Foreign matter detection method and detection system for wound battery and computer device
By combining infrared light source and image processing technology with machine learning models, the accuracy and safety issues of detecting tiny metal foreign objects in wound batteries have been solved, achieving efficient and economical foreign object detection results.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- 凯多智能科技(上海)有限公司
- Filing Date
- 2026-01-22
- Publication Date
- 2026-04-21
AI Technical Summary
Existing technologies cannot accurately detect tiny metallic foreign objects in wound batteries, leading to battery safety risks. Furthermore, X-ray inspection equipment is expensive and poses a certain radiation hazard.
Infrared light sources are used to detect the stacked materials of wound batteries. Foreign objects are identified by utilizing the grayscale distribution characteristics of infrared light. Detection images are acquired through imaging devices, and the presence of foreign objects is determined based on grayscale abrupt change regions in the images. Accurate identification is achieved by combining these with machine learning models.
It enables efficient and accurate detection of foreign objects in wound batteries, reduces detection costs, and improves battery safety and production efficiency.
Smart Images
Figure CN121904023A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of battery testing technology, and in particular to a method, system and computer device for detecting foreign objects in wound batteries. Background Technology
[0002] With the rapid development of the new energy industry, wound lithium-ion batteries are widely used in consumer electronics, electric vehicles, and energy storage systems due to their advantages such as high energy density, compact structure, and high production efficiency. The basic structure of a wound battery consists of a positive electrode, a negative electrode, and a separator between them. These are wound into a cell by a winding machine in a certain order and tension, and then assembled into a single battery cell.
[0003] During the winding process, to ensure battery performance and safety, the separator must possess good mechanical strength and insulation to prevent direct contact between the positive and negative electrodes, which could cause internal short circuits. However, because the winding process is carried out under high-speed continuous production conditions, and the positive electrode, negative electrode, and separator are all thin and flexible materials, minute impurities in the production environment can easily be introduced into the cell structure. In particular, foreign objects made of metal (such as metal shavings, equipment wear particles, and tool residues) pose a significant threat to battery safety.
[0004] Metallic foreign objects generally possess high hardness and a sharp shape. Under the influence of winding tension and material compression, they may directly pierce or scratch the separator, causing a loss of local insulation function. Once the separator is damaged, the positive and negative electrodes become directly conductive at the contact point, forming an internal micro-short circuit or a severe short circuit. This situation not only causes battery capacity decay and accelerated self-discharge but may also trigger localized high temperatures, further initiating thermal runaway, leading to swelling, leakage, fire, or even explosion.
[0005] In battery cell structures, the outermost layers of metal foil are often empty foils without any active material coating. Without the insulating and buffering effect of active material, foreign metal objects can more easily come into direct contact with the foil, significantly increasing the likelihood of short circuits. Furthermore, the outermost layers are the first to be exposed to the production environment, making them more susceptible to contamination by airborne metal particles.
[0006] However, while current technologies employ methods such as X-rays for detection, several limitations exist. Firstly, X-ray imaging resolution is affected by equipment hardware (e.g., X-ray source focal size, detector pixel size) and imaging parameters. For small metallic foreign objects, sufficiently clear images may not be formed, leading to missed detections. Secondly, the density difference between tiny metallic foreign objects and battery materials (e.g., copper foil, aluminum foil, separators) under X-rays is sometimes not significant, especially when the foreign object is very small or encased in multiple layers of material, resulting in low imaging contrast and difficulty in differentiation. Furthermore, X-ray detection equipment is expensive and poses a certain radiation hazard, requiring strict radiation protection and operation by skilled personnel, increasing the investment and maintenance costs of the production line.
[0007] Therefore, finding a better way to accurately detect foreign objects in wound batteries has become a pressing technical problem in the industry. Summary of the Invention
[0008] In view of the shortcomings of the prior art described above, the purpose of this disclosure is to provide solutions to the problems in the related art.
[0009] The first aspect of this disclosure provides a method for detecting foreign objects in a wound battery, wherein the wound battery has a structure formed by winding stacked materials; the method includes: acquiring a detection image obtained by irradiating the detected portion of the stacked materials with an infrared light source; obtaining a foreign object detection result based on the grayscale distribution characteristics of the detection image; wherein, a protrusion formed by the foreign object compressing its outer layer material will present a grayscale abrupt change region in the detection image.
[0010] In an embodiment of the first aspect, the wavelength range of the infrared light source is 750 nm to 1400 nm.
[0011] In an embodiment of the first aspect, the detected portion is located in the laminated material before winding, the unwound semi-finished cell, or the wound cell.
[0012] In an embodiment of the first aspect, obtaining the foreign object detection result based on the grayscale distribution features of the detected image includes: determining a grayscale abrupt change region based on the grayscale value difference between neighboring pixels in the detected image; and determining the presence of a foreign object based on the grayscale abrupt change region.
[0013] In an embodiment of the first aspect, determining the presence of a foreign object based on the grayscale abrupt change region includes: extracting geometric features of the grayscale abrupt change region; wherein the geometric features include shape and / or size; and determining the presence of a foreign object in response to the geometric features of the grayscale abrupt change region meeting preset conditions.
