Intelligent power grid line operation safety video monitoring system

Abstract

The invention discloses an intelligent power grid line operation safety video monitoring system, and relates to the technical field of power grid safety monitoring, and the system comprises a video monitoring module which is used for collecting monitoring video data; the target detection module is used for detecting and identifying a line image in the monitoring video data based on a target detection algorithm to generate line monitoring video data which represents the mth-frame line monitoring video data of the u-th line; the meteorological sensor is used for monitoring meteorological information in a power grid line setting range and generating meteorological data which represents the w-th type of meteorological data corresponding to the o-th section of line; according to the intelligent power grid line operation safety video monitoring system, the line shaking characteristic analysis module is arranged to analyze the type of the line abnormity based on the line monitoring video and the corresponding meteorological data when the power grid line has a problem, and decision-making assistance is provided for related personnel to handle the abnormity.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid security monitoring, and in particular to a smart grid line operation safety video monitoring system. Background Art

[0002] Electricity has become an indispensable energy source in contemporary society, and the power grid is the main way to transmit electricity. Therefore, in order to maintain stable power transmission, it is necessary to ensure that the power grid can operate safely and stably. The prior art with publication number CN114611966A discloses a method for quantitative intelligent assessment of the safety of power transmission and transformation operation in a smart grid power system. The method comprises: extracting basic information corresponding to the associated transmission lines; dividing the associated transmission lines into transmission line segments according to preset spacing, and detecting the line state parameters and power parameters corresponding to each transmission line segment; extracting historical meteorological information corresponding to the location of the associated transmission lines; processing and analyzing the line state parameters, power parameters and historical meteorological information corresponding to the associated transmission lines, and conducting a safety assessment of the power transmission and transformation operation of the power system to be monitored; solving the problem of the specificity and generality of the current assessment method, realizing a targeted assessment of the safety of overhead transmission line operation, and ensuring the accuracy, rationality and reference value of the assessment results of the safety of power transmission and transformation operation in the power system.

[0003] However, existing technologies for safety assessment of power grid lines mainly evaluate the transmission performance of the power grid lines themselves to determine whether the power grid is abnormal, ignoring the impact of external conditions on the power grid lines. For example, some power grid lines installed at high altitudes are often affected by strong winds, rain, snow, and low temperatures, which may cause the fixed parts of the power grid lines to loosen or the power grid lines to freeze. The freezing of the power grid lines may cause the shape of the power grid to change, making it more prone to shaking when encountering wind. Increasing the amplitude or frequency of the shaking may cause the fixed parts of the power grid lines to loosen. Summary of the Invention

[0004] The object of the present invention is to provide a smart grid line operation safety video monitoring system to solve at least one of the above-mentioned problems in the prior art.

[0005] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: a smart grid line operation safety video monitoring system, comprising a video monitoring module for collecting monitoring video data;

[0006] The target detection module is used to detect and identify the line image in the monitoring video data based on the target detection algorithm to generate line monitoring video data. , Represents the mth frame of line monitoring video data of the uth line segment;

[0007] Meteorological sensors are used to monitor meteorological information within the range of power grid lines and generate meteorological data , Indicates the wth type of meteorological data corresponding to the oth section of line;

[0008] Line sway feature analysis module, used based on the 、 Based on the normal meteorological sway characteristic data of the line, the line sway is analyzed to see if it is normal, and the line sway positive and abnormal analysis data is generated;

[0009] Line shaking abnormality type analysis module, used for when the line shaking abnormality analysis data is abnormal, based on the 、 Combined with the line shaking abnormality type line and meteorological characteristic data, the line shaking abnormality type analysis is processed to generate line shaking abnormality type analysis data ;

[0010] The abnormality feedback module is used to construct line monitoring abnormality feedback data and perform power grid line safety monitoring feedback operations based on the line monitoring abnormality feedback data.

