Automobile power battery collision test device and system thereof

Abstract

The invention discloses an automobile power battery collision test device and a system thereof, and belongs to the technical field of battery test.A deformation analysis module is used for analyzing the position and depth of a collision recess of a collided automobile power battery; the battery capacity of the impacted automobile power battery after preset times of charge and discharge cycles is obtained through a service life test module, and whether the position of the impacted recess and the depth of the recess affect the safety of the battery is judged according to the battery capacity; and finally, estimating the minimum recess depth influencing the safety of the automobile power battery at different positions of the automobile power battery by using a pre-trained deep learning model, accurately providing safety judgment after the battery is collided and deformed, and in a recess identification module, identifying a recess area in a collided surface image through a pre-trained YOLOv8 improved model, and finally, identifying the safety of the automobile power battery according to the recess area. The accuracy of recess recognition is improved, and the effectiveness and accuracy of testing are further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of battery testing, in particular to an automobile power battery collision testing device and a system thereof. Background Art

[0002] In the testing of automotive power batteries, automotive power battery collision testing is extremely important. After the battery is hit, it will produce a large or small deformation, that is, the battery will be dented. Sometimes the dent is very small, so people ignore that a small dent may also affect the safety or life of the battery, which in turn leads to driving hazards. Therefore, there is an urgent need for a test system that can obtain whether different degrees of battery dents have a practical impact on the safe use of the battery. Summary of the invention

[0003] The present invention is to solve the technical problems existing in the prior art. The present invention provides an automobile power battery collision test system, which specifically includes:

[0004] An impact device, used for impacting the vehicle power battery through an impact head;

[0005] A deformation analysis module, including an image acquisition module, a depression recognition module, an impact depression determination module and a laser distance measuring device;

[0006] The image acquisition module is used to acquire the image of the impacted surface of the vehicle power battery, wherein the impacted surface image includes an initial image and a post-impact image;

[0007] The concave recognition module is used to identify concave information in the hit surface image, specifically: using a pre-trained YOLOv8 improved model to identify the concave area in the hit surface image; using edge detection to identify the concave contour from the concave area;

[0008] The YOLOv8 improved model is improved on the YOLOv8 model, specifically: replacing the ordinary convolution module in the backbone network of the YOLOv8 model with the Ghost convolution module; introducing the CA attention mechanism in the C2f module in the feature enhancement network of the YOLOv8 model;

[0009] The impact dent determination module is used to determine the impact dent in the post-collision image that is caused by the vehicle power battery being hit by the impact head by comparing the dent information in the initial image and the post-collision image;

[0010] The laser distance measuring device is used to measure the depth of the impact depression;

[0011] The life test module is used to obtain the battery capacity after a preset number of charge and discharge cycles of the vehicle power battery after the collision;

[0012] A judgment module, used to judge whether the depth of the depression at the location of the impact depression of the current vehicle power battery affects the safety of the vehicle power battery according to the battery capacity;

[0013] The prediction module is used to estimate the minimum dent depth at different locations of the vehicle power battery that affects the safety of the vehicle power battery using a pre-trained deep learning model.

[0014] Furthermore, the CA attention mechanism is introduced into the C2f module in the feature enhancement network of the YOLOv8 model, specifically:

[0015] The feature map output by the concatenation layer of the C2f module is input into the CA self-attention mechanism module. The feature map of the CA self-attention mechanism module is encoded horizontally and vertically to generate a horizontal attention map and a vertical attention map, which are then fused to obtain a comprehensive attention map. The feature map is weighted using the comprehensive attention map to obtain an enhanced feature map, which is then input into the second convolutional layer of the C2f module.

[0016] Further, the measuring of the depression depth of the impact depression is specifically as follows:

[0017] Obtaining a distance h1 between the laser distance measuring device and the surface of the non-depressed area of ​​the impacted surface of the vehicle power battery by means of a laser distance measuring device;

[0018] Obtaining a position with the maximum gray value within the concave contour range of the impact concave in the post-collision image and taking its actual position in the impacted surface of the vehicle power battery as a second distance measurement point;

[0019] Aim the ranging light beam of the laser ranging device at the second ranging point and obtain the distance h2 between the laser ranging device and the second ranging point;

[0020] The depth of the impact depression is h2 minus h1.

