Intelligent defect grouping and visualization system

Abstract

An example method of a method for determining quality of a web roll includes monitoring data indicative of defects on either side of the web roll, the data including data indicative of: surface defects of the web roll; registration defects of the web roll; and quality and control system (QCS) defects of the web roll. The example method also includes grouping the defects into a set of defects; calculating a weighted centroid of the set of defects; and displaying a representation of the set of defects at the weighted centroid.

Description

Technical Field

[0001] This disclosure relates generally to sheet manufacturing control systems, and more specifically to sheet manufacturing control systems in which measuring devices scan across moving or traveling sheets. In particular, this disclosure relates to quality control of continuous sheet materials, and more specifically to using intelligent grouping algorithms and visualization techniques to monitor sheet materials, such as electrodes used in lithium-ion batteries, and to display defect information in an integrated and easily visualized manner. Background Technology

[0002] Online measurement is used to detect the properties of sheet materials during manufacturing, enabling rapid control of the sheet preparation process and thus ensuring sheet quality while reducing the amount of defective sheet material produced. For example, in the manufacture of electrodes for lithium-ion batteries, a mixture of active materials is used to continuously coat metal foil from metal rollers. A cutting machine then cuts the finished coated metal foil into electrode sheets, which are then assembled into cells and batteries.

[0003] To achieve and maintain the quality of continuous, roll-to-roll electrode production, constant online measurement of quality factors that are strongly correlated with battery performance is crucial. Failure to detect and correct or remove upstream defects can lead to battery failure. Multiple discrete defect monitoring systems are typically employed in lithium-ion battery production, including vision systems (cameras) and quality control system (QCS) scanning systems.

[0004] One of the main complicating factors in performing online measurements during sheet fabrication is that the physical properties of the sheet material typically vary along both the longitudinal (MD) and transverse (CD) directions. The "longitudinal" direction refers to the direction in which the sheet material travels during manufacturing, while the "transverse" direction refers to the direction perpendicular to the MD that runs across the sheet surface.

[0005] To detect changes in the sheet material, a scanning sensor is used. This sensor moves back and forth periodically across the sheet preparation machine on a CD, detecting values ​​for selected sheet properties (such as basis weight or card thickness) during each scan. Typically, during each scan, the produced sheet is moved from edge to edge.

[0006] During implementation, measurement information provided by the scanning sensors is typically aggregated after each scan to generate a profile of the detected sheet properties on the CD. Each profile includes a series of sheet measurements at adjacent locations in the lateral direction. These profiles allow the operator to easily identify lateral variations in the sheet properties. Based on these detected variations, appropriate control adjustments can be made to the sheet preparation machine with the goal of reducing profile variations on both the CD and MD.

[0007] A scanning sensor that periodically traverses a sheet at a roughly constant speed cannot measure the properties of the selected sheet at a position precisely aligned perpendicular to the longitudinal edge of the sheet. Due to the sheet's speed, the scanning sensor actually travels diagonally across the sheet surface, resulting in a continuous scanning path forming a zigzag pattern relative to the direction perpendicular to the longitudinal edge of the sheet. Therefore, the scanning sensor only measures a small portion of the sheet along the diagonal zigzag pattern. Typically, the average of the profile measurements is calculated after each scan; this is often referred to as the "final average."

[0008] Most manufacturing plants display real-time measurement data as color maps to illustrate changes detected on the sheet. For example, MD data from sensors is presented in vertical columns, with each column representing a different coated strip. In a six-strip coated section, six columns are shown, with the left column representing the most recent data and the right column representing earlier data. The top of the left column shows the real-time data, while the color legend associates a specific hue with a specific measurement. As the data changes, the operator observes the corresponding color shift, indicating potential changes or defects.

[0009] However, interpreting color maps can be challenging because operators must mentally associate color and pattern changes with specific defect types. While pattern changes can suggest defects, color maps alone do not definitively identify defect types. In lithium-ion battery manufacturing, defects such as decarburization, bubbling, air bubbles, pinholes, pits, and dark spots can affect surface quality. Color maps alone are insufficient to distinguish these defect types.

[0010] Additionally, because the scanning sensors move diagonally across the width of the sheet, their positioning is represented as a single CD position on the color map. This diagonal scan path appears as a single horizontal line in the corresponding column or map, thus distorting the operator's view and failing to reveal defects falling outside the scan path.

[0011] To complement the color mapping, manufacturing plants also use contour views to monitor variations and defects on the sheet. For example, graphs can display the sheet's basis weight (g / m³). 2 The relationship between scanner speed (mm / s) and binning is shown. Crossing any threshold line indicates a defect in that area of ​​the sheet. Another graph shows the relationship between scanner speed (mm / s) and binning, allowing the operator to correlate scanner speed with measurement data.

[0012] Current manufacturing technology employs both scanning monitoring systems positioned at various points along the manufacturing process (MD) and fixed monitoring systems. Some monitoring systems are placed earlier in the process, while others are positioned further downstream. This arrangement allows operators to monitor different upstream stages of the manufacturing process, ensuring data availability throughout production. However, these separate monitoring systems present challenges for plant operators and engineers, who must manually correlate data from multiple systems to analyze the same parts of the processed material. This segmented approach makes it difficult to make real-time quality control decisions, resulting in a higher percentage of defective batteries that must be scrapped.

[0013] Therefore, what is desired are systems and methods that can readily detect manufacturing defects (e.g., periodically occurring system defects) in discontinuously manufactured products (such as roll-to-roll lithium-ion battery electrodes), distinguish between longitudinal and transverse defects, detect defects on both sides (e.g., the top and bottom sides of the roll), intelligently group defects, and readily display clustered defects in an integrated and easily visualized manner. Summary of the Invention

[0014] This disclosure relates to quality control of continuous sheet materials, and more specifically to the use of intelligent grouping algorithms and visualization techniques to monitor sheet materials, such as electrodes used in lithium-ion batteries, and to display defect information in an integrated and easily visualized manner. While various embodiments are described herein in the context of roll-to-roll lithium-ion battery electrodes, this disclosure is not limited thereto. For example, this disclosure is applicable to other discontinuous and continuous (e.g., papermaking) manufacturing processes.

[0015] As detailed herein, this disclosure provides an intelligent defect grouping and visualization system. The intelligent defect grouping and visualization system described herein can utilize various grouping methods and algorithms, such as spatial proximity-based methods and mesh mapping-based methods. Therefore, the intelligent defect grouping and visualization system of this invention can intelligently group and display defects across the length of a long sheet while maintaining good defect visibility (e.g., good defect visibility even at different screen resolutions). For example, the intelligent defect grouping and visualization system of this invention can perform weighted centroid calculation and display the centroids of one or more different types of defects (e.g., as detected from one or more different types of sensors). Additionally, in some embodiments, the mesh-based method described herein can utilize resolution-dependent mesh size settings to automatically adapt defect visualization based on display constraints (e.g., the resolution of one or more displays or monitors).

[0016] This invention relates to integrated quality monitoring technologies that enable plant operators to simultaneously view and analyze data from multiple sensors. In the context of lithium-ion battery production, operators can view upstream quality issues, such as defects originating from the anode or cathode portions. Operators can effectively analyze sheet coatings in real time using multiple sensor and camera systems. Upon detecting defects in a continuous sheet and then identifying their location and source, operators can quickly initiate appropriate corrective measures (e.g., reconfiguring actuators associated with the lithium-ion battery production system, such as those described herein) to resolve the problem. These improvements collectively enhance system performance, efficiency, and accuracy, as detailed herein.

