Monitoring method and device for power system

Abstract

The invention discloses a method and a device for monitoring a power system. The method relates to the field of power system monitoring, and comprises the following steps: obtaining an image of a to-be-monitored area where a power system is located, the to-be-monitored area being an area including the power system in a preset area; the image is input into a forest fire recognition model, a recognition result of the image is obtained, and the recognition result is used for representing whether the forest fire exists in the to-be-monitored area or not; in response to the identification result that the forest fire exists in the to-be-monitored area, the image is segmented to obtain at least one first sub-image, and the first sub-image comprises a first sub-area where the forest fire exists; at least one first sub-region in the to-be-monitored region is monitored, a monitoring result is obtained, and the monitoring result is used for representing whether the power system is in danger or not. According to the invention, the technical problems of low monitoring efficiency and low monitoring accuracy of monitoring the safety of the power system in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the field of power systems, and in particular to a monitoring method and device for a power system. Background Art

[0002] Since the power transmission lines of the power grid pass through relatively remote areas such as mountains and forests. When mountains and forests cause wildfires due to other reasons, if the transmission lines are not handled in time, it will not only cause damage to the power facilities in the transmission lines, but also aggravate the severity of the wildfires, and even affect the personal safety of rescuers. At present, when wildfires occur in mountains and forests that include power systems, rescuers generally carry corresponding equipment such as drones and helicopters to the scene, and then patrol the area where the wildfire occurs to observe the specific area where the wildfire is located and the direction of the spread of the fire, so as to take corresponding rescue measures in time. However, the spread speed of wildfires is relatively fast, and relying on manual patrols will result in delays in wildfire information, which leads to low monitoring efficiency for the safety of the power system.

[0003] In addition, due to the low monitoring efficiency, when the wildfire area is confirmed by manual patrol and then reported, the wildfire area may spread to other areas and new wildfire areas will appear. This means that the reported wildfire area and the actual wildfire area are inconsistent, resulting in low monitoring accuracy for the safety of the power system.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide a method and device for monitoring an electric power system, so as to at least solve the technical problems of low monitoring efficiency and low monitoring accuracy in monitoring the safety of an electric power system in the related art.

[0006] According to one aspect of an embodiment of the present invention, there is provided a method for monitoring a power system, comprising: acquiring an image of a monitored area where the power system is located; inputting the image into a wildfire recognition model to obtain a recognition result of the image, wherein the recognition result is used to characterize whether a wildfire exists in the monitored area; in response to the recognition result that a wildfire exists in the monitored area, segmenting the image to obtain at least one first sub-image, wherein the first sub-image includes: a first sub-area where a wildfire exists; monitoring at least one first sub-area in the monitored area to obtain a monitoring result, wherein the monitoring result is used to characterize whether the power system is in danger.

[0007] Optionally, at least one first sub-area in the monitored area is monitored to obtain monitoring results, including: acquiring images of the first sub-area multiple times within a first preset time period to obtain at least one second sub-image set, wherein the second sub-images included in the same second sub-image set are used to characterize images obtained by capturing the same first sub-area multiple times; matching the second sub-areas corresponding to the second sub-images in the at least one second sub-image set with the first sub-areas respectively to obtain multiple matching results, wherein the multiple matching results are used to characterize the degree of fire spread in the first sub-area where a wildfire exists in the first sub-image within the first preset time period; and obtaining monitoring results based on the multiple matching results.

[0008] Optionally, acquiring images of the first sub-area multiple times to obtain at least one second sub-image set includes: acquiring images of the area to be monitored multiple times within a first preset time period to obtain an image sequence; and segmenting each image in the image sequence to obtain at least one second sub-image set.

[0009] Optionally, based on multiple matching results, a monitoring result is obtained, including: summarizing the multiple matching results to obtain fire spread information of the area to be monitored, wherein the fire spread information includes at least: the spread direction, spread range, and spread speed of the wildfire; analyzing the fire spread information based on the location of the power system to obtain an analysis result, wherein the analysis result is used to characterize whether the wildfire will affect the safety of the power system; in response to the analysis result that the wildfire will affect the safety of the power system, determining that the monitoring result is that the power system is in danger; in response to the analysis result that the wildfire will not affect the safety of the power system, determining that the monitoring result is that the power system is not in danger.

[0010] Optionally, before inputting the image into the wildfire recognition model to obtain the image recognition result, the method also includes: preprocessing the image to obtain a preprocessed image after removing interference data; performing feature extraction on the preprocessed image to obtain image features of the image, and the image features include at least: brightness and grayscale; inputting the image features into the wildfire recognition model to obtain the image recognition result.

[0011] Optionally, the method also includes: acquiring multiple historical images of the area to be monitored to construct a training data set, wherein the multiple historical images are multiple images of wildfires at different degrees when fires occurred in the area to be monitored at different historical moments; performing feature extraction on the training data set to obtain training image features, and the training image features include at least: brightness and grayscale; and training an initial wildfire recognition model based on the training image features to obtain a wildfire recognition model.