[0014] In an embodiment of the first aspect, obtaining the foreign object detection result based on the grayscale distribution features of the detected image includes: obtaining the foreign object detection result by identifying the detected image using a foreign object recognition model; wherein the foreign object recognition model is obtained by training a machine learning model with training data, and the training dataset includes a set of detected images labeled with foreign objects.
[0015] In an embodiment of the first aspect, the laminated material includes: a positive electrode material layer, a negative electrode material layer, and a membrane layer that insulatingly separates the positive electrode material layer and the negative electrode material layer.
[0016] A second aspect of this disclosure provides a computer apparatus, comprising: a processor and a memory; the memory storing a computer program or instructions; the processor being configured to run the computer program or instructions to perform any one of the first aspects.
[0017] A second aspect of this disclosure provides a foreign object detection system for a wound battery, the wound battery having a structure formed by winding stacked materials; comprising: an infrared light source configured to emit infrared light to illuminate the detected portion of the stacked materials; an imaging device configured to receive reflected light from the infrared light and image it to obtain a detection image; and a processing device connected to the imaging device configured to obtain a foreign object detection result based on the grayscale distribution characteristics of the detection image; wherein a protrusion formed by the foreign object pressing against its outer layer material will appear as a grayscale abrupt change region in the detection image.
[0018] In the second aspect of the embodiment, the wavelength range of the infrared light source is 750 nm to 1400 nm; and / or,
[0019] The infrared light source and imaging device are arranged in at least one of the following locations:
[0020] 1) The position settings correspond to the conveying of the laminated material before winding;
[0021] 2) The position is set according to the circumferential passage of the semi-finished battery cell during winding;
[0022] 3) The testing area is set up to correspond to the area where the battery cell to be tested is placed.
[0023] As described above, this disclosure relates to the field of battery detection technology, providing a method, system, and computer device for foreign object detection in wound batteries. The method includes: acquiring a detection image obtained by irradiating the detected portion of a stacked material with an infrared light source; obtaining a foreign object detection result based on the grayscale distribution characteristics of the detection image; wherein, protrusions formed by the foreign object compressing its outer layer material will appear as grayscale abrupt change regions in the detection image. X-rays used in related technologies, due to their extremely short wavelength and strong penetrating power, result in extremely dark images, making it difficult to detect foreign objects. In contrast, infrared light has a longer wavelength and moderate penetrating power, which can suppress the brightness of parts other than the foreign object (such as films or metals) in infrared imaging. However, due to the irregular structure of the foreign object, strong local scattering occurs at the foreign object, resulting in a significant brightness difference compared to other parts, making it easier to detect. Therefore, this method effectively solves the problems in related technologies, significantly reducing the difficulty of foreign object detection and improving accuracy. Attached Figure Description
[0024] Figure 1 A schematic diagram of the structure of a battery cell is shown in the example.
[0025] Figure 2 This diagram illustrates the structure of a stacked material consisting of a positive electrode layer, a negative electrode layer, and a separator layer, used to wind a battery into a spiral-wound battery.
[0026] Figure 3 A flowchart illustrating a foreign object detection method for a wound battery according to an embodiment of this disclosure is shown.
[0027] Figure 4 , Figure 5 and Figure 6 The following are schematic diagrams showing the detection images obtained by irradiating the same detection area with X-rays, white light, and infrared light respectively in the embodiments of this disclosure.
[0028] Figure 7 A schematic diagram of the foreign object detection system for a wound battery according to one embodiment of the present disclosure is shown.
[0029] Figure 8 A schematic diagram of a foreign object detection device for a wound battery according to an embodiment of the present disclosure is shown.
[0030] Figure 9 A schematic diagram of the structure of a computer device according to an embodiment of the present disclosure is shown. Detailed Implementation
[0031] The following specific examples illustrate the implementation of this disclosure. Those skilled in the art can easily understand other advantages and effects of this disclosure from the information disclosed herein. This disclosure can also be implemented or applied through other different specific embodiments, and various details in this disclosure can be modified or changed according to different viewpoints and application modules without departing from the spirit of this disclosure. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this disclosure can be combined with each other.
[0032] The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings, so that those skilled in the art to which this disclosure pertains can readily implement it. This disclosure may be embodied in many different forms and is not limited to the embodiments described herein.
[0033] In this disclosure, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic represented in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. Furthermore, the specific features, structures, materials, or characteristics represented may be combined in any suitable manner in any one or a group of embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples represented in this disclosure, as well as the features of those different embodiments or examples.
[0034] Furthermore, the terms "first" and "second" are used for illustrative purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the representation of this disclosure, "a set" means two or more, unless otherwise explicitly specified.
[0035] For the purpose of clarity, devices unrelated to the description are omitted, and the same or similar components throughout the specification are given the same reference numerals.
[0036] Throughout this specification, when it is said that a device is "connected" to another device, this includes not only "direct connection" but also "indirect connection" by placing other components in between. Furthermore, when it is said that a device "comprises" a certain constituent element, unless otherwise stated otherwise, this does not exclude other constituent elements, but rather implies that other constituent elements may be included.
