Lithium battery shell surface quality detection method, clamp and system for mobile phone

Abstract

The invention relates to the technical field of lithium batteries, in particular to a lithium battery shell surface quality detection method, clamp and system for a mobile phone. The method is applied to a system comprising a clamp and a shooting assembly, the clamp is provided with a pressure detection device, and the method comprises the following steps: acquiring a pressure data sequence of the clamp when a lithium battery is clamped based on the pressure detection device; a lithium battery grey-scale map is obtained through a shooting assembly, and the incidence relation between the grey-scale map of a single lithium battery and the corresponding pressure data sequence is established; analyzing the improper pressure of the clamp of the lithium battery based on the incidence relation, and analyzing the texture covering condition in the grey-scale map of the lithium battery according to the improper pressure of the clamp, so as to calculate the information covering degree of the lithium battery; and setting a judgment threshold according to the information covering degree, marking the detection result exceeding the threshold as a doubt detection result, and re-detecting the lithium battery corresponding to the doubt detection result. According to the invention, the false detection rate of lithium battery shell surface quality detection is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of lithium battery, in particular to a lithium battery shell surface quality detection method, clamp and system for mobile phones. BACKGROUND

[0002] The lithium battery shell of a mobile phone refers to the shell of an aluminum-plastic composite film soft package battery or the metal shell of a hard shell battery, which wraps the lithium battery inside to achieve the goal of protecting the lithium battery. In order to more conveniently and quickly monitor the shell of the lithium battery, a lithium battery automatic detection device is usually configured, which uses a cylinder suction cup to adsorb the lithium battery on the product line to achieve automatic feeding, and then transfers the lithium battery to a clamp to fix the lithium battery, and transfers the lithium battery to a CCD camera through a turntable for vertical image shooting and intelligent quality detection.

[0003] In the actual process, when the lithium battery adsorbed by the cylinder suction cup is transferred to the clamp, due to improper operation, wear of the built-in spring of the clamp and other factors, the lithium battery may not be completely clamped against the clamp, resulting in a certain degree of inclination of the surface of the lithium battery, the actual loss (hidden) of part of the image information of the surface of the lithium battery shell by the CCD camera, and the possibility of misjudgment of the result of the quality detection of the surface of the lithium battery shell, thereby reducing the reliability of the result of the quality detection of the surface of the lithium battery shell. SUMMARY

[0004] In order to solve the technical problem that the result of the quality detection of the surface of the lithium battery shell may be misjudged, the purpose of the present application is to provide a lithium battery shell surface quality detection method, clamp and system for mobile phones, and the technical solution adopted is as follows: In a first aspect, the present application provides a lithium battery shell surface quality detection method for mobile phones, which comprises the following steps: A lithium battery shell surface quality detection method for mobile phones is applied to a system comprising a clamp and a shooting assembly, wherein the clamp is provided with a pressure detection device, and the method comprises the following steps: Obtaining a pressure data sequence of the clamp when the lithium battery is clamped based on the pressure detection device; Obtaining a gray scale image of the lithium battery through the shooting assembly, and establishing an association between the gray scale image of a single lithium battery and the corresponding pressure data sequence; Analyzing the improper pressure of the clamp of the lithium battery based on the association, and analyzing the texture masking condition in the gray scale image of the lithium battery according to the improper pressure of the clamp, so as to calculate the information masking degree of the lithium battery; Setting a judgment threshold according to the information masking degree, marking the detection result exceeding the judgment threshold as a suspicious detection result, and re-detecting the lithium battery corresponding to the suspicious detection result.

[0005] In some embodiments, the clamp pressure unsuitability of the lithium battery is analyzed based on the correlation relationship, including: segmenting the pressure data sequence to obtain a plurality of pressure fluctuation segments; curve fitting each pressure fluctuation segment to filter out the pressure fluctuation segment with a negative slope as a clamp closing stage; calculating pressure driving for each clamp closing stage, and determining an ideal detection interval according to the pressure data sequence; combining the ideal detection interval and the pressure driving to calculate the clamp pressure unsuitability of the lithium battery.

[0006] In some embodiments, the texture masking situation in the lithium battery grayscale image is analyzed, including: performing preliminary defect detection on the lithium battery grayscale image using a preset defect recognition model; if the detection result is that there is a defect, removing the texture edge identified as a defect from the lithium battery grayscale image with the defect, retaining the texture not identified as a defect, and taking the processed texture as the to-be-analyzed texture of the corresponding lithium battery grayscale image; if the detection result is that there is no defect, taking all textures in the lithium battery grayscale image without defects as the to-be-analyzed texture of the corresponding lithium battery grayscale image.

