Metallized film capacitor self-healing area automatic identification method, device and system and application thereof

Abstract

The invention discloses a metallized film capacitor self-healing area automatic identification method, device and system and application thereof. The method comprises the following steps: acquiring image information of a capacitor metallized film; performing graying processing on the image information to obtain a grayed image; and carrying out image binaryzation, image denoising and contour detection on the grayed image to obtain parameter information of a self-healing area of the capacitor metallized film. According to the method, the self-healing area is accurately recognized based on image recognition of mathematical morphology, and the reliability and consistency of detection are improved.

Description

Technical Field

[0001] The present invention belongs to the field of power capacitors and relates to a method, a device, a system and an application thereof for automatically identifying a self-healing area of ​​a metallized film capacitor. Background Art

[0002] DC-Link capacitors have the characteristics of small size, large capacity, high voltage tolerance, large current tolerance, low loss, excellent temperature performance, high energy storage density, and good safety and reliability. The self-healing capacitor on the DC side bridge arm of the converter valve hall of the converter station is used for voltage support and DC filtering. It is an important component to maintain the stable operation of the entire transmission system, maintain good coordination, and ensure the quality of power transmission. According to the current research results at home and abroad, the damage of metallized film capacitors is mainly caused by the continuous occurrence of self-healing on the metallized film. Therefore, mastering the mechanism and parameters of self-healing is of great significance for designing capacitors to increase the life of capacitors, reduce enterprise costs, and improve the stability of power system transmission.

[0003] The self-healing of metallized film is a very complex process, involving both physical changes and chemical reactions. The self-healing process can be summarized as follows: the dielectric film breaks down and generates a current channel, the metal electrode near the breakdown point evaporates due to the heat generated by the current, the breakdown point is isolated, the discharge arc is extinguished, and the insulation is restored. After the dielectric film is partially broken down, a current channel is generated at the breakdown point, and the external energy is injected into the breakdown point to form a discharge loop. The electrode area removed around the breakdown point is the self-healing area, which is generally in the order of square millimeters, so the capacitance loss caused by a single self-healing is also very small, generally in the order of pF. However, multiple self-healing may occur in each charge and discharge cycle of the capacitor, and as the dielectric film ages, the number of self-healing events in each charge and discharge cycle will gradually increase. The superposition of multiple self-healing will cause a significant decrease in capacitance. When the actual capacitance is less than 95% of the rated capacitance, the capacitor fails.

[0004] Based on this, it is imperative to study a self-healing identification system and solution for metallized film capacitors. Summary of the invention

[0005] In order to overcome the above problems, the present invention proposes a method, device, system and application of automatic identification of the self-healing area of ​​a metallized film capacitor, the method comprising: obtaining image information of the metallized film of the capacitor; graying the image information to obtain a grayed image; performing image binarization, image denoising and contour detection on the grayed image to obtain parameter information of the self-healing area of ​​the metallized film of the capacitor. The present invention accurately identifies the self-healing area based on image recognition based on mathematical morphology, thereby improving the reliability and consistency of detection.

[0006] Specifically, the purpose of the present invention is to provide the following aspects:

[0007] In a first aspect, a method for automatically identifying a self-healing area of ​​a metallized film capacitor is provided, the method comprising:

[0008] Acquiring image information of the capacitor metallized film;

[0009] Performing grayscale processing on the image information to obtain a grayscale image;

[0010] The grayscale image is subjected to image binarization, image denoising and contour detection to obtain parameter information of the self-healing region of the capacitor metallized film.

[0011] The grayscale processing of the image information to obtain the grayscale image includes the following steps: converting the three channels (R, G, B) representing the colors in the pixel channels of the image information into a single grayscale value, and then summing the values ​​through coefficients.

[0012] The logic of the image binarization algorithm is: converting grayscale values ​​greater than a critical value to a maximum value, and converting grayscale values ​​less than the critical value to a minimum value.

[0013] Among them, the opening operation denoising method is used to perform image denoising.

[0014] The parameters include length, width and area.

