Transformer oil leakage early warning method, device, electronic device and storage medium

Abstract

The embodiments of the present application disclose a transformer oil leakage warning method, device, electronic device and storage medium. A rain signal is obtained; wherein the rain signal includes a start signal and a stop signal; if a stop signal is detected, ground oil pollution images at different times are continuously obtained, and the corresponding oil pollution area is determined based on each ground oil pollution image; the change trend of the current oil pollution area at the current moment and the historical oil pollution area at adjacent historical moments is determined; if the change trend changes from decreasing to increasing, the historical oil pollution area corresponding to the previous moment of the current oil pollution area is used as the post-rain area; based on the post-rain area and the oil pollution area subsequently adjacent to the post-rain area, the warning information is determined. The embodiments of the present application improve the real-time performance and accuracy of transformer oil leakage warning.

Description

Technical Field

[0001] The embodiments of the present application relate to information processing technology, and in particular to a transformer oil leakage early warning method, device, electronic device and storage medium. Background Art

[0002] Transformers are key relay equipment for power transmission, transformation, and distribution. Their health directly impacts the safe and stable operation of the power grid. Transformer oil leakage not only pollutes the environment and negatively impacts operations and maintenance, but also seriously impacts the safe operation of the transformer and creates potential safety hazards.

[0003] Existing technology primarily relies on manual inspections to detect goose pebble-sized oil stains on the bottom of transformers, thereby determining whether a transformer is leaking oil and issuing an early warning. However, this manual inspection-based transformer oil leakage warning is subject to weather conditions, resulting in poor real-time performance and low accuracy. Summary of the Invention

[0004] The present application provides a transformer oil leakage early warning method, device, electronic device and storage medium to improve the real-time performance and accuracy of transformer oil leakage early warning.

[0005] In a first aspect, an embodiment of the present application provides a transformer oil leakage early warning method, the transformer oil leakage early warning method comprising:

[0006] Obtaining a rain signal; wherein the rain signal includes a start signal and a stop signal;

[0007] If a stop signal is detected, the ground oil pollution images at different times are continuously acquired, and the corresponding oil pollution area is determined based on each ground oil pollution image;

[0008] Determine the change trend of the current oil pollution area at the current moment and the historical oil pollution area at the adjacent historical moments;

[0009] If the change trend changes from decreasing to increasing, the historical oil pollution area corresponding to the previous moment of the current oil pollution area is taken as the area after rain;

[0010] The warning information is determined based on the area after the rain and the oil pollution area adjacent to the area after the rain.

[0011] In a second aspect, an embodiment of the present application further provides a transformer oil leakage warning device, the transformer oil leakage warning device comprising:

[0012] A rain signal acquisition module is used to acquire a rain signal; wherein the rain signal includes a start signal and a stop signal;

[0013] The oil pollution area determination module is used to continuously obtain ground oil pollution images at different times if a stop signal is detected, and determine the corresponding oil pollution area based on each ground oil pollution image;

[0014] A change trend determination module is used to determine the change trend of the current oil pollution area at the current moment and the historical oil pollution area at adjacent historical moments;

[0015] A post-rainfall area determination module is configured to use the historical oil pollution area corresponding to the previous moment of the current oil pollution area as the post-rainfall area if the change trend changes from decreasing to increasing;

[0016] The early warning information determination module is used to determine the early warning information according to the area after the rain and the oil pollution area subsequently adjacent to the area after the rain.

[0017] In a third aspect, an embodiment of the present application further provides an electronic device, the electronic device comprising:

[0018] one or more processors;

[0019] a storage device for storing one or more programs;

[0020] When one or more programs are executed by one or more processors, the one or more processors implement any transformer oil leakage early warning method provided in the embodiments of the present application.

[0021] In a fourth aspect, an embodiment of the present application further provides a storage medium comprising computer-executable instructions, which, when executed by a computer processor, are used to execute any one of the transformer oil leakage early warning methods provided in the embodiments of the present application.

[0022] This application monitors rainy weather in real time by acquiring a rain signal, which includes a start signal and a stop signal. This allows for timely determination of whether to generate an early warning message after the rain stops, based on subsequent steps. If a stop signal is detected, ground oil pollution images are continuously acquired at different times, and the corresponding oil pollution area is determined based on each ground oil pollution image. After the rain, ground oil pollution images are continuously acquired at different times and the corresponding oil pollution area is determined, facilitating a more accurate determination of whether an oil leak has occurred. The current oil pollution area and the historical oil pollution area at adjacent moments are determined. If the trend changes from decreasing to increasing, the historical oil pollution area corresponding to the previous moment of the current oil pollution area is used as the post-rain area. Early warning messages are then determined based on the post-rain area and the oil pollution areas adjacent to the post-rain area. Determining the post-rain area allows for timely determination of oil leakage during and after the rain, enabling rapid generation of early warning messages. Therefore, the technical solution of this application solves the problem of poor real-time performance and low accuracy of transformer oil leakage early warning systems based on patrol, which can be affected by weather. This improves the real-time and accuracy of transformer oil leakage early warnings. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of a transformer oil leakage early warning method in Example 1 of the present application;

