Knife switch state determination method, apparatus and device, and medium

Abstract

The invention provides a disconnecting link state determination method and device, equipment and a medium. The method comprises the following steps: acquiring image information of a disconnecting link in a first preset time period, and determining a first state sequence of the disconnecting link according to the image information in the first preset time period; wherein the first state sequence comprises the on-off state of the disconnecting link at each moment in a first preset time period; if at least three pairs of adjacent on-off states in the first state sequence are opposite, determining a standard image from the image information in the first preset time period, and obtaining a real-time image of the disconnecting link; wherein the standard image represents an image of the disconnecting link without overexposure; and according to the standard image and the real-time image, determining the on-off state of the disconnecting link at the current moment. According to the method, the precision of determining the state of the disconnecting link is improved.

Description

Technical Field

[0001] This application relates to the field of power system technology, and in particular to a method, apparatus, equipment and medium for determining the state of a disconnector. Background Technology

[0002] In a power system, the automated operation of a smart substation depends on identifying or determining the open or closed state of disconnectors. In other words, the automated operation of a smart substation depends on identifying or determining the position (closed or open) of disconnectors.

[0003] Currently, the method for determining the status of a disconnect switch is to use a camera to capture an image of the switch. However, in practical applications, this method is not very effective, and there is a need to improve the accuracy of disconnect switch status determination. Summary of the Invention

[0004] This application provides a method, apparatus, device, and medium for determining the state of a disconnector, in order to solve the problem of low accuracy in determining the state of a disconnector.

[0005] Firstly, this application provides a method for determining the state of a disconnector, comprising:

[0006] Image information of the disconnect switch within a first preset time period is acquired, and a first state sequence of the disconnect switch is determined based on the image information within the first preset time period; wherein, the first state sequence includes the open and closed states of the disconnect switch at each moment within the first preset time period;

[0007] If there are at least three pairs of adjacent open / close states that are opposite in the first state sequence, then a standard image is determined from the image information within the first preset time period, and a real-time image of the disconnector is obtained; wherein, the standard image represents an image of the disconnector without overexposure;

[0008] Based on the standard image and the real-time image, determine the open / closed state of the disconnector at the current moment.

[0009] Optionally, as described above, the open / closed state of the disconnector at the current moment is determined based on the standard image and the real-time image, including:

[0010] Based on the standard image and the real-time image, determine the overexposed areas in the real-time image;

[0011] The overexposed areas in the real-time image are processed to grayscale, and the grayscale processed real-time image is determined as the first target image;

[0012] The first target image is processed by image recognition to obtain the opening and closing state corresponding to the first target image. The opening and closing state corresponding to the first target image is determined as the opening and closing state of the disconnector at the current moment.

[0013] Optionally, as described above, the standard image and the real-time image are the same size; based on the standard image and the real-time image, the overexposed areas in the real-time image are determined, including:

[0014] The pixel value at the position of each pixel in the standard image is determined as the first pixel value, and the pixel value at the corresponding position of the pixel in the real-time image is determined as the second pixel value.

[0015] For each pixel location, determine the difference between the first pixel value and the second pixel value;

[0016] If the difference between the first pixel value and the second pixel value is greater than a preset difference threshold, then the pixel position is determined as the first target position.

[0017] The overexposed areas are determined based on all the first target locations in the real-time image.

[0018] Optionally, the method described above further includes:

[0019] Obtain the second state sequence of the disconnector within a second preset time period; wherein the second preset time period is later than the first preset time period, and the second state sequence includes the open and closed states of the disconnector at each time point within the second preset time period;

[0020] If there are at least three pairs of adjacent open / close states that are opposite in the second state sequence, the preset difference threshold is adjusted to obtain a new difference threshold and a new real-time image of the switch is obtained.

[0021] Based on the standard image and the new real-time image, and using the new difference threshold, determine the open / closed state of the switch at the new current moment.

[0022] Optionally, as described above, based on the standard image and the new real-time image, and using a new difference threshold, the open / closed state of the switch at the new current moment is determined, including:

[0023] Determine the pixel value of the corresponding pixel position in the new real-time image, which is the third pixel value;

[0024] For each pixel position, determine the difference between the first pixel value and the third pixel value;

[0025] If the difference between the first pixel value and the third pixel value is greater than the new difference threshold, then the pixel position is determined as the second target position;

[0026] Based on all the second target locations in the new real-time image, determine the overexposed areas in the new real-time image;

[0027] The overexposed areas in the new real-time image are processed to obtain the second target image;

[0028] The second target image is processed by image recognition to obtain the opening and closing state corresponding to the second target image. The opening and closing state corresponding to the second target image is determined as the opening and closing state of the switch at the new current time.

[0029] Optionally, as described above, determining a standard image from image information within a first preset time period includes:

[0030] Traverse the first state sequence. If there are three consecutive identical split-combination states, determine the target state from the three consecutive split-combination states.

[0031] The image information corresponding to the target state is determined as the standard image.

[0032] Optionally, the method described above further includes:

[0033] If there are outliers in the first state sequence, a standard image is determined from the image information within the first preset time period; wherein, outliers represent the failure to identify the open / closed state of the disconnector.

[0034] Optionally, as described above, the first state sequence of the disconnector is determined based on image information within a first preset time period, including:

[0035] Image recognition processing is performed on each image information within the first preset time period to obtain the separation and combination states corresponding to the image information;

[0036] The first state sequence of the disconnector is determined based on the opening and closing states corresponding to each image information within the first preset time period.

[0037] Secondly, this application provides a device for determining the state of a disconnector, comprising:

[0038] The acquisition unit is used to acquire image information of the disconnector within a first preset time period, and determine a first state sequence of the disconnector based on the image information within the first preset time period; wherein, the first state sequence includes the open and closed states of the disconnector at each moment within the first preset time period.

[0039] The first processing unit is configured to determine a standard image from image information within a first preset time period and acquire a real-time image of the disconnector if at least three pairs of adjacent disconnection and connection states in the first state sequence are opposite states; wherein, the standard image represents an image of the disconnector without overexposure.