[0011] Furthermore, the video monitoring module collects monitoring video data, including the following steps:

[0012] S11. Collect surveillance videos of each line segment and generate surveillance video data sets , , Indicates the mth frame of surveillance video data for the uth segment of line, where M is the current maximum number of frames of the corresponding surveillance video data. , The maximum number of power grid segments. Video surveillance modules can be deployed at intervals along the power grid's route, with each module responsible for monitoring a specific segment of the grid. This ensures that the module's monitoring range covers the entire grid. Industrial cameras can be used in these modules to ensure high-definition monitoring under various complex conditions.

[0013] Furthermore, the target detection module generates line monitoring video data, including the following steps:

[0014] S21, based on the target detection algorithm, the monitoring video data Perform target detection analysis to identify the The power grid line images in the image are extracted and a line monitoring video data set is generated. Among them, the target detection algorithm can be pre-trained using a large number of road images with corresponding labels to improve the recognition accuracy.

[0015] Furthermore, the meteorological sensor generates meteorological data, comprising the following steps:

[0016] S31. Collect meteorological data of corresponding locations through meteorological sensors to generate meteorological data sets , , o is an integer , W is the maximum number of categories of meteorological data. Meteorological data can include wind speed, wind direction, temperature, humidity, rainfall, snowfall, air pressure, etc.

[0017] Furthermore, the line sway feature analysis module generates line sway positive and abnormal analysis data, including the following steps:

[0018] S41. Collect line monitoring video data of normal line shaking under various weather conditions to generate a line normal shaking monitoring video data set;

[0019] S42. Based on the DBSCAN algorithm, cluster analysis is performed on the line normal shaking monitoring video data set to generate the line corresponding meteorological normal shaking feature data set. , , the core point coordinate set D and core point label set of the DBSCAN algorithm and field radius , represents the data cluster consisting of the normal meteorological sway characteristic data corresponding to the r-th type line, R represents the maximum number of data clusters consisting of the normal meteorological sway characteristic data corresponding to the line, The rth class label representing the core point coordinates, and correspond;

[0020] S43, based on the double pointer algorithm, and stated Perform character matching search to generate the meteorological data set E corresponding to the line. When performing character matching search, you can search for the same number of u and o. and Generate data pairs ( , ), which means searching for line monitoring video data and meteorological data corresponding to the same line segment; then the data pair ( , ) collect and generate the meteorological data set E corresponding to the route;

[0021] S44. Based on the KD-Tree algorithm, search for the domain radius of E The core point coordinates and corresponding labels within , and count the highest frequency , generate line shaking positive and abnormal analysis data , among which if If it is an empty set, it means the line is shaking abnormally, or in If the value is greater than or equal to 2, it means the line is shaking abnormally; if in If it is 1, the line shaking is normal.

[0022] Furthermore, the line shaking anomaly analysis module generates line shaking anomaly type analysis data, including the following steps:

[0023] S51, collecting meteorological data and line monitoring video data of historical abnormal line shaking, forming a shaking abnormality type data pair; the shaking abnormality type data pair can be expressed as ( , ), where o is equal to u.

[0024] S52: Mark each sway anomaly type data pair with the sway anomaly type to generate a line sway anomaly type and meteorological data set; the sway anomaly type marker may include, for example, loose fixing point, aging conductor, broken conductor, line icing, detached anti-vibration hammer, broken damping wire, or unknown.

[0025] S53: Extract features from the abnormal line shaking type line and meteorological data set to generate a line shaking abnormal type line and meteorological feature data set. , , Represents the kth type of line shaking abnormality type line and meteorological characteristic data, that is, each Corresponding to a shaking abnormality type mark;

[0026] S54, searching the F for line shaking abnormality type line and meteorological characteristic data matching the E , generate line shaking abnormality type analysis data .