[0015] In a second aspect, a device for automatically identifying a self-healing area of ​​a metallized film capacitor is provided, the device comprising:

[0016] An image information acquisition component, used to acquire image information of the capacitor metallized film;

[0017] A grayscale processing component, used for performing grayscale processing on the image information to obtain a grayscale image;

[0018] The grayscale image processing component is used to perform image binarization, image denoising and contour detection on the grayscale image to obtain parameter information of the self-healing area of ​​the capacitor metallized film.

[0019] In a third aspect, a system for automatically identifying the self-healing area of ​​a metallized film capacitor is provided, the system comprising a data processing unit, and the data processing unit comprises the device described in the second aspect.

[0020] Wherein, the system further comprises:

[0021] An automatic sample changing unit, which is used to place or automatically change the capacitor metallized film;

[0022] The CCD image acquisition unit is used to capture the image information of the capacitor metallized film.

[0023] In a fourth aspect, a method for detecting a self-healing region of a metallized film capacitor is provided, wherein the system described in the third aspect is used to detect the self-healing region of the metallized film of the capacitor.

[0024] According to a fifth aspect, a storable medium is provided, wherein the storable medium is used to store a computer program, wherein the computer program includes instructions for implementing the method according to the first aspect.

[0025] The beneficial effects of the present invention include:

[0026] (1) The method for automatically identifying the self-healing area of ​​a metallized film capacitor provided by the present invention accurately identifies the self-healing area based on mathematical morphology image recognition, thereby improving the reliability and consistency of detection.

[0027] (2) The system provided by the present invention obtains information of different positions of capacitor metallized film samples, thereby providing a sufficient data source for accurately analyzing self-healing area parameters; the device realizes automatic sample changing and autonomous detection of sample information through an automatic sample changing unit; and provides solutions for parties with different demands through a CCD image acquisition unit and a data processing unit.

[0028] (3) The system provided by the present invention realizes high-speed and efficient automatic sample replacement, autonomous detection, damage identification and data analysis. Based on the artificial intelligence algorithm of image recognition and machine learning, it realizes data analysis of the self-healing area, generates a detection report with one click, obtains comprehensive and accurate analysis data, and provides an efficient solution for the liberation of manpower in enterprises and research institutes. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] By reading the detailed description of the preferred specific embodiments below, various other advantages and benefits of the present invention will become clear to those of ordinary skill in the art. The drawings in the specification are only used for the purpose of illustrating the preferred embodiments and are not considered to be limitations of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative work.

[0030] In the attached picture:

[0031] Figure 1 A schematic diagram showing the structure of the automatic self-healing area identification system of the metallized film capacitor of the present invention is shown;

[0032] Figure 2 The schematic diagram of the structure of the automatic sample changing unit of the present invention is shown;

[0033] Figure 3 The image information collected by the area array CCD camera in Example 1 is shown;

[0034] Figure 4 The image information collected in Example 1 is converted into a grayscale image;

[0035] Figure 5 The edge information of the self-healing point of the capacitor metallized film in Example 1 is shown;

[0036] Figure 6 The area ratio distribution of the self-healing region in Example 1 is shown;

[0037] Figure 7 A statistical diagram of the self-healing area in Example 1 is shown;

[0038] Description of Reference Numerals

[0039] 1-Automatic sample changing unit;

[0040] 11- MCU area;

[0041] 12- driving wheel;

[0042] 13- driven wheel;

[0043] 14-surface light source area;

[0044] 15-controller area;

[0045] 16- support plate;

[0046] 17-support frame;

[0047] 18- bottom plate fixing plate;

[0048] 19-concave groove;

[0049] 2-CCD image acquisition unit;

[0050] 3- Data processing unit. DETAILED DESCRIPTION

[0051] The following will refer to the attached Figures 1 to 7 Specific embodiments of the present invention are described in more detail. Although specific embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0052] It should be noted that certain words are used in the specification and claims to refer to specific components. Those skilled in the art should understand that technicians may use different nouns to refer to the same component. This specification and claims do not use the difference in nouns as a way to distinguish components, but use the difference in the functions of the components as the criterion for distinction. As mentioned throughout the specification and claims, "including" or "comprising" is an open term, so it should be interpreted as "including but not limited to". The subsequent description of the specification is a preferred embodiment of the present invention, but the description is based on the general principles of the specification and is not intended to limit the scope of the present invention. The scope of protection of the present invention shall be determined by the attached claims.

