Unmanned aerial vehicle power efficiency regulation management system and method based on real-time working condition identification

Abstract

This invention relates to the field of energy regulation and management technology, specifically disclosing a UAV power efficiency regulation and management system and method based on real-time operating condition identification. This invention acquires UAV flight status perception data in real time through airborne sensors, performs preprocessing to obtain flight status perception features, constructs a flight deviation analysis model to obtain flight deviation features, sorts the flight deviation features in chronological order based on a time-series model to obtain a flight deviation time series, builds a UAV control accuracy evaluation strategy based on the flight deviation time series, evaluates the control accuracy of the UAV during flight, establishes a power demand mapping relationship, filters sensitive flight states based on the power demand mapping relationship, extracts flight deviation features of sensitive flight states, and determines the sensitizing factors based on the flight deviation features. This invention can achieve differentiated energy efficiency regulation of the UAV flight process, improving the UAV's adaptability and robustness.

Description

Technical Field

[0001] This invention relates to the field of energy regulation and management technology, and more specifically, to a power efficiency regulation and management system and method for unmanned aerial vehicles (UAVs) based on real-time operating condition identification. Background Technology

[0002] In current UAV-based surveying and modeling applications, especially in scenarios such as terrain mapping, engineering modeling, and 3D reconstruction, a grid-based flight approach with pre-defined flight paths is typically used to systematically collect data from the target area. This data is then processed using photogrammetry and 3D reconstruction tools such as COLMAP to generate high-precision point cloud models or 3D structures. However, in practical applications, existing technologies still have significant shortcomings in flight control and power management.

[0003] Existing UAV flight control systems are mostly based on preset trajectories and fixed parameter control strategies, focusing on path tracking accuracy while paying insufficient attention to the changes in power demand under different operating conditions during flight. This is particularly true during the "turnaround flight" phase in gridded flight paths, where UAVs need to frequently decelerate, turn, and re-accelerate, exhibiting significant nonlinear and time-varying motion characteristics. In this process, the power demand of UAVs at different flight stages has distinct phased and transient characteristics. Traditional fixed or delayed response power control methods cannot accurately match these changes or analyze the main causes in a timely manner. Therefore, in practical applications, this manifests as energy waste and sluggish response, potentially causing the UAV to deviate from its intended flight path.

[0004] Therefore, it is necessary to provide a UAV power efficiency regulation and management system and method based on real-time operating condition identification to solve the above-mentioned technical problems. In order to solve the above problems, a technical solution is provided. Summary of the Invention

[0005] To overcome the aforementioned deficiencies in the prior art, this invention provides a UAV power efficiency control and management system and method based on real-time operating condition identification, which is used to solve the problem of mismatch between the nonlinear time-varying operating conditions and power control capabilities of gridded flight paths during the turnaround phase in existing UAV mapping and modeling, resulting in energy efficiency loss and response lag.

[0006] To achieve the above objectives, the present invention provides the following technical solution: The UAV power efficiency regulation and management system based on real-time operating condition identification includes a flight status perception data acquisition module, a flight deviation analysis module, a UAV control accuracy evaluation module, and a sensitive factor determination module. The flight status perception data acquisition module is used to acquire the flight status perception data of the UAV in real time through airborne sensors, and to preprocess the flight status perception data to obtain flight status perception features. The flight deviation analysis module is used to construct a flight deviation analysis model based on real-time flight status perception features and preset flight status perception features, obtain flight deviation features, and sort the flight deviation features in time order based on the time series model to obtain the flight deviation time series. The UAV control accuracy assessment module is used to build a UAV control accuracy assessment strategy based on the flight deviation time series, assess the control accuracy of the UAV during flight, and establish a power demand mapping relationship by combining flight status perception characteristics and UAV flight status. The sensitive factor determination module is used to screen sensitive flight states based on the power demand mapping relationship, extract flight deviation characteristics of sensitive flight states, and determine the sensitive factors based on the flight deviation characteristics.

[0007] As a further aspect of the present invention, the flight status perception data includes the UAV's trajectory perception data, attitude perception data, and energy consumption perception data. Trajectory perception data includes drone location data; Attitude perception data includes UAV attitude angle data; UAV attitude angle data includes roll angle, pitch angle, and yaw angle. Energy consumption sensing data includes drone energy consumption data.

[0008] As a further aspect of the present invention, the flight deviation features include trajectory deviation features and attitude deviation features; the flight deviation time series includes trajectory deviation time series and attitude deviation time series.

[0009] As a further aspect of the present invention, a flight deviation analysis model is constructed based on real-time flight status perception features and preset flight status perception features to obtain flight deviation features, as detailed below: Real-time trajectory perception data and real-time attitude perception data are extracted based on real-time flight status perception features, and preset trajectory perception data and preset attitude perception data are extracted based on preset flight status perception features. A first-class flight deviation analysis model is built based on real-time trajectory perception data and preset trajectory perception data to obtain trajectory deviation characteristics. Then, a second-class flight deviation analysis model is built based on real-time attitude perception data and preset attitude perception data to obtain attitude deviation characteristics.