[0012] Optionally, the method further includes: in response to the monitoring result indicating that the power system is in danger, cutting off relevant circuits of the power system.

[0013] Optionally, the method also includes: acquiring an image of the area to be monitored within a second preset time period; inputting the image into a wildfire recognition model to obtain an recognition result of the area to be monitored; and in response to the recognition result that there is no wildfire in the area to be monitored, restoring relevant circuits of the power system.

[0014] Optionally, the method further includes: in response to the monitoring result indicating that the power system is in danger, sending an alarm message to the cloud, wherein the alarm message is used to alert the cloud that a wildfire has occurred in the monitored area.

[0015] Optionally, the image is a satellite remote sensing image acquired via a satellite.

[0016] According to another aspect of an embodiment of the present invention, there is also provided a monitoring device for an electric power system, comprising: an acquisition module for acquiring an image of an area to be monitored in which the electric power system is located; an input module for inputting the image into a wildfire recognition model to obtain a recognition result of the image, wherein the recognition result is used to characterize whether there is a wildfire in the area to be monitored; a segmentation module for segmenting the image in response to the recognition result that there is a wildfire in the area to be monitored, to obtain at least one first sub-image, wherein the first sub-image includes: a first sub-area where a wildfire exists; a monitoring module for monitoring at least one first sub-area in the area to be monitored, to obtain a monitoring result, wherein the monitoring result is used to characterize whether there is a danger in the electric power system.

[0017] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the method in each embodiment of the present invention is executed when the program is running.

[0018] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0019] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0020] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0021] According to another aspect of the embodiments of the present invention, a computer program is further provided. When the computer program is executed by a processor, the methods in the embodiments of the present invention are implemented.

[0022] In an embodiment of the present invention, an image of the area to be monitored where the power system is located is obtained; the image is input into a wildfire recognition model to obtain an image recognition result; in response to the recognition result that there is a wildfire in the area to be monitored, the image is segmented to obtain at least one first sub-image; at least one first sub-area in the monitored area is monitored to obtain a monitoring result. It is easy to notice that, in the case of determining that a fire has occurred in the area where the power system is located, the monitored area can be automatically further divided to obtain multiple more accurate sub-areas where the fire has occurred, and new images can be obtained in a certain period of time. Based on the image of the sub-area where the fire occurred and the new image, the power system can be monitored more accurately, which not only saves the time wasted by manual patrols, but also does not require manual determination of the area, and achieves the purpose of accurately and efficiently monitoring the safety of the power system, thereby achieving the technical effect of improving the monitoring efficiency and monitoring accuracy of monitoring the safety of the power system, thereby solving the technical problems of low monitoring efficiency and monitoring accuracy of monitoring the safety of the power system in the related technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0024] Figure 1 is a flow chart of a method for monitoring a power system according to an embodiment of the present invention;

[0025] Figure 2 is a flow chart of an optional method for monitoring a power system according to an embodiment of the present invention;

[0026] Figure 3 is a schematic diagram of a monitoring device for a power system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below 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 of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] According to an embodiment of the present invention, an embodiment of a monitoring method for an electric power system is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0030] Figure 1 is a flow chart of a method for monitoring a power system according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0031] Step S102, acquiring an image of the area to be monitored where the power system is located.

[0032] The above-mentioned power system is a system composed of various equipment and facilities for generating, transmitting, distributing and using electric energy, wherein the power system mainly includes the following components: power generation equipment, transmission system, distribution system, power consumption equipment, monitoring and protection system, and dispatching control system. Among them, the power generation equipment includes generators, transformers, switchgear, etc., which are used to convert mechanical energy into electric energy. The transmission system includes transmission lines, substations and other facilities, which are used to transmit the electric energy generated by the power plant to the user's location. The distribution system includes distribution transformers, switchgear, cable lines, etc., which are used to distribute the electric energy transmitted by the transmission system to different users. Power consumption equipment includes household appliances, industrial equipment, etc., which are used to convert electric energy into actual energy for users to use. The monitoring and protection system includes monitoring equipment, automation system, etc., which are used to monitor the operating status of the power system, and timely discover and handle faults. Dispatching control system: including dispatching center, automation control system, etc., which are used to uniformly dispatch and control the power system to ensure the stable operation of the system. In this embodiment, the focus is on monitoring the transmission lines in the power system.

[0033] The above-mentioned area to be monitored may be any one or more areas where a power system is deployed, wherein the power system at least includes: a transmission line. For example, it may include but is not limited to: an urban area, a suburban area, a forest area, a mountain forest area. In this embodiment, the forest area or the mountain forest area is used as an example for explanation, but it is not limited thereto. The above-mentioned image may be a satellite remote sensing image acquired by a satellite.