[0021] Furthermore, the determination of whether the depth of the depression at the location of the impact depression of the current vehicle power battery affects the safety of the vehicle power battery is specifically as follows:

[0022] If the battery capacity is less than or equal to the preset capacity threshold, the depth of the dent at the location of the impact dent of the current vehicle power battery affects the safety of the vehicle power battery.

[0023] Furthermore, the system also includes a parameter acquisition module for acquiring the mass, initial velocity and instantaneous velocity of the impact head.

[0024] Furthermore, the judgment module is also used to judge whether the safety of the vehicle power battery is affected after an object with the same mass as the current impact head collides with the vehicle power battery at the same instantaneous impact speed according to the battery capacity, specifically:

[0025] If the battery capacity is less than or equal to the preset capacity threshold, an object with the same mass as the current impact head collides with the vehicle power battery at the same instantaneous impact speed, which will affect the safety of the vehicle power battery.

[0026] Furthermore, the image acquisition module also includes an image preprocessing unit for performing image preprocessing on the initial image and the post-collision image of the vehicle power battery.

[0027] The present invention also provides a vehicle power battery collision test device, comprising:

[0028] An impact device, used for impacting the vehicle power battery through an impact head;

[0029] An image acquisition device is used to acquire an image of the impacted surface of the vehicle power battery, wherein the impacted surface image includes an initial image and a post-impact image;

[0030] A life test device, used to obtain the battery capacity after a preset number of charge and discharge cycles of the vehicle power battery after the collision;

[0031] A laser rangefinder for measuring the depth of the impact depression;

[0032] The analysis platform is equipped with dent recognition algorithm, impact dent determination algorithm, judgment algorithm and prediction algorithm;

[0033] The concave recognition algorithm is used to identify the concave area in the impacted surface image through the pre-trained YOLOv8 improved model, and use edge detection to identify the concave contour from the concave area;

[0034] The YOLOv8 improved model is improved on the YOLOv8 model, specifically: replacing the ordinary convolution module in the backbone network of the YOLOv8 model with the Ghost convolution module; introducing the CA attention mechanism in the C2f module in the feature enhancement network of the YOLOv8 model;

[0035] The impact dent is determined by an impact dent determination algorithm, specifically by comparing the dent information in the initial image and the post-collision image to determine the impact dent in the post-collision image that is caused by the vehicle power battery being hit by the impact head;

[0036] The judgment algorithm is used to judge, based on the battery capacity, whether the depth of the depression at the location of the impact depression of the current vehicle power battery affects the safety of the vehicle power battery;

[0037] The prediction algorithm uses a pre-trained deep learning model to estimate the minimum dent depth at different locations of the vehicle power battery that affects the safety of the vehicle power battery.

[0038] Furthermore, the CA attention mechanism is introduced into the C2f module in the feature enhancement network of the YOLOv8 model, specifically:

[0039] The feature map output by the concatenation layer of the C2f module is input into the CA self-attention mechanism module. The feature map of the CA self-attention mechanism module is encoded horizontally and vertically to generate a horizontal attention map and a vertical attention map, which are then fused to obtain a comprehensive attention map. The feature map is weighted using the comprehensive attention map to obtain an enhanced feature map, which is then input into the second convolutional layer of the C2f module.

[0040] Furthermore, the depth of the impact depression is measured, specifically:

[0041] Obtaining a distance h1 between the laser distance measuring device and the surface of the non-depressed area of ​​the impacted surface of the vehicle power battery by means of a laser distance measuring device;

[0042] Obtaining a position with the maximum gray value within the concave contour range of the impact concave in the post-collision image and taking its actual position in the impacted surface of the vehicle power battery as a second distance measurement point;

[0043] Aim the ranging light beam of the laser ranging device at the second ranging point and obtain the distance h2 between the laser ranging device and the second ranging point;