[0053] In the description of the present invention, it should be noted that the terms "upper", "lower", "inner", "outer", "front", "rear", etc. indicate positions or positional relationships based on the working state of the present invention, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", "third", and "fourth" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0054] To facilitate understanding of the embodiments of the present invention, further explanation will be given below by taking specific embodiments as examples in conjunction with the accompanying drawings, and each of the accompanying drawings does not constitute a limitation on the embodiments of the present invention.

[0055] In a first aspect, a method for automatically identifying a self-healing area of ​​a metallized film capacitor according to the present invention comprises:

[0056] Step 1, obtaining image information of the capacitor metallized film;

[0057] Step 2, graying the image information to obtain a grayed image;

[0058] Step 3: perform image binarization, image denoising and contour detection on the grayscale image to obtain parameter information of the self-healing area of ​​the capacitor metallized film.

[0059] In step 2, the grayscale of the image is used to improve the recognition accuracy. After grayscale, the pixel information of the self-healing area only contains white grayscale values, while the remaining normal areas are other values, so the difficulty of contour division can be reduced and the resolution accuracy can be improved. The specific implementation method is: the three channels (R, G, B) representing the color in the pixel channel of the image information are converted into a single grayscale value (Y) by summing the coefficients, for example, the three channels (R, G, B) representing the color in the pixel channel of the image information are converted into a single grayscale value Y by Y=0.3R+0.5G+0.2B.

[0060] In step 3, image binarization converts the grayscale image into a binary image, which is a basic method of image segmentation. The logic of the image binarization algorithm is: convert grayscale values ​​greater than a certain critical value to maximum values, and convert grayscale values ​​less than this value to minimum values, specifically:

[0061] ;

[0062] In the formula, x represents the horizontal coordinate of the pixel; y represents the horizontal and vertical coordinates of the pixel; dst(x,y) represents the binary value of the pixel after binarization; maxval is the set binary maximum value, usually 250~255, for example 255; src(x,y) represents the grayscale value of the pixel in the grayscale image; thresh represents the set threshold, usually 180~255, for example 180.

[0063] In step 3, image denoising is used to deal with interference caused by external environments such as image transmission, thereby improving data accuracy. Here, for subsequent contour processing, the opening operation denoising method is used. The opening operation is an extension of the erosion and expansion algorithm to eliminate background noise points, smooth boundaries without significantly changing the volume, and separate adhesion targets. The specific algorithm logic is:

[0064] ;

[0065] In the formula, A represents the denoising area, B is the template used for the operation, and the above formula means that A is first eroded by B, and then A is expanded by B, that is, the opening operation is completed.

[0066] The mathematical logic of the corrosion involved above is:

[0067] ;

[0068] Among them (B) z Represents the translation when the structural element B is at position z. The result of the erosion operation is the set of all elements z in set A that can completely contain the structural element B. This process shrinks the image and eliminates the boundary part of the image. It is often used to eliminate small, meaningless objects or noise.

[0069] The mathematical logic of the expansion involved above is:

[0070] ;

[0071] The result of the dilation operation is the set of all elements z in set A that intersect with the structural element B. This process makes the image larger and is often used to connect adjacent objects or fill holes inside objects.

[0072] In step 3, contour detection is used to obtain the shape and position information of the self-healing area, that is, to obtain the edge of the self-healing point of the capacitor metallized film, and obtain the parameters of the self-healing area according to the edge of the self-healing point, and the parameters include length, width and area. Specifically, the cv2.findContours function is used to detect the contours in the image, and the cv2.drawContours is used to draw the contours, that is, contour detection is implemented. Use the for loop function to traverse all the self-healing areas, and use the cv2.contourArea function to obtain the length, width and area of ​​each area; according to the area size, the self-healing area area ratio distribution and self-healing area area statistics are performed, and the area ratio is divided into 0-400 mm according to the area. 2 、400-800mm 2 , 800-1200 mm 2 and 1200 mm 2 The above four ranges.

