A method and system for safety assessment of unmanned aerial vehicle aerodynamic deceleration control

Abstract

The application discloses a kind of unmanned aerial vehicle aerodynamic deceleration control safety evaluation method and system, belong to unmanned aerial vehicle flight control technical field.To solve the problem of improving the safety performance of unmanned aerial vehicle flight.The present application includes constructing a hidden layer of unmanned aerial vehicle aerodynamic deceleration control prediction model, using the three-layer architecture of dynamic perception layer, aerodynamic characteristic layer and control decision layer;Construct the output index of the model;The loss function of the prediction model of the unmanned aerial vehicle aerodynamic deceleration control is a composite loss function of the basic loss function, the speed loss term function, the flight characteristic loss term function and the stability loss term function;Get a trained unmanned aerial vehicle aerodynamic deceleration control prediction model;Based on the obtained M group input, output data constructs unmanned aerial vehicle aerodynamic deceleration control safety evaluation method, from system stability, structural integrity, flight state, energy management, control characteristics and environmental adaptability dimension comprehensive consideration establishes evaluation system.

Description

Technical Field

[0001] This invention belongs to the field of unmanned aerial vehicle (UAV) flight control technology, specifically a method and system for safety assessment of UAV aerodynamic deceleration control. Background Technology

[0002] The aerodynamic deceleration control process of unmanned aerial vehicles (UAVs) involves complex aerodynamic characteristic changes and multi-system coupling effects, and its safety directly affects the reliable operation and mission completion of the UAV. During deceleration, factors such as abrupt aerodynamic changes, enhanced unsteady aerodynamic effects, and rapid response of the overall mechanism can all lead to safety hazards. Simultaneously, the activation of the deceleration device causes aerodynamic redistribution, disturbing the aircraft's attitude, and environmental factors such as changes in atmospheric conditions and wind disturbances can also significantly affect the deceleration effect and safety. Therefore, establishing a scientific safety assessment system is of great significance for ensuring the reliability of UAV deceleration control.

[0003] Current safety assessment methods for UAV aerodynamic deceleration control suffer from the following main problems: First, most assessment methods focus only on a single safety indicator, such as stability or structural strength, lacking a multi-dimensional comprehensive assessment of the overall system safety. Second, existing methods often employ static assessment models, failing to effectively reflect the dynamic changes in various parameters during deceleration. Third, traditional assessment methods do not adequately consider the impact of environmental factors, making it difficult to accurately predict and assess the impact of external environmental changes on deceleration safety. Finally, the lack of a systematic safety level classification and early warning mechanism affects the practical guiding value of the assessment results.

[0004] These issues can lead to serious safety hazards in practical applications. Assessing a single indicator may overlook other important safety factors, resulting in a one-sided and incomplete safety assessment. Static assessment models cannot promptly identify dynamic safety risks during deceleration, delaying early warning. Insufficient consideration of environmental factors may lead to misjudgments under complex weather conditions, affecting the selection of deceleration control strategies. Furthermore, the lack of a systematic safety level classification makes it difficult to develop corresponding countermeasures for different risk levels, increasing the likelihood of safety accidents.

[0005] The limitations of traditional assessment methods are also reflected in the construction of assessment indicator systems. Existing methods often rely on empirical judgments, lacking theoretical support and the rigor of mathematical models, resulting in insufficient reliability and accuracy of assessment results. Furthermore, the absence of a correlation mechanism between various assessment indicators fails to reflect the mutual influence and coupling effects between different safety factors, making it difficult for the assessment results to comprehensively reflect the actual safety status of the system. These problems severely restrict the improvement of the safety of UAV deceleration control systems. Summary of the Invention

[0006] The problem this invention aims to solve is to improve the safety performance of unmanned aerial vehicles (UAVs) during flight, and proposes a safety assessment method and system for UAV aerodynamic deceleration control.

[0007] To achieve the above objectives, the present invention provides the following technical solution: A safety assessment method for aerodynamic deceleration control of unmanned aerial vehicles (UAVs) includes the following steps: S1. Collect and normalize the input feature parameters of the UAV aerodynamic deceleration control prediction model, including flight state parameters, control input parameters and environmental parameters; S2. Construct a hidden layer for a UAV aerodynamic deceleration control prediction model, adopting a three-layer architecture of dynamic perception layer, aerodynamic characteristics layer and control decision layer; S3. Output index of the hidden layer construction model of the UAV aerodynamic deceleration control prediction model obtained in step S2; S4. Construct a loss function for a prediction model of aerodynamic deceleration control for unmanned aerial vehicles (UAVs) that is a composite loss function consisting of a basic loss function, a velocity loss term function, a flight characteristic loss term function, and a stability loss term function. S5. Based on the input feature parameter data of the UAV aerodynamic deceleration control prediction model obtained in step S1 and the output index data of the UAV aerodynamic deceleration control prediction model obtained in step S3, construct a training set and a test set, set parameters for the UAV aerodynamic deceleration control prediction model constructed in steps S2-S4, train the UAV aerodynamic deceleration control prediction model using the obtained training set, and test it using the test set to obtain a trained UAV aerodynamic deceleration control prediction model. S6. After normalizing the input feature parameter sample points of the M-group UAV aerodynamic deceleration control prediction model, input them into the UAV aerodynamic deceleration control prediction model trained in step S5 to obtain the corresponding M-group output results. Then perform inverse normalization to obtain the output parameters with dimensions, and obtain the M-group input and output data. S7. Based on the M sets of input and output data obtained in step S6, construct a safety assessment method for UAV aerodynamic deceleration control, and establish an assessment system that comprehensively considers the dimensions of system stability, structural integrity, flight status, energy management, control characteristics and environmental adaptability.

