A data management system based on UAV surveying and mapping

Abstract

The present invention discloses a data management system based on unmanned aerial vehicle mapping, which relates to the technical field of unmanned aerial vehicle mapping data management. By determining the intensity and range of electromagnetic radiation and classifying the levels thereof, the operating status of the unmanned aerial vehicle in different environments is comprehensively evaluated in combination with the real-time operating data and flight test results of the unmanned aerial vehicle, and then the abnormal state, possible abnormal state and normal state of the unmanned aerial vehicle operation are classified; in the possible abnormal state, the unmanned aerial vehicle mapping data is intelligently managed through a prediction management module, the abnormal perception and processing efficiency is improved, the data quality and the reliability of subsequent analysis applications are further guaranteed, thereby optimizing the task execution results and improving the safety of equipment and personnel.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle surveying and mapping data management, and in particular to a data management system based on unmanned aerial vehicle surveying and mapping. Background Art

[0002] Data management based on drone mapping refers to the systematic and efficient management and application of various types of mapping data obtained by drones. First, it includes standardized processing of data collected by drones, including data cleaning, correction and format conversion, etc., to ensure the accuracy and consistency of the data. Secondly, data management based on drone mapping covers data storage, backup and sharing. It is necessary to establish a stable and reliable data storage system and design a reasonable data backup strategy to ensure the security and sustainability of the data.

[0003] In addition, data management based on drone mapping also includes data analysis and mining to discover valuable information hidden in the data, which can provide scientific basis and decision-making support for urban planning, disaster monitoring, resource management, etc. Therefore, data management based on drone mapping is not only the collection and organization of data, but also the in-depth use of data to provide accurate and efficient spatial information services for various industries.

[0004] The shortcomings of the prior art:

[0005] In the prior art, data management based on drone mapping includes data analysis and mining to discover valuable information hidden in the data. However, when a drone is in an operating environment near a high-voltage transmission line, the operating state of the drone may be subject to strong electromagnetic interference, affecting the normal operation of the drone's flight control system and sensor equipment. This may cause unstable drone flight, distorted data collection or interrupted transmission, making it difficult to obtain accurate mapping data. At the same time, if the mapping data is inaccurate, it may affect the accuracy and reliability of the navigation and positioning system, causing errors in drones or other aircraft when flying in the air, increasing the risk of flight accidents. Summary of the invention

[0006] The purpose of the present invention is to provide a data management system based on drone mapping to solve the shortcomings of the background technology.

[0007] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: a data management system based on drone mapping, comprising an electromagnetic monitoring module, a work area determination module, a judgment and evaluation module, a comprehensive analysis module, an abnormality classification module and a prediction management module;

[0008] Electromagnetic monitoring module: Determine the location and working condition of the high-voltage transmission line according to the UAV's operating area, monitor and analyze the electromagnetic field data in the area, and determine the intensity and range of electromagnetic radiation;

[0009] Working area determination module: divides the intensity of electromagnetic radiation into levels, obtains the real-time operation data of drones in different levels, compares and analyzes the real-time operation data of drones with the standard operation data of drones under normal working conditions, determines the level range of stable operation of drones, and marks the areas within this range as feasible working areas of drones;

[0010] Judgment and evaluation module: Conduct flight tests within the feasible working area of ​​the drone, record the flight status of the drone at different positions and altitudes, analyze the flight status of the drone under different electromagnetic interferences, and evaluate the interference degree of the drone's flight status; analyze the changes in the working status of the drone's sensor equipment, and evaluate the performance stability of the drone's sensor equipment;

[0011] Comprehensive analysis module: Comprehensively analyze the interference degree of the UAV's flight status and the performance stability of the UAV's sensor equipment to evaluate whether the UAV's operating status in the feasible working area is abnormal;

[0012] Abnormal classification module: According to the evaluation result of whether the UAV's operating status in the feasible working area is abnormal, the UAV's working status is divided into abnormal status, possible abnormal status, and normal status;

[0013] Prediction management module: When the operating status of the UAV in the feasible working area is possibly abnormal, the accuracy of the UAV mapping data is further analyzed and predicted, and the UAV mapping data is managed according to the prediction results.

[0014] In a preferred embodiment, in the working area determination module, the real-time operation data of the UAV is compared and analyzed with the standard operation data under normal working conditions using the K nearest neighbor algorithm, and the level range of stable operation of the UAV is determined, specifically including:

[0015] Preprocess the real-time operation data and the standard operation data, select features from the preprocessed data, and use the K nearest neighbor algorithm to calculate the distance between each real-time operation data and all samples in the standard operation data;

[0016] The features of the preprocessed real-time operation data of the UAV are represented as vectors. The feature vectors corresponding to the real-time operation data of the UAV and the standard operation data under normal working conditions are regarded as a set of data for comparison. The similarity is calculated by Minkowski distance. The specific calculation expression is: ;in, Indicates the similarity between the real-time operation data of the drone and the standard operation data under normal working conditions. is the feature vector of the real-time operation data of the UAV, is the characteristic vector of the standard operating data under the corresponding normal working condition, p is the distance measurement parameter, and p is a positive integer greater than 0, and a is the number of data groups.

