Battery cell installation accuracy judgment method, system and equipment and storage medium
By using image recognition technology to make multi-dimensional judgments on the number of battery cells, polarity arrangement, and placement angle, the problems of misjudgment and model adaptability caused by manual inspection are solved, enabling efficient and accurate detection of battery cell installation status and improving the flexibility and efficiency of battery module production.
Patent Information
- Application Number
- CN202511260777.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-04
- Publication Date
- 2025-12-12
AI Technical Summary
In current battery module production, the method of manually inspecting the installation position of battery cells is prone to visual fatigue and misjudgment. In addition, different models of modules require different tooling plates, which affects the flexibility and efficiency of the production line and makes it difficult to inspect the number of battery cells, polarity arrangement and placement angle under complex working conditions.
Image recognition technology is used to obtain the cell rectangle, polarity rectangle, and feature rectangle. The number of cells, polarity arrangement, and placement angle are progressively judged. Multi-dimensional comparison is used to determine the accuracy of cell installation, eliminating the need for manual inspection of the tooling board.
It improves the accuracy and efficiency of cell installation status identification, adapts to the testing needs of different module models, reduces design and manufacturing costs, and enhances production line flexibility.
Smart Images

Figure CN121120571A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of battery manufacturing, in particular to a battery cell installation accuracy determination method, system, device and storage medium. BACKGROUND
[0002] In the production and manufacturing process of the battery module, the accuracy of the battery cell installation position is one of the important parameter indexes affecting the overall performance of the module. Currently, the industrial production line generally uses manual visual detection combined with special tooling plate quality inspection method to test the installation quality of the battery cell.
[0003] The detection technology is based on the physical limiting principle of the mechanical tooling plate. The key feature parts of the battery cell to be detected are exposed by covering the surface of the module with a customized designed hollow tooling. The tooling plate is accurately mechanically aligned with the module by the detection personnel, and the position characteristics of the exposed part of the battery cell are visually observed to determine whether the installation accuracy of the battery cell number, the positive and negative electrode arrangement sequence and the battery cell placement angle meets the process specification requirements. This method requires accurate matching of the tooling plate and the specific model battery module, so each model of the module needs to be equipped with a special detection tooling.
[0004] However, manual detection through hollow tooling can easily cause visual fatigue and reduce the accuracy of judgment, resulting in missed detection, misjudgment and other quality risks. In addition, different models of modules require different tooling plates, which requires re-design of the tooling when switching to a new model or going online. This not only responds in a timely manner, but also increases the additional design and manufacturing costs, affecting the flexibility and efficiency of the production line, and making it difficult to detect the battery cell number, the positive and negative electrode arrangement sequence and the battery cell placement angle under complex working conditions. SUMMARY
[0005] Therefore, the purpose of the present application is to provide a battery cell installation accuracy determination method, system, device and storage medium, which progressively determines the battery cell number, the positive and negative electrode arrangement sequence and the battery cell placement angle, respectively, to determine the accuracy of the battery cell installation when all three conditions are met, without manual detection through tooling plates, so as to facilitate detection of the battery cell number, the positive and negative electrode arrangement sequence and the battery cell placement angle under complex working conditions.
[0006] To achieve the above object, in a first aspect, embodiments of the present application provide a method for judging installation accuracy of an electric core, the method comprising: obtaining an image of an electric core module to be detected, the image of the electric core module to be detected comprising a plurality of electric core rectangular frames, a plurality of electric core polarity rectangular frames and a plurality of electric core feature rectangular frames; the electric core polarity rectangular frame and the electric core feature rectangular frame corresponding to the same electric core being located within the electric core rectangular frame corresponding to the electric core; obtaining an electric core number based on the plurality of electric core rectangular frames, comparing the electric core number with a preset electric core number to obtain an electric core number comparison result; in a case where the electric core number comparison result represents a successful comparison, obtaining an electric core polarity arrangement order according to an arrangement order of the plurality of electric core polarity rectangular frames in the image of the electric core module to be detected; comparing the electric core polarity arrangement order with a preset electric core polarity arrangement order to obtain an electric core polarity comparison result; in a case where the electric core polarity comparison result represents a successful comparison, determining an orientation angle of the electric core polarity based on a direction of a line connecting the center of the electric core polarity rectangular frame within each electric core rectangular frame and the corresponding electric core feature rectangular frame and a length direction of the image of the electric core module to be detected, comparing the orientation angle with a preset electric core arrangement angle to obtain an electric core arrangement angle comparison result; and determining installation accuracy of the electric core in a case where the electric core arrangement angle comparison result represents a successful comparison.
[0007] In the present embodiment, the electric core number, the electric core polarity arrangement order and the electric core arrangement angle of the electric core module to be detected are obtained through the electric core rectangular frame, the electric core polarity rectangular frame and the electric core feature rectangular frame, so as to compare the electric core number, the electric core polarity arrangement order and the electric core arrangement angle with preset values respectively, compare the correct electric core module meeting the electric core number, the electric core polarity arrangement order and the electric core arrangement angle, and compare from the electric core number to the electric core polarity arrangement order and then to the electric core arrangement angle in the comparison process, so as to determine the installation accuracy of the electric core in a multi-dimensional progressive comparison without manual detection through a tooling plate, so as to detect the electric core number, the positive and negative electrode arrangement order of the electric core and the electric core arrangement angle in complex working conditions, and improve the accuracy of the identification of the installation state of the electric core in complex working conditions.
[0008] In some embodiments, the electric core polarity arrangement order is obtained according to the arrangement order of the plurality of electric core polarity rectangular frames in the image of the electric core module to be detected, which comprises: sorting the plurality of electric core polarity rectangular frames based on the horizontal coordinate and the vertical coordinate of the top left corner vertex of the electric core rectangular frame where each electric core polarity rectangular frame is located to obtain the electric core polarity arrangement order.
[0009] In this way, the electric core polarity arrangement order is ensured to be unique and repeatable, thereby providing an accurate basis for subsequent polarity order comparison and avoiding misjudgment due to inconsistent arrangement order.
