Apparatus, system and method for inspecting three-dimensional objects

Abstract

The invention relates to an apparatus, system and method for inspecting a three-dimensional object. Disclosed is a device for inspecting three-dimensional objects, such as pouch batteries, each object comprising a housing having a top side and a bottom side, the top side of the housing consisting of at least one upper surface section and a plurality of side surface sections, the device comprising: a motion detection unit; a line illumination unit that irradiates a linear region on the top side of the object to be inspected; a region illumination unit that irradiates the top side of the object housing from above in a stationary state of the object; a matrix camera arranged above the object stationary state position to capture image data in a field of view configured to capture light of the line illumination unit reflected by the linear region of the top side line by line in the object motion state and to capture light of the region illumination unit reflected upward from the entire top side in a matrix manner in the object stationary state, a data processing unit is provided that determines from the captured image data that there is a defect and / or a quality score of at least one defect type, which allows the quality of the object to be evaluated.

Description

[0001] Description

[0002] The present invention relates to a device and a corresponding method suitable for inspecting three-dimensional objects, in particular so-called soft pouch battery cells (in the following referred to as pouch cells).

[0003] Pouch cells are a type of battery, in particular for lithium-ion batteries. Pouch cells typically consist of a pouch-like housing or package formed from a plastic-coated metal foil, such as aluminum foil. This type of battery cell is therefore also referred to as a polymer battery. The housing is designed as a flexible, flat and lightweight pouch or cushion that is sealed from the outside. Inside the housing, there is typically a stack of superimposed electrode layers, active layers and separator layers. The terminals are formed as two tabs that protrude from the pouch-like housing adjacent on one side, on adjacent sides or on opposite sides. Pouch cells are known for their high energy density, compact design and flexibility, making them suitable for a variety of applications, including electric vehicles. Pouch cells can be easily sized to meet the specific requirements of different electric vehicle models. Their flat and flexible design also allows for easier integration into different vehicle spaces, enabling more efficient packaging and improved space utilization. A disadvantage of the pouch cell design is that due to their construction, they are typically sensitive to mechanical damage. This can easily lead to the release of gases or electrolytes or can cause the battery cell to swell significantly or cause internal short circuits.

[0004] It is therefore desirable to thoroughly inspect such and other three-dimensional objects during quality control to detect damaged objects at an early stage.

[0005] Various options for quality control of flat objects such as battery cells have been disclosed. For example, from the document US 2022 / 0 390 387 A1 a method is known in which optical coherence tomography (OCT) is used to inspect the gap between the lead foil and the tabs of a pouch cell. This can provide information about the quality of the sealing of the pouch cell, but this has very limited significance for the quality of the pouch cell. The document EP 4 117 081 A1 describes a very complex inspection system which comprises a thickness measuring unit, a unit for measuring electrical properties, a printing unit, a tab cutting unit, a weighing unit, a tab testing unit and a defect selection unit. The thickness measuring unit measures the thickness of the pouch cell and the printing unit is used to print information about the pouch cell on the surface of the pouch cell. The tab inspection unit uses visual inspection to determine the length and shape of the tabs. Defective pouch cells are separated by the defect selection unit into a hopper provided for this purpose. The document DE 10 2019 109 703 A1 shows and describes an arrangement for checking the quality of a battery cell, the transparent outer skin of which encloses an inner space. Within the inner space, i.e. under the outer skin, an (additional) glass pin or lithium metal wafer is arranged, which changes its optical appearance in the presence of a predetermined concentration of hydrogen fluoride. This glass pin or lithium metal wafer is therefore analyzed in detail by optoelectronic measurement in order to determine the hydrogen fluoride concentration and thus the quality of the battery cell. Finally, the document EP 3869 603 A1 describes a method for checking the quality of a laminated electrode-separator composite and a battery having the electrode-separator composite, which is suitable for large-scale production and ensures that the individual layers are firmly and reliably connected to one another. The inspection comprises detecting at least a portion of a surface of the electrode-separator composite by a detection device to generate a measurement result and evaluating the measurement result. The detection device is particularly suitable for determining the surface topography, the surface temperature and / or the surface color. This can be done with the aid of optical sensors, photographic equipment and / or cameras. In this case, the detection device can comprise at least one illumination device which can emit light onto the surface of the electrode-separator composite to be inspected. The evaluation can comprise image processing and / or image analysis.

[0006] Further systems for inspecting objects are known from the documents DE 10 202 205 760 A1, CN 111 965 185 A, DE 10 2020 109 945 A1 and DE 10 2011 113 670 A1.

[0007] The known methods mentioned above are either relatively complex or only allow a very limited assessment of the quality of three-dimensional objects, in particular of pouch batteries. It is therefore an object of the present application to create a simple and cost-effective device for inspecting objects which allows a comprehensive assessment of the quality of the objects. Similarly, it is an object of the present application to provide a corresponding inspection method.

[0008] The above objects are achieved by a device for inspecting three-dimensional objects, in particular battery cells, for example in the form of pouch batteries, having the features described below and by a corresponding inspection method having the features described below.

[0009] In particular, the objects are achieved by a device for inspecting three-dimensional objects, in particular battery cells in the form of pouch batteries, wherein each object comprises a housing which is substantially cushion-shaped or cuboid-shaped and has a top side and a bottom side (the housing can comprise a first protruding connection tab (hereinafter referred to as tab) and at least a second protruding connection tab (hereinafter referred to as tab)), wherein the top side of the housing consists of at least one (for example substantially horizontally arrangeable) upper surface section and a plurality of side surface sections which extend obliquely, parallel or perpendicularly with respect to the at least one upper surface section or form corner sections,

[0010] wherein the bottom side of the housing consists of at least one (for example substantially horizontally arrangeable) bottom surface section and a plurality of side surface sections which extend obliquely, parallel or perpendicularly with respect to the at least one bottom surface section or form corner sections, the device comprising:

[0011] a motion detection unit which captures motion data about the relative motion (motion state) of each object to be inspected with respect to the linear illumination unit and about the arrangement (rest state) with respect to the area illumination unit in a predetermined position and for a predetermined period of time,

[0012] a linear illumination unit for illuminating a linear area of the top side of the object to be inspected,

[0013] an area illumination unit for illuminating the top side of the housing of the object to be inspected from above in the rest state of the object to be inspected,

[0014] optionally at least one first deflection mirror which is arranged next to a side of the housing in the rest state of the object, respectively, and

[0015] a matrix camera which is arranged above the object to be inspected for capturing image data in a field of view, wherein the field of view is configured to:

[0016] for capturing light reflected from a linear area of a line illumination unit into a matrix camera in a line-by-line manner from the top side in a moving state of the object to be inspected, and

[0017] for capturing light reflected upwards from the top side of an area illumination unit in a matrix manner, optionally including light reflected from side surface sections, if applicable, via at least one first deflection mirror to the matrix camera in a stationary state of the object to be inspected, and

[0018] wherein a data processing unit is provided, which is configured to receive and process image data recorded by the matrix camera and detected movement data, wherein the data processing unit assigns the image data captured in a line-by-line manner in the moving state and the image data captured in a matrix manner in the stationary state to the respective object to be inspected and determines the presence of defects of at least one defect type and / or determines a quality score from these image data, which allows an assessment of the quality of the object.

[0019] The device is used for inspecting three-dimensional objects, for example flat objects in the form of pouches or cuboids, in particular for battery cells, for example pouch cells. In one embodiment, the present invention can be used for flat objects, wherein a three-dimensional object is referred to as a flat object if it exhibits a spatial extension in one spatial direction (for example, height) that is significantly smaller than in the other two spatial directions and thus essentially has the shape of a flat cuboid or pouch or a shape similar to these shapes. Alternatively, the dimension in one spatial direction can also be larger, so that the object is described as essentially a cuboid. In this context, "essentially" means that the shape of the object approximates the shape of a pouch or cuboid. For example, a cuboid can have steeply sloping edges. In many cases, such objects also comprise a first connection tab (short: tab, for example anode) and, if applicable, at least a second connection tab (short: tab, for example cathode), each of which protrudes laterally. Each object comprises a housing having a top side and a bottom side opposite the top side, wherein any tabs protruding belong to the housing. The device according to the present invention can be used both for inspecting three-dimensional objects comprising one or more such tabs and for inspecting three-dimensional objects without such tabs. In particular, the device is suitable for flat objects comprising stepped or terraced sections, in particular comprising these sections on their edges, or the aforementioned connection tabs. Thus, the object is observed in such a way that one of the two largest sides forms the top side, while likewise the large opposite side forms the bottom side. When the top side is on top and the bottom side is on the bottom, the top side of the housing has at least one upper surface section which extends essentially horizontally and is the surface section of the top side having the largest dimension. Further horizontally extending surface sections can be provided which extend parallel to the upper surface section of the top side, for example terraced surface sections of the top side. The top side also comprises a plurality of side surface sections which extend obliquely, parallel or perpendicularly with respect to the at least one upper surface section or form corner sections (for example, edges or side surfaces). The side surface sections also comprise sections which extend parallel to the upper surface section or a surface of a protruding tab (tab surface). Thus, the bottom side of the housing comprises at least one essentially horizontally extending bottom surface section which is the surface section having the largest dimension. Further horizontally extending surface sections can be provided which extend parallel to the "lower" surface section of the bottom side, for example terraced surface sections of the bottom side. The bottom side also comprises a plurality of side surface sections which extend obliquely, parallel or perpendicularly with respect to the at least one lower surface section or constitute corner sections (for example, edges or side surfaces). The first tab and the at least one second tab, if present, can for example protrude from a short side and / or a long side and each comprise an upper tab surface and a lower tab surface. For example, the first tab and the second tab protrude from a single short side or long side. In this case, the tabs are arranged adjacent to one another.Alternatively, the first tab and the second tab can protrude from opposite short sides or long sides. When viewed from above on the top side or the bottom side of the housing, the housing can have a substantially rectangular shape (not taking into account any tabs that can be present). The short sides are the short sides of this rectangle, and the long sides represent the long sides of this rectangle.