[0017] In a preferred embodiment, a K value is selected, and for each real-time operation data, the level range of stable operation is determined according to the data proportion of normal samples in its K nearest neighbors; when the data proportion of normal samples in the K nearest neighbors of the real-time operation data is greater than or equal to the proportion threshold, it is marked as the level range of stable operation of the UAV, and the area within the stable operation level range is marked as the feasible working area of ​​the UAV; when the data proportion of normal samples in the K nearest neighbors of the real-time operation data is less than the proportion threshold, it is marked as the level range of unstable operation of the UAV.

[0018] In a preferred embodiment, in the judgment and evaluation module, the flight state of the UAV under different electromagnetic interferences is analyzed, and the surveying and mapping electromagnetic interference index of the UAV is obtained according to the flight state data of the UAV, and the interference degree of the UAV flight state is evaluated. The method for obtaining the surveying and mapping electromagnetic interference index is:

[0019] Collect the UAV’s flight status data M and mapping data N, and pre-process the data;

[0020] For each given combination of M and N, count its frequency of occurrence and divide it by the total number of samples to calculate the joint probability distribution and mark it as , the specific calculation expression is: ; In the formula, is the total number of samples, represents the number of times the combination m and n appears in the sample;

[0021] Count the frequency of each value of M and N respectively, and divide it by the total number of samples to calculate the marginal probability distribution and , the specific calculation expressions are expressed as follows: , ; In the formula, and Respectively represent the number of times the individual values ​​m and n in the flight status data M and mapping data N appear in the sample, is the marginal probability distribution of the flight status data M, is the marginal probability distribution of surveying and mapping data N;

[0022] According to the calculated marginal probability distribution and And the joint probability distribution , calculate the interference value between the flight status data M and the surveying and mapping data N, that is, calculate the surveying and mapping electromagnetic interference index. The specific calculation expression is: ; In the formula, In a preferred embodiment, in the judgment and evaluation module, the changes in the working state of the sensor equipment of the drone are analyzed, and the fault frequency fluctuation value is obtained according to the frequency of failure of the sensor equipment during long-term operation to evaluate the performance stability of the drone sensor equipment. The method for obtaining the fault frequency fluctuation value is:

[0023] Acquire the fault data of the sensor device within the time period t, and arrange the acquired fault data in chronological order to form a time series, wherein each data point in the time series represents a sensor device fault event, including the specific time when the fault occurred;

[0024] Statistics are performed on the time series data to calculate the actual failure frequency in each time period. The specific calculation expression is: ; In the formula, is the actual fault frequency, The number of failures in each time period, is the total number of observations in each time period; the moving average method is used to calculate the mean of the failure frequency in the moving window to smooth the data. For each data point in the time series , calculate its mean within the window, the mean within the window The calculation expression is: ; In the formula, is the starting index of the current window, is the index within the window, is the number of windows, and the smoothed fault frequency is the set of means in all windows, that is: ,in, is the smoothed fault frequency, n is the number of samples;

[0025] By performing fluctuation analysis on the smoothed fault frequency time series, the fault frequency fluctuation value is calculated. The specific calculation expression is: ; In the formula, is the fault frequency fluctuation value, is the mean fault frequency.

[0026] In a preferred embodiment, in the comprehensive analysis module, the interference degree of the UAV flight state and the performance stability of the UAV sensor equipment are comprehensively analyzed, specifically:

[0027] The surveying and mapping electromagnetic interference index and fault frequency fluctuation value are normalized, and the abnormal coefficient of the operating status of the UAV in the feasible working area is calculated based on the normalized surveying and mapping electromagnetic interference index and fault frequency fluctuation value.

[0028] In a preferred embodiment, the acquired abnormal coefficient of the operating state of the UAV in the feasible working area is compared with the gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the abnormal coefficient of the operating state of the UAV in the feasible working area is compared with the first standard threshold and the second standard threshold respectively;

[0029] If the abnormal coefficient of the operating status of the drone in the feasible working area is greater than the second standard threshold, the operating status of the drone is classified as an abnormal state; if the abnormal coefficient of the operating status of the drone in the feasible working area is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the operating status of the drone is classified as a possible abnormal state; if the abnormal coefficient of the operating status of the drone in the feasible working area is less than the first standard threshold, the operating status of the drone is classified as a normal state.

[0030] In a preferred embodiment, when the working state of the UAV is a possible abnormal state, that is, the abnormality coefficient generated within a fixed time period is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, and the abnormality coefficients generated in subsequent fixed time periods are used to establish a data set, and the accuracy loss index of the UAV mapping data within the fixed time period is calculated.