[0007] In some embodiments, the information masking degree of the lithium battery is calculated, including: statistically processing the minimum distances between the to-be-analyzed textures and performing normalization processing, and determining the to-be-analyzed texture corresponding to the normalized value meeting a preset condition as a suspected masking texture; performing linear fitting on the suspected masking texture and calculating texture deviation difference, combining the clamp pressure unsuitability and the minimum distance to judge the masking possibility between the suspected masking textures; filtering out the suspected masking texture corresponding to the masking possibility meeting a preset standard as an initial masking texture, and calculating a texture occlusion degree based on the angle relationship between the initial masking texture and the edge of the lithium battery; combining the texture occlusion degree and the lithium battery grayscale image to calculate the information masking degree of the lithium battery.

[0008] In some embodiments, further comprising: placing the lithium battery corresponding to the suspicious detection result on the clamp again and adjusting the clamp to a standard clamping state; reacquiring the lithium battery grayscale image and calculating the information masking degree of the lithium battery again; if the information masking degree calculated again still exceeds the determination threshold, determining that the corresponding lithium battery is unqualified.

[0009] In some embodiments, further comprising: constructing a mapping relationship between each lithium battery model and the corresponding optimal detection parameters based on historical detection data; When the lithium battery model to be detected is changed, the system automatically calls the optimal detection parameters corresponding to the lithium battery model to be detected; If the lithium battery model to be detected is a new model, detection is performed based on initial parameters and the detection parameter library is updated in real time.

[0010] In some embodiments, further comprising: The detection data of the lithium battery is summarized according to the production batch; The average information masking degree, and / or defect occurrence rate, and / or re-inspection qualified rate of each batch are calculated, and the quality fluctuation between batches is identified through a control chart analysis method, and when the fluctuation exceeds a preset control threshold, a quality anomaly analysis report is generated and the production process parameters of the corresponding production batch are associated.

[0011] In some embodiments, further comprising: After obtaining the gray scale image of the lithium battery, the identified defects are classified through a pre-trained deep learning model, wherein the defect types include scratches, and / or depressions, and / or stains, and / or deformations; Each defect type is classified according to a preset defect severity grading standard, and finally a detection report containing the defect type, the location of the defect, and the severity is output and stored.

[0012] In a second aspect, the embodiments of the present application provide a clamp, comprising: A clamp body for clamping a lithium battery; A pressure detection device mounted on the clamp body for real-time detection and recording of pressure data when the lithium battery is clamped; A data transmission module connected to the pressure detection device for transmitting pressure data to a processing unit.

[0013] In a third aspect, the embodiments of the present application provide a lithium battery shell surface quality detection system for mobile phones, which is applied to a system comprising a clamp and a shooting assembly, wherein the clamp is provided with a pressure detection device, and the system comprises the following modules: An acquisition module for acquiring a pressure data sequence of the clamp when the lithium battery is clamped based on the pressure detection device; An establishment module for acquiring a gray scale image of the lithium battery through the shooting assembly and establishing an association between the gray scale image of a single lithium battery and the corresponding pressure data sequence; A calculation module for analyzing the improper nature of the clamp pressure of the lithium battery based on the association, and analyzing the texture masking in the gray scale image of the lithium battery according to the improper nature of the clamp pressure of the lithium battery, so as to calculate the information masking degree of the lithium battery. The marking module is configured to set a judgment threshold according to the information masking degree, and mark a detection result exceeding the judgment threshold as a suspicious detection result, and re-detect the lithium battery corresponding to the suspicious detection result.

[0014] In a fourth aspect, an electronic device is provided, including a memory and a processor, the memory stores executable code, and the processor executes the executable code to implement the embodiments of each possible implementation of the first aspect.

[0015] In a fifth aspect, a computer program product is provided, which includes computer program code, and when the computer program code is executed on a computer, the computer executes the method in the first aspect or any one of the possible implementation manners of the first aspect.

[0016] In a sixth aspect, a computer readable storage medium is provided, which stores a computer program, and when the computer program is executed in a computer, the computer executes the embodiments of each possible implementation of the first aspect.

[0017] The embodiments of the present application have at least the following beneficial effects: The present application fuses the real-time data of the pressure detection device and the shooting assembly, constructs a pressure data-gray scale image dynamic correlation model, accurately identifies the surface defect masking problem caused by abnormal clamp pressure (such as shell deformation caused by excessive pressure or contact blur caused by insufficient pressure) by using an information masking degree quantification algorithm, and effectively reduces the false detection rate of lithium battery shell surface quality detection. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor based on these drawings.

[0019] Figure 1 A method flowchart of a lithium battery shell surface quality detection method for a mobile phone provided by an embodiment of the present application; Figure 2 A system block diagram of a lithium battery shell surface quality detection system for a mobile phone provided by an embodiment of the present application; Figure 3 A structural schematic diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to further clarify the technical means and effects taken by the present application to achieve the predetermined object of the application, the following describes in detail the specific implementation, structure, features and effects of the method, clamp and system for detecting the surface quality of a lithium battery shell for a mobile phone according to the present application in combination with the accompanying drawings and preferred embodiments.