[0008] Furthermore, the specific input feature parameters of the UAV aerodynamic deceleration control prediction model in step S1 are as follows: Flight status parameters include airspeed X1, angle of attack X2, sideslip angle X3, altitude X4, Mach number X5, dynamic pressure X6, roll angle X7, and pitch angle X8; Control input parameters include aileron deflection angle X9 and rudder deflection angle X. 10 Elevator deflection angle X 11 Throttle opening X 12 Air brake deflection angle X 13 and the deployment area of ​​the deceleration parachute X 14 ; Environmental parameters include air density X 15 Temperature X 16 Wind speed X 17 Wind direction X 18 Atmospheric pressure X 19 and humidity X 20 .

[0009] Furthermore, the specific implementation method of step S2 includes the following steps: S2.1. Based on considering airspeed and altitude in flight state parameters, and also taking into account the influence of environmental parameters on dynamic characteristics, a dynamic sensing layer is constructed, expressed as: ; in, Output for the dynamic sensing layer. For activation function, Let be the weight coefficient of the j-th input feature parameter in the UAV aerodynamic deceleration control prediction model. Let j be the j-th input feature parameter of the UAV aerodynamic deceleration control prediction model. For dynamic characteristic coefficients, As a high-impact factor, The characteristic time scale factor characterizes the characteristic response speed during the deceleration process of the UAV. The characteristic height scale factor characterizes the sensitivity of the UAV to changes in altitude; For the bias term of the dynamic sensing layer, j=1~20; Dynamic characteristic coefficient The expression reflecting the dynamic characteristics of the UAV during deceleration is: ; in, For the quality of drones, This is the drag coefficient; High Impact Factor The expression reflecting the relationship between altitude and atmospheric pressure is: ; in, For reference height, Standard atmospheric pressure; S2.2. Based on dynamic characteristics, the influence of angle of attack and dynamic pressure on aerodynamic forces is considered, and the Mach number effect is also taken into account to construct an aerodynamic characteristic layer, the expression of which is: ; in, Output for aerodynamic characteristics layer; This is the bias term for the aerodynamic characteristic layer. This refers to the lift characteristic coefficient; As a factor influencing compressibility effect, The characteristic angle of attack characterizes the system's response to attitude changes during deceleration. Characteristic dynamic pressure, which represents the adaptability of an unmanned aerial vehicle (UAV) to changes in aerodynamics; Lift characteristic coefficient Aerodynamic characteristics are reflected by the ratio of dynamic pressure, the deceleration parachute deployment area, and gravity, expressed as: ; Where g is the acceleration due to gravity; Compressibility effect factor Considering the effects of air density and Mach number on compressibility, the expression is: ; S2.3. Construct a control decision layer. By establishing a direct information channel from the dynamic perception layer to the control decision layer, a rapid mapping from the initial dynamic state to the control decision is achieved. The expression is: ; in, To control the output of the decision-making level; The residual connectivity coefficient is determined by expert experience. To control the efficiency coefficient; As a stability influencing factor, To control the bias terms of the decision-making level; Characteristic force, representing the impact of changes in control force on the UAV; The characteristic rudder deflection angle characterizes the impact of rudder surface deflection on the UAV; Control efficiency coefficient By considering the relationship between dynamic pressure and characteristic length to reflect control efficiency, the product of dynamic pressure and deceleration parachute deployment area characterizes the aerodynamic control force, expressed as: ; in, For characteristic length, The average aerodynamic chord length; Stability Influencing Factors A stability evaluation index is constructed using Mach number, expressed as follows: .

[0010] Furthermore, step S3 is specifically implemented by weighting and combining the outputs of the three hidden layers constructed in step S2, and introducing a nonlinear activation function and a feature scaling factor for the corresponding index to achieve accurate prediction of the flight state prediction index and the control effect evaluation index. The nonlinear activation function introduced for the flight state prediction index is the hyperbolic tangent function, and the nonlinear activation function introduced for the control effect evaluation index is the sigmoid function, thus obtaining the flight state prediction index and the control effect evaluation index. The flight state prediction index includes predicted airspeed Y1, predicted angle of attack Y2, predicted altitude Y3, predicted Mach number Y4, and predicted dynamic pressure Y5. The control effect evaluation index includes deceleration rate Y6, aerodynamic drag coefficient Y7, lift-to-drag ratio Y8, energy loss rate Y9, and stability index Y1. 10 Establish the mapping relationship between the model's hidden layer and the output metrics.