[0024] Figure 2 This is a flow chart of a transformer oil leakage early warning method in Example 2 of the present application;

[0025] Figure 3 This is a flowchart of a transformer oil leakage warning method in Example 3 of this application

[0026] Figure 4 This is a structural diagram of a transformer oil leakage warning device in the fourth embodiment of the present application;

[0027] Figure 5 This is a structural diagram of an electronic device in Example 5 of the present application. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0029] It should be noted that the terms "first" and "second" in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Example 1

[0031] Figure 1 This is a flowchart of a transformer oil leakage warning method provided in Example 1 of the present application. This embodiment is applicable to situations where oil leakage warning is provided for a transformer. The method can be executed by a transformer oil leakage warning device, which can be implemented using software and / or hardware and specifically configured in an edge device, such as a smart terminal.

[0032] See also Figure 1 The transformer oil leakage warning method shown is applied to edge devices and includes the following steps:

[0033] S110. Acquire a rain signal; wherein the rain signal includes a start signal and a stop signal.

[0034] The rain signal may be a signal indicating whether it is raining, and is used to indicate whether rain is occurring at the location of the transformer. Specifically, the rain signal includes a start signal and a stop signal. The start signal indicates the start of rain, and the stop signal indicates the stop of rain.

[0035] A rain sensor is installed at an appropriate location on the transformer. It monitors rain in real time and generates a rain signal, which is then sent to the edge device. The rain sensor is connected to the edge device via a gateway. The edge device receives the rain signal from the rain sensor in real time to determine whether it is raining at the transformer's location. For example, when the rain sensor detects rain, it generates a start signal and sends it to the edge device. When the rain sensor stops detecting rain, it generates a stop signal and sends it to the edge device.

[0036] S120: If a stop signal is detected, continuously acquire ground oil pollution images at different times, and determine the corresponding oil pollution area based on each ground oil pollution image.

[0037] The oil stain image can be an image of the ground area contaminated by the transformer oil leak. The oil stain area is the area of ​​the oil-contaminated region in the oil stain image. The presence of a transformer oil leak can be determined by continuously acquiring the trend of the oil stain area change at different times. Specifically, the oil stain image can be segmented to obtain the oil-contaminated region in the oil stain image. Then, using an area calculation model, the area of ​​the oil-contaminated region can be calculated to obtain the oil stain area corresponding to the oil stain image.

[0038] The ground below the transformer is usually paved with pebbles. In the event of an oil leak in the transformer, the leaked oil will drip onto the pebbles, leaving obvious oil stains. This facilitates the subsequent determination of the oil contamination area and improves the accuracy of the oil contamination area.

[0039] A certain number of fixed cameras are installed around the transformer, and the camera lenses are aimed at the pebbles on the ground below the transformer, which can continuously capture images of the oil pollution on the ground at different times. Specifically, the number of cameras is based on the ability to capture a panoramic view of the pebbles on the ground below the transformer. The camera communicates with the gateway connected to the edge device via a network cable, and the edge device can obtain the images of the oil pollution on the ground taken by the camera in real time, that is, continuously obtain images of the oil pollution on the ground at different times. Specifically, the camera can shoot at a certain frequency, for example, once every 2 minutes. The shooting frequency of the camera can be determined based on experiments or experience, and this application does not make any specific restrictions on this.

[0040] After detecting the stop signal, images of the oil stain on the ground are continuously acquired at different times. That is, in the event of rain, images of the oil stain on the ground are not acquired. On the one hand, rain will gradually darken the color of the pebbles not contaminated by the oil stain, approaching the oil-stained areas in the oil stain image. At the same time, when it rains, the images captured by the camera will include raindrops, reducing image clarity and making it impossible to accurately determine the area of ​​the oil stain based on the oil stain image. On the other hand, rain will blend with the oil stain, increasing its surface area. In this case, it is impossible to determine whether the change in the oil stain area is due to rain or transformer oil leakage. Therefore, after detecting the stop signal, the edge device acquires images of the oil stain on the ground. After detecting the start signal, the edge device stops acquiring images of the oil stain on the ground. For example, after detecting the start signal, the edge device can send a stop signal to the camera, instructing it to stop capturing images of the oil stain on the ground, thereby avoiding wasting resources.

[0041] S130: Determine the change trends of the current oil pollution area at the current moment and the historical oil pollution areas at adjacent historical moments.

