Direct power transmission network risk assessment method

Abstract

The invention provides a direct power transmission network risk assessment method, and the method comprises the steps: carrying out the segmentation processing of each monitoring line in a monitoring region according to the line configuration information of a monitoring end, obtaining a plurality of sub-line segments, and obtaining the monitoring data collected by an environment monitoring device corresponding to each sub-line segment; determining the sub-line section meeting the completion condition as a completion line section, calling a completion strategy to obtain completion data of the completion line section, and determining environmental data of the corresponding sub-line section according to the monitoring data or the completion data; performing icing analysis on the environmental data based on the icing prediction model to obtain predicted icing data, and obtaining abnormal prediction data according to the actual icing data and the predicted icing data collected by the inspection terminal; and according to the abnormal prediction data, performing feedback adjustment on standard prediction data of the icing prediction model to obtain a training prediction model.

Description

Technical Field

[0001] The present invention relates to data processing technologies, and in particular to a method for risk assessment of a direct power transmission network. Background Art

[0002] After a transmission line is covered with ice and snow, the impedance of the line will increase, resulting in blocked or interrupted power transmission. In addition, the ice and snow above the transmission line may also cause a short circuit, resulting in an electrical fire or equipment failure. Therefore, the icing monitoring of the transmission line is extremely important.

[0003] In the prior art, when monitoring the icing of a transmission line, the icing condition of the transmission line is usually inspected by manually going to the field. However, since the length of the icing line has a large span, using this method for icing monitoring is very labor-consuming and has low accuracy.

[0004] Therefore, how to improve the efficiency and accuracy of icing monitoring of transmission lines has become an urgent problem to be solved today. Summary of the Invention

[0005] The present invention provides a method for risk assessment of a direct power transmission network, which can improve the efficiency and accuracy of icing monitoring of transmission lines.

[0006] In a first aspect of the present invention, there is provided a method for risk assessment of a direct power transmission network, including:

[0007] According to the line configuration information of the monitoring end, each monitoring line in the monitoring area is segmented to obtain a plurality of sub-line segments, and the monitoring data collected by the environmental monitoring equipment corresponding to each sub-line segment is acquired;

[0008] Determine the sub-line segments that meet the filling conditions as the filling line segments, retrieve the filling strategy to obtain the filling data of the filling line segments, and determine the environmental data of the corresponding sub-line segments according to the monitoring data or the filling data;

[0009] Based on the icing prediction model, icing analysis is performed on the environmental data to obtain predicted icing data, and abnormal prediction data is obtained according to the actual icing data and the predicted icing data collected by the inspection end;

[0010] According to the abnormal prediction data, feedback adjustment is performed on the standard prediction data of the icing prediction model to obtain a trained prediction model.

[0011] Optionally, in a possible implementation manner of the first aspect, determining the sub-line segments that meet the filling conditions as the filling line segments, retrieving the filling strategy to obtain the filling data of the filling line segments, and determining the environmental data of the corresponding sub-line segments according to the monitoring data or the filling data includes:

[0012] When there is a lack of the monitoring data in the sub-line segment, it is determined that the sub-line segment meets the filling condition, and the monitoring data at least includes temperature data, humidity data, and wind speed data;

[0013] Determine the sub-line segment that meets the filling condition as the filling line segment, and retrieve the monitoring map corresponding to the monitoring area;

[0014] Obtain the monitoring line where the filling line segment is located in the monitoring map as the target line, and determine the parallel line preset to be parallel to the target line in the monitoring map;

[0015] Perform screening on the same line segments of the target line to obtain the first reference line segment, and perform screening on the parallel line segments of the parallel line to obtain the second reference line segment;

[0016] Determine the filling data of the filling line segment according to the monitoring data of the first reference line segment and the second reference line segment, and determine the monitoring data or the filling data as the environmental data of the corresponding sub-line segment.

[0017] Optionally, in a possible implementation manner of the first aspect, performing screening on the same line segments of the target line to obtain the first reference line segment, and performing screening on the parallel line segments of the parallel line to obtain the second reference line segment includes:

[0018] Obtain the position points at both ends of the filling line segment as reference points, and determine the position points at a preset reference distance from the corresponding reference points in the target line as the termination points;

[0019] Wherein, the termination points are located in the sub-line segments of the target line other than the filling line segment;

[0020] Determine the sub-line segment included from the corresponding reference point to the termination point as the first reference line segment;

[0021] Connect the two reference points to obtain a range delimiting line, and determine the midpoint of the range delimiting line as the reference point;

[0022] Generate a reference line perpendicular to the range delimiting line and passing through the reference point, and obtain the line segment distance between the midpoint and any one of the reference points;

[0023] Respectively determine the two position points on the reference line at the line segment distance from the reference point as connection points, and connect the connection points and the two reference points to obtain a parallel screening range;

[0024] Determine the sub-line segment of the parallel line located within the parallel screening range as the second reference line segment.

[0025] Optionally, in a possible implementation of the first aspect, after determining that the sub-line segment included from the corresponding reference point to the termination point is the first reference line segment, the method further includes:

[0026] Obtaining the central position point of each of the first reference line segments as the first positioning point, and determining the first reference line segments whose first positioning points are not within the line area corresponding to the reference point to the termination point as the first line segments to be screened;

[0027] Determining the difference distance from the first positioning point of the first line segment to be screened to the termination point, and deleting the first line segments to be screened whose difference distance is greater than the reference difference distance;

[0028] After determining that the sub-line segments within the parallel screening range in the parallel lines are the second reference line segments, the method further includes:

[0029] Obtaining the central position point of each of the second reference line segments as the second positioning point, and determining the second reference line segments whose second positioning points are outside the parallel screening range as the second line segments to be screened;

[0030] Determining the shortest difference distance between the second positioning point of the second line segment to be screened and the parallel screening range, and deleting the second line segments to be screened whose shortest difference distance is greater than the reference difference distance.

[0031] Optionally, in a possible implementation of the first aspect, determining the complement data of the complement line segment according to the monitoring data of the first reference line segment and the second reference line segment includes:

[0032] Obtaining the missing data attribute of the complement line segment as the complement attribute, where the data attribute at least includes temperature attribute, humidity attribute, and wind speed attribute;

[0033] Determining the monitoring data corresponding to the complement attribute of the first reference line segment and the second reference line segment as the reference data;

[0034] Obtaining the central position point of the complement line segment as the target point, and the central position points of the first reference line segment and the second reference line segment as the positioning points;

[0035] According to the point distance between the positioning point and the target point, obtaining the line distances between each of the first reference line segments and the second reference line segments and the complement line segment;

[0036] Based on the ratio of the reference distance to the line distance, obtaining the influence coefficient corresponding to the first reference line segment or the second reference line segment;

[0037] The weighted sum is obtained according to the sum of the products of the respective influence coefficients and the reference data, and the filling data of the filling line segment is determined based on the ratio of the weighted sum to the total sum of the coefficients corresponding to the respective influence coefficients.

[0038] Optionally, in a possible implementation manner of the first aspect, icing analysis is performed on the environmental data based on the icing prediction model to obtain predicted icing data, and abnormal prediction data is obtained according to the actual icing data and the predicted icing data collected by the inspection terminal, including:

[0039] Based on the icing prediction model, the standard icing interval corresponding to each data attribute is obtained, and the monitoring values corresponding to the environmental data with the same data attribute are compared with the standard icing interval, and the standard prediction data includes the standard icing interval;

[0040] The sub-line segments where all the monitoring values are within the standard icing interval are determined as the predicted icing line segments, and the predicted icing line segments in the monitoring map are prominently displayed to obtain the predicted icing data;

[0041] The actual inspection images collected by the inspection terminal for each sub-line segment are obtained, and the actual icing line segments with icing are determined according to the actual inspection images;

[0042] The actual icing data is obtained according to the actual icing line segments. If the sub-line segments corresponding to the actual icing line segments and the predicted icing line segments are different, the corresponding sub-line segments are determined as abnormal line segments, and the abnormal prediction data is obtained according to the abnormal line segments.

