New energy battery heat dissipation equipment installation evaluation system

Abstract

The invention discloses a new energy battery heat dissipation equipment installation evaluation system, and belongs to the technical field of new energy electric vehicles. Through the arranged position detection module, the position of the liquid cooling plate can be accurately detected according to the preprocessed RGB image, and the position characteristic value of the current liquid cooling plate is obtained; through the arranged fitting degree detection module, the fitting degree of each fastening bolt on the liquid cooling plate can be accurately detected according to the preprocessed depth image, and the fitting degree characteristic value of the current liquid cooling plate is obtained; and finally, the installation quality of the current liquid cooling plate is scored based on the position characteristic value and the fitting degree characteristic value through a comprehensive evaluation module, an installation quality comprehensive score is obtained, accurate scoring of the installation quality of the liquid cooling plate is achieved, subsequent analysis and adjustment of an installation tool or an installation process are facilitated, and the installation quality of the liquid cooling plate is improved. And the heat dissipation effect and the performance of the battery pack are further ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy electric vehicles, and in particular to an installation evaluation system for new energy battery heat dissipation equipment. Background Art

[0002] New energy electric vehicles, usually referring to pure electric vehicles, are an important type of new energy vehicles. New energy electric vehicles are vehicles that use a single battery as a storage power source. They use batteries as a storage power source, provide electricity to the motor through the battery, drive the motor to operate, and thus drive the car. This type of car has the characteristics of zero emissions, low noise, high efficiency, new technology and new structure. The working principle of new energy electric vehicles is relatively simple. It mainly relies on the electric energy stored in the battery to drive the motor. When the electric energy in the battery passes through the motor, the motor will generate a magnetic field, which in turn drives the car forward. During the whole process, no fuel combustion is required, so no tail gas emissions are generated.

[0003] In new energy electric vehicles, the battery pack liquid cooling plate is a key component in the thermal management system of new energy electric vehicles and a key battery heat dissipation device. The battery pack liquid cooling plate, also known as the battery cooling plate, is a thermal management component that can maintain the temperature stability in the battery pack. It exchanges heat with the battery to take away the excess heat generated by the battery, thereby ensuring that the battery operates within the optimal temperature range, improving the performance of the battery, extending the battery life, and ensuring the safe operation of new energy vehicles. The liquid cooling plate is usually made of a plate-shaped aluminum device with a coolant flow channel inside. These flow channels can be designed at the module level or the cell level according to the different cooling ranges. The module-level liquid cooling plate is usually placed under the battery module and is in direct contact with the battery for heat dissipation. The cell-level liquid cooling plate is closer to the battery cell to achieve precise heat dissipation for each cell.

[0004] When installing the battery liquid cooling plate, its position may deviate, resulting in inaccurate relative position with the battery module, which in turn affects the heat dissipation effect and the performance of the battery pack. In addition, due to insufficient fastening of individual parts or loose fasteners, the liquid cooling plate may not be able to fit tightly with the battery module, which in turn affects the heat dissipation effect and the performance of the battery pack. How to accurately evaluate the installation quality of the liquid cooling plate is an urgent problem to be solved. To this end, a new energy battery heat dissipation equipment installation evaluation system is proposed. Summary of the invention

[0005] The technical problem to be solved by the present invention is: how to accurately evaluate the installation quality of the liquid cooling plate to facilitate the subsequent analysis and adjustment of the installation tooling or installation process, thereby ensuring its heat dissipation effect and the performance of the battery pack, and providing a new energy battery heat dissipation equipment installation evaluation system.

[0006] The present invention solves the above technical problems through the following technical solutions. The present invention includes an image acquisition module, a position detection module, a fit detection module and a comprehensive evaluation module; The image acquisition module is used to use a depth camera to shoot the installed liquid cooling plate directly below it, and simultaneously obtain an RGB image and a corresponding depth image, and preprocess the RGB image and the depth image to obtain the preprocessed RGB image and the depth image; The position detection module is used to detect the position of the liquid cooling plate according to the preprocessed RGB image and obtain the position characteristic value of the current liquid cooling plate; The fit detection module is used to detect the fit of each fastening bolt on the liquid cooling plate according to the preprocessed depth image, and obtain the fit characteristic value of the current liquid cooling plate; The comprehensive evaluation module is used to score the installation quality of the current liquid cooling plate according to the position characteristic value and the fit characteristic value of the current liquid cooling plate to obtain a comprehensive installation quality score.

