Fault detection method and device of oil-immersed equipment and computer equipment thereof

Abstract

The application relates to a fault detection method and device of an oil-immersed equipment and computer equipment thereof, and relates to the technical field of image processing. The method comprises the following steps: acquiring a to-be-detected image; wherein the to-be-detected image is an internal structure image of the to-be-detected oil-immersed equipment; performing image quality detection on each color channel in the to-be-detected image to obtain a quality detection result corresponding to each color channel; performing image processing on each color channel in the to-be-detected image based on the quality detection result corresponding to each color channel to obtain a target image; and performing fault detection on the oil-immersed equipment based on the target image. The application realizes targeted color correction processing on each color channel, prevents over-correction of the color channel, improves the definition of the internal structure image of the oil-immersed equipment, and ensures that the fault position of the oil-immersed equipment can be determined according to the internal structure image of the oil-immersed equipment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, in particular to a fault detection method and device of an oil-immersed equipment and a computer device thereof. BACKGROUND

[0002] The oil-immersed equipment is one of the important components of the power system, and its running state will directly affect the stability and reliability of the power system. However, with the increase of the use time of the oil-immersed equipment and the accelerated aging of the internal components of the oil-immersed equipment, the oil-immersed equipment malfunctions frequently, and the fault position of the oil-immersed equipment is random and complex, so it is difficult to determine the fault position and the cause only by the experience of the staff.

[0003] In the prior art, the internal structure image of the oil-immersed equipment can be obtained, and the internal image of the oil-immersed equipment is analyzed by combining the visual detection technology, so as to determine the fault position of the oil-immersed equipment.

[0004] However, there is a liquid medium (for example, transformer oil, lubricating oil, etc.) in the oil-immersed equipment, and the turbidity of the liquid medium will increase with the increase of the use time, so the internal structure image of the oil-immersed equipment will be affected by the liquid medium to cause color distortion, and cannot be used to determine the fault position of the oil-immersed equipment. SUMMARY

[0005] Therefore, it is necessary to provide a fault detection method and device of an oil-immersed equipment and a computer device thereof, which can determine the fault position of the oil-immersed equipment.

[0006] In a first aspect, the present application provides a fault detection method of an oil-immersed equipment. The method comprises:

[0007] obtaining a to-be-detected image; wherein the to-be-detected image is an internal structure image of a to-be-detected oil-immersed equipment;

[0008] performing image quality detection on each color channel in the to-be-detected image to obtain a quality detection result corresponding to each color channel;

[0009] performing image processing on each color channel in the to-be-detected image based on the quality detection result corresponding to each color channel to obtain a target image;

[0010] performing fault detection on the oil-immersed equipment based on the target image.

[0011] In one embodiment, performing image processing on each color channel in the to-be-detected image based on the quality detection result corresponding to each color channel to obtain a target image comprises:

[0012] adjust a pixel value of a pixel point corresponding to the first color channel in the to-be-detected image to obtain a first processing image corresponding to the first color channel;

[0013] fuse the first processing image corresponding to the first color channel and / or an original channel image corresponding to the second color channel in the to-be-detected image to obtain a target image; wherein the search result of the first color channel is that the quality detection passes; and the detection result of the second color channel is that the quality detection fails.

[0014] In one of the embodiments, adjusting the pixel value of the pixel point corresponding to the first color channel in the to-be-detected image to obtain the first processing image corresponding to the first color channel comprises:

[0015] determining a pixel standard deviation corresponding to the first color channel according to an original pixel value of the pixel point corresponding to the first color channel in the to-be-detected image;

[0016] adjusting the pixel value of the pixel point corresponding to the first color channel in the to-be-detected image based on the pixel standard deviation corresponding to the first color channel to obtain the first processing image corresponding to the first color channel.

[0017] In one of the embodiments, adjusting the pixel value of the pixel point corresponding to the first color channel in the to-be-detected image based on the pixel standard deviation corresponding to the first color channel to obtain the first processing image corresponding to the first color channel comprises:

[0018] determining a gain coefficient corresponding to the first color channel based on the pixel standard deviation corresponding to the first color channel;

[0019] adjusting the original pixel value of the pixel point corresponding to the first color channel in the to-be-detected image based on the gain coefficient corresponding to the first color channel to obtain the first processing image corresponding to the first color channel.

[0020] In one of the embodiments, adjusting the original pixel value of the pixel point corresponding to the first color channel in the to-be-detected image based on the gain coefficient corresponding to the first color channel to obtain the first processing image corresponding to the first color channel comprises:

[0021] determining a maximum pixel value and a minimum pixel value of the pixel point corresponding to the first color channel based on the gain coefficient corresponding to the first color channel;

[0022] adjusting the original pixel value of the pixel point corresponding to the first color channel in the to-be-detected image based on the maximum pixel value and the minimum pixel value to obtain a target pixel value of the pixel point corresponding to the first color channel;

[0023] The first color channel corresponding original channel image in the to-be-detected image is adaptively stretched based on the target pixel value of the pixel point corresponding to the first color channel, to obtain a first processing image corresponding to the first color channel.

[0024] In one of the embodiments, image quality detection is performed on each color channel in the to-be-detected image to obtain a detection result corresponding to each color channel, including:

[0025] The pixel standard deviation corresponding to each color channel is determined according to the original pixel value of the pixel point corresponding to each color channel in the to-be-detected image.

[0026] Image quality detection is performed on each color channel according to the relationship between the pixel standard deviation corresponding to each color channel and the standard deviation threshold, to obtain a detection result corresponding to each color channel.

[0027] In a second aspect, the present application further provides a fault detection device of an oil-immersed equipment. The device includes:

[0028] The acquisition module is configured to acquire a to-be-detected image, wherein the to-be-detected image is an internal structure image of the to-be-detected oil-immersed equipment.

[0029] The first detection module is configured to perform image quality detection on each color channel in the to-be-detected image to obtain a quality detection result corresponding to each color channel.

[0030] The processing module is configured to perform image processing on each color channel in the to-be-detected image based on the quality detection result corresponding to each color channel, to obtain a target image.

[0031] The second detection module is configured to perform fault detection on the oil-immersed equipment based on the target image.

[0032] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the fault detection method of the oil-immersed equipment according to any one of the embodiments of the first aspect when executing the computer program.

[0033] In a fourth aspect, the present application further provides a computer readable storage medium. The computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the fault detection method of the oil-immersed equipment according to any one of the embodiments of the first aspect.

[0034] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and the computer program is executed by a processor to implement the fault detection method of the oil-immersed equipment according to any one of the embodiments of the first aspect.