[0010] In some embodiments, sorting multiple cell polarity rectangles based on the x-coordinate and y-coordinate of the top-left corner vertex of each cell polarity rectangle to obtain the cell polarity arrangement order includes: if the distance between the x-coordinate of the top-left corner vertex of the current cell polarity rectangle and the x-coordinate of the top-left corner vertex of the first cell polarity rectangle in the current column is less than a preset threshold, then the current cell polarity rectangle is included in the current column; the preset threshold is half the length of the cell polarity rectangle; if the distance between the x-coordinate of the top-left corner vertex of the current cell polarity rectangle and the x-coordinate of the top-left corner vertex of the first cell polarity rectangle in the current column is not less than the preset threshold, then the current cell polarity rectangle is included in the next column of the current column; for each cell polarity rectangle included in the same column, sorting each cell polarity rectangle according to the y-coordinate of the top-left corner vertex of each cell polarity rectangle to obtain the cell polarity arrangement order.
[0011] This setting, by setting a preset threshold of half the length of the cell rectangle, makes it easier to divide the cell rectangles that are close to the horizontal axis into a column, thereby facilitating the sorting of the cell polarity of multiple columns of cell rectangles to obtain the cell polarity arrangement order.
[0012] In some embodiments, before determining the orientation angle of the cell polarity based on the center line direction of the cell polarity rectangle and the corresponding cell feature rectangle within each cell rectangle and the length direction of the cell module image to be detected, the method further includes: for each cell polarity rectangle within each cell rectangle, taking the cell feature rectangle closest to the cell polarity rectangle as the cell feature rectangle corresponding to the cell polarity rectangle.
[0013] This setup, which binds each cell polarity rectangle to its corresponding cell feature rectangle, effectively avoids mismatches caused by image recognition errors or overlapping feature points, improves the accuracy of subsequent angle calculations, and thus enhances the stability of the entire discrimination system.
[0014] In some embodiments, determining the orientation angle of the cell polarity based on the direction of the center line connecting the cell polarity rectangle and the corresponding cell feature rectangle within each cell rectangle, and the length direction of the cell module image to be tested, includes: establishing a first vector based on the center point of the cell polarity rectangle and the center point of the corresponding cell feature rectangle; the first vector represents the direction and distance of the center line connecting the cell polarity rectangle and the corresponding cell feature rectangle; establishing a second vector based on the center point of the cell polarity rectangle and a preset standard point; the second vector represents the direction and distance of the line connecting the center point of the cell polarity rectangle and the preset standard point; the direction of the line connecting the center point of the cell polarity rectangle and the preset standard point is the same as the length direction of the cell module image to be tested, and the abscissa of the preset standard point is the same as the abscissa of the center point of the cell polarity rectangle; and determining the orientation angle of the cell polarity based on the first vector and the second vector.
[0015] This setup allows for the calculation of the orientation angle of each cell's polarity rectangle through the first and second vectors, which helps determine the cell's deflection angle and, consequently, whether the cell's placement angle is accurate, thus improving the accuracy of the judgment.
[0016] In some embodiments, the orientation angle of the cell polarity includes a first orientation and a second orientation. Determining the orientation angle of the cell polarity based on the first vector and the second vector includes: calculating a trigonometric function of the angle between the first vector and the second vector; comparing the trigonometric function with a preset value; if the trigonometric function is less than the preset value, then determining the cell placement angle as the first orientation; if the trigonometric function is not less than the preset value, then determining the cell placement angle as the second orientation.
[0017] This setup, which compares the trigonometric function value of the angle calculated by the first and second vectors with a set threshold to determine the orientation of the battery cell, has high repeatability and adaptability.
[0018] Secondly, embodiments of the present invention provide a battery cell installation accuracy discrimination system, the system comprising: an acquisition module, configured to acquire an image of a battery cell module to be tested, the image of the battery cell module to be tested including multiple battery cell rectangles, multiple battery cell polarity rectangles, and multiple battery cell feature rectangles; the battery cell polarity rectangle and the battery cell feature rectangle corresponding to the same battery cell are located within the battery cell rectangle corresponding to the same battery cell; a battery cell quantity comparison module, configured to acquire the number of battery cells based on the multiple battery cell rectangles, compare the number of battery cells with a preset number of battery cells, and obtain a battery cell quantity comparison result; and a battery cell polarity arrangement order comparison module, configured to, if the battery cell quantity comparison result indicates a successful comparison, determine the battery cell installation accuracy based on the multiple battery cell polarity rectangles in the image of the battery cell module to be tested. The cell polarity arrangement order is obtained by arranging the images of the cell module. The cell polarity arrangement order is compared with the preset cell polarity arrangement order to obtain the cell polarity comparison result. The cell placement angle comparison module is used to determine the orientation angle of the cell polarity based on the center point coordinates of the cell polarity rectangle and the direction of the center line connecting the cell polarity rectangle and the corresponding cell feature rectangle within each cell rectangle, as well as the length direction of the cell module image to be detected, when the cell polarity comparison result is successfully matched. The orientation angle is compared with the preset cell placement angle to obtain the cell placement angle comparison result. When the cell placement angle comparison result is successfully matched, it is determined that the cell installation is accurate.
[0019] In some embodiments, the cell placement angle comparison module is used to: establish a first vector based on the center point of the cell polarity rectangle and the center point of the corresponding cell feature rectangle; the first vector represents the direction and distance of the line connecting the centers of the cell polarity rectangle and the corresponding cell feature rectangle; establish a second vector based on the center point of the cell polarity rectangle and a preset standard point; the second vector represents the direction and distance of the line connecting the center point of the cell polarity rectangle and the preset standard point; the direction of the line connecting the center point of the cell polarity rectangle and the preset standard point is the same as the length direction of the image of the cell module to be detected, and the abscissa of the preset standard point is the same as the abscissa of the center point of the cell polarity rectangle; and determine the orientation angle of the cell polarity based on the first vector and the second vector.