[0073] In step 3, all self-healing areas are traversed to perform threshold judgment, and the output results are stored by the print function to perform self-healing area area ratio distribution and self-healing area area statistics.

[0074] In a second aspect, a device for automatically identifying a self-healing area of ​​a metallized film capacitor according to the present invention comprises:

[0075] An image information acquisition component, used to acquire image information of the capacitor metallized film;

[0076] A grayscale processing component, used for performing grayscale processing on the image information to obtain a grayscale image;

[0077] The grayscale image processing component is used to perform image binarization, image denoising and contour detection on the grayscale image to obtain parameter information of the self-healing area of ​​the capacitor metallized film.

[0078] In the present invention, in an image information acquisition component, image information of the capacitor metallized film is acquired; then in a grayscale processing component, three channels (R, G, B) representing colors in the image information pixel channel are converted into a single grayscale value (Y) by summing coefficients, thereby completing grayscale processing and obtaining a grayscale image; then, in the grayscale image processing component, image binarization, image denoising and contour detection are performed in sequence to obtain parameter information of the self-healing area of ​​the capacitor metallized film.

[0079] Furthermore, the logic of the image binarization algorithm is: convert the grayscale value greater than a certain critical value to a maximum value, and convert the grayscale value less than this value to a minimum value; the image denoising adopts the opening operation denoising method; the contour detection uses the cv2.findContours function to detect the contour in the image, and uses cv2.drawContours to draw the contour, and then uses the for loop function to traverse all the self-healing areas, and obtains the length, width and area of ​​each area through the cv2.contourArea function, and uses the print function to store the output results for self-healing area area ratio distribution and self-healing area area statistics.

[0080] In a third aspect, a self-healing area automatic identification system for a metallized film capacitor according to the present invention comprises:

[0081] An automatic sample changing unit 1, which is used to place or automatically change the capacitor metallized film;

[0082] CCD image acquisition unit 2, which is used to capture capacitor metallized film image information;

[0083] The data processing unit 3 is used to process the image information to realize automatic identification of the self-healing area of ​​the capacitor metallized film.

[0084] In the present invention, the data processing unit 3 is connected to the CCD image acquisition unit 2 , and the CCD image acquisition unit 2 is located above the automatic sample changing unit 1 .

[0085] Furthermore, in order to ensure that the CCD image acquisition unit 2 can capture high-quality, high-contrast images, the system also includes a surface light source.

[0086] According to the present invention, Figure 2 As shown, the automatic sample changing unit 1 comprises:

[0087] A driving wheel 12, which is used to drive the capacitor metallized film to move and change samples;

[0088] The driven wheel 13 is used to assist the driving wheel 12 to move and change the capacitor metallized film;

[0089] A fixed stepper motor driving element, wherein the fixed stepper motor driving element is used to drive the driving wheel 12;

[0090] The single chip computer area 11 is used to place and fix the stepper motor driving components; the surface light source area 14 is used to place the surface light source;

[0091] A controller, the controller is used to control the operation of the driving wheel 12;

[0092] A controller area 15, which is used to place a controller;

[0093] A support plate 16, which is used to fix the driving wheel 12 and the driven wheel 13, and provides a surface light source area 14 and a controller area 15;

[0094] A support frame 17, which is used to fix the CCD image acquisition unit 2;

[0095] The bottom plate fixing plate 18 is used for the single chip computer area 11 , the driving wheel 12 , the driven wheel 13 , the surface light source area 14 , the controller area 15 , the support plate 16 and the support frame 17 .

[0096] In one embodiment, a concave groove 19 is provided on the bottom plate fixing plate 18, and preferably there are two concave grooves 19, which are symmetrically, parallelly, and of equal length arranged on the left and right sides of the bottom plate fixing plate 18; the concave groove 19 is used to fix the support plate 16, that is, there are preferably two support plates 16, and the support plate 16 is clamped in the groove of the concave groove 19.

