A new energy vehicle battery fault detection method

Abstract

The present invention discloses a new energy vehicle battery fault detection method, which relates to the field of battery detection technology, and includes the following steps: S1, collecting the surface working image data of the battery, and smoothing the surface working image data to obtain improved surface working image data; S2, determining the pixel quality amplitude of each pixel point; S3, determining whether the battery has a fault according to the pixel quality amplitude of each pixel point in the improved surface working image data. Determining whether there is an oxide in the improved surface working image data by the change of the pixel quality amplitude overcomes the shortcoming that manual observation may lead to missed detection due to carelessness, traversing the appearance image of the battery, ensuring that the detection is in place, and timely discovering the battery fault.

Description

Technical Field

[0001] The present invention relates to the technical field of battery detection, and in particular to a method for detecting battery failure in a new energy vehicle. Background Art

[0002] With the popularity of new energy vehicles, batteries are their core components, and their performance and safety are directly related to the overall performance of the vehicle and the user experience. When detecting battery faults, the appearance of the battery, as the most easily obtained and basic parameter, should be the first step in fault detection. When inspecting the appearance of the battery, bulging or deformation is easier to observe. However, during the use of new energy batteries (especially batteries using electrolytes), the chemicals inside the battery may react with oxygen or other gases in the air, resulting in oxides around the terminals. These oxides usually appear in the form of white or green powder; and the electrolyte in the battery (such as sulfuric acid) may volatilize due to increased temperature or poor sealing, and the volatilized electrolyte vapor may react with the metal material of the terminal to form oxides. However, oxides such as white or green powder around the terminal are not easy to be found. Therefore, a battery fault detection method needs to be designed to address this problem. Summary of the invention

[0003] In order to solve the above problems, the present invention proposes a new energy vehicle battery fault detection method.

[0004] The technical solution of the present invention is: a new energy vehicle battery fault detection method comprises the following steps:

[0005] S1, collecting the surface working image data of the battery, and smoothing the surface working image data to obtain improved surface working image data;

[0006] S2, using a sliding window to traverse the improved surface working image data to obtain an image quality matrix, and using the image quality matrix to process the improved surface working image data to determine the pixel quality amplitude of each pixel point;

[0007] S3. Determine whether the battery is faulty based on the pixel quality amplitude of each pixel point in the improved surface working image data.

[0008] Furthermore, S2 includes the following sub-steps:

[0009] S21, using a sliding window to traverse the surface improvement work image data, and mapping the pixel value of each pixel point into a vector as a pixel vector of each pixel point;

[0010] S22, determining the sliding vector of each pixel point in the corresponding sliding window;

[0011] S23, determining the traversal difference value of each pixel point according to the pixel vector and the sliding vector of each pixel point;

[0012] S24, determining an image quality matrix according to the traversal difference values ​​of all pixels;

[0013] S25. Using the image quality matrix, the surface improvement working image data is processed to obtain the pixel quality amplitude of each pixel point.

[0014] The beneficial effect of the above further scheme is: in the present invention, after S1 performs smoothing processing on the surface working image data of the battery, the brightness of the image will tend to be flat, but it may also cause the image to be blurred, so the pixel points of the improved surface working image data are processed in S2 to improve the image clarity. The present invention uses a sliding window to traverse each pixel point of the improved surface working image data, generates a pixel vector and a sliding vector of the pixel point, and the calculation results of the two vectors can determine the traversal difference value of each pixel point, and the upper and lower limits of the image quality range are determined by the traversal difference value. The elements of the image quality matrix are determined by the pixel points whose pixel values ​​belong to the upper and lower limits, and the pixel values ​​of the improved image data are processed using the image quality matrix to obtain the pixel quality amplitude of each pixel point itself.

[0015] Furthermore, in S22, the sliding vector s of the i-th pixel in the corresponding sliding window i The expression is:

[0016] ;

[0017] In the formula, Concat[·] represents the vector concatenation function, u i represents the pixel vector of the i-th pixel, v0 represents the pixel vector of the first pixel in the sliding window corresponding to the i-th pixel, and v1 represents the pixel vector of the last pixel in the sliding window corresponding to the i-th pixel.