[0044] The depth of the impact depression is h2 minus h1.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] The present invention analyzes the position and depth of the impact dent of the automobile power battery after the impact through a deformation analysis module, and then obtains the battery capacity of the automobile power battery after the impact for a preset number of charge and discharge cycles through a life test module, and judges whether the position and depth of the impact dent affect the battery safety according to the battery capacity, and finally uses a pre-trained deep learning model to estimate the minimum dent depth at different positions of the automobile power battery that affects the safety of the automobile power battery, accurately providing a safety judgment after the battery is deformed by impact, and in the dent recognition module, the pre-trained YOLOv8 improved model is used to identify the dent area in the impacted surface image, thereby improving the accuracy of dent recognition, thereby improving the effectiveness and accuracy of the test. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0049] Figure 1 It is a structural block diagram of an automobile power battery collision test system of the present invention;

[0050] Figure 2 The invention discloses a structural block diagram of a deformation analysis module of an automobile power battery collision test system. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0053] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0054] Embodiment 1

[0055] See also Figure 1 As shown, the present invention provides a vehicle power battery collision test system, which specifically includes:

[0056] An impact device, a deformation analysis module, a life test module, a judgment module and a prediction module, and a control center communicating with the above modules.

[0057] The impact device is used to impact the automobile power battery through an impact head.

[0058] The impact device can adopt impact heads of different shapes.

[0059] The deformation analysis module is used to analyze the deformation state of the vehicle power battery after being impacted.

[0060] See also Figure 2 As shown, the deformation analysis module includes: an image acquisition module, a depression recognition module, an impact depression determination module and a laser distance measuring device.

[0061] The image acquisition module is used to acquire the image of the impacted surface of the vehicle power battery, wherein the impacted surface image includes an initial image and a post-impact image.

[0062] The initial image is an image of the impacted surface of the vehicle power battery before the impact, and the post-impact image is an image of the impacted surface of the vehicle power battery after the impact.

[0063] The image acquisition module includes a shooting device and a light source device.

[0064] It should be noted that when capturing the initial image and the post-collision image, the shooting height and angle of the shooting device remain unchanged, as well as the lighting height, angle and brightness of the light source device remain unchanged, and both the shooting device and the light source device shoot and illuminate the impacted surface of the vehicle's power battery.

[0065] The image acquisition module further includes an image preprocessing unit for performing image preprocessing on the initial image and the post-collision image of the vehicle power battery, including but not limited to:

[0066] Grayscale processing, converting color images into grayscale images;

[0067] Filter denoising to remove noise points in the image and improve image quality. Specifically, median filtering can be used;

[0068] Histogram equalization is performed on the image after filtering and denoising to enhance the contrast of the image and make the depression more obvious.

[0069] The concave recognition module is used to recognize concave information in the impacted surface image.

[0070] The identifying of the concave information in the hit surface image is specifically:

[0071] The pre-trained YOLOv8 improved model is used to identify the concave area in the collision surface image;

[0072] The concave contour is identified from the concave area using edge detection.

[0073] It should be noted that the identification of the concave information in the impacted surface image is to identify the concave information in the initial image and the post-impact image respectively.

[0074] The YOLOv8 improved model is improved based on the YOLOv8 model, specifically:

[0075] Replace the normal convolution module in the backbone network of the YOLOv8 model with the Ghost convolution module;

[0076] The CA attention mechanism is introduced in the C2f module in the feature enhancement network of the YOLOv8 model.

[0077] The YOLOv8 model mainly consists of three parts: backbone network, feature enhancement network and detection head.

[0078] Among them, the backbone network contains multiple Conv modules, namely ordinary convolution modules. In the operation of ordinary convolution, each convolution kernel will independently generate a new feature map. There may be great similarity between these feature maps, namely redundancy, and the number of parameters and the amount of calculation of ordinary convolution are large, resulting in high model complexity, insufficient operation efficiency and low detection efficiency. Therefore, this scheme replaces the ordinary convolution module in the backbone network of the YOLOv8 model with a Ghost convolution module. The Ghost convolution module first uses a small convolution kernel (such as 1×1 convolution) to perform a convolution operation on the input image to generate a part of the intermediate feature map, and then uses the depth-separable convolution based on the intermediate feature map to generate a Ghost feature map, and splices the intermediate feature map and the Ghost feature map to obtain the final output feature map. Ghost convolution only needs a small number of ordinary convolution kernels and depth-separable convolution kernels to generate a large number of feature maps, thereby reducing the number of parameters and the amount of calculation.