[0020] The movement of the three-dimensional object to be inspected is performed by means of a drive unit, which moves the object to be inspected at a predetermined speed (movement state) relative to the line illumination unit, for example substantially parallel to the upper surface section, for example in the direction of the maximum dimension (length) of the upper surface section or transversely thereto. The predetermined speed is for example at least 500 mm / s, for example at least 800 mm / s. Furthermore, the drive unit is configured to arrange the object at a predetermined position relative to the area illumination unit and for a predetermined period of time during further movement of the respective object in a stationary state (stationary state). In this case, the predetermined period of time for the arrangement of the object in the stationary state can precede the movement state or can follow the movement state. The predetermined period of time in the stationary state can for example be at least 300 ms, for example at least 400 ms. In one embodiment, the drive unit is realized by a slide which can be moved in a predetermined manner over a linear unit. The slide comprises for example a suction cup by means of which the housing of the object can be attached to the slide at its bottom side. The movement data for moving the three-dimensional object to be inspected, i.e. its arrangement in the movement state and the stationary state, the position of the object and / or its speed, etc., are captured by a movement detection unit and transmitted to the data processing unit. In the data processing unit, the captured movement data are used together with the captured image data from the matrix camera for determining the presence and / or the quality score of defects.

[0021] The line illumination unit illuminates the linear area on the top side of the bag-like housing (optionally including the upper tab surface of the first tab and / or the second tab). For example, the line illumination unit is formed by a lamp having a plurality of LEDs arranged to illuminate the desired linear area. In this case, one LED line can be provided, or for wider linear areas, several LED lines (for example, 2 to 10 LED lines) can be provided which are arranged next to each other. In one embodiment, the line illumination unit can be switched in such a way that it illuminates each point of the linear area with light of two different intensities, i.e. high intensity A and low intensity B. Thus, the line-by-line detection of the light reflected from the linear area of the top side (optionally including the upper tab surface of the first tab and / or the second tab) is performed with an adapted switching rhythm in the form of ABABAB... (i.e. alternating switching of the two different intensities A, B). For this purpose, the line-by-line capture of the image data (capture frequency and capture time) and the feed rate of the drive unit are synchronized. This illumination is also referred to as HDR reflected bright field illumination.

[0022] The area illumination unit illuminates the top side of the housing of the object to be inspected (optionally the upper tab surface including the first tab and / or the second tab) from above. In one embodiment, the entire top side of the housing (optionally the upper tab surface including the first tab and / or the second tab) or at least a larger section of the top side of the housing (optionally the upper tab surface including the first tab and / or the second tab), for example at least 70%, for example at least 80%, of the entire top side of the housing, is illuminated by the area illumination unit. For example, the light from the area illumination unit is incident perpendicularly or obliquely onto the top side of the housing (optionally the upper tab surface including the first tab and / or the second tab), for example with an angle of incidence in the range of 10° to 60° with respect to the horizontal direction. By means of the oblique illumination by the area illumination unit, defects such as dents, protrusions, scratches, folding defects, edge cracks, defects at the seal and similar topological defects can be easily detected. Defects in the form of absorption defects (for example, contamination, foreign bodies on the surface) can also be detected. The area illumination unit is implemented by LED spots or other quasi-spotlights. In one embodiment, at least one second deflection mirror is arranged above the position of the object to be inspected in the rest state, which extends perpendicular to the horizontal direction and deflects the light from the area illumination unit such that it falls obliquely from above onto the top side of the bag-shaped housing (optionally with tabs). This can reduce the overall external dimensions of the inspection device.

[0023] The inspection device is characterized by the fact that the reflected light of the linearly illuminated area of the top side of the housing of the object to be inspected in the state of motion is recorded in the form of image data (image information, for example intensity, in one embodiment additionally also color values) by means of a single matrix camera line by line, and the reflected light of the top side of the housing (including the upper tab surface, if applicable) illuminated from above in the form of image data (image information, for example intensity, and in one embodiment additionally also color values) in the form of image data of the object to be inspected arranged in the state of rest is recorded in matrix fashion, and the two captured image data are transmitted to a data processing unit. For example, the matrix camera is arranged above the object when the object is in its state of rest at a specified location, i.e. in this embodiment the matrix camera is arranged above the state of rest position of the object to be inspected. The line-by-line capture represents a sub-area of the field of view of the matrix camera and produces one pixel line or several adjacently positioned pixel lines (for example pixel lines with 16 to 128 pixels) with image data, while the matrix capture produces a pixel matrix with image data, wherein the pixel matrix also represents a sub-area of the field of view. In one embodiment, the image data can be determined in a predetermined wavelength range. The field of view of the matrix camera is designed in such a way that the matrix image data and the line-by-line image data are captured by a single fixed, i.e. not moved during image data capture, matrix camera, which is subsequently assigned to the respective object by the data processing unit. In this context, the entire top side of the housing (optionally including the upper tab surface of the first tab and / or the second tab) or at least a section of the top side of the housing illuminated by the area illumination unit, i.e. at least a larger section of the top side of the housing (optionally including the upper tab surface of the first tab and / or the second tab), for example at least 70%, for example at least 80%, of the entire top side of the housing of the object to be inspected can be captured during the matrix capture.

[0024] The matrix camera can be designed as a CCD or CMOS camera, for example. The matrix camera captures the light intensity of a large number of pixels in the field of view, which are arranged in rows and columns, i.e. in a matrix. To this end, the matrix camera comprises a light-sensitive element (e.g. a CCD or CMOS sensor) for each pixel. The size of the area captured by each light-sensitive element determines the resolution of the matrix camera. The matrix camera can comprise a field of view of 9344 x 7000 pixels or 8192 x 8192 pixels, for example, and thus captures image data with dimensions of 805 x 603 mm. The line-by-line capture can comprise areas of 16 to 128 x 1000 to 8192 pixels, for example, accordingly. The matrix camera is also arranged in such a way that it looks vertically from above at the object to be inspected in the stationary state, so that it clearly sees this part of the field of view. The matrix camera is focused in such a way that it comprises a sharpness that is as uniform as possible over the entire field of view. In particular, this is achieved for the line of sight in which the image data from the object reaches the matrix camera via the mirror. This is achieved by a corresponding aperture setting, which achieves the necessary depth of field.

[0025] In one embodiment, the matrix camera is configured (e.g. controlled by the data processing unit in such a way) that the line-by-line and matrix-like capture of the image data takes place in a recording sequence (a time sequence of recording sequences of the matrix camera over its entire field of view). This can be synchronized with a corresponding control of the illumination (i.e. the line illumination unit and / or the area illumination unit). In one embodiment, the line-by-line captured image data of a first object to be inspected (in the motion state) can be captured at least partially simultaneously with the matrix-like captured image data of a second object to be inspected (in the stationary state), which is different from the first object. This design of the recording sequence can shorten the total time required for the quality assessment of the object.

[0026] This means that the matrix camera is configured in such a way that at least one of its recording sequences (i.e. in the same capture) contains:

[0027] in the motion state of the first object, the line-by-line capture of the light reflected from the top-side linear area of the line illumination unit, and

[0028] in the stationary state of the second object, the matrix-like capture of the light reflected upwards from the top side (in one embodiment, the entire top side and / or the upper tab surface optionally including the first tab and / or the second tab) of the area illumination unit, optionally including the light reflected from the side surface section of the second object, if applicable, via the at least one first deflection mirror to the matrix camera, wherein the second object is different from the first object.

[0029] The sequence of capturing and illuminating can for example comprise a plurality of line-by-line captures of light reflected from a linear area of the top side (optionally comprising the upper tab surface of the first tab and / or the second tab) (e.g. between 50 and 120 line-by-line captures) and wherein one of some (between 5 and 20) line-by-line captures partially comprising the top side (optionally comprising the top tab surface of the first tab and / or the second tab) in the same capture. Alternatively, the image data of the line-by-line captures and the image data captured in matrix fashion of the two different objects can be sequentially recorded by the matrix camera in a sequence of captures. In this case, in order to save time, only segments of the entire pixel matrix of the matrix camera can be read out, e.g. the corresponding segments of the line-by-line captures and the corresponding segments of the matrix captures.