[0042] The current moment is the moment corresponding to the latest ground oil pollution image acquired by the edge device. The current oil pollution area is the oil pollution area corresponding to the latest ground oil pollution image acquired by the edge device. That is, the oil pollution area corresponding to the current moment. The adjacent historical moment is the previous moment adjacent to the current moment, and accordingly, the historical oil pollution area is the oil pollution area corresponding to the adjacent historical moment. The change trend of the oil pollution area can be determined by comparing the sizes of the oil pollution areas at adjacent moments. Exemplarily, the change trend can be determined based on the difference in the oil pollution areas at adjacent moments. Specifically, the current oil pollution area at the current moment is compared with the size of the historical oil pollution area corresponding to the previous moment adjacent to the current oil pollution area, and the change trend of the current oil pollution area at the current moment can be determined. Specifically, the historical oil pollution area at adjacent historical moments is compared with the size of the historical oil pollution area corresponding to the previous moment adjacent to the current oil pollution area, and the change trend of the historical oil pollution area at adjacent historical moments can be determined.

[0043] S140: If the change trend changes from decreasing to increasing, the historical oil pollution area corresponding to the previous moment of the current oil pollution area is used as the area after rain.

[0044] The trend of change can include both decrease and increase. For example, the trend of change can be determined based on the difference between the oil spill areas at adjacent moments. A positive difference indicates an increase, while a negative difference indicates a decrease. The post-rainfall area is the oil spill area at the moment when the rainwater has completely evaporated after the stop signal is detected.

[0045] Because we continuously acquire images of the oil stain at different times after the stop signal is detected, the oil stain area tends to decrease during the evaporation process. If the transformer leaks oil after the stop signal is detected, the oil stain area's trend will shift from decreasing to increasing. If the trend shifts from decreasing to increasing, meaning the current oil stain area's trend is increasing and the historical oil stain area's trend at the moment before the current one was decreasing, the historical oil stain area corresponding to the moment before the current one is considered the post-rainfall area.

[0046] It should be noted that if the transformer does not leak oil after the stop signal is detected, the change trend of the oil contaminated area will change from decreasing to constant. At this time, S130 is continued to be executed, and S150 is continued to be executed when the conditions of this step are met.

[0047] S150: Determine warning information based on the post-rainfall area and the oil pollution area subsequently adjacent to the post-rainfall area.

[0048] The area after the rain can be used to determine whether an oil leak occurred during the rain. Specifically, the area after the rain can be compared with the oil spill area at the last moment before the start signal was detected. Based on the comparison result, whether an oil leak occurred during the rain can be determined. If an oil leak occurred during the rain, a rain leak warning can be generated.

[0049] The oil spill area subsequent to the post-rainfall area can be the oil spill area corresponding to the subsequent adjacent time instants of the post-rainfall area corresponding to the time instant. Whether an oil spill occurred after the rain can be determined based on the oil spill area subsequent to the post-rainfall area. Specifically, the oil spill area subsequent to the post-rainfall area can be compared with the oil spill area subsequent to the post-rainfall area, and whether an oil spill occurred after the rain can be determined based on the comparison result. If an oil spill occurred after the rain, a post-rainfall oil spill warning can be generated.

[0050] The warning information may be determined based on the area of ​​oil spillage after the rain and the oil spillage area subsequently adjacent to the area after the rain. Exemplarily, the warning information includes at least one of an oil spill warning during rain and an oil spill warning after rain. If no oil spill occurs during or after rain, no warning information is generated.

[0051] The technical solution of this embodiment monitors rainy weather in real time by acquiring a rain signal, which includes a start signal and a stop signal. This allows for timely determination of whether to generate an early warning message after the rain stops, based on subsequent steps. If a stop signal is detected, ground oil stain images are continuously acquired at different times, and the corresponding oil stain area is determined based on each ground oil stain image. After the rain, ground oil stain images are continuously acquired at different times and the corresponding oil stain area is determined, facilitating a more accurate determination of whether an oil leak has occurred. The changing trend of the current oil stain area and the historical oil stain area at adjacent moments is determined. If the changing trend changes from decreasing to increasing, the historical oil stain area corresponding to the previous moment of the current oil stain area is used as the post-rain area. Early warning messages are then determined based on the post-rain area and the oil stain areas adjacent to the post-rain area. By determining the post-rain area, oil leakage during and after the rain can be promptly determined, allowing for rapid generation of early warning messages. Therefore, the technical solution of this application solves the problem of poor real-time performance and low accuracy of transformer oil leakage early warning systems based on patrol, which can be affected by weather, thereby improving the real-time and accuracy of transformer oil leakage early warnings.

[0052] Example 2

[0053] Figure 2 This is a flowchart of a transformer oil leakage early warning method provided in Example 2 of the present application. The technical solution of this embodiment is further refined on the basis of the above technical solution.

[0054] Furthermore, "determining early warning information based on the area after the rain and the oil pollution area subsequently adjacent to the area after the rain" is refined into: "If the area after the rain matches the first area threshold, determining an oil leakage warning in the rain; determining whether to generate an oil leakage warning after the rain based on the oil pollution area subsequently adjacent to the area after the rain; if so, generating early warning information including an oil leakage warning in the rain and / or an oil leakage warning after the rain" to refine the early warning information generation process.

