart electrical conductors 14‴ and 14a'". The measured areas 18‴, 18a‴ are correspondingly different in size, so that the image processing system 30 can compare these areas 18‴ with stored data sets in order to define a reject if necessary. Otherwise, the control-specific parameters or control data set are used to control the cable conveyor or a crimping tool as an additional tool in the subsequent process step.

[0083] The front views shown are in particular with the imaging sensor device 25 separated from the cables according to the Fig. 2 to Fig. 7detectable, wherein the resulting cable-specific parameters and / or material-specific areas are used by the image processing system 30 to create control-specific parameters, which, for example, improve the positioning of the sealing elements or sleeves at the cable end. Furthermore, in a further embodiment, the imaging sensor device 25 is configured to detect the position of at least one of the tools described herein, for example, the position of a crimping tool, in order to precisely position the cable in a cable connector housing (not shown).

[0084] Fig. 11 shows a first method for automatically determining and generating control data sets and / or control-specific parameters for controlling at least one cable processing station 20, which is computer-implemented and stored in the control device 40 of the cable processing station 20. In the following, reference is made to the Fig. 1 Reference is made to the method disclosed below. Control data sets and / or control-specific parameters for processing the cables according to the Fig. 1 to Fig. 10 determinable and producible.

[0085] In a first step, an endless cable or a cable 10 already cut to a defined cable length is transported to the cable processing station 20 (step 100).

[0086] Subsequently, job data from the database 50 for processing the cable 10, which includes control data sets and / or control-specific parameters for controlling the first tool 22, are loaded into the control device 40 (step 101). The job data for the cable 10 to be processed also includes corresponding control tolerances as well as cable-specific image parameters and / or material-specific ranges including tolerance values.

[0087] Subsequently, the cable end 12a is processed, whereby in this case the cable insulation 13 is stripped (step 102).

[0088] Subsequently, an image 26 of at least one cable end 12b of the cable 10 is detected with the first imaging sensor device 25 (step 103).

[0089] Subsequently, the detected image 26 is transmitted to the image processing system 30 and a first cable-specific image parameter and at least one second cable-specific image parameter are recognized, and the first cable-specific image parameter and the second cable-specific image parameter are analyzed by the AI ​​module 32 and a semantic segmentation of the detected image 26 is carried out (step 104).

[0090] Subsequently, the detected image 26 of the cable end 12b is divided into at least two material-specific regions, which comprise the cable insulation 13 and the electrical conductor 14, on the basis of the first cable-specific image parameter and the second cable-specific image parameter, and the material-specific regions are geometrically measured by the image measurement algorithm in the computing unit in the image processing system 30 (step 105).

[0091] Subsequently, at least one of the measured cable-specific image parameters is compared with a target value for this cable-specific image parameter, the target value being derived from the order data (step 106). A deviation value is determined.

[0092] After comparing the measured cable-specific image parameter with the corresponding target value, it is determined whether the deviation value is within the control tolerance of the control-specific parameter (step 107).

[0093] If the measured cable-specific image parameter lies outside the respective control tolerance, the cable processing process is aborted and an error message is transmitted to the control device 40 or to the operator of the cable processing station (step 109). For example, the error message includes a request to replace the first tool 22 and is visually displayed on a display of the cable processing station 20. The faulty cable is ejected.

[0094] If the measured cable-specific image parameter lies within the respective control tolerance of the control-specific parameter of the first tool, then an average value is calculated in the image processing system 30 (step 108).

[0095] Based on the calculated mean value, at least one new control data set and / or at least one new control-specific parameter is created, stored in the storage unit 55 and transmitted to the control device 40 for controlling or regulating the tool 22 (step 110).

[0096] In a next step 111, the image processing system 30 compares the measured cable-specific image parameter with the corresponding target value or the tolerance value of the corresponding target value, wherein, in the event of a deviation of the comparison parameters, the cable 10 in the cable processing process is disposed of (step 112) or this cable processing process is terminated (step 113).