[0037] While the terms first, second, etc., are used in some examples herein to refer to various elements, these elements should not be limited by these terms. These terms are used only to distinguish one element from another. For example, first interface and second interface, etc., are used. Furthermore, as used herein, the singular forms “a,” “an,” and “the” are intended to also include the plural forms unless the context indicates otherwise. It should be further understood that the terms “comprising,” “including,” indicate the presence of the stated feature, step, operation, element, module, item, kind, and / or group, but do not exclude the presence, occurrence, or addition of one or more other features, steps, operations, elements, modules, items, kinds, and / or groups. The terms “or” and “and / or” as used herein are interpreted as inclusive, or mean any one or any combination thereof. Thus, “A, B, or C” or “A, B, and / or C” means “any one of: A; B; C; A and B; A and C; B and C; A, B, and C.” Exceptions to this definition will only occur if the combination of elements, functions, steps, or operations is inherently mutually exclusive in some way.
[0038] The technical terms used herein are for reference only to specific embodiments and are not intended to limit the scope of this disclosure. The singular form used herein includes the plural form unless the statement explicitly indicates otherwise. The word "comprising" as used in this specification means to specify a particular characteristic, region, integer, step, operation, element, and / or component, and does not exclude the presence or addition of other characteristics, regions, integers, steps, operations, elements, and / or components.
[0039] Although not explicitly defined, all terms, including technical and scientific terms used herein, shall have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains. Terms defined in commonly used dictionaries shall be further interpreted as having a meaning consistent with the relevant technical literature and the message of the present disclosure, and shall not be over-interpreted as having an ideal or overly formulaic meaning unless otherwise defined.
[0040] A wound battery is a type of battery that is assembled into a compact structure by winding a positive electrode material layer, a negative electrode material layer, and a separator layer. In some embodiments, wound batteries are shaped like cylinders or squares. The winding process of the battery cell involves stacking the positive electrode material layer, separator layer, and negative electrode material layer in sequence and then winding them under a certain tension.
[0041] Please refer to the following: Figure 1 and Figure 2 . Figure 1 A schematic diagram of the structure of a battery cell is shown in the example. Figure 2 A schematic diagram of the structure of a stacked material comprising a positive electrode material layer 101, a negative electrode material layer 102, and a separator layer 103 for winding into a wound battery is shown.
[0042] Depend on Figure 1 and Figure 2 As can be seen, the separator layer 103 separates the positive electrode material layer 101 and the negative electrode material layer 102 to isolate the positive and negative electrodes and avoid short circuits. In some winding processes, the positive electrode material layer 101, the negative electrode material layer 102, and the separator layer 103 can be pre-layered as a stacked material and then wound into a battery cell. In some winding processes, the positive electrode material layer 101, the negative electrode material layer 102, and the separator layer 103 can be fed to the winding needle by their respective transport lines. The winding needle sequentially positions and hooks the positive electrode material layer 101, the separator layer 103, the negative electrode material layer 102, and the separator layer 103 in the circumferential direction, so that they are continuously stacked and wound into a battery cell 100 during circumferential movement, hereinafter referred to as "core".
[0043] Regardless of the process, impurities and foreign objects may be introduced during the winding process. These foreign objects can exist between any of the layers: the positive electrode material layer 101, the negative electrode material layer 102, and the separator layer 103. Conductive metallic foreign objects, in particular, generally possess high hardness and a sharp shape. Under the influence of winding tension and material compression, they may directly pierce or scratch the separator layer 103, causing it to lose its insulating function. Once the separator layer 103 is damaged, the positive and negative electrode material layers 102 become directly conductive at the contact point, forming an internal micro-short circuit or a severe short circuit. This situation not only causes battery capacity decay and increased self-discharge but may also trigger localized high temperatures, further initiating thermal runaway, leading to swelling, leakage, fire, or even explosion.
[0044] Especially in the outermost layers of the wound battery cell, active coatings may not be applied for safety redundancy and process optimization. Without the insulating buffering effect of active materials, if the separator layer 103 is punctured, metallic foreign objects can more easily come into direct contact with the foils of the positive and negative electrode material layers 102, significantly increasing the probability of a short circuit. Furthermore, the outermost layers are the first to be exposed to the production environment and are more likely to be contaminated by airborne metal particles.
[0045] Current technologies employ methods such as X-rays for detection. However, X-ray imaging resolution is affected by equipment hardware (such as the focal size of the X-ray source and the pixel size of the detector) and imaging parameters. For small metallic foreign objects, it may not form a sufficiently clear image. Moreover, X-rays have high penetrating power, often failing to clearly detect the outermost layers of the core, which are particularly important to monitor, leading to missed detections. Furthermore, the density difference between tiny metallic foreign objects and battery materials (such as copper foil, aluminum foil, and separators) under X-rays is sometimes not significant, especially when the foreign object is very small or encased in multiple layers of material, resulting in low imaging contrast and making it even more difficult for X-rays to distinguish them. On the other hand, X-ray detection equipment is expensive and poses a certain radiation hazard, requiring strict radiation protection and operation by professional personnel, increasing the investment and maintenance costs of the production line.
