Power distribution network operation monitoring method and system

Abstract

The invention discloses a power distribution network operation monitoring method and system, and relates to the technical field of electric power engineering, and the method comprises the steps: obtaining topological structure data of a target power distribution network and remote sensing data of an area where the target power distribution network is located, and constructing a power distribution network model; unmanned aerial vehicle equipment is adopted to shoot power transmission lines between adjacent towers in the target power distribution network, and patrol videos corresponding to the power transmission lines are obtained; cutting the patrol video frame by frame to obtain multiple frames of patrol images, and determining a target image; comparing a power transmission line image area in the target image with a power transmission line model area in the power distribution network model, and outputting feature difference data; and evaluating the current state of the power transmission line according to the characteristic difference data to obtain a state score of the power transmission line. According to the invention, whether the power transmission line is abnormal or not can be accurately judged, so that the problems of missing detection and low accuracy during detection of the power transmission line in the prior art can be solved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power engineering, and in particular to a distribution network operation monitoring method and system. Background Art

[0002] The distribution network is a power grid that receives electrical energy from the transmission network or regional power plants and distributes it locally or step by step according to voltage to various types of users through distribution facilities. The transmission lines in the distribution network are built in a topological manner, which requires the use of poles and towers to support the transmission lines. The distance between adjacent poles and towers is usually set according to the distance requirements corresponding to the distribution network level, and can also be flexibly adjusted according to the terrain environment.

[0003] In some harsh environments, for example, freezing rain will adhere to the surface of the transmission line and freeze and solidify, causing the transmission line to bear additional weight. Although the impact of such harsh environments is taken into account during the design and construction of the transmission line, in extreme cases it can also cause the transmission line to break. The broken transmission line may be grounded, posing a risk of electric shock.

[0004] At present, drone equipment is usually used for inspections in such situations. The collected images or videos are used to determine whether the attachments on the transmission lines exceed the threshold. The detection principle is to identify the degree of curvature of the transmission lines. If it exceeds the threshold, it is determined that there is a risk of breakage. Although such a judgment mechanism is simple and fast, in some specific cases, the degree of curvature of the transmission lines will change all the time, resulting in low accuracy. Summary of the invention

[0005] In view of the deficiencies in the prior art, an object of the present invention is to provide a distribution network operation monitoring method and system, aiming to solve the problem of low detection accuracy of surface attachments of transmission lines in the distribution network in the prior art.

[0006] A first aspect of the present invention is to provide a method for monitoring the operation of a distribution network, the method comprising: Acquire topological structure data of a target distribution network and remote sensing data of an area where the target distribution network is located, and construct a distribution network model according to the topological structure data and the remote sensing data; Using a preset drone device to shoot the transmission lines between adjacent towers in the target distribution network to obtain a patrol video corresponding to the transmission lines; Cutting the inspection video frame by frame to obtain multiple inspection image frames, and determining a target image in the multiple inspection image frames according to a shooting angle; Comparing the transmission line image region in the target image with the transmission line model region in the distribution network model, and outputting feature difference data; The current state of the transmission line is evaluated according to the characteristic difference data to obtain a state score of the transmission line, and corresponding strategy data is output according to the state score.

[0007] According to one aspect of the above technical solution, the step of comparing the transmission line image area in the target image with the transmission line model area in the distribution network model and outputting feature difference data includes: In a preset backend server, a feature comparison interface is called; Fixing the end points on both sides of the transmission line image region in the target image and the transmission network model region in the distribution network model correspondingly; In the feature comparison interface, the transmission line image area in the target image is compared with the transmission line model area in the distribution network model, and feature difference data is output.

[0008] According to one aspect of the above technical solution, in the feature comparison interface, the step of comparing the transmission line image area in the target image with the transmission line model area in the distribution network model and outputting feature difference data includes: In the feature comparison interface, extracting a corresponding first feature according to the transmission line image region in the target image; Extracting a corresponding second feature according to a transmission line model region in the distribution network model; Comparing the similarity of feature vectors of the first feature and the second feature, and outputting feature difference data between the first feature and the second feature; The first feature and the second feature both include shape, size, color and texture features of the transmission line.

[0009] According to one aspect of the above technical solution, in the step of performing similarity comparison of feature vectors based on the first feature and the second feature and outputting feature difference data between the first feature and the second feature, the similarity comparison of the feature vectors is Euclidean distance comparison or cosine similarity comparison.