[0017] A particular aspect of this disclosure is an exemplary method for determining the quality of a sheet roll, the method comprising: monitoring data indicating defects on either side of the sheet roll, the data including data indicating: surface defects of the sheet roll; registration defects of the sheet roll; and quality and control system (QCS) defects of the sheet roll; grouping the defects into a group of defects; calculating a weighted centroid of the group of defects; and displaying a representation of the group of defects at the weighted centroid.

[0018] In some aspects that may be used in conjunction with or as an alternative to other aspects of this paper, the weighted centroid is based on the corresponding severity weight of each defect in the defect.

[0019] In some aspects, which may be used in conjunction with or as an alternative to other aspects of this paper, the method further includes: calculating the location of the weighted centroid according to the following formula: , Where: “w1”, “w2”, ..., “wn” represent the individual defect weights; “x1”, “x2”, ..., “xn” are the lateral locations of the defects; and “y1”, “y2”, ..., “yn” are the longitudinal locations of the defects.

[0020] In some aspects that may be used in conjunction with or as an alternative to other aspects of this document, the representation of a set of defects indicates: which side of the sheet roll the set of defects is located on; the location of the set of defects on one side of the sheet roll; the type of the set of defects; the severity of the set of defects; or any combination thereof.

[0021] In some aspects that may be used in conjunction with or as an alternative to other aspects of this document, the representation of a set of defects indicates which side of the sheet roll the set of defects is located on.

[0022] In some aspects that may be used in conjunction with or as an alternative to other aspects of this paper, the method also includes: calculating a spatial grid of the sheet roll; and grouping defects based on their location within the spatial grid.

[0023] In some aspects that may be used in conjunction with or as an alternative to other aspects of this document, the method further includes: calculating the number of grid cells in a spatial grid based on the size of the display, the horizontal and vertical scaling levels within the display application, and the minimum grid cell size.

[0024] In some aspects that may be used in conjunction with or as an alternative to other aspects of this paper, the method further includes: calculating the total number of mesh cells according to the following formula:

[0025] Horizontal grid cell count = f(W, HZ, MGS) = (W × (HZ / 100)) / MGS;

[0026] Vertical grid cell count = f(H, VZ, MGS) = (H × (VZ / 100)) / MGS; and

[0027] Total grid cell count = f(H, W, HZ, VZ, MGS) = horizontal cell count × vertical cell count; and where:

[0028] "H" represents the vertical height of the screen;

[0029] “W” represents the horizontal width of the screen;

[0030] "HZ" refers to the horizontal scaling within the application's display.

[0031] "VZ" is the vertical zoom within the application display, and

[0032] “MGS” is the smallest grid cell size.

[0033] In some aspects that may be used in conjunction with or as an alternative to other aspects of this paper, the method also includes grouping defects within the same grid cell in a plurality of grid cells.

[0034] In some aspects, which may be used in conjunction with or as an alternative to other aspects of this paper, the method further includes grouping edge defects located on mesh boundaries between two or more adjacent mesh cells in such a manner as follows:

[0035] In some aspects that may be used in conjunction with or as an alternative to other aspects of this paper, the distance to a nearby defect in one or more grid cells is calculated; and edge defects are grouped with the nearest defects in one or more adjacent grid cells.

[0036] In some aspects that may be used in conjunction with or as an alternative to other aspects of this paper, the method also includes grouping defects based on the Euclidean distance between defect centers.

[0037] In some aspects that may be used in conjunction with or as an alternative to other aspects of this paper, the Euclidean distance is determined according to the following formula: d = √((x2-x1)). 2 + (y2-y1) 2 ), where x1 and x2 are horizontal positioning and y1 and y2 are vertical positioning.

[0038] In some aspects that may be used in conjunction with or as an alternative to other aspects of this paper, the method further includes: comparing the Euclidean distance to a configurable distance threshold; and grouping defects with Euclidean distances within the configurable distance threshold.

[0039] In some aspects that may be used in conjunction with or as an alternative to other aspects of this paper, the method also includes taking corrective actions based on the representation of the set of defects at the weighted centroid.

[0040] Another aspect of this disclosure is a non-transitory computer-readable medium including instructions that, when executed by a processor, cause the processor to: monitor data indicating defects on either side of a continuous sheet roll moving in the longitudinal (MD) direction, the data including data indicating: surface defects of the continuous sheet roll; registration defects of the continuous sheet roll; and quality and control system (QCS) defects of the continuous sheet roll; group the defects into a group of defects based on the Euclidean distance between defects in a spatial grid of the continuous sheet roll or the location of the defects; calculate the weighted centroid of the group of defects; and display an image including a representation of the group of defects at the weighted centroid.

[0041] In some aspects that may be used in conjunction with or as an alternative to other aspects of this document, the method further includes simultaneously displaying: a first representation indicating a first set of defects on a first side of a continuous sheet roll; and a second representation indicating a second set of defects on a second side of a continuous sheet roll, wherein the second representation differs from the first representation.

[0042] In some aspects that may be used in conjunction with or as alternatives to other aspects of this document, wherein: the first indicates the MD and transverse (CD) positions of the weighted centroid on a first side of the continuous sheet roll, wherein the CD is perpendicular to the MD; and the second indicates the MD and CD positions of the weighted centroid on a second side of the continuous sheet roll.

[0043] In some aspects that may be used in conjunction with or as an alternative to other aspects of this document, magnifying the displayed representation of the set of defects results in the display of a representation of each individual defect among the various defects in the set of defects.

[0044] Another aspect of this disclosure is a system for monitoring the production of a continuous sheet roll traveling in the longitudinal (MD) direction, the system comprising: a computer device configured to: receive data from a plurality of sensors measuring one or more characteristics of the continuous sheet roll, the data indicating surface defects, registration defects, and quality and control system (QCS) defects of the continuous sheet roll; group defects into a group of defects based on the Euclidean distance between defects or the location of defects in a spatial grid of the continuous sheet roll; and calculate the weighted centroid of the group of defects; and a display device configured to display: a single representation indicating the MD position and transverse (CD) position of the weighted centroid of the group of defects at a first scaling level; and a plurality of representations indicating the corresponding MD position and CD position of each defect in the group of defects at a second scaling level above the first scaling level.

[0045] In some aspects that may be used in conjunction with or as an alternative to other aspects of this document, wherein: the computer device is configured to receive data indicating historical defects and real-time defects; and the display device is configured to switch between a first zoom level and a second zoom level in response to user input.

[0046] The foregoing description is provided to facilitate understanding of the innovative features unique to this disclosure and is not intended as a complete description. A full understanding of this disclosure can be obtained by considering the entire specification, claims, drawings, and abstract as a whole. Attached Figure Description

[0047] This disclosure can be more fully understood by taking into account the following description of various examples in conjunction with the accompanying drawings, in which:

[0048] Figure 1A A roll-to-roll sheet production system for continuously coating a metal substrate with an anode or cathode material is described.

[0049] Figure 1B The rolling process is described;

[0050] Figure 2A It is a plan view depicting a system for applying reference marks on a continuously moving sheet;

[0051] Figure 2B This is a plan view illustrating electrode fabrication, which uses reference markers to establish traceability of measurement results by reading the reference markers on a continuously moving sheet and using these markers to coordinate measurement results.

[0052] Figure 2C It is a diagram illustrating the data and logical flow;

[0053] Figure 3This is a schematic diagram of the monitoring and control device;

[0054] Figure 4 Example methods for intelligent defect grouping and visualization are illustrated;

[0055] Figure 5 This illustrates another example method for intelligent defect grouping and visualization;

[0056] Figure 6 An example defect map is shown for intelligent defect grouping and visualization;

[0057] Figure 7 Examples Figure 6 Examples of cluster magnification in the defect mapping graph

[0058] Figures 8A to 8C An example of grid-based intelligent defect groups and visualization is shown; and

[0059] Figures 9A to 9B Examples of distance-based intelligent defect groups and visualizations are shown.