[0035] The fault detection method, device and computer equipment of the oil immersion equipment can realize image processing on each color channel in the to-be-detected image according to the quality detection result corresponding to each color channel, obtain a target image, and then detect the fault of the oil immersion equipment according to the target image. In the foregoing process, different image processing methods can be used for each color channel according to the quality detection result of each color channel, targeted color correction processing can be performed on each color channel, the situation of over-correction of the color channel is prevented, the definition of the internal structure image of the oil immersion equipment is improved, and the fault position of the oil immersion equipment can be determined according to the internal structure image of the oil immersion equipment. BRIEF DESCRIPTION OF DRAWINGS

[0036] Figure 1 An application environment diagram of the fault detection method of the oil immersion equipment provided in an embodiment of the present application;

[0037] Figure 2 An image processing effect diagram provided in the embodiment of the present application;

[0038] Figure 3 A flowchart of the fault detection method of the oil immersion equipment provided in the embodiment of the present application;

[0039] Figure 4 A step flowchart of obtaining a target image provided in the embodiment of the present application;

[0040] Figure 5 A step flowchart of image quality detection on a color channel provided in the embodiment of the present application;

[0041] Figure 6 A flowchart of another fault detection method of the oil immersion equipment provided in the embodiment of the present application;

[0042] Figure 7 A structural block diagram of the first fault detection device of the oil immersion equipment provided in the embodiment of the present application;

[0043] Figure 8 A structural block diagram of the second fault detection device of the oil immersion equipment provided in the embodiment of the present application;

[0044] Figure 9 A structural block diagram of the third fault detection device of the oil immersion equipment provided in the embodiment of the present application;

[0045] Figure 10 A structural block diagram of the fourth fault detection device of the oil immersion equipment provided in the embodiment of the present application;

[0046] Figure 11 An internal structure diagram of the computer equipment in an embodiment. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not used to limit the present application.

[0048] It should be understood that the specific embodiments described herein are only used to explain the present application and not used to limit the present application. In the description of the present application, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the specification and the features of the different embodiments or examples without contradiction.

[0049] Based on the above, the fault detection method of the oil-immersed equipment provided by the embodiments of the present application can be applied to the application environment as shown in Figure 1 In one embodiment, a computer device is provided, which can be a server, and its internal structure diagram can be as shown in Figure 1 The computer device includes a processor, a memory and a network interface connected through a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the computer device is used to store the acquisition data of the fault detection method of the oil-immersed equipment. The network interface of the computer device is used to communicate with the external terminal through the network connection. The computer program is executed by the processor to implement a fault detection method of an oil-immersed equipment.

[0050] Due to the scattering of particulate matter in water, the absorption of water itself and other conditions, the image taken in water will have color distortion, low contrast, missing details, limited visual distance and other problems. Therefore, the internal structure image enhancement method of the oil-immersed equipment can learn from the research ideas of the underwater image enhancement method. Different scholars have made different researches on underwater image enhancement, such as gray world algorithm, perfect reflection algorithm, etc.

[0051] The perfect reflection method calculates the color cast correction coefficient by comparing the pixel values of the three color channels of the white point in the image according to the characteristic that the white point in the image reflects the color temperature of the light source. However, if there is no white point or the white point has a serious color drift, the effect of color cast correction is poor, and the perfect reflection method takes the brightest point in the image as the white point, so that the noise and highlight points seriously affect the color cast correction.

[0052] The gray world algorithm considers that the color change of an object and its surrounding environment in the objective world is random and independent. Further, the color is corrected according to and the Von Kries diagonal theory. The Von Kries diagonal theory proposes that the relationship between the surface colors of the same object under two light conditions can be represented by a diagonal matrix transformation.

[0053] The calculation formula (1) of the gray world algorithm is as follows:

[0054]

[0055] In the calculation formula (1), S k and E(λ) are unknown, and the calculation formula (1) is ill-conditioned without any assumption. Based on the gray world assumption, it is known that the average reflection of natural scenery to light is a constant value K, which is approximately close to "gray". The K value can be represented by the calculation formula (2):

[0056]

[0057] wherein K is a constant value, and there are two ways to obtain the K value. The first method is to directly give K as a fixed value, which is half of the maximum value of each channel, that is, K=128. The second method is to let represent the average pixel value of the red, green and blue color channels, respectively.

[0058] Further, the gain coefficient of each color channel (that is, R, G, B, which are the red, green and blue channels) can be calculated according to the K value and the calculation formula (3), and the pixel value of each channel is corrected according to the gain coefficient of each color channel to obtain the corrected pixel value R f , G f , B f , wherein the calculation formula (3) and the calculation formula (4) are as follows:

[0059]

[0060] wherein K RK refers to the gain coefficient corresponding to the red channel determined by the gray world algorithm, G K refers to the gain coefficient corresponding to the green channel determined by the gray world algorithm, B K refers to the gain coefficient corresponding to the blue channel determined by the gray world algorithm, R, G, and B respectively represent the average pixel values of the red, green, and blue color channels, and K is a constant value.

[0061]

[0062] K refers to the gain coefficient corresponding to the red channel determined by the gray world algorithm, R K refers to the gain coefficient corresponding to the red channel determined by the gray world algorithm, G K refers to the gain coefficient corresponding to the green channel determined by the gray world algorithm, B K refers to the gain coefficient corresponding to the blue channel determined by the gray world algorithm, R, G, and B respectively represent the pixel values of the red, green, and blue channels, and R f K refers to the gain coefficient corresponding to the red channel determined by the gray world algorithm, f K refers to the gain coefficient corresponding to the green channel determined by the gray world algorithm, f K refers to the gain coefficient corresponding to the blue channel determined by the gray world algorithm.

[0063] Finally, the corrected R f , G f , and B f can be limited by calculation formula (5) to make the pixel value range of each channel between [0-255]. The calculation formula (5) is as follows:

[0064]

[0065] K refers to the gain coefficient corresponding to the red channel determined by the gray world algorithm, i K refers to the gain coefficient corresponding to the red channel determined by the gray world algorithm, f K refers to the gain coefficient corresponding to the red channel determined by the gray world algorithm, f K refers to the gain coefficient corresponding to the red channel determined by the gray world algorithm, f The pixel value of the corrected R f , G f , and B f after limiting. As known from the above steps, the gray world algorithm is based on the gray world assumption. When the scene has a large single color or the color changes are less, it cannot solve the problem of image color distortion. To solve the above problem, the application discloses a fault detection method and device of an oil immersion equipment and a computer equipment thereof. The computer equipment performs image processing on each color channel in the to-be-detected image according to the quality detection results of each color channel to obtain a target image, and then performs fault detection on the oil immersion equipment according to the target image.

[0066] In an embodiment of the application, as Figure 2As shown in the figure, wherein (a) is an internal structure image of the oil-immersed equipment without processing, (b) is an internal structure image of the oil-immersed equipment processed by the gray world algorithm, (c) is an internal structure image of the oil-immersed equipment processed by the perfect reflection method, and (d) is an internal structure image of the oil-immersed equipment processed by the method.