[0040] The second processing unit determines the open / closed state of the disconnector at the current moment based on the standard image and the real-time image.

[0041] Thirdly, this application provides an electronic device, including: a memory and a processor;

[0042] The memory stores the instructions that the computer executes;

[0043] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0044] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible embodiments of the first aspect.

[0045] Fifthly, this application provides a computer program product, comprising: a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0046] The method, apparatus, device, and medium for determining the state of a disconnector provided in this application acquire image information of the disconnector within a first preset time period. Based on a first state sequence of the image information within the first preset time period, if at least three pairs of adjacent open / close states are opposite in the first state sequence, a standard image is determined from the image information within the first preset time period. Simultaneously, a real-time image of the disconnector is acquired, so that the open / close state of the disconnector at the current moment can be determined based on the standard image and the real-time image. The first state sequence includes the open / close states of the disconnector at various times within the first preset time period, and the standard image represents an image of the disconnector without overexposure. The method for determining the state of a disconnector provided in this application considers the possibility of overexposure in the disconnector image and determines the open / close state of the disconnector at the current moment by combining the difference between the standard image and the real-time image. The method for determining the state of a disconnector provided in this application improves the accuracy of determining the state of the disconnector. Attached Figure Description

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

[0048] Figure 1 A flowchart illustrating a method for determining the state of a disconnector provided in this application. Figure 1 ;

[0049] Figure 2 A schematic diagram showing the position of each pixel in the standard image provided in this application;

[0050] Figure 3 A schematic diagram showing the position of each pixel in the real-time image provided in this application;

[0051] Figure 4 A schematic diagram showing the positions of each pixel in the first target image provided in this application;

[0052] Figure 5 A flowchart illustrating a method for determining the state of a disconnector provided in this application. Figure 2 ;

[0053] Figure 6 A flowchart illustrating a method for determining the state of a disconnector provided in this application. Figure 3 ;

[0054] Figure 7 A schematic diagram of the structure of a device for determining the state of a disconnect switch provided in this application. Figure 1 ;

[0055] Figure 8 A schematic diagram of the structure of a device for determining the state of a disconnect switch provided in this application. Figure 2 ;

[0056] Figure 9 A schematic diagram of the structure of the electronic device provided in this application.

[0057] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0058] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0059] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0060] In a power system, the automated operation of a smart substation depends on identifying or determining the open or closed state of disconnectors. In other words, the automated operation of a smart substation depends on identifying or determining the position (closed or open) of disconnectors.

[0061] Currently, the method for determining whether a disconnector is in an open or closed state (also known as the disconnector position being open or closed) is to use a camera to capture an image of the disconnector, and then perform image recognition processing on the captured image to determine the disconnector's state.

[0062] However, in practical applications, the installation position and angle of the camera are generally fixed, and some knife switches are set outdoors. Therefore, with the rising and setting of the sun, there are strong light environments, and the images of the knife switches captured will be overexposed, which increases the difficulty of image recognition and processing, and thus leads to poor results in determining the status of the knife switches.

[0063] Therefore, there is a problem of low accuracy in determining the status of the disconnector.

[0064] The method, apparatus, device, and medium for determining the state of a disconnector provided in this application acquire image information of the disconnector within a first preset time period. Based on a first state sequence of the image information within the first preset time period, if at least three pairs of adjacent open / close states are opposite in the first state sequence, a standard image is determined from the image information within the first preset time period. Simultaneously, a real-time image of the disconnector is acquired, so that the open / close state of the disconnector at the current moment can be determined based on the standard image and the real-time image. The first state sequence includes the open / close states of the disconnector at various moments within the first preset time period, and the standard image represents an image of the disconnector without overexposure.

[0065] The method for determining the state of the disconnector provided in this application takes into account the case of overexposure in the image of the disconnector. By combining the difference between the standard image and the real-time image, the disconnector's open / closed state at the current moment is determined.

[0066] The method for determining the status of a disconnector provided in this application improves the accuracy of determining the status of the disconnector.

[0067] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0068] Figure 1 A flowchart illustrating a method for determining the state of a disconnector provided in this application. Figure 1 The execution subject of this method can be a server, host, or other device, such as... Figure 1 As shown, the method may include:

[0069] S101. Obtain image information of the disconnector within a first preset time period, and determine the first state sequence of the disconnector based on the image information within the first preset time period; wherein, the first state sequence includes the open and closed states of the disconnector at each moment within the first preset time period.

[0070] In a power system, a disconnector is a device used to control the opening and closing of circuits. Its main function is to mechanically disconnect or close circuits to ensure the safe operation of the power system. The open or closed state of the disconnector is crucial for the monitoring and automation of the power system. A power system may have one or multiple disconnectors.

[0071] The first preset time period can refer to the daytime hours of a day. For example, the first preset time period can be determined based on the normal daylight hours of a region. It is understood that the normal daylight hours are different in different regions. For example, if the normal daylight hours of region A are from 6:00 to 19:00, then 6:00 to 19:00 can be determined as the first preset time period.

[0072] Image information within the first preset time period can refer to the image information of the knife switch at various times within the first preset time period. It can be understood that image information can include the image itself as well as the image's size, pixel value, grayscale value, etc.

[0073] In one possible implementation, image information of the switch can be obtained by capturing images of the switch within a first preset time period using a preset image acquisition device.

[0074] The first state sequence of the disconnector can refer to the sequence of the disconnector's open and closed states at various moments within a first preset time period, arranged in chronological order, such as "close, close, open, close, open...".

[0075] It is understandable that the open / closed state can refer to the disconnector being in the closed or open state. "Closed" means the disconnector is in the closed position, and "open" means the disconnector is in the open position.

[0076] For example, the first preset time period can be from 6:00 to 19:00. The image of the switch is acquired once every hour to obtain the image information of the switch within the first preset time period. Based on the image information within the first preset time period, the first state sequence of the switch can be "close, close, open, close, open, close, close, open, open, open, close, close, open, close, close".