[0097] The Fig. 12 and 13show a cable processing machine 120 with several cable processing stations 60, 70, 80. A cable conveyor 90 for transporting the cable 10 to the cable processing stations 60, 70, 80 is arranged on the cable processing machine 120. The processing of the cable 10 takes place as in Fig. 1 shown and described, wherein instead of a cable processing station 20 with several tools 22, several cable processing stations 60, 70, 80, each with a separate tool, are provided. Fig. 10The cable processing machine 120 shown has a cable processing station 60 for stripping the cable insulation 13 from the cable 10, a cable processing station 70 for fitting a sealing element 15 to the cable 10, and a cable processing station 80 for crimping a cable connection element 16 to the cable 10. The cable processing stations 60, 70, 80 each have a tool, namely a stripping knife 61, a fitting device 71, and a crimping tool 81, each of which comprises a drive and is electrically connected to a central control device 140 for exchanging control-specific parameters and / or control data sets.

[0098] As already mentioned in Fig. 1As described above, an image processing system 30 is provided, which is connected to a central control device 140 of the cable processing machine 120 for exchanging control-specific parameters and / or control data sets. The image processing system 30 is configured to create at least one control-specific parameter and / or control data set based on the first cable-specific image parameter and the second cable-specific image parameter and to transmit it to the central control device 140 for controlling the tools of the cable processing stations 60, 70, 80. The first imaging sensor device 25 is designed to detect at least one separate image 62, 72, 82 of the cable end of the cable 10 before each process step in the individual cable processing stations 60, 70, 80.

[0099] Fig. 14shows a further method for automatically determining and generating control data sets and / or control-specific parameters for controlling the cable processing machine 120 with a plurality of cable processing stations 60, 70, 80, which are / are stored in a computer-implemented manner in the central control device 140 of the cable processing machine 120. The method described below at least partially comprises the Fig. 11 The following section will refer to the Fig. 1 , Fig. 12 as well as Fig. 13 Reference is made to the method disclosed below. Control data sets and / or control-specific parameters for processing the cables according to the Fig. 1 to Fig. 10 determinable and producible.

[0100] In a first step, an endless cable or a cable 10 already cut to a defined cable length is transported by the cable conveyor 90 to the cable processing station 60 (step 200).

[0101] Subsequently, job data from the storage unit 55 of the database 50 for processing the cable 10, which includes control data sets and / or control-specific parameters for controlling the stripping knife 61, are loaded into the central control device 140 (step 201). The job data for the cable 10 to be processed also includes corresponding control tolerances as well as cable-specific image parameters and / or material-specific ranges including tolerance values.

[0102] Subsequently, the cable end 12a is processed, whereby in this case the cable insulation 13 is stripped (step 202).

[0103] Subsequently, a first image 62 of the at least one cable end 12b of the cable is detected with the first imaging sensor device 25 (step 203).

[0104] Subsequently, the detected image 62 is transmitted to the image processing system 30 and a first cable-specific image parameter and at least one second cable-specific image parameter are recognized, and the first cable-specific image parameter and the second cable-specific image parameter are analyzed by the AI ​​module 32 and a semantic segmentation of the detected image 62 is carried out (step 204).

[0105] Subsequently, the detected image 62 of the cable end 12b is divided into at least two material-specific regions, which are associated with the cable insulation 13 and the electrical conductor 14, on the basis of the first cable-specific image parameter and the second cable-specific image parameter, and the material-specific regions are geometrically measured by the image measurement algorithm with regard to their surface area and / or region length and / or their edge structure in the computing unit in the image processing system 30 (step 205).

[0106] Subsequently, at least one of the cable-specific image parameters is compared with a target value for this cable-specific image parameter, or at least one material-specific range is compared with a target value for this material-specific range, wherein the respective target value originates from the order data (step 206). A deviation value is determined in this process.

[0107] After comparing the cable-specific image parameter or material-specific range with the corresponding target value, it is determined whether the deviation value is within the control tolerance of the control-specific parameter (step 207).

[0108] If the measured cable-specific image parameter or the material-specific range lies outside the respective control tolerance, the cable processing process is aborted and an error message is transmitted to the central control device 140 or to the operator of the cable processing station (step 209). For example, the error message includes a request to replace the tool and is displayed visually on a display of the cable processing station. The faulty cable is ejected.