[0010] According to one aspect of the above technical solution, the steps of evaluating the current state of the transmission line according to the characteristic difference data, obtaining a state score of the transmission line, and outputting corresponding strategy data according to the state score include: identifying the feature difference data, classifying the feature difference data, and obtaining a plurality of feature difference items; Score each characteristic difference item in the characteristic difference data respectively, and perform weighted average processing to obtain a status score of the transmission line; According to the status score of the transmission line, corresponding strategy data is output.

[0011] According to one aspect of the above technical solution, the step of scoring each feature difference item in the feature difference data and performing weighted average processing to obtain the status score of the transmission line includes: Scoring each feature difference item in the feature difference data respectively to obtain multiple difference item scores; According to the pre-assigned weights and correction factors of the multiple characteristic difference items, the scores of the multiple difference items are weighted averaged to obtain the status score of the transmission line.

[0012] According to one aspect of the above technical solution, in the step of obtaining the status score of the transmission line by performing weighted average processing on the scores of the multiple difference items according to the weights and correction factors pre-assigned to the multiple characteristic difference items, the expression of the weighted average processing is:

[0013] In the formula, X is the status score of the transmission line after weighted average processing, S i For the i The score of the feature difference item, K i For the i The weight value of the feature difference item, For the i Correction coefficient for characteristic difference terms.

[0014] A second aspect of the present invention is to provide a distribution network operation monitoring system, the system comprising: A model building module, used to obtain topological structure data of a target distribution network and remote sensing data of an area where the target distribution network is located, and to build a distribution network model according to the topological structure data and the remote sensing data; A video acquisition module is used to use a preset drone device to shoot the transmission line between adjacent towers in the target distribution network to obtain an inspection video corresponding to the transmission line; A video processing module, used for cutting the inspection video frame by frame to obtain multiple inspection images, and determining a target image in the multiple inspection images according to a shooting angle; A feature comparison module, used for comparing the transmission line image area in the target image with the transmission line model area in the distribution network model, and outputting feature difference data; A status scoring module is used to evaluate the current status of the transmission line according to the characteristic difference data, obtain a status score of the transmission line, and output corresponding strategy data according to the status score.

[0015] The third aspect of the present invention is to provide a readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the steps of the method described in the above technical solution.

[0016] The fourth aspect of the present invention is to provide an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the above technical solution when executing the program.

[0017] Compared with the prior art, the distribution network operation monitoring method and system shown in the present invention have the following beneficial effects: The method shown in the present invention obtains the topological structure data of the target distribution network and the remote sensing data of the area where the target distribution network is located, builds a distribution network model based on the topological structure data and the remote sensing data, and then during the operation of the target distribution network, uses the unmanned aerial vehicle equipment to shoot the transmission lines between the adjacent poles and towers of the target distribution network to obtain a patrol video, and obtains the target image after a series of image processing, and then compares the transmission line image area in the target image with the transmission line model area in the distribution network model, outputs the feature difference data of the two, and finally scores the current state of the transmission line based on the feature difference data to obtain the state score, so as to output the corresponding strategy data according to the state score. The method shown in the present invention is adopted, by pre-constructing the distribution network model, and then comparing the features of the actually collected target image with the corresponding transmission line in the distribution network model, it is possible to accurately determine whether the transmission line has abnormalities, thereby solving the problem of low accuracy in the detection of the transmission line in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which: Figure 1 It is a flow chart of the method for monitoring the operation of a distribution network in the first embodiment of the present invention; Figure 2 It is a structural block diagram of the distribution network operation monitoring system in the second embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings. Several embodiments of the present invention are shown in the accompanying drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0020] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0022] Embodiment 1 See also Figure 1 A first embodiment of the present invention provides a method for monitoring the operation of a distribution network, the method comprising: Step S10, acquiring topological structure data of a target distribution network and remote sensing data of an area where the target distribution network is located, and constructing a distribution network model according to the topological structure data and the remote sensing data.

[0023] First of all, it should be noted that the target distribution network, that is, the distribution network area that needs to be inspected, is usually finely divided into regions and covers a wide service range, so the structure of the distribution network is complex and diverse.