[0010] As a further aspect of the present invention, a UAV control accuracy evaluation strategy is established based on the flight deviation time series to evaluate the control accuracy of the UAV during flight. The specific UAV control accuracy evaluation strategy is as follows: Extract the trajectory deviation time series and attitude deviation time series respectively; After preprocessing the trajectory deviation time series and attitude deviation time series, a UAV control accuracy evaluation model is constructed to obtain control accuracy evaluation coefficients.

[0011] As a further aspect of the present invention, a power demand mapping relationship is established by combining flight state perception features and UAV flight state, specifically as follows: Extract energy consumption perception data from flight status perception features, calculate the difference between preset energy consumption perception data and real-time energy consumption perception data, and use it as the energy consumption deviation value; A power demand mapping relationship is established based on control accuracy evaluation coefficients, energy consumption deviation values, and UAV flight status. ,in, Let be the control accuracy evaluation coefficient at time t. Let be the energy consumption deviation value at time t. Let t represent the UAV's flight state at time t.

[0012] As a further aspect of the present invention, sensitive flight states are screened based on the power demand mapping relationship, specifically by: obtaining the power demand mapping relationship and extracting the UAV flight state. The corresponding control accuracy evaluation coefficient and energy consumption deviation value are compared with their respective thresholds, and the results are used to screen sensitive flight states. As a further aspect of this invention, the screening of sensitive flight states specifically involves: obtaining the control accuracy evaluation coefficient and energy consumption deviation value; comparing the control accuracy evaluation coefficient with a preset accuracy evaluation threshold; and marking the corresponding UAV flight state if the control accuracy evaluation coefficient is greater than or equal to the preset accuracy evaluation threshold. This is a type of flight state; if the control accuracy evaluation coefficient is less than the preset accuracy evaluation threshold, then no marking is required. The energy consumption deviation value is compared with a preset energy consumption deviation threshold. If the energy consumption deviation value is greater than or equal to the preset energy consumption deviation threshold, the corresponding drone flight status is marked. This is a Category II flight state; if the energy consumption deviation value is less than the preset energy consumption deviation threshold, no marking is required. If the drone is in flight status If a drone is simultaneously marked as both a Class I and Class II flight state, its flight state will be uniformly marked as a sensitive flight state; otherwise, no marking is required.

[0013] As a further aspect of the present invention, flight deviation characteristics of sensitive flight states are extracted, and sensitizing factors are determined based on the flight deviation characteristics, specifically as follows: The trajectory deviation features and attitude deviation features corresponding to the sensitive flight state are obtained. The trajectory deviation features and attitude deviation features are compared with the preset deviation thresholds. If the trajectory deviation features are greater than or equal to the preset trajectory deviation thresholds, the trajectory deviation is a sensitive factor; otherwise, it is not a sensitive factor. If the attitude deviation characteristic is greater than or equal to the preset attitude deviation threshold, then the attitude deviation is a sensitive factor; otherwise, it is not a sensitive factor.

[0014] The specific steps of the UAV power efficiency regulation and management method based on real-time operating condition identification are as follows: The flight status perception data of the UAV is acquired in real time by airborne sensors. The flight status perception data is preprocessed to obtain flight status perception features. A flight deviation analysis model is constructed based on the real-time flight status perception features and preset flight status perception features to obtain flight deviation features. The flight deviation features are sorted in time order based on the time series model to obtain the flight deviation time series. A control accuracy assessment strategy for unmanned aerial vehicles (UAVs) is developed based on flight deviation time series to assess the control accuracy of the UAV during flight. A power demand mapping relationship is established by combining flight state perception characteristics and UAV flight state. Sensitive flight states are screened based on the power demand mapping relationship, flight deviation characteristics of sensitive flight states are extracted, and factors causing sensitivity are determined based on the flight deviation characteristics.

[0015] The technical effects and advantages of this invention, a UAV power efficiency control management system and method based on real-time operating condition identification, are as follows: This invention obtains high-precision flight state perception features through multi-source sensor data fusion, effectively reducing the uncertainty caused by single sensor errors and improving the reliability and real-time performance of state perception. Through a flight deviation analysis module, trajectory and attitude deviations are quantitatively modeled and time-seriesed, comprehensively reflecting the dynamic deviation change trend during flight, thus providing a data foundation for subsequent evaluation. By weighted fusion of deviation features, a unified control accuracy evaluation index is formed, and a power demand mapping relationship is established in conjunction with different flight conditions, enabling differentiated energy efficiency control for different stages, such as turning or cruising. This invention, through screening and causal analysis of sensitive flight states, can accurately identify key factors leading to decreased control accuracy and abnormal energy consumption, such as trajectory or attitude deviations, avoiding the shortcomings of traditional methods that rely solely on overall indicators and struggle to pinpoint the root cause of problems, thereby supporting more targeted control strategy optimization. This invention can identify critical stages of high energy consumption and low precision in real time during flight and intervene in advance, such as adjusting control parameters or optimizing flight paths, effectively reducing unnecessary energy consumption, extending the flight time of UAVs, and improving flight stability and mission execution accuracy. Attached Figure Description