[0027] Furthermore, the S54 includes the following steps:

[0028] S541, initializing algorithm parameters, the number of particle populations N for searching line shaking anomaly types, and the maximum number of iterations T;

[0029] S542: Randomly generate N line shaking abnormality type search particles in the F search space, and record the position of each line shaking abnormality type search particle at the current iteration number as , t represents the t-th iteration, i represents the i-th line shaking anomaly type search particle;

[0030] S543, based on standardization The fitness function is constructed by the Euclidean distance between E and , and the fitness function is calculated based on the fitness function. The fitness value of , and the Set to individual optimal position , the minimum fitness value Corresponding Set to the global optimal position ;

[0031] S544. For each line shaking abnormality type search particle i, calculate the Euclidean distance between all other line shaking abnormality type search particles j in the line shaking abnormality type search particle population and the line shaking abnormality type search particle i. When the Euclidean distance is less than the set repulsion radius, the repulsive force between the line shaking abnormality type search particle j and the line shaking abnormality type search particle i is taken into account and updated. The formula is as follows:

[0032] ,

[0033] in, Initially 0, is the repulsive force coefficient, for non The line shaking anomaly type searches for the location of the particle, express and Euclidean distance

[0034] S545, line shaking abnormal type search particle i based on the corresponding individual optimal position , global optimal position and the total repulsive force, update the flight speed, and perform speed boundary processing on the updated flight speed. The flight speed update formula is as follows:

[0035] ,

[0036] Speed ​​boundary processing: judgment Is it less than or equal to the set maximum speed and greater than or equal to the set minimum speed? If so, proceed to the next step; if not, If the speed is greater than the set maximum speed, Reset to set maximum speed, if If the speed is less than the set minimum speed, Reset to set minimum speed;

[0037] in, is the inertia weight, and are the individual learning factor and the global learning factor, and is a random number, ;

[0038] S546: The line shaking abnormality type search particle i moves to a new position based on the updated flight speed, and performs position boundary processing on the updated position. The line shaking abnormality type search particle i's new position update formula is as follows:

[0039] ;

[0040] Position boundary processing: judgment Is it in the search space of line shaking abnormal type line and meteorological characteristic data set F? If so, unchanged, if not, then Reset to the nearest boundary position in the F search space.

[0041] S547. Calculate the fitness value of all line shaking abnormality types search particle i and update the individual optimal position and the global optimal position ;

[0042] S548: Determine whether the maximum number of iterations T or the global optimal position has been reached. Whether to continuously set the unupdated iteration number threshold number of iterations without updating, if so, output the global optimal position Corresponding line shaking abnormality type line and meteorological characteristic data , generate line shaking abnormality type analysis data ; If not, return to S544.

[0043] Furthermore, the abnormality feedback module constructs line monitoring abnormality feedback data and performs power grid line safety monitoring feedback operations, including the following steps:

[0044] S61, monitoring video data of the line and the corresponding labels u and The nearest weather data and line shaking abnormality type analysis data Collect and combine to generate line monitoring abnormal feedback data K=( ,u, , ), where u = o or o is the number with the smallest difference from u, that is, when collecting, select the meteorological data at the point closest to the line segment corresponding to the line monitoring video data; and Corresponding, because Only exists when the line vibration is abnormal, that is, only the abnormal to collect;

[0045] S62, perform power grid line safety monitoring feedback operation according to the K, so that system management personnel can use K to monitor the line monitoring video when the line vibration is abnormal Confirm and obtain the abnormal line segment u and the corresponding line shaking abnormal type analysis data .

[0046] 1. Compared with the existing technology, the smart grid line operation safety video monitoring system provided by the present invention analyzes the sway characteristics of the power grid line under various meteorological conditions by setting up a video monitoring module, a target detection module, a meteorological sensor, and a line sway characteristic analysis module, so as to quickly determine whether there is any abnormality in the power grid line.

[0047] 2. Compared with the existing technology, the smart grid line operation safety video monitoring system provided by the present invention can analyze the type of line anomaly based on line monitoring video and corresponding meteorological data when there is a problem with the grid line by setting a line shaking feature analysis module, providing decision-making assistance for relevant personnel to handle the anomaly.