[0031] In a preferred embodiment, by The mean and average of the anomaly coefficients within the time period Anomaly coefficient mean prediction within a time period The mean value of the abnormal coefficient within the time period, the specific calculation expression is: ; In the formula, For prediction The mean of the anomaly coefficients within the time period, for The mean of the anomaly coefficients within the time period, for The mean of the anomaly coefficients within the time period, is the smoothing coefficient, and The value range is , fixed time , c is a positive integer greater than 0;

[0032] The predictions obtained The average value of the abnormal coefficient within the time period is different from the preset The mean value of the standard anomaly coefficient within the time period is analyzed to calculate the accuracy loss index of the UAV mapping data within a fixed time period. The specific calculation expression is: ; In the formula, is the accuracy loss index, for The mean of the standardized anomaly coefficients over the time period.

[0033] In a preferred embodiment, the accuracy loss index of the UAV mapping data acquired within a fixed time period is compared with the accuracy loss index reference threshold. If the accuracy loss index of the UAV mapping data within the fixed time period is greater than or equal to the accuracy loss index reference threshold, a warning signal is generated; if the accuracy loss index of the UAV mapping data within the fixed time period is less than the accuracy loss index reference threshold, no warning signal is generated and no adjustment is required.

[0034] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0035] 1. The present invention comprehensively evaluates the operating status of drones in different environments by comprehensively using electromagnetic radiation analysis, flight testing, sensor equipment status evaluation and other means, and then divides them into abnormal, possible abnormal and normal states. For possible abnormal states, the drone mapping data is further analyzed and predicted through intelligent management strategies, which improves the perception and processing efficiency of abnormal situations, thereby optimizing the efficiency and safety of task execution. It not only helps to improve data quality and the reliability of subsequent data applications, but also effectively reduces the risk of flight accidents, providing a comprehensive and reliable solution for drone mapping data management.

[0036] 2. The present invention helps to ensure the safety of UAV equipment and personnel and optimize the results of task execution by timely discovering and handling possible abnormal situations. The intelligent management strategy improves the perception and processing efficiency of abnormal situations in UAV mapping data, further improves the quality and accuracy of the data, and ensures the effectiveness and reliability of subsequent data analysis and application. This comprehensive management solution not only improves the efficiency of task execution, but also helps to optimize resource utilization and cost control, providing a reliable and efficient solution for UAV mapping data management. It not only improves the perception and processing efficiency of UAV mapping data anomalies. It also improves the quality and accuracy of the data, ensuring the effectiveness and reliability of subsequent data analysis and application. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0038] Figure 1 The present invention is a flow chart of the method.

[0039] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] Example 1: Please refer to Figure 1 , 2 As shown, the data management system based on drone mapping described in this embodiment includes an electromagnetic monitoring module, a work area determination module, a judgment and evaluation module, a comprehensive analysis module, an abnormality classification module and a prediction management module;

[0042] Electromagnetic monitoring module: Determine the location and working condition of the high-voltage transmission line according to the UAV's operating area, monitor and analyze the electromagnetic field data in the area, and determine the intensity and range of electromagnetic radiation;

[0043] Working area determination module: divides the intensity of electromagnetic radiation into levels, obtains the real-time operation data of drones in different levels, compares and analyzes the real-time operation data of drones with the standard operation data of drones under normal working conditions, determines the level range of stable operation of drones, and marks the areas within this range as feasible working areas of drones;

[0044] Judgment and evaluation module: Conduct flight tests within the feasible working area of ​​the drone, record the flight status of the drone at different positions and altitudes, analyze the flight status of the drone under different electromagnetic interferences, and evaluate the interference degree of the drone's flight status; analyze the changes in the working status of the drone's sensor equipment, and evaluate the performance stability of the drone's sensor equipment;

[0045] Comprehensive analysis module: Comprehensively analyze the interference degree of the UAV's flight status and the performance stability of the UAV's sensor equipment to evaluate whether the UAV's operating status in the feasible working area is abnormal;

[0046] Abnormal classification module: According to the evaluation result of whether the UAV's operating status in the feasible working area is abnormal, the UAV's working status is divided into abnormal status, possible abnormal status, and normal status;

[0047] Prediction management module: When the operating status of the UAV in the feasible working area is possibly abnormal, the accuracy of the UAV mapping data is further analyzed and predicted, and the UAV mapping data is managed according to the prediction results.

[0048] Among them, in the electromagnetic monitoring module, the location and working conditions of the high-voltage transmission line are determined according to the operating area of ​​the drone, and the electromagnetic field data in the area is monitored and analyzed to determine the intensity and range of the electromagnetic radiation.

[0049] Before the drone takes off, plan and prepare the operation area. This includes determining the scope and boundaries of the survey and understanding the layout and distribution of power transmission lines. Use route planning software or systems to plan the flight route of the drone based on information such as the terrain of the operation area and the location of the transmission lines. Ensure that the route can cover all areas that need to be surveyed and take into account the safety distance to avoid contact with high-voltage transmission lines. Configure the electromagnetic field sensor on the drone, and calibrate and debug it to ensure that the sensor can accurately measure and record electromagnetic field data. Calibration includes calibrating the sensitivity of the sensor, correcting the position and orientation of the sensor, etc.