[0021] In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0022] In the description of embodiments of the present application, unless otherwise specified, " / " represents the meaning of or, for example, A / B can represent A or B: "and / or" in the text only describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which means that there are three cases of A alone, A and B together, and B alone. In addition, in the description of embodiments of the present application, "multiple" means two or more than two.

[0023] Hereinafter, the terms "first", "second" are only used for descriptive purposes, and cannot be understood as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more features.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by a person skilled in the art to which the present application belongs.

[0025] The embodiments of the present application are described below in combination with the accompanying drawings. Those skilled in the art can know that with the development of technology and the appearance of new scenes, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0026] The specific scheme of the method for detecting the surface quality of a lithium battery shell for a mobile phone, the clamp and the system provided by the present application is described in detail below in combination with the accompanying drawings.

[0027] Please refer to Figure 1 which shows the step flowchart of the method for detecting the surface quality of a lithium battery shell for a mobile phone provided by an embodiment of the present application. The method of the present embodiment is applied to a system comprising a clamp and a shooting assembly, wherein the clamp is provided with a pressure detection device. The method comprises the following steps: S10. Obtain the pressure data sequence of the clamp when the lithium battery is clamped based on the pressure detection device.

[0028] The method of the embodiment is applied to a system comprising a clamp and a shooting assembly. In actual application, a pressure detection device (e.g., a pressure sensor) is installed at the bottom of the clamp. When a lithium battery is put into the clamp, the measurement is started at a preset frequency (e.g., 0.5 seconds / time), and the measured clamp pressure data is recorded in real time until the lithium battery stops recording after the image is collected by the shooting assembly (e.g., a Charge-Coupled Device Camera (CCD)), and the sequence of pressure data is taken as the pressure data sequence of the lithium battery, thereby completing the clamping stage of the lithium battery.

[0029] S11. Obtain a lithium battery grayscale image through the shooting assembly, and establish an association between the single lithium battery grayscale image and the corresponding pressure data sequence.

[0030] Further, the clamp with the lithium battery is moved (e.g., through a turntable or a conveyor belt or other means) to below the pre-installed CCD camera. The CCD camera detects the object and takes an image, thereby obtaining the corresponding lithium battery grayscale image. The detected lithium battery corresponding pressure data sequence and the lithium battery grayscale image are uniformly transmitted to the built-in computing chip.

[0031] Each lithium battery corresponds to a lithium battery grayscale image and a pressure data sequence.

[0032] S12. Analyze the clamp pressure irregularity of the lithium battery based on the association, and analyze the texture masking condition in the lithium battery grayscale image according to the clamp pressure irregularity, thereby calculating the information masking degree of the lithium battery.

[0033] In some embodiments, the analysis of the clamp pressure irregularity of the lithium battery based on the association comprises: Segmenting the pressure data sequence to obtain a plurality of pressure fluctuation segments; Curve fitting is performed on each pressure fluctuation segment, and the pressure fluctuation segment with a negative slope is selected as the clamp closing stage; The pressure pushing property is calculated for each clamp closing stage, and the ideal detection interval is determined according to the pressure data sequence; The clamp pressure irregularity of the lithium battery is calculated in combination with the ideal detection interval and the pressure pushing property.

[0034] In normal circumstances, the lithium battery automatic detection equipment will be connected with the lithium battery produced on the production line, so that the whole production process of the lithium battery forms an industrial automation operation. Therefore, when the lithium battery is detected by the lithium battery automatic detection equipment, since the quality detection of different lithium batteries by the CCD is consistent, in normal circumstances, different lithium batteries will be image collected at a relatively fixed time interval, and the corresponding pressure state of the clamp will also be basically consistent; but if the clamp is not clamped properly, the clamp will usually need more time to adjust when clamping the lithium battery, so that the lithium battery will not be broken away from the clamp, and the stress state formed by the contact between the clamp and the lithium battery will be more fluctuant. Therefore, according to the pressure data of the clamp, the improperness of the clamp pressure of the corresponding lithium battery can be analyzed when the lithium battery is image monitored under the CCD camera.

[0035] Specifically, if the lithium battery is not completely clamped with the clamp, it means that there is a certain inclined space between the lithium battery and the horizontal surface of the clamp, which will change the original horizontal extrusion balance state of the two sides of the clamp in contact with the edge of the lithium battery into an incomplete horizontal extrusion balance state. During the process of transferring the lithium battery under the CCD camera, the clamp may gradually push the lithium battery over time, and the pressure detected by the clamp will decrease: Taking any lithium battery as an example, in the actual process, the process of pushing the clamp is usually intermittent: in the clamp pressure sequence of the lithium battery, the combination of the clamp pressure data whose adjacent slope change is greater than a preset value (for example, 0.6) is regarded as a clamp pressure data division section; and the center of the clamp pressure data division section (between two clamp pressure data) is regarded as a section point, so as to segment the clamp pressure sequence and obtain a plurality of clamp pressure fluctuation sections.