[0011] Furthermore, the specific implementation method of step S4 includes the following steps: S4.1. Design the basic loss function, using the mean squared error form, and calculate all output indices Y1~Y2. 10 The mean square error between the predicted and measured values ​​is the basic loss. ; S4.2. Design the velocity loss term function, quantify the deceleration effect by evaluating the difference between predicted and actual airspeed and the corresponding state transition efficiency, while also considering the effects of air density and parachute deployment area, resulting in the following expression: ; in, For the weighting coefficient of the velocity loss term; This is the weighting coefficient for state transition efficiency; , These represent the kinetic energy levels of the predicted state and the current state, respectively. , These respectively characterize the work done on the predicted resistance and the actual resistance; S4.3. Design the flight characteristic loss term function. By considering the influence of Mach number on aerodynamic characteristics and evaluating the accuracy of lift, drag, and moment predictions, a comprehensive evaluation index for flight quality is constructed by introducing characteristic length and aerodynamic parameters. The expression for the flight characteristic loss term function is as follows: ; in, The Mach number effect coefficient, This is the torque weighting coefficient. , These represent the predicted aerodynamic intensity level and the actual aerodynamic intensity level, respectively. , These respectively characterize the predicted torque level and the actual torque level; S4.4. Design a stability loss term function. By evaluating three aspects—height variation, static stability, and dynamic stability—a complete stability evaluation system is constructed. The expression for the stability loss term function is: ; in, As a high-impact coefficient, For stability weighting coefficients, and These represent the mechanical energy level of the predicted state and the mechanical energy level of the current state, respectively. and These represent the predicted stability moment level and the actual stability moment level, respectively. This is the static stability coefficient; Characteristic energy factor; The characteristic torque factor; S4.5. The loss function of the UAV aerodynamic deceleration control prediction model is a composite loss function including a velocity loss term, a flight characteristic loss term, and a stability loss term, expressed as: ; in, , , , They are respectively , , , The weighting coefficients.

[0012] Furthermore, the input feature parameter data of the UAV aerodynamic deceleration control prediction model after normalization in step S5 and the output index data of the UAV aerodynamic deceleration control prediction model obtained in step S3 are divided into training set and test set in a ratio of 8:2.

[0013] Furthermore, the specific implementation method of step S7 includes the following steps: S7.1. Taking into account both aerodynamic efficiency and deceleration intensity, the stability and safety assessment index is obtained, expressed as: ; in, As a stability and safety assessment indicator, aerodynamic efficiency coefficient, The deceleration intensity adjustment coefficient is determined by expert experience or design specifications, and the aerodynamic efficiency is adopted. The deceleration intensity is characterized by the square of the ratio of the deceleration rate to the predicted airspeed. S7.2. Based on the air brake deflection angle X 13 and the deployment area of ​​the deceleration parachute X 14 Considering the structural load influence during the deceleration process of the deceleration device, the structural load safety assessment index is obtained, expressed as: ; in, As a structural load safety assessment indicator, The influence coefficient of the basic load. This is the load distribution factor for the device. The dynamic load adjustment coefficient is determined by expert experience or design specifications. This represents the maximum deflection angle of the air brake plate. This represents the maximum deployed area of ​​the deceleration parachute. The maximum dynamic pressure should be determined with reference to expert experience or design specifications. S7.3. Flight envelope evaluation during deceleration considers speed, angle of attack limit, and dynamic pressure changes, resulting in a flight envelope safety evaluation index, expressed as: ; in, For flight envelope safety indicators, This is the speed limit factor. This is the angle-of-attack limiting factor. The dynamic pressure limit factor is determined by expert experience or design specifications. To limit speed, For maximum angle of attack, The maximum dynamic pressure should be determined with reference to expert experience or design specifications. S7.4. Based on the energy loss rate during the deceleration process, and considering the impact of energy dissipation on system stability and control effectiveness, the energy management safety index is obtained, expressed as: ; in, For energy management safety indicators, For the maximum energy loss rate, The maximum deceleration rate should be determined with reference to expert experience or design specifications. The energy loss coefficient, The deceleration efficiency coefficient is determined by expert experience or design specifications. S7.5. The coordinated operation of actuators involved in deceleration, including ailerons, rudder, elevator, dedicated deceleration device, air brakes, drag chute, and engine power regulation, to obtain control input safety indicators. The expression is: ; Where i = 9, 10, 11, 12; The maximum allowable values ​​for the corresponding input parameters i=9, 10, 11, and 12 should be determined with reference to expert experience or design specifications. , These are the coordination coefficients for conventional control surfaces and special deceleration devices, determined with reference to expert experience or design specifications. S7.6. Taking into account changes in atmospheric parameters and wind field disturbances, obtain the environmental adaptability safety index. The expression is: ; in, The atmospheric parameter influence coefficient, This is the wind field disturbance coefficient, determined by expert experience or design specifications; The atmospheric parameter coupling index. The wind direction deviation attenuation coefficient is determined by expert experience or design specifications. Standard air density; Standard atmospheric pressure; The wind speed is determined with reference to expert experience, historical data, or design specifications. S7.7. Based on steps S7.1-S7.6, and considering that when the structural load exceeds a certain threshold, the safety factor is rapidly reduced through exponential decay to prevent structural overload, and a comprehensive safety assessment index is obtained. The expression is: ; in, For stability weighting coefficients, This is the structural load weighting coefficient. This is the flight envelope weighting coefficient. For energy management weighting coefficients, To control the input weighting coefficients, For environmental adaptation weighting coefficients, This is the structural load limitation factor. To control the saturation suppression coefficient, all coefficients are determined by expert experience or design specifications; S7.8. Classify the comprehensive safety assessment indicators obtained in step S7.7 and provide corresponding safety level recommendations: when In the safe operating zone, continuously monitor various indicators and record performance data; when For areas of concern, the monitoring frequency of indicators will be increased, and early warnings will be issued when problems are detected by predicting performance trend changes. when This is a warning zone. At this point, the aerodynamic deceleration is too rapid, and it is necessary to reduce the deceleration intensity, strengthen manual monitoring, and prepare an emergency plan. when This is a danger zone. The deceleration procedure must be terminated immediately, the state restored to safety, and the emergency procedure activated.

[0014] in, , , These are the critical comprehensive safety assessment indicators corresponding to the safe operation zone, attention zone, warning zone, and danger zone.