[0043] Optionally, in a possible implementation manner of the first aspect, according to the abnormal prediction data, the standard prediction data of the icing prediction model is feedback-adjusted to obtain a training prediction model, including:

[0044] The geographical information corresponding to the central position point of the abnormal line segment is obtained, and the geographical information includes at least the geomorphic features;

[0045] According to the geomorphic features, the standard icing interval corresponding to each data attribute is feedback-adjusted to obtain an adjusted icing interval, and the geomorphic features include at least mountains;

[0046] The data attribute and the geomorphic feature are bound, and the standard icing interval of the data attribute under the geomorphic feature is updated to the adjusted icing interval;

[0047] According to the adjusted icing interval, the icing prediction model is feedback-adjusted to obtain a training prediction model.

[0048] Optionally, in a possible implementation manner of the first aspect, the standard icing intervals corresponding to the respective data attributes are feedback-adjusted according to the landform features to obtain adjusted icing intervals. The landform features at least include mountains, and it includes:

[0049] Determine that the sub-line segment corresponding to the actually iced line segment in the abnormal prediction data is a false negative line segment, and the sub-line segment corresponding to the predicted iced line segment is a false positive line segment;

[0050] Obtain the icing trends corresponding to the respective data attributes of the false negative line segment, and determine that the standard icing interval corresponding to the data attribute with a decreasing icing trend is a downward adjustment interval;

[0051] Determine that the standard icing interval corresponding to the data attribute with an increasing icing trend is an upward adjustment interval; or,

[0052] Obtain the non-icing trends corresponding to the respective data attributes of the false positive line segment, and determine that the standard icing interval corresponding to the data attribute with a decreasing non-icing trend is a downward adjustment interval;

[0053] Determine that the standard icing interval corresponding to the data attribute with an increasing non-icing trend is an upward adjustment interval;

[0054] Obtain the historical monitoring data corresponding to the landform features, and adjust the upward adjustment interval or the downward adjustment interval according to the historical monitoring data to obtain the adjusted icing interval corresponding to the respective data attributes.

[0055] Optionally, in a possible implementation manner of the first aspect, obtaining the historical monitoring data corresponding to the landform features, and adjusting the upward adjustment interval or the downward adjustment interval according to the historical monitoring data to obtain the adjusted icing interval corresponding to the respective data attributes includes:

[0056] When the data attribute corresponds to the upward adjustment interval, obtain the historical non-icing values corresponding to the data attribute under the landform features, and determine the first mean value of the respective historical non-icing values;

[0057] Obtain the first difference between the monitoring value corresponding to the data attribute and the first mean value, and obtain an upward adjustment coefficient according to the ratio of the first difference to the reference difference;

[0058] Obtain the first interval extreme value corresponding to the upward adjustment interval, obtain an upward extreme value based on the sum of the upward adjustment coefficient and the first interval extreme value, and obtain the adjusted icing interval corresponding to the respective data attributes based on the upward extreme value;

[0059] When the data attribute corresponds to the downward adjustment range, obtain the historical ice covering value corresponding to the data attribute under the geomorphic feature, and determine the second average value of each of the historical ice covering values. The historical monitoring data includes historical non-ice covering values and historical ice covering values;

[0060] Obtain the second difference between the monitoring value corresponding to the data attribute and the second average value, and determine the downward adjustment coefficient according to the ratio of the second difference to the reference difference;

[0061] Obtain the second interval extreme value corresponding to the downward adjustment range, obtain the downward adjustment extreme value based on the difference between the downward adjustment coefficient and the second interval extreme value, and obtain the adjusted ice covering range corresponding to the corresponding data attribute based on the downward adjustment extreme value.

[0062] In a second aspect of the present invention, there is provided a direct power grid risk assessment processing system, including:

[0063] A segmentation module, configured to segment each monitoring line in the monitoring area according to the line configuration information of the monitoring end to obtain a plurality of sub-line segments, and obtain the monitoring data collected by the environmental monitoring devices corresponding to each of the sub-line segments;

[0064] An extraction module, configured to determine the sub-line segments that meet the filling conditions as the filling line segments, extract the filling data of the filling line segments by obtaining the filling strategy, and determine the environmental data of the corresponding sub-line segments according to the monitoring data or the filling data;

[0065] An analysis module, configured to perform ice covering analysis on the environmental data based on an ice covering prediction model to obtain predicted ice covering data, and obtain abnormal prediction data according to the actual ice covering data and the predicted ice covering data collected by the inspection end;

[0066] A feedback module, configured to perform feedback adjustment on the standard prediction data of the ice covering prediction model according to the abnormal prediction data to obtain a trained prediction model.

[0067] In a third aspect of the present invention, there is provided a readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, it is used to implement the methods in the first aspect and various possible aspects of the first aspect of the present invention.

[0068] The beneficial effects of the present invention are as follows:

[0069] 1. The present invention can accurately predict whether a transmission line is iced based on the relevant data corresponding to the transmission line, so as to remotely determine the iced line and improve the de-icing efficiency. First, the present invention can divide each monitored line into multiple sub-line segments, making the obtained monitoring data more in line with the actual environment of the corresponding line segment. When predicting the icing of the sub-line segment based on the monitoring data, a more accurate prediction result can be obtained. Moreover, the present invention can also complete the corresponding attribute data of the missing data of the supplemented line segment through a supplementation strategy, and then perform icing analysis, which can improve the accuracy of the icing prediction result, and further improve the efficiency of line de-icing. Finally, the present invention can also continuously train the icing prediction model with data, and obtain a trained prediction model through feedback adjustment, so that the icing result of the line can be predicted more accurately through the trained prediction model.

[0070] 2. The present invention can complete the attribute data of the supplemented line segment with missing data to improve the accuracy of the icing prediction result of the sub-line segment. Among them, the present invention can screen out the first reference line segment and the second reference line segment according to the position information of the supplemented line segment, so as to obtain the corresponding environmental data, and calculate the corresponding environmental data with different weights according to the influence degree of the first reference line segment and the second reference line segment on the supplemented line segment, thereby improving the accuracy of the supplemented data and enhancing the accuracy of the icing prediction result.

[0071] 3. The present invention can adjust the standard icing interval of the corresponding attribute data according to different geographical information, so that the obtained adjusted icing interval can more accurately predict the icing result of the corresponding sub-line segment. At the same time, a trained prediction model corresponding to different geomorphic features can be obtained, so as to facilitate the rapid migration of the trained prediction model, thereby improving the icing prediction efficiency and accelerating the speed of line de-icing operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 is a flowchart of a direct power transmission network risk assessment method provided by the present invention;

[0073] Figure 2 is a schematic diagram of determining the first reference line segment provided by the present invention;

[0074] Figure 3 is a schematic diagram of determining the second reference line segment provided by the present invention;

[0075] Figure 4 is a schematic diagram of the structure of a direct power transmission network risk assessment processing system provided by the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0076] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0077] See Figure 1 , which is a schematic flowchart of a method for risk assessment of a direct power transmission network provided by an embodiment of the present invention. Among them, the method for risk assessment of the power transmission network includes steps S1 to S4, which are specifically as follows:

[0078] S1. According to the line configuration information of the monitoring end, each monitoring line in the monitoring area is segmented to obtain a plurality of sub-line segments, and the monitoring data collected by the environmental monitoring devices corresponding to each sub-line segment is acquired.

[0079] It should be noted that during the process of transmitting electricity, there is not only one transmission line between two places, but multiple lines can transmit electricity together. At the same time, when electricity is transmitted, the distance between the starting point and the ending point of the transmitted electricity may be relatively long. Therefore, on the same line, it is possible that part of the line is covered with ice while part of the line is not. Thus, the transmission line can be divided according to the distance or the route of the line, etc., to obtain a plurality of sub-line segments with shorter distances, so as to facilitate subsequent data analysis of the sub-line segments, thereby determining whether there is ice covering on the sub-line segments, and facilitating the quick determination of the specific location of the line with ice covering, so as to perform de-icing operations on the corresponding line.

[0080] It is not difficult to understand that since line icing is generally related to the environment where the line is located, in order to ensure the normal operation of the line, environmental monitoring devices can be installed to collect environmental data of the line. For example, environmental data such as the temperature, humidity, and wind speed of the line segment can be collected through the environmental monitoring devices, so as to determine whether there is ice covering on the line according to the collected data, and further understand the operation condition of the line.