[0018] Furthermore, in S23, the traversal difference value E of the i-th pixel point i The calculation formula is:

[0019] ;

[0020] In the formula, s i represents the sliding vector of the i-th pixel in the corresponding sliding window, u i Represents the pixel vector of the i-th pixel, Indicates a round-up operation.

[0021] Further, S24 includes the following sub-steps:

[0022] S241, arranging the traversal difference values ​​of each pixel point from large to small, taking the average of the first three traversal difference values ​​and the last three traversal difference values ​​as the direct threshold, and taking the average of the remaining traversal difference values ​​as the indirect threshold;

[0023] S242, using the smaller value of the direct threshold and the indirect threshold as the lower limit of the image quality interval, and using the larger value of the direct threshold and the indirect threshold as the upper limit of the image quality interval, to generate an image quality interval;

[0024] S243, extracting pixel points whose pixel values ​​belong to the image quality range as an inherent pixel point set, and determining an inherent value of image quality;

[0025] S244. Determine an image quality matrix according to the image quality intrinsic value.

[0026] Furthermore, in S243, the calculation formula of the image quality inherent value G is:

[0027] ;

[0028] In the formula, Represents the first pixel in the intrinsic pixel set The traversal difference value of pixels, Represents the first pixel in the intrinsic pixel set The sliding vector of the pixel point in the corresponding sliding window, Represents the first pixel in the intrinsic pixel set The pixel vector of pixels, Represents the first pixel in the intrinsic pixel set The pixel value of a pixel, Represents the total number of pixels in the intrinsic pixel set, Represents an exponential function.

[0029] Further, in S244, the image quality matrix The expression is:

[0030] ;

[0031] In the formula, Indicates the intrinsic value of image quality, Indicates the lower limit of the image quality range, Indicates the upper limit of the image quality range.

[0032] Further, in S25, the pixel quality amplitude of the pixel points in the surface working image data is improved. The calculation formula is:

[0033] ;

[0034] In the formula, Represents the horizontal coordinate of the pixel point, Represents the vertical coordinate of the pixel point. Indicates improving the pixel value of the pixel in the image data. Represents the image quality matrix.

[0035] Furthermore, in S3, the difference in pixel quality amplitudes between adjacent pixels is calculated. If the difference is greater than or equal to a threshold, the battery is faulty; otherwise, the battery is not faulty.

[0036] When the difference in the pixel quality amplitude between the connected pixels is large, it means that the pixel has a pixel mutation, and oxidation may exist here. The threshold value can be determined based on multiple experiments.

[0037] The beneficial effects of the present invention are as follows: the present invention performs image processing on the terminal condition of the battery appearance, determines the pixel quality amplitude of each pixel point in the battery surface image, determines whether there is oxide in the improved surface working image data through the change of the pixel quality amplitude, overcomes the disadvantage that manual observation may lead to missed detection due to carelessness, traverses the battery appearance image, ensures that the detection is in place, and discovers the battery fault in time. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 The figure is a flow chart of a new energy vehicle battery fault detection method. DETAILED DESCRIPTION

[0039] The embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0040] like Figure 1 As shown, the present invention provides a new energy vehicle battery fault detection method, comprising the following steps:

[0041] S1, collecting the surface working image data of the battery, and smoothing the surface working image data to obtain improved surface working image data;

[0042] S2, using a sliding window to traverse the improved surface working image data to obtain an image quality matrix, and using the image quality matrix to process the improved surface working image data to determine the pixel quality amplitude of each pixel point;

[0043] S3. Determine whether the battery is faulty based on the pixel quality amplitude of each pixel point in the improved surface working image data.