[0015] A safety assessment system for aerodynamic deceleration control of unmanned aerial vehicles (UAVs) includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed, it implements the steps of the aforementioned safety assessment method for aerodynamic deceleration control of UAVs.

[0016] The beneficial effects of this invention are: This invention discloses a safety assessment method for aerodynamic deceleration control of unmanned aerial vehicles (UAVs), constructing a comprehensive, dynamic, and reliable safety assessment system for UAV aerodynamic deceleration control. This system needs to be able to assess system safety from multiple dimensions, monitor and warn of safety risks in real time, accurately reflect the impact of environmental factors, and establish a scientific safety level classification mechanism. Simultaneously, the assessment method must possess theoretical rigor and engineering practicality, providing a reliable basis for optimizing deceleration control strategies and safety management. Attached Figure Description

[0017] Figure 1 This is a flowchart of a safety assessment method for aerodynamic deceleration control of an unmanned aerial vehicle (UAV) according to the present invention;

[0018] Figure 2 This is a comparison chart of the Sz calculation results under different working conditions of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only for explaining the invention and are not intended to limit the invention; that is, the described specific embodiments are merely a part of the embodiments of the invention, and not all of them. The components of the specific embodiments of the invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations, and the invention may also have other embodiments.

[0020] Therefore, the following detailed description of specific embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected specific embodiments of the invention. All other specific embodiments obtained by those skilled in the art based on these specific embodiments without inventive effort are within the scope of protection of this invention.

[0021] To further understand the invention's content, features, and effects, the following specific embodiments are provided, along with accompanying drawings. Figure 1 and attached Figure 2 Detailed explanation is as follows:

[0022] Example 1: A safety assessment method for aerodynamic deceleration control of unmanned aerial vehicles (UAVs), characterized by the following steps: S1. Collect and normalize the input feature parameters of the UAV aerodynamic deceleration control prediction model, including flight state parameters, control input parameters and environmental parameters; Furthermore, the specific input feature parameters of the UAV aerodynamic deceleration control prediction model in step S1 are as follows: Flight status parameters include airspeed X1, angle of attack X2, sideslip angle X3, altitude X4, Mach number X5, dynamic pressure X6, roll angle X7, and pitch angle X8; Control input parameters include aileron deflection angle X9 and rudder deflection angle X. 10 Elevator deflection angle X 11 Throttle opening X 12 Air brake deflection angle X 13 and the deployment area of ​​the deceleration parachute X 14 ; Environmental parameters include air density X 15 Temperature X 16 Wind speed X 17 Wind direction X 18 Atmospheric pressure X 19 and humidity X 20 .

[0023] S2. Construct a hidden layer for a UAV aerodynamic deceleration control prediction model, adopting a three-layer architecture of dynamic perception layer, aerodynamic characteristics layer and control decision layer; Furthermore, the specific implementation method of step S2 includes the following steps: S2.1. Based on considering airspeed and altitude in flight state parameters, and also taking into account the influence of environmental parameters on dynamic characteristics, a dynamic sensing layer is constructed, expressed as: ; in, Output for the dynamic sensing layer. For activation function, Let be the weight coefficient of the j-th input feature parameter in the UAV aerodynamic deceleration control prediction model. Let j be the j-th input feature parameter of the UAV aerodynamic deceleration control prediction model. For dynamic characteristic coefficients, As a high-impact factor, The characteristic time scale factor characterizes the characteristic response speed during the deceleration process of the UAV. The characteristic height scale factor characterizes the sensitivity of the UAV to changes in altitude; For the bias term of the dynamic sensing layer, j=1~20; Dynamic characteristic coefficient The expression reflecting the dynamic characteristics of the UAV during deceleration is: ; in, For the quality of drones, This is the drag coefficient; High Impact Factor The expression reflecting the relationship between altitude and atmospheric pressure is: ; in, For reference height, Standard atmospheric pressure; S2.2. Based on dynamic characteristics, the influence of angle of attack and dynamic pressure on aerodynamic forces is considered, and the Mach number effect is also taken into account to construct an aerodynamic characteristic layer, the expression of which is: ; in, Output for aerodynamic characteristics layer; This is the bias term for the aerodynamic characteristic layer. This refers to the lift characteristic coefficient; As a factor influencing compressibility effect, The characteristic angle of attack characterizes the system's response to attitude changes during deceleration. Characteristic dynamic pressure, which represents the adaptability of an unmanned aerial vehicle (UAV) to changes in aerodynamics; Lift characteristic coefficient Aerodynamic characteristics are reflected by the ratio of dynamic pressure, the deceleration parachute deployment area, and gravity, expressed as: ; Where g is the acceleration due to gravity; Compressibility effect factor Considering the effects of air density and Mach number on compressibility, the expression is: ; S2.3. Construct a control decision layer. By establishing a direct information channel from the dynamic perception layer to the control decision layer, a rapid mapping from the initial dynamic state to the control decision is achieved. The expression is: ; in, To control the output of the decision-making level; The residual connectivity coefficient is determined by expert experience. To control the efficiency coefficient; As a stability influencing factor, To control the bias terms of the decision-making level; Characteristic force, representing the impact of changes in control force on the UAV; The characteristic rudder deflection angle characterizes the impact of rudder surface deflection on the UAV; Control efficiency coefficient By considering the relationship between dynamic pressure and characteristic length to reflect control efficiency, the product of dynamic pressure and deceleration parachute deployment area characterizes the aerodynamic control force, expressed as: ; in, For characteristic length, The average aerodynamic chord length; Stability Influencing Factors A stability evaluation index is constructed using Mach number, expressed as follows: .