[0077] In one optional implementation, determining the first state sequence of the disconnector based on image information within a first preset time period may include:

[0078] Image recognition processing is performed on each image information within the first preset time period to obtain the corresponding opening and closing state of the image information; based on the opening and closing state corresponding to each image information within the first preset time period, the first state sequence of the disconnector is determined.

[0079] The image information within the first preset time period can refer to the image information of the switch collected at preset time intervals (e.g., once per hour) within the first preset time period. It can be understood that the image information can include the image itself as well as the image size, pixel value, grayscale value, etc.

[0080] Image recognition processing can refer to the analysis of each image using a preset image recognition algorithm or model to determine the open / closed state of the switch in that image.

[0081] For example, the steps of performing image recognition processing on a certain image information may include:

[0082] The image information is input into a preset image recognition model so that the preset image recognition model outputs the separation and combination state corresponding to the image information.

[0083] The preset image recognition model can be a pre-trained model, which may include, but is not limited to, the YOLO (You Only Look Once) model, the SSD (Single Shot MultiBox Detector) model, etc. No specific restrictions are placed on the image recognition algorithm or model, as long as it can determine the open / closed state of the switch in the image.

[0084] It is understandable that by arranging the separation and combination states corresponding to each image information within the first preset time period in chronological order, the first state sequence of the switch can be determined.

[0085] The advantage of this setup is that by performing image recognition processing on each image within the first preset time period, the state changes of the switch within the first preset time period can be accurately determined, providing a basis for subsequent judgment on whether the switch needs to be processed accordingly.

[0086] S102. If there are at least three pairs of adjacent separation and combination states that are opposite in the first state sequence, then a standard image is determined from the image information within the first preset time period, and a real-time image of the disconnector is obtained; wherein, the standard image represents an image of the disconnector without overexposure.

[0087] In this context, adjacent states of separation and combination being opposite states can refer to two consecutive states in the first state sequence that are "combined" and "separated" or "separated" and "combined".

[0088] For example, the first state sequence includes the opening and closing states of the switch at 5 moments within a first preset time period. If the first state sequence is "close, close, open, open, open", then there is a pair of adjacent opening and closing states that are opposite (the second and third opening and closing states); if the first state sequence is "close, close, open, close, close", then there are two pairs of adjacent opening and closing states that are opposite (the second and third opening and closing states, the third and fourth opening and closing states); if the first state sequence is "close, close, open, close, open", then there are three pairs of adjacent opening and closing states that are opposite (the second and third opening and closing states, the third and fourth opening and closing states, the fourth and fifth opening and closing states).

[0089] It is understandable that if there are at least three pairs of adjacent open / close states that are opposite in the first state sequence, it can be determined that the switch may be misidentified in a strong light environment, thus requiring further processing. The beneficial effect of this setting is that it can accurately screen out the switches that need to be processed under strong light, avoid unnecessary processing of switches in normal state, and save computing resources.

[0090] Furthermore, if there are at least three pairs of adjacent open / close states that are opposite in the first state sequence, then the step of determining a standard image from the image information within the first preset time period and obtaining a real-time image of the switch can be performed.

[0091] Among them, the standard image can represent the image of the knife switch without overexposure. It can be understood that the standard image can refer to the image of the knife switch that the image recognition algorithm can accurately identify and that is not overexposed under normal lighting conditions within a first preset time period.

[0092] Real-time images refer to the image information of the switch captured by a preset image acquisition device (such as a camera) at the current moment. It can be understood that standard images and real-time images can be captured by the same image acquisition device.

[0093] In one optional implementation, determining a standard image from image information within a first preset time period may include:

[0094] Traverse the first state sequence. If there are three consecutive identical split-combination states, determine the target state from the three consecutive split-combination states. Determine the image information corresponding to the target state as the standard image.

[0095] Traversing the first state sequence can be understood as checking the separation and combination states of each item in the first state sequence. Specifically, starting from the beginning of the first state sequence, each separation and combination state and its adjacent separation and combination states can be checked sequentially to find separation and combination states that satisfy specific conditions. A separation and combination state with specific conditions can refer to the existence of three consecutive identical separation and combination states, such as three consecutive identical separation and combination states all being "separation" or all being "combination".

[0096] In one possible implementation, the first state sequence can be "combined, combined, combined, combined, separated". Starting from the beginning of the first state sequence, the first, second, and third combined / separated states are three consecutive identical combined / separated states, i.e., all are "combined". The target state can then be determined from the first, second, and third combined / separated states.

[0097] For example, if three consecutive separation and combination states are at the beginning of the first state sequence, the first separation and combination state among these three separation and combination states can be taken as the target state, and the image information corresponding to the target state can be determined as the standard image.

[0098] In one possible implementation, the first state sequence can be "combined, separated, separated, separated, separated". Starting from the beginning of the first state sequence, the second, third, and fourth combined / separated states are three consecutive identical combined / separated states, that is, all are "separated" states.

[0099] For example, if three consecutive separation and combination states are not at the beginning of the first state sequence, the middle separation and combination state among these three separation and combination states can be taken as the target state, and the image information corresponding to the target state can be determined as the standard image.

[0100] It should be noted that the example of the first state sequence here is only for better understanding of how to determine the standard image. In actual application scenarios, the number of sequences in the first state sequence can be more, and there is no limit to the number of sequences in the first state sequence here.

[0101] It is understandable that by determining the target state from three consecutive open and closed states, and using the image information corresponding to the target state as the standard image, the image anomalies caused by changes in lighting or other environmental factors can be reduced, thereby improving the accuracy of subsequent processing and thus improving the precision of determining the switch state.

[0102] In an optional implementation, step S102 may further include:

[0103] If there are outliers in the first state sequence, a standard image is determined from the image information within the first preset time period; wherein, outliers represent the failure to identify the open / closed state of the disconnector.

[0104] It is understandable that if there are at least three pairs of adjacent open / close states that are opposite in the first state sequence, it can be determined that the switch may have identification errors under strong light conditions, thus requiring further processing.