[0020] Thirdly, embodiments of the present invention provide an electronic device, including a processor and a memory, wherein the memory stores a computer program executable by the processor, and the processor can execute the computer program to implement the cell installation accuracy determination method as described in the first aspect.
[0021] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the cell installation accuracy determination method as described in the first aspect.
[0022] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description
[0023] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0024] Figure 1 This is a schematic diagram of the battery module testing fixture structure provided in an embodiment of the present invention; Figure 2 A flowchart of a method for determining the accuracy of battery cell installation provided in an embodiment of the present invention; Figure 3 for Figure 2 Flowchart of the sub-steps in step S300; Figure 4 A cell arrangement diagram provided for an embodiment of the present invention; Figure 5 for Figure 2 Flowchart of the sub-steps in step S400; Figure 6 A vector diagram illustrating the negative electrode angle of the battery cell provided in an embodiment of the present invention; Figure 7 A vector diagram illustrating the positive electrode angle of the battery cell provided in an embodiment of the present invention; Figure 8 This is a schematic diagram of the functional modules of the battery cell installation accuracy judgment system provided in an embodiment of the present invention; Figure 9 This is a schematic diagram of an electronic device provided in an embodiment of the present invention.
[0025] Icons: 1000 - Cell installation accuracy judgment system; 1100 - Acquisition module; 1200 - Cell quantity comparison module; 1300 - Cell polarity arrangement order comparison module; 1400 - Cell placement angle comparison module; 2000 - Electronic equipment; 2100 - Processor; 2200 - Memory; 2300 - Bus; 2400 - Communication interface. Detailed Implementation
[0026] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.
[0027] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.
[0028] It should be noted that relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0029] As described in the background section, existing manual inspection methods typically require the design of dedicated tooling boards for different battery module models, such as... Figure 1 As shown, Figure 1 This is a schematic diagram of the battery module testing fixture structure provided in an embodiment of the present invention. The fixture has a hollow structure to cover the non-critical areas above the module during testing, leaving only the critical testing areas of the battery cells exposed. During each test, the operator must install the fixture on top of the module and manually determine whether the installation is correct by observing the position of the battery cells in the exposed areas.
[0030] Although this method can identify and judge the accuracy of battery cell installation to a certain extent, it has many problems. Long-term manual inspection can easily lead to visual fatigue and decreased accuracy, resulting in quality risks such as missed detection and misjudgment. Moreover, since different models of modules require different tooling boards, the tooling must be redesigned when switching to new models or going online. This not only results in untimely response but also increases additional design and manufacturing costs, affecting the flexibility and efficiency of the production line. It is also difficult to detect the number of battery cells, the arrangement order of the positive and negative electrodes of the battery cells, and the placement angle of the battery cells under complex working conditions.
[0031] Therefore, embodiments of the present invention provide a method for determining the accuracy of battery cell installation, see below. Figure 2 , Figure 2 This invention provides a flowchart of a method for determining the accuracy of battery cell installation. It uses image recognition processing to progressively determine the accuracy of battery cell installation across three dimensions: the number of cells, the positive and negative terminals of the cells, and the cell placement angle. This allows for the determination of cell installation accuracy only when all three conditions are met, eliminating the need for manual inspection using a tooling plate. This facilitates the detection of the number of cells, the order of the positive and negative terminals, and the cell placement angle under complex working conditions. The method includes steps S100-S500: S100. Obtain an image of the battery cell module to be tested. The image of the battery cell module to be tested includes multiple battery cell rectangles, multiple battery cell polarity rectangles, and multiple battery cell feature rectangles. The battery cell polarity rectangle and battery cell feature rectangle corresponding to the same battery cell are located within the corresponding battery cell rectangle.
[0032] In this embodiment, the image of the battery cell module to be detected is acquired by an industrial camera. After recognition by a deep learning model, multiple battery cell rectangles, multiple battery cell polarity rectangles, and multiple battery cell feature rectangles are obtained. Each battery cell rectangle contains a battery cell polarity rectangle and a battery cell feature rectangle. The battery cell polarity rectangle is used to identify the positive or negative electrode of the battery cell, and the battery cell feature rectangle is used to identify characteristic parts of the battery cell, such as the injection port or blue film. The battery cell polarity rectangle and the battery cell feature rectangle corresponding to the same battery cell are both located inside the corresponding battery cell rectangle. During the image recognition process, various targets in the image can be identified and selected based on the deep learning model, and finally, structured target rectangle information is output.
[0033] It should be noted that the image of the battery cell module to be tested contains feature information of each rectangle (the entire battery cell, positive and negative electrodes, liquid injection port or blue film) as well as the coordinates of the four vertices of the rectangle.
[0034] S200: Obtain the number of battery cells based on multiple battery cell rectangles, compare the number of battery cells with the preset number of battery cells, and obtain the battery cell number comparison result.
[0035] In this embodiment, the preset number of battery cells refers to the standard number of battery cells specified in the design of this model of battery cell module. By comparing the number, a preliminary judgment is made as to whether the battery cell installation meets the basic requirements. It should be noted that the number of battery cells is the first threshold for judging the installation status of the battery cell module. If the number does not match, there is no need to continue to perform subsequent judgment steps, and the installation is directly judged as failed, thereby improving the detection efficiency.
[0036] S300. If the comparison of the number of cells is successful, the polarity arrangement order of the cells is obtained according to the arrangement order of the polarity rectangles of multiple cells in the image of the cell module to be detected; the polarity arrangement order of the cells is compared with the preset polarity arrangement order of the cells to obtain the polarity comparison result.
