Unmanned aerial vehicle driving data management method and system based on environmental parameters

Abstract

The application discloses an unmanned aerial vehicle driving data management method and system based on environmental parameters and belongs to the technical field of data management. The system comprises a dynamic sensing module, an interference analysis module, an operation setting module and a driving management module. The dynamic sensing module is used for collecting GIS maps and scanning data of a specified area, and collecting operation parameters and environmental parameters of each unmanned aerial vehicle. The interference analysis module is used for constructing a three-dimensional airflow field, dividing a sampling area in the three-dimensional airflow field, analyzing changes in operation parameters of the unmanned aerial vehicle when hovering in the sampling area, calculating a stability coefficient and setting an interference area. The operation setting module is used for analyzing the interference area, setting an influence area and fitting a relational expression of each influence area. Different schemes are established, and an adjustment scheme is set in combination with the relational expression. The driving management module is used for fitting virtual sensors of different types in the unmanned aerial vehicle, and the weight of the virtual sensors of different types is adjusted according to the adjustment scheme in the flight process.

Description

Technical Field

[0001] This invention relates to the field of data management technology, specifically to a method and system for unmanned aerial vehicle (UAV) driven data management based on environmental parameters. Background Technology

[0002] In recent years, drone swarm technology has developed rapidly and is widely used in tasks such as performance formation, inspection, surveying, rescue, and logistics. Compared with single-drone flight, swarm operations have higher requirements for formation accuracy and time synchronization, making attitude stability and coordinated control particularly critical in complex environments. Strong turbulent environments can cause instantaneous, spatially unstable wind fields, significantly increasing the risk of attitude instability, formation deviation, and even collisions and crashes in drone swarms.

[0003] In complex airspace operation scenarios, high-precision flight control systems for UAVs place stringent demands on the environmental adaptability and dynamic response capabilities of inertial measurement units (IMUs). Existing technologies exhibit significant limitations in environmental parameter-driven operations: First, the output stability of distributed sensors of the same model suffers from insufficient stability due to the superposition of data fluctuations, making it difficult for traditional single-chip solutions to construct virtual sensing units that integrate multi-source information. Second, the accuracy characteristics of heterogeneous sensors in dynamic / static environments are inherently contradictory—for example, gyroscopes have significant advantages in high-speed response but are accompanied by significant noise, while accelerometers possess static accuracy advantages but suffer from dynamic hysteresis, preventing the system from dynamically allocating weights based on real-time environmental parameters to achieve complementary performance. Finally, the environmental perception and analysis mechanisms are highly rigid, failing to adaptively delineate key operational areas based on meteorological elements or establish a relationship model between flight stability and sensor weights, leading to a significant deterioration in the anti-disturbance capability during UAV swarm operations. Therefore, a more intelligent and efficient UAV-driven data management technology solution is needed to address these issues. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for managing unmanned aerial vehicle (UAV) driven data based on environmental parameters, so as to solve the problems mentioned in the background art.

[0005] To address the aforementioned technical problems, this invention provides a method for managing unmanned aerial vehicle (UAV) driven data based on environmental parameters, comprising:

[0006] S100 collects GIS maps and scanned data of the designated area, as well as the operating parameters and environmental parameters of each UAV.

[0007] Scan data refers to the three-dimensional physical space data within a specified airspace obtained through multi-source sensing devices.

[0008] The operating parameters include flight trajectory, spatial position, vibration intensity, and weight allocation. The flight trajectory refers to a preset track that simultaneously has a time node sequence and a spatial coordinate sequence.

[0009] The time-space dual-series track records the dwell time at waypoints, providing low-granular temporal characteristics for subsequent dwell analysis.

[0010] Vibration intensity refers to the degree of intensity of vibration generated by the drone's body during flight.

[0011] Weight allocation refers to the real-time weight distribution data of different types of virtual sensors during the flight of a drone. The virtual sensors are obtained by fitting multiple sensors of the same type inside the drone.

[0012] The weight allocation data not only represents the real-time sensor priority, but also includes historical weight adjustment records, which increases the correlation between environmental parameters and operating parameters.

[0013] Environmental parameters refer to the meteorological indicators of the surrounding environment collected by the drone through various sensors.

[0014] Constructing a multi-dimensional benchmark dataset provides an accurate spatiotemporal input source for airflow disturbance analysis, and the fusion of multi-source physical parameters reduces the risk of errors from a single sensor.