[0097] Furthermore, the support plate 16 is provided with holes for fixing the driving wheel 12 and the driven wheel 13. The driving wheel 12 and the driven wheel 13 are respectively arranged at two ends of the support plate 16.

[0098] According to the present invention, there are preferably two driving wheels 12, which are arranged in parallel up and down at one end of the support plate 16; there are preferably two driven wheels 13, which are arranged in parallel up and down at the other end of the support plate 16 and are at the same horizontal position as the two driving wheels 12.

[0099] When in use, the capacitor metallized film is clamped between the upper and lower wheels of the driving wheel 12 and the upper and lower wheels of the driven wheel 13, and the capacitor metallized film is driven to move by rotation to achieve sample change.

[0100] In the present invention, a surface light source area 14 and a controller area 15 are provided between the concave grooves 19, and the surface light source area 14 and the controller area 15 are both arranged between the driving wheel 12 and the driven wheel 13, that is, it can be understood that the driving wheel 12, the surface light source area 14, the controller area 15 and the driven wheel 13 are provided between the support plates 16 from left to right.

[0101] In the present invention, the support frame 17 is fixedly arranged on the left side of the driving wheel 12, that is, away from the end of the surface light source area 14. A ring for placing the CCD image acquisition unit 2 is provided on the support frame 17, and the ring is located above the surface light source area 14, and the ring is located higher than the height of the surface light source, the driving wheel 12 and the driven wheel 13. When in use, the surface light source is placed in the surface light source area 14, and the surface light source illuminates the capacitor metallized film, so that the capacitor metallized film is clearly visible in the field of view of the CCD image acquisition unit 2.

[0102] In the present invention, a single chip computer area 11 is provided on the outer side of the support plate 16 , that is, on the outer side of the concave groove 19 .

[0103] When in use, the capacitor metallized film is fixed between the upper and lower wheels of the driving wheel 12 and the driven wheel 13, and the capacitor metallized film is driven to move by the rotation of the driving wheel 12. The surface light source is placed in the surface light source area 14, the controller is placed in the controller area 15, the CCD image acquisition unit 2 is placed in the support frame 17, and the fixed stepper motor drive element is placed in the single-chip computer area 11.

[0104] In the present invention, the fixed stepper motor driving element includes a single chip microcomputer, a stepper motor driver and a closed-loop stepper motor, the single chip microcomputer is connected to the stepper motor driver, and the stepper motor driver is connected to the closed-loop stepper motor. The single chip microcomputer sends a pulse signal to the stepper motor driver, and the stepper motor driver controls the closed-loop stepper motor according to the received pulse signal. The closed-loop stepper motor drives the driving wheel 12 through gear transmission, thereby realizing the movement and sample change of the capacitor metallized film.

[0105] When in use, the capacitor metallized film is inserted between the upper and lower wheels of the driving wheel 12 and the upper and lower wheels of the driven wheel 13; when changing samples, the pulse signal generated by the single-chip microcomputer controls the stepper motor driver, thereby driving the closed-loop stepper motor and the driving wheel 12 to realize automatic movement and sample changing of the capacitor metallized film, and the driven wheel 13 assists in maintaining the tension and smooth movement of the capacitor metallized film.

[0106] Furthermore, the frequency of the pulse signal generated by the single-chip microcomputer determines the replacement speed of the capacitor metallized film. The frequency of the pulse signal generated by the single-chip microcomputer is converted into a current signal through the stepper motor driver, which then drives the closed-loop stepper motor to rotate, thereby driving the movement of the capacitor metallized film through the driving wheel 12. The faster the frequency, the faster the driving speed, the faster the sample change speed, and the slower the frequency, the slower the driving speed, the slower the sample change speed. That is, it can be understood that the single-chip microcomputer controls the driving speed of the stepper motor driver and then controls the speed of the driving wheel 12, thereby regulating the replacement speed of the capacitor metallized film to achieve automatic sample change.