[0048] 3. Compared with the existing technology, the smart grid line operation safety video monitoring system provided by the present invention can provide feedback to relevant personnel on the type of line anomaly, the corresponding line location and meteorological data by setting up an abnormality feedback module, so that relevant personnel can obtain line anomaly information in a timely manner for verification and determine the location of the line anomaly. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0050] Figure 1 A block diagram of the system structure provided by an embodiment of the present invention;

[0051] Figure 2 A schematic diagram of the system working steps provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0053] Example embodiments will be described more fully hereinafter with reference to the accompanying drawings, but the example embodiments may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the scope of this disclosure to those skilled in the art.

[0054] In the absence of conflict, the various embodiments of the present disclosure and the various features therein may be combined with each other.

[0055] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0056] The terms used herein are used only to describe specific embodiments and are not intended to limit the present disclosure. As used herein, the singular forms "a," "an," and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise. It will also be understood that when the terms "comprising" and / or "made of" are used in this specification, the presence of the features, wholes, steps, operations, elements, and / or components is specified, but the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or groups thereof is not excluded.

[0057] The embodiments described herein may be described with reference to plan views and / or cross-sectional views, with the aid of idealized schematic diagrams of the present disclosure. Thus, the example illustrations may be modified based on manufacturing techniques and / or tolerances. Therefore, the embodiments are not limited to the embodiments shown in the accompanying drawings, but include modifications of the configurations formed based on the manufacturing process. Therefore, the regions illustrated in the accompanying drawings are schematic in nature, and the shapes of the regions shown in the drawings illustrate specific shapes of the regions of the elements, but are not intended to be limiting.

[0058] See also Figure 1-Figure 2 A smart grid line operation safety video monitoring system includes a video monitoring module, a target detection module, a meteorological sensor, a line shaking feature analysis module, a line shaking abnormality type analysis module, and an abnormality feedback module. It works through the following steps:

[0059] S1, the video surveillance module is used to collect surveillance video data, including the following steps:

[0060] S11. Collect surveillance videos of each line segment and generate surveillance video data sets , , Indicates the mth frame of surveillance video data for the uth segment of line, where M is the current maximum number of frames of the corresponding surveillance video data. , The maximum number of power grid segments. Video surveillance modules can be deployed at intervals along the power grid's route, with each module responsible for monitoring a specific segment of the grid. This ensures that the module's monitoring range covers the entire grid. Industrial cameras can be used in these modules to ensure high-definition monitoring under various complex conditions.

[0061] S2, the target detection module is used to detect and identify the line image in the monitoring video data based on the target detection algorithm, and generate line monitoring video data , Representing the mth frame of line monitoring video data of the uth line segment includes the following steps:

[0062] S21, based on the target detection algorithm to monitor the video data Perform target detection analysis to identify The power grid line images in the image are extracted and a line monitoring video data set is generated. Among them, the target detection algorithm can be pre-trained using a large number of line images with corresponding labels to improve the recognition accuracy.

[0063] S3. Meteorological sensors are used to monitor meteorological information within the range of the power grid line and generate meteorological data , Representing the wth type of meteorological data corresponding to the oth section of line includes the following steps:

[0064] S31. Collect meteorological data of corresponding locations through meteorological sensors to generate meteorological data sets , , o is an integer , W is the maximum number of categories of meteorological data. Meteorological data can include wind speed, wind direction, temperature, humidity, rainfall, snowfall, air pressure, etc.

[0065] S4, line shaking feature analysis module is used based on line monitoring video data , meteorological data Based on the normal meteorological sway characteristic data corresponding to the line, whether the line sway is normal is analyzed and processed to generate the line sway positive and abnormal analysis data, including the following steps:

[0066] S41. Collect line monitoring video data of normal line shaking under various weather conditions to generate a line normal shaking monitoring video data set;

[0067] S42. Based on the DBSCAN algorithm, cluster analysis is performed on the line normal shaking monitoring video data set to generate the line corresponding meteorological normal shaking feature data set. , , the core point coordinate set D and core point label set of the DBSCAN algorithm and field radius , represents the data cluster consisting of the normal meteorological sway characteristic data corresponding to the r-th type line, R represents the maximum number of data clusters consisting of the normal meteorological sway characteristic data corresponding to the line, The rth class label representing the core point coordinates, and correspond;