[0079] The C2f module (CSP Bott leneck with 2Convo l ut ions) in the feature enhancement network aims to better aggregate multi-scale information while reducing computational complexity and memory consumption. It includes the first convolutional layer (Conv1), the feature map splitting layer (Sp l it), multiple bottleneck modules (Bott leneck), the concatenation layer (Concat) and the second convolutional layer (Conv2)

[0080] The first convolutional layer performs convolution transformation on the feature map output by the backbone network to generate the second intermediate feature map;

[0081] The feature map splitting layer is used to split the second intermediate feature map into two parts, one of which is directly passed to the concatenation layer, and the other is passed to the bottleneck module;

[0082] The concatenation layer concatenates the feature map processed by the bottleneck module with the intermediate feature map directly passed to the concatenation layer to form a fused feature map.

[0083] In the second convolution layer, the fused feature map is processed by convolution transformation.

[0084] The ordinary C2f module mainly relies on local convolution operations to extract features, which may cause the model to fail to fully capture the global information in the feature map and the accuracy of distinguishing key features is insufficient. Therefore, this scheme introduces the CA attention mechanism in the C2f module in the feature enhancement network of the YOLOv8 model, specifically:

[0085] The feature map F output by the concatenation layer of the C2f module is input into the CA self-attention mechanism module. The feature map F of the CA self-attention mechanism module is encoded in the horizontal and vertical directions to generate the horizontal attention map and the vertical attention map, which are then fused to obtain the comprehensive attention map. The feature map F is weighted using the comprehensive attention map to obtain the enhanced feature map, which is then input into the second convolutional layer of the C2f module.

[0086] The present invention introduces the CA attention mechanism in the C2f module and uses the comprehensive attention map to weight the feature map. The weight of the feature map is adjusted to better capture the global spatial relationship, thereby enhancing the feature extraction capability of the model and improving the accuracy of distinguishing key features.

[0087] The improved YOLOv8 model is trained using a large number of automobile power battery images with different concave area features.

[0088] The impact dent determination module is used to determine the impact dent in the post-collision image that is caused by the vehicle power battery being hit by the impact head by comparing the dent information in the initial image and the post-collision image. Specifically, the initial image and the post-collision image are compared for the dent area, and the dent area that exists in the post-collision image but not in the initial image is taken as the impact dent.

[0089] A laser distance measuring device is used to measure the depth of the impact depression.

[0090] The measuring of the depression depth of the impact depression is specifically as follows:

[0091] Obtaining a distance h1 between the laser distance measuring device and the surface of the non-depressed area of ​​the impacted surface of the vehicle power battery by means of a laser distance measuring device;

[0092] Obtaining a position with the maximum gray value within the concave contour range of the impact concave in the post-collision image and taking its actual position in the impacted surface of the vehicle power battery as a second distance measurement point;

[0093] Aim the ranging light beam of the laser ranging device at the second ranging point and obtain the distance h2 between the laser ranging device and the second ranging point;

[0094] The depth of the impact depression is h2 minus h1.

[0095] The life test module is used to obtain the battery capacity after a preset number of charge and discharge cycles of the car power battery after the collision.

[0096] The judgment module is used to judge whether the depth of the depression at the location of the impact depression of the current vehicle power battery affects the safety of the vehicle power battery according to the battery capacity, specifically:

[0097] If the battery capacity is less than or equal to the preset capacity threshold, the depth of the dent at the location of the impact dent of the current vehicle power battery affects the safety of the vehicle power battery.

[0098] Prediction module, which uses a pre-trained deep learning model to estimate the minimum dent depth at different locations of the vehicle power battery that affects the safety of the vehicle power battery

[0099] The deep learning model is trained using a large number of different positions, corresponding to different depression depths, corresponding battery capacities obtained from the life test module, and corresponding judgment results obtained from the judgment module as training data.

[0100] Different depression depths are obtained by adjusting the impact speed of the impact device.