[0067] In one embodiment, as Figure 3 shown, Figure 3 a flowchart of a fault detection method of an oil-immersed equipment provided by an embodiment of the present application, provides a fault detection method of an oil-immersed equipment, Figure 1 the fault detection method of the oil-immersed equipment executed by the computer device in

[0068] Step 301, acquiring a to-be-detected image.

[0069] The to-be-detected image is an internal structure image of the oil-immersed equipment to be detected.

[0070] It should be noted that the to-be-detected image can be acquired by a visual simultaneous localization and mapping (SLAM) technology, wherein the SLAM technology includes a visual SLAM technology and a laser radar SLAM technology, thus, when the to-be-detected image is needed to be acquired, the to-be-detected image can be acquired by the visual SLAM technology or the laser radar SLAM technology, and the following will be described in detail for the above two cases:

[0071] In an embodiment of the present application, when the to-be-detected image is acquired by the visual SLAM technology, an image sensor can be inserted into the interior of the oil-immersed equipment, so as to acquire an image collected by the image sensor in the internal structure of the oil-immersed equipment, and the image is the to-be-detected image.

[0072] The image sensor can include but is not limited to a camera, a compound eye camera, an RGB-D camera, etc.

[0073] In another embodiment of the present application, when the to-be-detected image is acquired by the laser radar SLAM technology, a laser radar device is used to scan the internal structure of the oil-immersed equipment, so as to acquire an image collected by the laser radar device in the internal structure of the oil-immersed equipment, and the image is the to-be-detected image.

[0074] The laser radar device can include but is not limited to a laser sensor, a distance sensor, etc.

[0075] Further, according to the specific situation of the oil-immersed equipment to be detected, different methods for obtaining the image to be detected can be selected. Specifically, firstly, it is determined whether the image sensor can be inserted into the interior of the oil-immersed equipment and whether the image acquisition condition of the image sensor is met. If the image sensor can be inserted into the interior of the oil-immersed equipment and the image acquisition condition of the image sensor is met, the image to be detected is obtained through the visual SLAM technology. If the image sensor cannot be inserted into the interior of the oil-immersed equipment, the image to be detected is obtained through the laser radar SLAM technology. If the image sensor can be inserted into the interior of the oil-immersed equipment but the image acquisition condition of the image sensor is not met, the image to be detected is obtained through the laser radar SLAM technology.

[0076] In step 302, image quality detection is performed on each color channel in the image to be detected, and quality detection results corresponding to each color channel are obtained.

[0077] It should be noted that there are many methods for performing image quality detection on each color channel in the image to be detected. For example, the standard deviation of each color channel can be used to perform image quality detection on each color channel. Alternatively, the normalized standard deviation of each color channel can be used to perform image quality detection on each color channel. Alternatively, a pre-trained image quality detection model can be used to perform image quality detection on each color channel. It can be understood that there are many methods for performing image quality detection on each color channel in the image to be detected, which will not be described here. In the following, the above three methods for performing image quality detection on each color channel in the image to be detected will be described in detail.

[0078] As an implementation manner, when the standard deviation of each color channel is used to perform image quality detection on each color channel, the pixel average value of the pixel point corresponding to each color channel in the image to be detected is determined according to the original pixel value of the pixel point corresponding to each color channel in the image to be detected. Then, the standard deviation of each color channel is determined according to the dispersion degree calculation of the original pixel value of the pixel point corresponding to each color channel and the pixel average value of the pixel point corresponding to each color channel. The size relationship between the standard deviation of each color channel and the standard deviation threshold is determined. If the standard deviation of a certain color channel is greater than the standard deviation threshold, it is proved that the search result of the color channel is passed in quality detection. If the standard deviation of a certain color channel is less than or equal to the standard deviation threshold, it is proved that the search result of the color channel is not passed in quality detection.

[0079] It can be understood that the greater the standard deviation of the color channel, the better the corresponding quality of the color channel. Conversely, the smaller the standard deviation of the color channel, the worse the corresponding quality of the color channel.

[0080] The standard deviation threshold can be set according to the historical experience and actual situation of the staff, and the value and value range of the standard deviation threshold are not limited here.

[0081] As another implementation manner, when the image quality detection is performed on each color channel by the normalized standard deviation of each color channel, the standard deviation of each color channel is determined according to the original pixel value of the pixel corresponding to each color channel in the image to be detected, and the standard deviation of each color channel is normalized to obtain the pixel standard deviation corresponding to each color channel; it is judged whether the difference between the value 1 and the pixel standard deviation corresponding to each color channel is greater than the difference threshold value, if the difference between the value 1 and the pixel standard deviation corresponding to a certain color channel is less than or equal to the difference threshold value, that is, the pixel standard deviation corresponding to the color channel is close to the value 1, it is proved that the search result of the color channel is that the quality detection is passed; if the difference between the value 1 and the pixel standard deviation corresponding to a certain color channel is greater than the difference threshold value, that is, the pixel standard deviation corresponding to the color channel is not close to the value 1, it is proved that the search result of the color channel is that the quality detection is not passed.

[0082] It can be understood that the closer the pixel standard deviation corresponding to the color channel is to the value 1, the better the image quality corresponding to the color channel is.

[0083] The difference threshold value can be set according to the historical experience and actual situation of the staff, and the value and value range of the difference threshold value are not limited here.

[0084] As another implementation manner, when the image quality detection is performed on each color channel by the pre-trained image quality detection model, the image quality detection model can be pre-trained, the original channel image corresponding to a certain color channel in the image to be detected is input into the image quality detection model, and the output result of the image quality detection model is obtained. The output result is the image quality score of the image quality detection model on the color channel, and the size relationship between the image quality score and the score difference threshold value is judged. If the image quality score of a certain color channel is greater than the score threshold value, it is proved that the search result of the color channel is that the quality detection is passed, and if the image quality score of a certain color channel is less than or equal to the score threshold value, it is proved that the search result of the color channel is that the quality detection is not passed.

[0085] The plurality of color channel samples can be obtained, and each color channel sample is marked by artificial marking, and the image quality detection model is trained based on the color channel sample after marking to ensure that the image quality score of each color channel can be determined according to the image quality detection model.

[0086] The score threshold value can be set according to the historical experience and actual situation of the staff, and the value and value range of the score threshold value are not limited here.

[0087] In step 303, based on the quality detection result corresponding to each color channel, image processing is performed on each color channel in the to-be-detected image to obtain a target image.

[0088] The quality detection result includes quality detection pass and quality detection fail, and further, if the search result of a color channel is quality detection pass, the color channel is a first color channel; if the search result of a color channel is quality detection fail, the color channel is a second color channel.