[0015] S200. Construct a three-dimensional airflow field based on environmental parameters to analyze the hovering position and dwell time of the UAV. Divide the sampling area in the three-dimensional airflow field and analyze the changes in operating parameters during the dwell time, calculate the stability coefficient, and define the interference zone. Specifically, this includes:

[0016] S201. Obtain environmental and operational parameters collected in real time by different UAVs, and extract terrain elevation and surface feature information by combining GIS maps and scanned data.

[0017] S202. The model is simplified by using the Kriging spatial interpolation algorithm and the Navier-Stokes equation. The three-dimensional airflow field is simulated and updated in real time by integrating discrete point data with the CFD physical simulation model.

[0018] S203, Analyze past duration Within the sample, the hovering positions and durations of each drone are recorded. Hovering positions with a duration exceeding a threshold are marked, and sampling areas are defined in a three-dimensional airflow field using these marked hovering positions as centers. Specifically, this includes:

[0019] S2031, Acquiring a Drone At the marker hover position Duration of stay In terms of duration Evenly distributed inside A specific point in time.

[0020] S2032. Analyze the drone at each time point. Collect wind speed from environmental parameters and calculate the standard deviation of wind speed at all time points. and average Preset base distance Then substitute the values ​​into the formula to calculate the distance of influence. :

[0021] ;

[0022] In the formula, The preset reference wind speed standard deviation, It is a constant greater than 1. This is the preset reference wind speed.

[0023] Based on the fluctuations and average wind speed intensity of the wind speed data, combined with the basic preset distance and logarithmic amplification effect, the radius of the spherical sampling area centered on the marked hovering position is calculated.

[0024] The core purpose of influencing the distance setting is to dynamically adjust the sampling range size. When wind speed variability is high, the sampling area is significantly expanded to capture highly turbulent regions. When the average wind speed is strong, the radius is further enlarged to enhance spatial coverage.

[0025] S2033, Mark the hover position The center of the ball affects the distance. Using a radius of 1, a spherical region is defined within the three-dimensional airflow field as the sampling area. The influence distance of each marker hovering position is calculated, and the sampling area is then defined accordingly.

[0026] The dwell time refers to the duration during which a drone hovers in the air without changing its position.

[0027] S204. Merge the intersecting sampling areas and analyze the changes in operating parameters during the dwell time at different marker hovering positions within the sampling areas. Calculate the stability coefficient for each sampling area and define the interference zone based on the stability coefficient. Specifically, this includes:

[0028] S2041. Determine if different sampling areas overlap, and merge all overlapping sampling areas. Obtain the dwell time of different marker hovering positions within the sampling area and analyze the start time. and end time .

[0029] S2042. Analyze the vibration intensity of the UAV at each time point and calculate the standard deviation of the vibration intensity at all time points. and average Get the current time. Substitute into the formula to calculate the stability coefficient of each sampling area. :

[0030] ;

[0031] In the formula, The number of hover positions marked in the sampling area. and These are the preset standard deviation of reference vibration intensity and the reference vibration intensity, respectively.

[0032] and The first The start and end times of the period during which the marker hovers at a position. and The first The standard deviation and mean of vibration intensity at all time points at each marker hovering position.

[0033] Based on preset reference vibration indicators, the overall stability of the sampling area is comprehensively evaluated by summarizing data from multiple hovering positions and combining the influence of the length of time spent at each position and its distance from the current time.

[0034] The numerator strengthens the reference value of the ideal stable state, while the denominator introduces the actual vibration deviation value and the time decay factor, thereby quantifying the dynamic impact of airflow interference on the UAV and marking the low-value sampling area as the interference area to achieve accurate identification of unstable areas.

[0035] S2043. Calculate the stability coefficient of each sampling area separately, and take the sampling area with the stability coefficient less than the threshold as the interference area.

[0036] Achieve dynamic modeling of three-dimensional airflow field and detection of spatiotemporal coupling interference, and quantify the impact of turbulent airflow regions on the stability of UAVs.

[0037] S300. The interference area traversed by the UAV's flight path is considered the affected area. The relationship expression for each affected area is fitted and analyzed. Different scenarios are established, and the predicted vibration intensity of each scenario is calculated based on the relationship expression, and an adjustment scheme is set. Specifically, this includes:

[0038] S301. Obtain the flight trajectory from the operating parameters of each UAV, extract the unflying portion of the flight trajectory and map it onto the three-dimensional airflow field, and use the interference area crossed by the flight trajectory as the affected area.

[0039] S302. Analyze the dwell time corresponding to each marker hovering position within the affected area, obtain the vibration intensity and weight distribution changes of the corresponding UAVs during the dwell time, and use fitting analysis to obtain the vibration relationship expressions for each affected area. Specifically, this includes:

[0040] S3021. Analyze the dwell time corresponding to each marker hovering position in the affected area, and obtain the vibration intensity and weight distribution changes of the corresponding UAVs during the dwell time.