[0036] Further, the curve fitting is performed on each clamp pressure fluctuation section to obtain a plurality of pressure fluctuation curves; the clamp pressure fluctuation section with a negative curve slope is regarded as a clamp closing stage. Each clamp pressure fluctuation section corresponds to a pressure fluctuation curve, and each lithium battery corresponds to a plurality of clamp closing stages.

[0037] Further, the formula for calculating the pressure pushing property A of each clamp closing stage is: ; Wherein represents the difference value of the initial and final clamp pressure data in each clamp closing stage. The greater the pressure pushing property, the greater the pushing pressure of the lithium battery in the corresponding clamp closing stage.

[0038] Meanwhile, in an industrial environment, each lithium battery typically undergoes image acquisition at a fixed frequency (due to identical operating procedures and the absence of abnormalities). Under normal circumstances, if the lithium battery clamp is improperly held, the battery may detach from the clamp before being transferred to image acquisition, thus affecting the progress of quality inspection. Therefore, if the lithium battery clamp is improperly held, the clamping plates are usually released, and the lithium battery is re-adsorbed and clamped using a cylinder suction cup before continuing image acquisition for the corresponding lithium battery. In summary, based on pressure-driven characteristics, the distribution of acquisition time among lithium batteries can be analyzed to calculate the improper clamping pressure for the corresponding lithium battery. Prior to this lithium battery, a lithium battery that has not been repositioned is considered an ideal operating lithium battery; the average length L of the clamp pressure sequence of the ideal operating lithium battery is taken as the ideal detection interval T.

[0039] It should be noted that for the same lithium battery, if its position has been readjusted, the corresponding process will be recorded in the clamp pressure sequence. Therefore, for a lithium battery, regardless of whether its position has been readjusted by the cylinder suction cup, its corresponding pressure data sequence will record the clamp pressure data during the corresponding process.

[0040] According to the ideal detection interval Pressure-driven Calculate the improper clamping pressure of the lithium battery. : in, This indicates the length of the clamp pressure sequence for the lithium battery; This indicates the total number of clamp closing stages included in the clamp pressure sequence of the lithium battery; Indicates the first The pressure driving force during the clamping stage; Indicates the first The duration of the clamp closing phase. This indicates the delay caused by the lithium battery in the normal image acquisition process. The larger the value, the more likely the lithium battery is to be affected by improper clamping in the subsequently acquired images. This indicates the degree to which the lithium battery may actually be pushed by the clamp. The higher the value, the more likely the lithium battery is to undergo actual positional movement. Greater clamping pressure inconsistency indicates a higher likelihood of actual positional movement of the lithium battery, and the more likely the effects of clamping inconsistency will be present in subsequently acquired images.

[0041] In some embodiments, the analysis of texture occlusion in the grayscale image of the lithium battery includes: A pre-defined defect identification model is used to perform preliminary defect detection on the grayscale image of the lithium battery. If the detection result is that there is a defect, the texture edge identified as a defect in the gray-scale image of the lithium battery with the defect is removed, the texture not identified as a defect is retained, and the processed texture is taken as the texture to be analyzed corresponding to the gray-scale image of the lithium battery; If the detection result is that there is no defect, all textures in the gray-scale image of the lithium battery without the defect are taken as the texture to be analyzed corresponding to the gray-scale image of the lithium battery.

[0042] In some embodiments, the information hiding degree of the lithium battery is calculated, including: The minimum distance between the textures to be analyzed is counted and normalized, and the texture to be analyzed corresponding to the normalized value meeting the preset condition is determined as a suspected hidden texture; The suspected hidden texture is subjected to linear fitting and calculation of texture deviation difference, and the hiding possibility between the suspected hidden textures is judged in combination with the improper clamp pressure and the minimum distance; The suspected hidden texture corresponding to the hiding possibility meeting the preset standard is selected as an initial hidden texture, and the texture hiding degree is calculated based on the angle relationship between the initial hidden texture and the edge of the lithium battery; The information hiding degree of the lithium battery is calculated in combination with the texture hiding degree and the gray-scale image of the lithium battery.

[0043] In actual scenarios, the phenomenon of clamp moving and closing is usually not obvious even if it actually exists, and it is not possible to visually observe whether the lithium battery is clamped firmly, while the improper clamp pressure calculated through the above steps starts from the pressure fluctuation state of the clamp itself before image acquisition by the CCD camera. Although it can reflect the abnormal situation of the clamp when clamping the lithium battery to a certain extent (i.e., improper clamping), since the effect is ultimately presented on the image (because not all improper clamping situations will affect the final quality detection result of the lithium battery shell, and some improper clamping states are not sufficient to cause identification interference to the image collected by the CCD camera), it is not advisable to use only the improper clamp pressure to reflect the situation that the final lithium battery image is disturbed by improper clamping. It is necessary to consider the effect of the corresponding lithium battery in the photographed image to make a comprehensive judgment.