[0050] Carry out the UAV flight mission and fly according to the pre-planned route. During the flight, the electromagnetic field sensor carried by the UAV will continuously monitor and record the electromagnetic field data in the area. The electromagnetic field data in the area is collected in real time through the sensors carried by the UAV. These data may include parameters such as electric field strength, magnetic field strength, frequency, and the corresponding spatial distribution. The collected electromagnetic field data is recorded and stored, usually through the data recording device on the UAV or wirelessly transmitted to the ground station for storage. Ensure the integrity and security of the data. Use professional data analysis software or algorithms to process and analyze the collected electromagnetic field data. This may include steps such as data cleaning, denoising, interpolation and spatial analysis to obtain more accurate information on the electromagnetic field strength and range. Finally, the analyzed and processed electromagnetic field data is presented, usually in the form of a map, chart or report. The report includes a distribution map of the electromagnetic field strength, a contour map, etc., as well as the corresponding analysis conclusions and suggestions.

[0051] Working area determination module: divide the intensity of electromagnetic radiation into levels, obtain the real-time operation data of drones in different levels, compare and analyze the real-time operation data of drones with the standard operation data of drones under normal working conditions, determine the level range of stable operation of drones, and mark the areas within this range as feasible working areas of drones.

[0052] Use appropriate electromagnetic field sensors to collect electromagnetic field data in the work area in real time. Ensure the accuracy and stability of the sensor to obtain reliable data. Preprocess the collected electromagnetic field data, including removing outliers, data smoothing, coordinate conversion, etc. Ensure the quality and availability of the data to prepare for subsequent analysis. Based on the collected data, calculate the electromagnetic radiation intensity at each location. This may involve the calculation of parameters such as electric field strength and magnetic field strength. You can choose the appropriate calculation method according to different needs.

[0053] The calculated electromagnetic radiation intensity is classified according to the pre-set standards, and the electromagnetic radiation intensity is divided into different level ranges. According to the divided level range, the specific standards for each level are determined. It may include the numerical range of electromagnetic radiation intensity, the corresponding safety threshold, possible health effects and other considerations. The divided electromagnetic radiation intensity levels are displayed in a graphical form.

[0054] Use the K-nearest neighbor algorithm to compare and analyze the real-time operation data of the drone with the standard operation data under normal working conditions, and determine the level range of stable operation of the drone, including:

[0055] Preprocess the real-time operation data and standard operation data, including data cleaning, normalization, feature extraction and other operations, to ensure the quality and consistency of the data.

[0056] Select appropriate features from the preprocessed data, which may include flight altitude, flight speed, attitude angle, sensor output, etc.

[0057] For each real-time operation data, the K nearest neighbor algorithm is used to calculate its distance from all samples in the standard operation data. The features of the preprocessed real-time operation data of the drone are represented as vectors, and the feature vectors corresponding to the real-time operation data of the drone and the standard operation data under normal working conditions are regarded as a set of data for comparison, and their similarity is calculated by Minkowski distance. The specific calculation expression is: ;in, Indicates the similarity between the real-time operation data of the drone and the standard operation data under normal working conditions. is the feature vector of the real-time operation data of the UAV, is the characteristic vector of the standard operating data under the corresponding normal working condition, p is the distance measurement parameter, and p is a positive integer greater than 0, and a is the number of data groups.

[0058] Select K, a parameter that determines the number of neighbors. The best K can be selected by cross-validation or heuristics.

[0059] For each real-time operation data, the stable operation level range is determined according to the data proportion of normal samples in its K nearest neighbors; when the data proportion of normal samples in the K nearest neighbors of the real-time operation data is greater than or equal to the proportion threshold, it is marked as the stable operation level range of the UAV, and the area within the stable operation level range is marked as the feasible working area of ​​the UAV; when the data proportion of normal samples in the K nearest neighbors of the real-time operation data is less than the proportion threshold, it is marked as the unstable operation level range of the UAV.

[0060] Judgment and evaluation module: Conduct flight tests within the feasible working area of ​​the UAV, record the flight status of the UAV at different positions and altitudes, analyze the flight status of the UAV under different electromagnetic interferences, and evaluate the interference degree of the UAV flight status; analyze the changes in the working status of the UAV's sensor equipment, and evaluate the performance stability of the UAV's sensor equipment.

[0061] Place the drone in a feasible working area and conduct flight tests. During the test, record the flight status of the drone at different positions and altitudes, including flight speed, attitude, altitude change and other information. Use sensor equipment or flight control systems to record the real-time operation data of the drone, including various parameters in flight and sensor output information.

[0062] The recorded data is analyzed, with special attention paid to the flight status of the drone at different locations and altitudes and at different flight stages. This includes evaluating the flight stability, attitude control, altitude control accuracy, etc. During the analysis, special attention is paid to the flight status of the drone in areas where electromagnetic interference may exist. By comparing these data with data from areas without electromagnetic interference, the degree of impact of electromagnetic interference on the flight status of the drone is evaluated.