[0060] While this disclosure is subject to various modifications and alternatives, its details have been shown by way of example in the accompanying drawings and will be described in detail. However, it should be understood that this disclosure is not intended to limit it to the specific examples described. Rather, it is intended to cover all modifications, equivalents, and alternatives that fall within the substance and scope of this disclosure. Detailed Implementation

[0061] The following description should be read with reference to the accompanying drawings, in which similar elements in different drawings are numbered in a similar manner. The drawings are not necessarily drawn to scale and depict examples that are not intended to limit the scope of this disclosure. While examples of various elements are illustrated, those skilled in the art will recognize that many of the examples provided have suitable alternatives available.

[0062] This document assumes that all numbers are modified by the term “about” unless otherwise explicitly stated. Expressions of numerical ranges using endpoints include all numbers contained within that range (e.g., 1 to 5 includes 1, 1.5, 2, 2.75, 3, 3.80, 4, and 5).

[0063] As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” include plural references unless otherwise expressly stated. As used in this specification and the appended claims, the term “or” is generally used in its meaning to include “and / or” unless otherwise expressly stated.

[0064] It should be noted that references to "implementation schemes," "some implementation schemes," or "other implementation schemes" in the specification indicate that the described implementation schemes may include specific features, structures, or characteristics; however, each implementation scheme may not necessarily include that specific feature, structure, or characteristic. Furthermore, these phrases do not necessarily refer to the same implementation scheme. Additionally, when a specific feature, structure, or characteristic is described in conjunction with an implementation scheme, it is assumed that the feature, structure, or characteristic described in conjunction with that implementation scheme is applicable to other implementation schemes, whether explicitly described or not, unless explicitly stated otherwise.

[0065] While various embodiments are described herein in the context of roll-to-roll lithium-ion battery electrodes, this disclosure is not limited thereto. For example, this disclosure is applicable to other discontinuous and continuous (e.g., papermaking) manufacturing processes. Examples of systems and various aspects commonly associated with roll-to-roll lithium-ion battery electrodes are described in U.S. Patent No. 18 / 144,657, entitled “Integrated Quality Monitoring View for Battery Manufacturing Process”; the entire contents of that U.S. Patent are hereby incorporated by reference.

[0066] Figure 1A An example is illustrated of a process for coating a metal web or sheet used in the manufacture of lithium-ion electrochemical batteries and their electrodes. For manufacturing the anode, the electrode coating comprises an anode active material such as graphite, and for manufacturing the cathode, the electrode coating comprises a cathode active material such as lithium metal oxide. The electrode comprises a current collector metal foil coated on both sides with an electrode slurry, which may also contain carbon black, a binder, and a solvent. After the electrode slurry is applied to one side of the foil, the wet-coated foil is heated in a dryer to remove the solvent, leaving a solid layer of electrode material adhered to the metal foil. Copper foil is a preferred anode current collector material, and aluminum foil is a preferred cathode current collector material.

[0067] like Figure 1A As shown, roll 2 is unwound by an unwinding machine and supplied as a continuous metal web or sheet 30, which is coated with an electrode paste layer on its top surface by a coater 6. The basis weight, thickness, and other properties of the metal web or sheet 30 from roll 2 are generally known; the basis weight and / or thickness are measured using scanning β gauges 4 and 8, respectively, before and after the electrode paste is applied by the coater 6.

[0068] The coater 6 (such as a cast coater) includes an actuator that controls the slit die / scraper to regulate the amount of slurry extruded onto the sheet 30. The dryer 10 removes excess solvent and solidifies the slurry on the moving coated sheet 32 ​​to form an electrode layer on the sheet. Imaging devices 58 and 78 capture images of the surface of the coated sheet 32 ​​before and after the dryer 10. Each imaging device typically includes a camera and a light source illuminating the surface of the coated sheet 32. The imaging devices can be stationary or scanning. For stationary devices, the camera captures digital images of the surface of the coated sheet 32 ​​across its entire width. The camera generates a series of images that can be superimposed to form a continuous image of the entire coated sheet 32.

[0069] A scanning beta meter 12 measures the basis weight and / or thickness of the moving coated sheet 32 ​​exiting the dryer 10 after the calender 54. Then, rolling supports 34, 36 reverse the orientation of the moving sheet 38 so that the uncoated side is on top, and the coater 14 applies a layer of electrode paste to the top uncoated surface of the moving sheet 38. The basis weight and / or thickness of the bilaterally coated sheet 40 is then measured using a scanning beta meter 16 before entering the dryer 18. Imaging devices 70 and 72 capture images of the top and bottom surfaces of the sheet before the dryer 18, while imaging devices 74 and 76 capture images of the top and bottom surfaces of the sheet after exiting the dryer 18.

[0070] Further downstream, as the scanning device 24 moves back and forth over the double-sided coated sheet 42, a β-meter housed in the scanning device 24, along with an infrared temperature sensor, measures the basis weight and / or thickness and temperature of the double-sided coated sheet 42. A rewinding machine rolls the double-sided coated sheet 42 into a roll 44. Surface defects on the top and bottom coatings are monitored by imaging devices 26 and 28.

[0071] Figure 1B The calendering process is illustrated, in which the double-sided coated electrode layer from roll 62 passes through calender 54, which performs surface finishing and smoothing on the electrode layer. The basis weight and / or thickness of the double-sided coated sheet is then measured using a scanning β gauge 56, and imaging devices 22 and 20 capture top and bottom surface images before being collected into roll 80. The scanners and cameras are part of a quality control system (QCS).

[0072] In order to monitor the double-sided coated sheet 42 using the present invention, the thermal image data of the double-sided coated sheet 42 is correlated and corrected with the online basis weight and / or thickness measurement results of the coated sheet 42 to generate more accurate basis weight and / or thickness calculation values ​​across the coated current collector along its entire transverse (CD) direction.

[0073] In such Figure 1A and Figure 1BDuring the production process shown, the continuous sheet 30 can be marked to identify its positioning along the MD. For example, reference marks or markings and associated tracking codes (collectively referred to as "reference markers") are used as reference points along the MD. Figure 2A A system is shown for applying a series of reference marks to a moving sheet of material 80, the series of reference marks including reference marks or markers and associated tracking codes. A fixing mark device 82 is positioned above the sheet to apply a series of reference marks 86 along one edge of the moving sheet, while a fixing mark device 84 is positioned above the sheet to apply another series of reference marks 88 along opposite edges of the moving sheet. Each series of reference marks is aligned along the MD. In the case of cutting the sheet along the MD, each series of reference marks can be applied individually. Reference marks or markers are configured as horizontal lines perpendicular to the MD and vertical lines parallel to the MD. A preferred configuration of the reference marks is a cross or a plus sign "+". Successive horizontal elements or components of the reference marks may be spaced apart by a distance D. Vertical elements or components of the reference marks may be formed at a specific known distance from the edge of the adjacent sheet. A tracking code uniquely identifies each associated reference mark 82, 84. The sheet 80 is supported and conveyed by a roller 94, the speed of which is monitored by an encoder 98. Marking devices can be any suitable device that produces sufficiently permanent markings on a metal substrate and / or coating. For example, lasers can be used to mark metals, while inkjet printers can be used to mark paper, plastics, and fabrics.