[0105] Similarly, if there are outliers in the first state sequence, it can be determined that when performing image recognition processing on each image information within the first preset time period, due to certain reasons (such as strong light irradiation, image overexposure, hardware failure of image acquisition equipment, etc.), the image recognition algorithm or model that can perform image recognition processing fails to successfully determine the opening and closing state corresponding to the image information, and then an outlier is output. The outlier represents the failure to recognize the opening and closing state of the switch.

[0106] For example, outliers can be represented as "algorithm timed out", "failed", or "no result", etc., without limiting the specific content of outliers.

[0107] For example, the first state sequence can be "combined, combined, failed, combined, separated", where "failed" represents an outlier. This indicates that when performing image recognition processing on the image information corresponding to the third time step in the first state sequence, the image recognition algorithm or model failed to successfully determine the combined / separated state corresponding to the image information. This may be due to strong light irradiation, image overexposure, or other reasons. Therefore, subsequent processing steps are also required.

[0108] That is, if there are abnormal values ​​in the first state sequence, the steps from "determining the standard image from the image information within the first preset time period" to "determining the open / closed state of the switch at the current moment based on the standard image and the real-time image" are executed.

[0109] The advantage of this setting is that it can accurately filter out knife gates under strong light that need further processing, and avoid unnecessary processing of knife gate images in normal state (such as images of knife gates that are not overexposed), thereby saving computing resources.

[0110] S103. Determine the open / closed state of the disconnector at the current moment based on the standard image and the real-time image.

[0111] It is understandable that the open / closed state of the disconnector at the current moment is determined based on the standard image and the real-time image.

[0112] For example, the overexposed portion in the real-time image can be determined based on the difference in grayscale values ​​between the standard image and the real-time image, and the overexposed portion in the real-time image can be processed accordingly to improve the quality of the real-time image, so that the preset image recognition algorithm or model can more accurately determine the opening and closing state of the switch.

[0113] In one alternative implementation, step S103 may include:

[0114] Based on the standard image and the real-time image, the overexposed areas in the real-time image are determined; the overexposed areas in the real-time image are processed into grayscale, and the grayscale processed real-time image is determined as the first target image; the first target image is processed into image recognition to obtain the opening and closing state corresponding to the first target image, and the opening and closing state corresponding to the first target image is determined as the opening and closing state of the switch at the current moment.

[0115] Here, an image can refer to a data matrix composed of multiple pixels. That is, a pixel can be the smallest unit of an image. Each pixel corresponds to grayscale information. In this application, the grayscale information of a pixel can be called the pixel value or grayscale value of the pixel.

[0116] Overexposed areas can be characterized in real-time images where the pixel values ​​of each pixel are high due to strong light. The pixel values ​​of these areas can be close to or equal to the maximum value of 255 of the image sensor, which makes some details in the real-time image unclear and affects the recognition or determination of the knife switch status by the preset image recognition algorithm or model.

[0117] Grayscale processing refers to adjusting overexposed areas in a real-time image to reduce their impact on image recognition results. For example, the pixel values ​​of overexposed areas can be adjusted to a suitable range, such as setting them to a fixed value (e.g., 0, i.e., pure black).

[0118] It is understandable that after grayscale processing of the overexposed areas in the real-time image, the resulting grayscale-processed real-time image can be identified as the first target image.

[0119] Furthermore, image recognition processing can be performed on the first target image to obtain the opening and closing state corresponding to the first target image, and the opening and closing state corresponding to the first target image can be determined as the opening and closing state of the disconnector at the current moment.

[0120] The advantage of this setting is that by performing grayscale processing on the overexposed areas in the real-time image to obtain the first target image, and then performing image recognition processing on the first target image, the influence of the overexposed areas on the image recognition processing results is reduced, which can improve the accuracy of determining the state of the switch.

[0121] In one alternative implementation, the standard image and the real-time image are the same size; determining the overexposed areas in the real-time image based on the standard image and the real-time image may include:

[0122] The pixel value at each pixel location in the standard image is determined as the first pixel value, and the pixel value at the corresponding pixel location in the real-time image is determined as the second pixel value. For each pixel location, the difference between the first pixel value and the second pixel value is determined. If the difference between the first pixel value and the second pixel value is greater than a preset difference threshold, the pixel location is determined as the first target location. Based on all the first target locations in the real-time image, the overexposed area is determined.

[0123] The standard image and the real-time image are the same size, which can be understood as a one-to-one correspondence between the position of each pixel in the standard image and the position of each pixel in the real-time image.

[0124] The pixel value at each pixel location in the standard image can be used as the first pixel value, and the pixel value at the corresponding pixel location in the real-time image can be used as the second pixel value.

[0125] For each pixel location, determine the difference between the first pixel value and the second pixel value.

[0126] For example, the dimensions of both the standard image and the real-time image are m. n can be understood as the number of pixels in a standard image or a real-time image being m rows and n columns. In other words, the number of pixels in a standard image or a real-time image can be the product of m and n.

[0127] For example, the difference between the first pixel value and the second pixel value can satisfy:

[0128] ;

[0129] in, This represents the difference between the first pixel value and the second pixel value. This represents the pixel value at the position of the pixel in the i-th row and j-th column of a standard image. This represents the pixel value at the position of the pixel in the i-th row and j-th column of the real-time image.

[0130] The preset difference threshold can be a pre-set difference threshold, and the value of this difference threshold can affect the determination of overexposed areas in the real-time image.

[0131] In one possible implementation, the preset difference threshold can be set by staff based on experience.

[0132] For example, the preset difference threshold is 150. For each pixel location, if the difference between the first pixel value and the second pixel value is greater than the preset difference threshold of 150, the pixel location is determined as the first target location. Then, based on all the first target locations in the real-time image, the overexposed area is determined. It can be understood that the overexposed area includes all the first target locations in the real-time image.

[0133] The method for determining the status of a disconnector provided in this application takes into account the possibility of overexposure in the disconnector image. By combining standard and real-time images, it determines the open / closed state of the disconnector at the current moment, without requiring additional image acquisition equipment, thus reducing hardware costs. The method for determining the status of a disconnector provided in this application improves the accuracy of disconnector status determination.