[0063] The flight status of the UAV under different electromagnetic interferences is analyzed, and the UAV's surveying and mapping electromagnetic interference index is obtained according to the UAV's flight status data to evaluate the interference degree of the UAV's flight status. The method for obtaining the surveying and mapping electromagnetic interference index is as follows:

[0064] Collect the UAV’s flight status data M and mapping data N, and pre-process the data to ensure data quality and availability;

[0065] For each given combination of M and N, count its frequency of occurrence and divide it by the total number of samples to calculate the joint probability distribution and mark it as , the specific calculation expression is: ; In the formula, is the total number of samples, represents the number of times the combination m and n appears in the sample;

[0066] Count the frequency of each value of M and N respectively, and divide it by the total number of samples to calculate the marginal probability distribution and , the specific calculation expressions are expressed as follows: , ; In the formula, and Respectively represent the number of times the individual values ​​m and n in the flight status data M and mapping data N appear in the sample, is the marginal probability distribution of the flight status data M, is the marginal probability distribution of surveying and mapping data N;

[0067] According to the calculated marginal probability distribution and And the joint probability distribution , calculate the interference value between the flight status data M and the surveying and mapping data N, that is, calculate the surveying and mapping electromagnetic interference index. The specific calculation expression is: ; In the formula, To map the electromagnetic interference index.

[0068] When the EMI index for surveying and mapping increases, it means that the UAV is subject to an increased degree of electromagnetic interference during its flight and data collection. It may indicate that the flight status of the UAV in the selected working area is disturbed to a greater extent, resulting in an unstable flight process and inability to accurately collect and transmit data. This situation may affect the integrity and accuracy of the data, thereby reducing the feasibility and efficiency of the UAV's surveying and mapping work in the area. Therefore, an increase in the EMI index for surveying and mapping means that the UAV may face more challenges and need to take additional measures to deal with electromagnetic interference to ensure the smooth execution of the flight mission.

[0069] In the process of data management based on UAV surveying and mapping, the state changes of the UAV sensor equipment are analyzed to evaluate the performance stability of the sensor equipment. This means monitoring the performance of the sensor equipment under different working conditions, including the working stability in different environments, different flight altitudes and speeds.

[0070] The working state changes of the drone's sensor equipment are analyzed, and the fault frequency fluctuation value is obtained according to the frequency of faults of the sensor equipment during long-term operation. The performance stability of the drone's sensor equipment is evaluated. The method for obtaining the fault frequency fluctuation value is as follows:

[0071] Acquire the fault data of the sensor device within the time period t, and arrange the acquired fault data in chronological order to form a time series, wherein each data point in the time series represents a sensor device fault event, including the specific time when the fault occurred;

[0072] Statistics are performed on the time series data to calculate the actual failure frequency in each time period. The specific calculation expression is: ; In the formula, is the actual fault frequency, The number of failures in each time period, is the total number of observations in each time period; the moving average method is used to calculate the mean of the failure frequency in the moving window to smooth the data. For each data point in the time series , calculate its mean within the window, the mean within the window The calculation expression is: ; In the formula, is the starting index of the current window, is the index within the window, is the number of windows, and the smoothed fault frequency is the set of means in all windows, that is: ,in, is the smoothed fault frequency, n is the number of samples;

[0073] By performing fluctuation analysis on the smoothed fault frequency time series, the fault frequency fluctuation value is calculated. The specific calculation expression is: ; In the formula, is the fault frequency fluctuation value, is the mean fault frequency.

[0074] The increase in the fault frequency fluctuation value usually means that the operating status of the drone's sensor equipment in the feasible working area changes more dramatically. In other words, the frequency of failures of the drone in the same time period changes more erratically.

[0075] The increase in the fault frequency fluctuation value may reflect the increased instability of the operating state of the drone sensor equipment. This may be caused by electromagnetic interference, mechanical failure, environmental changes or other factors.

[0076] Increased fluctuations in failure frequency may lead to more unexpected situations or failures during the operation of drones. This may increase the risk of mission failure, lead to incomplete or inaccurate data collection, and may even cause safety issues or damage equipment.

[0077] High fluctuations in the frequency of failures may affect the efficiency and stability of the drone. Frequent failures may cause the drone to require frequent repairs or adjustments, thus affecting the continuity of its work and the quality of data collection.

[0078] Comprehensive analysis module: Comprehensively analyze the interference degree of the drone's flight status and the performance stability of the drone's sensor equipment, and evaluate whether there are any abnormalities in the drone's operating status within the feasible working area.

[0079] The surveying and mapping electromagnetic interference index and fault frequency fluctuation value are normalized, and the abnormal coefficient of the operating status of the UAV in the feasible working area is calculated based on the normalized surveying and mapping electromagnetic interference index and fault frequency fluctuation value.

[0080] For example, the present invention can use the following formula to calculate the abnormal coefficient of the operating state of the UAV in the feasible working area, and the calculation expression is: ; In the formula, is the abnormal coefficient, To map the electromagnetic interference index, is the fault frequency fluctuation value, is the proportional coefficient for mapping the electromagnetic interference index and the fault frequency fluctuation value, and ;

[0081] It can be seen from the calculation expression that the surveying and mapping electromagnetic interference index and the fault frequency fluctuation value are positively correlated with the anomaly coefficient, and with the increase of the surveying and mapping electromagnetic interference index and the fault frequency fluctuation value, the anomaly coefficient also gradually increases, indicating that the stability of the UAV's operating state in the feasible working area is gradually decreasing, and the possibility of anomalies is higher.