[0089] It should be noted that if the quality detection result corresponding to a color channel is quality detection pass, the gain coefficient corresponding to the first color channel is determined according to the pixel standard deviation corresponding to the first color channel in the to-be-detected image; and based on the gain coefficient corresponding to the first color channel, the original pixel value of the pixel corresponding to the first color channel in the to-be-detected image is adjusted to obtain a first processing image corresponding to the first color channel.

[0090] In an embodiment of the present application, when adjusting the original pixel value of the pixel corresponding to the first color channel in the to-be-detected image, the maximum pixel value and the minimum pixel value of the pixel corresponding to the first color channel can be determined based on the gain coefficient corresponding to the first color channel; and then the original pixel value of the pixel corresponding to the first color channel in the to-be-detected image is adjusted according to the size relationship between the original pixel value and the maximum pixel value and the minimum pixel value.

[0091] It should be further noted that if the quality detection result corresponding to a color channel is quality detection fail, it means that the image quality of the original channel image corresponding to the second color channel in the to-be-detected image is low, and to prevent overcorrection, the original channel image corresponding to the second color channel in the to-be-detected image is not processed.

[0092] In step 304, based on the target image, fault detection is performed on the oil-immersed equipment.

[0093] It should be noted that when fault detection is needed for the oil-immersed equipment, the standard image corresponding to each target image can be determined in advance, and it is determined whether there is a difference point between the target image and the standard image, if there is a difference point, it is determined that the current oil-immersed equipment has a fault; if there is no difference point, it is determined that the current oil-immersed equipment has no fault.

[0094] The standard image refers to the internal structure image of the oil-immersed equipment without failure.

[0095] In an embodiment of the present application, the fault detection model can be pre-trained, and by inputting the target image into the fault detection model, the output result of the fault detection model is obtained, which indicates whether the region corresponding to the target image in the oil-immersed equipment has a fault.

[0096] Wherein, a plurality of target image samples can be obtained in advance, and whether there is a difference point between the target image sample and the standard image and the position of the difference point between the target image sample and the standard image are marked by manual marking; the fault detection model is trained based on the marked target image sample to ensure that the fault detection model can determine whether the region corresponding to the target image in the oil-immersed equipment has a fault.

[0097] In another embodiment of the present application, the target image in the output result of the fault detection model indicating that there is a fault in the oil-immersed equipment can be fed back to the computer device of the worker to enable the worker to secondarily confirm the target image with a fault, thereby further improving the accuracy of the target image determination.

[0098] The above fault detection method of the oil-immersed equipment realizes image processing of each color channel in the to-be-detected image according to the quality detection result corresponding to each color channel, obtains a target image, and then detects a fault of the oil-immersed equipment according to the target image. In the above process, different image processing methods can be used for each color channel according to the quality detection result of each color channel, targeted color correction processing of each color channel is realized, over-correction of the color channel is prevented, the clarity of the internal structure image of the oil-immersed equipment is improved, and the fault position of the oil-immersed equipment can be determined according to the internal structure image of the oil-immersed equipment.

[0099] Since the liquid medium in the oil-immersed equipment will gradually increase in turbidity with the increase of the use time, color distortion of the internal structure image of the oil-immersed equipment is caused, and then the worker cannot determine whether the oil-immersed equipment has a fault and the specific fault position when the oil-immersed equipment has a fault according to the internal structure image of the oil-immersed equipment. To solve the above problem, the terminal of the embodiment can obtain a target image by adjusting the pixel value of the pixel point corresponding to the first color channel in the to-be-detected image, and obtain a first processing image corresponding to the first color channel. Figure 4

[0100] Step 401: adjusting the pixel value of the pixel point corresponding to the first color channel in the to-be-detected image to obtain a first processing image corresponding to the first color channel.

[0101] Wherein, the search result of the first color channel is that the quality detection is passed. ​

[0102] It should be noted that when the first processing image corresponding to the first color channel is needed, the following can be specifically included: determining the pixel standard deviation corresponding to the first color channel according to the original pixel value of the pixel point corresponding to the first color channel in the to-be-detected image; adjusting the pixel value of the pixel point corresponding to the first color channel in the to-be-detected image based on the pixel standard deviation corresponding to the first color channel, to obtain the first processing image corresponding to the first color channel.

[0103] Further, the original pixel value of the pixel point corresponding to the first color channel in the to-be-detected image is subjected to standard deviation operation to determine the initial standard deviation corresponding to the first color channel, and then the initial standard deviation corresponding to the first color channel is subjected to normalization processing, so that the pixel standard deviation corresponding to the first color channel is obtained. The above content will be described in detail as follows:

[0104] The initial standard deviation corresponding to the first color channel is subjected to normalization processing according to the calculation formula (6), so that the pixel standard deviation corresponding to the first color channel is obtained. The calculation formula (6) is as follows:

[0105]

[0106] Wherein, N j is the pixel standard deviation corresponding to the first color channel, stdj is the initial standard deviation corresponding to different first color channels, and j is different first color channels (i.e. red channel, green channel and blue channel).

[0107] Further, when the pixel value of the pixel point corresponding to the first color channel in the to-be-detected image is needed to be adjusted, the following can be specifically included: determining the gain coefficient corresponding to the first color channel based on the pixel standard deviation corresponding to the first color channel; adjusting the original pixel value of the pixel point corresponding to the first color channel in the to-be-detected image based on the gain coefficient corresponding to the first color channel, to obtain the first processing image corresponding to the first color channel.

[0108] Wherein, the gain coefficient corresponding to the first color channel can be obtained by performing formula operation on the pixel standard deviation corresponding to the first color channel according to the calculation formula (7), and the calculation formula (7) is as follows:

[0109]

[0110] Wherein, N j is the pixel standard deviation corresponding to the first color channel, j is different first color channels (i.e. red, green and blue color channels), and K j is the gain coefficient corresponding to each color channel determined by the gray world algorithm, is the gain coefficient corresponding to the first color channel determined by the present application.

[0111] It should be noted that, since the detection result of the first color channel is quality detection pass, the corresponding original channel image of the first color channel in the image to be detected is of high quality, and therefore the N j Close to the value 1, according to the calculation formula (7), the N Close to the value 1, according to the calculation formula (7), the N j , Close to the value 1, according to the calculation formula (7), the N j Close to the value 1, according to the calculation formula (7), the N j Close to the value 1, according to the calculation formula (7), the N j Close to the value 1, according to the calculation formula (7), the N Close to the value 1, according to the calculation formula (7), the N

[0112] Further, when adjusting the original pixel value of the pixel point corresponding to the first color channel in the image to be detected, the following contents can be included: based on the gain coefficient corresponding to the first color channel, determining the maximum pixel value and the minimum pixel value of the pixel point corresponding to the first color channel; based on the maximum pixel value and the minimum pixel value, adjusting the original pixel value of the pixel point corresponding to the first color channel in the image to be detected to obtain the target pixel value of the pixel point corresponding to the first color channel; based on the target pixel value of the pixel point corresponding to the first color channel, performing adaptive stretching processing on the original channel image corresponding to the first color channel in the image to be detected to obtain the first processing image corresponding to the first color channel.