[0134] To better describe how to determine overexposed areas in a real-time image and how to obtain the first target image. Figure 2 A schematic diagram showing the position of each pixel in the standard image provided in this application. Figure 3 This is a schematic diagram showing the position of each pixel in the real-time image provided in this application. Figure 4 A schematic diagram of the pixel positions of the first target image provided in this application is shown below. Figure 2 , Figure 3 , Figure 4 Describe it.

[0135] like Figure 2 As shown, each pixel in a standard image corresponds to a pixel value (or grayscale value), which ranges from 0 to 255. Correspondingly, as... Figure 3 As shown, each pixel in the real-time image has a corresponding pixel value, which ranges from 0 to 255.

[0136] Furthermore, for each pixel location, the difference between the first pixel value and the second pixel value is determined.

[0137] Taking the first row of pixel positions in a standard image or a real-time image as an example, the pixel values ​​corresponding to each pixel position in the first row of the standard image, i.e., the first pixel values, can be "0, 1, 1, 0, 45, 65" in sequence. Correspondingly, the pixel values ​​corresponding to each pixel position in the first row of the real-time image, i.e., the second pixel values, can be "0, 1, 1, 0, 235, 235" in sequence. Then, the difference between the first pixel value and the second pixel value can be "0, 0, 0, 0, 190, 170" in sequence.

[0138] For example, for other rows of pixel positions in a standard image or a real-time image, the steps for determining the difference between the first pixel value and the second pixel value are the same as those for the first row, and will not be repeated here.

[0139] It is understandable that for each pixel position, the difference between the first pixel value and the second pixel value can be determined.

[0140] For example, the preset difference threshold is 150. For each pixel location, if the difference between the first pixel value and the second pixel value is greater than the preset difference threshold of 150, then the pixel location is determined as the first target location.

[0141] Taking the first row of the above pixel positions as an example, the difference between the first pixel value and the second pixel value can be "0, 0, 0, 0, 190, 170" in sequence. It can be seen that in the first row of the pixel positions, the difference between the first pixel value and the second pixel value corresponding to the 5th pixel position and the 6th pixel position is greater than the preset difference threshold of 150. Therefore, the 5th pixel position and the 6th pixel position can be determined as the first target position.

[0142] Similarly, the first target position in other rows is determined, and the first target position in all rows is identified as the overexposed area. It can be understood that the overexposed area includes all the first target positions in the real-time image.

[0143] For example, based on a standard image and a real-time image, overexposed areas in the real-time image can be identified, grayscale processing can be performed on the overexposed areas in the real-time image, and the grayscale-processed real-time image can be determined as the first target image.

[0144] Among them, grayscale processing can set the pixel value of overexposed areas in the real-time image to 0, and pixels with a pixel value of 0 can be pure black.

[0145] To better describe the first target image, Figure 4 A schematic diagram showing the pixel positions of the first target image provided in this application, as shown below. Figure 4 As shown, each pixel in the first target image has a corresponding pixel value, ranging from 0 to 255. The shaded areas represent overexposed regions in the real-time image.

[0146] Continuing with the description of the first row of pixel positions, the pixel values ​​corresponding to each pixel position in the first row of the real-time image, i.e., the second pixel values, can be "0, 1, 1, 0, 235, 235" in sequence. By determining the difference between the first pixel value and the second pixel value, the first target position in the first row of pixel positions is the 5th pixel position and the 6th pixel position. After performing grayscale processing on the 5th pixel position and the 6th pixel position, the pixel value of the first target position is 0. That is, the pixel values ​​corresponding to each pixel position in the first row of the first target image can be "0, 1, 1, 0, 0, 0" in sequence.

[0147] The positions of the pixels in the other rows of the first target image are similar and will not be repeated here.

[0148] By combining Figure 2 and Figure 3 It can be seen from Figure 4 It can be seen that the overexposed areas of the real-time image can be the 5th and 6th pixel positions in the first row, and the 5th and 6th pixel positions in the second to seventh rows. By processing the overexposed areas with grayscale, that is, setting the pixel values ​​of the overexposed areas of the real-time image to 0, the first target image is obtained.

[0149] It should be noted that, for ease of understanding of the embodiments of this application, Figure 2 , Figure 3 , Figure 4 The image size in this example is 12*6. In practical applications, the size of standard and real-time images can be larger. Therefore, no size limit is imposed on standard and real-time images here.

[0150] Figure 5 A flowchart illustrating a method for determining the state of a disconnector provided in this application. Figure 2 The execution subject of this method can be a server, host, or other device, such as... Figure 5 As shown, the method may include:

[0151] S501. Obtain the second state sequence of the disconnector within a second preset time period; wherein the second preset time period is later than the first preset time period, and the second state sequence includes the opening and closing states of the disconnector at various times within the second preset time period.

[0152] The second preset time period can refer to a time period after the first preset time period.

[0153] For example, the first preset time period is from 6:00 to 19:00 on April 1, 2025, and the second preset time period is from 6:00 to 6:10 on April 2, 2025.

[0154] The second state sequence can refer to the open / closed state of the disconnector at various times within a second preset time period. For example, the determination of the second state sequence can refer to the determination of the first state sequence of the disconnector in step S101 above, and will not be repeated here.

[0155] It is understood that by obtaining the second state sequence of the disconnector within the second preset time period, the accuracy of determining the disconnector state can be further evaluated. For example, if there are no at least three pairs of adjacent open and closed states that are opposite in the second state sequence and there are no outliers in the second state sequence, it is considered that the accuracy of determining the disconnector state has been improved, and no further processing steps are needed.

[0156] S502. If there are at least three pairs of adjacent open / close states that are opposite in the second state sequence, the preset difference threshold is adjusted to obtain a new difference threshold, and a new real-time image of the switch is obtained.

[0157] In one possible implementation, step S502 may also be: if there are at least three pairs of adjacent open / close states that are opposite states in the second state sequence or if there are outliers in the second state sequence, then the preset difference threshold is adjusted to obtain a new difference threshold, and a new real-time image of the switch is obtained.