[0044] In this embodiment of the present invention, S2 includes the following sub-steps:

[0045] S21, using a sliding window to traverse the surface improvement work image data, and mapping the pixel value of each pixel point into a vector as a pixel vector of each pixel point;

[0046] S22, determining the sliding vector of each pixel point in the corresponding sliding window;

[0047] S23, determining the traversal difference value of each pixel point according to the pixel vector and the sliding vector of each pixel point;

[0048] S24, determining an image quality matrix according to the traversal difference values ​​of all pixels;

[0049] S25. Using the image quality matrix, the surface improvement working image data is processed to obtain the pixel quality amplitude of each pixel point.

[0050] In the present invention, after S1 performs smoothing processing on the surface working image data of the battery, the brightness of the image will tend to be flat, but it may also cause the image to be blurred. Therefore, in S2, the pixel points of the improved surface working image data are processed to improve the image clarity. The present invention uses a sliding window to traverse each pixel point of the improved surface working image data to generate a pixel vector and a sliding vector of the pixel point. The calculation results of the two vectors can determine the traversal difference value of each pixel point, and the upper and lower limits of the image quality range are determined by the traversal difference value. The elements of the image quality matrix are determined by the pixel points whose pixel values ​​belong to the upper and lower limits. The image quality matrix is ​​used to process the pixel values ​​of the improved image data to obtain the pixel quality amplitude of each pixel point itself.

[0051] In the embodiment of the present invention, in S22, the i-th pixel point is in the sliding vector s corresponding to the sliding window. i The expression is:

[0052] ;

[0053] In the formula, Concat[·] represents the vector concatenation function, u i represents the pixel vector of the i-th pixel, v0 represents the pixel vector of the first pixel in the sliding window corresponding to the i-th pixel, and v1 represents the pixel vector of the last pixel in the sliding window corresponding to the i-th pixel.

[0054] In the embodiment of the present invention, in S23, the traversal difference value E of the i-th pixel point i The calculation formula is:

[0055] ;

[0056] In the formula, s i represents the sliding vector of the i-th pixel in the corresponding sliding window, ui Represents the pixel vector of the i-th pixel, Indicates a round-up operation.

[0057] In this embodiment of the present invention, S24 includes the following sub-steps:

[0058] S241, arranging the traversal difference values ​​of each pixel point from large to small, taking the average of the first three traversal difference values ​​and the last three traversal difference values ​​as the direct threshold, and taking the average of the remaining traversal difference values ​​as the indirect threshold;

[0059] S242, using the smaller value of the direct threshold and the indirect threshold as the lower limit of the image quality interval, and using the larger value of the direct threshold and the indirect threshold as the upper limit of the image quality interval, to generate an image quality interval;

[0060] S243, extracting pixel points whose pixel values ​​belong to the image quality range as an inherent pixel point set, and determining an inherent value of image quality;

[0061] S244. Determine an image quality matrix according to the image quality intrinsic value.

[0062] In the embodiment of the present invention, in S243, the calculation formula of the image quality inherent value G is:

[0063] ;

[0064] In the formula, Represents the first pixel in the intrinsic pixel set The traversal difference value of pixels, Represents the first pixel in the intrinsic pixel set The sliding vector of the pixel point in the corresponding sliding window, Represents the first pixel in the intrinsic pixel set The pixel vector of pixels, Represents the first pixel in the intrinsic pixel set The pixel value of a pixel, Represents the total number of pixels in the intrinsic pixel set, Represents an exponential function.

[0065] In the embodiment of the present invention, in S244, the image quality matrix The expression is:

[0066] ;

[0067] In the formula, Indicates the intrinsic value of image quality, Indicates the lower limit of the image quality range, Indicates the upper limit of the image quality range.

[0068] In the embodiment of the present invention, in S25, the pixel quality amplitude of the pixel points in the surface working image data is improved. The calculation formula is:

[0069] ;

[0070] In the formula, Represents the horizontal coordinate of the pixel point, Represents the vertical coordinate of the pixel point. Indicates improving the pixel value of the pixel in the image data. Represents the image quality matrix.

[0071] In the embodiment of the present invention, in S3, the difference in pixel quality amplitudes between adjacent pixels is calculated. If the difference is greater than or equal to a threshold, the battery is faulty; otherwise, the battery is not faulty.