[0041] S3022, Divide the weighted allocation duration into each dwell period. The average vibration intensity is calculated based on the changes in vibration intensity within a time period that remains unchanged.

[0042] S3023. Calculate the total number of all time periods within all periods of stay. The average vibration intensity of each time period is used as the dependent variable, and the weights of all virtual sensors are used as independent variables and packaged into samples.

[0043] S3024, Set intercept and regression coefficients And establish a linear regression model. This The independent variables in each sample are used as input values. The output value of each sample The difference between the dependent variable and the differential variable is used as the difference coefficient. The expression is as follows:

[0044] ;

[0045] S3025. Adjust the intercept and regression coefficients until the sum of the difference coefficients for all samples is minimized, thus obtaining the fitted vibration relationship expression. Repeat this process to fit vibration relationship expressions for each affected region.

[0046] S303, Establish for each affected area There are several schemes, each with weights assigned to different types of virtual sensors. The weights of all virtual sensors are not exactly the same across different schemes.

[0047] S304. Extract the weights of each virtual sensor in each scheme and substitute them into the vibration relationship expression to calculate the predicted vibration intensity. Select the scheme with the minimum predicted vibration intensity as the adjustment scheme for the corresponding influence zone.

[0048] A data-driven vibration intensity prediction and weight optimization model is established to generate a pre-adaptive control strategy for the disturbance area.

[0049] The S400 and UAV integrate multiple sensors of the same model into a single virtual sensor. During flight, the weights of different virtual sensors are adjusted in real time according to a specific plan. This includes:

[0050] S401. Multiple physical sensors of the same model inside the UAV are fitted into a single virtual sensor using a weighted average algorithm, forming multiple virtual sensors of different models.

[0051] When averaging physical sensors of the same model, the fusion weights are assigned based on historical confidence levels to form a noise-enhanced virtual sensor.

[0052] S402. During flight, monitor the spatial position of the UAV in real time. When the spatial position is in the affected area, control the virtual sensors inside the UAV to drive and debug according to the weights in the corresponding adjustment scheme.

[0053] Achieve cross-sensor heterogeneous data fusion and flight process self-optimization control, and construct a real-time control chain for interference response.

[0054] The present invention also provides an unmanned aerial vehicle (UAV) driven data management system based on environmental parameters, including a dynamic perception module, an interference analysis module, an operation setting module, and a drive management module.

[0055] The dynamic sensing module is used to collect GIS maps and scanned data of a specified area, as well as the operating parameters and environmental parameters of each UAV.

[0056] Collect GIS maps of the designated area, 3D physical space data scanned by multi-source sensing devices, and real-time operating parameters and environmental parameters of each UAV.

[0057] The operational parameters include time-space dual-dimensional flight path data, while environmental parameters are acquired in real time through the drone's sensors.

[0058] A multi-dimensional data foundation is established to provide accurate input for 3D airflow field modeling. Real-time monitoring of UAV status and external environmental dynamics supports subsequent interference analysis and weight optimization.

[0059] The interference analysis module is used to construct a three-dimensional airflow field and divide the field into sampling zones. It analyzes the changes in the operating parameters of the UAV while it hovers within the sampling zones, calculates the stability coefficient, and defines the interference zone.

[0060] By combining GIS topographic elevation and surface features, a simplified model using the Kriging spatial interpolation algorithm and the Navier-Stokes equations is constructed to create a real-time updated three-dimensional airflow field.

[0061] The location of drones whose hovering time exceeds a threshold is determined, and the sampling area is divided using the sphere center radius method.

[0062] After merging the overlapping sample areas, the stability coefficient is calculated using the time-varying characteristics of vibration intensity, and the area with low stability coefficient is marked as the interference area.

[0063] Accurately identify interference areas where vibration is aggravated due to unstable airflow. Quantify the intensity of environmental disturbances on the UAV, providing a spatial basis for subsequent weight adjustments.

[0064] The runtime configuration module is used to analyze the interference zone and define the affected zone, and fit the relationship expression for each affected zone. Different schemes are established, and adjustment schemes are set based on the relationship expression.

[0065] Interference zones traversed by unexecuted flight paths are extracted as the affected areas. Based on historical hovering periods and vibration intensity and weighting data, a linear regression model is constructed to fit the vibration relationship expression.

[0066] Vibration intensity is predicted by comparing multiple schemes, and the optimal scheme is selected as the adjustment scheme.