[0034] In an optional embodiment, when it is necessary to ensure that the transmission lines of the power system can transmit electricity safely and accurately in remote areas such as forest areas or mountainous areas, it is necessary to monitor the transmission lines in real time. At this time, in order to improve the monitoring efficiency and accuracy of the transmission lines of the power system, firstly, the forest area or mountainous area can be monitored by satellite to determine the area to be monitored that contains the transmission lines of the power system in the forest area or mountainous area. Secondly, the image of the area to be monitored can be obtained by satellite, so that the transmission lines of the power system in the area to be monitored can be monitored in real time to ensure the safety of the transmission lines.

[0035] Step S104, inputting the image into a wildfire recognition model to obtain a recognition result of the image, wherein the recognition result is used to characterize whether there is a wildfire in the area to be monitored.

[0036] The above-mentioned wildfire recognition model is used to identify the acquired images to determine whether a wildfire has occurred in the area to be monitored. Among them, the wildfire recognition model is pre-constructed using a machine learning algorithm. Specifically, by collecting multiple satellite remote sensing images of wildfires in the area to be monitored at historical moments, and constructing a data set, the machine learning model training is implemented using the data set as a collection, and then the wildfire recognition model is constructed. Among them, the satellite remote sensing images in the data set refer to the satellite remote sensing images of the area to be monitored at various stages when wildfires occurred in history, such as satellite remote sensing images of wildfires at various stages such as the initial appearance of wildfires and the spread of wildfires. Wildfire recognition in the area to be monitored is realized by constructing a data set, so as to subsequently realize the identification of wildfires in the area to be monitored. Since there are obvious differences between the areas where the fire occurs and the areas where the fire does not occur when a wildfire occurs, such as differences in image brightness, image grayscale, etc., a wildfire recognition model is constructed by extracting features from multiple satellite remote sensing images of the area to be monitored when a wildfire occurs for model training. Among them, the above-mentioned wildfire identification model can be deployed in a local server, but is not limited to this. It can also be deployed in an edge server or a cloud server. The specific deployment user can set it according to actual usage requirements, which is not limited in this embodiment.

[0037] In an optional embodiment, after acquiring a satellite remote sensing image (i.e., an image), the image can be input into a wildfire recognition model via satellite communication, and the wildfire recognition model recognizes the image to obtain a recognition result of whether a wildfire has occurred in the area to be monitored. In another optional embodiment, after acquiring a satellite remote sensing image, the image can first be preprocessed (for example, interference data in the image can be removed) to obtain a preprocessed image, and then feature extraction can be performed on the preprocessed image to obtain image features of the image, and finally the image features can be input into a wildfire recognition model, and the wildfire recognition model recognizes the image to obtain a recognition result of whether a wildfire has occurred in the area to be monitored.

[0038] Step S106 , in response to the recognition result that there is a wildfire in the area to be monitored, segment the image to obtain at least one first sub-image, wherein the first sub-image includes: a first sub-area where the wildfire exists.

[0039] In an optional embodiment, when it is determined that the identification result is that there is a wildfire in the area to be monitored, first, at least one first sub-area in the image where there is a wildfire can be determined, and then the image can be segmented based on the at least one first sub-area to obtain at least one first sub-image. For example, the brightness of the image can be identified, and when it is determined that the brightness is greater than a preset brightness, it can be determined that a wildfire has occurred in the sub-area corresponding to the brightness. At this time, the image position where the sub-area is located can be segmented to obtain at least one first sub-image, wherein the first sub-image includes: the first sub-area where there is a wildfire.

[0040] Step S108, monitoring at least one first sub-area in the monitored area to obtain a monitoring result, wherein the monitoring result is used to characterize whether there is danger in the power system.

[0041] In an optional embodiment, when at least one first sub-area is obtained, the at least one first sub-area can be continuously monitored to obtain a monitoring result of whether the power transmission line of the power system is in danger. For example, after obtaining at least one first sub-area, the distance between the wildfire in at least one first sub-area and the power system can be monitored, and when it is determined that the power system is in danger, rescue can be carried out in time to prevent the wildfire from spreading further.

[0042] For another example, after obtaining at least one first sub-region, first, images of at least one first sub-region can be acquired multiple times within a first preset time period to obtain at least one second sub-image set. Secondly, the second sub-regions corresponding to the second sub-images in each second sub-image set in at least one second sub-image set can be matched with the corresponding first sub-regions to obtain multiple matching results. Finally, the multiple results can be summarized to obtain the wildfire spread speed, spread direction, and spread range of at least one first sub-region. Finally, the wildfire spread speed, spread direction, spread range, and the distance between at least one first sub-region and the power system are used. That is, by monitoring the starting point of the wildfire in the monitored area, the location where the wildfire has spread can be inferred based on the analysis results, and the monitoring result of whether the transmission lines of the power system are in danger can be obtained.