[0082] Abnormal classification module: According to the evaluation result of whether the UAV's operating status in the feasible working area is abnormal, the UAV's working status is divided into abnormal status, possible abnormal status, and normal status;

[0083] Compare the acquired abnormal coefficient of the operating state of the UAV in the feasible working area with the gradient standard threshold, the gradient standard threshold in the present application includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and compare the abnormal coefficient of the operating state of the UAV in the feasible working area with the first standard threshold and the second standard threshold respectively;

[0084] If the abnormal coefficient of the UAV's operating state in the feasible working area is greater than the second standard threshold, it means that the stability of the UAV's operating state in the feasible working area is low, and the possibility of abnormality is greater. The UAV's operating state is classified as abnormal, and immediate action is required. It may be necessary to suspend the UAV's mission and inspect or adjust the UAV to ensure its safe operation;

[0085] If the abnormal coefficient of the UAV's operating state in the feasible working area is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it means that the stability of the UAV's operating state in the feasible working area is general and the possibility of abnormality is moderate. The UAV's operating state is classified as a possible abnormal state and further monitoring and analysis is required. Consider reducing the flight range or adjusting the flight parameters, and closely monitor the operation of the UAV.

[0086] If the abnormal coefficient of the UAV's operating state in the feasible working area is less than the first standard threshold, it means that the stability of the UAV's operating state in the feasible working area is higher, and the possibility of abnormality is smaller. The working state of the UAV is classified as normal. The operating state of the UAV is good and the mission or planned work can continue.

[0087] In this embodiment, by determining the intensity and range of electromagnetic radiation, the intensity of electromagnetic radiation is divided into levels, and real-time operation data of drones in different levels are obtained, and the real-time operation data of the drone is compared and analyzed with the standard operation data of the drone under normal working conditions, the level range of stable operation of the drone is determined, and the feasible working area of ​​the drone is marked; a flight test is performed in the feasible working area of ​​the drone, and the flight status of the drone at different positions and altitudes is recorded at the same time, the flight status of the drone under different electromagnetic interferences is analyzed, and the interference degree of the drone flight status is evaluated; the change of the working status of the sensor equipment of the drone is analyzed, and the performance stability of the drone sensor equipment is evaluated; the interference degree of the drone flight status and the performance stability of the drone sensor equipment are comprehensively analyzed, and whether the operating status of the drone in the feasible working area is abnormal; according to the evaluation result of whether the operating status of the drone in the feasible working area is abnormal, the working status of the drone is divided into abnormal state, possible abnormal state, and normal state; not only the operating status of the drone in different environments is comprehensively and accurately evaluated, but also the efficiency and safety of the flight mission are improved, which helps to ensure the safety of equipment and personnel, and optimizes the results of mission execution.

[0088] Embodiment 2: Prediction management module: When the operation state of the UAV in the feasible working area is a possible abnormal state, the accuracy of the UAV mapping data is further analyzed and predicted, and the UAV mapping data is managed according to the prediction results.

[0089] When the operating status of a drone in a feasible working area is judged to be possibly abnormal, it means that the system has detected some signs that the drone's behavior may be abnormal or unusual. In this case, the system needs to further analyze and predict the accuracy of the drone's mapping data and take intelligent management measures.

[0090] When the working state of the UAV is a possible abnormal state, that is, the abnormal coefficient generated within a fixed time period is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, and the abnormal coefficients generated in the subsequent fixed time period are used to establish a data set, and the accuracy loss index of the UAV mapping data within the fixed time period is calculated.

[0091] pass The mean and average of the anomaly coefficients within the time period Anomaly coefficient mean prediction within a time period The mean value of the abnormal coefficient within the time period, the specific calculation expression is: ; In the formula, For prediction The mean of the anomaly coefficients within the time period, for The mean of the anomaly coefficients within the time period, for The mean of the anomaly coefficients within the time period, is the smoothing coefficient, and The value range is , fixed time , c is a positive integer greater than 0;

[0092] The predictions obtained The average value of the abnormal coefficient within the time period is different from the preset The mean value of the standard anomaly coefficient within the time period is analyzed to calculate the accuracy loss index of the UAV mapping data within a fixed time period. The specific calculation expression is: ; In the formula, is the accuracy loss index, for The mean of the standardized anomaly coefficients over the time period.

[0093] The accuracy loss index of the UAV mapping data obtained within a fixed time period is compared with the accuracy loss index reference threshold. If the accuracy loss index of the UAV mapping data within the fixed time period is greater than or equal to the accuracy loss index reference threshold, it means that the accuracy of the UAV mapping data is lower. At this time, a warning signal is generated to notify relevant personnel to manually process the data; if the accuracy loss index of the UAV mapping data within the fixed time period is less than the accuracy loss index reference threshold, it means that the accuracy of the UAV mapping data is higher. At this time, no warning signal is generated and no adjustment is required.