[0068] S43, based on the double pointer algorithm, and Perform character matching search to generate the meteorological data set E corresponding to the line. When performing character matching search, you can search for the same number of u and o. and Generate data pairs ( , ), which means searching for line monitoring video data and meteorological data corresponding to the same line segment; then the data pair ( , ) collect and generate the meteorological data set E corresponding to the route;

[0069] S44. Based on the KD-Tree algorithm, search for the domain radius of E The core point coordinates and corresponding labels within , and count the highest frequency , generate line shaking positive and abnormal analysis data , among which if If it is an empty set, it means the line is shaking abnormally, or in If the value is greater than or equal to 2, it means the line is shaking abnormally; if in If it is 1, the line shaking is normal.

[0070] S5. Line shaking abnormality type analysis module is used to analyze the abnormality type of line shaking based on the line monitoring video data when the abnormality analysis data of the line shaking is abnormal. , meteorological data Combined with the line shaking abnormality type line and meteorological characteristic data, the line shaking abnormality type analysis is processed to generate line shaking abnormality type analysis data , including the following steps:

[0071] S51, collecting meteorological data and line monitoring video data of historical abnormal line shaking, forming a shaking abnormality type data pair; the shaking abnormality type data pair can be expressed as ( , ), where o is equal to u.

[0072] S52: Mark each sway anomaly type data pair with the sway anomaly type to generate a line sway anomaly type and meteorological data set; the sway anomaly type marker may include, for example, loose fixing point, aging conductor, broken conductor, line icing, detached anti-vibration hammer, broken damping wire, or unknown.

[0073] S53, extracting features from the line shaking abnormal type line and meteorological data set to generate the line shaking abnormal type line and meteorological feature data set , , Represents the kth type of line shaking abnormality type line and meteorological characteristic data, that is, each Corresponding to a shaking abnormal type mark;

[0074] S54. Search F for line shaking abnormality type line and meteorological characteristic data matching E. , generate line shaking abnormality type analysis data , specifically including the following steps:

[0075] S541, initializing algorithm parameters, the number of particle populations N for searching line shaking anomaly types, and the maximum number of iterations T;

[0076] S542, randomly generate N line shaking abnormality type search particles in the F search space, and record the position of each line shaking abnormality type search particle at the current iteration number as , t represents the t-th iteration, i represents the i-th line shaking anomaly type search particle;

[0077] S543, based on standardization The Euclidean distance between E and E is used to construct the fitness function, and the fitness function is used to calculate The fitness value of , and Set to individual optimal position , the minimum fitness value Corresponding Set to the global optimal position ;

[0078] S544. For each line shaking abnormality type search particle i, calculate the Euclidean distance between all other line shaking abnormality type search particles j in the line shaking abnormality type search particle population and the line shaking abnormality type search particle i. When the Euclidean distance is less than the set repulsion radius, the repulsive force between the line shaking abnormality type search particle j and the line shaking abnormality type search particle i is taken into account and updated. The formula is as follows:

[0079] ,

[0080] in, Initially 0, is the repulsive force coefficient, for non The line shaking anomaly type searches for the location of the particle, express and Euclidean distance

[0081] S545, line shaking abnormal type search particle i based on the corresponding individual optimal position , global optimal position and the total repulsive force, update the flight speed, and perform speed boundary processing on the updated flight speed. The flight speed update formula is as follows:

[0082] ,

[0083] Speed ​​boundary processing: judgment Is it less than or equal to the set maximum speed and greater than or equal to the set minimum speed? If so, proceed to the next step; if not, If the speed is greater than the set maximum speed, Reset to set maximum speed, if If the speed is less than the set minimum speed, Reset to set minimum speed;

[0084] in, is the inertia weight, and are the individual learning factor and the global learning factor, and is a random number, ;

[0085] S546: The line shaking abnormality type search particle i moves to a new position based on the updated flight speed, and performs position boundary processing on the updated position. The line shaking abnormality type search particle i's new position update formula is as follows:

[0086] ;

[0087] Position boundary processing: judgment Is it in the search space of line shaking abnormal type line and meteorological characteristic data set F? If so, unchanged, if not, then Reset to the nearest boundary position in the F search space.