[0016] Figure 1 A schematic diagram of the structure of the UAV power efficiency regulation and management system based on real-time operating condition identification provided in an embodiment of the present invention; Figure 2This is a flowchart illustrating the UAV power efficiency regulation and management method based on real-time operating condition identification, as provided in an embodiment of the present invention. Detailed Implementation

[0017] The technical solutions of this invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described technical solutions are only a part of this invention, and not all of it. All other technical solutions obtained by those skilled in the art based on the technical solutions of this invention without inventive effort are within the scope of protection of this invention. Example

[0018] like Figure 1 The diagram shown is a structural schematic of the UAV power efficiency regulation and management system based on real-time operating condition identification provided in an embodiment of the present invention. The UAV power efficiency regulation and management system based on real-time operating condition identification includes a flight state perception data acquisition module, a flight deviation analysis module, a UAV control accuracy evaluation module, and a sensitive factor determination module. The flight state perception data acquisition module is connected to the flight deviation analysis module, the flight deviation analysis module is connected to the UAV control accuracy evaluation module, and the UAV control accuracy evaluation module is connected to the sensitive factor determination module. The flight status perception data acquisition module is used to acquire the flight status perception data of the UAV in real time through airborne sensors, and to preprocess the flight status perception data to obtain flight status perception features. The flight status perception data includes the UAV's trajectory perception data, attitude perception data, and energy consumption perception data. Specifically, the preprocessing of the flight status perception data involves using Kalman filtering or complementary filtering to fuse the data and construct unified flight status perception features.

[0019] The flight deviation analysis module is used to construct a flight deviation analysis model based on real-time flight status perception features and preset flight status perception features, obtain flight deviation features, and sort the flight deviation features in chronological order based on the time series model to obtain the flight deviation time series; the flight deviation features include trajectory deviation features and attitude deviation features; the flight deviation time series includes trajectory deviation time series and attitude deviation time series; the UAV control accuracy evaluation module is used to build a UAV control accuracy evaluation strategy based on the flight deviation time series, evaluate the control accuracy of the UAV during flight, and establish a power demand mapping relationship by combining flight status perception features and UAV flight status; The sensitive factor determination module is used to screen sensitive flight states based on the power demand mapping relationship, extract flight deviation characteristics of sensitive flight states, and determine the sensitive factors based on the flight deviation characteristics.

[0020] It is important to emphasize that all parameters and data involved in the calculation have undergone preprocessing operations, including normalization.

[0021] Preferably, the flight status perception data includes the UAV's trajectory perception data, attitude perception data, and environmental perception data; Trajectory perception data includes drone location data; Attitude perception data includes UAV attitude angle data; UAV attitude angle data includes roll angle, pitch angle, and yaw angle. Energy consumption sensing data includes drone energy consumption data.

[0022] In one embodiment of the present invention, during power line inspection, the UAV, while flying along a preset route, acquires trajectory perception data in real time through its onboard GPS and visual positioning module to characterize the spatial position deviation of the UAV relative to the target line. Simultaneously, it continuously collects attitude perception data, including roll angle, pitch angle, and yaw angle, through an IMU (Inertial Measurement Unit), reflecting changes in the UAV's attitude stability under complex airflow or turning conditions. Furthermore, it synchronously acquires environmental perception data such as wind speed, wind direction, and temperature through environmental sensors to characterize the impact of external disturbances on the flight state. Based on this, and combined with energy consumption perception data collected in real time by the power management module, such as instantaneous power, battery voltage, current, and cumulative energy consumption, a correlation model between flight state and energy consumption is constructed.

[0023] Preferably, a flight deviation analysis model is constructed based on real-time flight status perception features and preset flight status perception features to obtain flight deviation features, as follows: Real-time trajectory perception data and real-time attitude perception data are extracted based on real-time flight status perception features, and preset trajectory perception data and preset attitude perception data are extracted based on preset flight status perception features. A first-class flight deviation analysis model is built based on real-time trajectory perception data and preset trajectory perception data to obtain trajectory deviation characteristics. Then, a second-class flight deviation analysis model is built based on real-time attitude perception data and preset attitude perception data to obtain attitude deviation characteristics.

[0024] It should be noted that the calculation formula for one type of flight deviation analysis model is as follows: In the formula: Trajectory deviation characteristics The preset UAV position data at time t. Here is the real-time drone location data at time t. The preset UAV position data at time t-1 This is the real-time drone location data at time t-1.

[0025] The calculation formula for the Type II flight deviation analysis model is as follows: In the formula: This represents the characteristics of attitude deviation. Let i be the preset UAV attitude angle data for the i-th term at time t. Let be the real-time UAV attitude angle data for the i-th term at time t. For the preset UAV attitude angle data of the i-th term at time t-1, This represents the real-time UAV attitude angle data for the i-th term at time t-1; Set one of the following for time t: roll angle, pitch angle, or yaw angle.