[0094] In this embodiment, the abnormal coefficient within a fixed time period is obtained based on the behavioral signs of the drone in a possible abnormal state. Then, the moving average method and other methods are used to predict the mean value of the abnormal coefficient in the next time period. The predicted mean value of the abnormal coefficient is compared and analyzed with the pre-set mean value of the standard abnormal coefficient. If the predicted value exceeds the reference threshold, an early warning signal is triggered to prompt relevant personnel that there may be data accuracy problems and manual processing is required; if it does not exceed the threshold, the data accuracy is considered acceptable and no adjustment is required. Such an intelligent management strategy can improve the perception and processing efficiency of abnormal drone mapping data. It improves the quality and accuracy of the data and ensures the effectiveness and reliability of subsequent data analysis and application.

[0095] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0096] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0097] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0098] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0099] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0100] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0101] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0102] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A data management system based on drone mapping, characterized by: It includes electromagnetic monitoring module, work area determination module, judgment and evaluation module, comprehensive analysis module, abnormal classification module and prediction management module; Electromagnetic monitoring module: Determine the location and working condition of the high-voltage transmission line according to the UAV's operating area, monitor and analyze the electromagnetic field data in the area, and determine the intensity and range of electromagnetic radiation; Working area determination module: divides the intensity of electromagnetic radiation into levels, obtains the real-time operation data of drones in different levels, compares and analyzes the real-time operation data of drones with the standard operation data of drones under normal working conditions, determines the level range of stable operation of drones, and marks the areas within this range as feasible working areas of drones; Judgment and evaluation module: Conduct flight tests within the feasible working area of ​​the drone, record the flight status of the drone at different positions and altitudes, analyze the flight status of the drone under different electromagnetic interferences, and evaluate the interference degree of the drone's flight status; analyze the changes in the working status of the drone's sensor equipment, and evaluate the performance stability of the drone's sensor equipment; The judgment and evaluation module includes: analyzing the flight status of the UAV under different electromagnetic interferences, obtaining the UAV's surveying and mapping electromagnetic interference index according to the UAV's flight status data, and evaluating the interference degree of the UAV's flight status. The method for obtaining the surveying and mapping electromagnetic interference index is: Collect the UAV’s flight status data M and mapping data N, and pre-process the data; For each given combination of M and N, count its frequency of occurrence and divide it by the total number of samples to calculate the joint probability distribution and mark it as p(m, n). The specific calculation expression is: In the formula, Q is the total number of samples, Q mn represents the number of times the combination m and n appears in the sample; The frequency of occurrence of each value of M and N is counted respectively, and divided by the total number of samples to calculate the marginal probability distribution p(m) and p(n). The specific calculation expressions are expressed as follows: In the formula, Q m and Q n They represent the number of times individual values ​​m and n in the flight status data M and surveying and mapping data N appear in the samples, respectively. p(m) is the marginal probability distribution of the flight status data M, and p(n) is the marginal probability distribution of the surveying and mapping data N. According to the calculated marginal probability distribution p(m) and p(n) and the joint probability distribution p(m,n), the interference value between the flight status data M and the mapping data N is calculated, that is, the mapping electromagnetic interference index is calculated. The specific calculation expression is: In the formula, YK MN To map the electromagnetic interference index; The working state changes of the drone's sensor equipment are analyzed, and the fault frequency fluctuation value is obtained according to the frequency of faults of the sensor equipment during long-term operation. The performance stability of the drone's sensor equipment is evaluated. The method for obtaining the fault frequency fluctuation value is as follows: Acquire the fault data of the sensor device within the time period t, and arrange the acquired fault data in chronological order to form a time series, wherein each data point in the time series represents a sensor device fault event, including the specific time when the fault occurred; Statistics are performed on the time series data to calculate the actual failure frequency in each time period. The specific calculation expression is: Where wk pf is the actual fault frequency, fh e Number of failures in each time period, km z is the total number of observations in each time period; the moving average method is used to calculate the mean of the failure frequency in the moving window to smooth the data. For each data point F in the time series T , calculate its mean within the window, the mean within the window F T The calculation expression is: Where T is the starting index of the current window, j is the index in the window, k is the number of windows, and the smoothed fault frequency is the set of means in all windows, that is: Fv = {F1, F2, ..., F n-k+1 }, where Fv is the smoothed fault frequency and n is the number of samples; By performing fluctuation analysis on the smoothed fault frequency time series, the fault frequency fluctuation value is calculated. The specific calculation expression is: In the formula, cb xd is the fault frequency fluctuation value, Fvr is the fault frequency mean value; Comprehensive analysis module: Comprehensively analyze the interference degree of the UAV's flight status and the performance stability of the UAV's sensor equipment to evaluate whether the UAV's operating status in the feasible working area is abnormal; Abnormal classification module: According to the evaluation result of whether the UAV's operating status in the feasible working area is abnormal, the UAV's working status is divided into abnormal status, possible abnormal status, and normal status; Prediction management module: When the operating status of the UAV in the feasible working area is possibly abnormal, the accuracy of the UAV mapping data is further analyzed and predicted, and the UAV mapping data is managed according to the prediction results.