[0067] Establish a data-driven vibration prediction model; dynamically generate sensor weight optimization schemes to minimize airframe vibration in specific areas and improve flight stability.

[0068] The drive management module is used to fit different types of virtual sensors inside the UAV and adjust the weights of different types of virtual sensors according to the adjustment scheme during flight.

[0069] By weighting and fusing physical sensors of the same type into a single virtual sensor, and switching the weight allocation of different adjustment schemes in real time according to the area of ​​influence, dynamic adjustment of the weights of multiple virtual sensors during flight can be achieved.

[0070] Sensor fusion reduces noise interference; real-time response to environmental changes and adaptive optimization of sensor data fusion strategies enhance the anti-disturbance capability and control precision of UAVs.

[0071] Each module forms a closed-loop data flow: the perception layer collects basic data → the analysis layer locates the interference area → the decision layer generates a weight scheme → the execution layer dynamically drives and debugs the system to achieve environmental adaptive flight control.

[0072] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0073] Precise Environmental Modeling and Risk Identification: By collecting GIS maps, scanning data, and environmental parameters, and combining multi-source sensing devices with real-time data updates, a dynamic three-dimensional airflow field is constructed to achieve a refined simulation of the specified airspace environment. The three-dimensional airflow field improves the accuracy of describing terrain elevation, surface features, and meteorological changes, thereby more effectively identifying unstable airflow areas during the hovering period. Through stability coefficient calculation and interference zone setting, high-risk airspace locations can be intelligently distinguished, providing a basis for pre-identification to reduce UAV vibration.

[0074] Dynamic optimization and real-time adaptation: An influence zone analysis and vibration relationship expression fitting mechanism are introduced. Based on flight trajectory, location, and vibration intensity data, multiple weight allocation schemes are established, and the adjustment scheme with the minimum predicted vibration is selected. This allows for real-time adjustment of the weights of different types of virtual sensors during flight, achieving optimal utilization of sensor resources. Compared to existing technologies, this avoids the lag of static calibration, improves the UAV's adaptability to airflow interference, and simplifies redundant data management through the integration of virtual sensors, enhancing flight stability and reliability.

[0075] Intelligent sensor integration and weight adjustment: By fitting physical sensors of the same type into a single virtual sensor, a dynamic combination of multiple virtual sensors is formed, enabling centralized management of sensor resources. Weight allocation is adjusted in real time during flight based on the location of the affected area, allowing for rapid response to environmental disturbances without external intervention. Compared to existing point-to-point sensor management technologies, this strategy significantly reduces hardware resource consumption and maintenance complexity, while improving data acquisition efficiency and overall system robustness. Attached Figure Description

[0076] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0077] Figure 1 This is a flowchart illustrating the UAV-driven data management method based on environmental parameters according to the present invention.

[0078] Figure 2 This is a schematic diagram of the structure of the UAV-driven data management system based on environmental parameters according to the present invention. Detailed Implementation

[0079] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0080] Example 1: Please refer to Figure 1 This invention provides a method for managing unmanned aerial vehicle (UAV) driven data based on environmental parameters, including:

[0081] S100 collects GIS maps and scanned data of the designated area, as well as the operating parameters and environmental parameters of each UAV.

[0082] Scan data refers to the three-dimensional physical space data within a specified airspace obtained through multi-source sensing devices.

[0083] The operating parameters include flight trajectory, spatial position, vibration intensity, and weight allocation. The flight trajectory refers to a preset track that simultaneously has a time node sequence and a spatial coordinate sequence.

[0084] In practice, the time-space dual-series track records the dwell time at waypoints, providing low-granular temporal characteristics for subsequent dwell analysis.

[0085] Vibration intensity refers to the degree of intensity of vibration generated by the drone's body during flight.

[0086] Weight allocation refers to the real-time weight distribution data of different types of virtual sensors during the flight of a drone. The virtual sensors are obtained by fitting multiple sensors of the same type inside the drone.

[0087] In practice, the weight allocation data not only represents the real-time sensor priority, but also includes historical weight adjustment records (such as the automatic increase of the infrared sensor weight when the temperature drops sharply), which increases the correlation between environmental parameters and operating parameters.

[0088] Environmental parameters refer to the meteorological indicators (such as wind speed, wind direction, temperature, and humidity) collected by the drone through various sensors.

[0089] Constructing a multi-dimensional benchmark dataset provides an accurate spatiotemporal input source for airflow disturbance analysis, and the fusion of multi-source physical parameters reduces the risk of errors from a single sensor.