[0107] Furthermore, in the fixed stepper motor drive element, the single chip microcomputer sends a pulse signal to the stepper motor driver, and the stepper motor driver controls the closed-loop stepper motor. For example, the single chip microcomputer provides 220V AC power, which is converted into 36V DC power by a DC module for powering the stepper motor driver, and the 36V DC power is converted into 5V DC power by a DC module for powering the closed-loop stepper motor.

[0108] In the present invention, the CCD image acquisition unit 2 is preferably a CCD camera, and the CCD image acquisition unit 2 is fixed on a support frame 17 .

[0109] Furthermore, the CCD camera converts the optical signal into a current signal, and the current signal is amplified and converted into analog to digital to achieve image acquisition, storage, transmission, processing and reproduction. The CCD camera has the advantages of small size, light weight, low power consumption, low operating voltage, shock and vibration resistance, stable performance, long life, high sensitivity, low noise, large dynamic range, fast response speed, self-scanning function, small image distortion, no residual image, and integrated circuit process technology production, high pixel integration, precise size, and low commercial production cost.

[0110] In the present invention, the CCD camera is a linear array CCD camera or an area array CCD camera, preferably an area array CCD camera. The linear array CCD camera is composed of a series of linear photosensitive elements, which are arranged in one direction and can capture one-dimensional image information at a higher speed, and is more suitable for fast scanning; the area array CCD camera is composed of a two-dimensional array of photosensitive elements, which can capture the entire two-dimensional image, usually has a larger photosensitive area, and can capture a wider range of image information for comprehensive image analysis.

[0111] In the present invention, the data processing unit 3 realizes contour recognition and automatic segmentation of the self-healing area based on mathematical morphology image recognition and machine learning artificial intelligence algorithms.

[0112] According to a preferred embodiment, the data processing unit 3 comprises:

[0113] An image information acquisition component, used to acquire image information of the capacitor metallized film;

[0114] A grayscale processing component, used for performing grayscale processing on the image information to obtain a grayscale image;

[0115] The grayscale image processing component is used to perform image binarization, image denoising and contour detection on the grayscale image to obtain parameter information of the self-healing area of ​​the capacitor metallized film.

[0116] In the present invention, the image information acquisition component receives the image information collected by the CCD image acquisition unit 2. The grayscale processing component performs grayscale processing on the image information to obtain a grayscale image. At this time, due to the loss of the electrode in the self-healing area, it is a white transparent area under the recognition of the scanning CCD image acquisition unit 2, while the remaining undamaged areas are normal colors; in the grayscale image, the pixel information of the self-healing area only includes white grayscale values, while the remaining normal areas are other values, so the difficulty of contour division can be reduced and the resolution accuracy can be improved.

[0117] In a fourth aspect, a method for detecting a self-healing region of a metallized film capacitor according to the present invention is provided, wherein the system described in the third aspect is used to detect the self-healing region of the metallized film of the capacitor.

[0118] In a fifth aspect, a storable medium is provided according to the present invention, wherein the storable medium is used to store a computer program, wherein the computer program includes instructions for implementing the method described in the first aspect.

[0119] The present invention is further described below through specific examples, but these examples are merely exemplary and do not constitute any limitation to the scope of protection of the present invention.

[0120] Example 1

[0121] like Figure 1 to Figure 2 As shown, the capacitor metallized film is placed between the upper and lower wheels of the driving wheel 12 and the driven wheel 13, the surface light source is placed in the surface light source area 14, the controller is placed in the controller area 15, and the area array CCD camera is used as the CCD image acquisition unit 2. The image information collected by the area array CCD camera is as shown in FIG. Figure 3 As shown in the figure, the collected image information is converted into a single grayscale value Y by Y=0.3R+0.5G+0.2B to represent the color of the three channels (R, G, B) in the pixel channel. The grayscale image is as follows: Figure 4 As shown; the following algorithm logic is used to convert the grayscale image into a binary image:

[0122] , set thresh to 180 and maxval to 255; then, through the open operation To denoise, , ; Use the cv2.findContours function to detect contours in the image, and use cv2.drawContours to draw the contours. Figure 5 The edge information of the capacitor metallization film self-healing point is shown. Figure 5The self-healing area of ​​the capacitor metallized film is presented intuitively. The for loop function is used to traverse all the self-healing areas. The length, width and area of ​​each area are obtained through the cv2.contourArea function. The self-healing area area ratio distribution and self-healing area area statistics are performed according to the area size. The area ratio is divided into 0-400 mm according to the area. 2 、400-800mm 2 , 800-1200 mm 2 and 1200 mm 2 The above four ranges. Figure 5 Ten regions are randomly selected from the graph, and their length, width and area parameters are shown in Table 1:

[0123]

[0124] Figure 6 The self-healing area ratio distribution is shown. It can be seen that the self-healing area is between 0 and 400 mm 2 The self-healing area is between 400 and 800 mm. 2 The self-healing area is 900~1200mm 2 The self-healing area is 1200 mm 2 The above is 30%.

[0125] Figure 7 Shows the self-healing area statistics, the self-healing area is between 0~400mm 2 The number of self-healing areas is 4, and the area of ​​self-healing area is between 400 and 800 mm. 2 The number of self-healing areas is 6, and the self-healing area is 900~1200mm 2 The number of self-healing areas is 7 and the area of ​​self-healing area is 1200 mm 2 The number above is 3.

[0126] The present invention is described in detail above in combination with preferred embodiments and exemplary examples. However, it should be noted that these specific embodiments are only illustrative explanations of the present invention and do not constitute any limitation on the protection scope of the present invention. Without exceeding the spirit and protection scope of the present invention, various improvements, equivalent substitutions or modifications may be made to the technical content of the present invention and its embodiments, which all fall within the protection scope of the present invention. The protection scope of the present invention shall be subject to the attached claims.

Claims

1. A method for automatically identifying the self-healing area of ​​a metallized film capacitor, characterized in that: The method comprises: Acquiring image information of the capacitor metallized film; Performing grayscale processing on the image information to obtain a grayscale image; The grayscale image is subjected to image binarization, image denoising and contour detection to obtain parameter information of the self-healing region of the capacitor metallized film.

2. The method according to claim 1, characterized in that Preferably, grayscale processing is performed on the image information to obtain a grayscale image, which includes the following steps: converting the three channels (R, G, B) representing the colors in the pixel channels of the image information into a single grayscale value, and then summing the values ​​through coefficients.

3. The method according to claim 1, characterized in that The logic of the image binarization algorithm is: converting grayscale values ​​greater than a critical value to a maximum value, and converting grayscale values ​​less than the critical value to a minimum value.

4. The method according to claim 1, characterized in that: The image denoising is performed using the opening operation denoising method.

5. The method according to claim 1, characterized in that The parameters include length, width and area.

6. A device for automatically identifying the self-healing area of ​​a metallized film capacitor, characterized in that: The device comprises: An image information acquisition component, used to acquire image information of the capacitor metallized film; A grayscale processing component, used for performing grayscale processing on the image information to obtain a grayscale image; The grayscale image processing component is used to perform image binarization, image denoising and contour detection on the grayscale image to obtain parameter information of the self-healing area of ​​the capacitor metallized film.

7. A metallized film capacitor self-healing area automatic identification system, characterized in that: The system comprises a data processing unit (3), which comprises the device according to claim 6.

8. The system according to claim 7, characterized in that The system further comprises: An automatic sample changing unit (1) for placing or automatically changing a capacitor metallized film; A CCD image acquisition unit (2) is used to capture capacitor metallized film image information.

9. A method for detecting the self-healing area of ​​a metallized film capacitor, characterized in that: The system described in claim 7 or 8 is used to detect the self-healing area of ​​the capacitor metallized film.

10. A storable medium, characterized in that: The storable medium is used to store a computer program, wherein the computer program includes instructions for implementing the method according to any one of claims 1 to 5.

Images