[0024] S3. Output index of the hidden layer construction model of the UAV aerodynamic deceleration control prediction model obtained in step S2; Furthermore, step S3 is specifically implemented by weighting and combining the outputs of the three hidden layers constructed in step S2, and introducing a nonlinear activation function and a feature scaling factor for the corresponding index to achieve accurate prediction of the flight state prediction index and the control effect evaluation index. The nonlinear activation function introduced for the flight state prediction index is the hyperbolic tangent function, and the nonlinear activation function introduced for the control effect evaluation index is the sigmoid function, thus obtaining the flight state prediction index and the control effect evaluation index. The flight state prediction index includes predicted airspeed Y1, predicted angle of attack Y2, predicted altitude Y3, predicted Mach number Y4, and predicted dynamic pressure Y5. The control effect evaluation index includes deceleration rate Y6, aerodynamic drag coefficient Y7, lift-to-drag ratio Y8, energy loss rate Y9, and stability index Y1. 10 Establish the mapping relationship between the model's hidden layer and the output metrics.

[0025] S4. Construct a loss function for a prediction model of aerodynamic deceleration control for unmanned aerial vehicles (UAVs) that is a composite loss function consisting of a basic loss function, a velocity loss term function, a flight characteristic loss term function, and a stability loss term function. Furthermore, the specific implementation method of step S4 includes the following steps: S4.1. Design the basic loss function, using the mean squared error form, and calculate all output indices Y1~Y2. 10 The mean square error between the predicted and measured values ​​is the basic loss. ; S4.2. Design the velocity loss term function, quantify the deceleration effect by evaluating the difference between predicted and actual airspeed and the corresponding state transition efficiency, while also considering the effects of air density and parachute deployment area, resulting in the following expression: ; in, For the weighting coefficient of the velocity loss term; This is the weighting coefficient for state transition efficiency; , These represent the kinetic energy levels of the predicted state and the current state, respectively. , These respectively characterize the work done on the predicted resistance and the actual resistance; The weighting coefficient of the velocity loss term reflects the variation of the deceleration effect with flight conditions, while the air density-predicted velocity square term characterizes the kinetic energy change. Considering air density, parachute deployment area, and mass factors, the expression is: ; The state transition efficiency weighting coefficient evaluates the energy conversion efficiency during deceleration. Considering the inertial characteristics of the UAV, the characteristics of the deceleration medium, the current motion state, and the characteristics of the deceleration device, the expression for the state transition efficiency weighting coefficient is as follows: ; S4.3. Design the flight characteristic loss term function. By considering the influence of Mach number on aerodynamic characteristics and evaluating the accuracy of lift, drag, and moment predictions, a comprehensive evaluation index for flight quality is constructed by introducing characteristic length and aerodynamic parameters. The expression for the flight characteristic loss term function is as follows: ; in, The Mach number effect coefficient, This is the torque weighting coefficient. , These represent the predicted aerodynamic intensity level and the actual aerodynamic intensity level, respectively. , These respectively characterize the predicted torque level and the actual torque level; The Mach number effect coefficient reflects the changes in aerodynamic characteristics during flight speed variations through the Mach number, directly reflecting the intensity of the Mach number effect. Its expression is: ; The torque weighting coefficient takes into account the effects of environmental characteristics, deceleration chute area, and characteristic length. The characteristic length assesses the impact of torque balance, and the predicted square velocity reflects the dynamic pressure effect. The expression is as follows: ; S4.4. Design a stability loss term function. By evaluating three aspects—height variation, static stability, and dynamic stability—a complete stability evaluation system is constructed. The expression for the stability loss term function is: ; in, As a high-impact coefficient, For stability weighting coefficients, and These represent the mechanical energy level of the predicted state and the mechanical energy level of the current state, respectively. and These represent the predicted stability moment level and the actual stability moment level, respectively. This is the static stability coefficient; Characteristic energy factor; The characteristic torque factor; The altitude influence coefficient characterizes the influence of altitude, and its expression is: ; The stability weighting coefficient assesses the impact on stability, while the predicted velocity square reflects the dynamic pressure effect. It also considers the influence of environmental characteristics, deceleration chute area, mean aerodynamic chord length, and characteristic length. The expression is: ; S4.5. The loss function of the UAV aerodynamic deceleration control prediction model is a composite loss function including a velocity loss term, a flight characteristic loss term, and a stability loss term, expressed as: ; in, , , , They are respectively , , , The weighting coefficients.

[0026] S5. Based on the input feature parameter data of the UAV aerodynamic deceleration control prediction model obtained in step S1 and the output index data of the UAV aerodynamic deceleration control prediction model obtained in step S3, construct a training set and a test set, set parameters for the UAV aerodynamic deceleration control prediction model constructed in steps S2-S4, train the UAV aerodynamic deceleration control prediction model using the obtained training set, and test it using the test set to obtain a trained UAV aerodynamic deceleration control prediction model. Furthermore, the input feature parameter data of the UAV aerodynamic deceleration control prediction model after normalization in step S5 and the output index data of the UAV aerodynamic deceleration control prediction model obtained in step S3 are divided into training set and test set in a ratio of 8:2.

[0027] Further, data acquisition and processing: Data sources include commercial flight data from the Civil Aviation Administration of China, test data from large UAV manufacturers, design parameters from UAV design specifications, experimental data from UAV laboratory tests, and monitoring data from UAV monitoring and management platforms. This data includes input data X1~X20 and output data Y1~Y10.