[0046] In view of this, one embodiment of the present disclosure provides a foreign object detection method for a wound battery, which uses infrared light to detect foreign objects in the wound battery. Since the wavelength of infrared light is much longer than that of X-rays, it has suitable penetrability, and is especially suitable for accurately detecting the outermost layers of the core. It can also suppress the brightness of parts other than foreign objects (such as films and metals) in infrared imaging, and because the foreign object structure is irregular, it will highlight the brightness of the foreign object, thereby achieving accurate foreign object detection.
[0047] like Figure 3 The diagram shown illustrates a flowchart of a foreign object detection method for a wound battery according to an embodiment of this disclosure.
[0048] The wound battery has a structure formed by winding stacked materials, which can be referred to as Figure 1 , Figure 2 The meaning is as shown.
[0049] exist Figure 3 The method includes:
[0050] Step S301: Obtain a detection image of the detected part of the stacked material irradiated by an infrared light source.
[0051] In some embodiments, infrared light emitted by an infrared light source illuminates the laminated material, and the resulting echo signal enters an imaging device to form a detection image. In some embodiments, the infrared light source and the imaging device can be an integrated unit or separate units. In some embodiments, the infrared light source can be implemented as a vertical-cavity surface-emitting laser (VCSEL), an LED light source, etc. The imaging device can be implemented as an infrared imager, etc.
[0052] It is known that the wavelength range of X-rays is 0.01 to 10 nanometers, and the wavelength range of infrared light is 760 nanometers to 1 millimeter. In this embodiment, the wavelength range of the infrared light source is selected as 750 nm to 1400 nm, preferably 760 nm to 1000 nm for optimal effect. This ensures that the infrared light emitted by the infrared light source has suitable penetrability, but lower penetration than X-rays, enabling accurate detection of foreign objects in multi-layered materials with interference suppression, especially suitable for detecting foreign objects in the outermost layers of the core. Specifically, the brightness of areas outside the foreign object in the image is suppressed due to the characteristics of infrared light, but strong local scattering occurs at the protrusions formed by the foreign object pressing against its outer layer material, causing the protrusions formed by the foreign object to appear as grayscale abrupt change areas (such as bright areas) in the detection image. Therefore, by using this grayscale (corresponding to brightness) feature for image analysis, the presence of foreign objects can be accurately detected.
[0053] In addition, although white light is also a commonly used light source in visual inspection technology, white light is a mixture of various colored lights with wavelengths shorter than infrared light wavelengths. It may also exhibit strong scattering and reflection in areas other than foreign objects on the membrane layer and electrode layer. This causes these areas to appear as gray-scale abrupt change areas in the white light inspection image, which will cause great interference to the gray-scale abrupt change areas of foreign objects, making it difficult to detect foreign objects.
[0054] The embodiments disclosed herein may provide relevant experimental results. Please refer to [link / reference]. Figure 4 , Figure 5 and Figure 6 The following are schematic diagrams showing the detection images obtained by irradiating the same detection area with X-rays, white light and infrared light respectively in the embodiments of this disclosure.
[0055] It is quite obvious, such as Figure 4 As shown, in the detection image obtained by irradiating the detected area with X-rays, the area is almost entirely black, the structure is difficult to distinguish, and it is impossible to determine the location of the foreign object.
[0056] exist Figure 5 The image shown is obtained by illuminating the detected area with white light and forming an image. It can be seen that the area A where the foreign object is located is a bright gray-scale abrupt change area. However, due to the reflection of the white light, other large gray-scale abrupt change areas, such as areas B and C, are also formed.
[0057] exist Figure 6The image shown is obtained by irradiating the detected area with infrared light (wavelength 760nm~1000nm) in an embodiment of this disclosure and imaging it. It can be seen that due to the effect of infrared light imaging, the brightness of the areas where B and C are located is suppressed, so that only the area A is a gray-scale abrupt change area that forms contrast. Thus, the interference from areas such as B and C is removed and the presence of foreign objects in the area A can be accurately detected.
[0058] Step S302: Obtain the foreign object detection result based on the grayscale distribution features of the detected image.
[0059] Understandably, the detection image formed by infrared light is a grayscale image, and the brightness of different pixels is related to their grayscale values. After eliminating interference areas using infrared light, the characteristic that "the area where the foreign object is located will show a sudden change in grayscale" can be easily identified using a preset image recognition algorithm, thereby determining the foreign object.
[0060] In some embodiments, the presence of abrupt changes can be determined based on the difference in grayscale values between adjacent pixels in the detected image, thereby identifying the existence of grayscale abrupt change regions. Specifically, grayscale abrupt change regions can be identified based on the difference in grayscale values of neighboring pixels in the detected image, specifically by identifying regions where grayscale abrupt changes occur (i.e., regions with lower grayscale values when grayscale abrupt changes occur). Furthermore, the presence of foreign objects can be determined based on these grayscale abrupt change regions.