[0055] See also Figure 2 A transformer oil leakage early warning method is shown, comprising:

[0056] S210: Acquire a rain signal; wherein the rain signal includes a start signal and a stop signal.

[0057] S220: If a stop signal is detected, continuously acquire ground oil pollution images at different times, and determine the corresponding oil pollution area based on each ground oil pollution image.

[0058] S230: Determine the change trends of the current oil pollution area at the current moment and the historical oil pollution areas at adjacent historical moments.

[0059] S240: If the change trend changes from decreasing to increasing, the historical oil pollution area corresponding to the previous moment of the current oil pollution area is used as the area after rain.

[0060] S250: If the area after the rain matches the first area threshold, determine an oil leakage warning in the rain.

[0061] The first area threshold is a pre-set area threshold used to determine whether a transformer is leaking oil during rain. For example, the time difference between the start and stop signals can be used as the duration of rain. The maximum area expansion after rain is determined by multiplying the oil contaminated area at the last moment before the start signal in the rain signal is received, the duration of rain, and the maximum rate of rain expansion. The sum of the oil contaminated area at the last moment before the start signal in the rain signal is received and the maximum area expansion after rain is used as the maximum area after rain. The maximum rate of rain expansion is the maximum rate at which an oil contaminated area at the same location expands after being soaked and dried by rainwater, for example, 0.03 square meters per minute. For example, the first area threshold can be a value greater than or equal to the maximum area after rain. Specifically, the first area threshold can be determined based on experimentation or experience, and this is not specifically limited in this application. A match between the area after rain and the first area threshold can mean that the area after rain is greater than the first area threshold. In this case, it can be determined that the transformer at the location corresponding to the area after rain is leaking oil during rain, and an oil leak warning during rain is issued. For example, the oil spill warning in the rain may include location information corresponding to the oil pollution area and current time information.

[0062] S260: Determine whether to generate a post-rain oil leakage warning based on an oil pollution area that is subsequently adjacent to the post-rain area.

[0063] The oil spill area subsequently adjacent to the post-rainfall area may be the oil spill area corresponding to a subsequent adjacent time after the corresponding time of the post-rainfall area. Whether an oil spill has occurred after the rain can be determined based on the changing trend of the oil spill area subsequently adjacent to the post-rainfall area. Specifically, if an oil spill is determined to have occurred after the rain based on the oil spill area subsequently adjacent to the post-rainfall area, a post-rainfall oil spill warning is generated; otherwise, no post-rainfall oil spill warning is generated. Exemplarily, the post-rainfall oil spill warning may include information such as the time corresponding to the oil spill area, the location of the oil spill, and the current time.

[0064] In an optional embodiment, whether it is necessary to generate a post-rain oil leak warning is determined based on the oil pollution area subsequently adjacent to the post-rain area, including: if the oil pollution area subsequently adjacent to the post-rain area gradually increases, it is determined that it is necessary to generate a post-rain oil leak warning.

[0065] If the oil contamination area adjacent to the post-rain area gradually increases, that is, the oil contamination area corresponding to the moment adjacent to the moment corresponding to the post-rain area gradually increases, it can be determined that the transformer has leaked oil after the rain. For example, a predetermined number of adjacent oil contamination areas subsequent to the post-rain area can be preset, for example, three. Accordingly, if the oil contamination area corresponding to the three moments adjacent to the post-rain area gradually increases, it can be determined that a post-rain oil leak warning is required.

[0066] If the adjacent oil pollution area after the rain gradually increases, it is determined that a post-rain oil leakage warning needs to be generated. According to the increase in the area, it is determined that a post-rain oil leakage warning needs to be generated, which can improve the real-time nature of the warning information.

[0067] S270: If yes, generate warning information including an oil leakage warning during rain and / or an oil leakage warning after rain.

[0068] If yes, then it is determined that a post-rain oil leak warning is required. This indicates that an oil leak has occurred both during and after the rain, and an alarm message including an oil leak warning during rain and / or an oil leak warning after rain can be generated. This provides an early warning of the transformer oil leak, alerting relevant personnel to promptly address the issue.

[0069] It should be noted that if no, it means that it is determined that there is no need to generate an oil leakage warning after the rain. At this time, it means that oil leakage occurred in the rain and no oil leakage occurred after the rain. This means that the transformer is no longer leaking oil, and it is not necessary to generate an early warning message, reducing the workload of relevant staff. Alternatively, an early warning message containing an oil leakage warning in the rain can be generated to remind relevant staff to check in time to avoid oil leakage from happening again and reduce the occurrence of oil leakage incidents. For the situation where oil leakage occurs in the rain and no oil leakage occurs after the rain, it can be set according to actual needs, and this application does not make specific restrictions on this.