[0028] Model building: Input layer construction: It contains 20 neuron nodes, divided into flight state parameters, control input parameters, and environmental parameters; The model structure is constructed in layers, including a dynamic perception layer, an aerodynamic characteristics layer, and a control decision layer. Output layer construction: It contains 10 neuron nodes, which are divided into flight state prediction indicators and control effect evaluation indicators; Loss function construction: It consists of four parts: basic loss term, velocity loss term, flight characteristic loss term, and stability loss term.

[0029] Parameter settings: Hyperparameters that need to be manually set based on expert experience include: network structure parameters and the number of neurons in each layer; The hyperparameters that need to be manually set during model training include: learning rate, batch size, number of training epochs, and weight coefficients in the loss function; The parameters that need to be determined during the training process are: the weight coefficients and bias terms of each layer.

[0030] Training strategy: The model training employs the backpropagation algorithm. During training, the model calculates predicted values ​​through forward propagation, substitutes the predicted and true values ​​into the loss function to calculate the loss, and then updates the network parameters through backpropagation. To prevent overfitting, an early stopping strategy is used: training stops when the test set loss does not decrease for 10 consecutive epochs.

[0031] Once the model is trained, the relationship between input and output is established. By inputting the parameters corresponding to X1-X20, Y1~Y10 can be predicted. The output results are then inversely normalized to recover the actual physical quantities.

[0032] S6. After normalizing the input feature parameter sample points of the M-group UAV aerodynamic deceleration control prediction model, input them into the UAV aerodynamic deceleration control prediction model trained in step S5 to obtain the corresponding M-group output results. Then perform inverse normalization to obtain the output parameters with dimensions, and obtain the M-group input and output data. S7. Based on the M sets of input and output data obtained in step S6, construct a safety assessment method for UAV aerodynamic deceleration control, and establish an assessment system that comprehensively considers the dimensions of system stability, structural integrity, flight status, energy management, control characteristics and environmental adaptability.

[0033] The aerodynamic deceleration process of unmanned aerial vehicles (UAVs) involves complex aerodynamic characteristic changes and multi-system coupling effects. Its safety assessment requires comprehensive consideration from multiple dimensions, including system stability, structural integrity, flight status, energy management, control characteristics, and environmental adaptability. During deceleration, the system is prone to instability due to abrupt changes in aerodynamic forces, enhanced unsteady aerodynamic effects, and rapid responses from various actuators. Furthermore, the activation of the deceleration device leads to aerodynamic force redistribution, causing disturbances in the aircraft's attitude. In addition, environmental factors such as changes in atmospheric conditions and wind disturbances can affect the deceleration effect and safety. Therefore, a multi-level, multi-dimensional safety assessment system is needed, combining quantitative indicators with qualitative analysis to comprehensively evaluate the safety of the deceleration process.

[0034] Data Acquisition

[0035] The UAV monitoring and management platform is used to acquire UAV monitoring data, specifically including 20 input parameters X1 to X20, including flight status parameters, control input parameters, and environmental parameters. These 20 input parameters are then input into the aforementioned UAV aerodynamic deceleration control prediction model to obtain the predicted output parameters Y1 to Y10. The prediction results are then inversely normalized to restore the actual physical quantities.

[0036] It should be noted that when the drone monitoring and management platform lacks the above data (X1~X20), it is necessary to consider combining multiple sources such as commercial flight data from the Civil Aviation Administration, test data from drone manufacturers, drone design specifications, and laboratory test data.

[0037] Furthermore, the specific implementation method of step S7 includes the following steps: S7.1. Taking into account both aerodynamic efficiency and deceleration intensity, the stability and safety assessment index is obtained, expressed as: ; in, As a stability and safety assessment indicator, aerodynamic efficiency coefficient, The deceleration intensity adjustment coefficient is determined by expert experience or design specifications, and the aerodynamic efficiency is adopted. The deceleration intensity is characterized by the square of the ratio of the deceleration rate to the predicted airspeed. The stability of a drone during deceleration involves attitude stability, trajectory stability, and dynamic response characteristics. When the deceleration device is activated, the sudden change in aerodynamic forces can cause attitude disturbances, while the reduction in speed can affect control effectiveness. Furthermore, the asymmetric deployment of deceleration devices (such as drag chutes or aerodynamic brakes) can induce unbalanced torques. Therefore, both static stability (restoring torque characteristics) and dynamic stability (damping characteristics) need to be considered comprehensively. S7.2. Based on the air brake deflection angle X 13 and the deployment area of ​​the deceleration parachute X 14 Considering the structural load influence during the deceleration process of the deceleration device, the structural load safety assessment index is obtained, expressed as: ; in, As a structural load safety assessment indicator, The influence coefficient of the basic load. This is the load distribution factor for the device. The dynamic load adjustment coefficient is determined by expert experience or design specifications. This represents the maximum deflection angle of the air brake plate. This represents the maximum deployed area of ​​the deceleration parachute. The maximum dynamic pressure should be determined with reference to expert experience or design specifications. The structural loads during deceleration primarily originate from aerodynamic forces, inertial forces, and their coupling effects. Special attention needs to be paid to the loads borne by the deceleration device, the structural stresses resulting from aerodynamic redistribution, and the vibrations and impacts caused by high-speed airflow. By establishing a structural load assessment model, the stress state of critical components can be predicted, preventing structural failure.