[0044] In the actual shooting of the lithium battery gray scale image, the improper clamping interferes with the identification of the defects of the lithium battery gray scale image. The improper clamping is that the lithium battery is not completely clamped by the clamp, so that there is a certain amount of inclined space between the lithium battery and the clamp. When the CCD camera shoots the image, the angle of view of the CCD camera is not completely perpendicular to the surface of the lithium battery shell, so that the image information of part of the surface of the lithium battery shell is actually lost (hidden). Other improper clamping conditions (such as placing the lithium battery upside down) will not interfere with the normal collection of image information of the surface of the lithium battery shell. If there is a certain amount of inclined space between the lithium battery and the clamp, the image information of the surface of the lithium battery shell collected by the CCD camera will be hidden, resulting in the breakage of part of the texture on the original surface of the lithium battery shell. Therefore, based on the improper clamping pressure, the texture masking condition in the corresponding lithium battery gray scale image can be analyzed to calculate the information masking degree of the corresponding lithium battery. Since the texture masking condition in the lithium battery gray scale image may be affected by the traditional detection result, it is necessary to first consider excluding the interference of the traditional detection result on the texture masking lithium. Taking the lithium battery gray scale image of any lithium battery as an example, the existing defect identification model is used to detect defects in the lithium battery gray scale image. The use method of such a defect identification model is a technology known to those skilled in the art, and will not be described here.

[0045] If the detection result is an image with defects: remove the texture edges identified as defects in the lithium battery gray scale image, retain the textures not identified as defects (for example, the textures can be identified by an edge detection algorithm), and use them as the textures to be analyzed in the lithium battery gray scale image.

[0046] If the detection result is an image without defects: all textures in the lithium battery gray scale image are used as the textures to be analyzed in the lithium battery gray scale image.

[0047] The textures to be analyzed obtained through the above steps can determine the objects suitable for analyzing texture breakage masking, and then calculate the texture masking degree of the lithium battery gray scale image: Calculate the minimum distance D between different (two) textures; the texture corresponding to the normalized value of the minimum distance D less than a preset value (for example, 0.3) is used as the suspected masking texture of the lithium battery gray scale image.

[0048] A straight line is fitted for each suspected masking texture to obtain the fitting straight line of each suspected masking texture.

[0049] Place the fitting straight lines of different suspected masking textures at the corresponding positions in the lithium battery gray scale image, draw the extension lines on the respective fitting straight lines, and use the included angle formed by different extension lines as the texture deviation difference p between different suspected masking textures.

[0050] According to the texture bias difference , minimum distance , clamp pressure inappropriateness , calculate the masking possibility between different suspected masking textures , wherein norm represents a normalization function. The larger the value, the more coherent and reasonable the overall change state of the texture formed after the simulation docking between the corresponding suspected masking textures, and the more likely the corresponding suspected masking textures are masked. In the embodiments of the present application, the normalization function can use the maximum and minimum value normalization function.

[0051] Since the textures distributed on the surface of the conventional lithium battery shell are usually regularly distributed, when part of the textures is blocked due to the inclination of the lithium battery, the information of this part of the blocked part will be overall masked in a certain edge direction of the lithium battery due to the formation of the inclination direction: The suspected masking texture with a masking possibility greater than a preset value (for example, 0.7) is taken as the initial masking texture; and the minimum circumscribed rectangle of the overall area occupied by the initial masking texture is taken as the initial masking distribution area of the lithium battery.

[0052] The angles between the lengths of the initial masking distribution area and the four edges of the lithium battery are calculated, and the reciprocal value of the minimum angle is taken as the texture blocking degree K of the lithium battery grayscale image. The larger the value, the more the area distribution of the possible masking texture in the lithium battery grayscale image conforms to the masking distribution state formed when the lithium battery is inclined; and the more likely the masking information exists in the lithium battery grayscale image.

[0053] In addition, when the lithium battery is inclined, the size of the lithium battery itself in the corresponding lithium battery grayscale image will be reduced to a certain extent, so the analysis of the size change of the lithium battery can be added on the basis of the texture blocking degree, and finally the information masking degree of the corresponding lithium battery is obtained : , wherein represents the difference between the area of the lithium battery in the lithium battery grayscale image of the lithium battery and the standard area of the same model lithium battery stored in the database. The larger the information masking degree, the more likely the lithium battery is to be inclined due to improper clamping of the clamp, and the more information is blocked in the lithium battery grayscale image obtained by the CCD camera, and the greater the interference with the surface quality detection of the lithium battery shell.

[0054] S13. According to the information masking degree, set a decision threshold (for example, 0.4), and mark the detection result exceeding the decision threshold as a suspicious detection result. The lithium battery corresponding to the suspicious detection result is re-detected.

[0055] In some embodiments, further comprising: The lithium battery corresponding to the suspicious detection result is placed in the clamp again, and the clamp is adjusted to the standard clamping state; The gray image of the lithium battery is acquired again, and the information masking degree of the lithium battery is calculated again; If the information masking degree calculated again is still greater than the determination threshold, it is determined that the corresponding lithium battery is unqualified.