[0113] Specifically, according to the gain coefficient corresponding to the first color channel and the calculation formula (8), the pixel value of each pixel point of the first color channel after being corrected by the gain coefficient corresponding to the first color channel can be determined, and the maximum pixel value and the minimum pixel value are selected from the pixel value, wherein the calculation formula (8) is as follows:

[0114]

[0115] Wherein, is the gain coefficient corresponding to the first color channel determined by the present application, j is different first color channel (i.e. red, green, blue three color channels), j1 is the pixel value of different first color channel, j f is the original pixel value of each pixel point after being corrected by the gain coefficient corresponding to the first color channel.

[0116] Further, the maximum pixel value V max and the minimum pixel value V min are selected, and the target pixel value of the pixel point corresponding to the first color channel is adjusted based on the maximum pixel value Vmax , the minimum pixel value V min and the calculation formula (9) adjusts the original pixel value of the pixel point corresponding to the first color channel in the to-be-detected image to obtain the target pixel value of the pixel point corresponding to the first color channel; wherein the calculation formula (9) is as follows:

[0117]

[0118] wherein V j is the original pixel value of the pixel point corresponding to the first color channel in the to-be-detected image, V max is the maximum pixel value in the original pixel value, V min is the minimum pixel value in the original pixel value, V fj is the target pixel value of the pixel point corresponding to the first color channel, and j is different first color channels (i.e. red, green, and blue color channels).

[0119] Therefore, the first processing image corresponding to the first color channel is obtained by adaptively stretching the original channel image corresponding to the first color channel in the to-be-detected image through the target pixel value of the pixel point corresponding to the first color channel.

[0120] Step 402, fusing the first processing image corresponding to the first color channel and / or the original channel image corresponding to the second color channel in the to-be-detected image to obtain a target image.

[0121] wherein the detection result of the second color channel is that the quality detection fails.

[0122] In an embodiment of the application, if both the first processing image corresponding to the first color channel and the original channel image corresponding to the second color channel in the to-be-detected image exist, the first processing image corresponding to the first color channel and the original channel image corresponding to the second color channel in the to-be-detected image are subjected to image fusion operation, and it is ensured that the target image after fusion does not exist ghosting and deviation.

[0123] In another embodiment of the application, if only the first processing image corresponding to the first color channel exists, and the original channel image corresponding to the second color channel in the to-be-detected image does not exist, only the first processing image corresponding to the first color channel is subjected to image fusion operation, and it is ensured that the target image after fusion does not exist ghosting and deviation.

[0124] In still another embodiment of the application, if the first processing image corresponding to the first color channel does not exist, but the original channel image corresponding to the second color channel in the to-be-detected image exists, only the original channel image corresponding to the second color channel in the to-be-detected image is subjected to image fusion operation, and it is ensured that the target image after fusion does not exist ghosting and deviation.

[0125] The fault detection method of the oil immersion device has the color correction processing on the target image by fusing the first processing image corresponding to the first color channel and / or the original channel image corresponding to the second color channel in the to-be-detected image, improves the definition of the internal structure image of the oil immersion device, and provides a basic guarantee for determining the fault position of the oil immersion device according to the internal structure image of the oil immersion device.

[0126] In one embodiment, when image quality detection needs to be performed on each color channel in the to-be-detected image, the pixel standard deviation corresponding to each color channel can be determined. At this time, as shown in the following formula (1), the method comprises the following steps. Figure 5

[0127] Step 501: determining the pixel standard deviation corresponding to each color channel according to the original pixel value of the pixel point corresponding to each color channel in the to-be-detected image.

[0128] The pixel standard deviation corresponding to each color channel is used to represent the dispersion degree of the original pixel value of the pixel point corresponding to each color channel in the to-be-detected image and the pixel average value.

[0129] In one embodiment of the present application, when the pixel standard deviation corresponding to each color channel needs to be determined, the original pixel value of the pixel point corresponding to each color channel in the to-be-detected image can be subjected to mean value operation to determine the pixel average value of the pixel point corresponding to each color channel in the to-be-detected image. Then, the standard deviation of each color channel is determined according to the dispersion degree calculation of the original pixel value of the pixel point corresponding to each color channel and the pixel average value of the pixel point corresponding to each color channel.

[0130] Step 502: performing image quality detection on each color channel according to the relationship between the pixel standard deviation corresponding to each color channel and the standard deviation threshold value to obtain the detection result corresponding to each color channel.

[0131] In one embodiment of the present application, when image quality detection needs to be performed on each color channel, the following content can be specifically included: judging the size relationship between the standard deviation of each color channel and the standard deviation threshold value. If the standard deviation of a certain color channel is greater than the standard deviation threshold value, it proves that the search result of the color channel is that the quality detection passes. If the standard deviation of a certain color channel is less than or equal to the standard deviation threshold value, it proves that the search result of the color channel is that the quality detection does not pass. The standard deviation threshold value can be set according to the historical experience and actual situation of the staff, and the value and value range of the standard deviation threshold value are not limited herein.

[0132] It is further explained that the greater the standard deviation of the color channel, the better the corresponding quality of the color channel, and vice versa, the smaller the standard deviation of the color channel, the worse the corresponding quality of the color channel. ​

[0133] The fault detection method of the oil-immersed equipment determines the detection result of each color channel according to the relationship between the pixel standard deviation corresponding to each color channel and the standard deviation threshold, realizes different image processing modes for each color channel according to the quality detection result of each color channel, and realizes targeted color correction processing for each color channel.

[0134] In this embodiment, as shown in Figure 6 Figure 6 The flowchart of another fault detection method of the oil-immersed equipment provided by the embodiment of the application is shown in the figure. When it is necessary to detect the fault of the oil-immersed equipment, the following contents can be included:

[0135] Step 601: An image to be detected is acquired.

[0136] Step 602: The pixel standard deviation corresponding to each color channel is determined according to the original pixel value of the pixel point corresponding to each color channel in the image to be detected.

[0137] Step 603: The image quality of each color channel is detected according to the relationship between the pixel standard deviation corresponding to each color channel and the standard deviation threshold, and the detection result corresponding to each color channel is obtained.

[0138] Step 604: The pixel standard deviation corresponding to the first color channel is determined according to the original pixel value of the pixel point corresponding to the first color channel in the image to be detected.

[0139] Step 605: The gain coefficient corresponding to the first color channel is determined based on the pixel standard deviation corresponding to the first color channel.

[0140] Step 606: The maximum pixel value and the minimum pixel value of the pixel point corresponding to the first color channel are determined based on the gain coefficient corresponding to the first color channel.