[0088] S547. Calculate the fitness value of all line shaking abnormality types search particle i and update the individual optimal position and the global optimal position ;

[0089] S548: Determine whether the maximum number of iterations T or the global optimal position has been reached. Whether to continuously set the unupdated iteration number threshold number of iterations without updating, if so, output the global optimal position Corresponding line shaking abnormality type line and meteorological characteristic data , generate line shaking abnormality type analysis data ; If not, return to S544.

[0090] S6. The abnormality feedback module is used to construct line monitoring abnormality feedback data and perform power grid line safety monitoring feedback operations based on the line monitoring abnormality feedback data, including the following steps:

[0091] S61, line monitoring video data and the corresponding labels u and The nearest weather data and line shaking abnormality type analysis data Collect and combine to generate line monitoring abnormal feedback data K=( ,u, , ), where u = o or o is the number with the smallest difference from u, that is, when collecting, select the meteorological data at the point closest to the line segment corresponding to the line monitoring video data; and Corresponding, because Only exists when the line vibration is abnormal, that is, only the abnormal to collect;

[0092] S62, based on K, the power grid line safety monitoring feedback operation is performed, so that the system management personnel can use K to monitor the line when the line vibration is abnormal. Confirm and obtain the abnormal line segment u and the corresponding line shaking abnormal type analysis data .

[0093] The above description is merely illustrative of certain exemplary embodiments of the present invention. It goes without saying that those skilled in the art will be able to modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims.

Claims

1. A smart grid line operation safety video monitoring system, characterized by: It includes a video surveillance module for collecting surveillance video data; The target detection module is used to detect and identify the line image in the monitoring video data based on the target detection algorithm to generate line monitoring video data. , Represents the mth frame of line monitoring video data of the uth line segment; Meteorological sensors are used to monitor meteorological information within the range of power grid lines and generate meteorological data , Indicates the wth type of meteorological data corresponding to the oth section of line; Line sway feature analysis module, used based on the 、 Based on the normal meteorological sway characteristic data of the line, the line sway is analyzed to see if it is normal, and the line sway positive and abnormal analysis data is generated; Line shaking abnormality type analysis module, used for when the line shaking abnormality analysis data is abnormal, based on the 、 Combined with the line shaking abnormality type line and meteorological characteristic data, the line shaking abnormality type analysis is processed to generate line shaking abnormality type analysis data ; The abnormality feedback module is used to construct line monitoring abnormality feedback data and perform power grid line safety monitoring feedback operations based on the line monitoring abnormality feedback data.

2. The smart grid line operation safety video monitoring system according to claim 1, characterized in that: The video monitoring module collects monitoring video data, including the following steps: S11. Collect surveillance videos of each line segment and generate surveillance video data sets , , Indicates the mth frame of surveillance video data for the uth segment of line, where M is the current maximum number of frames of the corresponding surveillance video data. , The maximum number of segments of the power grid line.

3. The smart grid line operation safety video monitoring system according to claim 1, characterized in that: The target detection module generates line monitoring video data, including the following steps: S21, based on the target detection algorithm, the monitoring video data Perform target detection analysis to identify the The power grid line images in the image are extracted and a line monitoring video data set is generated. .

4. The smart grid line operation safety video monitoring system according to claim 1, characterized in that: The meteorological sensor generates meteorological data, comprising the following steps: S31. Collect meteorological data of corresponding locations through meteorological sensors to generate meteorological data sets , , o is an integer , W is the maximum number of categories of meteorological data.