[0061] Of course, there may be exceptions, such as a non-foreign object being identified as a foreign object. Therefore, in some optional embodiments, the geometric features of the gray-scale abrupt change region can also be extracted, including shape and / or size. Specifically, contour information, i.e., shape features, can be extracted from the edges of the gray-scale abrupt change region. Furthermore, the physical size grayscale of the gray-scale abrupt change region can be obtained from the image size using a pre-obtained conversion relationship between the image size and the actual physical size (e.g., obtained through calibration). In response to regions where the geometric features of the gray-scale abrupt change region meet preset conditions, such as a size greater than a preset threshold, or a shape that differs from a preset foreign object shape (e.g., differences in angle, side length, etc.), similar to... Figure 5 Regions B and C, etc. Specifically,
[0062] In some embodiments, a foreign object detection result can also be obtained from the detected image by using a foreign object recognition model trained based on a machine learning model. As an example, the machine learning model can be implemented based on, for example, a neural network model. In some preferred examples, the machine learning model can be implemented as a convolutional neural network (CNN) based object detection model (such as the YOLO series, SSD, etc.) or a semantic segmentation model (such as DeepLab, etc.). As an example, a training dataset can be constructed from a set of real-world images labeled with foreign objects, and the machine learning model can be trained until training conditions are met (such as loss convergence or reaching the required number of training iterations), thereby obtaining the trained foreign object recognition model.
[0063] In practical applications, the detected image is input into the foreign object recognition model, which can then output the foreign object detection result, such as providing definite information or probability of the presence of a foreign object, and / or directly marking the location of the foreign object in the detected image as the foreign object detection result.
[0064] Therefore, if a foreign object is present, an accurate detection image can be obtained by irradiating the stacked materials of the wound battery with infrared light, eliminating the interference area and highlighting the gray-scale abrupt change area of the foreign object. Based on the accurate detection image, feature recognition can be performed to obtain an accurate foreign object detection result, which can achieve a good foreign object detection effect. Compared with X-ray or white light detection methods in related technologies, the accuracy is greatly improved.
[0065] In some embodiments, the foreign object detection method can be implemented in any one or more stages of the winding process, before, during, or after the formation of the laminated materials, to detect foreign objects. This can achieve a reliable foreign object detection effect in one or more stages that can be flexibly implemented, thereby effectively improving the yield of wound batteries.
[0066] In one embodiment, the detected area is located in the laminated material before winding. That is, foreign object detection can be performed before winding at the location where the multilayer materials (electrode layer and diaphragm layer) are stacked, such as the location of the pre-stacked laminated material or the location where the laminated material is formed before being wound by the winding needle. This allows for timely detection of foreign objects before winding, enabling timely stopping of winding and preventing foreign objects from entering the core from upstream.
[0067] In another embodiment, the detected area is located on the unwound battery cell semi-finished product. That is, foreign object detection can be performed on the laminated material currently wound onto the core during winding. Therefore, foreign objects can be detected in time during winding, and winding can be stopped promptly.
[0068] In another embodiment, the area to be detected is located on the already wound battery cell. That is, foreign object detection can be performed on the core after winding. In this case, foreign object detection is mainly performed by looking through the outermost few layers of the stacked material on the core. Since the electrode material layers in the outermost few layers may not have a coating to buffer the penetration of foreign objects through the separator layer, the risk of short circuit is the highest. Therefore, the detection method in this embodiment mainly excludes foreign object situations with the highest risk of short circuit.
[0069] like Figure 7 The diagram shown illustrates the structure of a foreign object detection system for a wound battery according to an embodiment of this disclosure.
[0070] exist Figure 7 The foreign object detection system 700 shown in the image includes: an infrared light source 701, an imaging device 702, and a processing device 703.
[0071] The infrared light source 701 is configured to emit infrared light to illuminate the area to be detected in the laminated material. In some embodiments, the infrared light source 701 may be implemented as a vertical cavity surface-emitting laser (VCSEL), an LED light source, etc.
[0072] The imaging device 702 is configured to receive the reflected light from the infrared light and image it to obtain a detection image. Protrusions formed by foreign objects pressing against the outer layer material will appear as areas of abrupt grayscale changes in the detection image. In some embodiments, the infrared light emitted by the infrared light source 701, after illuminating the stacked materials, returns as echo signals and are imaged in the imaging device 702 to obtain a detection image. In some embodiments, the infrared light source 701 and the imaging device 702 can be an integrated device or separate components. In some embodiments, the imaging device 702 can be implemented as an infrared imager, etc.
[0073] It is known that the wavelength range of X-rays is 0.01 to 10 nanometers, and the wavelength range of infrared light is 760 nanometers to 1 millimeter. In this embodiment, the wavelength range of the infrared light source 701 is selected to be 750 nm to 1400 nm. This ensures that the infrared light emitted by the infrared light source 701 has suitable penetrability, but lower than that of X-rays, enabling accurate detection of foreign objects in multi-layered materials with interference suppression, especially suitable for detecting foreign objects in the outermost layers of the core. Specifically, the brightness of areas outside the foreign object in the image is suppressed due to the characteristics of infrared light, but strong local scattering occurs at the protrusions formed by the foreign object pressing against its outer layer material, causing the protrusions to appear as grayscale abrupt changes in the detection image. Therefore, image analysis using this grayscale (corresponding to brightness) feature can accurately detect the presence of foreign objects.
[0074] In addition, although white light is also a commonly used light source in visual inspection technology, white light is a mixture of various colored lights with wavelengths shorter than infrared light wavelengths. It may also exhibit strong scattering and reflection in areas other than foreign objects on the membrane layer and electrode layer. This causes these areas to appear as gray-scale abrupt change areas in the white light inspection image, which will cause great interference to the gray-scale abrupt change areas of foreign objects, making it difficult to detect foreign objects.