[0037] In this embodiment, when the cell quantity comparison result indicates a successful comparison, the cell polarity arrangement order determination stage begins. A cell polarity arrangement order is generated based on the arrangement order of multiple cell polarity rectangles in the image of the cell module to be tested. This arrangement order is derived from the arrangement order of the cell rectangles within the image. Since cell polarity rectangles are within each other, their arrangement order represents the overall arrangement order of the cell polarity rectangles. Furthermore, because each cell rectangle contains the entire cell, its size and position are relatively easy to compare, making it easy to obtain the arrangement order in the image of the cell module to be tested. Then, the cell polarity arrangement order is compared with a preset cell polarity arrangement order, which refers to the cell polarity arrangement order specified in the design of this model of cell module. The comparison determines whether the cell polarity installation is correct. It should be noted that the order of cell polarity arrangement is the second threshold for judging the installation status of the cell module. If the order of cell polarity arrangement is incorrect, there is no need to continue to perform subsequent judgment steps, and the installation is directly judged as failed, thereby improving the detection efficiency.
[0038] S400. If the cell polarity comparison result is successfully matched, the orientation angle of the cell polarity is determined based on the direction of the center line connecting the cell polarity rectangle and the corresponding cell feature rectangle within each cell rectangle and the length direction of the cell module image to be detected. The orientation angle is then compared with the preset cell placement angle to obtain the cell placement angle comparison result.
[0039] In this embodiment, the cell polarity rectangle includes a positive cell rectangle and a negative cell rectangle. The cell feature rectangle includes an injection port rectangle and a blue film rectangle. The positive cell is associated with both the injection port and the blue film feature points, while the negative cell is associated only with the blue film. Next, the center point coordinates of the polarity rectangle and feature rectangle are extracted for each cell, and these two center points are connected to form a vector. The direction of this vector reflects the cell's deflection trend. Simultaneously, the overall length direction of the image of the cell module under test is used as the reference direction of the coordinate system. Typically, the length direction of the image corresponds to the Y-axis, and the width direction corresponds to the X-axis. By combining these two directions, the deflection angle of the cell polarity rectangle relative to the image coordinate system can be calculated. Specifically, if the deflection angle is between 0° and 180°, the cell is determined to be facing left; if the deflection angle is between 180° and 360°, the cell is determined to be facing right. Finally, the obtained cell polarity orientation angle is compared with the preset cell placement angle to determine whether the cell placement angle is correct.
[0040] S500: If the comparison of the cell placement angle is successful, the cell installation is confirmed to be accurate.
[0041] In this embodiment, when the comparison result of the cell placement angle indicates a successful comparison, the accurate installation of the cell module is finally determined. It can be understood that a correct installation result is obtained only if the quantity, polarity arrangement, and placement angle all pass the comparison; otherwise, the installation fails. It should be noted that this determination logic adopts a progressive judgment mechanism, meaning that if the comparison fails in the previous stage, subsequent judgment steps will not be executed, thereby avoiding invalid calculations and improving response efficiency.
[0042] In some embodiments, multiple cell polarity rectangles are sorted based on the x-coordinate and y-coordinate of the upper left corner vertex of the cell polarity rectangle where each cell polarity rectangle is located, to obtain the cell polarity arrangement order.
[0043] Furthermore, when sorting multiple cell polarity rectangles using the x and y coordinates of the top-left vertex of each cell polarity rectangle, refer to... Figure 3 , Figure 3 for Figure 2 The flowchart of the sub-steps of step S300, which includes steps S301 to S303: S301. If the distance between the x-coordinate of the top left corner vertex of the current cell polarity rectangle and the x-coordinate of the top left corner vertex of the first cell rectangle in the current column is less than a preset threshold, then the current cell polarity rectangle is included in the current column; the preset threshold is half the length of the cell rectangle.
[0044] In this embodiment, when sorting the cell polarity rectangles, it is first necessary to determine the column affiliation of the cell, that is, to determine whether a certain cell belongs to the current column. Specifically, see [link to documentation]. Figure 4 , Figure 4 The battery cell arrangement sequence diagram provided in this embodiment of the invention is obtained by sorting the battery cell rectangles according to their upper left corner vertex x-coordinates from smallest to largest, resulting in a set of sorted battery cell rectangles. The x-coordinates of the battery cell rectangles are sorted along the width direction of the image of the battery cell module to be detected (X-axis in the figure), and the y-coordinates of the battery cell rectangles are sorted along the length direction of the image of the battery cell to be detected (Y-axis in the figure). Then, the first battery cell rectangle in the set is selected as a reference, and the x-coordinate of its upper left corner vertex is obtained. Subsequently, the distance between the x-coordinate of the upper left corner vertex of the current battery cell rectangle to be judged and the x-coordinate of the upper left corner vertex of the reference battery cell rectangle is calculated. If the distance is less than a preset threshold, the battery cell rectangle is determined to belong to the current column. The preset threshold is defined as half the length of the battery cell rectangle; that is, when the horizontal deviation between two battery cell rectangles does not exceed half the length, they are considered to belong to the same column. This setting fully considers the slight deviations that may occur during image recognition, avoids incorrect column classification due to recognition errors, and thus improves the accuracy of column classification.
[0045] S302. If the distance between the x-coordinate of the top left corner vertex of the current cell polarity rectangle and the x-coordinate of the top left corner vertex of the first cell rectangle in the current column is not less than a preset threshold, then the current cell polarity rectangle is included in the next column of the current column.
[0046] In this embodiment, when determining whether the current cell polarity rectangle belongs to the current column, if the distance between the x-coordinate of the top-left corner of the cell's rectangle and the x-coordinate of the top-left corner of the first cell's rectangle in the current column is not less than a preset threshold (i.e., half the length of the cell's rectangle), then the cell is determined not to belong to the current column, but to belong to the next column. The above steps are then repeated to complete the sorting of the cell rectangles in the second column, until all columns are sorted. When a cell has a large offset in its horizontal arrangement or the module structure changes, the cell may actually be located in the next column. Forcibly classifying it into the current column would cause the subsequent sorting to be inconsistent with the actual physical arrangement, thus affecting the accuracy of polarity arrangement recognition. This judgment logic dynamically adjusts column assignments to ensure that the sorting result is consistent with the actual cell arrangement.