[0007] Furthermore, the position detection module includes a target detection unit, a distance calculation unit, an angle calculation unit and a position feature value calculation unit; the target detection unit is used to detect the liquid cooling plate, each positioning square plate and each fastening bolt in the preprocessed RGB image using the trained multi-target detection model, and obtain the coordinates of the upper left corner point and the lower right corner point of the detection frame corresponding to the liquid cooling plate, each positioning square plate and each fastening bolt in the image; the distance calculation unit is used to calculate the distance according to the coordinates of the upper left corner point and the lower right corner point of the detection frame of each positioning square plate in the image, and the coordinates of the upper left corner point and the lower right corner point of the detection frame of each fastening bolt in the image. The distance value between each fastening bolt closest to each positioning square plate and the corresponding positioning square plate; the angle calculation unit is used to calculate the angle value formed by the line between each fastening bolt closest to each positioning square plate and the corresponding positioning square plate and the X-axis of the image coordinate system according to the coordinates of the upper left corner point and the lower right corner point of each positioning square plate detection frame in the image, and the coordinates of the upper left corner point and the lower right corner point of each fastening bolt detection frame in the image, and the angle is an acute angle; the position feature value calculation unit is used to calculate and obtain the distance difference and angle difference of the current liquid cooling plate according to the distance obtained by the distance calculation unit and the angle values ​​obtained by the angle calculation unit, that is, to obtain the position feature value.

[0008] Furthermore, in the distance calculation unit, the specific processing process is as follows: Step S11: Obtain the coordinates of the upper left corner and lower right corner of each positioning square plate detection frame in the image, and calculate the coordinates of the center point of each positioning square plate detection frame, which is recorded as DF i , where i represents the i-th positioning square plate detection frame; Step S12: obtaining the coordinates of the upper left corner and the lower right corner of the liquid cooling plate detection frame in the image, and calculating the coordinates of the four corner points of the liquid cooling plate detection frame in the image, the four corner points are YL1, YL2, YL3, and YL4; Step S13: Obtain the coordinates of the upper left corner and the lower right corner of each fastening bolt detection frame in the image, and calculate the coordinates of the center point of each fastening bolt detection frame, which is recorded as LS j , where j represents the jth fastening bolt detection frame; Step S14: For the four corner points of the liquid cooling plate detection frame, traverse the center point coordinates of each fastening bolt detection frame respectively, and obtain the center points of the four fastening bolt detection frames closest to the four corner points of the liquid cooling plate detection frame, which are recorded as the center points of the corner fastening bolt detection frames JLS k , where k is 1, 2, 3 or 4; Step S15: For the center points of the four positioning square plate detection frames, traverse the center points JLS of the corner fastening bolt detection frames respectively k , calculate the center point JLS of the fastening bolt detection frame at each corner k and the center point DF of the nearest positioning square plate detection frame i The distances between them are obtained to obtain four distance values, which are recorded as JD1, JD2, JD3, and JD4, that is, the distance values ​​between each fastening bolt closest to each positioning square plate and the corresponding positioning square plate are obtained.

[0009] Furthermore, in the angle calculation unit, the specific processing process is as follows: Step S16: Set the center point JLS of the corner fastening bolt detection frame in step S15 k and the center point DF of the nearest positioning square plate detection frame i Connect the lines to obtain four line segments, which are recorded as L1, L2, L3, and L4; Step S17: Calculate the angle between each line segment and the X-axis of the image coordinate system, recorded as θ1, θ2, θ3, θ4, that is, obtain the angle between the line between each fastening bolt closest to each positioning square plate and the corresponding positioning square plate and the X-axis of the image coordinate system.

[0010] Furthermore, in the position feature value calculation unit, the specific processing process is as follows: Step S21: Compare the four distance values ​​JD1, JD2, JD3, JD4 with the standard distance value JD 标准 By subtracting, we get four distance differences, which are recorded as JD 1c ,JD 2c ,JD 3c ,JD 4c ; Step S22: Compare the four included angle values ​​θ1, θ2, θ3, and θ4 with the standard angle value θ 标准 Difference, get four angle differences θ 1c ,θ 2c ,θ 3c ,θ 4c The four distance differences and angle differences are the distance difference and angle difference of the current liquid cooling plate, that is, the position characteristic value is obtained.

[0011] Furthermore, the fit detection module includes a contour detection unit, an area determination unit and a fit characteristic value calculation unit; the contour detection unit is used to detect the outer contour line of the liquid cooling plate inside the liquid cooling plate detection frame, and obtain the coordinates of the outer contour line of the liquid cooling plate and each point on it in the image; the area determination unit is used to determine each sub-region inside the plate and the sub-region outside the plate according to the coordinates of the outer contour line of the liquid cooling plate and each point on it in the image; the fit characteristic value calculation unit is used to calculate the fit characteristic value at each fastening bolt according to the depth value of each pixel point in the sub-region inside the plate and the sub-region outside the plate corresponding to each fastening bolt detection frame, that is, to obtain the fit characteristic value of the current liquid cooling plate.