[0090] S200. Construct a three-dimensional airflow field based on environmental parameters to analyze the hovering position and dwell time of the UAV. Divide the sampling area in the three-dimensional airflow field and analyze the changes in operating parameters during the dwell time, calculate the stability coefficient, and define the interference zone. Specifically, this includes:

[0091] S201. Obtain environmental and operational parameters collected in real time by different UAVs, and extract terrain elevation and surface feature information by combining GIS maps and scanned data.

[0092] S202. The model is simplified by using the Kriging spatial interpolation algorithm and the Navier-Stokes equation. The three-dimensional airflow field is simulated and updated in real time by integrating discrete point data with the CFD physical simulation model.

[0093] S203, Analyze past duration Within the sample, the hovering positions and durations of each drone are recorded. Hovering positions with a duration exceeding a threshold are marked, and sampling areas are defined in a three-dimensional airflow field using these marked hovering positions as centers. Specifically, this includes:

[0094] S2031, Acquiring a Drone At the marker hover position Duration of stay In terms of duration Evenly distributed inside A specific point in time.

[0095] S2032. Analyze the drone at each time point. Collect wind speed from environmental parameters and calculate the standard deviation of wind speed at all time points. and average Preset base distance Then substitute the values ​​into the formula to calculate the distance of influence. :

[0096] ;

[0097] In the formula, The preset reference wind speed standard deviation, It is a constant greater than 1. This is the preset reference wind speed.

[0098] In the specific implementation process, based on the fluctuation of wind speed data (i.e., the comparison between the standard deviation and the reference value) and the average wind speed intensity (the ratio with the preset reference wind speed), combined with the basic preset distance and the logarithmic amplification effect, the radius of the spherical sampling area centered on the marker hovering position is calculated.

[0099] The core purpose of influencing the distance setting is to dynamically adjust the sampling range size. When wind speed variability is high, the sampling area is significantly expanded to capture highly turbulent regions. When the average wind speed is strong, the radius is further enlarged to enhance spatial coverage.

[0100] S2033, Mark the hover position The center of the ball affects the distance. Using a radius of 1, a spherical region is defined within the three-dimensional airflow field as the sampling area. The influence distance of each marker hovering position is calculated, and the sampling area is then defined accordingly.

[0101] The dwell time refers to the duration during which a drone hovers in the air without changing its position.

[0102] S204. Merge the intersecting sampling areas and analyze the changes in operating parameters during the dwell time at different marker hovering positions within the sampling areas. Calculate the stability coefficient for each sampling area and define the interference zone based on the stability coefficient. Specifically, this includes:

[0103] S2041. Determine if different sampling areas overlap, and merge all overlapping sampling areas. Obtain the dwell time of different marker hovering positions within the sampling area and analyze the start time. and end time .

[0104] S2042. Analyze the vibration intensity of the UAV at each time point and calculate the standard deviation of the vibration intensity at all time points. and average Get the current time. Substitute into the formula to calculate the stability coefficient of each sampling area. :

[0105] ;

[0106] In the formula, The number of hover positions marked in the sampling area. and These are the preset standard deviation of reference vibration intensity and the reference vibration intensity, respectively.

[0107] and The first The start and end times of the period during which the marker hovers at a position. and The first The standard deviation and mean of vibration intensity at all time points at each marker hovering position.

[0108] Based on preset reference vibration indicators, the overall stability of the sampling area is comprehensively evaluated by summarizing data from multiple hovering locations (including the dispersion and average value of vibration intensity) and combining the influence of the length of time spent at each location and its distance from the current time.

[0109] In the specific implementation process, the numerator strengthens the reference value of the ideal stable state (such as the vibration standard deviation and mean), while the denominator introduces the actual vibration deviation value and the time decay factor (i.e., more recent data is given higher weight), thereby quantifying the dynamic impact of airflow interference on the UAV and marking the low-value sampling area as the interference area to achieve accurate identification of unstable areas.

[0110] S2043. Calculate the stability coefficient of each sampling area separately, and take the sampling area with the stability coefficient less than the threshold as the interference area.

[0111] Achieve dynamic modeling of three-dimensional airflow field and detection of spatiotemporal coupling interference, and quantify the impact of turbulent airflow regions on the stability of UAVs.

[0112] S300. The interference area traversed by the UAV's flight path is considered the affected area. The relationship expression for each affected area is fitted and analyzed. Different scenarios are established, and the predicted vibration intensity of each scenario is calculated based on the relationship expression, and an adjustment scheme is set. Specifically, this includes:

[0113] S301. Obtain the flight trajectory from the operating parameters of each UAV, extract the unflying portion of the flight trajectory and map it onto the three-dimensional airflow field, and use the interference area crossed by the flight trajectory as the affected area.