[0070] The technical solution of this embodiment detects oil leakage in a transformer during rain by issuing an oil leakage warning if the post-rain area matches a first area threshold. The need for a post-rain oil leakage warning is determined based on the oil contamination area adjacent to the post-rain area, confirming whether the transformer is leaking oil after the rain stops. If so, warning information is generated, including both an oil leakage warning during rain and / or an oil leakage warning after rain. This improves the comprehensiveness of warning information, facilitates appropriate maintenance based on the warning information, and ensures safe operation of the transformer.

[0071] In an optional embodiment, the warning information is determined based on the area after the rain and the oil pollution area subsequently adjacent to the area after the rain, including: if the area after the rain matches the second area threshold, determining whether to generate the warning information based on the oil pollution area subsequently adjacent to the area after the rain.

[0072] The second area threshold is a pre-set area threshold used to determine whether the area is growing normally after a rain event. For example, the time difference between the start and stop signals can be used as the rain duration, and the second area expansion can be determined by multiplying the oil spill area at the last moment before the start signal in the rain signal is received, the rain duration, and the average rate of rain expansion. The sum of the oil spill area at the last moment before the start signal in the rain signal is received and the second area expansion is used as the second area threshold. The average rate of rain expansion is the average rate at which the oil spill area at the same location expands after being soaked and dried by rain. Because the average rate of rain expansion varies with rain intensity, the average rate of rain expansion can fall within a range of rates, and accordingly, the second area threshold also falls within a range of areas. Specifically, the second area threshold can be determined based on experimentation or experience, and this is not specifically limited in this application. The post-rain area matching the second area threshold can mean that the post-rain area is within the second area threshold range, that is, the post-rain area is greater than the minimum value of the second area threshold and less than or equal to the maximum value of the second area threshold. At this point, it can be determined that the transformer at the location corresponding to the post-rainfall area did not leak oil during the rain. Therefore, whether to generate a warning message is determined based on the oil-stained area subsequently adjacent to the post-rainfall area. In other words, whether to generate a warning message is determined based on whether the transformer leaked oil after the rain. Specifically, if the oil-stained area subsequently adjacent to the post-rainfall area determines that an oil leak occurred after the rain, then a warning message is generated. Specifically, generating a post-rainfall oil leak warning can be based on generating a warning message based on the post-rainfall oil leak warning. Specifically, if the oil-stained area subsequently adjacent to the post-rainfall area determines that no oil leak occurred after the rain, then a warning message is not generated.

[0073] In an optional embodiment, whether to generate warning information is determined based on the oil pollution area subsequently adjacent to the post-rain area, including: if the oil pollution area subsequently adjacent to the post-rain area gradually increases, then generating warning information.

[0074] After determining that the transformer has not leaked oil during rain, there's no need to worry about the situation during rain. If the oil contamination area at adjacent moments to the post-rain area gradually increases, it indicates an oil leak. For example, a preset number of adjacent oil contamination areas, such as three, can be used. Comparisons are performed on the oil contamination areas in groups of three. If the adjacent three oil contamination areas gradually increase, it's determined that an oil leak warning is necessary, providing early warning of transformer oil leaks.

[0075] If the oil spill area adjacent to the post-rainfall area remains unchanged, no warning will be generated. It should be noted that, absent special circumstances, the oil spill area adjacent to the post-rainfall area will not gradually decrease. If the oil spill area gradually decreases, relevant personnel can be alerted to verify the situation and clear the original data.

[0076] If the adjacent oil pollution area after the rain gradually increases, it is determined that an oil leak warning needs to be generated. By determining that an oil leak warning needs to be generated based on the increase in area, the real-time performance of the warning information can be improved.

[0077] If the post-rain area matches a second area threshold, the transformer is identified as leaking oil during the rain, accurately determining its status in the rain. This reduces the impact of rain on transformer oil leakage and improves the accuracy of subsequent warnings. The system also determines whether to generate a warning based on the adjacent oil contamination area. This allows for continuous post-rain oil leakage detection and timely generation of warnings when a leak occurs, improving the real-time nature of warnings.

[0078] Example 3

[0079] Figure 3 This is a flowchart of a transformer oil leakage early warning method provided in Example 3 of the present application. The technical solution of this embodiment is further refined on the basis of the above technical solution.

[0080] Furthermore, "if a stop signal is detected, the ground oil pollution images at different times are continuously acquired, and the corresponding oil pollution area is determined based on each ground oil pollution image" is refined into: "perform image segmentation on each ground oil pollution image to obtain each oil pollution image; and determine the corresponding oil pollution area based on each oil pollution image" to determine the oil pollution area corresponding to each oil pollution image.

[0081] See also Figure 3 A transformer oil leakage early warning method is shown, comprising:

[0082] S310: Acquire a rain signal; wherein the rain signal includes a start signal and a stop signal.

[0083] S320: Segment each surface oil pollution image to obtain each oil pollution image.