[0012] Furthermore, in the area determination unit, the specific processing process is as follows: Step S31: Obtain the coordinates of the upper left corner and the lower right corner of each fastening bolt detection frame in the image, calculate the coordinates of the four sides of each fastening bolt detection frame, and draw rays along the two sides of each fastening bolt detection frame parallel to the Y axis of the image coordinate system toward the battery module mounting plate. The starting points of the rays are the two corner points of the fastening bolt detection frame close to the outer contour of the liquid cooling plate. The two rays intersect the outer contour of the liquid cooling plate at two points, which are recorded as S j , T j ; Step S32: For each fastening bolt detection frame, the intersection S j , T j is the boundary on one side, the two rays are the boundaries on both ends, and the intersection point S j , T j The outer contour line segment of the liquid cooling plate is taken as the starting edge, and the area covered by the width of N pixels in the direction of the fastening bolt detection frame is recorded as the sub-area A within the plate. 1j , the area covered by N pixels in width towards the edge of the battery module mounting board is recorded as the off-board sub-area A 2j , sub-area A within the plate 1j With the outer sub-area A 2j The corresponding outer contour line segments of the liquid cooling plate are not included, where N is a positive integer.

[0013] Furthermore, in the fit characteristic value calculation unit, the specific processing process is as follows: Step S41: For each fastening bolt detection frame, the sum of the depth values ​​of all pixels in a corresponding sub-region inside the board and a sub-region outside the board is counted, where the sum of the depth values ​​of all pixels in the sub-region inside the board is recorded as DP 1j , the sum of the depth values ​​of all pixels in the sub-region outside the plate is recorded as DP 2j , calculate the mean depth value D of each pixel in the sub-region inside the plate and the sub-region outside the plate 1javg , D 2javg : D 1javg =DP 1j / E1; D 2javg =DP 2j / E2; Among them, E1 and E2 are the number of pixels in the corresponding sub-region inside the plate and the sub-region outside the plate respectively; Step S42: For each fastening bolt detection frame, calculate the mean value D of the depth value 2javg Subtract the mean of the depth values ​​D 1javg The difference is recorded as the depth mean difference D cj , that is, the fitting characteristic value of each fastening bolt is obtained, that is, the fitting characteristic value of the current liquid cooling plate is obtained.

[0014] Furthermore, in the comprehensive evaluation module, the specific processing process is as follows: Step S51: Based on the four distance difference values ​​JD obtained in step S21 1c ,JD 2c ,JD 3c ,JD 4c Search in the preset distance difference-distance score database to obtain the corresponding distance scores FJ1, FJ2, FJ3, and FJ4; Step S52: Calculate the four distance difference angle differences θ obtained in step S22 1c ,θ 2c ,θ 3c ,θ 4c Search in the preset angle difference-angle score database to obtain the corresponding angle scores FZ1, FZ2, FZ3, FZ4; Step S53: Determine the depth mean difference D obtained in step S42. cj Search in the preset depth mean difference-fit score database to obtain the corresponding fit score FD j ; Step S54: Calculate the mean value FJ of all distance scores avg , the mean of all angle scores FZ avg , the mean of all fit scores FD avg, and then calculate the comprehensive score of installation quality F total : F total =FJ avg +FZ avg +FD avg .

[0015] Furthermore, the distance difference-distance score database presets a correspondence between the range of distance differences and the distance scores, the angle difference-angle score database presets a correspondence between the range of angle differences and the angle scores, and the depth mean difference-fit score database presets a correspondence between the range of depth mean difference and the fit score.

[0016] Compared with the prior art, the present invention has the following advantages: the new energy battery heat dissipation equipment installation evaluation system can accurately detect the position of the liquid cooling plate according to the preprocessed RGB image through the set position detection module, and obtain the position characteristic value of the current liquid cooling plate; through the set fit detection module, the fit of each fastening bolt on the liquid cooling plate can be accurately detected according to the preprocessed depth image, and the fit characteristic value of the current liquid cooling plate can be obtained; finally, the installation quality of the current liquid cooling plate is scored based on the position characteristic value and the fit characteristic value through the comprehensive evaluation module, and a comprehensive score of the installation quality is obtained, thereby achieving an accurate score of the installation quality of the liquid cooling plate, facilitating the subsequent analysis and adjustment of the installation tooling or the installation process, thereby ensuring its heat dissipation effect and the performance of the battery pack. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a structural schematic diagram of a new energy battery heat dissipation equipment installation evaluation system in an embodiment of the present invention; Figure 2 is a schematic diagram of the position between the fastening bolts and the positioning square plate in the RGB image in an embodiment of the present invention; Figure 3 is the sub-region A in the plate in the depth image in the embodiment of the present invention 1j With the outer sub-area A 2j Schematic diagram of the location; In the figure: 1. Battery module mounting plate; 21. Flow channel plate (hollow) of liquid cooling plate; 22. Mounting plate of liquid cooling plate; 3. Fastening bolts; 4. Positioning square plate; 5. Fastening bolt detection frame; 6. Outer contour of liquid cooling plate. DETAILED DESCRIPTION

[0018] The following is a detailed description of an embodiment of the present invention. This embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation method and a specific operation process are given, but the protection scope of the present invention is not limited to the following embodiment.