[0109] If the measured cable-specific image parameter or the material-specific range lies within the respective control tolerance of the control-specific parameter of the stripping knife 61, then an average value is calculated in the image processing system 30 (step 208).

[0110] In a next step 211, the image processing system 30 compares the material-specific range with the corresponding tolerance value, wherein, if the deviation value deviates, the cable 10 in the cable processing process is disposed of (step 212).

[0111] In a further step, the previously processed cable 10 is transported by the cable conveyor 90 along the direction of movement 23 to the cable processing station 70, and the order data from the storage unit 55 of the database 50 for processing the cable 10, which includes control data sets and / or control-specific parameters for controlling the assembly device 71 for equipping the sealing element 15 and / or the cable conveyor 90, is loaded into the central control device 140. Subsequently, the processing of the cable end 12c takes place, with the sealing element 15 being arranged at the cable end 12c (step 300). The order data for the cable 10 to be processed further includes corresponding control tolerances as well as cable-specific image parameters and / or material-specific ranges including tolerance values.

[0112] Subsequently, a second image 72 of the at least one cable end 12c of the cable is detected with the first imaging sensor device 25 (step 302).

[0113] Subsequently, the second detected image 72 is transmitted to the image processing system 30 and a first cable-specific image parameter, a second cable-specific image parameter and a further / third cable-specific image parameter are recognized, and the first cable-specific image parameter, the second cable-specific image parameter and the third cable-specific image parameter are analyzed by the AI ​​module 32 and a semantic segmentation of the detected image 72 is carried out (step 303).

[0114] Subsequently, the second detected image 72 of the cable end 12c is divided into at least three material-specific regions, which are assigned to the cable insulation 13, the electrical conductor 14 and the sealing element 15, on the basis of the first cable-specific image parameter, the second cable-specific image parameter and the third cable-specific image parameter, and the material-specific regions are geometrically measured by the image measurement algorithm with regard to their surface area and / or region length and / or their edge structure in the computing unit in the image processing system 30 (step 304).

[0115] Subsequently, at least one of the cable-specific image parameters is compared with a target value for this cable-specific image parameter, or at least one material-specific range is compared with a target value for this material-specific range, wherein the respective target value originates from the order data (step 305). A deviation value is determined in this process.

[0116] After comparing the cable-specific image parameter or material-specific range with the corresponding target value, it is determined whether the deviation value is within the control tolerance of the control-specific parameter (step 307).

[0117] If the measured cable-specific image parameter or the material-specific range lies outside the respective control tolerance, the cable processing process is aborted and / or an error message is transmitted to the central control device 140 or to the operator of the cable processing station (step 309). For example, the error message includes a request to clean the tool and is displayed visually on a display of the cable processing station. The faulty cable is ejected.

[0118] If the measured cable-specific image parameter or the material-specific range lies within the respective control tolerance of the control-specific parameter of the placement device 71 and / or the cable conveyor 90, then an average value is calculated in the image processing system 30 (step 308).

[0119] Based on the calculated mean value, at least one new control data set and / or at least one new control-specific parameter is created, stored in the storage unit 55 and transmitted to the central control device 140 for controlling or regulating the assembly device 71 and / or the cable conveyor 90 (step 310).

[0120] In a next step 311, the image processing system 30 compares the material-specific range with the corresponding tolerance value, wherein, if the deviation value deviates, the cable 10 in the cable processing process is disposed of (step 212).

[0121] In a further step, the previously processed cable 10 is transported by the cable conveyor 90 along the direction of movement 23 to the cable processing station 80, and the order data from the storage unit 55 of the database 50 for processing the cable 10, which includes control data sets and / or control-specific parameters for controlling a crimping tool 81 for crimping a cable connection element 16 onto the cable end of the cable 10 and / or the cable conveyor 90, is loaded into the central control device 140. Subsequently, the processing of the cable end 12d takes place, with the cable connection element 16 being arranged on the cable end 12d (step 400).