2. A data management system based on drone mapping according to claim 1, characterized in that: In the working area determination module, the K nearest neighbor algorithm is used to compare and analyze the real-time operation data of the drone with the standard operation data under normal working conditions, and determine the level range of stable operation of the drone, including: Preprocess the real-time operation data and the standard operation data, select features from the preprocessed data, and use the K nearest neighbor algorithm to calculate the distance between each real-time operation data and all samples in the standard operation data; The features of the preprocessed real-time operation data of the UAV are represented as vectors. The feature vectors corresponding to the real-time operation data of the UAV and the standard operation data under normal working conditions are regarded as a set of data for comparison. The similarity is calculated by Minkowski distance. The specific calculation expression is: Among them, D(x,y) represents the similarity between the real-time operation data of the drone and the standard operation data under normal working conditions, x i is the feature vector of the real-time operation data of the UAV, y i is the characteristic vector of the standard operating data under the corresponding normal working condition, p is the distance measurement parameter, and p is a positive integer greater than 0, and a is the number of data groups.

3. A data management system based on drone mapping according to claim 2, characterized in that: Select the K value, and for each real-time operation data, determine the level range of stable operation according to the data proportion of normal samples in its K nearest neighbors; when the data proportion of normal samples in the K nearest neighbors of the real-time operation data is greater than or equal to the proportion threshold, it is marked as the level range of stable operation of the UAV, and the area within the stable operation level range is marked as the feasible working area of ​​the UAV; when the data proportion of normal samples in the K nearest neighbors of the real-time operation data is less than the proportion threshold, it is marked as the level range of unstable operation of the UAV.

4. The data management system based on drone mapping according to claim 1 is characterized by: In the comprehensive analysis module, the interference degree of the UAV flight status and the performance stability of the UAV sensor equipment are comprehensively analyzed, specifically: The surveying and mapping electromagnetic interference index and fault frequency fluctuation value are normalized, and the abnormal coefficient of the operating status of the UAV in the feasible working area is calculated based on the normalized surveying and mapping electromagnetic interference index and fault frequency fluctuation value.

5. The data management system based on drone mapping according to claim 4 is characterized by: The acquired abnormal coefficient of the operating state of the UAV in the feasible working area is compared with the gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the abnormal coefficient of the operating state of the UAV in the feasible working area is compared with the first standard threshold and the second standard threshold respectively; If the abnormal coefficient of the operating state of the drone in the feasible working area is greater than the second standard threshold, the operating state of the drone is classified as an abnormal state; if the abnormal coefficient of the operating state of the drone in the feasible working area is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the operating state of the drone is classified as a possible abnormal state; If the abnormal coefficient of the operating state of the UAV in the feasible working area is less than the first standard threshold, the working state of the UAV is classified as a normal state.

6. The data management system based on drone mapping according to claim 1 is characterized by: When the working state of the UAV is a possible abnormal state, that is, the abnormal coefficient generated within a fixed time period is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, and the abnormal coefficients generated in the subsequent fixed time period are used to establish a data set, and the accuracy loss index of the UAV mapping data within the fixed time period is calculated.

7. A data management system based on drone mapping according to claim 6, characterized in that: The mean of the abnormal coefficient in the time period s+1 is predicted by the mean of the abnormal coefficient in the time period s and the mean of the abnormal coefficient in the time period s-1. The specific calculation expression is: kt (h，s+1) =Z*kt (h，s) +(1-Z)*kt (h，s-1) ; In the formula, kt (h，s+1) is the mean value of the abnormal coefficient in the predicted s+1 period, kt (h，s) is the mean of the abnormal coefficient in the s time period, kt (h，s-1 is the mean value of the abnormal coefficient in the time period s-1, Z is the smoothing coefficient, and the value range of Z is [0, 1], the fixed time s = 1, 2, 3, ..., c, c is a positive integer greater than 0; The obtained average value of the anomaly coefficient in the predicted s+1 time period is analyzed with the preset average value of the standard anomaly coefficient in the s+1 time period, and the accuracy loss index of the UAV mapping data in a fixed time period is calculated. The specific calculation expression is: In the formula, tk bf is the accuracy loss index, KTG s+1 is the mean of the standard anomaly coefficient in the time period s+1.

8. The data management system based on drone mapping according to claim 7 is characterized by: The accuracy loss index of the UAV mapping data obtained within a fixed time period is compared with the accuracy loss index reference threshold. If the accuracy loss index of the UAV mapping data within the fixed time period is greater than or equal to the accuracy loss index reference threshold, a warning signal is generated; if the accuracy loss index of the UAV mapping data within the fixed time period is less than the accuracy loss index reference threshold, no warning signal is generated and no adjustment is required.

Images