[0114] S302. Analyze the dwell time corresponding to each marker hovering position within the affected area, obtain the vibration intensity and weight distribution changes of the corresponding UAVs during the dwell time, and use fitting analysis to obtain the vibration relationship expressions for each affected area. Specifically, this includes:

[0115] S3021. Analyze the dwell time corresponding to each marker hovering position in the affected area, and obtain the vibration intensity and weight distribution changes of the corresponding UAVs during the dwell time.

[0116] S3022, Divide the weighted allocation duration into each dwell period. The average vibration intensity is calculated based on the changes in vibration intensity within a time period that remains unchanged.

[0117] S3023. Calculate the total number of all time periods within all periods of stay. The average vibration intensity of each time period is used as the dependent variable, and the weights of all virtual sensors are used as independent variables and packaged into samples.

[0118] S3024, Set intercept and regression coefficients And establish a linear regression model. This The independent variables in each sample are used as input values. The output value of each sample The difference between the dependent variable and the differential variable is used as the difference coefficient. The expression is as follows:

[0119] ;

[0120] S3025. Adjust the intercept and regression coefficients until the sum of the difference coefficients for all samples is minimized, thus obtaining the fitted vibration relationship expression. Repeat this process to fit vibration relationship expressions for each affected region.

[0121] S303, Establish for each affected area There are several schemes, each with weights assigned to different types of virtual sensors. The weights of all virtual sensors are not exactly the same across different schemes.

[0122] S304. Extract the weights of each virtual sensor in each scheme and substitute them into the vibration relationship expression to calculate the predicted vibration intensity. Select the scheme with the minimum predicted vibration intensity as the adjustment scheme for the corresponding influence zone.

[0123] A data-driven vibration intensity prediction and weight optimization model is established to generate a pre-adaptive control strategy for the disturbance area.

[0124] The S400 and UAV integrate multiple sensors of the same model into a single virtual sensor. During flight, the weights of different virtual sensors are adjusted in real time according to a specific plan. This includes:

[0125] S401. Multiple physical sensors of the same model inside the UAV are fitted into a single virtual sensor using a weighted average algorithm, forming multiple virtual sensors of different models.

[0126] In the specific implementation process, when the physical sensors of the same model are weighted and averaged, the fusion weights are allocated according to the historical confidence level (for example, sensors with less than 3 vibration intensity exceedances under high weights continue to have their weights increased) to form a noise-enhanced virtual sensor.

[0127] S402. During flight, monitor the spatial position of the UAV in real time. When the spatial position is in the affected area, control the virtual sensors inside the UAV to drive and debug according to the weights in the corresponding adjustment scheme.

[0128] Achieve cross-sensor heterogeneous data fusion and flight process self-optimization control, and construct a real-time control chain for interference response.

[0129] Example 2: Please refer to Figure 2 The present invention also provides an unmanned aerial vehicle (UAV) driven data management system based on environmental parameters, including a dynamic perception module, an interference analysis module, an operation setting module, and a drive management module.

[0130] The dynamic sensing module is used to collect GIS maps and scanned data of a specified area, as well as the operating parameters and environmental parameters of each UAV.

[0131] In the specific implementation process, GIS maps of designated areas, three-dimensional physical space data scanned by multi-source sensing devices, and real-time operating parameters (flight trajectory, spatial position, vibration intensity, weight allocation) and environmental parameters (wind speed, wind direction, temperature, humidity) of each UAV are collected.

[0132] The operational parameters include time-space dual-dimensional flight path data, while environmental parameters are acquired in real time through the drone's sensors.

[0133] A multi-dimensional data foundation is established to provide accurate input for 3D airflow field modeling. Real-time monitoring of UAV status and external environmental dynamics supports subsequent interference analysis and weight optimization.

[0134] The interference analysis module is used to construct a three-dimensional airflow field and divide the field into sampling zones. It analyzes the changes in the operating parameters of the UAV while it hovers within the sampling zones, calculates the stability coefficient, and defines the interference zone.

[0135] By combining GIS topographic elevation and surface features, a simplified model using the Kriging spatial interpolation algorithm and the Navier-Stokes equations is constructed to create a real-time updated three-dimensional airflow field.

[0136] In the specific implementation process, the location of drones whose hovering time exceeds the threshold is determined, and the sampling area is divided using the sphere radius method (the radius is dynamically calculated from the standard deviation and mean of wind speed).