[0030] When capturing the image data, the matrix camera is stationary (i.e. it does not move, nor do its parts) and the size of the field of view of the matrix camera is such that both the image data to be captured line-by-line and the image data to be captured in matrix fashion are contained in the same field of view. The object to be inspected is in motion during the line-by-line capture, i.e. the object to be inspected continues to move while the image data is created. In contrast, during the matrix capture, the object to be inspected is stationary (i.e. in a stationary state) in a predetermined position and for a predetermined period of time, so that the image data captured in matrix fashion can be determined accurately. Furthermore, at least two first deflection mirrors can be arranged next to the object to be inspected, which first deflection mirrors can also be captured by the field of view of the matrix camera and provide further image data of the side surface segments of the top side of the object to be inspected. In this embodiment, these further image data are captured together with (simultaneously, i.e. in the same recording) the matrix capture of the object to be inspected. The image data of the line-by-line captures and the image data captured in matrix fashion, including the image data transmitted via the first deflection mirrors if applicable, are assigned to the respective inspected object and are included in the determination of the presence of defects of at least one defect type and / or the determination of the quality score. Due to its above-described technical features, the inspection device is able to quickly assess the quality of various objects, in particular of soft pack batteries, with little effort. In particular, only a single matrix camera is sufficient for the quality assessment of the top side of the object.

[0031] From the image data transmitted by the matrix camera to the data processing unit, the presence of defects of at least one defect type and / or the determination of the quality score is determined by appropriate data processing, which allows the quality of the object to be assessed. For example, the defect types include inclusions, dents (dimples), protrusions (bumps), contamination (dust, electrolyte residues), pseudo-edges, orange peel, porosity, cracks, grinding marks, spots, surface defects, blisters, scratches and wet prints. This will be explained in more detail below.

[0032] In the above embodiments, the arrangement and inclination of the at least one first deflection mirror is such that the matrix camera receives light reflected from the largest possible area of the respective side surface section of the top side. In one embodiment of the device, at least two, in particular four, first deflection mirrors are provided, wherein in the resting state of the object, each first deflection mirror is arranged next to the respective side of the housing. With four first deflection mirrors, it is possible to capture reflected light of the side surface sections of all sides of the housing. As an example, each first deflection mirror is designed in such a way that its length (dimension parallel to the respective side next to which the first deflection mirror is arranged) corresponds at least to the length of the respective side of the housing. Furthermore, in one embodiment, each first deflection mirror is arranged at a distance of at least 30 mm from the respective side of the housing in the horizontal direction. In another embodiment, the width (dimension perpendicular to the respective side next to which the respective first deflection mirror is arranged) of each first deflection mirror is at least 20 mm. The angle of inclination of the first deflection mirror is, for example, at least 30° with respect to the horizontal direction. Furthermore, it is advantageous for the accuracy of the inspection if the deflection mirrors achieve very good optical imaging quality to avoid distortions in the images of the matrix camera.

[0033] In one embodiment of the device, the illuminated linear area extends over the entire length of the top side (optionally including the protruding first and second tabs). Here, the length of the top side is the dimension of the housing in its largest dimension. In this embodiment, the illuminated linear area can be used to obtain image data about the entire top side (and optionally the two tabs) when the entire object is moved past the line illumination unit.

[0034] In one embodiment of the device, the area illumination unit is configured to illuminate the top side, for example the entire top side (optionally including the upper tab surface of the first and / or second tabs), of the housing of the object to be inspected obliquely from above in time succession from at least two different directions in the resting state of the object, and the matrix camera is correspondingly configured to capture image data of the light reflected from the top side of the housing in time succession in a matrix manner, which results from the illumination from the at least two directions of the area illumination unit, and the data processing unit is correspondingly configured to receive and process at least two image data captured in a matrix manner during the illumination from the at least two directions of the area illumination unit, to associate these image data with the respective object, and to use these image data to determine the presence and / or the quality fraction of defects of at least one defect type, which allows the quality of the object to be assessed.

[0035] In one embodiment of the device, the data processing unit determines the presence and / or characteristic score of defects of at least one defect type using a maximum image, a topographic image and / or an absorption image of the image data determined from at least two image data captured in a matrix manner during illumination in at least two directions of the area illumination unit. The matrix image, the topographic image and / or the absorption image are each generated from n matrix captures of image data of a predetermined image data portion captured in temporal succession. The maximum image represents the image data of the regions which are best attainable for the respective illumination situation and thus identified as the brightest. The advantage of the topographic image is that it emphasizes topographic changes in the image, while the absorption image highlights defects caused by light absorption, such as contamination on the surface. For example, the image data is generated pixel-identically, i.e. the image data of the at least two matrix captures of the entire top side (optionally including the upper tab surface of the first tab and / or the second tab) are each generated from the same point on the surface. Each of these matrix captures is referred to as an image data matrix M, wherein at least two image data matrices Mk(k > 2, k 2... n) are captured for each object. Thus, a pixel Pi of the first captured image data matrix M1 corresponds to the same position on the surface of the top side (optionally including the upper tab surface) as the same pixel Pi of the second (third, fourth, etc.) captured image data matrix Mk(M2, M3, M4,... Mn). The captured light intensity in the pixel Pi is denoted as i(Pi). The captured light intensity of the first image data matrix M1 at the pixel Pi is referred to as i1(Pi).

[0036] The maximum image can be determined by forming the maximum value of the light intensity of all image data matrices Mk in the respective pixel Pi, i.e. Max(i1(Pi), i2(Pi),... i i ), i2(P i )) for the two determined image data matrices M1, M2 of the two illuminations in two different directions, or Max(i1(Pi), i2(Pi),... i n (Pi)) if n illuminations in n different directions are used. In one embodiment, n = 4. The maximum value for each pixel Pi is calculated and represented in the entire matrix (maximum matrix), resulting in the maximum image.

[0037] The topographic image and the absorption image can be determined by first applying two different parameterized low-pass filters (e.g. box filters) to each image data matrix Mk of each illumination situation independently of one another and subtracting them from one another:

[0038] Fk = low-pass1(Mk) - low-pass2(Mk)

[0039] In this context, the parameters of the two low-pass filters low-pass 1 and low-pass 2 differ, for example, in that a first parameter of the first low-pass filter low-pass 1 is smaller than a second parameter of the second low-pass filter low-pass 2. By this operation the light intensity assigned to each pixel Pi of the matrix Fk is called fk(Pi) (k = 2... n). Subsequently, from the resulting matrices Fk, similar to the maximum image above, the minimum or maximum is determined over all matrices, pixel by pixel, so that a minimum matrix MinM and a maximum matrix MaxM are determined, wherein each point Pi of the minimum matrix MinM is calculated as Min(f1(Pi), f2(Pi),..., fn(Pi)) and each point Pi of the maximum matrix MaxM is calculated as Max(f1(Pi), f2(Pi),..., fn(Pi)). Subsequently, a matrix H with values h(Pi) is determined, which is determined (again pixel by pixel) from the product of the minimum and maximum calculated at the respective point Pi with a scaling factor a (for example a = 64). This means that for each point Pi the value is

[0040] h(Pi) = Min(f1(Pi), f2(Pi),..., fn(Pi)) * Max(f1(Pi), f2(Pi),..., fn(Pi)) * a

[0041] Finally, from this a matrix Q with q(Pi) is determined, wherein

[0042] q(Pi) = sqrt(abs(h(Pi))),

[0043] where abs(q(Pi)) is the absolute value of the value q(Pi) and sqrt() is the root function. This results in a value of the topology matrix T, wherein the value t(Pi) is as follows:

[0044] t(Pi) = q(Pi) if h(Pi) < 0; or t(Pi) = 0 if h(Pi) > 0.

[0045] Thus, the values of the absorption matrix A with values a(Pi) are obtained as follows

[0046] a(Pi) = q(Pi) if h(Pi) > 0; or a(Pi) = 0 if h(Pi) < 0.

[0047] The topology matrix T with values t(Pi) calculated in this way is also referred to as a topology image, and the absorption matrix A with values a(Pi) is also referred to as an absorption image.

[0048] If the matrix-like capturing of the light reflected upwards by the area lighting unit from the top side, optionally from the entire top side and / or optionally including the upper tab surface, is performed four times in the case of oblique illumination from above from four different directions, these directions are selected, for example, such that illumination is performed from two opposite long sides and two opposite short sides of the housing. Alternatively, the illumination can illuminate the top side from the direction of each of the four corners of the housing. In one embodiment, it is advantageous if the capturing is produced with illumination in which all illumination directions together cover an angle of 360°, optionally in terms of their component extending in the plane of the upper surface section (i.e. when illuminated from four different directions, directions offset by 90° from each case provide illumination, or when illuminated from six different directions, directions offset by 60° from each case provide illumination, etc.).