[0074] In operation, computer 100 (e.g., computer equipment) regulates motor 96 to control the MD speed. A computer including a processor and storage device (memory) can be used, such as a laptop computer. Markers 82 and 84 each periodically mark uncoated or coated areas of the sheet using a reference marker that tracks a time or roll encoder measurement generated by encoder 98. The code from encoder 98 can be, for example, an encoder count, millisecond time, or a digital or computer-readable code associated with such a quantity. The code is stored in database 102. The code is unique and therefore cannot be duplicated. As further described herein, readers 90, 92 (such as optical character recognition detectors) scan the reference markers 82, 84. It should be understood that reference markers 82, 84 can be applied to any part of the moving sheet 80, including uncoated and / or coated areas.

[0075] Figure 2BThe use of reference markers 82 and 84 in tracking different measurements of the electrode layer on a moving sheet is illustrated. The electrode layer 110 is coated on a moving metal substrate, which is supported and conveyed along the MD by a roller 112 operated by a motor 114. An encoder 116 monitors the speed of the roller 112. A reader 118 identifies reference marker characters 126 on the uncoated side of the moving sheet. A frame 120 supports a scanning device 122, which includes a measuring instrument for measuring the basis weight and / or thickness of the coated sheet. The scanning device typically traverses the coated sheet 110 periodically at a constant speed. The measuring instrument is shown as measuring points or areas 124 of the coated sheet 110. Due to the sheet speed, the scanning device travels diagonally across the surface of the coated sheet, resulting in a continuous scanning path with a zigzag pattern relative to the direction perpendicular to the longitudinal edge of the coated sheet 110. An example of this zigzag pattern is scan path 128, which is tracked by a measuring instrument as the scanning device 122 traverses the sheet surface during continuous back-and-forth scanning. The angle of the scan path relative to the actual CD depends on the transverse (CD) rate of the scanning device and the known longitudinal (MD) rate of the coated sheet 110. The zigzag pattern of the inquiry point covers a relatively small portion of the surface of the coated sheet 110.

[0076] The computer 130 coordinates the measurement results of the scanning device 122 so that the position of the query point in pattern 128, along with the corresponding reference marker, is recorded in the database 132. In this way, the measurement results performed on each electrode are known.

[0077] Another feature is the ability to use reference markers to synchronize subsequent measurements with previous measurements. For example, Figure 2B The coated sheet 110, after being measured by sensor 122, can be moved to another production line for further processing, such as drying or calendering. The coated sheet 140, thus processed, is then formed and subjected to a second measurement. Sheet movement is supported on rollers 142 and a frame 150, which holds a second scanner device 152. Computer 130 controls motor 144, encoder 146, and scanner device 152 to synchronize the second measurement performed by scanner device 152 with the first measurement performed by downstream scanner device 122. Reader 148 detects reference marker 156, and scanning device 152 can be reset to begin measurement at interrogation point 154, such that the interrogation point in pattern 158 coincides with the interrogation point in the zigzag pattern.

[0078] If scanners 122 and 152 are properly aligned, such that when scanner 122 is in the first scanner position along the CD and detects a specific reference marker, the edge of the coated sheet is measured at the same scanner compartment on both scanners, then when scanner 152 detects the same specific reference marker, scanner 152 should also be in the same first scanner position along the CD. However, in practice, even if the scanners are properly aligned, the moving coated sheet may drift left and right along the CD, so it is necessary to adjust the operation to address this movement by using edge detection. The edge of the moving sheet can be specified as being detected at a specific reference marker xxx + a number counted by the encoder. Specifically, the computer receives a signal when one of the reference markers is read. However, these reference markers can be far apart, so an encoder signal can be used to monitor the sheet between consecutive reference markers. In particular, the encoder transmits pulses at a much higher rate, so the computer can use the pulses to interpolate positioning between reference markers. This also applies to the next scanner in the process.

[0079] When the second measurement is performed by the scanning device 152, the position of the inquiry point in pattern 158, along with the corresponding reference marker, is recorded in the database 132. Therefore, this database contains a library of first and second measurements performed on substantially the same inquiry point.

[0080] This invention allows for real-time monitoring of the sheet production process. The display can run on a PC, laptop computer, tablet computer, smartphone, or other portable, mobile, or handheld device.

[0081] Figure 2C A system for generating process quality data based on online measurements in a continuous electrode manufacturing plant is shown. The system includes various scanners 624 and cameras 618, a QCS server 614, a surface defect detection system and a vision measurement system 600, an aggregator node 610, and an encoded pulse generator and a network time protocol synchronization service 620.

[0082] The edges of the electrode substrate surface are marked with identifiers using a laser etcher / marker at pre-configured regular length intervals, ensuring that the identifier is present in every frame captured by the camera system. This identifier can be used to identify the length of the substrate / material currently being inspected. The identifier can be a barcode, QR code, or any other numeric / alphanumeric ID 622 understood by various systems within the solution.

[0083] All data generated from various systems (camera system, surface defect detection system, vision measurement system, and QCS server) is tagged with encoder pulses and timestamps (620) for synchronization in a data aggregator node, which combines data from various sources for calculating product quality disposal at the unit level (cathode, anode, etc.).

[0084] Images of the coated substrate / material are streamed from camera system 618 to surface defect detection system and critical measurement and analysis system 600. The surface defect detection system is configured to analyze the image data to detect surface defects, such as, but not limited to, edge voids, coating spots, and coating gaps. Furthermore, it classifies defects into predetermined categories and tags the data with metadata for further processing. Based on the configuration, it stores anomaly (data containing only problems) / complete image data in a designated network location 616.

[0085] The critical measurement analysis system (visual measurement system) is configured to analyze image data to detect critical measurement issues, such as, but not limited to, the width of the coating from the substrate edge to the edge and the width of coated and uncoated areas. Furthermore, it subscribes to setpoints, limits, and other metadata from the QCS server 614 to efficiently run algorithms against setpoints, processing limits, etc., from the currently selected product formulation. Based on the configuration, it stores anomaly (only problematic data) / complete image data in a designated network location.

[0086] Aggregator node 610 is configured to sort data based on time and encoder pulses, and transform the data as needed. It combines data from the surface defect detection system vision measurement system 600 and the QCS server 614. It also combines data to detect data patterns, thereby identifying and marking conditions such as periodic defects, defect clusters, etc., as described herein, so that operators can easily mark / annotate defective material for appropriate action by downstream operations. Based on configuration, it can historically record anomalies (data containing only problems) / complete data with signals to the history server 612. Furthermore, aggregator node 610 provides data in a well-designed, user-friendly view for monitoring, analyzing, and reporting operator efficiency, and calculates overall product quality handling based on the analysis of aggregated and synchronized data. The application programming interface (API) uses an open protocol to expose aggregated defect data and / or quality results to connected clients 602, 604, 606, and 608.

[0087] Figure 3This is an embodiment of a display monitoring device 250, which includes an imaging device 252 equipped with a lens 272, a display device 254 (e.g., a monitor), a processor 256, and a memory 258. In the case of monitoring lithium-ion battery production, measurement information on the quality of the metal substrate and electrodes is stored in the memory 258.

[0088] Suitable imaging equipment 252 includes a digital camera and a video camera that captures video frame by frame. Device 250 may also include a ranging device 260 configured to determine distances from the ranging device 260 to the sheet and other surfaces, and a Global Positioning System (GPS) receiver 262 configured to determine the positioning of system 250. Device 250 may include a sensor 264 for recognizing operator movements and a microphone 266 for capturing voice commands or input from the operator. Processor 256 may be configured for voice recognition and gesture detection so that operator hand or finger gestures are identified as user commands to operate device 250.