[0056] In some embodiments, further comprising: Based on historical detection data, a mapping relationship between each lithium battery model and corresponding optimal detection parameters is constructed; When the lithium battery model to be detected is changed, the system automatically calls the optimal detection parameters corresponding to the lithium battery model to be detected; If the lithium battery model to be detected is a new model, detection is performed based on initial parameters, and the detection parameter library is updated in real time.

[0057] In actual application, a mapping relationship library between lithium battery models and optimal detection parameters can be constructed, and the detection parameters can include imaging exposure time, light source intensity, image processing threshold, etc. Specifically, decision tree algorithm (such as Classification and Regression Tree (CART)) can be used to analyze historical detection data to generate parameter-model association rules (such as if model=A→exposure time=20ms, light source intensity=80%). Then, the model of the lithium battery to be detected is read by a barcode scanner or Radio Frequency Identification (RFID), and the system automatically calls the corresponding optimal parameters from the parameter library and configures the detection equipment.

[0058] If the detection model is a new model (no record in the parameter library), the default initial parameters (such as exposure time=15ms) are used for detection, and the detection results (such as defect types) are recorded in real time. Online learning algorithm (such as incremental Support Vector Machine (SVM)) is used to gradually optimize the parameters of the new model, and the parameter library is updated every N times of detection (N is a preset learning sample size).

[0059] In some embodiments, further comprising: The detection data of the lithium battery is summarized according to production batches; The average information masking degree, and / or defect occurrence rate, and / or re-inspection qualified rate of each batch are calculated, and the quality fluctuation between batches is identified through control chart analysis method, when the fluctuation exceeds the preset control threshold, a quality abnormality analysis report is generated and the production process parameters corresponding to the production batch are associated.

[0060] Specifically, the production batch aggregation detection data includes defect type and location information of each lithium battery. The batch data can be stored in a time series database to support quick query according to a time range. Further, the average information masking degree, defect occurrence rate (defect sample number / total sample number) and re-inspection qualified rate (second detection qualified number / first detection unqualified number) of the batch are calculated.

[0061] Further, the X-bar control chart (monitoring the average information masking degree) or P control chart (monitoring the defect occurrence rate) can be drawn by integrating Minitab or the stats models library of Python, and when the index exceeds the control threshold (such as ±3σ, wherein σ represents the standard deviation), a quality abnormality report is generated.

[0062] In some embodiments, further comprising: After obtaining the gray image of the lithium battery, the identified defects are classified by a pre-trained deep learning model, wherein the defect types include scratches, and / or depressions, and / or stains, and / or deformations. Each defect type is graded according to a preset defect severity grading standard, and finally a detection report containing the defect type, defect location and severity is output and stored.

[0063] Specifically, the deep learning model (such as ResNet-50) can be trained based on a pre-labeled defect image dataset (containing four types of scratches, depressions, stains and deformations (additional defect types can be added according to actual needs)). The model training is realized using the PyTorch framework, and the data enhancement strategies include rotation, flipping and noise injection, etc. Further, the collected gray image of the lithium battery is input into the trained model to output the defect type and location (annotated by a bounding box). Finally, the defects are graded according to the preset grading standard (such as scratches longer than 5mm are severe, 2-5mm are moderate, and <2mm are slight), a JSON format report containing the type, location and grading is generated, and stored in the database for traceability.

[0064] The embodiment of the present application provides a clamp, comprising: A clamp body for clamping a lithium battery; A pressure detection device mounted on the clamp body for real-time detection and recording of pressure data when the lithium battery is clamped; A data transmission module connected with the pressure detection device for transmitting the pressure data to a processing unit.

[0065] Embodiment two: Please refer to Figure 2As shown in the figure, the embodiment of the present application provides a lithium battery shell surface quality detection system for mobile phones, which is applied to a system including a clamp and a shooting assembly, the clamp is provided with a pressure detection device, and the system includes the following modules: An acquisition module 20 is configured to acquire a pressure data sequence of the clamp when the lithium battery is clamped based on the pressure detection device; An establishment module 21 is configured to acquire a gray scale image of the lithium battery through the shooting assembly and establish an association between the gray scale image of the single lithium battery and the corresponding pressure data sequence; A calculation module 22 is configured to analyze the clamp pressure improperness of the lithium battery based on the association, analyze the texture masking in the gray scale image of the lithium battery according to the clamp pressure improperness, and calculate the information masking degree of the lithium battery; A marking module 23 is configured to set a judgment threshold according to the information masking degree, mark the detection result exceeding the judgment threshold as a suspicious detection result, and re-detect the lithium battery corresponding to the suspicious result.

[0066] Optionally, the transmission medium can be a wired link such as, but not limited to, a coaxial cable, an optical fiber, a digital subscriber line, etc., or a wireless link such as, but not limited to, a wireless fidelity (WIFI), a Bluetooth, a mobile device network, etc.