[0026] In one embodiment of the present invention, a flight deviation analysis model is embedded in the UAV flight control system or ground monitoring platform to achieve dynamic evaluation and feedback control of flight deviations. Specifically, firstly, preset flight state perception features are generated based on the mission plan, including preset trajectory perception data, i.e., the three-dimensional path point sequence corresponding to the planned route, and preset attitude perception data, i.e., the expected roll angle, pitch angle, and heading angle at each path point.

[0027] During mission execution, the UAV acquires its current flight status in real time through GPS positioning and IMU sensors, generating real-time trajectory perception data and real-time attitude perception data. Subsequently, at each instant, the real-time trajectory points are matched with preset trajectory points. Based on a type I flight deviation analysis model, trajectory deviation characteristics are calculated. By analyzing the ratio of the trajectory deviation at the current instant to that at the previous instant, the trend of the UAV deviating from the preset path is reflected. If the trajectory deviation characteristic is greater than 1, it indicates that the trajectory deviation is increasing, and the flight trajectory is gradually deviating from the planned route, possibly due to wind disturbance or control lag. Simultaneously, using a type II flight deviation analysis model, the real-time attitude angles are compared with the corresponding preset attitude angles to calculate attitude deviation characteristics, which characterize changes in the UAV's attitude stability. When the attitude deviation characteristic is significantly greater than 1, it indicates that the attitude error is amplified, potentially indicating unstable attitude control or increased external disturbances. Based on the aforementioned trajectory deviation and attitude deviation characteristics, the system can further construct flight deviation assessment indicators and identify abnormal flight phases by combining threshold judgment mechanisms. For example, when entering a "high deviation sensitive phase" in a strong crosswind environment, the system can automatically trigger control strategy adjustments, such as increasing attitude control gain, reducing flight speed, or replanning local routes, thereby achieving real-time optimization of flight path accuracy and attitude stability, and improving the safety and energy efficiency of mission execution.

[0028] Preferably, a UAV control accuracy evaluation strategy is established based on the flight deviation time series to evaluate the control accuracy of the UAV during flight. The specific UAV control accuracy evaluation strategy is as follows: Extract trajectory deviation time series respectively and attitude deviation time series Where T is the flight time of the drone; After preprocessing the trajectory deviation time series and attitude deviation time series, a UAV control accuracy evaluation model is constructed to obtain control accuracy evaluation coefficients.

[0029] The formula for the UAV control accuracy evaluation model is as follows: In the formula: Let be the control accuracy evaluation coefficient at time t. The dynamic weighting coefficient for trajectory deviation. This represents the dynamic weighting coefficient for attitude deviation.

[0030] In one embodiment of the present invention, during actual UAV fine inspection or complex environment mapping tasks, a control accuracy evaluation strategy is constructed based on the deviation time series of the entire flight process to achieve dynamic quantitative evaluation of UAV control performance. Specifically, during the mission execution, the UAV continuously records the trajectory deviation characteristics and attitude deviation characteristics at each moment, forming trajectory deviation time series and attitude deviation time series respectively. Subsequently, preprocessing operations are performed on the two types of time series, including outlier removal, normalization, and sliding window smoothing, to eliminate the impact of sensor noise and sudden interference on the evaluation results.

[0031] Based on this, a UAV control accuracy evaluation model is constructed, and the control accuracy evaluation coefficient is calculated at each time t. The weight coefficient can be dynamically adjusted according to the task scenario. For example, in the route inspection task with high path accuracy requirements, the dynamic weight coefficient of trajectory deviation is increased, while in the hovering detection task with high attitude stability requirements, the dynamic weight coefficient of attitude deviation is increased.

[0032] By analyzing the changes in the control accuracy evaluation coefficient over time, the control accuracy level of the UAV can be assessed in real time: when the control accuracy evaluation coefficient remains at a low level, it indicates high flight control accuracy and stable system operation; when the control accuracy evaluation coefficient shows a continuous increase or drastic fluctuation, it indicates a decrease in UAV control accuracy, which may be affected by factors such as wind field disturbances, control parameter mismatch, or power response lag. Furthermore, a control accuracy level classification mechanism can be constructed based on the control accuracy evaluation coefficient, dividing the flight process into high-precision, general-precision, and low-precision sensitive stages. Adaptive control strategies can be triggered in the low-precision stage, such as adjusting PID parameters, optimizing thrust distribution, or reducing flight speed, thereby achieving closed-loop optimization of UAV flight control performance and improving the overall safety and stability of mission execution.

[0033] Preferably, a power demand mapping relationship is established by combining flight status perception features and UAV flight status. Specifically, energy consumption perception data is extracted from the flight status perception features, and the difference between preset energy consumption perception data and real-time energy consumption perception data is calculated as the energy consumption deviation value. A power demand mapping relationship is established based on control accuracy evaluation coefficients, energy consumption deviation values, and UAV flight status. ,in, Let be the energy consumption deviation value at time t. Let t represent the UAV's flight state at time t; the UAV's flight state includes the constant speed cruise phase, the curve entry phase, the curve turning phase, and the curve exit phase.