[0089] Finally, device 250 may include a receiver 268 for receiving data from the quality control system of the manufacturing plant and a transmitter 270 for sending data to the quality control system. For example, during battery production, various scanners are used to measure paper quality. The measurement results can be sent to device 250 and stored in memory 258. Device 250 may be a portable device equipped with a camera that can be modified and programmed, such as a tablet computer and a smartphone.

[0090] The following figures illustrate an exemplary defect map showing the integrated quality monitoring view of the present invention. The defect map is based on the electrode manufacturing process, wherein the coated electrode has 250 points or bins in width; each bin represents a distance of approximately 5 mm.

[0091] As detailed herein, this disclosure provides an intelligent defect grouping and visualization system that intelligently groups and displays defects across long sheet lengths using spatial proximity or grid mapping, while maintaining the visibility of critical defects. This intelligent grouping yields various benefits over simple detection or less sophisticated attempts to cluster defects (e.g., those that do not employ centroid-based representations of defect clusters, grid-based defect grouping, etc.). For example, conventional systems display all defects individually, leading to cognitive overload when viewing long sheet lengths (e.g., 500 meters longitudinally). Furthermore, some previous simple defect combination or grouping methods may lose severity information, while the weighted centroids in this paper preserve the prominence of critical defects within that group. Moreover, the method of this paper allows for efficient visualization even when pixel-to-millimeter ratios would otherwise prevent the display of a specific representation of each individual defect (e.g., two separate defects located 2 mm apart on a sheet roll with a length of 500 meters). Additionally, the method described herein allows operators to seamlessly switch between a wide-angle view displaying the entire length of the sheet (e.g., 500 meters) and a detailed magnified view of specific defects, with different icon systems distinguishing top-side and bottom-side defects (e.g., which can be displayed simultaneously on the same screen to allow operators to easily identify defect clusters on either side of the roll). Given the above, the system and method described herein enhance operator situational awareness and efficiency while reducing cognitive workload. For example, the system and method described herein allow operators to adjust the level of detail and grouping criteria based on application and preference. In other words, the system and method described herein generate technical benefits such as improved accuracy in sheet quality analysis processes by representing each defect uniquely located by spatial coordinates (e.g., longitudinal and lateral positioning), reduced waste and rework costs, and improved product quality.

[0092] In some implementations, the systems and methods of this paper use a spatial grid approach to group defects into a set of defects. For example, such methods may use a spatial grid (e.g., a spatial grid previously calculated for a given set of display sizes, display aspect ratios, display resolutions, and / or any combination thereof). This grid can be determined by identifying or receiving information indicating the resolution of a monitor (e.g., one configured to display the defects clustered in this paper), the size of the monitor (e.g., the diagonal size of the monitor, such as a 24-inch monitor), the aspect ratio of the monitor (e.g., 16:9), and / or any combination thereof). Examples of monitor resolutions include 4K, 2K, or Full HD (1080p) monitor resolutions. The dimensions of other monitor parameters may be detected automatically (e.g., based on data received from the monitor) or provided via input (e.g., input from an operator, system administrator, etc.).

[0093] Additionally, the spatial grid (i.e., the grid itself) can be determined by calculating the dimensions of the display screen. The dimensions include the length (L) and width (W) of the display screen. The dimensions can be automatically detected (e.g., based on data received from one or more cameras or sensors described herein), calculated, or provided via input (e.g., input from an operator, system administrator, etc.). For example, for a 16:9 aspect ratio, the width and height can be calculated using the following formula:

[0094] Width = diagonal screen size × 16 / {sqrt{16^2 + 9^2}}; and

[0095] Height = diagonal screen size × 9 / {sqrt{16^2 + 9^2}}.

[0096] In some implementations, the total number of grid cells can be equal to the total number of horizontal grid cells multiplied by the total number of vertical grid cells. The total number of horizontal and vertical grid cells can each be calculated as described herein. In some implementations, the methods and systems described herein can calculate the number of grid cells based on the following formula:

[0097] Horizontal cell count = f(W, HZ, MGS) = (W × (HZ / 100)) / MGS

[0098] Vertical cell count = f(H, VZ, MGS) = (H × (VZ / 100)) / MGS; and

[0099] Total cell count = f(H, W, HZ, VZ, MGS) = Horizontal cell count × Vertical cell count;

[0100] Where “H” is the vertical height of the screen, “W” is the horizontal width of the screen, “HZ” is the horizontal scaling within the application display (e.g., a defect mapping application), “VZ” is the vertical scaling within the application display, and “MGS” is the minimum grid cell size (e.g., the minimum vertical height and minimum horizontal width of a square grid cell).

[0101] For example, in some implementations, a higher screen resolution (and / or a larger screen size) may correspond to a higher number of grid cells.

[0102] In some implementations, the minimum cell size can be adjusted to control the count of grid cells as the screen size changes (increases or decreases), thereby allowing defects to be clearly viewed by default or grouped into larger groups.

[0103] In some embodiments, each grid cell in the grid may be the same size (e.g., having the same shape and the same dimensions). In some embodiments, a single grid cell may be a rectangular or square grid cell. In some embodiments, the number of grid cells may range from about 2,000 to about 6,000 (e.g., 2,442 or 4,312 grid cells, and other possible values), and other possible values. In some embodiments, the size of a single grid cell may range from 5 mm to 10 mm (e.g., 8 mm), and other possible values.

[0104] In some implementations, the length and width of the grid (e.g., all grid cells combined) may be proportional to the length and width of the entire sheet roll or a portion of the sheet roll. For example, the ratio of the grid size to the size of the entire sheet roll may be 1:10, 1:20, 1:30, 1:50, 1:100, 1:200, 1:300, 1:400, 1:500, 1:1000, 1:2000, and other possible values.

[0105] A mesh can be overlaid on a defect map (e.g., generated from defect data from multiple sources). All defects located within a single mesh cell can be grouped together (e.g., as a set of defects). For example, all defects falling within a single mesh cell that comprises multiple mesh cells can be automatically grouped together.

[0106] In some implementations, the systems and methods of this paper can identify edge defects and assign them to specific mesh cells. Edge defects located in two or more mesh cells (e.g., on the boundary between two or more mesh cells) can be grouped together with defects in one of the mesh cells. The systems and methods of this paper can automatically handle edge cases. For example, for a defect falling on a mesh cell boundary, the system identifies the location of the defect relative to the cell edge (e.g., whether the defect is located on the mesh boundary). If the defect is located on the mesh boundary, the system of this paper can calculate the distance from the edge defect to nearby defects in the adjacent mesh cells of the boundary immediately adjacent to the edge defect (e.g., Euclidean distance as described herein). Edge defects can be assigned to defects in the adjacent mesh cells closest to the location of the edge defect and may be clustered together with defects in the adjacent mesh cells closest to the location of the edge defect. This prevents the artificial separation of related defects that happen to fall on mesh boundaries. The method ensures that logical grouping is maintained while avoiding the arbitrary separation of defects that may be physically close but fall in different adjacent mesh cells. Edge case handling is particularly important when dealing with high defect density near mesh boundaries, or when the mesh size changes due to display resolution adjustments (e.g., in response to operator or other individual zooming in or out).

[0107] Defects can be grouped based on their location within the spatial grid. For example, all defects in a single grid cell can be grouped (i.e., clustered) together. However, in some implementations, a subset of all defects in a single grid cell can be grouped together (e.g., based on spatial proximity within the grid cell, based on the type of defect, based on one side of the sheet roll with the defect, and / or based on the severity of the defect, etc.).