[0081] Among them, the monitoring end is the information terminal of the personnel for line monitoring, the line configuration information is the line segmentation information correspondingly configured by the monitoring personnel for each line, the monitoring area is the area for icing monitoring, the monitoring line is the line for icing monitoring, the sub-line segment is the line segment obtained after segmenting the monitoring line, the environmental monitoring device is the device for collecting environmental data, and the monitoring data is the data collected by the environmental monitoring device, which can include temperature data, humidity data, and wind speed data. For example, it can be a temperature of 26°, a humidity of 55%, and a wind speed of 5 m / s.

[0082] Through the above embodiments, the present invention can obtain the monitoring data of the line collected in real time by the environmental monitoring device, so as to predict whether the corresponding sub-line segment is covered with ice according to the monitoring data subsequently.

[0083] S2. Determine the sub-line segment that meets the filling condition as the filling line segment, retrieve the filling strategy to obtain the filling data of the filling line segment, and determine the environmental data of the corresponding sub-line segment according to the monitoring data or the filling data.

[0084] It should be noted that in actual applications, there may be missing data in the sub-line segment. For example, the environmental monitoring device of the sub-line segment may be damaged due to the harsh environment, resulting in missing data collected from the corresponding sub-line segment. For example, in order to distinguish each sub-line segment, corresponding numbers can be configured for each sub-line segment. When the sensor for monitoring the temperature corresponding to the 8th sub-line segment is damaged, it can be determined that there is missing data in the 8th sub-line segment. Therefore, in order to improve the accuracy of subsequent icing prediction, the data of the relevant line can be filled according to the filling strategy to make the environmental data of each sub-line segment complete.

[0085] It can be understood that when any data in the monitoring data of the sub-line segment is missing, it can be determined that the sub-line segment meets the filling condition, and the corresponding sub-line segment is used as the filling line segment. For example, when the data of the displayed temperature is missing in the 8th sub-line segment, it is determined that the 8th sub-line segment meets the filling condition, and the 8th sub-line segment is used as the filling line segment.

[0086] Among them, the filling data is the data after supplementing the missing data corresponding to the filling line segment, and the environmental data is the data related to the environment corresponding to each sub-line segment. When there is no missing data in the sub-line segment, its corresponding environmental data is the monitoring data. When there is missing data in the sub-line segment, its corresponding environmental data is the filling data.

[0087] Based on the above embodiments, the specific implementation manner of step S2 (determine the sub-line segment that meets the filling condition as the filling line segment, retrieve the filling strategy to obtain the filling data of the filling line segment, and determine the environmental data of the corresponding sub-line segment according to the monitoring data or the filling data) can be:

[0088] S21. When there is missing monitoring data in the sub-line segment, determine that the sub-line segment meets the filling condition, and the monitoring data at least includes temperature data, humidity data, and wind speed data.

[0089] It can be understood that when any one of the monitoring data corresponding to the sub-line segment is missing, that is, when the monitoring data is incomplete, it can be determined that the corresponding sub-line segment meets the filling condition, that is, meets the condition for data filling, so that the data of the relevant sub-line segment can be filled to make the predicted icing result more accurate.

[0090] S22. Determine the sub-line segment that meets the filling condition as the filling line segment, and retrieve the monitoring map corresponding to the monitoring area.

[0091] It can be understood that the filling line segment is the line segment that meets the filling condition, and the monitoring map is a map that can view the line arrangement. For example, when there are 5 lines in the monitoring area, the monitoring map can show the arrangement of the corresponding 5 lines, so that through the monitoring map, the target line that needs to fill data and its corresponding parallel lines can be determined, so as to facilitate subsequent supplementing the missing monitoring data of the filling line segment through the target line and the parallel lines.

[0092] S23. Obtain the monitoring line where the filling line segment is located in the monitoring map as the target line, and determine the parallel line preset parallel to the target line in the monitoring map.

[0093] It can be understood that the target line is the monitoring line where the filling line segment is located in the monitoring map. For example, when there are 5 lines in the monitoring map and the filling line segment is on the 03rd monitoring line in the monitoring map, the target line can be obtained as the 03rd monitoring line, and the remaining lines parallel to the target line in the monitoring map are parallel lines. For example, the 01st monitoring line, 02nd monitoring line, 04th monitoring line, and 05th monitoring line in the monitoring map are all parallel to the 03rd monitoring line, so they can be used as parallel lines.

[0094] In practical applications, the parallel line can generally be other lines on the same high-voltage tower as the target line, or other lines on adjacent high-voltage towers. These lines are generally close to the target line, and the corresponding environmental data is generally relatively close. Therefore, the missing data of the target line can be filled in the subsequent process through the environmental data corresponding to the parallel line. The parallel line can be pre-configured. After determining the target line, its corresponding parallel line can be directly obtained.

[0095] S24. Screen the same line segments of the target line to obtain the first reference line segment, and screen the parallel line segments of the parallel line to obtain the second reference line segment.

[0096] It can be understood that since the filling line segment is located on the target line, and the environmental data between line segments on the same line may be relatively close, therefore, other sub-line segments on the same target line as the filling line segment can be screened to obtain the monitoring data corresponding to the sub-line segments with relatively close environmental data, so as to provide data reference and improve the accuracy of the subsequent filled data. It can also be understood that there may be multiple sub-line segments on the parallel line, and the distances between different sub-line segments and the filling line segment may be different. In order to screen out the sub-line segments with data closer to the filling line segment, the parallel line can also be screened accordingly.

[0097] Among them, the first reference line segment is the sub-line segment screened out on the same target line as the filling line segment, and the second reference line segment is the second reference line segment obtained by screening the parallel line segments.

[0098] Through the above implementation manner, the present invention can obtain the corresponding first reference line segment and second reference line segment, so that the subsequent obtained corresponding monitoring data is more in line with the monitoring data missing in the filling line segment, making the preset result more accurate.

[0099] Based on the above embodiment, the specific implementation manner of step S24 (screening the same-line segments of the target line to obtain the first reference line segment, and screening the parallel line segments of the parallel line to obtain the second reference line segment) can be:

[0100] S241, obtain the position points at both ends of the filling line segment as reference points, and determine the position points at a preset reference distance from the corresponding reference points on the target line as the termination points.

[0101] Among them, the termination points are located on the sub-line segments of the target line other than the filling line segment.

[0102] It can be understood that the preset reference distance is the distance for determining adjacent line segments, used to determine other line segments on the target line that are relatively close to the filling line segment. It can be set artificially according to the actual situation, and can be 20m.

[0103] It is not difficult to understand that in order to determine other line segments that are relatively close to the filling line segment, the termination points are not within the filling line segment. Specifically, the positions of the termination points can be determined according to the positions of the reference points. For example, as Figure 2 shown, it is a schematic diagram for determining the first reference line segment provided by the present invention. By the reference point 1 on the left side of the filling line segment, it is possible to determine the extension to the left by the preset reference distance, thereby determining the position of the termination point 1 on the left side. By the reference point 2 on the right side of the filling line segment, it is possible to determine the extension to the right by the preset reference distance, thereby determining the position of the termination point 2 on the right side.

[0104] Through the above embodiments, the present invention can obtain the corresponding termination point position, so as to facilitate the subsequent determination of the first reference line segment that meets the data requirements.

[0105] S242. Determine that the sub-line segment from the corresponding reference point to the termination point is the first reference line segment.

[0106] Through the above embodiments, the present invention can determine the first reference section on the target line that is relatively close to the complement line segment, so as to facilitate the subsequent acquisition of the corresponding monitoring data, and further predict the accuracy of the monitoring data missing from the complement line segment.

[0107] Based on the above embodiments, after step S242 (determining that the sub-line segment from the corresponding reference point to the termination point is the first reference line segment), it further includes:

[0108] S2421. Obtain the central position point of each first reference line segment as the first positioning point, and determine the first reference line segment whose first positioning point is not within the line area corresponding to the reference point to the termination point as the first line segment to be screened.

[0109] It can be understood that the first positioning point is the central position point of the first reference line segment, and the first line segment to be screened is the first reference line segment whose first positioning point is not within the line area corresponding to the reference point to the termination point.

[0110] For example: as Figure 2 shown, the central position points of the first reference line segment 1 and the first reference line segment 2 can be obtained respectively as the first positioning point 1 and the first positioning point 2. If the first positioning point 1 and the first positioning point 2 are not within the line area between the reference point and the termination point, the corresponding first reference line segment 1 and the first reference line segment 2 can be used as the first line segments to be screened, that is, the line segments to be screened.