[0101] In some embodiments, the system further includes a parameter acquisition module for acquiring the mass, initial velocity and instantaneous velocity of the impact head.

[0102] The mass of the impact head is obtained in advance through a weight sensor; the initial speed is set and adjusted manually; and the instantaneous speed of impact is obtained through a speed sensor.

[0103] The judgment module is also used to judge whether the safety of the vehicle power battery is affected after an object with the same mass as the current impact head collides with the vehicle power battery at the same instantaneous impact speed according to the battery capacity, specifically:

[0104] If the battery capacity is less than or equal to the preset capacity threshold, an object with the same mass as the current impact head collides with the vehicle power battery at the same instantaneous impact speed, which will affect the safety of the vehicle power battery.

[0105] Embodiment 2

[0106] The present invention also provides a vehicle power battery collision test device, which specifically includes:

[0107] An impact device, used for impacting the vehicle power battery through an impact head;

[0108] An image acquisition device is used to acquire an image of the impacted surface of the vehicle power battery, wherein the impacted surface image includes an initial image and a post-impact image;

[0109] A life test device, used to obtain the battery capacity after a preset number of charge and discharge cycles of the vehicle power battery after the collision;

[0110] A laser rangefinder for measuring the depth of the impact depression;

[0111] The analysis platform is equipped with a dent recognition algorithm, an impact dent determination algorithm, and a judgment algorithm;

[0112] The concave recognition algorithm is used to identify the concave area in the impacted surface image through the pre-trained YOLOv8 improved model, and use edge detection to identify the concave contour from the concave area;

[0113] The YOLOv8 improved model is improved on the YOLOv8 model, specifically: replacing the ordinary convolution module in the backbone network of the YOLOv8 model with the Ghost convolution module; introducing the CA attention mechanism in the C2f module in the feature enhancement network of the YOLOv8 model;

[0114] The impact dent is determined by an impact dent determination algorithm, specifically by comparing the dent information in the initial image and the post-collision image to determine the impact dent in the post-collision image that is caused by the vehicle power battery being hit by the impact head;

[0115] The judgment algorithm is used to judge, based on the battery capacity, whether the depth of the depression at the location of the impact depression of the current vehicle power battery affects the safety of the vehicle power battery.

[0116] The image acquisition device includes a shooting device and a light source device.

[0117] When capturing the initial image and the post-collision image, the shooting height and angle of the shooting device remain unchanged, as do the lighting height, angle and brightness of the light source device. In addition, the shooting device and the light source device both shoot and illuminate the impacted surface of the vehicle's power battery.

[0118] The analysis platform is also provided with an image preprocessing algorithm for performing image preprocessing on the initial image and post-collision image of the vehicle power battery, including but not limited to: grayscale processing, converting the color image into a grayscale image; filtering and denoising processing, removing noise points in the image and improving the image quality, specifically, median filtering processing can be selected; histogram equalization processing, performing histogram equalization on the image after filtering and denoising processing, enhancing the contrast of the image and making the dent more obvious.

[0119] The CA attention mechanism is introduced in the C2f module in the feature enhancement network of the YOLOv8 model, specifically:

[0120] The feature map F output by the concatenation layer of the C2f module is input into the CA self-attention mechanism module. The feature map F of the CA self-attention mechanism module is encoded in the horizontal and vertical directions to generate the horizontal attention map and the vertical attention map, which are then fused to obtain the comprehensive attention map. The feature map F is weighted using the comprehensive attention map to obtain the enhanced feature map, which is then input into the second convolutional layer of the C2f module.

[0121] In some embodiments, the automobile power battery collision test device also includes a weight sensor to obtain the mass of the impact head; and a speed sensor to obtain the instantaneous impact speed of the impact head.

[0122] The judgment algorithm is also used to judge whether an object with the same mass as the current impact head collides with the vehicle power battery at the same instantaneous impact speed and affects the safety of the vehicle power battery, specifically:

[0123] If the battery capacity is less than or equal to the preset capacity threshold, an object with the same mass as the current impact head collides with the vehicle power battery at the same instantaneous impact speed, which will affect the safety of the vehicle power battery.