[0108] Figure 4 An example method 400 for intelligent defect grouping and visualization is illustrated. At 402, method 400 may include: receiving information indicating multiple defects. This information may be received at one or more components described herein, such as the surface defect visualization detection system 600 and other possible components. This information may originate from multiple sensors, such as a QCS scanner and / or the camera system described herein.

[0109] At 404, method 400 may include: determining the size of the monitor, as described herein. Method 400 may also include determining the number of grid cells. For example, at 405, the method may include: determining the number (count) of horizontal grid cells. The number (count) of horizontal grid cells may be based on the determined monitor size (e.g., monitor width and monitor height), scaling level (e.g., vertical scaling level), and a predefined minimum grid cell size, as described herein. Similarly, at 406, method 400 may include: determining the number (count) of vertical grid cells. The number (count) of vertical grid cells may be based on the determined monitor size (e.g., monitor width and monitor height), scaling level (e.g., vertical scaling level), and a predefined minimum grid cell size, as described herein. At 408, method 400 may include: determining the total number of grid cells (e.g., these grid cells have the same shape and size), as described herein. For example, the total number of grid cells can be determined by multiplying the number of horizontal grid cells (as determined at 405) by the number of vertical grid cells (as determined at 406) to produce the total number of grid cells.

[0110] As a non-limiting example, to calculate the number of grid cells for a full HD screen (1920×1080 resolution) with a diagonal size of 24 inches and 32 inches and a minimum grid cell size of 8mm, follow these steps:

[0111] Step 1: Convert diagonal size to physical dimensions

[0112] Assuming an aspect ratio of 16:9, the width and height of the screen (in inches) can be calculated using the following formula:

[0113] Width = diagonal × 16 / {sqrt{16^2 + 9^2}}

[0114] Height = diagonal × 9 / {sqrt{16^2 + 9^2}}

[0115] The diagonal size is given in inches, so calculations are performed for both 24 inches and 32 inches:

[0116] For 24-inch:

[0117] Width = 24 × 16 / {sqrt{16^2 + 9^2}} = approximately 20.92 inches

[0118] Height = 24 × 9 / {sqrt{16^2 + 9^2}} = approximately 11.77 inches

[0119] For 32-inch:

[0120] Width = 32 × 16 / {sqrt{16^2 + 9^2}} = approximately 27.89 inches

[0121] Height = 32 × 9 / {sqrt{16^2 + 9^2}} = approximately 15.69 inches

[0122] Step 2: Convert inches to millimeters

[0123] 1 inch = 25.4 mm. Therefore:

[0124] For 24-inch:

[0125] Width = 20.92 × 25.4 = approximately 531.37 mm

[0126] Height = 11.77 × 25.4 = approximately 299.18 mm

[0127] For 32-inch:

[0128] Width = 27.89 × 25.4 = approximately 708.49 mm

[0129] Height = 15.69 × 25.4 = approximately 398.91 mm

[0130] Step 3: Calculate the number of grid cells

[0131] If the minimum grid cell size is 8mm, and the horizontal and vertical scaling is 100%, then to calculate the number of grid cells, divide the width and height by the grid cell size:

[0132] For 24-inch:

[0133] Horizontal cell = (width × (horizontal scaling / 100)) / minimum grid cell size = (531.37 × 1) / 8 = approximately 66

[0134] Vertical cell = (height × (vertical scaling horizontal / 100)) / minimum grid cell size = (299.18 × 1) / 8 = approximately 37

[0135] Total number of units = Horizontal units × Vertical units = 66 × 37 = 2442

[0136] For 32-inch:

[0137] Horizontal cell = (width × (horizontal scaling / 100)) / minimum grid cell size = 708.49 / 8 = approximately 88

[0138] Vertical cell = (height × (vertical scaling horizontal / 100)) / minimum grid cell size = 398.91 / 8 = approximately 49

[0139] Total number of units = Horizontal units × Vertical units = 88 × 49 = 4312

[0140] result:

[0141] For a 24-inch screen: 66 x 37 grid cells = 2442 cells; and

[0142] For a 32-inch screen: 88×49 grid cells = 4312 cells.

[0143] While the examples above use specific sizes (e.g., 24-inch screens and 32-inch screens) and values, these are merely examples and other sizes or values ​​may be used.

[0144] At 410, method 400 may include grouping defects. For example, each defect within a mesh cell may be grouped together. Additionally, edge defects located on the boundary between two or more mesh cells may be grouped together with one or more defects in adjacent mesh cells, as described herein.

[0145] At 412, method 400 may include: calculating the centroids of grouped defects, as described herein. That is, each group of defects may have a single corresponding centroid (e.g., a weighted centroid), as described herein.

[0146] At 414, method 400 may include: displaying a representation of grouped defects at the weighted centroid. As mentioned, this representation may be a single icon indicating: the location on one side of the sheet roll, the type of defect, the severity of the grouped defects (e.g., average severity, minimum severity, or maximum severity), the defect density within that group of defects; or any combination thereof. For example, in some embodiments, a first representation indicating a first group of defects on a first side of the continuous sheet roll may be displayed, and a second representation different from the first representation may be displayed indicating a second group of defects on a second side of the continuous sheet roll. For example, the representation of defects may be provided as a first type of icon (e.g., a solid icon) for top surface defects and a second type of icon (e.g., a hollow icon) for bottom surface defects. That is, the first representation indicates the MD and lateral (CD) position of the weighted centroid on the first side of the continuous sheet roll (e.g., where CD is perpendicular to MD); and the second representation indicates the MD and CD positions of the weighted centroid on the second side of the continuous sheet roll. Therefore, compared to other methods that limit themselves to showing the operator only defects on the top or bottom side of the sheet at a given time, it is easy (e.g., simultaneously) to display representations of both top and bottom surface defects in each group of icons. Similarly, the icons can also display indicators of the defect type and / or severity for each of multiple groups of icons.

[0147] Although grid-based methods (e.g., regarding...) can be used... Figure 4 The methods described herein group defects, but this disclosure is not limited thereto. Instead, in some embodiments, defects may be grouped based on their proximity. For example, two or more defects within a threshold distance (e.g., 1 mm, 2 mm, 3 mm, 4 mm, etc.) may be grouped together (e.g., in the absence of a grid). For example, defects spaced apart by a distance less than or equal to the threshold distance (e.g., Euclidean distance) may be grouped together. The threshold distance may be a predetermined distance or may be specified by an individual (e.g., based on input from an operator, etc.). In some embodiments, defects may be grouped based on the Euclidean distance between the defect center and / or the pixels where the representation of the corresponding defect is located. For example, the Euclidean distance between defects may be determined according to Formula 2 below.

[0148] d = √((x2-x1) 2 + (y2-y1) 2 (Formula 2); where:

[0149] “d” is the distance between two defects on the same side of the sheet roll;

[0150] "x1" and "y1" are the lateral and longitudinal locations of the first defect on the sheet roll (e.g., obtained at the center point of the first defect); and

[0151] “x2” and “y2” are the lateral and longitudinal locations of the second defect on the sheet roll (e.g., as obtained at the center point of the second defect).

[0152] The system and method described in this paper can calculate the centroid of a group of defects (e.g., defects grouped based on their location in a mesh or based on the distance between defects). The centroid can be calculated based on the spatial location of the defects. That is, the centroid can be determined based on the corresponding longitudinal and lateral locations of the defects in the group.

[0153] In some implementations, the centroid may be a weighted centroid. Each defect may have a corresponding weight. The location of the centroid may be based on the corresponding defect weight of the defect whose location is calculated from it. For example, the centroid may be based on the corresponding weight (e.g., severity weight) of each defect in a set of defects. For example, the location of the weighted centroid may be determined based on Formula 3 below.