[0049] In one embodiment of the device, the matrix camera is calibrated in such a way that the data processing unit can take into account the perspective and optical distortions from the image data captured in matrix fashion. For such a calibration, for example, the method described in the article "Digital camera self-calibration" by C. S. Fraser (published in 1997 in the journal ISPRS Photogrammetry & Remote Sensing 52, pages 149-159) is used. In one embodiment of the device, the data processing unit is configured to determine at least one dimension of the object and / or at least one size of the detected defect after taking into account the perspective and optical distortions. To this end, for example, a look-up table is predetermined on the basis of the calibration, by means of which a conversion of the number of pixels into length or area units is provided. The look-up table is stored, for example, in a memory unit of the data processing unit.

[0050] In one embodiment, the position correction can additionally be performed using calibration and by means of the data processing unit using fixed points, for example, corner points of the housing. Here, the coordinates of the four corner points of the housing are determined, for example, by means of a software-based "probing" of the housing in horizontal and vertical directions. The probing involves checking the intensity variations of the respective rows and columns of the image data matrix (large increases or decreases in intensity from one pixel to the next). The position correction facilitates the comparison of the captured image data of the matrix with the corresponding target values to determine defects or to determine a quality score, since the object can not always be in exactly the same position in the stationary state. In one embodiment, the position correction can also be used to determine the positioning (position) of each detected defect on the top side, optionally including the upper tab surface. Based on this positioning information, a marking device downstream of the inspection device can, for example, mark the defect by applying (e.g., spraying) a water-soluble pigment around the defect on the object surface. Alternatively or additionally, knowledge of the positioning of the defect can make it easier to control a device for removing the defect.

[0051] The above object is also solved by a system comprising a first device for inspecting a three-dimensional object having the above-mentioned features and a second device for inspecting a three-dimensional object having the above-mentioned features, wherein the second device for inspecting is arranged downstream of the first device for inspecting in the conveying direction, wherein the bottom side of the object, which is located on top after the object has been flipped over after the first device for inspecting a three-dimensional object, is inspected by the second device for inspecting a three-dimensional object. For example, the bottom side of the object is inspected in the same way as the top side of the object. For example, a flipping device can be arranged between the first device for inspecting and the second device for inspecting in the conveying direction, which flips the object in such a way that the bottom side is on top for inspection in the second device. The system enables the detection of defects and / or the determination of a quality score on the top side of the object and on the bottom side of the object, optionally including the bottom tab surface, after the flipping device. For example, the flipping device is realized by means of grippers and / or suction cups.

[0052] The above object is further solved by a method for inspecting three-dimensional objects, in particular pouch batteries, wherein each object comprises a housing which is substantially bag-like or cuboid and has a top side and a bottom side opposite the top side, wherein the top side of the housing consists of at least one upper surface section and a plurality of side surface sections which extend obliquely, parallel or perpendicularly to the at least one upper surface section or form corner sections, wherein the bottom side of the housing consists of at least one lower surface section on the bottom side and a plurality of side surface sections which extend obliquely, parallel or perpendicularly to the at least one lower surface section or form corner sections, wherein the method comprises the following steps:

[0053] detecting, by a motion detection unit, motion data regarding a relative motion (motion state) of each object to be inspected with respect to the line illumination unit and regarding an arrangement (rest state) of the respective object with respect to the area illumination unit within a predetermined position and a predetermined time period,

[0054] illuminating, by the line illumination unit, a linear area of the top side of the object to be inspected, for example, the line illumination unit emits a linear HDR reflective flood illumination,

[0055] illuminating, by the area illumination unit, the top side of the housing of the object to be inspected in the rest state from above,

[0056] capturing, by a matrix camera arranged above the rest state position of the object to be inspected, image data in a field of view, wherein the field of view is configured to:

[0057] for capturing, in the motion state of the object to be inspected, light of the line illumination unit reflected by the linear area of the top side into the matrix camera line by line, and

[0058] for capturing, in the rest state of the object to be inspected, light of the area illumination unit reflected upwards from the top side in a matrix manner, optionally including light reflected from a lateral surface section of the object to be inspected, if applicable, via at least one first deflection mirror, which, in the rest state of the object, is arranged next to one respective side of the housing, into the matrix camera,

[0059] receiving and processing, by a data processing unit, the image data captured by the matrix camera and the detected motion data, wherein the data processing unit assigns the image data captured line by line in the motion state and the image data captured in a matrix manner in the rest state to the respective object to be inspected and determines the presence of defects of at least one defect type and / or determines a quality score from these image data, which allows an assessment of the quality of the object.

[0060] In one embodiment of the method, the illuminated linear area extends over the entire length of the top side and / or at least four first deflection mirrors are provided, wherein each deflection mirror is arranged next to a respective side of the housing in the rest state of the object.

[0061] In one embodiment of the method, in at least one of the capturing / recording of the detection sequence by the matrix camera, i.e. in the same recording / capturing step, the following capturing is carried out by the matrix camera:

[0062] in the motion state of the first object, light of the line illumination unit reflected from the linear area of the top side line by line, and

[0063] In a stationary state of the second object, light reflected upwards from the top side of the area illumination unit, optionally including light reflected from the side surface section of the second object, if applicable, via the at least one first deflection mirror to the matrix camera, is captured in a matrix manner, wherein the second object is different from the first object.

[0064] In one embodiment of the method, by the area illumination unit, in a stationary state of the object to be inspected, the top side of the housing of the object (the entire top side or a large part of the top side (see above)) is obliquely illuminated from above in at least two different directions in time succession, and by the matrix camera, correspondingly in matrix manner in time succession, at least two image data are captured which are caused by the illumination of the area illumination unit in the at least two directions, wherein the image data result from the reflected light of the area illumination unit, and by the data processing unit, the at least two image data captured in matrix manner are received and correspondingly processed, which are assigned to the respective object and are used to determine the presence and / or the quality fraction of defects of at least one defect type, wherein the data processing unit uses, for example, the largest image of the image data to determine the presence and / or the quality fraction of defects of at least one defect type, which is determined from the at least two image data captured in matrix manner upon illumination from the at least two directions of the area illumination unit.

[0065] In one embodiment of the method, the matrix camera is calibrated in such a way that the image data processing of the data processing unit takes into account the perspective and optical distortions contained in the image data captured in matrix manner, wherein, for example, at least one dimension of the object and / or at least one size of the detected defects is determined after taking into account the perspective and optical distortions by the data processing unit.

[0066] The device for inspection can comprise further illumination devices and / or cameras, which illuminate predetermined specific sections of the housing surface or generate image data from these sections, which are used to carry out the inspection of the object.

[0067] The method for inspecting an object can be implemented as a computer-implemented method on the basis of the captured image data, i.e. as a method carried out with a data processing unit (computer). The method can also comprise controlling the line illumination unit and / or the area illumination unit and / or the matrix camera, so that a predetermined recording and / or illumination sequence is implemented. For this purpose, the data processing unit and the line illumination unit and / or the area illumination unit are connected to each other by wire or wirelessly. The matrix camera is also connected to the data processing unit by wire or wirelessly, also for transmitting the image data captured by the matrix camera to the data processing unit.

[0068] The data processing unit for processing image data and determining whether at least one defect type of a defect is present and / or determining which quality score can be assigned to the object comprises a processor which is a functional module interpreting and executing instructions / commands of an algorithm and comprises a command control unit as well as an arithmetic unit and a logic unit. The processor can comprise at least a microprocessor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA - a digital integrated circuit into which logic circuits can be programmed), a discrete logic circuit, or any combination of these components. The data processing unit can further comprise a memory unit, an input module (e.g. a keyboard or touchpad), a power module (e.g. a battery), and a display module (e.g. a display). The data processing unit can be configured as a real hardware resource, e.g. a smartphone, a desktop computer, a server, a notebook, a cluster / warehouse scale computer, an embedded system, etc., or as a virtualized computer resource. Furthermore, the data processing unit can comprise a transmitter / receiver (transceiver) for exchanging data / image data with a display device (display). The data processing unit further comprises an interface for exchanging data with the line illumination unit and / or the area illumination unit and / or the matrix camera and / or the control device for the drive unit.

[0069] As already indicated above, the above explained method can for example be implemented as a computer program comprising instructions which, when executed, cause the processor of the data processing unit to perform the steps of the above described method, wherein the computer program comprises a combination of the above described steps and data definitions which enable the computer hardware to perform a calculation or control function, and / or is a syntactic unit consisting of declarations and statements or instructions which are in compliance with the rules of a specific programming language and which are required by the above described function, task or problem solution.

[0070] It is further disclosed a computer program product comprising instructions which, when executed by the processor of the data processing unit, cause the apparatus to perform the steps of any or all of the above defined methods. It is thus disclosed a computer readable medium storing such a computer program product. The computer program product can be a software routine. BRIEF DESCRIPTION OF DRAWINGS

[0071] Further advantages, features and possible applications of the present application are described below with reference to embodiments and drawings. All features described and / or illustrated form the subject of the present application, even independently of their summary in the claims and references thereto.