[0124] In some embodiments, the analysis platform is also provided with a prediction algorithm for estimating the minimum estimated depression depth at different locations in the automotive power battery that affects the safety of the automotive power battery using a pre-trained deep learning model.

[0125] Embodiment 3

[0126] The present invention also provides an electronic device, including: a processor, a sending device, an input device, an output device and a memory. The processor can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit, or one or more integrated circuits, and is used to execute relevant programs to implement the technical solution provided in the embodiment of the present application. The memory can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device or a random access memory (RAM), and is used to store computer program codes. The computer program codes include computer instructions. When the processor executes the computer instructions, the electronic device executes a method as described in any of the above possible implementation methods.

[0127] Embodiment 4

[0128] The present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes a method as described in any possible implementation manner.

[0129] The beneficial effects of the present invention are:

[0130] The present invention analyzes the position and depth of the impact dent of the automobile power battery after the impact through a deformation analysis module, and then obtains the battery capacity of the automobile power battery after the impact for a preset number of charge and discharge cycles through a life test module, and judges whether the position and depth of the impact dent affect the battery safety according to the battery capacity, and finally uses a pre-trained deep learning model to estimate the minimum dent depth at different positions of the automobile power battery that affects the safety of the automobile power battery, accurately providing a safety judgment after the battery is deformed by impact, and in the dent recognition module, the pre-trained YOLOv8 improved model is used to identify the dent area in the impacted surface image, thereby improving the accuracy of dent recognition, thereby improving the effectiveness and accuracy of the test.

[0131] In the description of the specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0132] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method of each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (RandomAccess Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0133] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. An automobile power battery collision test system, characterized in that: Specifically include: An impact device, used for impacting the vehicle power battery through an impact head; A deformation analysis module, including an image acquisition module, a depression recognition module, an impact depression determination module and a laser distance measuring device; The image acquisition module is used to acquire the image of the impacted surface of the vehicle power battery, wherein the impacted surface image includes an initial image and a post-impact image; The concave recognition module is used to identify concave information in the hit surface image, specifically: using a pre-trained YOLOv8 improved model to identify the concave area in the hit surface image; using edge detection to identify the concave contour from the concave area; The YOLOv8 improved model is improved on the YOLOv8 model, specifically: replacing the ordinary convolution module in the backbone network of the YOLOv8 model with the Ghost convolution module; introducing the CA attention mechanism in the C2f module in the feature enhancement network of the YOLOv8 model; The impact dent determination module is used to determine the impact dent in the post-collision image that is caused by the vehicle power battery being hit by the impact head by comparing the dent information in the initial image and the post-collision image; The laser distance measuring device is used to measure the depth of the impact depression; The life test module is used to obtain the battery capacity after a preset number of charge and discharge cycles of the vehicle power battery after the collision; A judgment module, used to judge whether the depth of the depression at the location of the impact depression of the current vehicle power battery affects the safety of the vehicle power battery according to the battery capacity; The prediction module is used to estimate the minimum dent depth at different locations of the vehicle power battery that affects the safety of the vehicle power battery using a pre-trained deep learning model.

2. The automotive power battery collision test system according to claim 1, characterized in that: The CA attention mechanism is introduced into the C2f module in the feature enhancement network of the YOLOv8 model, specifically: The feature map output by the concatenation layer of the C2f module is input into the CA self-attention mechanism module. The feature map of the CA self-attention mechanism module is encoded in the horizontal and vertical directions to generate the horizontal attention map and the vertical attention map, which are then fused to obtain the comprehensive attention map. The feature map is weighted using the comprehensive attention map to obtain the enhanced feature map, which is then input into the second convolutional layer of the C2f module.

3. The automotive power battery collision test system according to claim 1, characterized in that: The measuring of the depression depth of the impact depression is specifically as follows: Obtaining a distance h1 between the laser distance measuring device and the surface of the non-depressed area of ​​the impacted surface of the vehicle power battery by means of a laser distance measuring device; Obtaining a position with the maximum gray value within the concave contour range of the impact concave in the post-collision image and taking its actual position in the impacted surface of the vehicle power battery as a second distance measurement point; Aim the ranging light beam of the laser ranging device at the second ranging point and obtain the distance h2 between the laser ranging device and the second ranging point; The depth of the impact depression is h2 minus h1.