[0154] Weighted position of the centroid = , (Formula 3); where:

[0155] "w1", "w2",..., "w n "Indicates the weight of a single defect (e.g., a weight that indicates the severity of a single defect);

[0156] "x1", "x2",..., "x n "This refers to the lateral location of the corresponding defect on the sheet roll (e.g., as obtained at the center point of the defect); and

[0157] "y1", "y2",..., "y n "It is the longitudinal location of the corresponding defect on the sheet roll (e.g., as obtained at the center point of the defect).

[0158] In some implementations, defect weights can be severity weights that indicate the specific severity of an individual defect. The severity weight of an individual defect can be determined based on its location, type, shape, and / or size (e.g., depth). For example, a small hole or bubble may have a low numerical severity weight, while a large hole or bubble may have a high or critical numerical weight associated with it. Weights can be automatically assigned and associated with defects by the system described herein, for example, based on one or more thresholds (e.g., size, depth, type, etc.). Weights can be associated with defects in real time (e.g., in response to defect detection).

[0159] As indicated in Equation 3 above, the numerator is summed with respect to the weights and their corresponding coordinates, while the denominator is summed with respect to the weights. This results in an average location of defects weighted by their severity, providing a more accurate representation of the location and salience of defects in the cluster. This method ensures that more severe defects have a greater impact on the location of unique defects, which helps to prioritize areas requiring immediate attention. Therefore, spatial proximity techniques simplify defect management, allowing for a more efficient and effective maintenance process.

[0160] Figure 5 Another example method for intelligent defect grouping and visualization is illustrated. At 502, method 500 may include: receiving information indicating multiple defects. As mentioned, this information may be received at one or more components described herein, such as the surface defect visualization detection system 600 and other possible components. This information may originate from multiple sensors, such as a QCS scanner and / or the camera system described herein.

[0161] At 507, method 500 may include: determining the distance between defects. For example, method 500 may include: determining the Euclidean distance between defects, as described herein. At 509, method 500 may utilize a rule engine to determine one or more criteria for grouping defects based on proximity measurements. Specifically, the rule engine may take the calculated Euclidean distance between defects as input and apply one or more configurable thresholds to determine when defects should be grouped together. For example, the rule engine may be used to make a decision about whether defects are “too close” (e.g., too close to be represented as a single defect based on the screen resolution of a given monitor). If it is determined that defects are too close (e.g., less than a threshold distance apart), these defects should be grouped together. The output grouping decision may then be fed into a weighted centroid calculation. Thus, the rule engine acts as a decision-making component that evaluates the spatial relationships between defects and determines whether these defects should be grouped, for example, using operator-configurable criteria to maintain clarity while preventing cognitive overload.

[0162] At 512, method 500 may include: calculating the centroids of the set of defects, as described herein. That is, each set of defects may have a single corresponding centroid (e.g., a weighted centroid), as described herein.

[0163] At 514, method 500 may include: displaying a representation of the group of defects at the weighted centroid. As mentioned, the representation may be a single icon indicating whether the defect is a single defect or a group of defects (e.g., these defects have been grouped together using the methods described herein), its location on one side of the sheet roll, the type of defect, the severity of the defect (e.g., average severity, minimum severity, or maximum severity), the defect density within the group of defects, or any combination thereof. In some embodiments, a first representation indicating that the defect is a single defect may be displayed, and a second representation different from the first representation indicating a group of defects on a continuous sheet roll may be displayed. For example, the representation of the defect may be provided as a first type of icon (e.g., a hollow icon) for a single defect and a second type of icon (e.g., a solid icon) for a group of defects that have been grouped together, as described herein. That is, compared to other methods that are limited to displaying a single defect at a given time, it is easier (e.g., simultaneously) to display both a single defect icon and the group of defect icons.

[0164] Similarly, in some embodiments, a first representation indicating a first group of defects on a first side of a continuous sheet roll may be displayed, and a second representation, different from the first representation, indicating a second group of defects on a second side of the continuous sheet roll may be displayed. For example, the defect representation may be provided as a first type of icon (e.g., a solid icon) for top-side defects and a second type of icon (e.g., a hollow icon) for bottom-side defects. That is, representations of both top-side and bottom-side defects can be easily (e.g., simultaneously) displayed compared to other methods that limit themselves to showing only defects on the top or bottom side of the sheet to an operator at a given time. Similarly, the icons may also display indicators of defect type and / or defect severity, as well as other characteristics associated with the detected defects.

[0165] Additional examples of the representation of a defect are described in U.S. Patent No. 18 / 144,657 entitled “Integrated Quality Monitoring View for Battery Manufacturing Process”, the entire contents of which are hereby incorporated by reference.

[0166] In various implementations, the systems and methods of this invention can display a representation of a set of defects as a single icon located at a position calculated for a weighted centroid of the defects. The representation of the set of defects can be designed in terms of size, shape, color, and / or include numbers or text indicating one or more characteristics of the defects in the set. The characteristics of the defects include which side of the sheet roll the set of defects is located on, its position on one side of the sheet roll, the type of defect, the severity of the set of defects, or any combination thereof. Therefore, the systems and methods of this invention can use an appropriate icon system for distinguishing defect types, etc., to render a display with a set of defects. Thus, the systems and methods of this invention can automatically adapt to different display resolutions and sheet sizes while maintaining logical defect grouping and visual clarity based on display resolution constraints, the current zoom level, defect proximity and / or location and / or defect severity in the grid.

[0167] Figure 6 A monitor screen 600 is shown illustrating a defect mapping diagram 601 of the present invention. Figure 6 A wide-angle view interface showing defects across the sheet width and a group of defects 603 is shown. The interface displays multiple defect indicators at different longitudinal (MD) and transverse (CD) locations, with measurements shown along both axes. The display includes surface defects represented by different icons, registration defects shown using different icon systems, weight defects indicated by specific markers, defect groups shown as combined indicators, sheet width measurements (mm) on the horizontal axis, and longitudinal measurements on the vertical axis.

[0168] This diagram illustrates how the system provides a comprehensive view of the entire sheet length while using intelligent grouping to maintain defect visibility across the extended observation area. The interface allows operators to monitor defects across long sheet lengths (e.g., 500 meters) while maintaining the ability to distinguish different defect types and their locations. The visualization uses a different icon system to differentiate defect types and sources, with solid icons representing top surface defects and hollow icons representing bottom surface defects. This comprehensive view enables operators to quickly identify areas with high defect density and make informed quality control decisions.

[0169] Figure 7 Examples of amplification portions (e.g., including those from...) Figure 6 An example of the region of defect 603 in the defect mapping map. That is, Figure 7 A magnified view of the interface is shown, illustrating how to inspect individual defects within a group (e.g., by the operator). Figure 7 The interface is configured to display surface defects (e.g., displaying both solid top surface defect icons 702, 704 and hollow bottom surface defect icons 706, 708), registration defects, weight defects, and defect groups. Figure 7 The view in the middle shows the relationship with Figure 6 The wide-angle view, compared to defects spanning a narrower range of sheet widths (approximately 195mm to 230mm), allows the operator to see individual defects in detail rather than as a single group of defects. The interface includes a legend at the top, illustrating the different defect types and their corresponding icon sets. Figure 7 The magnified view allows for selective, detailed inspection of specific defects within a set of defects, such as by an operator, distinguishing different defect types, viewing both top and bottom surface defects simultaneously, and / or analyzing defect patterns in specific regions of interest within a sheet roll, among other possibilities. For example, the system and method described herein can display a single representation at a first zoom level indicating the longitudinal (MD) and lateral (CD) positions of the weighted centroids of that set of defects, such as... Figure 6 As illustrated, and at a second zoom level above the first zoom level, multiple representations indicating the corresponding MD and CD positions of each defect in this set of defects can be displayed, such as... Figure 7 As indicated. Therefore, magnifying the displayed representation of this set of defects results in displaying the representation of each individual defect in this set of defects.