[0141] Step 607: The original pixel value of the pixel point corresponding to the first color channel in the image to be detected is adjusted based on the maximum pixel value and the minimum pixel value, and the target pixel value of the pixel point corresponding to the first color channel is obtained.

[0142] Step 608: The original channel image corresponding to the first color channel in the image to be detected is adaptively stretched based on the target pixel value of the pixel point corresponding to the first color channel, and the first processing image corresponding to the first color channel is obtained.

[0143] Step 609: The first processing image corresponding to the first color channel and / or the original channel image corresponding to the second color channel in the image to be detected is fused, and a target image is obtained.

[0144] Step 610: The fault of the oil-immersed equipment is detected based on the target image.​

[0145] The fault detection method of the oil immersion device described above, by performing image quality detection on each color channel in the to-be-detected image, realizes image processing on each color channel in the to-be-detected image according to the quality detection result corresponding to each color channel to obtain a target image, and then performs fault detection on the oil immersion device according to the target image. In the above process, different image processing methods can be used for each color channel according to the quality detection result of each color channel, targeted color correction processing is realized for each color channel, over-correction of the color channel is prevented, the clarity of the internal structure image of the oil immersion device is improved, and the fault position of the oil immersion device can be determined according to the internal structure image of the oil immersion device.

[0146] It should be understood that, although each step in the flowchart involved in each of the above embodiments is displayed in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in each of the above embodiments can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be alternately executed with at least part of other steps or steps or stages in other steps.

[0147] Based on the same inventive concept, the embodiments of the present application also provide a fault detection device of an oil immersion device for implementing the above-mentioned fault detection method of the oil immersion device. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more fault detection device embodiments of the oil immersion device provided below can refer to the limitations of the oil immersion device fault detection method in the above text, which will not be repeated here.

[0148] In one embodiment, as shown in Figure 7 A fault detection device of an oil immersion device is provided, comprising: an acquisition module 10, a first detection module 20, a processing module 30, and a second detection module 40, wherein:

[0149] The acquisition module 10 is configured to acquire a to-be-detected image; wherein the to-be-detected image is an internal structure image of a to-be-detected oil immersion device.

[0150] The first detection module 20 is configured to perform image quality detection on each color channel in the to-be-detected image to obtain a quality detection result corresponding to each color channel.

[0151] The processing module 30 is configured to perform image processing on each color channel in the to-be-detected image based on the quality detection result corresponding to each color channel, to obtain a target image.

[0152] The second detection module 40 is configured to perform fault detection on the oil-immersed equipment based on the target image.

[0153] The fault detection device for the oil-immersed equipment can perform image quality detection on each color channel in the to-be-detected image, perform image processing on each color channel in the to-be-detected image based on the quality detection result corresponding to each color channel, and obtain a target image. Then, the fault detection device performs fault detection on the oil-immersed equipment based on the target image. In the above process, different image processing methods can be used for each color channel based on the quality detection result of each color channel, so that targeted color correction processing can be performed on each color channel, and over-correction of the color channel can be prevented. The clarity of the internal structure image of the oil-immersed equipment is improved, and the fault position of the oil-immersed equipment can be determined based on the internal structure image of the oil-immersed equipment.

[0154] In one embodiment, as shown in FIG. 1, a fault detection device for an oil-immersed equipment is provided. Figure 8 The processing module 30 in the fault detection device for the oil-immersed equipment includes an adjusting unit 31 and a fusion unit 32.

[0155] The adjusting unit 31 is configured to adjust the pixel value of the pixel point corresponding to the first color channel in the to-be-detected image to obtain a first processing image corresponding to the first color channel.

[0156] The fusion unit 32 is configured to fuse the first processing image corresponding to the first color channel and / or the original channel image corresponding to the second color channel in the to-be-detected image to obtain a target image. The detection result of the first color channel is that the quality detection is passed. The detection result of the second color channel is that the quality detection is not passed.

[0157] In one embodiment, as shown in FIG. 1, a fault detection device for an oil-immersed equipment is provided. Figure 9 The adjusting unit 31 in the fault detection device for the oil-immersed equipment includes a determination sub-unit 311 and an adjusting sub-unit 312.

[0158] The determination sub-unit 311 is configured to determine the pixel standard deviation corresponding to the first color channel based on the original pixel value of the pixel point corresponding to the first color channel in the to-be-detected image.

[0159] The adjusting sub-unit 312 is configured to adjust the pixel value of the pixel point corresponding to the first color channel in the to-be-detected image based on the pixel standard deviation corresponding to the first color channel, to obtain a first processing image corresponding to the first color channel.

[0160] The adjusting subunit is specifically configured to: determine a gain coefficient corresponding to the first color channel based on the pixel standard deviation corresponding to the first color channel; and adjust the original pixel value of the pixel point corresponding to the first color channel in the to-be-detected image based on the gain coefficient corresponding to the first color channel, to obtain the first processing image corresponding to the first color channel.

[0161] The adjusting subunit is specifically configured to: determine a gain coefficient corresponding to the first color channel based on the pixel standard deviation corresponding to the first color channel; and adjust the original pixel value of the pixel point corresponding to the first color channel in the to-be-detected image based on the gain coefficient corresponding to the first color channel, to obtain the first processing image corresponding to the first color channel.

[0162] In one embodiment, as shown in FIG. 1, a fault detection device of an oil-immersed equipment is provided, and the first detection module 20 of the fault detection device of the oil-immersed equipment includes a determining unit 21 and a detection unit 22, where: Figure 10

[0163] The determining unit 21 is configured to determine the pixel standard deviation corresponding to each color channel according to the original pixel value of the pixel point corresponding to each color channel in the to-be-detected image.

[0164] The detection unit 22 is configured to perform image quality detection on each color channel according to the relationship between the pixel standard deviation corresponding to each color channel and the standard deviation threshold, to obtain the detection result corresponding to each color channel.

[0165] The above modules of the fault detection device of the oil-immersed equipment can be all or partially implemented by software, hardware, and a combination thereof. The above modules can be embedded in or independent of a processor in a computer device in a hardware form, or can be stored in a memory in the computer device in a software form, so as to be called and executed by the processor to perform the operations corresponding to the above modules.

[0166] In one embodiment, a computer device is provided, which can be a terminal, and an internal structure diagram of the computer device can be as shown in FIG. 2. Figure 11 ​The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected through a system bus. The communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to perform wired or wireless communication with external terminals. The wireless communication can be achieved through WIFI, mobile cellular network, NFC (Near Field Communication), or other technologies. The computer program is executed by the processor to implement a fault detection method for an oil-immersed device. The display unit of the computer device is configured to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball, or touchpad arranged on the shell of the computer device. The input device can also be an external keyboard, touchpad, or mouse, etc.