[0047] S303. For each cell polarity rectangle included in the same column, sort the cell polarity rectangles according to the ordinate of the upper left corner vertex of the cell rectangle in which each cell polarity rectangle is located, and obtain the cell polarity arrangement order.
[0048] In this embodiment, the cells are arranged in ascending order of their vertical coordinates based on the top-left corner vertex of the cell rectangle, thus determining the top-to-bottom arrangement of the cells within each column. After completing the vertical sorting of all columns, the columns are sequentially concatenated to form a complete cell polarity arrangement order. This arrangement order is represented by a string of "0" and "1", where "0" represents the positive electrode and "1" represents the negative electrode. This string is compared with a preset standard order to determine whether the cell polarity arrangement meets the set requirements. Therefore, the vertical sorting method achieves structured recognition of the cell polarity arrangement order, providing a reliable basis for subsequent consistency judgment. The generation of this order is based on the horizontal and vertical coordinate information of the top-left corner vertex of the cell rectangle. First, the cells are sorted in ascending order of their horizontal coordinates to form a preliminary column distribution. Then, within each column, the cells are sorted in ascending order of their vertical coordinates to finally generate the cell polarity arrangement order. The generated cell polarity arrangement order is compared with the preset cell polarity arrangement order to determine whether the cell polarity arrangement is consistent. Therefore, by using a structured arrangement sequence identification and standard comparison mechanism, the accuracy of the cell polarity arrangement can be ensured, and circuit connection abnormalities caused by polarity misalignment can be avoided.
[0049] In some embodiments, before step S400, the cell installation accuracy determination method further includes, for each cell polarity rectangle within a cell rectangle, taking the cell feature rectangle closest to the cell polarity rectangle as the cell feature rectangle corresponding to the cell polarity rectangle.
[0050] In this embodiment, to accurately identify the correspondence between the polarity and features of each battery cell, the binding operation between the battery cell polarity rectangle and the battery cell feature rectangle needs to be completed before identifying the battery cell placement angle. After the image recognition stage is completed, multiple battery cell rectangles have been acquired. Each battery cell rectangle contains a battery cell polarity rectangle (used to identify the positive or negative electrode) and one or more battery cell feature rectangles (such as the injection port or blue film). To determine the feature rectangle corresponding to each battery cell polarity rectangle, the following operation is performed on the battery cell polarity rectangle within each battery cell rectangle: the distance between the center point of the battery cell polarity rectangle and the center points of all battery cell feature rectangles is calculated, and the nearest battery cell feature rectangle is selected as the corresponding feature rectangle of the battery cell polarity rectangle. It should be noted that the coordinates of the center point of the battery cell polarity rectangle and the coordinates of the center point of the battery cell feature rectangle can both be calculated using the coordinates of the four vertices of the battery cell polarity rectangle and the four vertices of the battery cell feature rectangle.
[0051] For example, for a positive electrode cell, its cell polarity rectangle should be associated with an injection port rectangle and a blue film rectangle; while for a negative electrode cell, its cell polarity rectangle is associated with only one blue film rectangle. This principle of minimum distance ensures accurate binding between cell polarity and its characteristics, avoiding misbinding problems caused by identification errors or layout deviations.
[0052] In some embodiments, when determining the orientation angle of the cell polarity, refer to Figure 5 , Figure 5 for Figure 2 The flowchart of the sub-steps of step S400, which includes steps S401 to S403: S401. Establish a first vector based on the center point of the cell polarity rectangle and the center point of the corresponding cell feature rectangle; the first vector represents the direction and distance of the line connecting the center of the cell polarity rectangle and the center of the corresponding cell feature rectangle.
[0053] In this embodiment, the coordinates of the center point of the cell polarity rectangle (denoted as point O) and the coordinates of the center point of its corresponding cell feature rectangle (denoted as point B) are obtained, and a first vector OB is constructed using these two points as the starting and ending points. The first vector OB represents the direction and distance of the center line connecting the cell polarity rectangle and the feature rectangle, and is an important basis for determining the cell placement angle. For example, if the cell is a negative electrode, its polarity rectangle will be bound to the blue film rectangle, and the first vector OB is the line connecting the center of the negative electrode rectangle and the center of the blue film rectangle.
[0054] S402. Establish a second vector based on the center point of the cell polarity rectangle and a preset standard point; the second vector represents the direction and distance of the line connecting the center point of the cell polarity rectangle and the preset standard point; the direction of the line connecting the center point of the cell polarity rectangle and the preset standard point is the same as the length direction of the image of the cell module to be tested, and the abscissa of the preset standard point is the same as the abscissa of the center point of the cell polarity rectangle.
[0055] In this embodiment, a preset standard point is first set. The horizontal coordinate of this point is the same as that of the center point of the cell polarity rectangle, and the vertical coordinate is set according to the length of the cell rectangle. Specifically, this preset standard point (denoted as point A) is located directly above or below the center point (point O) of the cell polarity rectangle. The direction of the line connecting the center point O and point A is consistent with the length direction of the image of the cell module to be tested, thereby constructing the second vector OA. It should be noted that the length direction of the image of the cell module to be tested is usually consistent with the cell arrangement direction. By setting a second vector consistent with this direction, a reference direction aligned with the image coordinate system can be established for subsequent angle calculation with the first vector.
[0056] For example, seeFigure 6 and Figure 7 , Figure 6 This is a vector diagram illustrating the negative electrode angle of the battery cell provided in an embodiment of the present invention. Figure 7 This is a vector diagram illustrating the positive electrode angle of a battery cell according to an embodiment of the present invention. For example, for a negative electrode battery cell, in Figure 6 In the diagram, point A is set to have the same x-coordinate as point O, but a larger y-coordinate, such that vector OA points upwards, serving as a reference vector for the length direction of the image. The line connecting the center of the negative electrode rectangle of the battery cell and the center of the blue film rectangle is OB. In other words, the first vector is OB, and the second vector is OA.