[0170] therefore, Figures 6 to 7 The systems and methods described herein demonstrate that they can maintain defect identification and characteristics even when defects are grouped in a wider view, thereby allowing for detailed inspection when operators need to examine specific areas more closely and thus facilitating corrective actions to remedy defects and thereby improve the yield and / or quality of the final product. Alternatively or further, the intelligent identification and visualization of defects described herein can facilitate the grading or evaluation of manufactured materials (e.g., sheets and rolls of lithium-ion batteries), and thereby facilitate the inclusion of specific grades of manufactured materials in suitable products and / or the appropriate sale of manufactured materials.

[0171] In some embodiments, the monitor screen described herein may display various filters, defect details (e.g., type, location, size, quantity, etc.), defect maps, grids, mappings of defects to columns on the sheet roll, roll details (e.g., coating weight, edge characteristics, etc.), and / or various thresholds, such as those described in U.S. Patent No. 18 / 144,657 entitled “Integrated Quality Monitoring View for Battery Manufacturing Process,” the entire contents of which are hereby incorporated by reference.

[0172] Figures 8A to 8CAn example of using a grid-based intelligent defect group and visualization with grid 800 is shown. Grid 800 can include any number of grid cells, for example, such as... Figure 8A Visually represented (e.g., using an ellipse). That is to say, Figures 8A to 8C These are merely illustrative examples and are not intended to convey a specific number or size of grid cells in grid 800. For example, the number of grid cells may be determined, at least in part, based on the monitor's resolution and / or size, as described herein.

[0173] like Figure 8A As illustrated, mesh 800 may include multiple defects within a single mesh cell of the mesh (in Figure 8A (A single defect represented by a square). In such cases, each defect within a defect can be grouped together, as detailed herein. For example, Figure 8A In grid 800, each defect in a single grid cell can be grouped together, and the group can be displayed as a collection of overlapping individual icons placed at the centroid of the group (e.g., each of these overlapping individual icons has a portion overlapping with the weighted center point of the group), as shown. Figure 8B As illustrated. Alternatively, the group can be displayed as a single representation at the weighted centroid of a single defect within a single cell of grid 800. However, as mentioned, when defects are located in different groups (e.g., entirely within the grid and a portion of them not located on the boundaries between grid cells), the corresponding defects may remain ungrouped. For example, Figure 8C An example is given of a single defect that remains ungrouped (by...) Figure 8C (The square in the diagram represents a single defect), for example, because these defects do not include any other defects within the corresponding grid cell where the single defect is located. Figure 8C Examples of the same Figure 8A The defects in the grid are the same single defects, but at different scaling levels (e.g., with higher horizontal and / or vertical scaling). That is, zooming in or out on different parts of all grids 800 can result in defects being automatically grouped or not grouped based on their respective positions at different horizontal and / or vertical scaling levels.

[0174] Figures 9A to 9B Examples of distance-based intelligent defect grouping and visualization are illustrated. As detailed herein, in some implementations, individual defects can be selectively grouped based on distances between individual defects (e.g., between the centers of individual defects) such as... Figure 9A As illustrated, individual defects 931 may have corresponding distances 932 within (e.g., less than) a configurable distance threshold (such as those described herein). Therefore, Figure 9AIndividual defects in 931 can be grouped together and a single representation of the grouped defects can be displayed, as described herein. Conversely, as... Figure 9B As illustrated, individual defects 931 may have corresponding distances 933 that are outside the range of the configurable distance threshold (e.g., greater than or equal to the configurable distance threshold). Therefore, Figure 9B Individual defects in 931 are not grouped together and can be represented as two corresponding representations that can be displayed separately, as described herein.

[0175] Although several exemplary embodiments of this disclosure have been described thus, those skilled in the art will readily understand that other embodiments can be made and used within the scope of the appended claims. However, it should be understood that this disclosure is merely illustrative in many respects. Changes may be made to details, particularly those relating to shape, size, arrangement of parts, and exclusion and sequence of steps, without departing from the scope of this disclosure. The scope of this disclosure is, of course, defined by the language expressed in the appended claims.

Claims

1. A method for determining the quality of a sheet roll, the method comprising: Monitoring data indicating defects on either side of the sheet roll, the data including data indicating the following: Surface defects of the sheet roll; The registration defects of the sheet roll; and The quality and control system (QCS) defects of the sheet roll; as well as The defects are grouped into a set of defects; Calculate the weighted centroid of the set of defects; as well as This displays a representation of the set of defects at the weighted centroid.

2. The method of claim 1, wherein the weighted centroid is based on the corresponding severity weight of each defect among the defects.

3. The method according to claim 2, further comprising: The location of the weighted centroid is calculated using the following formula: , ;in: "w1", "w2", ..., "w n " indicates the individual defect weight of the defect; "x1", "x2", ..., "x n "This refers to the lateral location of the defect; and" "y1", "y2", ..., "y n "This refers to the longitudinal location of the defect." 4. The method according to any one of claims 1 to 3, wherein the representation of the set of defects indicates: On which side of the sheet roll are the set of defects located? The location of the set of defects on the said side of the sheet roll; The types of the set of defects; The severity of the set of defects; or Any combination of them.

5. The method of claim 4, wherein the representation of the set of defects indicates which side of the sheet roll the set of defects is located.

6. The method according to any one of claims 1 to 3, further comprising: Calculate the spatial grid of the sheet roll; as well as The defects are grouped based on their location within the spatial grid.

7. The method according to claim 6, further comprising: The number of grid cells in the spatial grid is calculated based on the display size, the horizontal and vertical zoom levels within the display application, and the minimum grid cell size, where: Horizontal grid cell count = f(W, HZ, MGS) = (W × (HZ / 100)) / MGS; Vertical grid cell count = f(H, VZ, MGS) = (H × (VZ / 100)) / MGS; and Total grid cell count = f(H, W, HZ, VZ, MGS) = horizontal cell count × vertical cell count; where: "H" is the vertical height of the screen; "W" is the horizontal width of the screen; "HZ" is the horizontal scaling within the application display; "VZ" is the vertical scaling within the application display; and "MGS" is the minimum grid cell size.

8. The method according to any one of claims 1 to 3, further comprising: The defects are grouped based on the Euclidean distance between their centers; Optionally, the Euclidean distance is determined according to the following formula: d = √((x2-x1)) 2 + (y2-y1) 2 ), where x1 and x2 are horizontal positioning and y1 and y2 are vertical positioning.

9. The method according to any one of claims 1 to 3, further comprising: Corrective actions are taken based on the representation of the set of defects at the weighted centroid.

10. A system for monitoring the production of a continuous sheet roll traveling in the longitudinal direction (MD), the system comprising: Computer equipment, the computer equipment being configured to: Data is received from multiple sensors that measure one or more characteristics of the continuous sheet roll, the data indicating surface defects of the continuous sheet roll, registration defects of the continuous sheet roll, and quality and control system (QCS) defects of the continuous sheet roll. The defects are grouped into a group based on the Euclidean distance between the defects in the spatial grid of the continuous sheet roll or the position of the defects. as well as Calculate the weighted centroid of the set of defects; and A display device configured to display: A single representation of the MD position and lateral (CD) position of the weighted centroid of the set of defects at a first scaling level; and Multiple representations indicating the corresponding MD and CD positions of each defect in the set of defects at a second scaling level higher than the first scaling level.

Images