[0034] Preferably, sensitive flight states are screened based on the power demand mapping relationship, specifically by: obtaining the power demand mapping relationship. Extracting the flight status of the drone The corresponding control accuracy evaluation coefficient and energy consumption deviation value are compared with their respective thresholds. Sensitive flight states are then selected based on the comprehensive comparison results. Specifically, the selection of sensitive flight states involves: obtaining the control accuracy evaluation coefficient and energy consumption deviation value; comparing the control accuracy evaluation coefficient with a preset accuracy evaluation threshold; and marking the corresponding UAV flight state if the control accuracy evaluation coefficient is greater than or equal to the preset accuracy evaluation threshold. This is a type of flight state; if the control accuracy evaluation coefficient is less than the preset accuracy evaluation threshold, then no marking is required. The energy consumption deviation value is compared with a preset energy consumption deviation threshold. If the energy consumption deviation value is greater than or equal to the preset energy consumption deviation threshold, the corresponding drone flight status is marked. This is a Category II flight state; if the energy consumption deviation value is less than the preset energy consumption deviation threshold, no marking is required. If the drone is in flight status If a drone is simultaneously marked as both a Class I and Class II flight state, its flight state will be uniformly marked as a sensitive flight state; otherwise, no marking is required.

[0035] In one embodiment of the present invention, the power demand mapping relationship and the sensitive flight state screening mechanism are integrated into the UAV intelligent flight control and energy management system to achieve collaborative analysis and dynamic optimization of "control accuracy—energy consumption—flight conditions". Specifically, during mission execution, the UAV first collects energy consumption perception data in real time through the power management module and compares it with the preset energy consumption perception data obtained during the mission planning phase. The energy consumption deviation value at each moment is calculated to characterize the degree of deviation of the current flight energy consumption from the ideal state. Simultaneously, the control accuracy evaluation coefficient is calculated in real time using the aforementioned method. Based on flight trajectory characteristics and attitude changes, the current flight phase is divided into a constant speed cruise phase, a curve entry phase, a turn phase, or a curve exit phase, forming corresponding flight states, thereby constructing a power demand mapping relationship. The system further analyzes the mapping relationship at each moment to screen out sensitive flight states that significantly affect control and energy consumption. Specifically, at each moment, the control accuracy evaluation coefficient is compared with the preset accuracy evaluation threshold. When the control accuracy evaluation coefficient is greater than or equal to the threshold, it indicates that the current flight control accuracy is low or there is a trend of deviation amplification. The corresponding flight state is then marked as a Class I flight state. At the same time, the energy consumption deviation value is compared with the preset energy consumption deviation threshold. When the energy consumption deviation value is greater than or equal to the threshold, it indicates that the current energy consumption is significantly higher than expected. The corresponding flight state is then marked as a Class II flight state.

[0036] If a flight state simultaneously meets both of the above-mentioned marking conditions, it is uniformly classified as a sensitive flight state. For example, in practical applications, when a UAV is in a "turning phase," if crosswind interference causes an increase in trajectory deviation, the control accuracy evaluation coefficient rises. Simultaneously, to maintain attitude stability, the motor output power is increased, leading to an increase in energy consumption deviation. Therefore, this turning phase will be identified as a sensitive flight state. For identified sensitive flight states, adaptive power scheduling and control optimization strategies can be further triggered, such as pre-allocating higher power redundancy, optimizing attitude control parameters, or adjusting flight speed and turning radius, thereby reducing deviation accumulation and suppressing abnormal energy consumption growth. For unmarked ordinary flight states, conventional control strategies are maintained to ensure optimal overall energy efficiency. Through this invention, refined modeling and dynamic control of the power requirements of UAVs under different flight conditions can be achieved, effectively improving flight control accuracy and energy utilization efficiency, and is particularly suitable for high-reliability mission execution in complex environments.

[0037] Preferably, flight deviation characteristics of sensitive flight states are extracted, and sensitizing factors are determined based on these characteristics, specifically as follows: The trajectory deviation features and attitude deviation features corresponding to sensitive flight states are obtained. The trajectory deviation features and attitude deviation features are compared with preset deviation thresholds. If the trajectory deviation features are greater than or equal to the preset trajectory deviation thresholds, the trajectory deviation is a sensitive factor; otherwise, it is not a sensitive factor. If the attitude deviation features are greater than or equal to the preset attitude deviation thresholds, the attitude deviation is a sensitive factor; otherwise, it is not a sensitive factor.

[0038] In one embodiment of the present invention, after identifying a sensitive flight state, its causes can be further analyzed in detail to achieve targeted control optimization. Specifically, when the system determines that the flight state at a certain moment is a sensitive flight state, it retrieves the trajectory deviation features and attitude deviation features corresponding to that moment and compares them with preset trajectory deviation thresholds and attitude deviation thresholds, respectively. If the trajectory deviation features are greater than or equal to the trajectory deviation thresholds, it indicates that the path tracking error is significant during the current flight process and is the main factor causing the sensitive state; in this case, the trajectory deviation is determined to be the causative factor. Conversely, if the trajectory deviation features are less than or equal to the thresholds, it is considered that the trajectory deviation contributes little to the current sensitive state.