[0075] The embodiments disclosed herein may provide relevant experimental results. Please refer to [link / reference]. Figure 4 , Figure 5 and Figure 6 The following are schematic diagrams showing the detection images obtained by irradiating the same detection area with X-rays, white light and infrared light respectively in the embodiments of this disclosure.
[0076] It is quite obvious, such as Figure 4 As shown, in the detection image obtained by irradiating the detected area with X-rays, the area is almost entirely black, the structure is difficult to distinguish, and it is impossible to determine the location of the foreign object.
[0077] exist Figure 5 The image shown is obtained by illuminating the detected area with white light and forming an image. It can be seen that the area A where the foreign object is located is a bright gray-scale abrupt change area. However, due to the reflection of the white light, other large gray-scale abrupt change areas, such as areas B and C, are also formed.
[0078] exist Figure 6 The image shown is obtained by irradiating the detected area with infrared light (wavelength 760nm~1000nm) in an embodiment of this disclosure and imaging it. It can be seen that due to the effect of infrared light imaging, the brightness of the areas where B and C are located is suppressed, so that only the area A is a gray-scale abrupt change area that forms contrast. Thus, the interference from areas such as B and C is removed and the presence of foreign objects in the area A can be accurately detected.
[0079] The processing device 703, connected to the imaging device 702, is configured to obtain a foreign object detection result based on the grayscale distribution characteristics of the detected image. It is understood that the detection image formed by infrared light is a grayscale image, and the brightness of different pixels is related to their grayscale values. When interference areas are eliminated using infrared light, the feature that "the area where the foreign object is located will exhibit a grayscale abrupt change" can be easily identified using a preset image recognition algorithm, thereby determining the foreign object.
[0080] In some embodiments, the processing device 703 can determine whether a sudden change exists based on the difference in grayscale values between adjacent pixels in the detected image, thereby determining the existence of a grayscale change region. Specifically, the grayscale change region can be determined based on the difference in grayscale values of adjacent pixels in the detected image, identifying regions where grayscale changes occur (i.e., regions with lower grayscale values when grayscale changes occur). Furthermore, the presence of a foreign object is determined based on the grayscale change region.
[0081] Of course, there may be exceptions, such as a non-foreign object being identified as a foreign object. Therefore, in some optional embodiments, the geometric features of the gray-scale abrupt change region can also be extracted, including shape and / or size. Specifically, contour information, i.e., shape features, can be extracted from the edges of the gray-scale abrupt change region. Furthermore, the physical size grayscale of the gray-scale abrupt change region can be obtained from the image size using a pre-obtained conversion relationship between the image size and the actual physical size (e.g., obtained through calibration). In response to regions where the geometric features of the gray-scale abrupt change region meet preset conditions, such as a size greater than a preset threshold, or a shape that differs from a preset foreign object shape (e.g., differences in angle, side length, etc.), similar to... Figure 5 Regions B and C, etc. Specifically,
[0082] In some embodiments, the processing device 703 can also obtain foreign object detection results based on the detected images using a foreign object recognition model trained on a machine learning model. As an example, the machine learning model can be implemented based on, for example, a neural network model. In some preferred examples, the machine learning model can be implemented as a convolutional neural network (CNN) based object detection model (such as YOLO series, SSD, etc.) or a semantic segmentation model (such as DeepLab, etc.). As an example, a training dataset can be constructed from a set of real-world images labeled with foreign objects, and the machine learning model can be trained until training conditions are met (such as loss convergence or reaching the required number of training iterations), thereby obtaining the trained foreign object recognition model.
[0083] In practical applications, the detected image is input into the foreign object recognition model, which can then output the foreign object detection result, such as providing definite information or probability of the presence of a foreign object, and / or directly marking the location of the foreign object in the detected image as the foreign object detection result.
[0084] Therefore, if a foreign object is present, an accurate detection image can be obtained by irradiating the stacked materials of the wound battery with infrared light, eliminating the interference area and highlighting the gray-scale abrupt change area of the foreign object. Based on the accurate detection image, feature recognition can be performed to obtain an accurate foreign object detection result, which can achieve a good foreign object detection effect. Compared with X-ray or white light detection methods in related technologies, the accuracy is greatly improved.
[0085] In some embodiments, the processing device 703 may be implemented as a computer device, which may be a processing component or processing terminal, such as a controller, or a server, desktop computer, laptop computer, or mobile terminal.
[0086] In some embodiments, the foreign object detection system 700 can be arranged at the winding process site to detect foreign objects at any one or more stages before, during, or after the formation of the laminated material. It can achieve reliable foreign object detection at one or more stages that can be flexibly implemented, thereby effectively improving the yield of the wound battery.
[0087] In one embodiment, the infrared light source 701 and imaging device 702 are arranged at a position corresponding to the transport path of the stacked material before winding. That is, foreign object detection can be performed before winding, corresponding to the position where the multi-layered materials (electrode layer and diaphragm layer) are stacked, such as the position of the pre-stacked stacked material or the position where the stacked material is formed before being wound by the winding needle. Thus, foreign objects can be detected in time before winding, and winding can be stopped promptly, preventing foreign objects from entering the core from upstream.