[0038] S7.3. Flight envelope evaluation during deceleration considers speed, angle of attack limit, and dynamic pressure changes, resulting in a flight envelope safety evaluation index, expressed as: ; in, For flight envelope safety indicators, This is the speed limit factor. This is the angle-of-attack limiting factor. The dynamic pressure limit factor is determined by expert experience or design specifications. To limit speed, For maximum angle of attack, The maximum dynamic pressure should be determined with reference to expert experience or design specifications. Flight envelope assessment during deceleration needs to consider factors such as speed, angle-of-attack limits, and dynamic pressure changes. Particular attention should be paid to critical states that may occur during deceleration, such as minimum safe speed and maximum permissible dynamic pressure. By monitoring the relationship between flight status parameters and safety boundaries in real time, it is ensured that the aircraft always operates within its safety envelope.

[0039] S7.4. Based on the energy loss rate during the deceleration process, and considering the impact of energy dissipation on system stability and control effectiveness, the energy management safety index is obtained, expressed as: ; in, For energy management safety indicators, For the maximum energy loss rate, The maximum deceleration rate should be determined with reference to expert experience or design specifications. The energy loss coefficient, The deceleration efficiency coefficient is determined by expert experience or design specifications. Deceleration is essentially a rapid energy dissipation process. It's necessary to assess the energy loss rate to ensure the energy dissipation process is controllable. Simultaneously, the impact of energy dissipation on system stability and control effectiveness must be considered.

[0040] S7.5. The coordinated operation of actuators involved in deceleration, including ailerons, rudder, elevator, dedicated deceleration device, air brakes, drag chute, and engine power regulation, to obtain control input safety indicators. The expression is: ; Where i = 9, 10, 11, 12; The maximum allowable values ​​for the corresponding input parameters i=9, 10, 11, and 12 should be determined with reference to expert experience or design specifications. , These are the coordination coefficients for conventional control surfaces and special deceleration devices, determined with reference to expert experience or design specifications. Deceleration involves the coordinated operation of multiple actuators, including conventional aerodynamic control surfaces (ailerons, rudder, elevator), dedicated deceleration devices (air brakes, drag chutes), and engine power regulation. Complex aerodynamic interferences and coupling effects exist among these control inputs. It is necessary to evaluate the operating status, response characteristics, and coordination of each actuator to ensure the rationality and effectiveness of the control inputs.

[0041] S7.6. Taking into account changes in atmospheric parameters and wind field disturbances, obtain the environmental adaptability safety index. The expression is: ; in, The atmospheric parameter influence coefficient, This is the wind field disturbance coefficient, determined by expert experience or design specifications; The atmospheric parameter coupling index. The wind direction deviation attenuation coefficient is determined by expert experience or design specifications. Standard air density; Standard atmospheric pressure; The wind speed is determined with reference to expert experience, historical data, or design specifications. Environmental factors have a significant impact on the deceleration process, mainly including changes in atmospheric parameters and wind field disturbances. It is necessary to assess the extent to which current environmental conditions affect the deceleration effect and predict the potential risks posed by environmental changes. An environmental adaptability assessment model should be established to provide a basis for adjusting deceleration control strategies.

[0042] S7.7. Based on steps S7.1-S7.6, and considering that when the structural load exceeds a certain threshold, the safety factor is rapidly reduced through exponential decay to prevent structural overload, and a comprehensive safety assessment index is obtained. The expression is: ; in, For stability weighting coefficients, This is the structural load weighting coefficient. This is the flight envelope weighting coefficient. For energy management weighting coefficients, To control the input weighting coefficients, For environmental adaptation weighting coefficients, This is the structural load limitation factor. To control the saturation suppression coefficient, all coefficients are determined by expert experience or design specifications; S7.8. Classify the comprehensive safety assessment indicators obtained in step S7.7 and provide corresponding safety level recommendations: when In the safe operating zone, continuously monitor various indicators and record performance data; when For areas of concern, the monitoring frequency of indicators will be increased, and early warnings will be issued when problems are detected by predicting performance trend changes. when This is a warning zone. At this point, the aerodynamic deceleration is too rapid, and it is necessary to reduce the deceleration intensity, strengthen manual monitoring, and prepare an emergency plan. when This is a danger zone. The deceleration procedure must be terminated immediately, the state restored to safety, and the emergency procedure activated.

[0043] in, , , These are the critical comprehensive safety assessment indicators corresponding to the safe operation zone, attention zone, warning zone, and danger zone. Figure 2 This is a comparison chart of the Sz calculation results under different working conditions in this embodiment.

[0044] Example 2: A safety assessment system for aerodynamic deceleration control of a drone includes a processor, a memory, and a computer program stored in the memory and run on the processor. When the computer program is run, it implements the steps of a safety assessment method for aerodynamic deceleration control of a drone as described in Example 1.