[0043] In an embodiment of the present invention, an image of the area to be monitored where the power system is located is obtained; the image is input into a wildfire recognition model to obtain an image recognition result; in response to the recognition result that there is a wildfire in the area to be monitored, the image is segmented to obtain at least one first sub-image; at least one first sub-area in the monitored area is monitored to obtain a monitoring result. It is easy to notice that, in the case of determining that a fire has occurred in the area where the power system is located, the monitored area can be automatically further divided to obtain multiple more accurate sub-areas where the fire has occurred, and new images can be obtained in a certain period of time. Based on the image of the sub-area where the fire occurred and the new image, the power system can be monitored more accurately, which not only saves the time wasted by manual patrols, but also does not require manual determination of the area, and achieves the purpose of accurately and efficiently monitoring the safety of the power system, thereby achieving the technical effect of improving the monitoring efficiency and monitoring accuracy of monitoring the safety of the power system, thereby solving the technical problems of low monitoring efficiency and monitoring accuracy of monitoring the safety of the power system in the related technology.

[0044] Optionally, at least one first sub-area in the monitored area is monitored to obtain monitoring results, including: acquiring images of the first sub-area multiple times within a first preset time period to obtain at least one second sub-image set, wherein the second sub-images included in the same second sub-image set are used to characterize images obtained by capturing the same first sub-area multiple times; matching the second sub-areas corresponding to the second sub-images in the at least one second sub-image set with the first sub-areas respectively to obtain multiple matching results, wherein the multiple matching results are used to characterize the degree of fire spread in the first sub-area where a wildfire exists in the first sub-image within the first preset time period; and obtaining monitoring results based on the multiple matching results.

[0045] The above-mentioned first preset time period can be set in advance by the user and is used to monitor whether there is any danger in the power transmission line of the power system. The specific time period is not limited in this embodiment, and the user can set it according to actual monitoring needs.

[0046] In an optional embodiment, when at least one first sub-region is obtained, the image of the first sub-region can be acquired multiple times within the first preset time period to obtain at least one second sub-image set. For example, when the number of sub-regions is one, a second sub-image set can be obtained, wherein the second sub-image set includes multiple second sub-images captured of the first sub-region within the first preset time period. For another example, when the number of sub-regions is five, five second sub-image sets can be obtained, wherein each second sub-image set includes multiple second sub-images captured of the corresponding first sub-region within the first preset time period.

[0047] In another optional embodiment, when at least one second sub-image set is obtained, the second sub-region corresponding to the second sub-image in the at least one second sub-image set can be matched with the first sub-region respectively to obtain multiple matching results, wherein the multiple matching results can be reflected in the first sub-region where the wildfire exists in the first sub-image within the first preset time period (for example, including but not limited to faster spread, slower spread). Finally, the multiple matching results can be summarized, that is, the fire spread information (for example, including but not limited to: spread speed, spread range and spread direction) can be obtained, and the fire spread information can be analyzed to obtain the monitoring result, wherein, when the analysis shows that the fire spread degree of the sub-region where the wildfire exists will not affect the power transmission line of the power system, it can be determined that the monitoring result is that the power system is not in danger. When the analysis shows that the fire spread degree of any sub-region where the wildfire exists will affect the power transmission line of the power system, it can be determined that the monitoring result is that the power system is in danger.

[0048] Optionally, acquiring images of the first sub-area multiple times to obtain at least one second sub-image set includes: acquiring images of the area to be monitored multiple times within a first preset time period to obtain an image sequence; and segmenting each image in the image sequence to obtain at least one second sub-image set.

[0049] In an optional embodiment, when at least one first sub-image is obtained, in order to more accurately monitor the wildfire in the monitoring area, the image of the monitoring area can be obtained multiple times within the first preset time period to obtain an image sequence. For example, the image sequence can be obtained multiple times at equal intervals, or multiple times at unequal intervals, but is not limited thereto.

[0050] In another optional embodiment, after obtaining the image sequence, each image in the image sequence can be segmented to obtain at least one second sub-image set. The method of segmenting the image is consistent with the above-mentioned method of segmenting the image to obtain at least one first sub-image, and is not described here. In the second sub-image set, the area corresponding to each second sub-image is the first sub-area where the wildfire occurs in the monitored area.

[0051] Optionally, based on multiple matching results, a monitoring result is obtained, including: summarizing the multiple matching results to obtain fire spread information of the area to be monitored, wherein the fire spread information includes at least: the spread direction, spread range, and spread speed of the wildfire; analyzing the fire spread information based on the location of the power system to obtain an analysis result, wherein the analysis result is used to characterize whether the wildfire will affect the safety of the power system; in response to the analysis result that the wildfire will affect the safety of the power system, determining that the monitoring result is that the power system is in danger; in response to the analysis result that the wildfire will not affect the safety of the power system, determining that the monitoring result is that the power system is not in danger.

[0052] In an optional embodiment, when multiple matching results are obtained, the multiple matching results can be summarized first to obtain the complete fire spread degree of the monitored area within the first preset time period. Based on the complete fire spread degree, the fire spread information of the monitored area can be automatically obtained through machine learning methods without manual inspections. Secondly, based on the location of the power system's transmission lines in the monitored area, the fire spread information can be analyzed to obtain an analysis result on whether the wildfire will affect the safety of the power system's transmission lines.