[0088] In another embodiment, the infrared light source 701 and imaging device 702 are arranged at positions corresponding to the circumferential passage of the semi-finished battery cell during winding. That is, foreign object detection can be performed on the currently wound stacked material during winding. Thus, foreign objects can be detected promptly during winding, allowing for timely cessation of winding.
[0089] In another embodiment, the infrared light source 701 and imaging device 702 are arranged in a detection area corresponding to the placement of the battery cell under test. That is, foreign object detection can be performed on the core after winding is completed. In this case, foreign object detection is mainly performed by looking through the outermost layers of the core. Since the electrode material layers in the outermost layers may not have a coating to buffer the penetration of foreign objects through the separator layer, the risk of short circuit is the highest. Therefore, the detection method in this embodiment mainly excludes foreign objects with the highest risk of short circuit.
[0090] like Figure 8 The diagram shows a schematic representation of a foreign object detection device for a wound battery according to an embodiment of this disclosure. It should be noted that the principle and technical implementation of the foreign object detection device for the wound battery can refer to the foreign object detection method for wound batteries in previous embodiments; therefore, it will not be repeated in this embodiment.
[0091] The foreign object detection device 800 includes:
[0092] The image acquisition module 801 is used to acquire a detection image obtained by irradiating the detected part of the stacked material with an infrared light source. Protrusions formed by foreign objects pressing against the outer layer of material will appear as areas of abrupt grayscale changes in the detection image.
[0093] The foreign object detection module 802 is used to obtain the foreign object detection result based on the grayscale distribution features of the detection image.
[0094] It should be noted that, in Figure 8 The various functional modules in the embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any combination thereof. When implemented in software, they can be implemented, in whole or in part, in the form of a computer program or instruction product. A computer program or instruction product includes one or more computer programs or instructions. When a computer program or instruction is loaded and executed on a computer, it produces, in whole or in part, the flow or function according to this disclosure. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another.
[0095] and, Figure 8 The apparatus disclosed in the embodiments can be implemented through other modular division methods. The apparatus embodiments shown above are merely illustrative. For example, the module division is only a logical functional division, and in actual implementation, there may be other division methods. For example, a group of modules or modules may be combined or dynamically integrated into another system, or some features may be ignored or not executed. Furthermore, the shown or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces, and the indirect coupling or communication connection between devices or modules may be electrical or other forms.
[0096] in addition, Figure 8 The functional modules and sub-modules in the embodiments can be dynamically integrated within a single processing unit, or each module can exist physically independently, or two or more modules can be dynamically integrated within a single unit. These dynamic units can be implemented in hardware or as software functional modules. If these dynamic units are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. This storage medium can be a read-only memory, a hard disk, or an optical disk, etc.
[0097] It should be specifically noted that the flowchart representations of the embodiments described above in this disclosure can be understood as representing a module, segment, or portion of code comprising one or more executable instructions configured to implement a specific logical function or process. Furthermore, the scope of the preferred embodiments of this disclosure includes other implementations in which functions may be performed not in the indicated order, such as substantially simultaneously or in reverse order depending on the functions involved.
[0098] For example, Figure 3 The order of the steps in the method embodiments may vary in specific scenarios and is not limited to the above representation.
[0099] like Figure 9 The diagram shown illustrates the structure of a computer device according to an embodiment of the present disclosure.
[0100] The computer device 900 may be exemplified as a processing terminal, such as a server, desktop computer, laptop computer, tablet computer, smartphone, or other terminal.
[0101] The computer device 900 includes a bus 901, a processor 902, and a memory 903. The processor 902 and the memory 903 can communicate via the bus 901. The memory 903 can store computer programs or instructions. The processor 902 implements the method flow or function of the previous embodiments by running the computer program or instructions in the memory 903, for example... Figure 3 .in addition, Figure 7 The processing device in the embodiment can also be implemented by the computer device 900 in this embodiment.
[0102] Bus 901 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, although only one thick line is used in the diagram, this does not indicate that there is only one bus or one type of bus.
[0103] In some embodiments, processor 902 may be implemented as a central processing unit (CPU), microprocessor unit (MCU), system on chip (System on Chip), or field-programmable array (FPGA). Memory 903 may include volatile memory for temporary data storage during program execution, such as random access memory (RAM).
[0104] The memory 903 may also include non-volatile memory for data storage, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid-state disk (SSD).
[0105] In some embodiments, the computer device 900 may further include a communicator 904. The communicator 904 is used for communication with external devices. In specific examples, the communicator 904 may include one or more wired and / or wireless communication circuit modules. For example, the communicator 904 may include one or more of, such as a wired network card, a USB module, a serial interface module, etc. The wireless communication protocols followed by the wireless communication module include, for example, Nearfield Communication (NFC) technology, Infrared (IR) technology, Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Time-Division Code Division Multiple Access (TD-SCDMA), Long Term Evolution (LTE), Bluetooth (BT), Global Navigation Satellite System (GNSS), etc.
[0106] This disclosure also provides a computer-readable storage medium storing a computer program or instructions, which, when run, implement the method flow or function of any of the previous embodiments.