[0019] like Figures 1 to 3 As shown, this embodiment provides a technical solution: a new energy battery heat dissipation equipment installation evaluation system, including an image acquisition module, a position detection module, a fit detection module and a comprehensive evaluation module; The following is a further description of the functions and specific processing procedures of the above modules: In this embodiment, the image acquisition module is used to use a depth camera to shoot the installed liquid cooling plate directly below it, and simultaneously obtain an RGB image and a corresponding depth image, and preprocess the RGB image and the depth image to obtain the preprocessed RGB image and depth image, and then send the RGB image to the position detection module, and send the depth image to the fit detection module to perform subsequent position detection and fit detection work.

[0020] More specifically, the image acquisition module includes an image acquisition unit and an image preprocessing unit. The image acquisition unit is used to photograph the liquid cooling plate using an RGBD depth camera to obtain an RGB image and a corresponding depth image; the image preprocessing unit is used to preprocess the RGB image and the depth image.

[0021] To be more specific, the RGB image / depth image includes a battery module mounting plate 1 and an installed liquid cooling plate. The flow channel plate 21 (hollow) of the liquid cooling plate and the mounting plate 22 of the liquid cooling plate together constitute the liquid cooling plate. The liquid cooling plate is an integral component. There is also a corresponding battery module at the upper end of the liquid cooling plate, but it cannot be photographed due to angle issues, so the battery module is not included in the image.

[0022] More specifically, the preprocessing methods include but are not limited to noise reduction, contrast enhancement processing, and size adjustment.

[0023] It should be noted that the RGBD depth camera is a device that integrates a color camera and a depth camera module. Among them, the color camera module is responsible for acquiring color images (RGB images), and it uses a traditional color CCD / CMOS sensor. The depth camera module is responsible for acquiring depth information, and it is generally composed of an infrared transmitter, a CMOS sensor, and a corresponding algorithm module. The depth camera module determines the distance between the target object and the camera by emitting an infrared signal and measuring the time it takes for the signal to be reflected back from the target object (or based on other technologies such as structured light), thereby generating a depth image. The resolution, size, and other specifications of the depth image are consistent with those of the above-mentioned RGB image, and the pixels correspond one to one. The optical axis of the RGBD depth camera is considered to be perpendicular to the lower end surface of the liquid cooling plate and the battery module mounting plate 1.

[0024] In this embodiment, the position detection module is used to detect the position of the liquid cooling plate according to the preprocessed RGB image to obtain the position characteristic value of the current liquid cooling plate.

[0025] More specifically, the position detection module includes a target detection unit, a distance calculation unit, an angle calculation unit and a position feature value calculation unit; the target detection unit is used to detect the liquid cooling plate, each positioning square plate 4 and each fastening bolt 3 in the preprocessed RGB image using a trained multi-target detection model, and obtain the coordinates of the upper left corner and lower right corner of the detection frame corresponding to the liquid cooling plate, each positioning square plate 4 and each fastening bolt 3 in the image; the distance calculation unit is used to calculate the distance according to the coordinates of the upper left corner and lower right corner of the detection frame of each positioning square plate in the image, and the coordinates of the upper left corner and lower right corner of the detection frame of each fastening bolt 5 in the image. The distance value between each fastening bolt 3 closest to each positioning square plate 4 and the corresponding positioning square plate 4; the angle calculation unit is used to calculate the angle value formed by the line between each fastening bolt 3 closest to each positioning square plate 4 and the corresponding positioning square plate 4 and the X-axis of the image coordinate system according to the coordinates of the upper left corner point and the lower right corner point of each positioning square plate detection frame in the image, and the coordinates of the upper left corner point and the lower right corner point of each fastening bolt detection frame 5 in the image, and the angle is an acute angle; the position feature value calculation unit is used to calculate and obtain the distance difference and the angle difference of the current liquid cooling plate according to the distance obtained by the distance calculation unit and the angle values ​​obtained by the angle calculation unit, that is, to obtain the position feature value.

[0026] More specifically, the multi-target detection model is trained based on the yolo v3s network.