[0067] It should be noted that the device provided in the above embodiment is only exemplified by the division of the above functional modules, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above.

[0068] Figure 3 is a structural schematic diagram of a computer device provided by the embodiment of the present application. As shown in the figure, Figure 3 the computer device 30 includes a memory 31, a processor 32, and a computer program 33 stored in the memory 31 and running on the processor 32, wherein when the processor 32 executes the computer program 33, the computer device can execute any of the above-mentioned lithium battery shell surface quality detection methods for mobile phones.

[0069] In addition, the embodiment of the present application also protects a device, which can include a memory and a processor, wherein the memory stores executable program code, and the processor is configured to call and execute the executable program code to execute the lithium battery shell surface quality detection method for mobile phones provided by the embodiment of the present application.

[0070] The embodiment of the present application can divide the functions of the device according to the above method examples, for example, each function module can be obtained, two or more functions can be integrated in one processing module, and the integrated module can be realized in the form of hardware. It should be noted that the division of the modules in the embodiment is illustrative, and is only a logical function division. In actual implementation, another division mode can be used.

[0071] It should be understood that the device provided by the embodiment of the present application is used to execute the above-mentioned method for detecting the surface quality of the lithium battery shell of the mobile phone, and thus the same effect as the above-mentioned implementation method can be achieved.

[0072] In the case of using an integrated unit, the device can include a processing module and a storage module. When the device is applied to equipment, the processing module can be used to control and manage the actions of the equipment. The storage module can be used to support the equipment to execute mutual program codes and the like. The processing module can be a processor or a controller, which can realize or execute various exemplary logical blocks, modules and circuits described in combination with the disclosure of the present application. The processor can also be a combination of computing functions, such as one or more microprocessor combinations, a combination of digital signal processing (Digital Signal Processing, DSP) and microprocessors, and the like. The storage module can be a memory.

[0073] In addition, the device provided by the embodiment of the present application can be a chip, an assembly or a module. The chip can include a connected processor and a memory. The memory is used to store instructions. When the processor calls and executes the instructions, the chip can execute the above-mentioned method for detecting the surface quality of the lithium battery shell of the mobile phone provided by the embodiment.

[0074] The embodiment of the present application also provides a computer readable storage medium, which stores computer program codes. When the computer program codes run on a computer, the computer executes the above-mentioned related method steps to realize the above-mentioned method for detecting the surface quality of the lithium battery shell of the mobile phone provided by the embodiment.

[0075] The embodiment of the present application also provides a computer program product. When the computer program product runs on a computer, the computer executes the above-mentioned related steps to realize the above-mentioned method for detecting the surface quality of the lithium battery shell of the mobile phone provided by the embodiment.

[0076] Among them, the device, computer readable storage medium, computer program product or chip provided by the embodiment of the application are used to execute the corresponding method provided above, so the beneficial effects that can be achieved are referred to the beneficial effects of the corresponding method provided above, which will not be repeated here. Through the description of the above implementation mode, those skilled in the art can understand that, for the convenience and brevity of description, only the above-mentioned division of functional modules is taken as an example, and in actual application, the above-mentioned functions can be completed by different functional modules according to the needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In the embodiments provided by the application, it should be understood that the disclosed device and method can be implemented in other ways.

[0077] The device embodiment described above is only schematic, for example, the division of modules or units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed each other can be indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0078] It should be further understood that the terms "comprise", "comprise", or any other variant thereof are intended to cover non-exclusive inclusion, so that processes, methods, articles or terminal devices including a series of elements not only include those elements, but also include other elements not explicitly listed or inherent to such processes, methods, articles or terminal devices. Without more limitations, the element defined by the statement "comprises a" does not exclude the presence of additional identical elements in the process, method, article or terminal device comprising the element.

[0079] It should be noted that: the above-mentioned sequence of the embodiments of the application is only for description, not representing the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0080] Each embodiment in the specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other, and each embodiment mainly describes the difference from other embodiments.

[0081] The above merely illustrates the specific embodiments of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application.

Claims

1. A method for detecting surface quality of a lithium battery case for a mobile phone, characterized in that, Applied to a system including a clamp and a shooting assembly, wherein the clamp is equipped with a pressure detection device, the method includes the following steps: The pressure data sequence of the clamp when the lithium battery is clamped is obtained based on the pressure detection device; The imaging component acquires a grayscale image of the lithium battery and establishes a correlation between the grayscale image of a single lithium battery and the corresponding pressure data sequence. Based on the aforementioned correlation, the improper clamping pressure of the lithium battery is analyzed, and based on the improper clamping pressure, the texture occlusion in the grayscale image of the lithium battery is analyzed, thereby calculating the degree of information occlusion of the lithium battery. A judgment threshold is set based on the degree of information obfuscation. Detection results that exceed the judgment threshold are marked as suspicious detection results, and the lithium batteries corresponding to the suspicious detection results are re-detected.