[0122] Subsequently, a third image 82 of the at least one cable end 12d of the cable 10 is detected with the first imaging sensor device 25 (step 402).

[0123] Subsequently, the third detected image 82 is transmitted to the image processing system 30 and a first cable-specific image parameter, a second cable-specific image parameter, a third cable-specific image parameter and a further cable-specific image parameter are recognized, and the first cable-specific image parameter, the second cable-specific image parameter, the third cable-specific image parameter and the further cable-specific image parameter are analyzed by the AI ​​module 32 and a semantic segmentation of the third detected image 82 is carried out (step 403).

[0124] Subsequently, the third detected image 82 of the cable end 12d is divided into at least four material-specific regions, which are assigned to the cable insulation 13, the electrical conductor 14, the sealing element 15, and the cable connection element 16, on the basis of the first cable-specific image parameter, the second cable-specific image parameter, the third cable-specific image parameter, and the further cable-specific image parameter, and the material-specific regions are geometrically measured by the image measurement algorithm with regard to their surface area and / or region length and / or their edge structure in the computing unit in the image processing system 30 (step 404).

[0125] Subsequently, at least one of the cable-specific image parameters is compared with a target value for this cable-specific image parameter, or at least one material-specific area is compared with a target value for this material-specific area, wherein the respective target value originates from the order data (step 405). A deviation value is determined in this process.

[0126] After comparing the cable-specific image parameter or material-specific range with the corresponding target value, it is determined whether the deviation value is within the control tolerance of the control-specific parameter (step 407).

[0127] If the measured cable-specific image parameter or the material-specific range lies outside the respective control tolerance, the cable processing process is aborted and an error message is transmitted to the central control device 140 or to the operator of the cable processing station (step 409). For example, the error message includes a request to replace the tool or to check the tool for defects and is visually displayed on a display of the cable processing station. The defective cable is ejected.

[0128] If the measured cable-specific image parameter or the material-specific range lies within the respective control tolerance of the control-specific parameter of the crimping tool 81 and / or the cable conveyor 90, then an average value is calculated in the image processing system 30 (step 408).

[0129] Based on the calculated mean value, at least one new control data set and / or at least one new control-specific parameter is created, stored in the storage unit 55 and transmitted to the central control device 140 for controlling or regulating the crimping tool 81 and / or the cable conveyor 90 (step 410).

[0130] Furthermore, the image processing system 30 compares the measured material-specific area with the corresponding tolerance value, whereby if the deviation value deviates, the cable 10 in the cable processing process is disposed of (step 212).

[0131] The finished cable 10 is then placed in a cable tray (step 411). List of reference symbols

[0132] 10Cable 10'Cable 10"Cable (high-voltage cable) 10"Cable (high-voltage cable) 12a-12dCable end of 10 12d'Cable end of 10' 12d"Cable end of 10" 12d‴Cable end of 10‴ 13Cable insulation of 10 (jacket) 13'Cable insulation of 10' (jacket) 13"Inner cable insulation (inner insulation) 13a"Outer cable insulation (outer insulation) 13"Inner cable insulation (inner insulation) 13a‴Inner cable insulation (inner insulation) 13b‴Insulating filler (filler) 13c'"Outer cable insulation (outer insulation) 14Electrical conductors of 10 (strand) 14'Electrical conductors of 10' (strand) 14" electrical conductor of 10" (strand) 14‴ first electrical conductor of 10‴ (strand) 14a‴ second electrical conductor of 10‴ (strand) 15 sealing element of 10 (dielectric) 15' dielectric of 10' (dielectric) 16 cable connection element of 10 (terminal) 16' cable connection element of 10' (crimp region) 16a' crimp region of 10' (crimp region) 17' cable shield of 10' (shield) 17" cable shield of 10" (shield) 17a "foil of 10" (foil)17‴Cable shielding of 10‴ (shield) 17a‴Adhesive strip (tape) 18Areas 18"Area 18‴Areas 18a‴Areas 19"Ferrule 19‴Ferrule 20Cable processing station 22First tool 23Direction of movement of 22 24Drive of 22 25Imaging sensor device 26Image 27Filter elements of 25 30Image processing system 32AI module 33Computing unit 34Neural network 40Control device 50Database 55Storage unit 60Cable processing station 61Stripping knife 62First image 70Cable processing station 71Assembly device 72Second image 80Cable processing station 81Crimp tool 82Third image 90Cable conveyor 120Cable processing machine 140Central control device 100-113 Process work steps 200-411 Process work steps