[0027] More specifically, in the distance calculation unit, the specific processing process is as follows: Step S11: Obtain the coordinates of the upper left corner and lower right corner of each positioning square plate detection frame in the image, and calculate the coordinates of the center point of each positioning square plate detection frame, which is recorded as DF i , where i represents the i-th positioning square plate detection frame, which can be 1, 2, 3 or 4; Step S12: obtaining the coordinates of the upper left corner and the lower right corner of the liquid cooling plate detection frame in the image, and calculating the coordinates of the four corner points of the liquid cooling plate detection frame in the image, the four corner points are YL1, YL2, YL3, and YL4; Step S13: Obtain the coordinates of the upper left corner and the lower right corner of each fastening bolt detection frame 5 in the image, and calculate the coordinates of the center point of each fastening bolt detection frame 5, which is recorded as LS j , where j represents the j-th fastening bolt detection frame 5; Step S14: For the four corner points of the liquid cooling plate detection frame, traverse the center point coordinates of each fastening bolt detection frame 5 respectively, and obtain the center points of the four fastening bolt detection frames 5 closest to the four corner points of the liquid cooling plate detection frame, which are recorded as the center points of the corner fastening bolt detection frames JLS k , where k is 1, 2, 3 or 4; Step S15: For the center points of the four positioning square plate detection frames, traverse the center points JLS of the corner fastening bolt detection frames respectively k , calculate the center point JLS of the fastening bolt detection frame at each corner k and the center point DF of the nearest positioning square plate detection frame i The distances between them are obtained to obtain four distance values, which are recorded as JD1, JD2, JD3, and JD4, that is, the distance values ​​between each fastening bolt 3 closest to each positioning square plate 4 and the corresponding positioning square plate 4 are obtained.

[0028] It should be noted that in the above steps, the distances in the images are all calculated using Euclidean distance.

[0029] More specifically, in the angle calculation unit, the specific processing process is as follows: Step S16: Set the center point JLS of the corner fastening bolt detection frame in step S15 k and the center point DF of the nearest positioning square plate detection frame i Connect the lines to obtain four line segments, denoted as L1, L2, L3, and L4, see Figure 2 .

[0030] Step S17: Calculate the angle between each line segment and the X-axis of the image coordinate system, recorded as θ1, θ2, θ3, θ4, that is, obtain the angle between the line between each fastening bolt 3 closest to each positioning square plate 4 and the corresponding positioning square plate 4 and the X-axis of the image coordinate system.

[0031] More specifically, in the position feature value calculation unit, the specific processing process is as follows: Step S21: Compare the four distance values ​​JD1, JD2, JD3, JD4 with the standard distance value JD 标准 By subtracting, we get four distance differences, which are recorded as JD 1c ,JD 2c ,JD 3c ,JD 4c ; Step S22: Compare the four included angle values ​​θ1, θ2, θ3, and θ4 with the standard angle value θ 标准 Difference, get four angle differences θ 1c ,θ 2c ,θ 3c ,θ 4cThe four distance differences and angle differences are the distance difference and angle difference of the current liquid cooling plate, that is, the position characteristic value is obtained.

[0032] It should be noted that the standard distance value JD 标准 With the standard angle value θ 标准 The present invention uses the distance difference and angle difference of the corresponding positions as the characteristic value of the installation position of the current liquid cooling plate, which is more convenient and accurate.

[0033] In this embodiment, the fit detection module is used to detect the fit of each fastening bolt 3 on the liquid cooling plate according to the preprocessed depth image, and obtain the fit characteristic value of the current liquid cooling plate.

[0034] More specifically, the fit detection module includes a contour detection unit, an area determination unit and a fit feature value calculation unit; the contour detection unit is used to detect the outer contour line 6 of the liquid cooling plate inside the liquid cooling plate detection frame, and obtain the coordinates of the outer contour line 6 of the liquid cooling plate and each point thereon in the image; the area determination unit is used to determine each sub-region inside the plate and each sub-region outside the plate according to the coordinates of the outer contour line 6 of the liquid cooling plate and each point thereon in the image; the fit feature value calculation unit is used to calculate the fit feature value at each fastening bolt 3 according to the depth value of each pixel point in the inner sub-region and the outer sub-region corresponding to each fastening bolt detection frame 5, that is, to obtain the fit feature value of the current liquid cooling plate.

[0035] More specifically, the contour detection unit is used to detect the outer contour line 6 of the liquid cooling plate inside the liquid cooling plate detection frame by using the contour detection function in OpenCV.

[0036] More specifically, in the area determination unit, the specific processing process is as follows: Step S31: Obtain the coordinates of the upper left corner and the lower right corner of each fastening bolt detection frame 5 in the image, calculate the coordinates of the four sides of each fastening bolt detection frame 5, and draw rays along the two sides of each fastening bolt detection frame 5 parallel to the Y axis of the image coordinate system toward the battery module mounting plate 1. The starting points of the rays are the two corner points of the fastening bolt detection frame 5 close to the outer contour line 6 of the liquid cooling plate. The two rays intersect the outer contour line 6 of the liquid cooling plate at two points, which are recorded as S j , T j ,See Figure 3 ; Step S32: For each fastening bolt detection frame 5, the intersection S j , T j is the boundary on one side, the two rays are the boundaries on both ends, and the intersection point S j , T jThe 6 segments of the outer contour of the liquid cooling plate are taken as the starting edge, and the area covered by the width of 10 pixels in the direction of the fastening bolt detection frame 5 is recorded as the sub-area A within the plate. 1j The area covered by 10 pixels in width toward the edge of the battery module mounting plate 1 is recorded as the off-board sub-area A 2j , sub-area A within the plate 1j With the outer sub-area A 2j The corresponding 6 segments of the outer contour line of the liquid cooling plate are not included.