[0137] After merging overlapping sample areas, the stability coefficient is calculated using the time-varying characteristics (standard deviation and mean) of vibration intensity, and areas with low stability coefficients are marked as interference areas.

[0138] Accurately identify interference areas where vibration is aggravated due to unstable airflow. Quantify the intensity of environmental disturbances on the UAV, providing a spatial basis for subsequent weight adjustments.

[0139] The runtime configuration module is used to analyze the interference zone and define the affected zone, and fit the relationship expression for each affected zone. Different schemes are established, and adjustment schemes are set based on the relationship expression.

[0140] Interference zones traversed by unexecuted flight paths are extracted as the affected areas. Based on historical hovering periods and vibration intensity and weighting data, a linear regression model is constructed to fit the vibration relationship expression.

[0141] The vibration intensity is predicted by comparing multiple schemes (using virtual sensor weight combinations), and the optimal scheme is selected as the adjustment scheme.

[0142] In the specific implementation process, a data-driven vibration prediction model is established; a sensor weight optimization scheme is dynamically generated to minimize the vibration of the aircraft in a specific area and improve flight stability.

[0143] The drive management module is used to fit different types of virtual sensors inside the UAV and adjust the weights of different types of virtual sensors according to the adjustment scheme during flight.

[0144] In the specific implementation process, physical sensors of the same type are weighted and fused into a single virtual sensor, and the weight allocation of different adjustment schemes is switched in real time according to the influence area, so as to realize the dynamic adjustment of the weight of multiple virtual sensors during flight.

[0145] Sensor fusion reduces noise interference; real-time response to environmental changes and adaptive optimization of sensor data fusion strategies enhance the anti-disturbance capability and control precision of UAVs.

[0146] Each module forms a closed-loop data flow: the perception layer collects basic data → the analysis layer locates the interference area → the decision layer generates a weight scheme → the execution layer dynamically drives and debugs the system to achieve environmental adaptive flight control.

[0147] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0148] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A UAV-driven data management method based on environmental parameters, characterized in that: The method includes: S100: Collect GIS maps and scanned data of the designated area, as well as the operating parameters and environmental parameters of each UAV; S200. Construct a three-dimensional airflow field based on environmental parameters, and analyze the hovering position and dwell time of the UAV; divide the sampling area in the three-dimensional airflow field and analyze the changes in operating parameters during the dwell time, calculate the stability coefficient, and set the interference zone; specifically including: S201. Obtain environmental and operational parameters collected in real time by different UAVs, and extract terrain elevation and surface feature information by combining GIS maps and scanning data; S202. The model is simplified by using the Kriging spatial interpolation algorithm and the Navier-Stokes equation. The three-dimensional airflow field is simulated and updated in real time by integrating discrete point data with the CFD physical simulation model. S203, Analyze past duration Within the data, the hovering positions and durations of each drone are recorded; hovering positions with a duration exceeding a threshold are marked, and sampling areas are defined in a three-dimensional airflow field using the marked hovering positions as the centers; specifically including: S2031, Acquiring a Drone At the marker hover position Duration of stay In terms of duration Evenly distributed inside A point in time; S2032. Analyze the drone at each time point. Collect wind speed from environmental parameters and calculate the standard deviation of wind speed at all time points. and average Preset base distance Then substitute the values ​​into the formula to calculate the distance of influence. : ； In the formula, The preset reference wind speed standard deviation, It is a constant greater than 1. This is the preset reference wind speed; S2033, Mark the hover position The center of the ball affects the distance. Using a radius of 1, a spherical region is defined in the three-dimensional airflow field as the sampling area; the influence distance of each marker hovering position is calculated, and the sampling area is defined accordingly. S204. Merge intersecting sampling areas and analyze the changes in operating parameters during the dwell time at different marker hovering positions within the sampling areas; calculate the stability coefficient of each sampling area and set the interference zone based on the stability coefficient; specifically including: S2041. Determine whether different sampling areas overlap, and merge all overlapping sampling areas; obtain the dwell time of different marker hovering positions within the sampling area, and analyze the start time. and end time ; S2042. Analyze the vibration intensity of the UAV at each time point and calculate the standard deviation of the vibration intensity at all time points. and average Get the current time Substitute into the formula to calculate the stability coefficient of each sampling area. : ； In the formula, The number of hover positions marked in the sampling area. and These are the preset standard deviation of the reference vibration intensity and the reference vibration intensity, respectively; and The first The start and end times of the period during which the marker hovers at its position; and The first The standard deviation and mean of vibration intensity at all time points at each marker hovering position; S2043. Calculate the stability coefficient of each sampling area and take the sampling area with a stability coefficient less than the threshold as the interference area. S300. The interference area traversed by the UAV's flight path is taken as the affected area. The relationship expression of each affected area is fitted and analyzed. Different schemes are established, and the predicted vibration intensity of each scheme is calculated by combining the relationship expression and the adjustment scheme is set. The S400 and the UAV combine multiple sensors of the same model into a single virtual sensor, and adjust the weights of different virtual sensors in real time according to the adjustment scheme during flight.