[0072] schematically shown:

[0073] Figure 1 is a first perspective view from the side of an embodiment of the apparatus according to the present application,

[0074] Figure 2 is a second perspective view from the side of an embodiment according to Figure 1

[0075] Figure 3 is a side view of an embodiment according to Figure 1 with the edge rays of the illumination device and the edge rays of the field of view of the matrix camera,

[0076] Figure 4 is a front view of an embodiment according to Figure 1 with the edge rays of the illumination device and the center rays of the field of view of the matrix camera,

[0077] Figure 5 is a front view of an embodiment according to Figure 1 with the edge rays of the illumination device and the edge rays of the field of view of the matrix camera,

[0078] Figure 6 is a lower section according to Figure 1 with the field of view of the matrix camera viewed from above,

[0079] Figure 7 is a perspective side view of an embodiment of the system according to the invention,

[0080] Figure 8 is a perspective side view of a first example of a design of an object (soft pack battery),

[0081] Figure 9 is a perspective side view of a second example of a design of an object (soft pack battery), and

[0082] Figure 10 is an embodiment of a method for inspection as a flow chart.

[0083] Figures 1 to 6 The embodiment of the device for inspection shown is for inspecting an object in the form of a soft pack battery.

[0084] In Figure 8 and Figure 9 two examples of a soft pack battery 11, 111 are shown.

[0085] The soft pack battery 11 (see Figure 8 ) comprises a substantially pouch-like housing 12. The housing 12 comprises a first connection tab (short: tab) 14 protruding from one short side and a second connection tab (short: tab) 15 protruding from the opposite second short side. The housing 12 comprises a top side with a substantially horizontally extending upper surface section 13. The first tab 14 has an upper tab surface 17 and the second tab 15 has a corresponding upper tab surface 18. The corresponding lower tab surfaces of the tabs 14, 15 are in the​Figure 8 The shape of the housing 12 is essentially cuboid. The housing 12 comprises side surfaces 21, 22 on the short sides and side surfaces 23, 24 on the long sides. The side surfaces 21, 22, 23, 24 extend essentially perpendicular to the horizontal upper surface section 13. The horizontal upper surface section 13, the upper tab surfaces 17, 18 of the tabs 14, 15 and the side surfaces 21, 22, 23, 24 together form a top side of the housing 12. The bottom side is correspondingly shaped and comprises a horizontal lower surface section, the lower tab surfaces of the tabs 14, 15 and the side surfaces 21, 22, 23, 24. In this embodiment, the side surfaces 21, 22, 23, 24 belong to both the top side and the bottom side, since these side surfaces can also be detected when inspecting the top side and the bottom side, respectively. In Figure 8 In this embodiment, the length of the housing 12 is denoted L and the width is denoted B (see double arrowed dashed lines). Due to the simple design of the pouch cell 11, this pouch cell is used to illustrate the mode of operation of the inspection device 1 (see Figures 1 to 6 ). However, correspondingly, the inspection device 1 can also be used for other types of objects, in particular objects in the form of pouch cells.

[0086] Figure 9 A second embodiment of a pouch cell 111 is shown, which comprises a bag-like housing 112 with a horizontal upper surface section 113. The housing further comprises a first connecting tab 114 and a second connecting tab 115, which are adjacently arranged on a single short side 112 and protrude from this short side. The first tab 114 has an upper tab surface 117 and the second tab 115 has an upper tab surface 118.

[0087] The pouch cell 111 further comprises side edges 121, 122, 123, 124 on the housing 112 around the horizontal upper surface section 113, which extend at an angle to the horizontal upper surface section 113 and are incorporated in curves. Corners 125 are formed at the transition from one side edge to the adjacent side edge 121, 122, 123, 124. Furthermore, the housing 112 comprises platform sections 126, 127, 128, 129, each of which subsequently adjoins a side edge 121, 122, 123, 124 and extends essentially parallel to the horizontal upper surface section 113. The top side of the housing 112 is formed by the horizontal upper surface section 113, the side edges 121, 122, 123, 124, the corners 125 and the platform sections 126, 127, 128, 129.

[0088] Figures 1 to 6 The shown device 1 for inspecting a pouch cell 11 has a support frame 3 on which a base plate 5 is arranged, which has a first through-going opening 7 and a second through-going opening 8 (see Figure 1 ,Figure 2 and Figure 6 ). Figures 1 to 6 Two of the plurality of soft-pack batteries 11, 31 to be inspected are shown, which are guided under the base plate 5 through the inspection device 1 as indicated by arrows 11a and 31a. The soft-pack battery 31 is another soft-pack battery having a structure as shown in Figure 8 .

[0089] Above the base plate 5, a matrix camera 40 is arranged on the frame 3, which observes the soft-pack batteries 11, 31 through the openings 7, 8 from above. Here, the soft-pack batteries 11, 31 are arranged in such a way that the top side of the housing 12 is in each case at the top and the horizontal upper surface section 13 can be observed from above with the matrix camera 40. The upper tab surface 17 of the first tab 14 and the upper tab surface 18 of the second tab 15 are also captured by the matrix camera 40. Here, the field of view 42 of the matrix camera 40 is so large (see in particular Figure 6 ) that it extends over both openings 7, 8 so that not only the soft-pack batteries 11, 31 arranged below the respective openings 7, 8 are covered by the field of view 42 of the matrix camera over their entire length and width (viewed from above), but also the deflection mirrors 65, 67 arranged next to the soft-pack batteries 11 are covered.

[0090] In addition, a line illumination unit 51 is provided on the frame 3, which illuminates the top side of the housing and the upper tab surfaces of the tabs in a linear region 31b. It can be seen from Figure 4 that the light reflected from the top side of the housing (including the upper tab surfaces) reaches the matrix camera 40 via the observation light rays 41 and is captured there. Thus, the matrix camera 40 captures the respective illuminated linear region 31b of the top side of the housing (including the upper tab surfaces) of the soft-pack battery 31 line by line, wherein the soft-pack battery 31 is moved during the capturing transversely to the length of the opening 8 (see arrow 31A in Figure 6 ). Thus, a plurality of recordings is generated by the matrix camera 40. Each recording comprises a respective capturing of the respective illuminated linear region of the top side of the housing (including the upper tab surfaces) of the soft-pack battery 31 moved past. The soft-pack battery is moved in the moving state by a drive unit described in more detail below and is brought into a stationary state for a predetermined period of time and moved out of the inspection device from the stationary state.

[0091] In addition, four area illumination units 52, 53, 55, 56 are provided on the frame. As can be seen from Figure 2 , Figure 3 , Figure 5 and Figure 6As can be seen, and as indicated by the edge rays 52a and 52b or 53a, 53b of the area lighting units 52, 53, the area lighting units 52, 53 obliquely from above illuminate the top side of the housing 12 of the pouch cell 11 over the entire length L, including the upper tab surfaces 17, 18 of the tabs 14, 15, such that in particular the width of the pouch cell 11 is captured, in particular compared to the length of the pouch cell 11. Figure 5 As can be seen, and as indicated by the edge rays 52a and 52b or 53a, 53b of the area lighting units 52, 53, the area lighting units 52, 53 obliquely from above illuminate the top side of the housing 12 of the pouch cell 11 over the entire length L, including the upper tab surfaces 17, 18 of the tabs 14, 15, such that in particular the width of the pouch cell 11 is captured, in particular compared to the length of the pouch cell 11. Figure 3 As can be seen, and as indicated by the edge rays 52a and 52b or 53a, 53b of the area lighting units 52, 53, the area lighting units 52, 53 obliquely from above illuminate the top side of the housing 12 of the pouch cell 11 over the entire length L, including the upper tab surfaces 17, 18 of the tabs 14, 15, such that in particular the width of the pouch cell 11 is captured, in particular compared to the length of the pouch cell 11.

[0092] By the illumination by the area lighting units 52, 53, 55, 56 now occurs in such a way that these area lighting units each one after the other are switched on, such that the pouch cell 11 is obliquely illuminated from above, while the other three area lighting units are each switched off. For example, the illumination is first provided by the area lighting unit 52, then by the area lighting unit 55, then by the area lighting unit 53 and finally by the area lighting unit 56. The matrix camera 40 captures the reflected light in each of the four illumination states, wherein the pouch cell 11 is in a stationary state in all four illumination states, i.e. in the same predetermined position under the opening 7 in the substrate 5. Thus, four recordings of the entire top side of the housing 12, including the upper tab surfaces 17, 18, are generated by the matrix camera 40, which captures these areas four times in the matrix, namely once when the area lighting unit 52, the area lighting unit 55, the area lighting unit 53 and the area lighting unit 56 are switched on, wherein the pouch cell 11 is in the same position in each case.