[0057] For example, for positive electrode cells, the process is similar to that of negative electrode cells, except that the negative electrode uses the blue film as a reference point, while the positive electrode uses the electrolyte filling port as the reference point. Figure 7 In this process, the first vector OC is constructed based on the coordinates of the center point of the cell polarity rectangle (denoted as point O) and the coordinates of the center point of the corresponding cell liquid injection port rectangle (denoted as point C). The preset standard point (denoted as point A) is set in the same way as the preset standard point of the cell negative electrode. Both are located directly above or below the center point (point O) of the cell polarity rectangle. The line connecting the center point O and point A is consistent with the length direction of the cell module image to be tested. This constructs the second vector OA, ensuring that the second vector has a clear directionality and providing a reliable reference for the subsequent determination of the cell polarity orientation angle.
[0058] S403. Determine the orientation angle of the cell polarity based on the first vector and the second vector.
[0059] In this embodiment, after constructing the first vector (OB) and the second vector (OA), the angle θ between the two vectors is further calculated. The angle between the two vectors is calculated using the dot product formula or cross product formula of the vectors. This angle is the orientation angle of the cell polarity.
[0060] In some embodiments, the orientation angle of the cell polarity includes a first orientation and a second orientation. A trigonometric function of the angle between the first vector and the second vector is calculated based on the first vector and the second vector. The trigonometric function is compared with a preset value. If the trigonometric function is less than the preset value, the cell placement angle is determined to be the first orientation. If the trigonometric function is not less than the preset value, the cell placement angle is determined to be the second orientation.
[0061] In this embodiment, the first orientation is typically used to indicate that the cell feature (such as the injection port or blue film) is located on the left side of the cell polarity rectangle, while the second orientation indicates that it is located on the right side. The angle between the first vector (i.e., the line vector connecting the center point of the cell polarity rectangle to the center point of the corresponding cell feature rectangle) and the second vector (i.e., the line vector connecting the center point of the cell polarity rectangle to a preset standard point) is calculated. Through vector operations, the angle θ between the two vectors is calculated, and the trigonometric function value of this angle, such as the sine value, is further calculated. This serves as the basis for judgment.
[0062] For example, the calculated trigonometric function value is compared with a preset threshold. If the trigonometric function value is less than the preset value, the cell polarity is determined to be in a first orientation; if the trigonometric function value is not less than the preset value, it is determined to be in a second orientation. It can be understood that if the blue film of the negative electrode of the cell is located to the left of its polarity rectangle, the calculated angle trigonometric function value will be less than the set threshold, and it is determined to be in the first orientation; if the blue film is located to the right, the angle trigonometric function value will be greater than or equal to the threshold, and it is determined to be in the second orientation. For the positive electrode cell, the judgment logic is similar, only the feature point is the liquid injection port. For example, by calculating... The value of θ is used to determine the orientation of the cell deflection. When θ∈[0,180], When θ ∈ [0,1], the cell faces left. When θ ∈ [180,360], ∈[-1,0], the cell faces to the right.
[0063] For example, the angle determination result of each battery cell is combined into a string of 0s and 1s according to the cell arrangement order, where 0 represents left and 1 represents right. This string is then compared bit by bit with a pre-defined standard placement angle string. This standard string is determined by design requirements and represents the proper angular arrangement of the battery cells in the module. Only when the actually generated angle string completely matches the standard string is the battery cell module considered to meet the installation requirements in terms of placement angle; otherwise, it is considered an abnormal placement angle. The entire judgment process is completed based on image recognition and data processing, possessing a high degree of automation and accuracy. It can effectively identify and eliminate installation errors caused by battery cell deflection, thus providing a reliable basis for subsequent module assembly and quality control.
[0064] Based on the above method, embodiments of the present invention also provide a system corresponding to the above method, such as... Figure 8 As shown, Figure 8This is a functional module diagram of the battery cell installation accuracy judgment system 1000 provided in an embodiment of the present invention. It should be noted that the basic principle and technical effects of the battery cell installation accuracy judgment system 1000 provided in this embodiment are the same as those in the above method embodiments. For the sake of brevity, parts not mentioned in this embodiment can be referred to the corresponding content in the method embodiments.
[0065] In this embodiment, the battery cell installation accuracy judgment system 1000 includes an acquisition module 1100, a battery cell quantity comparison module 1200, a battery cell polarity arrangement order comparison module 1300, and a battery cell placement angle comparison module 1400.
[0066] The acquisition module 1100 is used to acquire an image of the battery cell module to be tested. The image of the battery cell module to be tested includes multiple battery cell rectangles, multiple battery cell polarity rectangles, and multiple battery cell feature rectangles. The battery cell polarity rectangle and the battery cell feature rectangle corresponding to the same battery cell are located within the corresponding battery cell rectangle. It can be understood that the acquisition module 1100 is also used to perform the above step S100.
[0067] The cell quantity comparison module 1200 is used to obtain the cell quantity based on multiple cell rectangles, compare the cell quantity with a preset cell quantity, and obtain the cell quantity comparison result. It can be understood that the cell quantity comparison module 1200 is also used to perform the above step S200.
[0068] The cell polarity arrangement order comparison module 1300 is used to obtain the cell polarity arrangement order based on the arrangement order of multiple cell polarity rectangles in the image of the cell module to be detected, when the cell quantity comparison result indicates a successful comparison; and compare the cell polarity arrangement order with a preset cell polarity arrangement order to obtain the cell polarity comparison result. It can be understood that the cell polarity arrangement order comparison module 1300 is also used to perform the above step S300.
[0069] The cell placement angle comparison module 1400 is used to determine the orientation angle of the cell polarity based on the coordinates of the center point of the cell polarity rectangle and, if the cell polarity comparison result is successful, the direction of the center line connecting the cell polarity rectangle within each cell rectangle to the corresponding cell feature rectangle and the length direction of the image of the cell module to be detected. This orientation angle is then compared with a preset cell placement angle to obtain the cell placement angle comparison result. If the cell placement angle comparison result is successful, it is determined that the cell is installed accurately. It can be understood that the cell placement angle comparison module 1400 is also used to perform the above step S400.