[0084] Image segmentation is a commonly used image processing method that can isolate a desired target area from an image to facilitate subsequent processing. The oil stain image is the target image obtained by segmenting the ground oil stain image, i.e., the oil-contaminated area. Image segmentation of each ground oil stain image aims to separate the oil stain image from the ground oil stain image, thereby accurately determining the area of ​​the oil stain image. Exemplary methods for segmenting each ground oil stain image include threshold segmentation algorithms, edge segmentation algorithms, and deep learning algorithms.

[0085] In an optional embodiment, performing image segmentation on each surface oil pollution image to obtain each oil pollution image includes: performing image segmentation on each surface oil pollution image based on a lightweight convolutional neural network to obtain each oil pollution image.

[0086] A lightweight convolutional neural network is a deep learning algorithm capable of semantically segmenting images. For example, a labeled training set of data can be created based on historically collected ground oil pollution images. This training set is then divided into a training set, a validation set, and a test set in an 8:1:1 ratio. The lightweight convolutional neural network is then trained and validated. The trained lightweight convolutional neural network is then used to segment each ground oil pollution image, generating individual oil pollution images.

[0087] By performing image segmentation on each surface oil pollution image based on a lightweight convolutional neural network, each oil pollution image is obtained. By utilizing the high performance characteristics of the neural network, the segmentation rate and accuracy can be improved, thereby improving the accuracy of subsequent oil pollution images and the accuracy of oil leak warnings.

[0088] S330: Determine the corresponding oil stain area according to each oil stain image.

[0089] Each oil stain image is an irregular closed figure, and the oil stain images corresponding to each oil stain image can be determined according to a pre-established mathematical model. For example, the oil stain image can be cut into multiple triangles, and the sum of the areas of all triangles is calculated to obtain the corresponding oil stain area.

[0090] S340: Determine the change trends of the current oil pollution area at the current moment and the historical oil pollution areas at adjacent historical moments.

[0091] S350: If the change trend changes from decreasing to increasing, the historical oil pollution area corresponding to the previous moment of the current oil pollution area is used as the area after rain.

[0092] S360: Determine warning information based on the area after the rain and the oil pollution area subsequently adjacent to the area after the rain.

[0093] The technical solution of this embodiment is to obtain each oil stain image by performing image segmentation on each surface oil stain image, accurately determine the area of ​​oil pollution, and improve the accuracy of the subsequently determined oil stain area; based on each oil stain image, the corresponding oil stain area is quickly determined, thereby improving the efficiency of oil stain area determination.

[0094] Example 4

[0095] Figure 4 The figure shows a schematic diagram of the structure of a transformer oil leakage warning device provided by the fourth embodiment of the present application. This embodiment is applicable to the case of providing an oil leakage warning for a transformer. The specific structure of the transformer oil leakage warning device is as follows:

[0096] A rain signal acquisition module 410 is used to acquire a rain signal; wherein the rain signal includes a start signal and a stop signal;

[0097] The oil pollution area determination module 420 is configured to continuously acquire ground oil pollution images at different times if a stop signal is detected, and determine the corresponding oil pollution area based on each ground oil pollution image;

[0098] A change trend determination module 430 is used to determine the change trend of the current oil pollution area at the current moment and the historical oil pollution area at adjacent historical moments;

[0099] The post-rainfall area determination module 440 is configured to use the historical oil pollution area corresponding to the previous moment of the current oil pollution area as the post-rainfall area if the change trend changes from decreasing to increasing;

[0100] The warning information determination module 450 is used to determine warning information based on the post-rainfall area and the oil pollution area subsequently adjacent to the post-rainfall area.

[0101] The technical solution of this embodiment monitors rainy weather in real time by acquiring a rain signal, which includes a start signal and a stop signal. This allows for timely determination of whether to generate an early warning message after the rain stops, based on subsequent steps. If a stop signal is detected, ground oil stain images are continuously acquired at different times, and the corresponding oil stain area is determined based on each ground oil stain image. After the rain, ground oil stain images are continuously acquired at different times and the corresponding oil stain area is determined, facilitating a more accurate determination of whether an oil leak has occurred. The changing trend of the current oil stain area and the historical oil stain area at adjacent moments is determined. If the changing trend changes from decreasing to increasing, the historical oil stain area corresponding to the previous moment of the current oil stain area is used as the post-rain area. Early warning messages are then determined based on the post-rain area and the oil stain areas adjacent to the post-rain area. By determining the post-rain area, oil leakage during and after the rain can be promptly determined, allowing for rapid generation of early warning messages. Therefore, the technical solution of this application solves the problem of poor real-time performance and low accuracy of transformer oil leakage early warning systems based on patrol, which can be affected by weather, thereby improving the real-time and accuracy of transformer oil leakage early warnings.