[0111] It is not difficult to understand that when the first positioning point is not within the line area corresponding to the reference point to the termination point, it can be explained that only a small part of the corresponding first reference line segment may be within the line area from the reference point to the termination point, and most of its line segments may be outside the line area corresponding to the reference point to the termination point. And the collected environmental data is corresponding to the entire line segment. In this case, there may be a deviation between the data of the corresponding line segment and the complement line segment. Therefore, the first reference line segment can be screened again to find the line segment with a higher data fitting degree with the complement line segment for subsequent icing prediction, so as to improve the accuracy during icing prediction.

[0112] S2422. Determine the difference distance from the first positioning point of the first line segment to be screened to the end point, and delete the first line segments to be screened whose difference distance is greater than the reference difference distance.

[0113] It can be understood that when the difference distance from the first positioning point of the first line segment to be screened to the end point is relatively close and within the allowable reference difference distance, it can indicate that most of the line areas of the first line segment to be screened are relatively close to the supplementary line segment, and the corresponding environmental data is relatively similar to the environmental data of the supplementary line segment. When the difference distance is greater than the reference difference distance, it can indicate that the distance between most of the line areas in the first line segment to be screened and the supplementary line segment is large, and thus the corresponding environmental data may also deviate. Therefore, in order to ensure the accuracy of the supplementary data, the first line segments to be screened with a large difference distance can be deleted.

[0114] Among them, the difference distance is the distance between the first positioning point and the end point of the first line segment to be screened, and the reference difference distance is the threshold corresponding to the deviation distance between the first positioning point and the end point, which can be set artificially in advance.

[0115] S243. Connect the two reference points to obtain a range delimiting line, and determine the midpoint of the range delimiting line as the reference point.

[0116] It can be understood that the range delimiting line is the connection line between two reference points, and thus the reference point can be obtained. Through the reference point and the range delimiting line, the screening range for screening the second reference line segment can be determined subsequently, so as to determine the specific second reference line segment.

[0117] Among them, the reference point is the midpoint of the range delimiting line. For example, as Figure 3 shown, it is a schematic diagram for determining the second reference line segment provided by the present invention. The position of the reference point can be determined through the positions of the two reference points.

[0118] S244. Generate a reference line perpendicular to the range delimiting line and passing through the reference point, and obtain the line segment distance between the midpoint and any one of the reference points.

[0119] It can be understood that in order to select eligible parallel lines and make the supplementary data corresponding to the supplementary line segment more accurate, the corresponding selection area can be determined through the target line, so as to obtain the corresponding second reference line segment.

[0120] Among them, the reference line is a straight line passing through the reference point and perpendicular to the range delimiting line, and the line segment distance is the distance between the midpoint and any one of the reference points.

[0121] Through the above embodiments, the present invention can obtain the corresponding reference line and the line segment distance, so as to facilitate the subsequent determination of the range for screening the second reference line segment.

[0122] S245. Respectively determine two position points on the reference line at the line segment distance from the reference point as connection points, and connect the connection points and the two reference points to obtain a parallel screening range.

[0123] It can be understood that the connection point is the position point for connecting the reference points to determine the parallel screening range. As Figure 3 shown, connection points are determined at intervals of the line segment distance from the reference point to the upper and lower sides, and then each connection point is respectively connected to the two reference points, and thus the enclosed area is the parallel screening range.

[0124] Through the above embodiments, the present invention can determine the parallel screening range, so as to facilitate the subsequent screening of appropriate second reference line segments, thereby making the prediction result more accurate.

[0125] S246. Determine the sub-line segments in the parallel line that are within the parallel screening range as the second reference line segments.

[0126] Through the above embodiments, the present invention can determine the second reference line segments, so as to facilitate the subsequent acquisition of corresponding environmental data, thereby making the supplementary data for the supplementary line segments more accurate.

[0127] Based on the above embodiments, after step S246 (determining the sub-line segments in the parallel line that are within the parallel screening range as the second reference line segments), it further includes:

[0128] S2461. Obtain the central position points of the second reference line segments as the second positioning points, and determine the second reference line segments whose second positioning points are outside the parallel screening range as the second line segments to be screened.

[0129] It can be understood that there may be multiple second reference line segments within the parallel screening range. However, some second reference line segments may only have a small segment included within the parallel screening range, and the collected environmental data is for the entire line segment. In this case, there may be a deviation between the data of the corresponding sub-line segment and the supplementary line segment. Therefore, the monitoring data of the corresponding sub-line segment may not match the environmental data of the actual supplementary line segment. Therefore, the second reference line segments can be screened again to obtain second reference line segments with more accurate environmental data, so as to improve the accuracy of the subsequent predicted icing results.

[0130] It is not difficult to understand that multiple lines within the parallel screening range in the supplementary line can be viewed in the monitoring map. The division of each line into sub-line segments can be different. For example, some lines may be short in distance but pass through complex terrains, and the corresponding monitoring data will be very different. For instance, when a line is in a mountainous area, the same line may pass through the mountaintop and the foot of the mountain, but the environmental differences such as temperature and humidity between the mountaintop and the foot of the mountain are significant. Therefore, when dividing this line, the distance of each sub-line segment obtained may be short, but there may still be parallel lines with longer distances within the screening range. For example, when the environments of the areas passed by the parallel lines are the same, the monitoring data within the distance of the corresponding sub-line segments may also be the same. Therefore, when dividing this parallel line, the distance of each corresponding sub-line segment may be long. Therefore, in order to more accurately select the environmental data corresponding to the actual supplementary line segment, furthermore, the second reference line segment will be screened again to ensure the accuracy of the subsequent prediction results.

[0131] Among them, the second positioning point is the central position point of the second reference line segment, and the second line segment to be screened is the second reference line segment where the second positioning point is outside the parallel screening range.

[0132] S2462, determine the shortest difference distance between the second positioning point of the second line segment to be screened and the parallel screening range, and delete the second line segment to be screened whose shortest difference distance is greater than the reference difference distance.

[0133] It can be understood that when the shortest difference distance from the second positioning point of the second line segment to be screened to the parallel screening range is greater than the reference difference distance, it can be explained that the corresponding second line segment to be screened is relatively far from the supplementary line segment, and the sub-line segment within the parallel screening range is short. Since the monitoring data is the environmental data of the corresponding longer line segment, the corresponding monitoring data has a large deviation from the environmental data of the supplementary line segment. Therefore, the corresponding second line segment to be screened can be deleted so that when calculating the obtained data subsequently, the error can be reduced to a large extent, thereby improving the accuracy of the supplementary data.

[0134] It is not difficult to understand that the shortest difference distance is the shortest distance from the second positioning point to the parallel screening range.

[0135] S25, determine the supplementary data of the supplementary line segment according to the monitoring data of the first reference line segment and the second reference line segment, and determine that the monitoring data or the supplementary data is the environmental data of the corresponding sub-line segment.

[0136] Through the above embodiments, the present invention can obtain the environmental data of the corresponding sub-line segment, so as to subsequently predict whether the sub-line segment is ice-covered according to the environmental data, thereby improving the ice protection of high-voltage wires and accurately removing ice from the ice-covered line in a timely manner.

[0137] Based on the above embodiments, the specific implementation manner of step S25 (determining the filling data of the filling line segment according to the monitoring data of the first reference line segment and the second reference line segment) may be:

[0138] S251, obtain that the data attribute missing in the filling line segment is the filling attribute, and the data attribute at least includes a temperature attribute, a humidity attribute, and a wind speed attribute.

[0139] It can be understood that the data attribute is the attribute of environmental data. For example, the attribute corresponding to temperature data is the temperature attribute, the attribute corresponding to humidity data is the humidity attribute, and the attribute corresponding to wind speed data is the wind speed attribute.

[0140] It is not difficult to understand that when the data missing in the filling line segment is a temperature value, the temperature attribute corresponding to the temperature data can be used as the filling attribute, so as to subsequently obtain the data of the same attribute corresponding to the first reference line segment and the second reference line segment.

[0141] S252, determine the monitoring data corresponding to the filling attribute of the first reference line segment and the second reference line segment as the reference data.

[0142] It can be understood that the reference data is the monitoring data of the first reference line segment and the second reference line segment that is the same as the filling attribute.