[0093] In the four-matricial capturing of the entire top side of the housing 12, including the upper tab surfaces 17, 18, the side surfaces 21, 22, 23, 24 are also captured via the deflection mirrors 65, 67, since the light reflected from these side surfaces 21, 22, 23, 24 reaches the matrix camera 40 via the deflection mirrors 65, 67, since the field of view 42 of the matrix camera 40 includes these regions, as Figure 6 is shown.

[0094] The plurality of line-by-line capturing and matrix-by-matrix capturing of the soft- pack batteries 11, 31 by the matrix camera 40 are transmitted to a data processing unit (computer) 70 (see Figure 1 ) after they have been captured. The data processing unit 70 receives the image data from the line-by-line capturing and matrix-by-matrix capturing of the respective soft-pack battery 11, 31.

[0095] In this respect, the motion state and the rest state of the soft-pack batteries 11, 31 are captured by a motion detection unit of the inspection device. For example, by monitoring the movement of a predetermined marking, for example a barcode, on the soft-pack battery 11, 31 or a corresponding signal from the drive unit, motion data are generated which, in particular, contain information about the respective motion state in which the respective soft-pack battery 11, 31 is located. For example, the motion unit can transmit information to the motion detection unit that the soft-pack battery is ready for inspection (start signal). From this point in time, the motion detection unit can continuously capture the motion data of the motion unit and thus of the respective soft-pack battery (for example, the movement speed of the motion unit). Alternatively or additionally, the motion detection unit receives a signal when the line-by-line capturing of the respective soft-pack battery is complete. Subsequently, when the respective soft-pack battery is in a predetermined position in the rest state and remains stationary there, a signal is generated by the motion unit or by means of a marking of the soft-pack battery and transmitted to the motion detection unit. As soon as the matrix capturing of the respective soft-pack battery has been completed, the motion detection unit then generates a further signal indicating that the respective soft-pack battery can be transported out of the inspection device. These signals also represent important motion data required for processing the image data.

[0096] The image data and motion data are further processed and analyzed by the data processing unit 70 and the object is evaluated considering the presence of defects of at least one defect type and / or determining a quality score as will be shown in more detail below, which allows evaluating the quality of the pouch cells 11, 31. In this context, the image data determined from different points in time of the line-by-line capturing and the matrix-by-matrix capturing are assigned to the respective pouch cell 11, 31 or to the motion state and the rest state. This can be done, for example, using the motion data transmitted by the motion detection unit for the motion state and the rest state of the respective pouch cell 11, 31. In this process, the recorded image data is generated with regard to image cropping, mirror distortion, line-by-line capturing (so-called line scan correction) and with regard to position correction associated with the respective motion state or rest state.

[0097] The image data of the line-by-line capturing of the respective pouch cell 11, 31 can be used, for example, to search for defects using bright field illumination (reflected bright field (RBF) illumination) or to determine a quality score, which in particular relates to evaluating the tab surfaces and possible contamination of the electrolyte.

[0098] For example, as explained in more detail below, the data processing unit 70 generates a quality rating (quality score) from the number, defect type and size / dimension of the detected defects.

[0099] Further cameras 45, 46 are also arranged on the frame 3, which are attached to the frame 3 below the matrix camera. These cameras observe the top side of the pouch cell 11 from above in such a way (see edge light rays 45a, 45b, 46a, 46b) that they observe the top tab surface 17 of the first tab 14 and the top tab surface 18 of the second tab 15 as well as adjacent portions of the upper surface section of the top side 13. The further cameras 45, 46 generate images with a higher resolution in the indicated portions of the pouch cell 11. The image data obtained from the corresponding field of view is transmitted to the data processing unit 70 and further information about the presence of smaller defects is generated therefrom.

[0100] Figure 7A system for inspecting pouch cells according to the present application is shown. A top side of a pouch cell, for example pouch cell 11, is first inspected by an inspection device 1. Subsequently, the pouch cell, for example pouch cell 11, reaches a flipping unit 180 with a flipping device and a gripper with suction cups, which flips the pouch cell, for example pouch cell 11, so that the bottom side is now on top. Subsequently, the pouch cell, for example pouch cell 11, i.e. the bottom side of the cell, which here is on top, is inspected by an inspection device 101 which is identical in construction to the inspection device 1. The processing of the image data obtained by the inspection devices 1, 101 about the pouch cell, for example pouch cell 11, and the determination from the image data about the presence of defects / at least one defect type of several defects and / or the determination of a quality score which allows an assessment of the quality of the object is performed by a data processing unit 170 which is connected with a display 172 for displaying the inspection results. The pouch cell, for example pouch cell 11, is transported from the first inspection device 1 to the flipping device 180 and the second inspection device 101 by a drive unit which comprises for example a slide which can be displaced on a linear unit. The respective pouch cell is attached to the slide by suction cups. After the capturing of the image data by the matrix camera 40 and optionally by the further cameras 45, 46, in particular after the matrix-like capturing of the respective pouch cell is completed, a corresponding signal is generated by the inspection device, which signal is transmitted to a control device of the drive unit. The drive unit is then controlled in such a way that it moves the respective pouch cell out of the respective inspection device 1, 101 and, if necessary, moves the pouch cell to the flipping device 180 in order to be flipped subsequently and then transported to the second inspection device 101.

[0101] The analysis of the captured image data to determine the presence of defects and / or to determine a quality score can for example be performed as follows. The process is illustrated using the flowchart shown in Fig. Figure 10

[0102] The starting point for the analysis of the captured image data is the four matrix-like captured image data 200 of the top side of the object generated by illumination from different illumination directions and the line-by-line captured image data 201 of the top side of the object using the pouch cell 111 as an example.

[0103] ​As described above, first in step 202 the perspective and / or optical distortion of the matrix camera is compensated for each of the four image data captured in a matrix fashion. Subsequently, if necessary, in step 204 (position correction) the current position of the object during the optical capturing by the matrix camera is corrected, i.e. the object is rotated and / or shifted such that the image data occupies a predetermined position of the object in the field of view of the matrix camera. At the same time, in step 203 the plurality of individually line-by-line captured image data 201 is merged into a single image (data) by the data processing unit 70 and, if necessary, as described above, the inconsistencies / overlaps are corrected during the merging of the images of the top side of the object from the line-by-line captured image data. The merging comprises the juxtaposition of the line-by-line captured image data of the object such that a matrix (second overall matrix) of image data is created. In other words, the second overall matrix contains the individually line-by-line determined image data for the entire top side of the object or for predetermined sections of the top side which correspond to the positions on the top side of the object where the incident light of the line lighting unit is reflected and thus the second overall matrix also contains the image of the top side of the object. Subsequently, as described above, this data is also corrected in step 204, for example with respect to its position and / or the size of the matrix. The merged and corrected line-by-line captured image data form the second overall matrix.

[0104] For the four matrix captured, compensated and corrected image data, subsequently in step 206 the maximum image, the absorption image and / or the topological image of the top side of the object is determined. The calculation from the four matrices of image data is described in detail above. The maximum image is also referred to as the first overall matrix.

[0105] Now, in step 210 the segmentation is performed. For the segmentation, for example, a layout recipe can be used to extract the desired image data portions from the respective (corrected) matrix of image data of the top side determined by the matrix capture or the line-by-line capture.

[0106] In principle, when using a layout recipe for the segmentation, the layout recipe predefines a given portion of the object with respect to the field of view of the matrix camera. Since the object is not always exactly in the specified ideal position when the image is captured by the matrix camera, but can be shifted / rotated by a few pixels, for example, a position correction is performed using a specified fixed point of the object, i.e. a registration to the intended position, so that the first overall matrix (or correspondingly n first overall matrices determined from the line-by-line view or the second overall matrix) is adapted accordingly to the ideal position of the object. The above-described matrix with the image data is rotated and / or shifted accordingly. Once this adaptation has been performed, the desired image data portions can be reliably identified using the specified layout recipe and extracted accordingly.

[0107] For example, a first image data portion in the form of an upper surface section 113 (directly recorded image data from the camera / matrix camera) is extracted, a second image data portion in the form of two corner sections 125 is extracted from the recording area via a mirror on the short side, and a further second image data portion in the form of four platform sections 126, 127, 128, 129 (directly recorded image data from the camera / matrix camera) is extracted. Segmentation is performed for the corrected and merged line-by-line captured image data (i.e. from the second overall matrix) and for the matrix-by-matrix captured, compensated and corrected image data and the maximum image (first overall matrix) and / or the absorption image and / or the topological image. Subsequently, the image data portions obtained by segmentation are processed in parallel and finally fed to the overall evaluation of the object.