5. The smart grid line operation safety video monitoring system according to claim 1, characterized in that: The line sway feature analysis module generates line sway positive and abnormal analysis data, including the following steps: S41. Collect line monitoring video data of normal line shaking under various weather conditions to generate a line normal shaking monitoring video data set; S42. Based on the DBSCAN algorithm, cluster analysis is performed on the line normal shaking monitoring video data set to generate the line corresponding meteorological normal shaking feature data set. , , the core point coordinate set D and core point label set of the DBSCAN algorithm and field radius , represents the data cluster consisting of the normal meteorological sway characteristic data corresponding to the r-th type line, R represents the maximum number of data clusters consisting of the normal meteorological sway characteristic data corresponding to the line, The rth class label representing the core point coordinates; S43, based on the double pointer algorithm, and stated Perform character matching search to generate the meteorological data set E corresponding to the route; S44. Based on the KD-Tree algorithm, search for the domain radius of E The core point coordinates and corresponding labels within , and count the highest frequency , generate line shaking positive and abnormal analysis data .

6. The smart grid line operation safety video monitoring system according to claim 1, characterized in that: The line shaking anomaly analysis module generates line shaking anomaly type analysis data, including the following steps: S51, collecting meteorological data and line monitoring video data during historical abnormal line shaking to form shaking abnormality type data pairs; S52, marking each sway anomaly type data pair with the sway anomaly type, and generating a line sway anomaly type line and meteorological data set; S53: Extract features from the abnormal line shaking type line and meteorological data set to generate a line shaking abnormal type line and meteorological feature data set. , , Indicates the kth type of line sway anomaly type and meteorological characteristic data; S54, searching the F for line shaking abnormality type line and meteorological characteristic data matching the E , generate line shaking abnormality type analysis data .

7. The smart grid line operation safety video monitoring system according to claim 6, characterized in that: The S54 includes the following steps: S541, initializing algorithm parameters, the number of particle populations N for searching line shaking anomaly types, and the maximum number of iterations T; S542: Randomly generate N line shaking abnormality type search particles in the F search space, and record the position of each line shaking abnormality type search particle at the current iteration number as , t represents the t-th iteration, i represents the i-th line shaking anomaly type search particle; S543, based on standardization The fitness function is constructed by the Euclidean distance between E and , and the fitness function is calculated based on the fitness function. The fitness value of , and the Set to individual optimal position , the minimum fitness value Corresponding Set to the global optimal position ; S544. For each line shaking abnormality type search particle i, calculate the Euclidean distance between all other line shaking abnormality type search particles j in the line shaking abnormality type search particle population and the line shaking abnormality type search particle i. When the Euclidean distance is less than the set repulsion radius, the repulsive force between the line shaking abnormality type search particle j and the line shaking abnormality type search particle i is taken into account and updated. The formula is as follows: ， in, Initially 0, is the repulsive force coefficient, for non The line shaking anomaly type searches for the location of the particle, express and Euclidean distance S545, line shaking abnormal type search particle i based on the corresponding individual optimal position , global optimal position and the total repulsive force, update the flight speed, and perform speed boundary processing on the updated flight speed. The flight speed update formula is as follows: ， in, is the inertia weight, and are the individual learning factor and the global learning factor, and is a random number, ; S546: The line shaking abnormality type search particle i moves to a new position based on the updated flight speed, and performs position boundary processing on the updated position. The line shaking abnormality type search particle i's new position update formula is as follows: ； S547. Calculate the fitness value of all line shaking abnormality types search particle i and update the individual optimal position and the global optimal position ; S548: Determine whether the maximum number of iterations T is reached. If so, output the global optimal position. Corresponding line shaking abnormality type line and meteorological characteristic data , generate line shaking abnormality type analysis data ; If not, return to S544.

8. The smart grid line operation safety video monitoring system according to claim 1, characterized in that: The abnormality feedback module constructs line monitoring abnormality feedback data and performs power grid line safety monitoring feedback operations, including the following steps: S61, monitoring video data of the line and the corresponding labels u and The nearest weather data and line shaking abnormality type analysis data Collect and combine to generate line monitoring abnormal feedback data K=( ,u, , ); S62. Execute power grid line safety monitoring and feedback operations according to K.

Images