[0102] Optionally, the warning information determination module 450 includes:

[0103] a first area threshold matching unit, configured to determine an oil leak warning in the rain if the area after the rain matches the first area threshold;

[0104] a post-rain oil spill warning determination unit, configured to determine whether a post-rain oil spill warning needs to be generated based on an oil pollution area subsequently adjacent to the post-rain area;

[0105] The warning information generating unit is configured to generate warning information including an oil leakage warning during rain and / or an oil leakage warning after rain if yes.

[0106] Optional, post-rain oil leak warning determination unit, including:

[0107] The post-rain oil spill warning generating subunit is used to determine that a post-rain oil spill warning needs to be generated if a preset number of adjacent oil pollution areas after the post-rain area gradually increase.

[0108] Optionally, the warning information determination module 450 includes:

[0109] The second area threshold matching unit is used to determine whether to generate early warning information based on the oil pollution area subsequently adjacent to the post-rain area if the post-rain area matches the second area threshold.

[0110] Optionally, the second area threshold matching unit includes:

[0111] The early warning information generating subunit is used to generate early warning information if the oil pollution area adjacent to the post-rain area gradually increases.

[0112] Optionally, the oil pollution area determination module 420 includes:

[0113] An image segmentation unit is used to segment each surface oil pollution image to obtain each oil pollution image;

[0114] The oil stain area obtaining unit is used to determine the corresponding oil stain area according to each oil stain image.

[0115] Optionally, the image segmentation unit includes:

[0116] The neural network processing subunit is used to perform image segmentation on each ground oil pollution image based on a lightweight convolutional neural network to obtain each oil pollution image.

[0117] The transformer oil leakage early warning device provided in the embodiment of the present application can execute the transformer oil leakage early warning method provided in any embodiment of the present application, and has the corresponding functional modules and beneficial effects for executing the transformer oil leakage early warning method.

[0118] Example 5

[0119] Figure 5 This is a structural diagram of an electronic device provided in Example 5 of the present application, such as Figure 5 As shown, the electronic device includes a processor 510, a memory 520, an input device 530, and an output device 540; the number of processors 510 in the electronic device can be one or more. Figure 5 In the figure, a processor 510 is used as an example; the processor 510, memory 520, input device 530 and output device 540 in the electronic device can be connected via a bus or other means. Figure 5 The bus connection is taken as an example.

[0120] Memory 520, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the transformer oil leakage early warning method in the embodiments of the present application (e.g., rain signal acquisition module 410, oil contamination area determination module 420, change trend determination module 430, post-rainfall area determination module 440, and early warning information determination module 450). Processor 510 executes the software programs, instructions, and modules stored in memory 520 to execute various functional applications and data processing of the electronic device, thereby implementing the aforementioned transformer oil leakage early warning method.

[0121] The memory 520 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created based on the use of the terminal, etc. In addition, the memory 520 may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 520 may further include a memory remotely located relative to the processor 510, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0122] The input device 530 may be used to receive input character information and generate key signal input related to user settings and function control of the electronic device. The output device 540 may include a display device such as a display screen.

[0123] Example 6

[0124] Embodiment 6 of the present application also provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to execute a transformer oil leakage warning method, the method comprising: obtaining a rain signal; wherein the rain signal comprises a start signal and a stop signal; if a stop signal is detected, continuously obtaining ground oil pollution images at different times, and determining the corresponding oil pollution area based on each ground oil pollution image; determining the change trend of the current oil pollution area at the current moment and the historical oil pollution area at adjacent historical moments; if the change trend changes from decreasing to increasing, taking the historical oil pollution area corresponding to the previous moment of the current oil pollution area as the post-rain area; and determining the warning information based on the post-rain area and the oil pollution area subsequently adjacent to the post-rain area.

[0125] Of course, the computer-executable instructions of the storage medium provided in the embodiment of the present application are not limited to the operations of the method described above, but can also execute the relevant operations in the transformer oil leakage early warning method provided in any embodiment of the present application.

[0126] Through the above description of the implementation methods, those skilled in the art can clearly understand that the present application can be implemented with the help of software and necessary general-purpose hardware, and of course it can also be implemented with hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the existing technology, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., and includes a number of instructions for enabling an electronic device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0127] It is worth noting that in the embodiment of the above-mentioned search device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application.

[0128] Note that the above are only preferred embodiments of the present application and the technical principles employed. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, readjustments, and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application has been described in more detail through the above embodiments, the present application is not limited to the above embodiments and may include many other equivalent embodiments without departing from the scope of the present application. The scope of the present application is determined by the scope of the appended claims.