[0143] For example: when the filling attribute is the temperature attribute, the temperature data of the first reference line segment and the second reference line segment can be used as the reference data, so as to subsequently obtain the temperature value corresponding to the temperature value of the filling line segment.

[0144] S253, obtain the center position point of the filling line segment as the target point, and the center position points of the first reference line segment and the second reference line segment as the positioning points.

[0145] It can be understood that the target point is the midpoint position point of the filling line segment, and the positioning points are the center position points of the first reference line segment and the second reference line segment.

[0146] Through the above embodiments, the present invention can determine the target point corresponding to the filling line segment and the positioning points corresponding to the first reference line segment and the second reference line segment, so as to subsequently obtain the point distance, and thus facilitate subsequently determining the proportion weights of the monitoring data corresponding to the first reference line segment and the second reference line segment according to the point distance, making the calculated data more accurate.

[0147] S254. Obtain the line distances between each of the first reference line segments and the second reference line segments and the complement line segment according to the point distances between the positioning points and the target points.

[0148] It can be understood that the point distance is the distance between the positioning point and the target point, and there can be multiple first reference line segments and multiple second reference line segments. Therefore, the line distance is the distance between each first reference line segment and second reference line segment and the complement line segment.

[0149] For example: when the distance between the positioning point and the target point on the first reference line segment is 20m and the distance between the positioning point and the target point on the second reference line segment is 30m, the line distance between the corresponding first reference line segment and the complement line segment is 20m, and the line distance between the second reference line segment and the complement line segment is 30m.

[0150] S255. Obtain the influence coefficient corresponding to the first reference line segment or the second reference line segment based on the ratio of the reference distance and the line distance.

[0151] Obtain the weighted sum according to the sum of the products of each corresponding influence coefficient and the reference data, and determine the complement data of the complement line segment based on the ratio of the weighted sum to the total sum of the coefficients corresponding to each influence coefficient.

[0152] Specifically, the above complement data can be obtained through the following formula:

[0153]

[0154] Among them, B is the complement data, k 1 is the influence coefficient of the first first reference line segment or the second reference line segment, C 1 is the reference data of the first first reference line segment or the second reference line segment, k 2 is the influence coefficient of the second first reference line segment or the second reference line segment, C 2 is the reference data of the second first reference line segment or the second reference line segment, k n is the influence coefficient of the nth first reference line segment or the second reference line segment, C n is the reference data of the nth first reference line segment or the second reference line segment, d 0 is the reference distance, d n is the line distance of the nth first reference line segment or the second reference line segment.

[0155] It can be understood that the reference distance is a pre-set distance threshold, and the influence coefficient is a weight value for calculating the influence degree of the reference data corresponding to different line segments on the supplemented data. Since the influence degrees of the reference data corresponding to the reference line segments at different distances on the supplemented data are different, therefore, weighted averaging can be performed through different influence coefficients corresponding to the reference line segments, so that the calculated supplemented data is more accurate.

[0156] For example, when there are three reference line segments, the line distances from them to the supplemented line segment are 5m, 10m, and 50m respectively, and the terrain of the monitoring area is mountainous. Then, the farther the line distance is, the greater the deviation between the reference data corresponding to the reference line segment and the actual environmental data of the current supplemented line segment. Then, the proportion of the reference degree of this reference data will decrease. Also, it can be obtained from the above formula that the greater the line distance, the smaller the corresponding influence coefficient. Thus, multiplying different influence coefficients by the corresponding reference data and calculating the average can make the obtained supplemented data more accurate.

[0157] S3. Based on the icing prediction model, perform icing analysis on the environmental data to obtain predicted icing data, and obtain abnormal prediction data according to the actual icing data and the predicted icing data collected by the inspection terminal.

[0158] It can be understood that after obtaining the environmental data of each sub-line segment, it is possible to predict whether icing will occur on the corresponding sub-line segment based on the environmental data. For example, when the environmental data of the environment where the line is located reaches the standard icing data conditions, it can be predicted that the corresponding line is already iced. For example, when the standard icing data conditions are that the surface temperature of the line is lower than 0°C, the environmental humidity is higher than 85%, and the wind speed is greater than 1 m / s at the same time. Thus, when the environmental data of the line meets the conditions that the temperature is lower than 0°C, the environmental humidity is higher than 85%, and the wind speed is greater than 1 m / s at the same time, it can be predicted that icing may occur on this line, and the drone can be made to perform de-icing operations in time to ensure the normal operation of the line.

[0159] Among them, the icing prediction model is a model for predicting icing on the line, the predicted icing data is the prediction result of whether the sub-line segment is iced or not, the inspection terminal is the device for performing inspection and detection, which can be a drone, the actual icing data is the result of whether the sub-line segment is actually iced or not. For example, through the actual shooting of the inspection terminal, it is obtained that the sub-line segment is actually frozen, or through the actual shooting of the inspection terminal, it is obtained that the sub-line segment is actually not frozen. The abnormal prediction data is the data where the actual icing data is inconsistent with the predicted icing data, that is, when the predicted result is inconsistent with the actually detected result, it can be explained that the predicted result data is abnormal data.

[0160] Based on the above embodiments, the specific implementation manner of step S3 (performing icing analysis on the environmental data based on the icing prediction model to obtain predicted icing data, and obtaining abnormal prediction data according to the actual icing data and the predicted icing data collected by the inspection terminal) may be as follows:

[0161] S31. Based on the icing prediction model, obtain the standard icing intervals corresponding to each data attribute, and compare the monitored values corresponding to the environmental data with the same data attribute with the standard icing intervals. The standard prediction data includes the standard icing intervals.

[0162] It can be understood that the standard icing interval is the standard data interval in which the line can be iced. For example, for the temperature attribute, the standard icing interval is (0°, -5°), for the humidity attribute, the standard icing interval is (85%, 100%), and for the wind speed attribute, the standard icing interval is (1 m / s, 15 m / s), etc. The monitored value is the value monitored corresponding to the data attribute in the environmental data.

[0163] It is not difficult to understand that by comparing the monitored value with the standard icing interval of the same data attribute, when the monitored value is within the standard icing interval, it can indicate that the line segment has the condition of icing.

[0164] S32. Determine the sub-line segments where all the monitored values are within the standard icing intervals as the predicted icing line segments, and prominently display the predicted icing line segments in the monitoring map to obtain the predicted icing data.

[0165] It can be understood that when the monitored values of all attributes are within the corresponding standard icing intervals, it can be predicted that the corresponding sub-line segments may freeze. Therefore, the corresponding sub-line segments can be used as the predicted icing line segments, and the corresponding predicted icing line segments are prominently displayed in the monitoring map for the inspection of the monitoring personnel, so as to dispatch the unmanned aerial vehicle to perform de-icing operations on the predicted icing line segments.

[0166] Among them, the predicted icing data is the image data of the monitoring map after prominently displaying the predicted icing line segments.

[0167] S33. Obtain the actual inspection images collected by the inspection terminal for each sub-line segment, and determine the actual icing line segments with icing according to the actual inspection images.

[0168] It can be understood that the actual inspection images of each sub-line segment can be collected through the inspection terminal, so that it can be directly seen whether the corresponding sub-line segment is iced under the actual conditions in the actual inspection images. When it is determined that the corresponding sub-line segment is iced in the actual inspection image, the actual icing line segments with icing can be obtained.

[0169] It is not difficult to understand that after determining the actual ice-covered line segment, the drone can be operated for de-icing operations.

[0170] S34. Obtain actual ice-covering data based on the actual ice-covered line segment. If the sub-line segments corresponding to the actual ice-covered line segment and the predicted ice-covered line segment are different, determine the corresponding sub-line segment as an abnormal line segment, and use the abnormal line segment as abnormal prediction data.

[0171] It can be understood that the actual ice-covering data is the information data of the actual ice-covered line segment, the abnormal line segment is the predicted ice-covered line segment where the sub-line segments corresponding to the actual ice-covered line segment and the predicted ice-covered line segment are different, and the abnormal prediction data is the data showing the abnormal line segment.

[0172] Through the above implementation manner, the present invention can obtain corresponding abnormal prediction data, so that after subsequent judgment, the ice-covering prediction model can be feedback-adjusted according to the abnormal prediction data, making the predicted result data more accurate.

[0173] S4. According to the abnormal prediction data, perform feedback adjustment on the standard prediction data of the ice-covering prediction model to obtain a trained prediction model.