[0037] More specifically, in the fit characteristic value calculation unit, the specific processing process is as follows: Step S41: For each fastening bolt detection frame 5, the sum of the depth values ​​of all pixels in a corresponding sub-region inside the board and a sub-region outside the board is counted, where the sum of the depth values ​​of all pixels in the sub-region inside the board is recorded as DP 1j , the sum of the depth values ​​of all pixels in the sub-region outside the plate is recorded as DP 2j , calculate the mean depth value D of each pixel in the sub-region inside the plate and the sub-region outside the plate 1javg , D 2javg : D 1javg =DP 1j / E1; D 2javg =DP 2j / E2; Among them, E1 and E2 are the number of pixels in the corresponding sub-region inside the plate and the sub-region outside the plate respectively; Step S42: For each fastening bolt detection frame 5, calculate the mean value D of the depth value 2javg Subtract the mean of the depth values ​​D 1javg The difference is recorded as the depth mean difference D cj , that is, the characteristic value of the fit at each fastening bolt 3 is obtained, that is, the characteristic value of the fit of the current liquid cooling plate is obtained. In the present invention, the depth mean difference is innovatively used to characterize the local fit at each fastening bolt 3, which is conducive to obtaining an accurate comprehensive score of installation quality in the subsequent process.

[0038] In this embodiment, the comprehensive evaluation module is used to score the installation quality of the current liquid cooling plate according to the position characteristic value and the fit characteristic value of the current liquid cooling plate to obtain the installation quality comprehensive score F total .

[0039] More specifically, in the comprehensive evaluation module, the specific processing process is as follows: Step S51: Based on the four distance difference values ​​JD obtained in step S21 1c ,JD 2c ,JD 3c ,JD 4cSearch in the preset distance difference-distance score database to obtain the corresponding distance scores FJ1, FJ2, FJ3, and FJ4; Step S52: Calculate the four distance difference angle differences θ obtained in step S22 1c ,θ 2c ,θ 3c ,θ 4c Search in the preset angle difference-angle score database to obtain the corresponding angle scores FZ1, FZ2, FZ3, FZ4; Step S53: Determine the depth mean difference D obtained in step S42. cj Search in the preset depth mean difference-fit score database to obtain the corresponding fit score FD j ; Step S54: Calculate the mean value FJ of all distance scores avg , the mean of all angle scores FZ avg , the mean of all fit scores FD avg , and then calculate the comprehensive score of installation quality F total : F total =FJ avg +FZ avg +FD avg .

[0040] In this embodiment, the distance difference-distance score database presets a correspondence between the range of distance differences and the distance scores, the angle difference-angle score database presets a correspondence between the range of angle differences and the angle scores, and the depth mean difference-fit score database presets a correspondence between the range of depth mean difference and the fit score.

[0041] It should be noted that in this embodiment, the position characteristic values, fit characteristic values, comprehensive installation quality scores and intermediate parameter values ​​of each liquid cooling plate in the calculation process will be recorded in the corresponding database to facilitate subsequent tracing and analysis and adjustment of the installation tooling or installation process.

[0042] To summarize, the new energy battery heat dissipation equipment installation evaluation system of the above-mentioned embodiment can accurately detect the position of the liquid cooling plate according to the preprocessed RGB image through the set position detection module, and obtain the position characteristic value of the current liquid cooling plate; through the set fit detection module, it can accurately detect the fit of each fastening bolt on the liquid cooling plate according to the preprocessed depth image, and obtain the fit characteristic value of the current liquid cooling plate; finally, the comprehensive evaluation module is used to score the installation quality of the current liquid cooling plate based on the position characteristic value and the fit characteristic value, and a comprehensive score of the installation quality is obtained, thereby achieving accurate scoring of the installation quality of the liquid cooling plate, facilitating subsequent analysis and adjustment of the installation tooling or installation process, thereby ensuring its heat dissipation effect and the performance of the battery pack.

[0043] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying 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 the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0044] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" 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 representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0045] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A new energy battery heat dissipation equipment installation evaluation system, characterized in that: It includes image acquisition module, position detection module, fit detection module and comprehensive evaluation module; The image acquisition module is used to use a depth camera to shoot the installed liquid cooling plate directly below it, and simultaneously obtain an RGB image and a corresponding depth image, and preprocess the RGB image and the depth image to obtain the preprocessed RGB image and depth image; The position detection module is used to detect the position of the liquid cooling plate according to the preprocessed RGB image and obtain the position characteristic value of the current liquid cooling plate; The fit detection module is used to detect the fit of each fastening bolt on the liquid cooling plate according to the preprocessed depth image, and obtain the fit characteristic value of the current liquid cooling plate; The comprehensive evaluation module is used to score the installation quality of the current liquid cooling plate according to the position characteristic value and the fit characteristic value of the current liquid cooling plate to obtain a comprehensive installation quality score.