[0039] Similarly, by comparing the attitude deviation characteristics with the attitude deviation threshold, if the characteristics are greater than or equal to the threshold, it indicates that the attitude control of the UAV is unstable or significantly affected by external disturbances. In this case, the attitude deviation is identified as a sensitive factor.

[0040] Through the above-mentioned dual-dimensional judgment mechanism, different types of causes can be distinguished under the same sensitive flight conditions. For example, in the turning phase, if the trajectory deviation is large and the attitude deviation is small, it can be judged that the path planning or navigation error is dominant; while if the attitude deviation is significant and the trajectory deviation is relatively small, it is more likely to be attitude instability caused by wind disturbance or mismatch of control parameters.

[0041] Based on the identification results of sensitive factors, the system can further implement differentiated control strategies. For example, it can optimize the path tracking algorithm or enhance the positioning accuracy when the trajectory deviation is dominant, and adjust the attitude control gain or improve the dynamic response when the attitude deviation is dominant, thereby achieving precise intervention and targeted improvement of control performance in sensitive flight states.

[0042] Example 2: In one embodiment of the present invention, the UAV power efficiency control and management system based on real-time operating condition identification is used in actual UAV intelligent inspection and autonomous operation scenarios. This system is deployed in the collaborative platform between the UAV flight control computing unit and the ground station to achieve closed-loop management of flight status, control accuracy, and energy efficiency throughout the entire process. Specifically, the flight status perception data acquisition module uses onboard multi-source sensors to collect real-time trajectory perception data, attitude perception data, and energy consumption perception data of the UAV. Kalman filtering or complementary filtering is then used to fuse the multi-source data, eliminating noise interference and measurement errors, and constructing unified flight status perception features to comprehensively characterize the UAV's spatial position, attitude changes, and energy consumption at the current moment.

[0043] The flight deviation analysis module compares the preset flight state perception features generated during the mission planning phase with the real-time acquired flight state perception features, and constructs trajectory deviation analysis models and attitude deviation analysis models respectively. It calculates the trajectory deviation features and attitude deviation features, and arranges the deviation features at each moment in chronological order through time-series modeling methods, such as sliding window or recursive update mechanism, to form trajectory deviation time series and attitude deviation time series, thereby reflecting the deviation evolution trend of the UAV throughout the entire flight process.

[0044] The UAV control accuracy assessment module constructs a control accuracy assessment strategy based on the aforementioned flight deviation time series. It calculates the control accuracy assessment coefficient at each moment by weighted fusion of trajectory deviation and attitude deviation, and identifies the current flight condition by combining flight state perception features, such as constant speed cruise, entering a curve, turning or exiting a curve. It further establishes a power demand mapping relationship to achieve a quantitative description of the coupling relationship between control accuracy and energy consumption under different flight conditions.

[0045] The sensitivity factor determination module, based on the constructed power demand mapping relationship, performs threshold judgments on the control accuracy evaluation coefficient and energy consumption deviation, screening out sensitive flight states that simultaneously exhibit decreased control accuracy and abnormally increased energy consumption. For these sensitive flight states, corresponding trajectory deviation features and attitude deviation features are extracted and compared with preset deviation thresholds to identify the dominant factors causing the current sensitive state, such as trajectory deviation or attitude deviation. For example, in practical applications, when a UAV performs a surround detection task around a wind turbine, if trajectory deviation frequently exceeds limits and energy consumption increases significantly during the turning phase, the system can determine that this phase is a sensitive flight state and further identify trajectory deviation as the main sensitivity factor, thereby triggering path tracking optimization or navigation accuracy improvement strategies. If attitude deviation is dominant, attitude control parameters can be adjusted or anti-disturbance control capabilities can be enhanced. This embodiment of the invention can not only identify high-risk and high-energy-consumption flight phases in real time, but also implement differentiated control strategies for different sensitivity factors, thereby significantly improving the flight stability, control accuracy, and energy utilization efficiency of UAVs under complex operating conditions.

[0046] In another embodiment of the present invention, a drone power efficiency control and management system based on real-time operating condition identification is deployed in a logistics delivery drone and cloud scheduling scenario to achieve intelligent control over the entire delivery process. For example, during the delivery of packages from a delivery station to multiple users, the flight status perception data acquisition module collects real-time data such as the drone's trajectory position, attitude angle, and power consumption through onboard GPS, IMU, and battery management system, and performs fusion processing through Kalman filtering to obtain stable and reliable flight status perception features; the flight deviation analysis module compares the real-time flight data with the pre-planned delivery route and attitude parameters, calculates the trajectory deviation and attitude deviation, and constructs the corresponding time series to reflect the drone's flight deviation in complex urban environments.