2. The method for detecting surface quality of a lithium battery case for a mobile phone according to claim 1, wherein The analysis of improper clamping pressure of lithium batteries based on the aforementioned correlation includes: The pressure data sequence is segmented to obtain several pressure fluctuation segments; Curve fitting is performed on each of the pressure fluctuation segments, and the pressure fluctuation segments with negative slopes are selected as the clamp closing stage. The pressure driving force is calculated for each clamp closing stage, and the ideal detection interval is determined based on the pressure data sequence; The improper clamping pressure of the lithium battery is calculated by combining the ideal detection interval and the pressure driving force.

3. The method for detecting surface quality of a lithium battery case for a mobile phone according to claim 1, wherein The analysis of texture occlusion in the grayscale image of the lithium battery includes: A pre-defined defect identification model is used to perform preliminary defect detection on the grayscale image of the lithium battery. If the detection result indicates the presence of defects, the texture edges identified as defects in the grayscale image of the lithium battery with defects will be removed, while the textures not identified as defects will be retained, and the processed textures will be used as the textures to be analyzed in the corresponding grayscale image of the lithium battery. If the detection result indicates that there are no defects, then all textures in the grayscale image of the lithium battery without defects will be used as the textures to be analyzed in the corresponding grayscale image of the lithium battery.

4. The method for detecting surface quality of a lithium battery case for a mobile phone according to claim 3, wherein The calculation of the information masking degree of the lithium battery includes: The minimum distance between the textures to be analyzed is calculated and normalized. The textures to be analyzed that meet the normalized values ​​are identified as suspected occlusion textures. The suspected occlusion textures are fitted with straight lines and the texture bias difference is calculated. The occlusion probability between the suspected occlusion textures is determined by combining the improper clamp pressure with the minimum distance. Select the suspected occlusion textures that meet the preset criteria as the initial occlusion textures, and calculate the degree of texture occlusion based on the angular relationship between the initial occlusion textures and the edge of the lithium battery. The degree of information masking of the lithium battery is calculated by combining the texture occlusion degree and the lithium battery grayscale image.

5. The method for detecting surface quality of a lithium battery case for a mobile phone according to claim 1, wherein Also includes: The lithium battery corresponding to the questionable test result is placed back into the fixture, and the fixture is adjusted to the standard clamping state; Re-acquire the grayscale image of the lithium battery and recalculate the degree of information masking of the lithium battery; If the degree of information obfuscation still exceeds the judgment threshold after recalculation, the corresponding lithium battery is deemed unqualified.

6. The method for detecting surface quality of a lithium battery case for a mobile phone according to claim 1, wherein Also includes: A mapping relationship between each lithium battery model and its corresponding optimal testing parameters was constructed based on historical testing data. When the lithium battery model to be tested is changed, the system automatically calls the optimal testing parameters corresponding to the lithium battery model to be tested; If the lithium battery model to be detected is a new model, detection is performed based on initial parameters and the detection parameter library is updated in real time.

7. The method for detecting surface quality of a lithium battery case for a mobile phone according to claim 1, wherein Also includes: The detection data of the lithium battery is summarized according to the production batch; The average information masking degree, and / or defect occurrence rate, and / or re-inspection qualified rate of each batch is calculated, and the quality fluctuation between batches is identified through control chart analysis method, when the fluctuation exceeds the preset control threshold, a quality abnormality analysis report is generated and the production process parameters of the corresponding production batch are associated.

8. The method for detecting surface quality of a lithium battery case for a mobile phone according to claim 1, wherein, Also includes: After obtaining the gray image of the lithium battery, the identified defects are classified through a pre-trained deep learning model, wherein the defect types include scratches, and / or depressions, and / or stains, and / or deformations; Each defect type is classified according to a preset defect severity grading standard, and finally a detection report containing the defect type, defect location and severity is output and stored.

9. A clamp characterized in that, Includes: A clamp body for clamping a lithium battery; A pressure detection device mounted on the clamp body for real-time detection and recording of pressure data when the lithium battery is clamped; A data transmission module connected to the pressure detection device for transmitting pressure data to a processing unit.

10. A surface quality inspection system for a lithium battery casing of a mobile phone, characterized in that, Applied to a system including a clamp and a shooting assembly, the clamp is provided with a pressure detection device, and the system includes the following modules: An acquisition module for acquiring pressure data sequence of the clamp when the lithium battery is clamped based on the pressure detection device; An establishment module for acquiring a gray image of the lithium battery through the shooting assembly and establishing an association between the gray image of a single lithium battery and the corresponding pressure data sequence; A calculation module for analyzing the improper nature of the clamp pressure of the lithium battery based on the association, and analyzing the texture masking in the gray image of the lithium battery according to the improper nature of the clamp pressure, so as to calculate the information masking degree of the lithium battery; A marking module for setting a decision threshold according to the information masking degree, marking the detection results exceeding the decision threshold as suspicious detection results, and re-detecting the lithium battery corresponding to the suspicious results.

Images