[0108] In step 230, the result of the segmentation is, for example, the maximum image, the absorption image, the topological image and the image data portion of the upper surface in the second overall matrix, respectively. In step 232, the data processing unit 70 checks each of these image data portions for each pixel to determine whether they exceed a predetermined threshold value. Such a threshold value can be 240 for the image data portion of the maximum image, 220 for the image data portion of the topological image, 203 for the image data portion of the absorption image and 120 for the image data portion of the second overall matrix. If the image data value of the respective pixel is equal to or higher than the respective threshold value, a defect is detected. Subsequently, in step 234, further characteristics of the detected defect are determined, for example its pixel size (by analyzing whether a defect is also detected in neighboring pixels), a histogram of the image data values in the area of the respective defect and / or the shape and orientation of the defect. The characteristics of the found defect and any other defects found in the image data portions are then used in step 236 to determine the defect type, wherein different images / matrices related to the same location of the image data portion can be considered for this purpose. For example, based on the absence of a defect at the location in the absorption image, based on a determined aspect ratio in the absorption image being greater than 5 and based on an average value of the image data histogram along the defect in the topological image being greater than 200, the defect type "scratch" can be inferred together. In step 238, the severity of the detected scratch defect is then determined, wherein the determination can be based on, for example, an assignment of a severity level to the size of the scratch. In this context, a scratch defect can be assigned a severity level of zero if the defect is smaller than 2 pixels, a severity level of 1 if the defect is greater than or equal to 2 pixels and smaller than 4 pixels, a severity level of 2 if the defect is greater than or equal to 4 pixels and smaller than 6 pixels, and so on.

[0109] The segmentation result in step 240 is, for example, image data portions in the form of four "corner segments" (e.g. 128x128 pixels) from the largest image determined in step 206, wherein the "corner segments" are obtained, for example, from the image data generated via the mirrors 67 on the short sides of the soft pack. As explained below, a CNN algorithm with a binary classifier is now applied to each of these image data portions in step 242. Thus, for each corner image data portion, the attribute "defective corner" (step 244) or "complete corner" (step 246) is determined and assigned to the respective corner in step 248.

[0110] The corner image data matrix of each corner segment can be analyzed using, for example, a convolutional neural network (CNN) algorithm, which includes a binary classifier (a classifier with two states, i.e., “complete corner” and “defective corner”). The corner image data matrix is defined to be relatively small (e.g., 128 x 128 pixels), and the image data forming the corner image data matrix is taken only from the area of the respective corner of the case. This CNN model is specifically developed for this low class classification task and low pixel matrix. The CNN model includes a compact structure, for example, more compact than regular deep architectures. For example, it consists of three strands with different convolution sizes, which are then merged. This structure reduces the number of parameters to be trained, making the model learn fewer features. As such, it is ideal for binary classification or other low-dimensional classification. For the training and evaluation of the CNN model, a large and extensive dataset containing corner structures and corresponding expected defects is used. This dataset is compiled with respect to the respective object to be analyzed and annotated by engineers. The dataset contains corner images of the respective object (i.e., the soft-pack battery to be inspected), which are classified into two categories: “defective” and “complete”. These images are carefully selected and annotated to ensure that they cover a variety of defects and variations of the battery corners. The training of the model is performed on the dataset, where the images in the dataset can be divided into a training set and a validation set. For example, an 80% rate can be used for the training data, and a 20% rate can be used for the validation data. In addition, five-fold cross-validation can be performed to ensure that all images are present in the training data and the validation data. The model consists of several convolutional layers, pooling layers, and fully connected layers, which enable the model to extract important features in the images and identify subtle differences between defective and complete corners. The convolutional layers are used to train the trainable weights of the convolution operation, which are then used to identify image features. These features are then aggregated with the pooling layers. Subsequently, the weights of the fully connected layers are iteratively trained to determine the probability of the associated class from the features. In addition, all images / segments can be cut to the same size as the corner image data matrix (128 x 128 pixels) to be analyzed before being analyzed with the CNN algorithm, and the images / segments are oriented in such a way that they have the same orientation to achieve a consistent view.

[0111] The segmentation result in step 250 is, for example, an image data portion in the form of the platform portion (platforms 126, 127, 128, 129) of the maximum image determined in step 206, wherein the image data has been generated by direct capturing from above by means of the matrix camera 40. Now, the mask RCNN algorithm is applied to these platform image data portions (described in more detail below, step 252). Thus, defects in the platform image data portions of different defect types are identified and provided with a bounding box (step 254). Subsequently, the severity of the respective defect is also determined with respect to the defects detected in the platform image data portion, for example based on the detected defect type, the size of the bounding box, the shape of the bounding box, etc. (step 256).

[0112] In this process, each of the predetermined portions of the side surface section extracted by segmentation, for example the platform section of the pouch cell, is analyzed using an object detection network based on a mask RCNN model. This algorithm identifies defects of various different defect types (for example, 6 different defect types, such as protrusions / noses / protrusions, dents, folds, scratches, contamination, particles) and adds corresponding bounding boxes to the data of the corresponding second image data portion in the defect area. In order to train the mask-RCNN model as an algorithm, data representing the corresponding second image data portion is used, wherein the corresponding defects are annotated in these image data matrices and provided with bounding boxes. The architecture of the mask RCNN model is carefully selected. This model is a further development of the faster R-CNN model and is capable of generating bounding boxes and masks for defects in a specified area. Defect types that occur rarely are artificially inserted into the corresponding image data portions of the given area to train the model. The performance of each model is evaluated using a separate validation data set. For example, a validation data set with a ratio of 80% for training data and 20% for validation data can be used. This ensures that the model effectively and accurately identifies defects and correctly classifies these defects.

[0113] For example, in step 260, the result of the segmentation is an image data portion in the form of the upper surface section 113, for example a maximum image and a merged image from the line-by-line capturing, each image data portion covering the upper surface section 113. These image data portions are divided into patches in step 262 and, as described below, are subsequently analyzed in step 264 using a pre-trained CNN algorithm "Wide ResNet-50". As a result of this analysis, one or more anomalies can be detected in some of the patches. In step 266, the relative normal distribution Mahalanobis distance is determined for each patch in which an anomaly is detected, and each detected anomaly is determined. Thereby, the severity of the anomaly and the severity of the respective defect are determined in step 268.

[0114] When analyzing the segmentation result in step 260, in one embodiment, the resolution in the predetermined (sub)region can be reduced to a predetermined value (e.g. from 5120 x 2216 to 841 x 265 pixels) to speed up the process. The image is divided into several small patches (subregions) (step 262). Subsequently, each patch is examined using a pre-trained CNN algorithm “Wide ResNet-50” as the first NN algorithm to determine whether one or more predetermined features (defects / abnormalities) are present in the respective patch. In “Wide ResNet-50”, the layers of the network are made “wider” by increasing the number of channels in the convolutional layers. This kind of CNN is able to recognize complex patterns and textures. It is also observed that this wider CNNs are generally able to generalize better, which means that they can process new, unknown data more effectively. This method is also known as PaDiM (Patch Distribution Modeling Framework for Anomaly Detection and Localization) and is an algorithm for anomaly detection and localization tasks. This method is particularly suitable for the detection of industrial defects, whose aim is to identify irregularities or deviations from a relative standard in visual data. PaDiM models the distribution of features in the image. Subsequently, features extracted by the CNN are collected for each patch. For each patch, the Mahalanobis distance between the features of the patch and a normal distribution derived from the training data is calculated. This step determines how “abnormal” or unusual each patch is compared to the normal training data. The calculated Mahalanobis distance is used as an anomaly score, where higher values indicate a greater deviation from the normality. A threshold is set based on the anomaly score. Patches whose score exceeds this threshold are considered abnormal. The anomaly is localized by marking the location of the patch classified as abnormal in the image data portion, which enables the localization of the anomaly in the respective image data portion.

[0115] The anomaly score is calculated individually for each patch by computing the Mahalanobis distance of its features with respect to an expected normal distribution, represented by the mean and the covariance matrix from the training data. A large Mahalanobis distance indicates that the features of the patch strongly deviate from the normal distribution, indicating a potential anomaly. Mathematically, the Mahalanobis distance D of a point x to a distribution with mean μ and covariance matrix ∑ is computed as follows:

[0116]

[0117] D(x) refers to the Mahalanobis distance of the point.

[0118] x refers to the vector of observed values.

[0119] μ is the mean vector based on the amount of training data.

[0120] ∑ refers to the covariance matrix of the training data.

[0121] ∑ -1 is the inverse of the covariance matrix.

[0122] T denotes the transposition of a vector.

[0123] For each block, the anomaly score gives rise to an assessment of the severity of the defects present in the respective block.

[0124] In all the above cases, the severity of the defects is expressed in predetermined classes.

[0125] Subsequently, in step 270, the data processing unit 70 assesses the overall quality of the soft pack battery 111 based on all the defects determined in the four analysis chains, the respective defect types and the respective defect severities. It is assessed whether the soft pack battery 111 as a whole meets the specified quality requirements. In step 280, the result of the overall assessment is provided at the interface of the data processing unit, optionally together with a list of the determined defects and their properties. For example, a soft pack battery having two defects of the type “dents” with a severity rating of 5 is judged to be sufficient to meet the quality requirements. In contrast, for example, a soft pack battery having a defect of the type “dents” with a severity rating of 7 can be classified as not meeting the quality requirements.