[0174] It is not difficult to understand that in order to make the prediction result more accurate, the ice-covering prediction model can be continuously trained with the data actually collected by the drone, improving the accuracy of the prediction result, so that it is possible to more quickly and accurately judge whether the corresponding line is ice-covered and take corresponding measures.

[0175] It can be understood that when abnormal prediction data appears, it can indicate that there is a certain difference between the predicted ice-covering result and the actual ice-covering result. Therefore, it is necessary to perform data training on the ice-covering prediction model to improve the accuracy of the prediction result.

[0176] Among them, the trained prediction model is the model after feedback adjustment of the ice-covering prediction model. By using this model to predict the ice-covering of the line, the prediction result can be made more accurate.

[0177] Based on the above embodiments, the specific implementation manner of step S4 (according to the abnormal prediction data, perform feedback adjustment on the standard prediction data of the ice-covering prediction model to obtain a trained prediction model) can be:

[0178] S41. Obtain the geographical information corresponding to the central position point of the abnormal line segment, and the geographical information at least includes landform features.

[0179] It can be understood that the geographical information is the information of the geographical location where the line is located, including landform features, etc. Among them, the landform feature is the feature of the geography, such as mountains, etc.

[0180] It is not difficult to understand that the icing conditions of different geomorphic features may have certain differences. For example, when the terrain is mountainous, the corresponding temperature, humidity, and wind speed of the line icing may be different from those of the line icing in the plain area. Therefore, the icing prediction model can be adjusted by feedback according to the geographical information.

[0181] S42. Adjust the standard icing interval corresponding to each data attribute according to the geomorphic feature to obtain an adjusted icing interval, where the geomorphic feature at least includes mountains.

[0182] It can be understood that by adjusting the standard icing intervals of each data attribute through different geomorphic features, the accurate adjusted icing intervals corresponding to different geomorphic features can be obtained, so that the icing condition of the line at the corresponding position can be quickly predicted through the geomorphic feature, and the predicted icing result can be made more accurate.

[0183] Among them, the adjusted icing interval is the icing data interval adjusted according to different geomorphic features.

[0184] It is worth mentioning that when the geographical attributes are the same, the trained model can directly be used to predict the line icing in the area with the same geographical information, improving the icing prediction efficiency.

[0185] Based on the above embodiments, the specific implementation manner of step S42 (adjust the standard icing interval corresponding to each data attribute according to the geomorphic feature to obtain an adjusted icing interval, where the geomorphic feature at least includes mountains) can be:

[0186] S421. Determine the sub-line segment corresponding to the actual icing line segment in the abnormal prediction data as a false negative line segment, and the sub-line segment corresponding to the predicted icing line segment as a false positive line segment.

[0187] It can be understood that a false negative line segment is a sub-line segment that was predicted to have no icing in advance but was actually detected to have icing on the line segment, and a false positive line segment is a sub-line segment that was predicted to have icing on the sub-line segment in advance but was actually detected to have no icing on the line segment.

[0188] Through the above implementation manner, the present invention can determine the false negative line segment and the false positive line segment, so as to adjust according to the data corresponding to different types of line segments subsequently.

[0189] S422. Obtain the icing tendency corresponding to each data attribute of the false negative line segment, and determine the standard icing interval corresponding to the data attribute whose icing tendency is a decreasing tendency as the downward adjustment interval.

[0190] It can be understood that for the humidity in the icing condition, the higher the humidity, the easier it is for the line to ice. Therefore, when the sub-line segment is a false negative line segment, that is, the predicted line has no ice, but the line segment is actually detected to be iced, it can be shown that the humidity icing prediction interval corresponding to the determination of icing at this geographical location is relatively high. Therefore, the icing prediction interval corresponding to the predicted humidity attribute can be adjusted downward to make the icing prediction corresponding to this landform more accurate and conform to the actual icing situation.

[0191] Among them, the icing trend is the trend of adjusting the data corresponding to the data attributes in the line. Among them, it includes a downward trend and an upward trend. For example, when the humidity of the environmental data at the geographical location where the line is located is 80%, according to the standard icing interval, the humidity needs to reach more than 85% to predict that the corresponding sub-line segment has no ice. However, when actually detecting with a drone, it is determined that the sub-line segment is already iced. Therefore, the standard icing interval (85%, 100%) corresponding to the humidity can be adjusted downward to include the humidity data value of the actual icing. The downward trend is the trend of decreasing downward, and the downward adjustment interval is the standard icing interval of the data that needs to be adjusted downward.

[0192] It is not difficult to understand that for the wind speed in the icing condition, the greater the wind speed, the easier it is for the line to ice. Therefore, when the sub-line segment is a false negative line segment, that is, the predicted line has no ice, but the line segment is actually detected to be iced, it can be shown that the wind speed icing prediction interval corresponding to the determination of icing at this geographical location is relatively high. Therefore, the icing prediction interval corresponding to the predicted wind speed attribute can be adjusted downward to make the icing prediction corresponding to this landform more accurate and conform to the actual icing situation.

[0193] S423. Determine that the standard icing interval corresponding to the data attribute with an upward icing trend is the upward adjustment interval.

[0194] It can be understood that for the temperature in the icing condition, the lower the temperature, the easier it is for the line to ice. Therefore, when the sub-line segment is a false negative line segment, that is, the predicted line has no ice, but the line segment is actually detected to be iced, it can be shown that the temperature value corresponding to the determination of icing at this geographical location is relatively high. Therefore, the icing prediction interval corresponding to the predicted temperature attribute can be adjusted upward to make the icing prediction corresponding to this landform more accurate and conform to the actual icing situation.

[0195] Among them, the upward trend is the trend of rising upward, and the upward adjustment interval is the standard icing interval of the data attribute that needs to be adjusted upward.

[0196] S424. Obtain the no-icing trend corresponding to each data attribute of the false positive line segment, and determine that the standard icing interval corresponding to the data attribute with a downward no-icing trend is the downward adjustment interval.

[0197] It can be understood that the false positive line segment is the predicted line icing, but the actual line has no icing. Therefore, the trend corresponding to each data attribute in the false positive line segment is the non-icing trend, where the non-icing trend includes a downward trend and an upward trend.

[0198] It is not difficult to understand that for the temperature in the icing condition, the lower the temperature, the easier the line is to ice. Therefore, when the sub-line segment is a false positive line segment, that is, the predicted line is iced, but the actual detection shows that the line segment has no icing, it can be explained that the temperature value corresponding to the determination of icing at this geographical location is relatively high. In order to conform to the actual non-icing situation, the corresponding non-icing trend is a downward trend. Therefore, the icing prediction interval corresponding to the predicted temperature attribute can be adjusted downward to make the icing prediction for this landform more accurate and conform to the actual icing situation. S425. Determine that the standard icing interval corresponding to the data attribute with an upward non-icing trend is the upward adjustment interval.

[0199] It can be understood that when the humidity of the environmental data at the geographical location where the line is located is 85%, according to the standard icing interval, the humidity needs to reach more than 85% to predict that the corresponding sub-line segment is iced. However, when actually detecting with a drone, it is determined that there is no icing on the sub-line segment. Therefore, the standard icing interval (85%, 100%) corresponding to the humidity can be adjusted upward, that is, the data interval for determining the icing of the line at the corresponding geographical location is increased, so that the humidity data value of the actual icing conforms to the corresponding icing situation and makes the predicted icing result more accurate.

[0200] It is worth mentioning that when the humidity is 100%, when the standard icing interval (85%, 100%) is adjusted upward, the maximum value of the corresponding obtained interval can still be 100%. For example, the adjusted interval is (86%, 100%). S426. Obtain the historical monitoring data corresponding to the landform feature, and adjust the upward adjustment interval or the downward adjustment interval according to the historical monitoring data to obtain the adjusted icing interval corresponding to the corresponding data attribute.

[0201] It can be understood that the historical monitoring data is the data monitored for the corresponding landform feature in the historical time period. For example, the environmental data monitored when the sub-line segment in this landform was iced in the past 3 years.

[0202] Through the above implementation manner, the present invention can obtain the adjusted icing interval corresponding to each data attribute, so that when predicting through the adjusted icing interval subsequently, the accuracy of the data of the prediction result can be improved.