[0024] In this embodiment, in order to efficiently manage the target distribution network, the topological structure data of the target distribution network is generated by collecting the topological structures of multiple parent nodes of the target distribution network and multiple child nodes connected to the parent nodes. Based on the topological structure data of the target distribution network, the basic trend of the target distribution network can be clarified.

[0025] Furthermore, in this embodiment, remote sensing data of the area where the target distribution network is located is obtained, remote sensing features of each terrain unit are extracted based on the remote sensing data, and a distribution network model is constructed together with the topological structure data of the target distribution network.

[0026] The distribution network model is a three-dimensional virtual model, which is used to express the topography of the target distribution network area and the construction of the target distribution network based on the topography. In the distribution network model, there are towers and transmission line models, which are mapped based on the real distribution network structure. For example, the transmission line model presents a vertical downward arc.

[0027] The above is the preliminary processing flow of the target distribution network operation monitoring, which is used for subsequent monitoring by constructing a distribution network model.

[0028] Step S20, using a preset drone device to shoot the transmission lines between adjacent towers in the target distribution network to obtain an inspection video corresponding to the transmission lines.

[0029] In this embodiment, the operation of the target distribution network is detected by taking photos through drone equipment to determine the health of the target distribution network, especially the transmission lines.

[0030] Among them, the drone equipment can be a small civilian drone or a drone adjusted based on the particularity of power engineering. When monitoring the operation of the distribution network, the user needs to control the drone equipment to fly, or fly according to a pre-set flight trajectory, and then shoot the transmission lines between adjacent towers in the target distribution network, such as continuously shooting along the general extension direction of the transmission line, and then obtaining the inspection video corresponding to the transmission line.

[0031] Specifically, when using drone equipment to shoot transmission lines, the drone equipment will be controlled to shoot the transmission lines at multiple predetermined shooting angles, such as forward shooting, reverse shooting, oblique shooting, etc., and then the inspection videos of the transmission lines shot at multiple angles will be stored, processed and transmitted.

[0032] Step S30, cutting the inspection video frame by frame to obtain multiple inspection image frames, and determining a target image in the multiple inspection image frames according to the shooting angle.

[0033] In this embodiment, after the inspection video is obtained by inspecting the transmission lines in the target distribution network through drone equipment, the inspection video will be cut frame by frame according to preset requirements to obtain multiple frames of inspection images, and then a target image will be determined in the multiple frames of inspection images for subsequent feature comparison and scoring.

[0034] Among them, after the inspection video is cut frame by frame to obtain multiple frames of inspection images, the multiple frames of inspection images will be screened to screen out inspection images that do not meet the image quality requirements, such as blurred images or incomplete display of power transmission lines. Then, from the remaining multiple frames of inspection images, according to the requirements of the forward shooting angle, an inspection image with the best image quality is selected, and it is required that the power transmission line can be fully presented in the inspection image, and it is determined as the target image.

[0035] Specifically, the forward shooting angle requires that the center of the eye of the camera in the drone equipment is in the same straight line with the geometric center point of the largest circumscribed rectangular frame of the transmission line. By adjusting the vertical distance between the drone equipment and the transmission line or adjusting the focal length of the camera, the transmission line can be fully presented in the inspection image serving as the target image, ensuring that the transmission line is located in the middle position in the target image and accurately presenting the current shape of the transmission line.

[0036] Step S40, comparing the transmission line image area in the target image with the transmission line model area in the distribution network model, and outputting feature difference data.

[0037] In this embodiment, after constructing the distribution network model and selecting the target image of the transmission line, the transmission line image area in the target image is compared with the transmission line model area in the distribution network model, including various feature comparisons, such as the outer contour and color of the transmission line, and then the feature difference data is output.

[0038] The step of comparing the transmission line image area in the target image with the transmission line model area in the distribution network model and outputting feature difference data comprises: In a preset backend server, a feature comparison interface is called; Fixing the end points on both sides of the transmission line image region in the target image and the transmission network model region in the distribution network model correspondingly; In the feature comparison interface, the transmission line image area in the target image is compared with the transmission line model area in the distribution network model, and feature difference data is output.