Claims

1. A cable-processing station (20; 60; 70; 80) for processing a cable end (12a-12d; 12d') of a cable (10; 10'), in particular an electrical or optical cable, including at least a first tool (22; 61; 71; 81; 90) for processing the cable (10; 10'), a control device (40) for controlling the at least one first tool (22; 61; 71; 81; 90) and at least one first imaging sensor device (25) for detecting at least one image (62; 72; 82) of at least one cable end (12a-12d; 12d') of the cable (10; 10'), and an image processing system (30), wherein the image processing system (30) is connected to the control device (40) in order to exchange control-specific parameters for controlling the first tool (22; 61; 71; 81; 90), characterized in that the image processing system (30) is configured to identify, in the at least one detected image (62; 72; 82), a first cable-specific image parameter of the cable end (12a-12d; 12d') of the cable (10; 10') and at least one second cable-specific image parameter of the cable end (12a-12d; 12d') of the cable (10; 10'), and to generate at least one control-specific parameter based on the first cable-specific image parameter and the second cable-specific image parameter and to transmit said generated at least one control-specific parameter to the control device (40) for controlling the first tool (22; 61; 71; 81; 90), wherein the cable-specific image parameter is selected from the group of parameters consisting of material, structure, colour, shape, cable insulation, cable shielding, sealing element, cable connection element and cable type.

2. A cable-processing station according to claim 1, characterized in that a computer-implemented AI (artificial intelligence) module (32) is provided, which is connected to the at least one first imaging sensor device (25) and which is configured to capture the first cable-specific image parameter and the at least one second cable-specific image parameter in the at least one detected image (62; 72; 82).

3. A cable-processing station according to claim 2, characterized in that the AI module (32) includes at least one neural network (34) which is designed to analyse the at least one detected image (62; 72; 82) and preferably to perform a semantic segmentation of the at least one detected image (62; 72; 82) in order to assign at least one cable-specific image parameter to each pixel of the detected image (62; 72; 82), and to transmit the first analysed cable-specific image parameter and the at least one second analysed cable-specific image parameter to the image processing system (30).

4. A cable-processing station according to one of claims 1 to 3, characterized in that the image processing system (30) is configured to perform a segmentation of the at least one detected image (62; 72; 82).

5. A cable-processing station according to one of claims 1 to 4, characterized in that the image processing system (30) is configured to divide the at least one detected image (62; 72; 82) of the cable end (12a-12d; 12d') of the cable (10; 10') based on the first cable-specific image parameter and the second cable-specific image parameter into at least two material-specific regions, preferably based on the first analysed cable-specific image parameter and the second analysed cable-specific image parameter into at least two material-specific regions.

6. A cable-processing station according to claim 5, characterized in that the first material-specific region includes at least the electrical conductor (14; 14') of the cable (10; 10') and the second material-specific region includes at least the cable insulation (13; 13').

7. A cable-processing station according to one of claims 1 to 6, characterized in that a database (50) is provided which is connected to the image processing system (30) and / or to the AI module (32), wherein the database (50) contains at least one storage unit (55) and reference images and / or reference contours for different cable ends (12a-12d; 12d') are stored in the at least one storage unit (55).

8. A cable-processing station according to claim 7, characterized in that at least one target value for at least one cable-specific image parameter and / or for at least one material-specific region at the cable end (12a-12d; 12d') is stored in the at least one storage unit (55).

9. A cable-processing station according to one of claims 1 to 8, characterized in that the image processing system (30) is configured to capture at least the first cable-specific image parameter and / or at least the first analysed cable-specific image parameter in the detected image (62; 72; 82) of the cable end (12a-12d; 12d') of the cable (10; 10') by means of an image measurement method.