[0070] In some embodiments, the cell polarity arrangement order comparison module 1300 is further used to sort multiple cell polarity rectangles based on the horizontal and vertical coordinates of the upper left corner vertex of the cell rectangle where each cell polarity rectangle is located, so as to obtain the cell polarity arrangement order.
[0071] In some embodiments, the cell polarity arrangement order comparison module 1300 is further configured to: if the distance between the x-coordinate of the upper left corner vertex of the cell rectangle containing the current cell polarity rectangle and the x-coordinate of the upper left corner vertex of the first cell rectangle in the current column is less than a preset threshold, then the current cell polarity rectangle is included in the current column; the preset threshold is half the length of the cell rectangle; if the distance between the x-coordinate of the upper left corner vertex of the cell rectangle containing the current cell polarity rectangle and the x-coordinate of the upper left corner vertex of the first cell rectangle in the current column is not less than the preset threshold, then the current cell polarity rectangle is included in the next column of the current column; for each cell polarity rectangle included in the same column, the cell polarity rectangles are sorted according to the y-coordinate of the upper left corner vertex of the cell rectangle containing each cell polarity rectangle to obtain the cell polarity arrangement order. It can be understood that the cell polarity arrangement order comparison module 1300 is also configured to perform the above steps S301~S301.
[0072] In some embodiments, the cell placement angle comparison module 1400 is further configured to, for each cell polarity rectangle within a cell rectangle, identify the cell feature rectangle closest to the cell polarity rectangle as the cell feature rectangle corresponding to the cell polarity rectangle.
[0073] In some embodiments, the cell placement angle comparison module 1400 is used to establish a first vector based on the center point of the cell polarity rectangle and the center point of the corresponding cell feature rectangle; the first vector represents the direction and distance of the line connecting the centers of the cell polarity rectangle and the corresponding cell feature rectangle; a second vector is established based on the center point of the cell polarity rectangle and a preset standard point; the second vector represents the direction and distance of the line connecting the center point of the cell polarity rectangle and the preset standard point; the direction of the line connecting the center point of the cell polarity rectangle and the preset standard point is the same as the length direction of the image of the cell module to be detected, and the abscissa of the preset standard point is the same as the abscissa of the center point of the cell polarity rectangle; the orientation angle of the cell polarity is determined based on the first vector and the second vector. It can be understood that the cell placement angle comparison module 1400 is also used to perform the above steps S401~S403.
[0074] In some embodiments, the orientation angle of the cell polarity includes a first orientation and a second orientation. The cell placement angle comparison module 1400 is further used to calculate a trigonometric function of the angle between the first vector and the second vector based on the first vector and the second vector; compare the trigonometric function with a preset value; if the trigonometric function is less than the preset value, the cell placement angle is determined to be the first orientation; if the trigonometric function is not less than the preset value, the cell placement angle is determined to be the second orientation.
[0075] Based on the same inventive concept disclosed above, the present invention also provides a block diagram of an electronic device 2000 performing the above method. Please refer to... Figure 9 , Figure 9 This is a schematic diagram of an electronic device 2000 provided in an embodiment of the present invention. The electronic device 2000 includes a processor 2100, a memory 2200, a bus 2300, and a communication interface 2400. The processor 2100 and the memory 2200 are connected via the bus 2300, and the processor 2100 communicates with external devices via the communication interface 2400.
[0076] Processor 2100 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed through integrated logic circuits in the hardware of processor 2100 or through software instructions. The processor 2100 may be a general-purpose processor 2100, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.
[0077] The memory 2200 is used to store computer programs. For example, the cell installation accuracy discrimination system 1000 in this embodiment of the invention includes at least one software function module that can be stored in the memory 2200 in the form of software or firmware. After receiving the execution instruction, the processor 2100 executes the program to implement the cell installation accuracy discrimination method in this embodiment of the invention.
[0078] The memory 2200 may include high-speed random access memory (RAM) or non-volatile memory. Optionally, the memory 2200 may be a storage device built into the processor 2100 or a storage device independent of the processor 2100.
[0079] Bus 2300 can be ISA bus 2300, PCI bus 2300 or EISA bus 2300, etc. Figure 9 It is indicated by only one double-headed arrow, but does not mean that there is only one bus 2300 or one type of bus 2300.
[0080] Electronic devices 2000 can be mobile phones, tablets, laptops, desktop computers, and other computer devices.
[0081] Based on the same inventive concept, embodiments of the present invention also provide a computer-readable storage medium storing a computer program thereon. When executed by processor 2100, this computer program implements the cell installation accuracy determination method described above. This computer-readable storage medium may include various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.
[0082] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. A method for judging the accuracy of battery cell installation, characterized in that, The method includes: An image of a battery cell module to be tested is acquired. The image of the battery cell module to be tested includes multiple battery cell rectangles, multiple battery cell polarity rectangles, and multiple battery cell feature rectangles. The battery cell polarity rectangle and the battery cell feature rectangle corresponding to the same battery cell are located within the corresponding battery cell rectangle. The number of battery cells is obtained based on multiple battery cell rectangles, and the number of battery cells is compared with a preset number of battery cells to obtain a battery cell number comparison result; If the comparison of the number of battery cells is successful, the battery cell polarity arrangement order is obtained according to the arrangement order of the multiple battery cell polarity rectangles in the image of the battery cell module to be detected; the battery cell polarity arrangement order is compared with the preset battery cell polarity arrangement order to obtain the battery cell polarity comparison result. If the cell polarity comparison result is successful, the orientation angle of the cell polarity is determined based on the direction of the center line connecting the cell polarity rectangle and the corresponding cell feature rectangle within each cell rectangle and the length direction of the cell module image to be detected. The orientation angle is then compared with the preset cell placement angle to obtain the cell placement angle comparison result. If the comparison of the cell placement angle indicates a successful comparison, the cell installation is confirmed to be accurate.