Claims

1. A transformer oil leakage early warning method, characterized in that: Applied to edge devices, including: Acquire a rain signal; wherein the rain signal includes a start signal and a stop signal; If the stop signal is detected, continuously acquiring ground oil pollution images at different times, and determining the corresponding oil pollution area based on each ground oil pollution image; Determine the change trend of the current oil pollution area at the current moment and the historical oil pollution area at the adjacent historical moments; If the change trend changes from decreasing to increasing, the historical oil pollution area corresponding to the previous moment of the current oil pollution area is used as the area after rain; Determining early warning information based on the post-rainfall area and the oil pollution area subsequently adjacent to the post-rainfall area; The determining of early warning information based on the post-rainfall area and the oil pollution area subsequently adjacent to the post-rainfall area includes: If the post-rainfall area matches a first area threshold, an oil leak warning in the rain is determined. The first area threshold is determined by obtaining the time difference between the start signal and the stop signal as the rain duration, and determining the maximum expansion area after the rain based on the product of the oil spill area at the last moment before the start signal in the rain signal is received, the rain duration, and the maximum rate of rain expansion. The sum of the oil spill area at the last moment before the start signal in the rain signal is received and the maximum expansion area after the rain is used as the first area threshold. The maximum rate of rain expansion is the maximum rate at which the area of ​​the oil spill area at the same location expands after being soaked and dried by rain. determining whether it is necessary to generate a post-rainfall oil spill warning based on an oil pollution area subsequently adjacent to the post-rainfall area; If so, early warning information including the oil leakage warning in rain and the oil leakage warning after rain is generated.

2. The method according to claim 1, characterized in that The determining whether to generate a post-rain oil spill warning based on an oil spill area subsequently adjacent to the post-rain area includes: If the oil pollution area subsequently adjacent to the post-rain area gradually increases, it is determined that a post-rain oil leakage warning needs to be generated.

3. The method according to claim 1, characterized in that The determining of early warning information based on the post-rainfall area and the oil pollution area subsequently adjacent to the post-rainfall area includes: If the post-rainfall area matches a second area threshold, it is determined that the transformer has leaked oil during the rain; wherein, the second area threshold is determined by: obtaining the time difference between the start signal and the stop signal as the rain duration, and determining the second expanded area based on the product of the oil contaminated area at the last moment before the start signal in the rain signal is received, the rain duration, and the average rate of rain expansion; and taking the sum of the oil contaminated area at the last moment before the start signal in the rain signal is received and the second expanded area as the second area threshold; wherein, the average rate of rain expansion is the average rate at which the area of ​​the oil contaminated area on the ground at the same location expands after being soaked and dried by rainwater; Whether to generate the warning information is determined based on the oil pollution area subsequently adjacent to the post-rain area.

4. The method according to claim 3, characterized in that The determining whether to generate the warning information according to the oil pollution area subsequently adjacent to the post-rainfall area includes: If the oil pollution area adjacent to the post-rain area gradually increases, the warning information is generated.

5. The method according to any one of claims 1 to 4, characterized in that Determining the corresponding oil pollution area according to each of the ground oil pollution images includes: Performing image segmentation on each of the ground oil pollution images to obtain each oil pollution image; According to each of the oil stain images, the corresponding oil stain area is determined.

6. The method according to claim 5, characterized in that The step of performing image segmentation on each of the ground oil pollution images to obtain each oil pollution image includes: Based on a lightweight convolutional neural network, image segmentation is performed on each of the ground oil pollution images to obtain the respective oil pollution images.

7. A transformer oil leakage warning device, characterized in that: Configured on edge devices, including: A rain signal acquisition module, configured to acquire a rain signal; wherein the rain signal includes a start signal and a stop signal; an oil pollution area determination module, configured to continuously acquire ground oil pollution images at different times if the stop signal is detected, and determine the corresponding oil pollution area based on each ground oil pollution image; A change trend determination module is used to determine the change trend of the current oil pollution area at the current moment and the historical oil pollution area at adjacent historical moments; a post-rainfall area determination module, configured to use the historical oil pollution area corresponding to the previous moment of the current oil pollution area as the post-rainfall area if the change trend changes from decrease to increase; an early warning information determination module, configured to determine early warning information based on the post-rainfall area and the oil pollution area subsequently adjacent to the post-rainfall area; The warning information determination module includes: A first area threshold matching unit is configured to determine an oil leak warning during rain if the post-rain area matches a first area threshold; the first area threshold is determined by obtaining a time difference between the start signal and the stop signal as the rain duration, and determining a maximum area expansion after rain based on the product of the oil spill area at the last moment before the start signal in the rain signal is received, the rain duration, and the maximum rate of rain expansion; and taking the sum of the oil spill area at the last moment before the start signal in the rain signal is received and the maximum area expansion after rain as the first area threshold; wherein the maximum rate of rain expansion is the maximum rate at which the area of ​​an oil spill area at the same location expands after being soaked and dried by rainwater. a post-rain oil leakage warning determination unit, configured to determine whether a post-rain oil leakage warning needs to be generated based on an oil pollution area subsequently adjacent to the post-rain area; The warning information generating unit is configured to generate warning information including the oil leakage warning in the rain and the oil leakage warning after the rain if yes.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the transformer oil leakage early warning method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a transformer oil leakage early warning method according to any one of claims 1 to 6 is implemented.

Images