[0203] Based on the above embodiments, the specific implementation manner of step S426 (obtaining historical monitoring data corresponding to the geomorphic features, adjusting the upward adjustment range or downward adjustment range according to the historical monitoring data, and obtaining an adjusted ice covering range corresponding to the data attribute) may be as follows:

[0204] S4261, when the data attribute corresponds to the upward adjustment range, obtain the historical non-ice-covered value corresponding to the data attribute under the geomorphic features, and determine the first mean value of each historical non-ice-covered value.

[0205] It can be understood that the historical non-ice-covered value is the data value when there is no ice covering on the sub-line segment within the historical time. For example, when the humidity within the historical time is 85%, 87%, and 86% respectively, and there is no ice covering on the line, the historical non-ice-covered values with humidity of 85%, 87%, and 86% are obtained. The first mean value is the average value of the historical non-ice-covered values. For example, when the historical non-ice-covered values have humidity of 85%, 87%, and 86%, the first mean value can be obtained as (85% + 87% + 86%) / 3 = 86%.

[0206] Through the above implementation manner, the present invention can obtain the corresponding first mean value to facilitate obtaining the corresponding adjustment coefficient.

[0207] S4262, obtain the first difference between the monitored value corresponding to the data attribute and the first mean value, and obtain an upward adjustment coefficient according to the ratio of the first difference to the reference difference.

[0208] It can be understood that the first difference is the difference between the monitored value corresponding to the data attribute in the upward adjustment range and the first mean value, the reference difference is the reference deviation value allowed between the monitored value and the first mean value, and the upward adjustment coefficient is the offset value used to numerically adjust the standard range.

[0209] It is not difficult to understand that in order to improve the accuracy of the ice covering prediction result, when the difference between the monitored value and the first mean value in the case of historical non-ice covering is larger, the corresponding upward adjustment coefficient can also be larger, so that the amplitude of subsequent adjustment of the range can also be correspondingly increased, making the adjusted range closer to the judgment range in the case of non-ice covering in the corresponding area.

[0210] Through the above implementation manner, the present invention can obtain the upward adjustment coefficient of the corresponding attribute data to facilitate subsequent determination of the corresponding adjusted ice covering range.

[0211] S4263, obtain the first interval extreme value corresponding to the upward adjustment range, obtain an upward extreme value based on the sum of the upward adjustment coefficient and the first interval extreme value, and obtain an adjusted ice covering range corresponding to the data attribute based on the upward extreme value.

[0212] It can be understood that the upward adjustment range has corresponding first interval extreme values, corresponding to the interval maximum value and the interval minimum value respectively. Thus, the upward adjustment coefficient can be added to the values in the first interval extreme values to obtain the upward adjustment extreme value, and then the corresponding adjusted ice accretion range can be obtained based on the upward adjustment extreme value.

[0213] Among them, the first interval extreme values are the interval maximum value and the interval minimum value in the upward adjustment range. For example, when the upward adjustment range is (-5°, 0°) corresponding to temperature, the first interval extreme values are -5° and 0°, and the upward adjustment extreme value is the sum of the upward adjustment coefficient and the first interval extreme values.

[0214] S4264, when the data attribute corresponds to the downward adjustment range, obtain the historical ice accretion value corresponding to the data attribute under the geomorphic feature, and determine the second mean value of each historical ice accretion value. The historical monitoring data includes historical non-ice accretion values and historical ice accretion values.

[0215] It can be understood that the second mean value is the average value of the historical ice accretion values corresponding to the data attribute corresponding to the downward adjustment range, and the historical ice accretion value is the data value corresponding to the ice accretion of the sub-line segment within the historical time period.

[0216] S4265, obtain the second difference between the monitored value corresponding to the data attribute and the second mean value, and obtain the downward adjustment coefficient according to the ratio of the second difference to the reference difference.

[0217] It can be understood that the second difference is the difference between the monitored value of the data attribute corresponding to the downward adjustment range and the second mean value, and the downward adjustment coefficient is the offset value used to numerically down-adjust the standard range.

[0218] Through the above implementation manners, the present invention can obtain the downward adjustment coefficient of the downward adjustment range, so as to facilitate data adjustment of the downward adjustment range, thereby obtaining the corresponding adjusted ice accretion range and improving the accuracy of the ice accretion prediction result.

[0219] S4266, obtain the second interval extreme values corresponding to the downward adjustment range, obtain the downward adjustment extreme value based on the difference between the downward adjustment coefficient and the second interval extreme values, and obtain the adjusted ice accretion range corresponding to the corresponding data attribute based on the downward adjustment extreme value.

[0220] It can be understood that the second interval extreme values are the interval maximum value and the interval minimum value corresponding to the downward adjustment range, the downward adjustment extreme value is the difference between the downward adjustment coefficient and the second interval extreme values, and further the numerical range of the adjusted ice accretion range can be determined according to the downward adjustment extreme value.

[0221] Through the above implementation manners, the present invention can obtain the adjusted ice accretion range after adjustment of the downward adjustment range, so as to facilitate improving the accuracy of ice accretion prediction for the sub-line segment subsequently.

[0222] S43. Bind the data attributes and the geomorphic features, and update the standard icing interval of the data attributes under the geomorphic features to the adjusted icing interval.

[0223] It can be understood that binding the data attributes and the geomorphic features facilitates retrieving the corresponding adjusted icing interval according to the geomorphic features for icing prediction subsequently, and thus can improve the accuracy of icing prediction for the sub-line segments of this geomorphic area.

[0224] S44. Perform feedback adjustment on the icing prediction model according to the adjusted icing interval to obtain a trained prediction model.

[0225] It can be understood that by continuously adjusting the icing interval and performing feedback adjustment on the icing prediction model to obtain a trained prediction model, the accuracy of the prediction result can be improved.

[0226] See Figure 4 , which is a schematic structural diagram of a power transmission network risk assessment and processing system provided by an embodiment of the present invention. The power transmission network risk assessment and processing system includes:

[0227] A segmentation module, configured to segment each monitoring line in the monitoring area according to the line configuration information of the monitoring end to obtain a plurality of sub-line segments, and acquire the monitoring data collected by the environmental monitoring devices corresponding to each of the sub-line segments.

[0228] An extraction module, configured to determine the sub-line segments that meet the filling conditions as the filling line segments, extract the filling strategies to obtain the filling data of the filling line segments, and determine the environmental data of the corresponding sub-line segments according to the monitoring data or the filling data.

[0229] An analysis module, configured to perform icing analysis on the environmental data based on the icing prediction model to obtain predicted icing data, and obtain abnormal prediction data according to the actual icing data and the predicted icing data collected by the inspection end.

[0230] A feedback module, configured to perform feedback adjustment on the standard prediction data of the icing prediction model according to the abnormal prediction data to obtain a trained prediction model.

[0231] The present invention also provides a readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, it is used to implement the methods provided by the above various embodiments.

[0232] Among them, the readable storage medium can be a computer storage medium or a communication medium. The communication medium includes any medium that facilitates the transmission of a computer program from one place to another. The computer storage medium can be any available medium accessible by a general or special purpose computer. For example, the readable storage medium is coupled to the processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an Application Specific Integrated Circuits (ASIC). In addition, the ASIC can be located in the user equipment. Of course, the processor and the readable storage medium can also exist as discrete components in the communication device. The readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0233] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A direct transmission network risk assessment method, characterized in that: include: According to the line configuration information of the monitoring terminal, each monitoring line in the monitoring area is segmented to obtain multiple sub-line segments, and the monitoring data collected by the environmental monitoring equipment corresponding to each sub-line segment is obtained; Determine a sub-line segment that meets the filling condition as a filling line segment, call the filling strategy to obtain the filling data of the filling line segment, and determine the environmental data corresponding to the sub-line segment according to the monitoring data or the filling data; Performing icing analysis on the environmental data based on an icing prediction model to obtain predicted icing data, and obtaining abnormal prediction data based on actual icing data and predicted icing data collected by the inspection end; According to the abnormal prediction data, feedback adjustment is performed on the standard prediction data of the icing prediction model to obtain a training prediction model.