[0107] That is, the method steps in the above embodiments are implemented as software or computer code that can be stored in a recording medium (such as CD ROM, RAM, floppy disk, hard disk or magneto-optical disk), or implemented as computer code that is originally stored in a remote recording medium or a non-transitory machine-readable medium and will be stored in a local recording medium after being downloaded via a network, so that the method represented herein can be stored in such software processing on a recording medium using a general-purpose computer, a special processor or programmable or special hardware (such as ASIC or FPGA).
[0108] This disclosure may also provide a computer program product, comprising one or more computer programs or instructions, which, when run, perform all or part of the processes or functions described in this disclosure. The computer program product includes one or more computer programs or instructions.
[0109] Computer programs or instructions can be stored in a readable storage medium or transferred from one readable storage medium to another. For example, the computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The readable storage medium can be any available medium capable of access, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; an optical medium, such as a digital video optical disc; or a semiconductor medium, such as a solid-state drive. The computer-readable storage medium can be a volatile or non-volatile storage medium, or it can include both volatile and non-volatile types of storage media.
[0110] In summary, this disclosure relates to the field of battery detection technology, providing a method, system, and computer device for foreign object detection in wound batteries. The method includes: acquiring a detection image obtained by irradiating the detected portion of a stacked material with an infrared light source; obtaining a foreign object detection result based on the grayscale distribution characteristics of the detection image; wherein, protrusions formed by the foreign object compressing its outer layer material will appear as grayscale abrupt change regions in the detection image. X-rays used in related technologies, due to their extremely short wavelength and strong penetrating power, result in extremely dark images, making it difficult to detect foreign objects. In contrast, infrared light has a longer wavelength and moderate penetrating power, which can suppress the brightness of parts other than the foreign object (such as films or metals) in infrared imaging. However, due to the irregular structure of the foreign object, strong local scattering occurs at the foreign object, resulting in a significant brightness difference compared to other parts, making it easier to detect. Therefore, this method effectively solves the problems in related technologies, significantly reducing the difficulty of foreign object detection and improving accuracy.
[0111] The above embodiments are merely illustrative of the principles and effects of this disclosure and are not intended to limit this disclosure. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this disclosure. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this disclosure should still be covered by the protection scope of this disclosure.
Claims
1. A method for detecting foreign objects in a wound battery, characterized in that, The wound battery is a structure formed by winding stacked materials; the method includes: Acquire a detection image obtained by irradiating the detected area of the laminated material with an infrared light source; Foreign object detection results are obtained based on the grayscale distribution characteristics of the detected image; wherein, the protrusion formed by the foreign object squeezing its outer material will appear as a grayscale abrupt change region in the detected image.
2. The foreign object detection method according to claim 1, characterized in that, The wavelength range of the infrared light source is 750~1400nm.
3. The foreign object detection method according to claim 1, characterized in that, The area to be detected is located in the laminated material before winding, the unwound semi-finished cell, or the wound cell.
4. The foreign object detection method according to claim 1, characterized in that, The process of obtaining the foreign object detection result based on the grayscale distribution features of the detected image includes: Regions with abrupt changes in grayscale are determined based on the difference in grayscale values between neighboring pixels in the detected image; The presence of foreign matter is determined based on the grayscale abrupt change region.
5. The foreign object detection method according to claim 4, characterized in that, The step of determining the presence of a foreign object based on the grayscale abrupt change region includes: Extract the geometric features of the grayscale abrupt change region; wherein, the geometric features include shape and / or size; The presence of a foreign object is determined when the geometric features of the grayscale abrupt change region meet preset conditions.
6. The foreign object detection method according to claim 1, characterized in that, The process of obtaining foreign object detection results based on the grayscale distribution features of the detected image includes: Foreign object detection results are obtained by using a foreign object recognition model to identify foreign objects based on the detected images; The foreign object recognition model is obtained by training a machine learning model with training data, and the training dataset includes a set of detected images labeled with foreign objects.
7. The foreign object detection method according to claim 1, characterized in that, The laminated material includes: a positive electrode material layer, a negative electrode material layer, and a membrane layer that insulatingly separates the positive electrode material layer and the negative electrode material layer.
8. A computer device, characterized in that, include: Processor and memory; The memory stores computer programs or instructions; The processor is configured to run the computer program or instructions to perform the foreign object detection method as described in any one of claims 1 to 7.
9. A foreign object detection system for a wound battery, characterized in that, The wound battery is a structure formed by winding stacked materials; the system includes: An infrared light source is configured to emit infrared light to illuminate the area of the laminated material to be inspected. An imaging device is configured to receive the reflected light of the infrared light and image it to obtain a detection image; The processing device, connected to the imaging device, is configured to obtain foreign object detection results based on the grayscale distribution characteristics of the detection image; wherein, the protrusion formed by the foreign object pressing against its outer material will appear as a grayscale abrupt change region in the detection image.
10. The foreign object detection system according to claim 9, characterized in that, The wavelength range of the infrared light source is 750~1400nm; And / or, The infrared light source and imaging device are arranged in at least one of the following locations: 1) The position settings correspond to the conveying of the laminated material before winding; 2) The position is set according to the circumferential passage of the semi-finished battery cell during winding; 3) The testing area is set up to correspond to the area where the battery cell to be tested is placed.