[0158] Understandable, Figure 1 The method for determining the state of the disconnect switch in the steps may include: acquiring image information of the disconnect switch within a first preset time period (e.g., from 6:00 to 19:00 on April 1, 2025); determining a first state sequence of the disconnect switch based on the image information within the first preset time period; if there are at least three pairs of adjacent open / close states that are opposite states in the first state sequence or if there are outliers in the second state sequence, then determining a standard image from the image information within the first preset time period and acquiring a real-time image of the disconnect switch (a real-time image at a time after 19:00 on April 1, 2025, e.g., 6:00 on April 2, 2025); determining overexposed areas in the real-time image based on the standard image and the real-time image; performing grayscale processing on the overexposed areas in the real-time image, and determining the grayscale processed real-time image as the first target image; performing image recognition processing on the first target image to obtain the open / close state corresponding to the first target image, and determining the open / close state corresponding to the first target image as the open / close state of the disconnect switch at the current time.

[0159] As time passes, for example, during the second preset time period from 6:00 AM to 6:10 AM on April 2, 2025, if there are at least three pairs of adjacent open / close states that are opposite in the second state sequence of the switch during the second preset time period, or if there are outliers in the second state sequence, it indicates that the switch may still have identification errors under strong light conditions. In this case, the preset difference threshold can be adjusted to make the subsequent determination of overexposed areas more accurate, thereby improving the accuracy of determining the switch state.

[0160] In one possible implementation, adjusting a preset difference threshold to obtain a new difference threshold may include:

[0161] Subtract the preset first difference value from the preset difference threshold to obtain the new difference threshold.

[0162] For example, if the preset difference threshold is 150 and the preset first difference value is 10, then the new difference threshold can be 140.

[0163] In one possible implementation, adjusting the preset difference threshold to obtain a new difference threshold may further include:

[0164] Determine the sum of the number of logarithms of adjacent split-and-combine states that are opposite states in the second state sequence and the number of outliers;

[0165] If the sum of the logarithm of adjacent states that are opposite in the second state sequence and the number of outliers is greater than or equal to a preset threshold (e.g., 4), then the preset second difference value (e.g., 20) is subtracted from the preset difference threshold (e.g., 150) to obtain a new difference threshold (e.g., 130). The preset second difference value is greater than the preset first difference value.

[0166] If the sum of the logarithm of the adjacent split-combination states that are opposite states and the number of outliers in the second state sequence is less than a preset number threshold (e.g., 4), then the preset second difference value (e.g., 20) is subtracted from the preset difference threshold (e.g., 150) to obtain a new difference threshold (e.g., 140).

[0167] The advantage of this setting is that by adjusting the preset difference threshold, a new difference threshold is obtained, which makes the subsequent determination of the overexposed area more accurate, thereby improving the accuracy of determining the state of the knife switch.

[0168] It should be noted that, Figure 1 The real-time image of the disconnect switch in the steps is a real-time image of the disconnect switch at a certain moment after a first preset time period. The moment corresponding to this real-time image can be after the first preset time period and before the second preset time period, or it can be within the second preset time period. Figure 5 In the corresponding steps, the new real-time image of the switch can be generated after the second preset time period.

[0169] For example, the first preset time period can be from 6:00 to 19:00 on April 1, 2025, the time corresponding to the real-time image can be 6:00 on April 2, 2025, the second preset time period can be from 6:00 to 6:10 on April 2, 2025, and the time corresponding to the new real-time image can be 6:11 on April 2, 2025.

[0170] S503. Based on the standard image and the new real-time image, and using the new difference threshold, determine the open / closed state of the disconnector at the new current moment.

[0171] In one optional implementation, determining the open / closed state of the switch at the new current moment based on a new difference threshold, using a standard image and a new real-time image, may include:

[0172] The pixel value of the corresponding pixel location in the new real-time image is determined as the third pixel value. For each pixel location, the difference between the first pixel value and the third pixel value is determined. If the difference between the first pixel value and the third pixel value is greater than a new difference threshold, the pixel location is determined as the second target location. Based on all the second target locations in the new real-time image, the overexposed areas in the new real-time image are determined. The overexposed areas in the new real-time image are processed to obtain the second target image. Image recognition processing is performed on the second target image to obtain the separation and connection state corresponding to the second target image. The separation and connection state corresponding to the second target image is determined as the separation and connection state of the switch at the new current time.

[0173] In this case, the pixel value of the corresponding pixel position in the new real-time image can be used as the third pixel value.

[0174] Furthermore, the pixel positions where the difference between the first pixel value and the third pixel value is greater than a new difference threshold are determined as the second target positions. All second target positions in the new real-time image are used to determine the overexposed areas in the new real-time image. Further, the overexposed areas in the new real-time image are subjected to grayscale processing to obtain the second target image. Image recognition processing is then performed on the second target image to obtain the separation and connection state corresponding to the second target image. The separation and connection state corresponding to the second target image is determined as the separation and connection state of the switch at the new current moment.

[0175] For example, based on the standard image and the new real-time image, and based on the new difference threshold, the open / closed state of the switch at the new current moment can be determined by referring to the above step S103, which will not be repeated here.

[0176] In one alternative implementation, Figure 1 The corresponding steps are taken as the first iteration. Figure 5 The corresponding steps are used as the second iteration. Figure 5 After the steps are completed, iteration can continue until there are no more than three pairs of adjacent open and closed states that are opposite and there are no outliers in the state sequence. If the accuracy of determining the disconnector state is high, iteration can stop.

[0177] In one possible implementation, if the number of iterations exceeds a preset number of iterations (e.g., 10 times), it indicates that the preset image acquisition device (e.g., a camera) may have a hardware failure, and a warning signal is issued. The warning signal is used to instruct staff to troubleshoot the hardware environment of the switch.

[0178] The method for determining the status of a disconnector provided in this application considers the possibility of overexposure in the disconnector image. It adjusts a preset difference threshold to obtain a new difference threshold, and then, by combining a standard image and a new real-time image, determines the disconnector's open / closed state at the new current moment based on the new difference threshold. This method improves the accuracy of determining the disconnector's status.