[0072] When the difference in the pixel quality amplitude between the connected pixels is large, it means that the pixel has a pixel mutation, and oxidation may exist here. The threshold value can be determined based on multiple experiments.

[0073] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific variations and combinations that do not deviate from the essence of the present invention based on the technical revelations disclosed by the present invention, and these variations and combinations are still within the protection scope of the present invention.

Claims

1. A new energy vehicle battery fault detection method, characterized in that: The following steps are involved: S1, collecting the surface working image data of the battery, and smoothing the surface working image data to obtain improved surface working image data; S2, using a sliding window to traverse the improved surface working image data to obtain an image quality matrix, and using the image quality matrix to process the improved surface working image data to determine the pixel quality amplitude of each pixel point; S3, determining whether the battery is faulty according to the pixel quality amplitude of each pixel point in the surface working image data; The S2 comprises the following sub-steps: S21, using a sliding window to traverse the surface improvement work image data, and mapping the pixel value of each pixel point into a vector as a pixel vector of each pixel point; S22, determining the sliding vector of each pixel point in the corresponding sliding window; S23, determining the traversal difference value of each pixel point according to the pixel vector and the sliding vector of each pixel point; S24, determining an image quality matrix according to the traversal difference values ​​of all pixels; S25, using the image quality matrix, processing the surface improvement working image data to obtain the pixel quality amplitude of each pixel point; In S22, the i-th pixel point is in the sliding vector s of the corresponding sliding window. i The expression is: ； In the formula, Concat[·] represents the vector concatenation function, u i represents the pixel vector of the i-th pixel, v0 represents the pixel vector of the first pixel in the sliding window corresponding to the i-th pixel, and v1 represents the pixel vector of the last pixel in the sliding window corresponding to the i-th pixel; In S23, the traversal difference value E of the i-th pixel point i The calculation formula is: ； In the formula, s i represents the sliding vector of the i-th pixel in the corresponding sliding window, u i Represents the pixel vector of the i-th pixel, Indicates rounding up operation; The S24 comprises the following sub-steps: S241, arranging the traversal difference values ​​of each pixel point from large to small, taking the average of the first three traversal difference values ​​and the last three traversal difference values ​​as the direct threshold, and taking the average of the remaining traversal difference values ​​as the indirect threshold; S242, using the smaller value of the direct threshold and the indirect threshold as the lower limit of the image quality interval, and using the larger value of the direct threshold and the indirect threshold as the upper limit of the image quality interval, to generate an image quality interval; S243, extracting pixel points whose pixel values ​​belong to the image quality range as an inherent pixel point set, and determining an inherent value of image quality; S244, determining an image quality matrix according to the image quality intrinsic value; In S243, the calculation formula of the image quality inherent value G is: ； In the formula, Represents the first pixel in the intrinsic pixel set The traversal difference value of pixels, Represents the first pixel in the intrinsic pixel set The sliding vector of the pixel point in the corresponding sliding window, Represents the first pixel in the intrinsic pixel set The pixel vector of pixels, Represents the first pixel in the intrinsic pixel set The pixel value of a pixel, Represents the total number of pixels in the intrinsic pixel set, represents the exponential function; In S244, the image quality matrix The expression is: ； In the formula, Indicates the intrinsic value of image quality, Indicates the lower limit of the image quality range, Indicates the upper limit of the image quality range; In said S25, the pixel quality amplitude of the pixel points in the surface working image data is improved The calculation formula is: ； In the formula, Represents the horizontal coordinate of the pixel point, Represents the vertical coordinate of the pixel point. Indicates improving the pixel value of the pixel in the image data. Represents the image quality matrix.

2. The new energy vehicle battery fault detection method according to claim 1, characterized in that: In S3, the difference in pixel quality amplitudes between adjacent pixels is calculated. If the difference is greater than or equal to a threshold, the battery is faulty; otherwise, the battery is not faulty.

Images