2. The method according to claim 1, characterized in that: Determine a sub-line segment that meets the filling condition as a filling line segment, call a filling strategy to obtain filling data of the filling line segment, and determine the environmental data of the corresponding sub-line segment according to the monitoring data or the filling data, including: When the monitoring data is missing in the sub-line segment, it is determined that the sub-line segment meets the completion condition, and the monitoring data includes at least temperature data, humidity data and wind speed data; Determine the sub-line segment that meets the completion condition as the completion line segment, and retrieve the monitoring map corresponding to the monitoring area; Acquire the monitoring line where the completed line segment in the monitoring map is located as the target line, and determine a parallel line in the monitoring map that is preset parallel to the target line; Screening the target line for the same line segment to obtain a first reference line segment, and screening the parallel line for the parallel line segment to obtain a second reference line segment; The complementary data of the complementary line segment is determined according to the monitoring data of the first reference line segment and the second reference line segment, and the monitoring data or the complementary data is determined to be the environmental data of the corresponding sub-line segment.

3. The method according to claim 2, characterized in that Screening the target line for the same line segment to obtain a first reference line segment, and screening the parallel line for the parallel line segment to obtain a second reference line segment, including: Acquire the position points at both ends of the padded route segment as reference points, and determine the position points in the target route that are at a preset reference distance from the corresponding reference points as the end points; The termination point is located at a sub-route segment of the target route except the completed route segment; Determine a sub-line segment from the reference point to the termination point as a first reference line segment; Connecting the two reference points to obtain a range delimiting line, and determining the midpoint of the range delimiting line as a reference point; Generate a reference line perpendicular to the range demarcation line and passing through the reference point, and obtain a line segment distance between the midpoint and any one of the reference points; Respectively determine two position points on the reference line at a line segment distance from the reference point as connection points, connect the connection points and the two reference points to obtain a parallel screening range; A sub-line segment in the parallel line that is within the parallel screening range is determined as a second reference line segment.

4. The method according to claim 3, characterized in that After determining that the sub-line segment from the reference point to the termination point is the first reference line segment, the method further includes: Acquire the center position point of each of the first reference route segments as a first positioning point, and determine that the first reference route segment in which the first positioning point is not within the route area corresponding to the reference point to the end point is a first route segment to be screened; Determine the difference distance between the first positioning point and the end point of the first line segment to be screened, and delete the first line segment to be screened whose difference distance is greater than the reference difference distance; After determining that the sub-line segment in the parallel line that is within the parallel screening range is the second reference line segment, the method further includes: Acquire the center position point of each second reference line segment as the second positioning point, and determine that the second reference line segment where the second positioning point is outside the parallel screening range is the second line segment to be screened; Determine the shortest phase difference between the second positioning point of the second line segment to be screened and the parallel screening range, and delete the second line segment to be screened whose shortest phase difference is greater than the reference phase difference.

5. The method according to claim 2, characterized in that: Determining the complementary data of the complementary line segment according to the monitoring data of the first reference line segment and the second reference line segment includes: Acquiring missing data attributes of the completed route segment as the completed attributes, wherein the data attributes at least include a temperature attribute, a humidity attribute, and a wind speed attribute; Determine monitoring data corresponding to the first reference line segment and the second reference line segment and the complementing attribute as reference data; Acquire the center position point of the completed route segment as the target point, and the center position points of the first reference route segment and the second reference route segment as the positioning point; According to the point distance between the positioning point and the target point, obtaining the route distance between each of the first reference route segment and the second reference route segment and the completed route segment; Obtaining an influence coefficient corresponding to the first reference line segment or the second reference line segment based on a ratio of a reference distance to the line distance; A weighted sum is obtained according to the sum of the products of each corresponding influence coefficient and the reference data, and the padding data of the padding line segment is determined based on the ratio of the weighted sum to the sum of coefficients corresponding to each influence coefficient.

6. The method according to claim 5, characterized in that Based on the icing prediction model, the environmental data is subjected to icing analysis to obtain predicted icing data, and abnormal prediction data is obtained according to the actual icing data and predicted icing data collected by the inspection end, including: Based on the icing prediction model, a standard icing interval corresponding to each of the data attributes is obtained, and a monitoring value corresponding to the environmental data with the same data attribute is compared with the standard icing interval, wherein the standard prediction data includes the standard icing interval; Determine that the sub-line segment where each of the monitoring values ​​is within the standard icing range is a predicted icing line segment, and highlight the predicted icing line segment in the monitoring map to obtain predicted icing data; Acquire actual inspection images collected by the inspection end on each of the sub-line segments, and determine actual ice-covered line segments where ice is present according to the actual inspection images; Actual ice-covered data is obtained according to the actual ice-covered route segment. If the actual ice-covered route segment and the sub-route segment corresponding to the predicted ice-covered route segment are different, the corresponding sub-route segment is determined to be an abnormal route segment, and abnormal prediction data is obtained according to the abnormal route segment.

7. The method according to claim 8, characterized in that According to the abnormal prediction data, feedback adjustment is performed on the standard prediction data of the icing prediction model to obtain a training prediction model, including: Acquire geographic information corresponding to the center point of the abnormal line segment, wherein the geographic information at least includes geomorphic features; Feedback adjustment is performed on the standard ice-covered interval corresponding to each of the data attributes according to the landform features to obtain an adjusted ice-covered interval, wherein the landform features at least include mountains; Binding the data attribute and the landform feature, and updating the standard ice coverage interval of the data attribute under the landform feature to the adjusted ice coverage interval; Feedback adjustment is performed on the icing prediction model according to the adjusted icing interval to obtain a training prediction model.

8. The method according to claim 7, characterized in that Feedback adjustment is performed on the standard ice-covered interval corresponding to each of the data attributes according to the landform features to obtain an adjusted ice-covered interval, wherein the landform features at least include mountains, including: Determining that the sub-line segment corresponding to the actual ice-covered line segment in the abnormal prediction data is a false negative line segment, and the sub-line segment corresponding to the predicted ice-covered line segment is a false positive line segment; Acquire the icing trend corresponding to each of the data attributes of the false negative line segment, and determine that the standard icing interval corresponding to the data attribute in which the icing trend is a downward trend is a downward adjustment interval; Determine that the standard ice coverage interval corresponding to the data attribute indicating that the ice coverage trend is an upward trend is an upward adjustment interval; or, Obtaining the non-icing trend corresponding to each of the data attributes of the false positive line segment, and determining that the standard icing interval corresponding to the data attribute in which the non-icing trend is a decreasing trend is a downward adjustment interval; Determine that the standard ice coverage interval corresponding to the data attribute that the non-ice coverage trend is an upward trend is an upward adjustment interval; The historical monitoring data corresponding to the geomorphic features is obtained, and the upward adjustment interval or the downward adjustment interval is adjusted according to the historical monitoring data to obtain the adjusted ice coverage interval corresponding to the corresponding data attribute.

9. The method according to claim 8, characterized in that Acquiring historical monitoring data corresponding to the geomorphic feature, adjusting the upward adjustment interval or the downward adjustment interval according to the historical monitoring data, and obtaining an adjusted ice coverage interval corresponding to the corresponding data attribute, including: When the data attribute corresponds to the upward adjustment interval, obtaining the historical ice-free value corresponding to the data attribute under the geomorphic feature, and determining a first mean value of each of the historical ice-free values; Obtaining a first difference between a monitoring value corresponding to the data attribute and the first mean value, and obtaining an upward adjustment coefficient according to a ratio of the first difference to a benchmark difference; Acquire a first interval extreme value corresponding to the upward adjustment interval, obtain an upward adjustment extreme value based on the sum of the upward adjustment coefficient and the first interval extreme value, and obtain an adjusted ice coverage interval corresponding to the corresponding data attribute based on the upward adjustment extreme value; When the data attribute corresponds to the downward adjustment interval, obtaining the historical ice cover value corresponding to the data attribute under the geomorphic feature, and determining the second mean value of each of the historical ice cover values, wherein the historical monitoring data includes the historical no-ice value and the historical ice cover value; Obtaining a second difference between the monitoring value corresponding to the data attribute and the second mean value, and obtaining a downward adjustment coefficient according to a ratio of the second difference to the benchmark difference; A second interval extreme value corresponding to the downward adjustment interval is obtained, a downward adjustment extreme value is obtained based on a difference between the downward adjustment coefficient and the second interval extreme value, and an adjusted icing interval corresponding to the corresponding data attribute is obtained based on the downward adjustment extreme value.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, it is used to implement any one of the methods of claims 1 to 9.

Images