[0039] Specifically, in the process of comparing the transmission line image area of ​​the target image with the transmission line model area of ​​the distribution network model to output feature difference data, a feature comparison interface will first be called on the background server. The feature comparison interface is a UI interface with scale marks, specifically with coordinate scale marks. Then, the transmission line image area in the target image and the transmission line model area in the distribution network model are matched according to a preset ratio to make them consistent in size. Then, the end points on both sides of the transmission line are fixed in the interface with anchor points. Based on the assistance of the interface, the feature comparison between the transmission line image area and the transmission line model area is realized, and finally the feature difference data is output.

[0040] Among them, in the feature comparison interface, the step of comparing the transmission line image area in the target image with the transmission line model area in the distribution network model and outputting feature difference data includes: In the feature comparison interface, extracting a corresponding first feature according to the transmission line image region in the target image; Extracting a corresponding second feature according to a transmission line model region in the distribution network model; Comparing the similarity of feature vectors of the first feature and the second feature, and outputting feature difference data between the first feature and the second feature; The first feature and the second feature both include shape, size, color and texture features of the transmission line.

[0041] Specifically, in the feature comparison interface of the background server, the first feature corresponding to the transmission line is extracted according to the transmission line image area in the target image, including the shape, size, color and texture features of the transmission line. Then, the second feature corresponding to the transmission line is extracted according to the transmission line model area in the distribution network model, also including the shape, size, color and texture features of the transmission line. Then, the first feature and the second feature are compared for the similarity of the feature vectors, such as Euclidean distance comparison or cosine similarity comparison, and the feature difference data of the first feature and the second feature are output.

[0042] Furthermore, the feature difference data includes a plurality of feature difference items, each of which corresponds to a detailed record of feature differences. For example, the curvature of the shape contour of the transmission line photographed by the drone equipment is increased compared to the distribution network model, and the diameter of the transmission line is increased. Based on such feature difference data, it can be explained that the transmission line carries attachments, such as the freezing rain shown in the background technology. It is easy to understand that if the curvature of the shape contour of the transmission line increases significantly, and the diameter increases significantly, it means that the weight and volume of the attachments attached to the surface of the transmission line are large. If intervention is not carried out in time, it may cause the transmission line to break. Therefore, in this embodiment, it is also necessary to quantify the risk and output a corresponding response strategy.

[0043] Step S50, evaluating the current state of the transmission line according to the characteristic difference data to obtain a state score of the transmission line, and outputting corresponding strategy data according to the state score.

[0044] In this embodiment, after obtaining the feature difference data between the transmission line image area and the transmission line model area, each feature difference item in the feature difference data will be scored separately, and then the current state of the transmission line will be scored based on the score of each feature difference item to obtain the state score of the transmission line, and finally the corresponding strategy data will be output based on the state score.

[0045] Among them, the status score is, for example, a score of 10 or 100, which corresponds to multiple levels for characterizing the health of the transmission line. The higher the status score, the higher the health, and the lower the status score, the lower the health.

[0046] In the case of a low status score, such as due to freezing rain, the inspection video taken by the drone equipment is combined to output the strategy data corresponding to the transmission line or the entire target distribution network. The strategy data records the topological nodes where the transmission line is located to determine the actual geographical location, as well as the current risk level, recommended response strategies, etc. For example, the transmission line can be controlled to instantly pass a large current to generate heat to melt the ice, or manual management can be performed.

[0047] In summary, compared with the prior art, the distribution network operation monitoring method shown in this embodiment has the following beneficial effects: The method shown in this embodiment obtains the topological structure data of the target distribution network and the remote sensing data of the area where the target distribution network is located, and constructs a distribution network model based on the topological structure data and the remote sensing data. Then, during the operation of the target distribution network, the transmission lines between the adjacent towers of the target distribution network are photographed by drone equipment to obtain a patrol video, and a target image is obtained after a series of image processing. Then, the transmission line image area in the target image is compared with the transmission line model area in the distribution network model, and the feature difference data of the two are output. Finally, the current state of the transmission line is scored based on the feature difference data to obtain a state score, so as to output corresponding strategy data according to the state score. By adopting the method shown in this embodiment, by pre-constructing the distribution network model, and then comparing the features of the actually collected target image with the corresponding transmission line in the distribution network model, it is possible to accurately determine whether the transmission line has abnormalities, thereby solving the problem of low accuracy in the detection of transmission lines in the prior art.