10. A cable-processing station according to one of claims 2 to 9, characterized in that the AI module (32) and / or the image processing system (30) is configured to capture at least one further cable-specific image parameter in the at least one detected image (62; 72; 82), wherein the at least one further cable-specific image parameter is to be assigned in particular to a cable connection element (15) for the cable end (12a-12d; 12d') of the cable (10; 10'), and the neural network (34) is preferably formed in the AI module (32).

11. A cable-processing station according to one of claims 1 to 10, characterized in that the control device (40) is designed to stop and / or prevent a process step of the at least one first tool (22; 61; 71; 81; 90) based on the at least one control-specific parameter.

12. A computer-implemented method for automatically determining and generating control data records and / or control-specific parameters for controlling at least one cable-processing station (20; 60; 70; 80), in particular a cable-processing station (20) according to one of claims 1 to 11 which processes at least one cable end of a cable, wherein at least one image (62; 72; 82) of the at least one cable end (12a-12d; 12d') of the cable (10; 10') is detected with a first imaging sensor device (25), and at least one control data record and / or one control-specific parameter is automatically generated and stored, and an image processing system (30) is provided which receives the detected image (62; 72; 82) and identifies a first cable-specific image parameter of the cable end of the cable and at least one second cable-specific image parameter of the cable end of the cable and generates the at least one control data record and / or the at least one control-specific parameter based on the first cable-specific image parameter and the second cable-specific image parameter, wherein the cable-specific image parameter is selected from the group of parameters consisting of material, structure, colour, shape, cable insulation, cable shielding, sealing element, cable connection element and cable type.

13. A computer- implemented method according to claim 12, characterized in that at least one control-specific parameter is transmitted to the control device (40) and preferably at least one control data record is transmitted to a storage unit (55).

14. A computer-implemented method according to claim 12 or 13, characterized in that the first cable-specific image parameter and the at least one second cable-specific image parameter are captured in the at least one detected image (62; 72; 82) by means of a computer-implemented AI (artificial intelligence) module (32), wherein the AI module (32) and / or the image processing system (30) analyses the at least one detected image (62; 72; 82).

15. A computer-implemented method according to one of claims 12 to 14, characterized in that an AI module (32) and / or the image processing system (30) performs a semantic segmentation of the at least one detected image (62; 72; 82) and assigns at least one cable-specific image parameter to each pixel of the detected image.

16. A computer-implemented method according to claim 14 or 15, characterized in that the AI module (32) is trained using the at least one cable-specific image parameter.

17. A computer-implemented method according to one of claims 12 to 16, characterized in that the at least one detected image (62; 72; 82) of the cable end (12a-12d; 12d') of the cable (10; 10') is divided based on the first cable-specific image parameter and the second cable-specific image parameter into at least two material-specific regions, preferably based on the first analysed cable-specific image parameter and the second analysed cable-specific image parameter into at least two material-specific regions.

18. A computer-implemented method according to one of claims 12 to 17, characterized in that the at least one cable-specific image parameter is compared with a target value for this cable-specific image parameter and, based on this comparison, at least one control-specific parameter and / or at least one control data record is generated.

19. A cable-processing machine (120) with at least two cable-processing stations (20; 60; 70; 80), wherein at least one cable-processing station (20) is designed according to one of the preceding claims 1 to 11, with which in particular a computer-implemented method according to one of claims 12 to 18 can be executed, characterized in that the image processing system (30) is connected to a central control device (140) in order to exchange control-specific parameters and / or control data records, and the image processing system (30) is configured to generate at least one control-specific parameter and / or one control data record based on the first cable-specific image parameter and the second cable-specific image parameter and to transmit the generated at least one control-specific parameter and / or one control data record to the central control device (140) for controlling at least one of the tools (22; 61; 71; 81; 90) of at least one of the two cable-processing stations (20; 60; 70; 80), wherein the cable-specific image parameter is selected from the group of parameters consisting of material, structure, colour, shape; cable insulation, cable shielding, sealing element, cable connection element and cable type.