[0053] In another optional embodiment, when the analysis result is that the wildfire will affect the safety of the power system, the monitoring result can be determined that the power system is in danger; when the analysis result is that the wildfire will not affect the safety of the power system, the monitoring result can be determined that the power system is not in danger.

[0054] Optionally, before inputting the image into the wildfire recognition model to obtain the image recognition result, the method also includes: preprocessing the image to obtain a preprocessed image after removing interference data; performing feature extraction on the preprocessed image to obtain image features of the image, and the image features include at least: brightness and grayscale; inputting the image features into the wildfire recognition model to obtain the image recognition result.

[0055] In an optional method to ensure the processing efficiency and accuracy of the wildfire recognition model, before inputting the image into the wildfire recognition model, the image can be preprocessed first, that is, the interference data in the image is removed to obtain a preprocessed image after removing the interference data. Secondly, feature extraction can be performed on the preprocessed image to obtain image features of the image. Finally, the image features can be input into the wildfire recognition model to obtain the recognition result of the image.

[0056] Optionally, the method also includes: acquiring multiple historical images of the area to be monitored to construct a training data set, wherein the multiple historical images are multiple images of wildfires at different degrees when fires occurred in the area to be monitored at different historical moments; performing feature extraction on the training data set to obtain training image features, and the training image features include at least: brightness and grayscale; and training an initial wildfire recognition model based on the training image features to obtain a wildfire recognition model.

[0057] In an optional embodiment, in order to ensure the processing accuracy of the wildfire recognition model, the wildfire recognition model can also be trained in advance, wherein, first, multiple images of the wildfire at different degrees (for example, including but not limited to: the initial appearance of the wildfire, the wildfire spread process) when the fire occurred in the monitored area at different historical moments can be obtained to obtain multiple historical images, and then a training data set can be constructed using multiple historical images, and then feature extraction can be performed on the training data set to obtain training image features. Finally, the initial wildfire recognition model can be trained based on the training image features to obtain a wildfire recognition model, wherein the wildfire recognition model can identify the area where the wildfire has occurred in the image.

[0058] Optionally, the method further includes: in response to the monitoring result indicating that the power system is in danger, cutting off relevant circuits of the power system.

[0059] The above-mentioned related circuits may be transmission lines directly or indirectly connected to the transmission lines of the power system in the area where the wildfire occurs, that is, circuits that may be affected by the transmission lines in the area where the wildfire occurs.

[0060] In an optional embodiment, when the monitoring result determines that the power system is in danger, in order to block the spread of the wildfire, the relevant circuits of the power system can be cut off to avoid further spread of the wildfire and ensure the safety of other transmission lines in the power system.

[0061] Optionally, the method also includes: acquiring an image of the area to be monitored within a second preset time period; inputting the image into a wildfire recognition model to obtain an recognition result of the area to be monitored; and in response to the recognition result that there is no wildfire in the area to be monitored, restoring relevant circuits of the power system.

[0062] The second preset time period may be set in advance by the user to determine whether the wildfire has been extinguished. The specific time period is not limited in this embodiment, and the user may set it according to actual needs.

[0063] In an optional embodiment, within a second preset time period, images of the area to be monitored can be automatically acquired via satellite, and secondly, the images can be input into a wildfire recognition model via satellite communication to obtain an recognition result of the area to be monitored. When the recognition result is that there is no wildfire in the area to be monitored, it indicates that the wildfire has been extinguished. At this time, the relevant circuits of the power system can be restored to carry out normal power transmission.

[0064] Optionally, the method further includes: in response to the monitoring result indicating that the power system is in danger, sending an alarm message to the cloud, wherein the alarm message is used to alert the cloud that a wildfire has occurred in the monitored area.

[0065] In an optional embodiment, when it is determined that the monitoring result is that the power system is in danger, an alarm message can be sent to the cloud. After receiving the alarm message, the cloud can immediately forward the alarm message to the terminal so that the staff can perform real-time rescue tasks after receiving the alarm message.

[0066] Optionally, the image is a satellite remote sensing image acquired via a satellite.

[0067] In an optional embodiment, the image of the present invention is a satellite remote sensing image acquired by a satellite.

[0068] Figure 2 is a flow chart of an optional method for monitoring a power system according to an embodiment of the present invention, such as Figure 2 As shown, the method comprises the following steps:

[0069] Step S21, obtaining a satellite remote sensing image of the area to be monitored.

[0070] The present invention uses satellite remote sensing images and satellite communications to identify wildfire risk areas of power facilities in power grids. The area to be monitored in the present invention refers to the area where the power facilities to be monitored are located, such as the area formed by radiating a preset distance outward from the location of the power facilities of the power grid as the center.