[0047] The UAV control accuracy assessment module calculates control accuracy assessment coefficients based on deviation time series and, combined with typical flight conditions during the delivery process, such as takeoff and climb, constant speed cruise, turning and obstacle avoidance, and landing and delivery, establishes a power demand mapping relationship to identify energy efficiency variation characteristics under different conditions. For example, if control accuracy decreases and energy consumption increases significantly when turning around buildings or avoiding obstacles, this stage may be identified as a high power demand stage. The sensitive factor determination module further analyzes these sensitive flight states. By comparing the relationship between trajectory deviation and attitude deviation with their respective thresholds, it determines whether the increased energy consumption is caused by path tracking error or attitude instability. For example, when the wind corridor effect between tall buildings is significant, it often manifests as a sensitive state dominated by attitude deviation.

[0048] Based on the above embodiments, the system can adjust its flight strategy in real time. For example, it can reduce flight speed, optimize turning radius, or enhance attitude control parameters during sensitive turning phases, while prioritizing low-energy cruise mode during long-distance cruise phases. This ensures timely delivery while reducing overall energy consumption. Furthermore, the cloud-based scheduling platform can continuously optimize delivery route planning based on historical flight data, avoiding high-energy-consumption sensitive areas. These embodiments of the invention can improve the safety and stability of drone logistics delivery, significantly enhance energy efficiency and endurance, and reduce operating costs, demonstrating strong practical application value.

[0049] Example 3: The specific steps of the UAV power efficiency regulation and management method based on real-time operating condition identification are as follows: Step S1: Acquire flight status perception data of the UAV in real time through airborne sensors, and preprocess the flight status perception data to obtain flight status perception features. Step S2: Construct a flight deviation analysis model based on real-time flight status perception features and preset flight status perception features, obtain flight deviation features, and sort the flight deviation features in time order based on the time series model to obtain the flight deviation time series. Step S3: Build a UAV control accuracy assessment strategy based on the flight deviation time series, assess the control accuracy of the UAV during flight, and establish a power demand mapping relationship by combining flight status perception characteristics and UAV flight status. Step S4: Based on the power demand mapping relationship, screen sensitive flight states, extract flight deviation characteristics of sensitive flight states, and determine the factors causing sensitivity based on the flight deviation characteristics.

[0050] like Figure 2 The diagram shown is a flowchart illustrating the UAV power efficiency control and management method based on real-time operating condition identification according to an embodiment of the present invention, which can be used to execute... Figure 1 The steps in the method embodiments shown are implemented in a similar manner and have similar technical effects, and will not be repeated here.

[0051] Through the above embodiments, this invention obtains high-precision flight status perception features through multi-source sensor data fusion, effectively reducing the uncertainty caused by single sensor errors and improving the reliability and real-time performance of status perception; the flight deviation analysis module quantifies and models trajectory and attitude deviations and forms a time series, which can comprehensively reflect the dynamic deviation change trend during flight, thus providing a data foundation for subsequent evaluation; by weighted fusion of deviation features, a unified control accuracy evaluation index is formed, and a power demand mapping relationship is established in combination with different flight conditions, enabling the system to achieve differentiated energy efficiency control for different stages, such as turning or cruise.

[0052] This invention, through screening and causal analysis of sensitive flight states, can accurately identify key factors leading to decreased control accuracy and abnormal energy consumption, such as trajectory or attitude deviations. This avoids the shortcomings of traditional methods that rely solely on overall indicators and struggle to pinpoint the root cause of problems, thus supporting more targeted control strategy optimization. This invention can identify critical stages of high energy consumption and low accuracy in real time during flight and intervene proactively, such as adjusting control parameters or optimizing flight paths, effectively reducing unnecessary energy consumption, extending UAV endurance, and simultaneously improving flight stability and mission execution accuracy.

[0053] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

[0054] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. 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 power efficiency control and management system based on real-time operating condition identification, characterized in that, It includes a flight status perception data acquisition module, a flight deviation analysis module, an UAV control accuracy evaluation module, and a sensitive factor determination module; The flight status perception data acquisition module is used to acquire the flight status perception data of the UAV in real time through airborne sensors, and to preprocess the flight status perception data to obtain flight status perception features. The flight deviation analysis module is used to construct a flight deviation analysis model based on real-time flight status perception features and preset flight status perception features, obtain flight deviation features, and sort the flight deviation features in time order based on the time series model to obtain the flight deviation time series. The UAV control accuracy assessment module is used to build a UAV control accuracy assessment strategy based on the flight deviation time series, assess the control accuracy of the UAV during flight, and establish a power demand mapping relationship by combining flight status perception characteristics and UAV flight status. The sensitive factor determination module is used to screen sensitive flight states based on the power demand mapping relationship, extract flight deviation characteristics of sensitive flight states, and determine the sensitive factors based on the flight deviation characteristics.

2. The UAV power efficiency control and management system based on real-time operating condition identification as described in claim 1, characterized in that, Flight status perception data includes the UAV's trajectory perception data, attitude perception data, and energy consumption perception data; Trajectory perception data includes drone location data; Attitude perception data includes UAV attitude angle data; UAV attitude angle data includes roll angle, pitch angle, and yaw angle. Energy consumption sensing data includes drone energy consumption data.

3. The UAV power efficiency control and management system based on real-time operating condition identification as described in claim 1, characterized in that, Flight deviation characteristics include trajectory deviation characteristics and attitude deviation characteristics; Flight deviation time series include trajectory deviation time series and attitude deviation time series.