[0048] Embodiment 2 The second embodiment of the present invention also provides a distribution network operation monitoring method, which is basically similar to the method shown in the first embodiment, except that: In this embodiment, the steps of evaluating the current state of the transmission line according to the characteristic difference data, obtaining a state score of the transmission line, and outputting corresponding strategy data according to the state score include: identifying the feature difference data, classifying the feature difference data, and obtaining a plurality of feature difference items; Score each characteristic difference item in the characteristic difference data respectively, and perform weighted average processing to obtain a status score of the transmission line; According to the status score of the transmission line, corresponding strategy data is output.

[0049] Specifically, in the present embodiment, after feature comparison between the transmission line image area of ​​the target image and the transmission line model area of ​​the distribution network model is performed to output feature difference data, the feature difference data is identified and classified to obtain a plurality of feature difference items, such as feature difference items including shape, size, color and texture features, and then each feature difference item is scored separately according to a pre-set scoring rule to obtain a score for each feature difference item, and finally the scores of all feature difference items are weighted averaged to obtain a status score of the transmission line, which is used to characterize the health of the transmission line. The higher the status score, the healthier the transmission line and the lower its risk, and vice versa, the lower the health, the higher the risk.

[0050] The step of scoring each feature difference item in the feature difference data and performing weighted average processing to obtain the status score of the transmission line comprises: Scoring each feature difference item in the feature difference data respectively to obtain multiple difference item scores; According to the pre-assigned weights and correction factors of the multiple characteristic difference items, the scores of the multiple difference items are weighted averaged to obtain the status score of the transmission line.

[0051] The expression of weighted average processing is:

[0052] In the formula, X is the status score of the transmission line after weighted average processing, S i For the i The score of the feature difference item, K i For the i The weight value of the feature difference item, For the i Correction coefficient for characteristic difference terms.

[0053] Specifically, the above X The higher the value, the healthier the transmission line is and the lower the risk of rupture. Conversely, the lower the health of the transmission line is and the higher the risk of rupture.

[0054] Embodiment 3 See also Figure 2 The third embodiment of the present invention provides a distribution network operation monitoring system, which includes: a model building module 10, a video acquisition module 20, a video processing module 30, a feature comparison module 40 and a status scoring module 50.

[0055] The model building module 10 is used to obtain the topological structure data of the target distribution network and the remote sensing data of the area where the target distribution network is located, and to build a distribution network model according to the topological structure data and the remote sensing data; The video acquisition module 20 is used to use a preset drone device to shoot the transmission line between adjacent towers in the target distribution network to obtain the inspection video corresponding to the transmission line; The video processing module 30 is used to cut the inspection video frame by frame to obtain multiple inspection images, and determine a target image in the multiple inspection images according to the shooting angle; A feature comparison module 40 is used to compare the transmission line image area in the target image with the transmission line model area in the distribution network model, and output feature difference data; The state scoring module 50 is used to evaluate the current state of the transmission line according to the characteristic difference data, obtain the state score of the transmission line, and output corresponding strategy data according to the state score.

[0056] Compared with the prior art, the distribution network operation monitoring system shown in this embodiment has the following beneficial effects: The system shown in this embodiment obtains the topological structure data of the target distribution network and the remote sensing data of the area where the target distribution network is located, and constructs a distribution network model based on the topological structure data and the remote sensing data. Then, during the operation of the target distribution network, the transmission lines between the adjacent poles and towers of the target distribution network are photographed by drone equipment to obtain a patrol video, and a target image is obtained after a series of image processing. Then, the transmission line image area in the target image is compared with the transmission line model area in the distribution network model, and the feature difference data of the two are output. Finally, the current state of the transmission line is scored based on the feature difference data to obtain a state score, so as to output corresponding strategy data according to the state score. The system shown in this embodiment is used to construct a distribution network model in advance, and then compare the features of the actually collected target image with the corresponding transmission line in the distribution network model, so as to accurately determine whether the transmission line has abnormalities, thereby solving the problem of low accuracy in the detection of transmission lines in the prior art.

[0057] Embodiment 4 A fourth embodiment of the present invention provides a readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the steps of the method described in the above embodiment.

[0058] Embodiment 5 A fifth embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the above embodiment when executing the program.