[0071] Step S22, preprocessing the acquired satellite remote sensing image of the area to be monitored and performing feature extraction.

[0072] Preprocessing refers to removing interference data from satellite remote sensing images. The corresponding preprocessing method can be selected according to actual needs. Removing interference data through preprocessing can ensure the processing efficiency of subsequent data and improve accuracy.

[0073] Step S23, matching the feature extraction results of the satellite remote sensing image with the wildfire identification model constructed in the system to determine whether there is a wildfire in the monitored area. If so, proceed to step S24, if not, return to step S21.

[0074] Step S24, when there is a wildfire in the area to be monitored, a plurality of first sub-areas where there is a wildfire in the area to be monitored are obtained based on the matching result of the preprocessed satellite remote sensing image and the model.

[0075] In actual situations, the wildfire area in the area to be monitored may not be continuous, and there may be several small areas with fire points. Therefore, the present invention identifies the area where the wildfire exists and divides it into several sub-areas. In this way, the wildfires in each sub-area are subsequently handled separately to ensure the efficiency of wildfire handling and provide auxiliary reference for rescue personnel on site. At the same time, the spread direction, spread range, and spread speed of the wildfire can also be analyzed and predicted based on the several sub-areas where the wildfire exists. That is, by monitoring the fire points of the wildfires in the area to be monitored, the location where the wildfire has spread can be inferred based on the analysis results, and rescue can be carried out in time to avoid the further spread of the wildfire.

[0076] Step S25, obtaining satellite remote sensing images of the area to be monitored multiple times within a preset time, and matching each satellite remote sensing image with the wildfire identification model to obtain a number of second sub-areas in the corresponding area to be monitored. The second sub-area refers to the area where wildfires exist.

[0077] When it is determined that there is a wildfire in the area to be monitored, the acquired satellite remote sensing image of the area to be monitored is further matched with the wildfire identification model to obtain a plurality of second sub-areas in the area to be monitored.

[0078] Step S26, matching and comparing each second sub-region corresponding to each satellite remote sensing image within the preset time period with each first sub-region, and obtaining the wildfire spread information within the preset time period according to the comparison result. The wildfire spread information includes the wildfire spread direction, wildfire spread range, wildfire spread speed and other information.

[0079] Step S27, combining the location of the power facilities of the power grid with the wildfire spread information to predict whether the power facilities of the power grid are in danger.

[0080] At the same time, when determining the sub-area where the wildfire is located and predicting the spread of the wildfire, the location of the power facilities of the power grid in the monitored area is combined to determine whether the power facilities of the power grid are dangerous, so that when there is a danger, the relevant circuits can be cut off in time or corresponding measures can be taken to block the spread of the wildfire to ensure the safety of the power facilities of the power grid.

[0081] In addition, when judging the spread of wildfires, the spread speed of wildfires can be judged in combination with the distribution of vegetation in the monitored area, and rescue tasks can be implemented according to the spread speed and spread trend of wildfires to ensure efficient rescue with minimal losses. By communicating with local rescuers in real time to report wildfire intelligence data, rescue efficiency can be improved and rescue losses can be reduced.

[0082] At the same time, the present invention also pushes the obtained wildfire spread information to the rescue department to assist the rescue department in participating in wildfire rescue. In this way, the spread of wildfire can be pushed to the rescue site in time, and the rescue personnel on site can be provided with help and rescue in time to ensure the safety of the rescue personnel. Once the dispatch personnel on site find that there are rescue personnel within the spread range of the wildfire, they can promptly notify the rescue personnel to evacuate to ensure the safety of the rescue personnel.

[0083] After determining whether the power facilities are dangerous, step S25 is repeatedly executed to continue analyzing and predicting the wildfire.

[0084] In addition, until the system receives a notification that the wildfire has been extinguished, the system is restored and step S21 is re-executed to continue to determine whether there is a wildfire in the monitored area. The present invention can realize the identification and monitoring of wildfires at the location of power facilities of the power grid, as well as the identification and monitoring of wildfire areas, realize the monitoring of the spread of wildfires, timely predict dangers, provide auxiliary references for on-site rescue personnel, improve rescue efficiency, reduce the further expansion of wildfires, etc., and reduce losses.

[0085] In addition, after obtaining the wildfire spread information within a preset time period, the present invention can also predict the wildfire spread trend information in combination with the geographic information in the monitored area. For example, when there are weeds in part of the monitored area, the spread speed is faster, and the wildfire will spread to the area with weeds; on the contrary, when there are no plants in part of the monitored area, the spread speed is slower, etc. That is, the geographic information of the monitored area is combined with the prediction of the wildfire spread to achieve the prediction of the speed and direction of the wildfire spread. For example, according to the spread trend of the wildfire, corresponding fire prevention measures are added to some areas that are about to spread, so as to block the spread of the wildfire and avoid further expansion of the wildfire.