[0167] Those skilled in the art can understand that Figure 11 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0168] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the following steps:

[0169] An image to be detected is acquired; wherein the image to be detected is an internal structure image of an oil-immersed device to be detected;

[0170] Image quality detection is performed on each color channel in the image to be detected to obtain a quality detection result corresponding to each color channel;

[0171] Based on the quality detection result corresponding to each color channel, image processing is performed on each color channel in the image to be detected to obtain a target image;

[0172] Based on the target image, fault detection is performed on the oil-immersed device.

[0173] In one embodiment, the processor executing the computer program further implements the following steps:

[0174] adjusting a pixel value of a pixel point corresponding to the first color channel in the to-be-detected image to obtain a first processing image corresponding to the first color channel;

[0175] fusing the first processing image corresponding to the first color channel and / or an original channel image corresponding to the second color channel in the to-be-detected image to obtain a target image; wherein the search result of the first color channel is that the quality detection passes; and the detection result of the second color channel is that the quality detection fails.

[0176] In an embodiment, the processor, when executing the computer program, further implements the following steps:

[0177] determining a pixel standard deviation corresponding to the first color channel according to an original pixel value of a pixel point corresponding to the first color channel in the to-be-detected image;

[0178] adjusting the pixel value of the pixel point corresponding to the first color channel in the to-be-detected image based on the pixel standard deviation corresponding to the first color channel to obtain a first processing image corresponding to the first color channel.

[0179] In an embodiment, the processor, when executing the computer program, further implements the following steps:

[0180] determining a gain coefficient corresponding to the first color channel based on the pixel standard deviation corresponding to the first color channel;

[0181] adjusting an original pixel value of a pixel point corresponding to the first color channel in the to-be-detected image based on the gain coefficient corresponding to the first color channel to obtain a first processing image corresponding to the first color channel.

[0182] In an embodiment, the processor, when executing the computer program, further implements the following steps:

[0183] determining a maximum pixel value and a minimum pixel value of a pixel point corresponding to the first color channel based on the gain coefficient corresponding to the first color channel;

[0184] adjusting an original pixel value of a pixel point corresponding to the first color channel in the to-be-detected image based on the maximum pixel value and the minimum pixel value to obtain a target pixel value of the pixel point corresponding to the first color channel;

[0185] performing adaptive stretching processing on an original channel image corresponding to the first color channel in the to-be-detected image based on the target pixel value of the pixel point corresponding to the first color channel to obtain a first processing image corresponding to the first color channel.

[0186] In an embodiment, the processor, when executing the computer program, further implements the following steps:

[0187] According to the original pixel value of the pixel point corresponding to each color channel in the image to be detected, the pixel standard deviation corresponding to each color channel is determined.

[0188] According to the relationship between the pixel standard deviation corresponding to each color channel and the standard deviation threshold, image quality detection is performed on each color channel to obtain the detection result corresponding to each color channel.

[0189] In one embodiment, a computer readable storage medium is provided, and a computer program is stored on the computer readable storage medium. The computer program is executed by a processor to implement the following steps:

[0190] An image to be detected is obtained; wherein the image to be detected is an internal structure image of an oil-immersed device to be detected;

[0191] Image quality detection is performed on each color channel in the image to be detected to obtain a quality detection result corresponding to each color channel;

[0192] Based on the quality detection result corresponding to each color channel, image processing is performed on each color channel in the image to be detected to obtain a target image;

[0193] Based on the target image, fault detection is performed on the oil-immersed device.

[0194] In one embodiment, the computer program is executed by the processor to further implement the following steps:

[0195] The pixel value of the pixel point corresponding to the first color channel in the image to be detected is adjusted to obtain a first processing image corresponding to the first color channel;

[0196] The first processing image corresponding to the first color channel and / or the original channel image corresponding to the second color channel in the image to be detected are fused to obtain a target image; wherein the detection result of the first color channel is that the quality detection passes; the detection result of the second color channel is that the quality detection fails.

[0197] In one embodiment, the computer program is executed by the processor to further implement the following steps:

[0198] According to the original pixel value of the pixel point corresponding to the first color channel in the image to be detected, the pixel standard deviation corresponding to the first color channel is determined;

[0199] Based on the pixel standard deviation corresponding to the first color channel, the pixel value of the pixel point corresponding to the first color channel in the image to be detected is adjusted to obtain a first processing image corresponding to the first color channel.

[0200] In one embodiment, the computer program is executed by the processor to further implement the following steps:

[0201] determine a gain coefficient corresponding to the first color channel based on the pixel standard deviation corresponding to the first color channel;

[0202] adjust the original pixel value of the pixel point corresponding to the first color channel in the to-be-detected image based on the gain coefficient corresponding to the first color channel, to obtain a first processing image corresponding to the first color channel.

[0203] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0204] determine a maximum pixel value and a minimum pixel value of the pixel point corresponding to the first color channel based on the gain coefficient corresponding to the first color channel;

[0205] adjust the original pixel value of the pixel point corresponding to the first color channel in the to-be-detected image based on the maximum pixel value and the minimum pixel value, to obtain a target pixel value of the pixel point corresponding to the first color channel;

[0206] perform adaptive stretching processing on the original channel image corresponding to the first color channel in the to-be-detected image based on the target pixel value of the pixel point corresponding to the first color channel, to obtain a first processing image corresponding to the first color channel.

[0207] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0208] determine a pixel standard deviation corresponding to each color channel in the to-be-detected image according to the original pixel value of the pixel point corresponding to each color channel;

[0209] perform image quality detection on each color channel according to the relationship between the pixel standard deviation corresponding to each color channel and a standard deviation threshold, to obtain a detection result corresponding to each color channel.

[0210] In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the following steps:

[0211] obtain a to-be-detected image; wherein the to-be-detected image is an internal structure image of an oil-immersed equipment to be detected;

[0212] perform image quality detection on each color channel in the to-be-detected image, to obtain a quality detection result corresponding to each color channel;

[0213] perform image processing on each color channel in the to-be-detected image based on the quality detection result corresponding to each color channel, to obtain a target image;

[0214] perform fault detection on the oil-immersed equipment based on the target image.

[0215] In one embodiment, the computer program, which is executed by the processor, further implements the following steps:

[0216] adjusting the pixel value of the pixel point corresponding to the first color channel in the to-be-detected image to obtain a first processing image corresponding to the first color channel;

[0217] fusing the first processing image corresponding to the first color channel and / or the original channel image corresponding to the second color channel in the to-be-detected image to obtain a target image; wherein the search result of the first color channel is that the quality detection passes; and the detection result of the second color channel is that the quality detection fails.

[0218] In one embodiment, the computer program, which is executed by the processor, further implements the following steps:

[0219] determining a pixel standard deviation corresponding to the first color channel according to the original pixel value of the pixel point corresponding to the first color channel in the to-be-detected image;

[0220] adjusting the pixel value of the pixel point corresponding to the first color channel in the to-be-detected image based on the pixel standard deviation corresponding to the first color channel to obtain a first processing image corresponding to the first color channel.