2. A new energy battery heat dissipation equipment installation evaluation system according to claim 1, characterized in that: The position detection module includes a target detection unit, a distance calculation unit, an angle calculation unit and a position feature value calculation unit; the target detection unit is used to detect the liquid cooling plate, each positioning square plate and each fastening bolt in the preprocessed RGB image using the trained multi-target detection model, and obtain the coordinates of the upper left corner point and the lower right corner point of the detection frame corresponding to the liquid cooling plate, each positioning square plate and each fastening bolt in the image; the distance calculation unit is used to calculate the distance to each positioning square plate according to the coordinates of the upper left corner point and the lower right corner point of the detection frame of each positioning square plate in the image, and the coordinates of the upper left corner point and the lower right corner point of the detection frame of each fastening bolt in the image. The distance value between each fastening bolt closest to the positioning square plate and the corresponding positioning square plate; the angle calculation unit is used to calculate the angle value formed by the line between each fastening bolt closest to each positioning square plate and the corresponding positioning square plate and the X-axis of the image coordinate system according to the coordinates of the upper left corner point and the lower right corner point of each positioning square plate detection frame in the image, and the coordinates of the upper left corner point and the lower right corner point of each fastening bolt detection frame in the image, and the angle is an acute angle; the position feature value calculation unit is used to calculate and obtain the distance difference and angle difference of the current liquid cooling plate according to the distance obtained by the distance calculation unit and the angle values ​​obtained by the angle calculation unit, that is, to obtain the position feature value.

3. A new energy battery heat dissipation equipment installation evaluation system according to claim 2, characterized in that: In the distance calculation unit, the specific processing process is as follows: Step S11: Obtain the coordinates of the upper left corner and lower right corner of each positioning square plate detection frame in the image, and calculate the coordinates of the center point of each positioning square plate detection frame, which is recorded as DF i , where i represents the i-th positioning square plate detection frame; Step S12: obtaining the coordinates of the upper left corner and the lower right corner of the liquid cooling plate detection frame in the image, and calculating the coordinates of the four corner points of the liquid cooling plate detection frame in the image, the four corner points are YL1, YL2, YL3, and YL4; Step S13: Obtain the coordinates of the upper left corner and the lower right corner of each fastening bolt detection frame in the image, and calculate the coordinates of the center point of each fastening bolt detection frame, which is recorded as LS j , where j represents the jth fastening bolt detection frame; Step S14: For the four corner points of the liquid cooling plate detection frame, traverse the center point coordinates of each fastening bolt detection frame respectively, and obtain the center points of the four fastening bolt detection frames closest to the four corner points of the liquid cooling plate detection frame, which are recorded as the center points of the corner fastening bolt detection frames JLS k , where k is 1, 2, 3 or 4; Step S15: For the center points of the four positioning square plate detection frames, traverse the center points JLS of the corner fastening bolt detection frames respectively k , calculate the center point JLS of the fastening bolt detection frame at each corner k and the center point DF of the nearest positioning square plate detection frame i The distances between them are obtained to obtain four distance values, which are recorded as JD1, JD2, JD3, and JD4, that is, the distance values ​​between each fastening bolt closest to each positioning square plate and the corresponding positioning square plate are obtained.

4. A new energy battery heat dissipation equipment installation evaluation system according to claim 3, characterized in that: In the angle calculation unit, the specific processing process is as follows: Step S16: Set the center point JLS of the corner fastening bolt detection frame in step S15 k and the center point DF of the nearest positioning square plate detection frame i Connect the lines to obtain four line segments, which are recorded as L1, L2, L3, and L4; Step S17: Calculate the angle between each line segment and the X-axis of the image coordinate system, recorded as θ1, θ2, θ3, θ4, that is, obtain the angle between the line between each fastening bolt closest to each positioning square plate and the corresponding positioning square plate and the X-axis of the image coordinate system.

5. A new energy battery heat dissipation equipment installation evaluation system according to claim 4, characterized in that: In the position feature value calculation unit, the specific processing process is as follows: Step S21: Compare the four distance values ​​JD1, JD2, JD3, JD4 with the standard distance value JD 标准 By subtracting, we get four distance differences, which are recorded as JD 1c ,JD 2c ,JD 3c ,JD 4c ; Step S22: Compare the four included angle values ​​θ1, θ2, θ3, and θ4 with the standard angle value θ 标准 Difference, get four angle differences θ 1c ,θ 2c ,θ 3c ,θ 4c The four distance differences and angle differences are the distance difference and angle difference of the current liquid cooling plate, that is, the position characteristic value is obtained.