[0086] The present invention combines satellites with remote sensing to identify wildfires at the locations of power facilities. The present invention first uses satellite remote sensing images to identify wildfires, and then predicts and identifies the spread of wildfires in areas where wildfires exist to assist on-site rescue. When predicting the spread of wildfires, the present invention combines satellite remote sensing images with geographic information in the corresponding area to improve the accuracy of the prediction.

[0087] The present invention uses satellite remote sensing technology to identify wildfires at the location of power facilities and monitor the spread of wildfires, and monitor the positional relationship between wildfires and power facilities in real time, so as to provide rescue assistance to rescue personnel, and timely rescue power facilities in dangerous areas, reduce the losses caused by wildfires, and improve rescue efficiency. The present invention can not only identify wildfires in power facilities, but also identify the area of ​​wildfires. The process does not require human participation or human presence on site, is easy to operate, and has accurate judgment results. It can also provide rescue personnel with data support for rescue assistance during wildfires.

[0088] According to an embodiment of the present invention, an embodiment of a monitoring device for an electric power system is provided. It should be noted that the device can be used to execute the above-mentioned monitoring method for an electric power system. Figure 3 is a schematic diagram of a monitoring device for a power system according to an embodiment of the present invention. Figure 3 As shown, the device includes: an acquisition module 32, used to acquire an image of the area to be monitored where the power system is located; an input module 34, used to input the image into a wildfire recognition model to obtain a recognition result of the image, wherein the recognition result is used to characterize whether there is a wildfire in the area to be monitored; a segmentation module 36, used to segment the image in response to the recognition result that there is a wildfire in the area to be monitored, to obtain at least one first sub-image, wherein the first sub-image includes: a first sub-area where the wildfire exists; a monitoring module 38, used to monitor at least one first sub-area in the area to be monitored, to obtain a monitoring result, wherein the monitoring result is used to characterize whether there is a danger in the power system.

[0089] Optionally, the monitoring module includes: an acquisition unit, used to acquire images of the first sub-area multiple times within a first preset time period to obtain at least one second sub-image set, wherein the second sub-images contained in the same second sub-image set are used to represent the images obtained by capturing the same first sub-area multiple times; a matching unit, used to match the second sub-area corresponding to the second sub-image in at least one second sub-image set with the first sub-area respectively to obtain multiple matching results, wherein the multiple matching results are used to represent the degree of fire spread in the first sub-area where a wildfire exists in the first sub-image within the first preset time period; a processing unit, used to obtain monitoring results based on the multiple matching results.

[0090] Optionally, the acquisition unit includes: an acquisition subunit, used to acquire images of the area to be monitored multiple times within a first preset time period to obtain an image sequence; and a segmentation subunit, used to segment each image in the image sequence to obtain at least one second sub-image set.

[0091] Optionally, the processing unit includes: a summary subunit, used to summarize multiple matching results to obtain fire spread information of the monitored area, wherein the fire spread information includes at least: the spread direction, spread range, and spread speed of the wildfire; an analysis subunit, used to analyze the fire spread information based on the location of the power system to obtain an analysis result, wherein the analysis result is used to characterize whether the wildfire will affect the safety of the power system; a first determination subunit, used to determine that the monitoring result is that the power system is in danger in response to the analysis result that the wildfire will affect the safety of the power system; a second determination subunit, used to determine that the monitoring result is that the power system is not in danger in response to the analysis result that the wildfire will not affect the safety of the power system.

[0092] Optionally, before inputting the image into the wildfire recognition model to obtain the recognition result of the image, the device also includes: a preprocessing module, used to preprocess the image to obtain a preprocessed image after removing interference data; a feature extraction module, used to extract features from the preprocessed image to obtain image features of the image, and the image features include at least: brightness and grayscale; a first input module, used to input the image features into the wildfire recognition model to obtain the recognition result of the image.

[0093] Optionally, the device also includes: a historical image acquisition module, used to acquire multiple historical images of the area to be monitored and construct a training data set, wherein the multiple historical images are multiple images of wildfires at different degrees when fires occurred in the area to be monitored at different historical moments; an extraction module, used to extract features from the training data set to obtain training image features, and the training image features include at least: brightness and grayscale; a training module, used to train an initial wildfire recognition model based on the training image features to obtain a wildfire recognition model.

[0094] Optionally, the device further comprises: a cutting-off module, configured to cut off relevant circuits of the power system in response to a monitoring result indicating that the power system is in danger.

[0095] Optionally, the device also includes: an image acquisition module, used to acquire images of the area to be monitored within a second preset time period; a second input module, used to input the image into a wildfire recognition model to obtain an recognition result of the area to be monitored; and a control module, used to restore relevant circuits of the power system in response to the recognition result that there is no wildfire in the area to be monitored.

[0096] Optionally, the device further includes: a sending module for sending an alarm message to the cloud in response to a monitoring result indicating that the power system is in danger, wherein the alarm message is used to alert the cloud that a wildfire has occurred in the monitored area.