4. The UAV power efficiency control and management system based on real-time operating condition identification according to claim 1, characterized in that, A flight deviation analysis model is constructed based on real-time flight status perception features and preset flight status perception features to obtain flight deviation features, as detailed below: Real-time trajectory perception data and real-time attitude perception data are extracted based on real-time flight status perception features, and preset trajectory perception data and preset attitude perception data are extracted based on preset flight status perception features. A first-class flight deviation analysis model is built based on real-time trajectory perception data and preset trajectory perception data to obtain trajectory deviation characteristics. Then, a second-class flight deviation analysis model is built based on real-time attitude perception data and preset attitude perception data to obtain attitude deviation characteristics.

5. The UAV power efficiency control and management system based on real-time operating condition identification according to claim 1, characterized in that, A UAV control accuracy evaluation strategy is built based on the flight deviation time series to evaluate the control accuracy of the UAV during flight. The specific UAV control accuracy evaluation strategy is as follows: Extract the trajectory deviation time series and attitude deviation time series respectively; After preprocessing the trajectory deviation time series and attitude deviation time series, a UAV control accuracy evaluation model is constructed to obtain control accuracy evaluation coefficients.

6. The UAV power efficiency control and management system based on real-time operating condition identification according to claim 1, characterized in that, A power demand mapping relationship is established by combining flight status perception features and UAV flight status, specifically as follows: Energy consumption perception data is extracted from flight status perception features, and the difference between preset energy consumption perception data and real-time energy consumption perception data is calculated as the energy consumption deviation value. A power demand mapping relationship is established based on the control accuracy evaluation coefficient, the energy consumption deviation value, and the UAV flight status. ,in, Let be the control accuracy evaluation coefficient at time t. Let be the energy consumption deviation value at time t. Let t represent the UAV's flight state at time t.

7. The UAV power efficiency control and management system based on real-time operating condition identification according to claim 6, characterized in that, Sensitive flight states are filtered based on power demand mapping relationships, specifically by: obtaining the power demand mapping relationship. Extracting the flight status of the drone The corresponding control accuracy evaluation coefficient and energy consumption deviation value are compared with the corresponding threshold values, and the comprehensive comparison results are used to screen sensitive flight states.

8. The UAV power efficiency control and management system based on real-time operating condition identification according to claim 7, characterized in that, The process of screening sensitive flight states involves: obtaining the control accuracy evaluation coefficient and energy consumption deviation value; comparing the control accuracy evaluation coefficient with a preset accuracy evaluation threshold; and marking the corresponding UAV flight state if the control accuracy evaluation coefficient is greater than or equal to the preset accuracy evaluation threshold. This is a type of flight condition; If the control accuracy evaluation coefficient is less than the preset accuracy evaluation threshold, no marking is required; The energy consumption deviation value is compared with a preset energy consumption deviation threshold. If the energy consumption deviation value is greater than or equal to the preset energy consumption deviation threshold, the corresponding drone flight status is marked. This is a Category II flight state; if the energy consumption deviation value is less than the preset energy consumption deviation threshold, no marking is required. If the drone is in flight status If a drone is simultaneously marked as both a Class I and Class II flight state, its flight state will be uniformly marked as a sensitive flight state; otherwise, no marking is required.

9. The UAV power efficiency control and management system based on real-time operating condition identification according to claim 1, characterized in that, Extract flight deviation characteristics of sensitive flight states, and determine the sensitizing factors based on these characteristics, specifically: The trajectory deviation features and attitude deviation features corresponding to the sensitive flight state are obtained. The trajectory deviation features and attitude deviation features are compared with the preset deviation thresholds. If the trajectory deviation features are greater than or equal to the preset trajectory deviation thresholds, the trajectory deviation is a sensitive factor; otherwise, it is not a sensitive factor. If the attitude deviation characteristic is greater than or equal to the preset attitude deviation threshold, then the attitude deviation is a sensitive factor; otherwise, it is not a sensitive factor.

10. A method for controlling and managing the power efficiency of unmanned aerial vehicles (UAVs) based on real-time operating condition identification, applied to the UAV power efficiency control and management system based on real-time operating condition identification as described in any one of claims 1-9, characterized in that... The specific steps are as follows: acquire the flight status perception data of the UAV in real time through airborne sensors, and preprocess the flight status perception data to obtain flight status perception features; A flight deviation analysis model is constructed based on real-time flight status perception features and preset flight status perception features to obtain flight deviation features. Based on the time series model, the flight deviation features are sorted in time order to obtain the flight deviation time series. A control accuracy assessment strategy for unmanned aerial vehicles (UAVs) is developed based on flight deviation time series to assess the control accuracy of the UAV during flight. A power demand mapping relationship is established by combining flight state perception characteristics and UAV flight state. Sensitive flight states are screened based on the power demand mapping relationship, flight deviation characteristics of sensitive flight states are extracted, and factors causing sensitivity are determined based on the flight deviation characteristics.

Images