2. The method according to claim 1, characterized in that, The step of obtaining the cell polarity arrangement order based on the arrangement order of the plurality of cell polarity rectangles in the image of the cell module to be detected includes: The multiple cell polarity rectangles are sorted based on the x and y coordinates of the top left corner vertex of each cell polarity rectangle to obtain the cell polarity arrangement order.
3. The method according to claim 2, characterized in that, The process of sorting multiple cell polarity rectangles based on the x and y coordinates of the top-left corner vertex of each cell polarity rectangle to obtain the cell polarity arrangement order includes: If the distance between the x-coordinate of the top left corner vertex of the current cell polarity rectangle and the x-coordinate of the top left corner vertex of the first cell rectangle in the current column is less than a preset threshold, then the current cell polarity rectangle is included in the current column; the preset threshold is half the length of the cell rectangle. If the distance between the x-coordinate of the top left corner vertex of the current cell polarity rectangle and the x-coordinate of the top left corner vertex of the first cell rectangle in the current column is not less than a preset threshold, then the current cell polarity rectangle is included in the next column of the current column. For each of the cell polarity rectangles included in the same column, the cell polarity rectangles are sorted according to the ordinate of the upper left corner vertex of the cell rectangle in which each cell polarity rectangle is located, to obtain the cell polarity arrangement order.
4. The method according to claim 1, characterized in that, Before determining the orientation angle of the cell polarity based on the center line direction of the cell polarity rectangle and the corresponding cell feature rectangle within each cell rectangle and the length direction of the cell module image to be detected, the method further includes: For each cell polarity rectangle within a cell rectangle, the cell feature rectangle closest to the cell polarity rectangle is taken as the cell feature rectangle corresponding to the cell polarity rectangle.
5. The method according to claim 1, characterized in that, The determination of the cell polarity orientation angle based on the center line direction of the cell polarity rectangle and the corresponding cell feature rectangle within each cell rectangle, and the length direction of the cell module image to be detected, includes: A first vector is established based on the center point of the cell polarity rectangle and the center point of the corresponding cell feature rectangle; the first vector represents the direction and distance of the line connecting the center of the cell polarity rectangle and the center of the corresponding cell feature rectangle. A second vector is established based on the center point of the cell polarity rectangle and a preset standard point; the second vector represents the direction and distance of the line connecting the center point of the cell polarity rectangle and the preset standard point; the direction of the line connecting the center point of the cell polarity rectangle and the preset standard point is the same as the length direction of the image of the cell module to be tested, and the abscissa of the preset standard point is the same as the abscissa of the center point of the cell polarity rectangle; The orientation angle of the cell polarity is determined based on the first vector and the second vector.
6. The method according to claim 5, characterized in that, The orientation angle of the cell polarity includes a first orientation and a second orientation, and the determination of the orientation angle of the cell polarity based on the first vector and the second vector includes: Calculate the trigonometric function of the angle between the first vector and the second vector based on the first vector and the second vector; The trigonometric function is compared with a preset value. If the trigonometric function is less than the preset value, the cell placement angle is determined to be the first orientation. If the trigonometric function is not less than the preset value, the cell placement angle is determined to be the second orientation.
7. A system for judging the accuracy of battery cell installation, characterized in that, The system includes: The acquisition module is used to acquire an image of the battery cell module to be tested. The image of the battery cell module to be tested includes multiple battery cell rectangles, multiple battery cell polarity rectangles, and multiple battery cell feature rectangles. The battery cell polarity rectangle and the battery cell feature rectangle corresponding to the same battery cell are located within the corresponding battery cell rectangle. A cell quantity comparison module is used to obtain the cell quantity based on multiple cell rectangles, compare the cell quantity with a preset cell quantity, and obtain a cell quantity comparison result. The cell polarity arrangement order comparison module is used to obtain the cell polarity arrangement order based on the arrangement order of multiple cell polarity rectangles in the image of the cell module to be detected when the cell quantity comparison result indicates a successful comparison; and compare the cell polarity arrangement order with a preset cell polarity arrangement order to obtain the cell polarity comparison result. The cell placement angle comparison module is used to determine the orientation angle of the cell polarity based on the center point coordinates of the cell polarity rectangle and, if the cell polarity comparison result is successfully matched, the direction of the center line connecting the cell polarity rectangle and the corresponding cell feature rectangle within each cell rectangle, and the length direction of the cell module image to be detected. The orientation angle is then compared with a preset cell placement angle to obtain the cell placement angle comparison result. If the cell placement angle comparison result is successfully matched, it is determined that the cell is installed accurately.
8. The cell installation accuracy judgment system according to claim 7, characterized in that, The cell placement angle comparison module is used for: A first vector is established based on the center point of the cell polarity rectangle and the center point of the corresponding cell feature rectangle; the first vector represents the direction and distance of the line connecting the center of the cell polarity rectangle and the center of the corresponding cell feature rectangle. A second vector is established based on the center point of the cell polarity rectangle and a preset standard point; the second vector represents the direction and distance of the line connecting the center point of the cell polarity rectangle and the preset standard point; the direction of the line connecting the center point of the cell polarity rectangle and the preset standard point is the same as the length direction of the image of the cell module to be tested, and the abscissa of the preset standard point is the same as the abscissa of the center point of the cell polarity rectangle; The orientation angle of the cell polarity is determined based on the first vector and the second vector.
9. An electronic device, characterized in that, It includes a processor and a memory, the memory storing a computer program that can be executed by the processor, the processor being able to execute the computer program to implement the cell installation accuracy determination method according to any one of claims 1-6.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the cell installation accuracy determination method as described in any one of claims 1-6.
Citation Information
Patent Citations
Module polarity detection method and detection tool
CN111239618A
Battery cell assembly indicating device and method
CN111403794A
Rotating target detection method, device and system and readable medium
CN111815519A
Installation state recognition method, installation method and installation state recognition device
CN112928392A
ODF socket state identification method and system based on machine vision
CN114926414A