[0097] Optionally, the image is a satellite remote sensing image acquired via a satellite.

[0098] An embodiment of the present application further provides an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of the present invention when running.

[0099] An embodiment of the present application further provides a computer-readable storage medium, which includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0100] An embodiment of the present application further provides a computer program product, including a computer program, which implements the methods in various embodiments of the present invention when executed by a processor.

[0101] An embodiment of the present application further provides a computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0102] The embodiments of the present application further provide a computer program, which implements the methods in the above-mentioned embodiments of the present invention when executed by a processor.

[0103] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0104] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0105] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0106] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0107] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, 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, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0108] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for monitoring a power system, characterized in that: include: Acquire an image of the area to be monitored where the power system is located; Inputting the image into a wildfire recognition model to obtain a recognition result of the image, wherein the recognition result is used to characterize whether there is a wildfire in the area to be monitored; In response to the recognition result that a wildfire exists in the area to be monitored, segmenting the image to obtain at least one first sub-image, wherein the first sub-image includes: a first sub-area where the wildfire exists; At least one first sub-area in the area to be monitored is monitored to obtain a monitoring result, wherein the monitoring result is used to characterize whether the power system is in danger.

2. The method according to claim 1, characterized in that Monitoring at least one first sub-area in the area to be monitored to obtain a monitoring result includes: Within a first preset time period, images of the first sub-area are acquired multiple times to obtain at least one second sub-image set, wherein the second sub-images included in the same second sub-image set are used to represent images obtained by acquiring the same first sub-area multiple times; Matching the second sub-regions corresponding to the second sub-images in the at least one second sub-image set with the first sub-regions respectively to obtain a plurality of matching results, wherein the plurality of matching results are used to characterize the extent of fire spread in the first sub-region where the wildfire exists in the first sub-image within the first preset time period; Based on the multiple matching results, the monitoring result is obtained.

3. The method according to claim 2, characterized in that Acquiring the image of the first sub-area multiple times to obtain at least one second sub-image set includes: Acquire images of the area to be monitored multiple times within the first preset time period to obtain an image sequence; Each image in the image sequence is segmented to obtain the at least one second sub-image set.

4. The method according to claim 2, characterized in that: Based on the multiple matching results, the monitoring result is obtained, including: Summarizing the multiple matching results to obtain the fire spread information of the area to be monitored, wherein the fire spread information at least includes: the spread direction, spread range, and spread speed of the wildfire; Analyzing the fire spread information based on the location of the power system to obtain an analysis result, wherein the analysis result is used to indicate whether the wildfire will affect the safety of the power system; In response to the analysis result being that the wildfire will affect the safety of the power system, determining the monitoring result is that the power system is in danger; In response to the analysis result being that the wildfire will not affect the safety of the power system, it is determined that the monitoring result is that there is no danger to the power system.

5. The method according to claim 1, characterized in that Before inputting the image into a wildfire recognition model to obtain a recognition result of the image, the method further includes: Preprocessing the image to obtain a preprocessed image after removing interference data; Extracting features from the preprocessed image to obtain image features of the image, wherein the image features at least include brightness and grayscale; The image features are input into the wildfire recognition model to obtain a recognition result of the image.

6. The method according to claim 1, characterized in that The method further comprises: Acquire multiple historical images of the area to be monitored to construct a training data set, wherein the multiple historical images are multiple images of the wildfire at different degrees when a fire occurred in the area to be monitored at different historical moments; Extracting features from the training data set to obtain training image features, wherein the training image features at least include: brightness and grayscale; The initial wildfire recognition model is trained based on the training image features to obtain the wildfire recognition model.

7. The method according to claim 1, characterized in that The method further comprises: In response to the monitoring result indicating that the power system is in danger, relevant circuits of the power system are cut off.

8. The method according to claim 7, characterized in that The method further comprises: Acquiring an image of the area to be monitored within a second preset time period; Inputting the image into a wildfire recognition model to obtain a recognition result of the area to be monitored; In response to the identification result that there is no wildfire in the monitored area, the relevant circuits of the power system are restored.

9. The method according to claim 1, characterized in that: The method further comprises: In response to the monitoring result indicating that the power system is in danger, an alarm message is sent to the cloud, wherein the alarm message is used to alert the cloud that the wildfire has occurred in the monitored area.

10. A monitoring device for an electric power system, characterized in that: include: An acquisition module, used for acquiring an image of the area to be monitored where the power system is located; An input module, used to input the image into a wildfire recognition model to obtain a recognition result of the image, wherein the recognition result is used to characterize whether there is a wildfire in the area to be monitored; A segmentation module, configured to segment the image in response to the recognition result that there is a wildfire in the area to be monitored, to obtain at least one first sub-image, wherein the first sub-image includes: a first sub-area where the wildfire exists; The monitoring module is used to monitor at least one first sub-area in the area to be monitored to obtain a monitoring result, wherein the monitoring result is used to characterize whether the power system is in danger.

Images