6. A new energy battery heat dissipation equipment installation evaluation system according to claim 5, characterized in that: The fit detection module includes a contour detection unit, an area determination unit and a fit feature value calculation unit; the contour detection unit is used to detect the outer contour line of the liquid cooling plate inside the liquid cooling plate detection frame, and obtain the coordinates of the outer contour line of the liquid cooling plate and each point thereon in the image; the area determination unit is used to determine each sub-region inside the plate and the sub-region outside the plate according to the coordinates of the outer contour line of the liquid cooling plate and each point thereon in the image; the fit feature value calculation unit is used to calculate the fit feature value at each fastening bolt according to the depth value of each pixel point in the sub-region inside the plate and the sub-region outside the plate corresponding to each fastening bolt detection frame, that is, to obtain the fit feature value of the current liquid cooling plate.

7. A new energy battery heat dissipation equipment installation evaluation system according to claim 6, characterized in that: In the area determination unit, the specific processing process is as follows: Step S31: Obtain the coordinates of the upper left corner and the lower right corner of each fastening bolt detection frame in the image, calculate the coordinates of the four sides of each fastening bolt detection frame, and draw rays along the two sides of each fastening bolt detection frame parallel to the Y axis of the image coordinate system toward the battery module mounting plate. The starting points of the rays are the two corner points of the fastening bolt detection frame close to the outer contour of the liquid cooling plate. The two rays intersect the outer contour of the liquid cooling plate at two points, which are recorded as S j , T j ; Step S32: For each fastening bolt detection frame, the intersection S j , T j is the boundary on one side, the two rays are the boundaries on both ends, and the intersection point S j , T j The outer contour line segment of the liquid cooling plate is taken as the starting edge, and the area covered by the width of N pixels in the direction of the fastening bolt detection frame is recorded as the sub-area A within the plate. 1j , the area covered by N pixels in width towards the edge of the battery module mounting board is recorded as the off-board sub-area A 2j , sub-area A within the plate 1j With the outer sub-area A 2j The corresponding outer contour line segments of the liquid cooling plate are not included, where N is a positive integer.

8. A new energy battery heat dissipation equipment installation evaluation system according to claim 7, characterized in that: In the fit characteristic value calculation unit, the specific processing process is as follows: Step S41: For each fastening bolt detection frame, the sum of the depth values ​​of all pixels in a corresponding sub-region inside the board and a sub-region outside the board is counted, where the sum of the depth values ​​of all pixels in the sub-region inside the board is recorded as DP 1j , the sum of the depth values ​​of all pixels in the sub-region outside the plate is recorded as DP 2j , calculate the mean depth value D of each pixel in the sub-region inside the plate and the sub-region outside the plate 1javg , D 2javg : D 1javg =DP 1j / E1; D 2javg =DP 2j / E2; Among them, E1 and E2 are the number of pixels in the corresponding sub-region inside the plate and the sub-region outside the plate respectively; Step S42: For each fastening bolt detection frame, calculate the mean value D of the depth value 2javg Subtract the mean of the depth values ​​D 1javg The difference is recorded as the depth mean difference D cj , that is, the fitting characteristic value of each fastening bolt is obtained, that is, the fitting characteristic value of the current liquid cooling plate is obtained.

9. A new energy battery heat dissipation equipment installation evaluation system according to claim 8, characterized in that: In the comprehensive evaluation module, the specific processing process is as follows: Step S51: Based on the four distance difference values ​​JD obtained in step S21 1c ,JD 2c ,JD 3c ,JD 4c Search in the preset distance difference-distance score database to obtain the corresponding distance scores FJ1, FJ2, FJ3, and FJ4; Step S52: Calculate the four distance difference angle differences θ obtained in step S22 1c ,θ 2c ,θ 3c ,θ 4c Search in the preset angle difference-angle score database to obtain the corresponding angle scores FZ1, FZ2, FZ3, FZ4; Step S53: Determine the depth mean difference D obtained in step S42. cj Search in the preset depth mean difference-fit score database to obtain the corresponding fit score FD j ; Step S54: Calculate the mean value FJ of all distance scores avg , the mean of all angle scores FZ avg , the mean of all fit scores FD avg , and then calculate the comprehensive score of installation quality F total : F total =FJ avg +FZ avg +FD avg 。 10. A new energy battery heat dissipation equipment installation evaluation system according to claim 9, characterized in that: The distance difference-distance score database presets a correspondence between the range of distance differences and the distance scores, the angle difference-angle score database presets a correspondence between the range of angle differences and the angle scores, and the depth mean difference-fit score database presets a correspondence between the range of depth mean difference and the fit score.

Images