4. The automotive power battery collision test system according to claim 1, characterized in that: The determination of whether the depth of the depression at the location of the impact depression of the current vehicle power battery affects the safety of the vehicle power battery is specifically as follows: If the battery capacity is less than or equal to the preset capacity threshold, the depth of the dent at the location of the impact dent of the current vehicle power battery affects the safety of the vehicle power battery.

5. The automotive power battery collision test system according to claim 1, characterized in that: The system also includes a parameter acquisition module, which is used to acquire the mass, initial velocity and instantaneous velocity of the impact head.

6. The automotive power battery collision test system according to claim 5, characterized in that: The judgment module is also used to judge whether the safety of the vehicle power battery is affected after an object with the same mass as the current impact head collides with the vehicle power battery at the same instantaneous impact speed according to the battery capacity, specifically: If the battery capacity is less than or equal to the preset capacity threshold, an object with the same mass as the current impact head collides with the vehicle power battery at the same instantaneous impact speed, which will affect the safety of the vehicle power battery.

7. The automotive power battery collision test system according to claim 1, characterized in that: The image acquisition module also includes an image preprocessing unit for performing image preprocessing on the initial image and the post-collision image of the vehicle power battery.

8. An automobile power battery collision test device, using an automobile power battery collision test system as claimed in any one of claims 1 to 7, characterized in that: include: An impact device, used for impacting the vehicle power battery through an impact head; An image acquisition device is used to acquire an image of the impacted surface of the vehicle power battery, wherein the impacted surface image includes an initial image and a post-impact image; A life test device, used to obtain the battery capacity after a preset number of charge and discharge cycles of the vehicle power battery after the collision; A laser rangefinder for measuring the depth of the impact depression; The analysis platform is equipped with dent recognition algorithm, impact dent determination algorithm, judgment algorithm and prediction algorithm; The concave recognition algorithm is used to identify the concave area in the impacted surface image through the pre-trained YOLOv8 improved model, and use edge detection to identify the concave contour from the concave area; The YOLOv8 improved model is improved on the YOLOv8 model, specifically: replacing the ordinary convolution module in the backbone network of the YOLOv8 model with the Ghost convolution module; introducing the CA attention mechanism in the C2f module in the feature enhancement network of the YOLOv8 model; The impact dent is determined by an impact dent determination algorithm, specifically by comparing the dent information in the initial image and the post-collision image to determine the impact dent in the post-collision image that is caused by the vehicle power battery being hit by the impact head; The judgment algorithm is used to judge whether the depth of the depression at the location of the impact depression of the current vehicle power battery affects the safety of the vehicle power battery according to the battery capacity. The prediction algorithm uses a pre-trained deep learning model to estimate the minimum dent depth at different locations of the vehicle power battery that affects the safety of the vehicle power battery.

9. The vehicle power battery collision test device according to claim 8, characterized in that: The CA attention mechanism is introduced into the C2f module in the feature enhancement network of the YOLOv8 model, specifically: The feature map output by the concatenation layer of the C2f module is input into the CA self-attention mechanism module. The feature map of the CA self-attention mechanism module is encoded in the horizontal and vertical directions to generate the horizontal attention map and the vertical attention map, which are then fused to obtain the comprehensive attention map. The feature map is weighted using the comprehensive attention map to obtain the enhanced feature map, which is then input into the second convolutional layer of the C2f module.

10. The vehicle power battery collision test device according to claim 8, characterized in that: The depth of the impact depression is measured as follows: Obtaining a distance h1 between the laser distance measuring device and the surface of the non-depressed area of ​​the impacted surface of the vehicle power battery by means of a laser distance measuring device; Obtaining a position with the maximum gray value within the concave contour range of the impact concave in the post-collision image and taking its actual position in the impacted surface of the vehicle power battery as a second distance measurement point; Aim the ranging light beam of the laser ranging device at the second ranging point and obtain the distance h2 between the laser ranging device and the second ranging point; The depth of the impact depression is h2 minus h1.

Images