[0059] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples" or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0060] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A distribution network operation monitoring method, characterized in that: The method comprises: Acquire topological structure data of a target distribution network and remote sensing data of an area where the target distribution network is located, and construct a distribution network model according to the topological structure data and the remote sensing data; Using a preset drone device to shoot the transmission lines between adjacent towers in the target distribution network to obtain a patrol video corresponding to the transmission lines; Cutting the inspection video frame by frame to obtain multiple inspection image frames, and determining a target image in the multiple inspection image frames according to a shooting angle; Comparing the transmission line image region in the target image with the transmission line model region in the distribution network model, and outputting feature difference data; The current state of the transmission line is evaluated according to the characteristic difference data to obtain a state score of the transmission line, and corresponding strategy data is output according to the state score.

2. The distribution network operation monitoring method according to claim 1, characterized in that: The step of comparing the transmission line image region in the target image with the transmission line model region in the distribution network model and outputting feature difference data comprises: In a preset backend server, a feature comparison interface is called; Fixing the end points on both sides of the transmission line image region in the target image and the transmission network model region in the distribution network model correspondingly; In the feature comparison interface, the transmission line image area in the target image is compared with the transmission line model area in the distribution network model, and feature difference data is output.

3. The distribution network operation monitoring method according to claim 2, characterized in that: In the feature comparison interface, the step of comparing the transmission line image region in the target image with the transmission line model region in the distribution network model and outputting feature difference data includes: In the feature comparison interface, extracting a corresponding first feature according to the transmission line image region in the target image; Extracting a corresponding second feature according to a transmission line model region in the distribution network model; Comparing the similarity of feature vectors of the first feature and the second feature, and outputting feature difference data between the first feature and the second feature; The first feature and the second feature both include shape, size, color and texture features of the transmission line.

4. The distribution network operation monitoring method according to claim 3, characterized in that: In the step of performing similarity comparison of feature vectors according to the first feature and the second feature and outputting feature difference data between the first feature and the second feature, the similarity comparison of the feature vectors is Euclidean distance comparison or cosine similarity comparison.

5. The distribution network operation monitoring method according to any one of claims 1 to 4, characterized in that: The steps of evaluating the current state of the transmission line according to the characteristic difference data to obtain a state score of the transmission line, and outputting corresponding strategy data according to the state score include: identifying the feature difference data, classifying the feature difference data, and obtaining a plurality of feature difference items; Score each characteristic difference item in the characteristic difference data respectively, and perform weighted average processing to obtain a status score of the transmission line; According to the status score of the transmission line, corresponding strategy data is output.

6. The method for monitoring the operation of a distribution network according to claim 5, characterized in that: The step of scoring each characteristic difference item in the characteristic difference data respectively and performing weighted average processing to obtain the status score of the transmission line comprises: Scoring each feature difference item in the feature difference data respectively to obtain multiple difference item scores; According to the pre-assigned weights and correction factors of the multiple characteristic difference items, the scores of the multiple difference items are weighted averaged to obtain the status score of the transmission line.

7. The method for monitoring the operation of a distribution network according to claim 6, characterized in that: In the step of performing weighted average processing on the scores of the multiple difference items according to the pre-assigned weights and correction factors of the multiple characteristic difference items to obtain the status score of the transmission line, the expression of the weighted average processing is: In the formula, X is the status score of the transmission line after weighted average processing, S i For the i The score of the feature difference item, K i For the i The weight value of the feature difference item, For the i Correction coefficient for characteristic difference terms.

8. A distribution network operation monitoring system, characterized in that: The system comprises: A model building module, used to obtain topological structure data of a target distribution network and remote sensing data of an area where the target distribution network is located, and to build a distribution network model according to the topological structure data and the remote sensing data; A video acquisition module is used to use a preset drone device to shoot the transmission line between adjacent towers in the target distribution network to obtain an inspection video corresponding to the transmission line; A video processing module, used for cutting the inspection video frame by frame to obtain multiple inspection images, and determining a target image in the multiple inspection images according to a shooting angle; A feature comparison module, used for comparing the transmission line image area in the target image with the transmission line model area in the distribution network model, and outputting feature difference data; A status scoring module is used to evaluate the current status of the transmission line according to the characteristic difference data, obtain a status score of the transmission line, and output corresponding strategy data according to the status score.

9. A readable storage medium having computer instructions stored thereon, characterized in that: When the instruction is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method according to any one of claims 1 to 7 are implemented.

Images