[0126] The above-described method can likewise be performed for the bottom side of the soft pack battery.

[0127] As described above, the method according to the application can be used to perform an inspection of a three-dimensional object, for example a soft pack battery, in a simple and fast manner, in which various properties of the segments of the object can be taken into account during the analysis.

Claims

1. A device (1, 101) for inspecting three-dimensional objects, such as soft pack batteries (11, 31, 111), wherein each object comprises a housing which is substantially bag- or cuboid-shaped and has a top side and a bottom side, wherein the top side of the housing (12, 112) consists of at least one upper surface section (13, 113) and a plurality of side surface sections (17, 18, 21, 22, 23, 24, 117, 118, 121, 122, 123, 124, 125, 126, 127, 128, 129) which extend obliquely, parallel or perpendicularly relative to the at least one upper surface section (13, 113) or form corner sections (125), wherein the bottom side of the housing consists of at least one bottom surface section and a plurality of side surface sections which extend obliquely, parallel or perpendicularly relative to the at least one bottom surface section or form corner sections, the device comprising: a motion detection unit which captures motion data about each object to be inspected, about the relative motion (motion state) relative to a line illumination unit and about the arrangement (rest state) relative to a region illumination unit in a predetermined position and for a predetermined period of time, the line illumination unit (51) for illuminating a linear region of the top side of the object to be inspected, the region illumination unit (52, 53, 55, 56) for illuminating the top side of the housing of the object to be inspected from above in the rest state of the object to be inspected, if necessary, at least one first deflection mirror (65, 67) which is arranged next to one side of the housing in the rest state of the object, and a matrix camera (40) which is arranged above the object to be inspected for capturing image data in a field of view, wherein the field of view is configured to: capture the light reflected from the linear region of the top side of the line illumination unit into the matrix camera in the motion state of the object to be inspected line by line, and capture the light reflected upwards from the top side of the region illumination unit in the rest state of the object to be inspected in a matrix manner, optionally including the light reflected from the side surface sections, if applicable, via the at least one first deflection mirror into the matrix camera, and wherein a data processing unit (70, 170) is provided which is configured to receive and process the image data recorded by the matrix camera and the detected motion data, wherein the data processing unit assigns the image data captured line by line in the motion state and the image data captured in a matrix manner in the rest state to the respective object to be inspected and determines the presence of defects of at least one defect type and / or determines a quality score from these image data, which allows the quality of the object to be assessed.

2. The apparatus of claim 1, wherein, The illuminated linear region extends over the entire length of the top side.

3. The device of any of the preceding claims, characterized in that, The matrix camera is configured to capture the following in at least one of the captures of the detection sequence by the matrix camera: line illumination unit in a line-by-line manner in a moving state of the first object, and matrix manner in a stationary state of a second object, optionally light reflected from the side surface section of the second object, if applicable, via the at least one first deflection mirror into the matrix camera, wherein the second object is different from the first object.

4. The device of any of the preceding claims, characterized in that, at least four first deflection mirrors are provided, wherein each first deflection mirror is arranged next to a side of the housing in a stationary state of the object, respectively.

5. The device of any of the preceding claims, characterized in that, The area illumination unit is configured to illuminate the top side of the housing of the object from an inclined top side in at least two different directions in time succession in a stationary state of the object to be inspected, and characterized in that the matrix camera is configured for capturing at least two image data in a matrix manner in time succession for the illumination of the area illumination unit in at least two directions, and characterized in that the data processing unit is correspondingly configured to receive and process the at least two image data captured in a matrix manner, to associate these image data with the respective object, and to determine the presence and / or the quality score of defects of at least one defect type using these image data, which allows an assessment of the quality of the object.

6. The apparatus of claim 5, wherein, The data processing unit determines the presence and / or the quality score of defects of at least one defect type using a maximum image of the image data, which is determined from the at least two image data captured in a matrix manner when illuminated from the at least two directions of the area illumination unit.

7. The device of any of the preceding claims, characterized in that, The line illumination unit emits a line-shaped HDR reflective flood illumination.

8. The device of any of the preceding claims, characterized in that, The matrix camera is calibrated in such a way that the image data processing by the data processing unit takes into account the perspective distortion and the optical distortion contained in the image data captured in a matrix manner.

9. The apparatus of claim 8, wherein, The data processing unit is configured to determine at least one dimension of the object and / or at least one size of the detected defects after taking into account the perspective distortion and the optical distortion.

10. A system comprising a first device and a second device, the first device being a first device for inspecting a three-dimensional object according to any one of the preceding claims, the second device being a second device for inspecting a three-dimensional object according to any one of the preceding claims, wherein, The second device for inspecting three-dimensional objects is arranged downstream of the first device for inspecting three-dimensional objects in the direction of transport of the object to be inspected, wherein the bottom side of the object after the first device for inspecting three-dimensional objects is located at the top after the object has been turned over, the inspection being carried out by the second device for inspecting three-dimensional objects.

11. A method for inspecting three-dimensional objects, in particular soft pack batteries, wherein each object comprises a housing which is substantially bag-like or cuboid and has a top side and a bottom side, wherein the top side of the housing consists of at least one upper surface section and a plurality of side surface sections which extend obliquely, parallel or perpendicularly with respect to the at least one upper surface section or form corner sections, wherein the bottom side of the housing consists of at least one lower surface section which is located on the bottom side and a plurality of side surface sections which extend obliquely, parallel or perpendicularly with respect to the at least one lower surface section or form corner sections, wherein the method comprises the following steps: detecting, by means of a motion detection unit, motion data regarding the relative motion (motion state) of each object to be inspected with respect to a line illumination unit and regarding the arrangement (rest state) of the respective object with respect to an area illumination unit in a predetermined position and for a predetermined period of time, illuminating, by means of the line illumination unit, a linear region of the top side of the object to be inspected, the line illumination unit emitting, for example, a linear HDR reflective flood illumination, illuminating, by means of the area illumination unit, the top side of the housing of the object to be inspected from above in the rest state of the object to be inspected, capturing, by means of a matrix camera arranged above the position of the rest state of the object to be inspected, image data in a field of view which is configured to: capture the light reflected by the linear region of the top side into the matrix camera of the line illumination unit line by line in the motion state of the object to be inspected, and capture the light reflected upwards from the top side of the area illumination unit, optionally including the light reflected from the side surface sections of the object to be inspected, if applicable, via at least one first deflection mirror into the matrix camera in a matrix manner in the rest state of the object to be inspected, receiving and processing, by means of a data processing unit, the image data captured by the matrix camera and the detected motion data, wherein the data processing unit assigns the image data captured line by line in the motion state and the image data captured in a matrix manner in the rest state to the respective object to be inspected and determines the presence of defects of at least one defect type and / or determines a quality score from these image data, which allows the quality of the object to be assessed.

12. The method of claim 11, wherein, The illuminated linear region extends over the entire length of the top side and / or at least four first deflection mirrors are provided, wherein each deflection mirror is arranged next to the respective side of the housing in the rest state of the object.

13. The method of any one of claims 11-12, wherein, In at least one of the captures of the detection sequence by the matrix camera, the following is captured by the matrix camera: in the motion state of the first object, the light reflected from the linear region of the top side of the line illumination unit line by line, and in the rest state of the second object, the light reflected upwards from the top side of the area illumination unit in a matrix manner. in a stationary state of a second object, which is different from the first object, the light of the area illumination unit, which is reflected from the top side upwards, optionally the light, which is reflected from a lateral surface section of the second object, if applicable, via the at least one first deflection mirror into the matrix camera, is captured in a matrix manner.

14. The method according to any one of claims 11 to 13, characterized in that, in a stationary state of the object to be inspected, the area illumination unit illuminates the top side of the housing of the object obliquely from above in time succession from at least two different directions, and it is characterized in that the matrix camera correspondingly captures at least two image data in a matrix manner in time succession from the illumination of the area illumination unit in the at least two directions, and it is characterized in that the at least two image data captured in a matrix manner are received and correspondingly processed by the data processing unit, which are assigned to the respective object and are used for determining the presence and / or the quality score of defects of at least one defect type, wherein the data processing unit determines the presence and / or the quality score of defects of at least one defect type, for example, using the largest image of the image data, which is determined from the at least two image data captured in a matrix manner upon illumination in the at least two directions of the area illumination unit.

15. The method according to any one of claims 11 to 14, characterized in that, the matrix camera is calibrated in such a way that the image data processing of the data processing unit takes into account the perspective distortion and the optical distortion contained in the image data captured in a matrix manner, wherein, for example, at least one dimension of the object and / or at least one size of the detected defects is determined after taking into account the perspective distortion and the optical distortion by the data processing unit. the matrix camera is calibrated in such a way that the image data processing of the data processing unit takes into account the perspective distortion and the optical distortion contained in the image data captured in a matrix manner, wherein, for example, at least one dimension of the object and / or at least one size of the detected defects is determined after taking into account the perspective distortion and the optical distortion by the data processing unit.

Images