[0221] In one embodiment, the computer program, which is executed by the processor, further implements the following steps:

[0222] determining a gain coefficient corresponding to the first color channel based on the pixel standard deviation corresponding to the first color channel;

[0223] adjusting the original pixel value of the pixel point corresponding to the first color channel in the to-be-detected image based on the gain coefficient corresponding to the first color channel to obtain a first processing image corresponding to the first color channel.

[0224] In one embodiment, the computer program, which is executed by the processor, further implements the following steps:

[0225] determining a maximum pixel value and a minimum pixel value of the pixel point corresponding to the first color channel based on the gain coefficient corresponding to the first color channel;

[0226] adjusting the original pixel value of the pixel point corresponding to the first color channel in the to-be-detected image based on the maximum pixel value and the minimum pixel value to obtain a target pixel value of the pixel point corresponding to the first color channel;

[0227] performing adaptive stretching processing on the original channel image corresponding to the first color channel in the to-be-detected image based on the target pixel value of the pixel point corresponding to the first color channel to obtain a first processing image corresponding to the first color channel.

[0228] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0229] According to the original pixel value of each color channel corresponding to the pixel point in the image to be detected, the pixel standard deviation corresponding to each color channel is determined;

[0230] According to the relationship between the pixel standard deviation corresponding to each color channel and the standard deviation threshold, the image quality of each color channel is detected to obtain the detection result corresponding to each color channel.

[0231] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0232] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0233] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0234] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A fault detection method for oil-immersed equipment, characterized in that, The method comprises: acquiring a to-be-detected image; wherein the to-be-detected image is an internal structure image of an oil-immersed device to be detected; performing image quality detection on each color channel in the to-be-detected image to obtain a quality detection result corresponding to each color channel; adjusting pixel values of pixel points corresponding to a first color channel in the to-be-detected image to obtain a first processing image corresponding to the first color channel; if both the first processing image corresponding to the first color channel and an original channel image corresponding to a second color channel in the to-be-detected image exist, performing image fusion operation on the first processing image corresponding to the first color channel and the original channel image corresponding to the second color channel in the to-be-detected image to obtain a target image; if only the first processing image corresponding to the first color channel exists and no original channel image corresponding to the second color channel in the to-be-detected image exists, performing image fusion operation only on the first processing image corresponding to the first color channel to obtain a target image; if no first processing image corresponding to the first color channel exists but an original channel image corresponding to the second color channel in the to-be-detected image exists, performing image fusion operation only on the original channel image corresponding to the second color channel in the to-be-detected image to obtain a target image; wherein the detection result of the first color channel is that the quality detection passes, and the detection result of the second color channel is that the quality detection fails; based on the target image, performing fault detection on the oil-immersed device.

2. The method of claim 1, wherein, The adjusting of the pixel values of the pixel points corresponding to the first color channel in the to-be-detected image to obtain the first processing image corresponding to the first color channel comprises: determining a pixel standard deviation corresponding to the first color channel according to original pixel values of the pixel points corresponding to the first color channel in the to-be-detected image; based on the pixel standard deviation corresponding to the first color channel, adjusting the pixel values of the pixel points corresponding to the first color channel in the to-be-detected image to obtain the first processing image corresponding to the first color channel.

3. The method of claim 2, wherein, The adjusting of the pixel values of the pixel points corresponding to the first color channel in the to-be-detected image to obtain the first processing image corresponding to the first color channel based on the pixel standard deviation corresponding to the first color channel comprises: determining a gain coefficient corresponding to the first color channel based on the pixel standard deviation corresponding to the first color channel; based on the gain coefficient corresponding to the first color channel, adjusting the original pixel values of the pixel points corresponding to the first color channel in the to-be-detected image to obtain the first processing image corresponding to the first color channel.

4. The method of claim 3, wherein, The adjusting of the pixel values of the pixel points corresponding to the first color channel in the to-be-detected image to obtain the first processing image corresponding to the first color channel based on the gain coefficient corresponding to the first color channel comprises: determining a maximum pixel value and a minimum pixel value of the pixel points corresponding to the first color channel based on the gain coefficient corresponding to the first color channel; based on the maximum pixel value and the minimum pixel value, adjusting the original pixel values of the pixel points corresponding to the first color channel in the to-be-detected image to obtain target pixel values of the pixel points corresponding to the first color channel; The first color channel corresponding original channel image in the to-be-detected image is adaptively stretched based on the target pixel value of the pixel point corresponding to the first color channel, to obtain a first processing image corresponding to the first color channel.

5. The method of claim 1, wherein, The image quality detection on each color channel in the to-be-detected image comprises: The pixel standard deviation corresponding to each color channel is determined according to the original pixel value of the pixel point corresponding to each color channel in the to-be-detected image. The detection result corresponding to each color channel is obtained by detecting the image quality of each color channel according to the relationship between the pixel standard deviation corresponding to each color channel and the standard deviation threshold.

6. The method of claim 1, wherein, The pixel standard deviation corresponding to each color channel is used to represent the dispersion degree of the original pixel value of the pixel point corresponding to each color channel in the to-be-detected image and the pixel average value.

7. A fault detection device for oil-immersed equipment, characterized in that, The device comprises: The acquisition module is configured to acquire a to-be-detected image; wherein the to-be-detected image is an internal structure image of an oil-immersed equipment to be detected; The first detection module is configured to detect the image quality of each color channel in the to-be-detected image to obtain a quality detection result corresponding to each color channel; The processing module is configured to adjust the pixel value of the pixel point corresponding to the first color channel in the to-be-detected image to obtain a first processing image corresponding to the first color channel; if both the first processing image corresponding to the first color channel and the original channel image corresponding to the second color channel in the to-be-detected image exist, the first processing image corresponding to the first color channel and the original channel image corresponding to the second color channel in the to-be-detected image are subjected to image fusion operation to obtain a target image; if only the first processing image corresponding to the first color channel exists and the original channel image corresponding to the second color channel in the to-be-detected image does not exist, only the first processing image corresponding to the first color channel is subjected to image fusion operation to obtain a target image; if the first processing image corresponding to the first color channel does not exist but the original channel image corresponding to the second color channel in the to-be-detected image exists, only the original channel image corresponding to the second color channel in the to-be-detected image is subjected to image fusion operation to obtain a target image; wherein the search result of the first color channel is that the quality detection passes; the detection result of the second color channel is that the quality detection fails; The second detection module is configured to detect the fault of the oil-immersed equipment based on the target image.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to realize the steps of the method in any one of claims 1 to 6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the method in any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the method in any one of claims 1 to 6. The computer program is executed by the processor to realize the steps of the method in any one of claims 1 to 6.

Images