[0179] Figure 6 A flowchart illustrating a method for determining the state of a disconnector provided in this application. Figure 3 The execution subject of this method can be a server, host, or other device, such as... Figure 6 As shown, the method may include:

[0180] S601. Obtain image information of the disconnector within a preset time period, and determine the state sequence of the disconnector based on the image information within the preset time period; wherein, the state sequence includes the open and closed states of the disconnector at each moment within the preset time period.

[0181] S602. If there are no at least three pairs of adjacent split and merge states that are opposite states in the state sequence and there are no outliers in the state sequence, then no processing is performed.

[0182] S603. If there are at least three pairs of adjacent open / close states that are opposite in the state sequence, or if there are abnormal values ​​in the state sequence, then the disconnector shall be identified as a disconnector to be processed.

[0183] S604. Based on the image information of the switch to be processed within a preset time period, determine the standard image from the image information within the preset time period, and obtain the real-time image of the switch to be processed.

[0184] For example, the steps for determining the standard image can refer to step S102 above, and will not be repeated here.

[0185] S605. Based on the standard image, the real-time image, and the preset difference threshold, determine the overexposed areas in the real-time image.

[0186] For example, determining the overexposed area in the real-time image can refer to step S103 above, and will not be repeated here.

[0187] S606. Perform grayscale processing on the overexposed areas in the real-time image, and determine the grayscale-processed real-time image as the target image.

[0188] S607. Perform image recognition processing on the target image to obtain the opening and closing state corresponding to the target image, and determine the opening and closing state corresponding to the target image as the opening and closing state of the switch to be processed at the current moment.

[0189] S608. Obtain the image information of the disconnector within a new preset time period, and determine the new state sequence of the disconnector based on the image information within the new preset time period.

[0190] S609. If there are no at least three pairs of adjacent split-combination states that are opposite states in the new state sequence and there are no outliers in the new state sequence, then no processing is performed.

[0191] S610. If there are at least three pairs of adjacent states that are opposite in the new state sequence or if there are outliers in the state sequence, the preset difference threshold is adjusted to obtain a new difference threshold, and step S604 is executed according to the new difference threshold.

[0192] The method for determining the status of a disconnector provided in this application takes into account the possibility of overexposure in the disconnector image. By combining standard and real-time images, it determines the open / closed state of the disconnector at the current moment, without requiring additional image acquisition equipment, thus reducing hardware costs. The method for determining the status of a disconnector provided in this application improves the accuracy of disconnector status determination.

[0193] Figure 7 A schematic diagram of the structure of a device for determining the state of a disconnect switch provided in this application. Figure 1 ,like Figure 7 As shown, the device 70 for determining the state of the disconnect switch may include: an acquisition unit 701, a first processing unit 702, and a second processing unit 703.

[0194] The acquisition unit 701 is used to acquire image information of the disconnector within a first preset time period, and determine a first state sequence of the disconnector based on the image information within the first preset time period; wherein, the first state sequence includes the open and closed states of the disconnector at each moment within the first preset time period.

[0195] The first processing unit 702 is configured to determine a standard image from the image information within a first preset time period and acquire a real-time image of the disconnector if there are at least three pairs of adjacent disconnection and connection states that are opposite in the first state sequence; wherein the standard image represents an image of the disconnector without overexposure.

[0196] The second processing unit 703 determines the open / closed state of the disconnector at the current moment based on the standard image and the real-time image.

[0197] Figure 8 A schematic diagram of the structure of a device for determining the state of a disconnect switch provided in this application. Figure 2 ,like Figure 8As shown, the device 80 for determining the state of the disconnect switch may include: an acquisition unit 801, a first processing unit 802, and a second processing unit 803, wherein the second processing unit 803 further includes a first processing module 8031, a second processing module 8032, and a third processing module 8033.

[0198] The first processing module 8031 ​​is used to determine the overexposed areas in the real-time image based on the standard image and the real-time image.

[0199] The second processing module 8032 is used to perform grayscale processing on the overexposed areas in the real-time image and determine the grayscale processed real-time image as the first target image.

[0200] The third processing module 8033 is used to perform image recognition processing on the first target image to obtain the opening and closing state corresponding to the first target image, and to determine the opening and closing state corresponding to the first target image as the opening and closing state of the disconnector at the current moment.

[0201] In an optional example, the standard image and the real-time image are the same size. The first processing module 8021 is also used to determine the pixel value of each pixel position in the standard image as the first pixel value, and to determine the pixel value of the corresponding pixel position in the real-time image as the second pixel value.

[0202] For each pixel location, determine the difference between the first pixel value and the second pixel value;

[0203] If the difference between the first pixel value and the second pixel value is greater than a preset difference threshold, then the pixel position is determined as the first target position.

[0204] The overexposed areas are determined based on all the first target locations in the real-time image.

[0205] In an optional example, the device 80 for determining the state of the disconnector may further include a third processing unit 804, which is used to acquire a second state sequence of the disconnector within a second preset time period; wherein the second preset time period is later than the first preset time period, and the second state sequence includes the open and closed states of the disconnector at each time point within the second preset time period.

[0206] If there are at least three pairs of adjacent open / close states that are opposite in the second state sequence, the preset difference threshold is adjusted to obtain a new difference threshold and a new real-time image of the switch is obtained.

[0207] Based on the standard image and the new real-time image, and using the new difference threshold, determine the open / closed state of the switch at the new current moment.

[0208] In an optional example, the third processing unit 804 is also used to determine the pixel value of the corresponding pixel position in the new real-time image, which is the third pixel value;

[0209] For each pixel position, determine the difference between the first pixel value and the third pixel value;

[0210] If the difference between the first pixel value and the third pixel value is greater than the new difference threshold, then the pixel position is determined as the second target position;

[0211] Based on all the second target locations in the new real-time image, determine the overexposed areas in the new real-time image;

[0212] The overexposed areas in the new real-time image are processed to obtain the second target image;

[0213] The second target image is processed by image recognition to obtain the opening and closing state corresponding to the second target image. The opening and closing state corresponding to the second target image is determined as the opening and closing state of the switch at the new current time.