2. The UAV-driven data management method based on environmental parameters according to claim 1, characterized in that: In S100, scan data refers to the three-dimensional physical space data within a specified airspace obtained through multi-source sensing devices. The operating parameters include flight trajectory, spatial position, vibration intensity, and weight allocation; the flight trajectory refers to a preset track that simultaneously has a time node sequence and a spatial coordinate sequence; Vibration intensity refers to the degree of intensity of vibration generated by the drone's body during flight; Weight allocation refers to the real-time weight allocation data of different types of virtual sensors during the flight of the UAV; the virtual sensors are obtained by fitting multiple sensors of the same type inside the UAV; Environmental parameters refer to the meteorological indicators of the surrounding environment collected by the drone through various sensors.

3. The UAV-driven data management method based on environmental parameters according to claim 1, characterized in that: The S300 includes: S301. Obtain the flight trajectory from the operating parameters of each UAV, extract the flight trajectory of the unflying part and map it into the three-dimensional airflow field, and take the interference area crossed by the flight trajectory as the influence area. S302. Analyze the dwell time corresponding to each marker hovering position in the affected area, obtain the vibration intensity and weight distribution changes of the corresponding UAVs during the dwell time, and obtain the vibration relationship expression of each affected area through fitting analysis. S303, Establish for each affected area There are several schemes, each with weights set for different types of virtual sensors. The weights of all virtual sensors in different schemes are not exactly the same. S304. Extract the weights of each virtual sensor in each scheme and substitute them into the vibration relationship expression to calculate the predicted vibration intensity; select the scheme with the minimum predicted vibration intensity as the adjustment scheme for the corresponding influence area.

4. The UAV-driven data management method based on environmental parameters according to claim 3, characterized in that: S302 includes: S3021. Analyze the dwell time corresponding to each marker hovering position in the affected area, and obtain the vibration intensity and weight distribution changes of the corresponding UAVs during the dwell time. S3022, Divide the weighted allocation duration into each dwell period. The average vibration intensity is calculated based on the changes in vibration intensity within a time period that remains unchanged. S3023. Calculate the total number of all time periods within all periods of stay. The average vibration intensity of each time period is used as the dependent variable, and the weights of all virtual sensors are used as independent variables and packaged into samples. S3024, Set intercept and regression coefficients And establish a linear regression model; The independent variables in each sample are used as input values. The output value of each sample The difference between the dependent variable and the differential variable is used as the difference coefficient; the expression is as follows: ； S3025. Adjust the intercept and regression coefficients until the sum of the difference coefficients of all samples is minimized to obtain the fitted vibration relationship expression; and so on, fit the vibration relationship expression for each influence area.

5. The UAV-driven data management method based on environmental parameters according to claim 3, characterized in that: The S400 includes: S401. Multiple physical sensors of the same model inside the UAV are fitted into a single virtual sensor through a weighted average algorithm, forming multiple virtual sensors of different models. S402. During flight, monitor the spatial position of the UAV in real time. When the spatial position is in the affected area, control the virtual sensors inside the UAV to drive and debug according to the weights in the corresponding adjustment scheme.

6. An unmanned aerial vehicle (UAV) driven data management system based on environmental parameters, applied to the UAV driven data management method based on environmental parameters as described in claim 1, characterized in that: The system includes a dynamic sensing module, an interference analysis module, an operation setting module, and a drive management module; The dynamic sensing module is used to collect GIS maps and scanned data of a designated area, as well as the operating parameters and environmental parameters of each UAV. The interference analysis module is used to construct a three-dimensional airflow field, divide the sampling area in the three-dimensional airflow field, analyze the changes in the operating parameters of the UAV when hovering in the sampling area, calculate the stability coefficient and set the interference area; The operation setting module is used to analyze the interference area and set the influence area, and fit the relationship expression of each influence area; different schemes are established, and the adjustment scheme is set in combination with the relationship expression. The drive management module is used to fit different types of virtual sensors inside the UAV and adjust the weights of different types of virtual sensors according to the adjustment scheme during flight.

Images