[0214] In an optional example, the first processing unit 802 is also configured to traverse the first state sequence and, if there are three consecutive identical split-combination states, determine the target state from the three consecutive split-combination states.

[0215] The image information corresponding to the target state is determined as the standard image.

[0216] In an optional example, the first processing unit 802 is further configured to determine a standard image from the image information within a first preset time period if there is an outlier in the first state sequence; wherein the outlier represents the failure to identify the open / closed state of the switch.

[0217] In an optional example, the acquisition unit 801 is also used to perform image recognition processing on each image information within a first preset time period to obtain the separation and combination state corresponding to the image information.

[0218] The first state sequence of the disconnector is determined based on the opening and closing states corresponding to each image information within the first preset time period.

[0219] Figure 9 A schematic diagram of the structure of the electronic device provided in this application, such as... Figure 9 As shown, the electronic device 90 provided in this embodiment includes at least one processor 901 and a memory 902. Optionally, the device 90 further includes a communication component 903. The processor 901, memory 902, and communication component 903 are connected via a bus 904.

[0220] In a specific implementation, at least one processor 901 executes computer execution instructions stored in memory 902, causing at least one processor 901 to perform the above-described method.

[0221] The specific implementation process of processor 901 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0222] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0223] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0224] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0225] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0226] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0227] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0228] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0229] It should be understood that the above-described device embodiments are merely illustrative, and the device of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.

[0230] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0231] When integrated units / modules are implemented in hardware, the hardware can be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor can be any suitable hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC, etc. Unless otherwise specified, the storage unit can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc.

[0232] If the integrated unit / module is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0233] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0234] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0235] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for determining the state of a disconnector, characterized in that, include: Image information of the disconnect switch within a first preset time period is acquired, and a first state sequence of the disconnect switch is determined based on the image information within the first preset time period; wherein, the first state sequence includes the open and closed states of the disconnect switch at each moment within the first preset time period; If there are at least three pairs of adjacent separation and combination states that are opposite in the first state sequence, a standard image is determined from the image information within the first preset time period, and a real-time image of the switch is obtained; wherein, the standard image represents an image of the switch without overexposure; Based on the standard image and the real-time image, determine the open / closed state of the disconnector at the current moment.

2. The method according to claim 1, characterized in that, Based on the standard image and the real-time image, the open / closed state of the disconnector at the current moment is determined, including: Based on the standard image and the real-time image, determine the overexposed areas in the real-time image; The overexposed areas in the real-time image are processed to grayscale, and the grayscale-processed real-time image is determined as the first target image; The first target image is subjected to image recognition processing to obtain the opening and closing state corresponding to the first target image, and the opening and closing state corresponding to the first target image is determined as the opening and closing state of the switch at the current moment.

3. The method according to claim 2, characterized in that, The standard image and the real-time image are the same size; determining the overexposed areas in the real-time image based on the standard image and the real-time image includes: The pixel value at each pixel position in the standard image is determined as the first pixel value, and the pixel value at the corresponding pixel position in the real-time image is determined as the second pixel value; For each pixel location, determine the difference between the first pixel value and the second pixel value; If the difference between the first pixel value and the second pixel value is greater than a preset difference threshold, then the pixel position is determined as the first target position; The overexposed area is determined based on all the first target locations in the real-time image.

4. The method according to claim 3, characterized in that, Also includes: Obtain the second state sequence of the disconnector within a second preset time period; wherein the second preset time period is later than the first preset time period, and the second state sequence includes the open and closed states of the disconnector at each time point within the second preset time period; If there are at least three pairs of adjacent open / close states that are opposite in the second state sequence, the preset difference threshold is adjusted to obtain a new difference threshold, and a new real-time image of the switch is obtained. Based on the standard image and the new real-time image, and using the new difference threshold, the open / closed state of the switch at the new current moment is determined.

5. The method according to claim 4, characterized in that, Based on the standard image and the new real-time image, and using the new difference threshold, the open / closed state of the disconnector at the new current moment is determined, including: The pixel value at the corresponding pixel position in the new real-time image is determined as the third pixel value; For each pixel location, determine the difference between the first pixel value and the third pixel value; If the difference between the first pixel value and the third pixel value is greater than the new difference threshold, then the pixel position is determined as the second target position; Based on all the second target locations in the new real-time image, determine the overexposed areas in the new real-time image; The overexposed areas in the new real-time image are processed to obtain the second target image; The second target image is subjected to image recognition processing to obtain the opening and closing state corresponding to the second target image. The opening and closing state corresponding to the second target image is determined as the opening and closing state of the switch at the new current time.

6. The method according to claim 1, characterized in that, Determining a standard image from image information within the first preset time period includes: Traverse the first state sequence. If there are three consecutive identical split-combination states, determine the target state from the three consecutive split-combination states. The image information corresponding to the target state is determined as the standard image.

7. The method according to claim 1, characterized in that, Also includes: If there are outliers in the first state sequence, a standard image is determined from the image information within the first preset time period; wherein, the outlier indicates that the open / closed state of the disconnector was not identified.

8. The method according to any one of claims 1-7, characterized in that, Based on the image information within the first preset time period, the first state sequence of the disconnector is determined, including: Image recognition processing is performed on each image information within the first preset time period to obtain the separation and combination state corresponding to the image information; The first state sequence of the disconnector is determined based on the separation and combination states corresponding to each image information within the first preset time period.

9. A device for determining the state of a disconnector, characterized in that, include: The acquisition unit is used to acquire image information of the disconnector within a first preset time period, and determine a first state sequence of the disconnector based on the image information within the first preset time period; wherein, the first state sequence includes the open / closed state of the disconnector at each moment within the first preset time period; The first processing unit is configured to determine a standard image from the image information within the first preset time period and acquire a real-time image of the switch if there are at least three pairs of adjacent open / close states that are opposite in the first state sequence; wherein the standard image represents an image of the switch that is not overexposed. The second processing unit determines the open / closed state of the disconnector at the current moment based on the standard image and the real-time image.

10. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-8.

Images