[0045] It should be noted that relational terms such as "first" and "second" are used merely 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 a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0046] Although this application has been described above with reference to specific embodiments, various modifications can be made and components can be replaced with equivalents without departing from the scope of this application. In particular, as long as there is no structural conflict, the features in the specific embodiments disclosed in this application can be combined with each other in any way. The lack of an exhaustive description of these combinations in this specification is merely for the sake of brevity and resource conservation. Therefore, this application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A safety assessment method for aerodynamic deceleration control of unmanned aerial vehicles (UAVs), characterized in that, Includes the following steps: S1. Collect and normalize the input feature parameters of the UAV aerodynamic deceleration control prediction model, including flight state parameters, control input parameters and environmental parameters; S2. Construct a hidden layer for a UAV aerodynamic deceleration control prediction model, adopting a three-layer architecture of dynamic perception layer, aerodynamic characteristics layer and control decision layer; S3. Output index of the hidden layer construction model of the UAV aerodynamic deceleration control prediction model obtained in step S2; S4. Construct a loss function for a prediction model of aerodynamic deceleration control for unmanned aerial vehicles (UAVs) that is a composite loss function consisting of a basic loss function, a velocity loss term function, a flight characteristic loss term function, and a stability loss term function. S5. Based on the input feature parameter data of the UAV aerodynamic deceleration control prediction model obtained in step S1 and the output index data of the UAV aerodynamic deceleration control prediction model obtained in step S3, construct a training set and a test set, set parameters for the UAV aerodynamic deceleration control prediction model constructed in steps S2-S4, train the UAV aerodynamic deceleration control prediction model using the obtained training set, and test it using the test set to obtain a trained UAV aerodynamic deceleration control prediction model. S6. After normalizing the input feature parameter sample points of the M-group UAV aerodynamic deceleration control prediction model, input them into the UAV aerodynamic deceleration control prediction model trained in step S5 to obtain the corresponding M-group output results. Then perform inverse normalization to obtain the output parameters with dimensions, and obtain the M-group input and output data. S7. Based on the M sets of input and output data obtained in step S6, construct a safety assessment method for UAV aerodynamic deceleration control, and establish an assessment system that comprehensively considers the dimensions of system stability, structural integrity, flight status, energy management, control characteristics and environmental adaptability. The specific input feature parameters of the UAV aerodynamic deceleration control prediction model in step S1 are as follows: Flight status parameters include airspeed X1, angle of attack X2, sideslip angle X3, altitude X4, Mach number X5, dynamic pressure X6, roll angle X7, and pitch angle X8; Control input parameters include aileron deflection angle X9 and rudder deflection angle X. 10 Elevator deflection angle X 11 Throttle opening X 12 Air brake deflection angle X 13 and the deceleration parachute deployment area X 14 ; Environmental parameters include air density X 15 Temperature X 16 Wind speed X 17 Wind direction X 18 Atmospheric pressure X 19 and humidity X 20 ; The specific implementation method of step S2 includes the following steps: S2.

1. Based on considering airspeed and altitude in flight state parameters, and also taking into account the influence of environmental parameters on dynamic characteristics, a dynamic sensing layer is constructed, expressed as: in, Output for the dynamic sensing layer. For activation function, Let be the weight coefficient of the j-th input feature parameter in the UAV aerodynamic deceleration control prediction model. Let j be the j-th input feature parameter of the UAV aerodynamic deceleration control prediction model. For dynamic characteristic coefficients, As a high-impact factor, The characteristic time scale factor characterizes the characteristic response speed during the deceleration process of the UAV. The characteristic height scale factor characterizes the sensitivity of the UAV to changes in altitude; For the bias term of the dynamic sensing layer, j=1~20; S2.

2. Based on dynamic characteristics, the influence of angle of attack and dynamic pressure on aerodynamic forces is considered, and the Mach number effect is also taken into account to construct an aerodynamic characteristic layer, the expression of which is: in, Output for aerodynamic characteristics layer; This is the bias term for the aerodynamic characteristic layer. This is the lift characteristic coefficient; As a factor influencing compressibility effect, The characteristic angle of attack characterizes the system's response to attitude changes during deceleration. Characteristic dynamic pressure, which represents the adaptability of an unmanned aerial vehicle (UAV) to changes in aerodynamics; S2.

3. Construct a control decision layer. By establishing a direct information channel from the dynamic perception layer to the control decision layer, a rapid mapping from the initial dynamic state to the control decision is achieved. The expression is: in, To control the output of the decision-making level; The residual connectivity coefficient is determined by expert experience. To control the efficiency coefficient; As a stability influencing factor, To control the bias terms of the decision-making level; Characteristic force, representing the impact of changes in control force on the UAV; The characteristic rudder deflection angle characterizes the impact of rudder surface deflection on the UAV.

2. The method for safety assessment of aerodynamic deceleration control of an unmanned aerial vehicle (UAV) according to claim 1, characterized in that, The specific implementation method of step S3 is to weight and combine the outputs of the three hidden layers constructed in step S2, and introduce a nonlinear activation function and the feature scale factor of the corresponding index to achieve accurate prediction of flight state prediction index and control effect evaluation index. The nonlinear activation function introduced for the flight state prediction index is the hyperbolic tangent function, and the nonlinear activation function introduced for the control effect evaluation index is the sigmoid function, thus obtaining the flight state prediction index and control effect evaluation index. The flight state prediction index includes predicted airspeed Y1, predicted angle of attack Y2, predicted altitude Y3, predicted Mach number Y4, and predicted dynamic pressure Y5. The control effect evaluation index includes deceleration rate Y6, aerodynamic drag coefficient Y7, lift-to-drag ratio Y8, energy loss rate Y9, and stability index Y1. 10 Establish the mapping relationship between the model's hidden layer and the output metrics.

3. The method for safety assessment of aerodynamic deceleration control of an unmanned aerial vehicle (UAV) according to claim 2, characterized in that, The specific implementation method of step S4 includes the following steps: S4.

1. Design the basic loss function, using the mean squared error form, and calculate all output indices Y1~Y2. 10 The mean square error between the predicted and measured values ​​is the basic loss. ; S4.

2. Design the velocity loss term function, quantify the deceleration effect by evaluating the difference between predicted and actual airspeed and the corresponding state transition efficiency, while also considering the effects of air density and parachute deployment area, resulting in the following expression: in, For the weighting coefficient of the velocity loss term; This is the weighting coefficient for state transition efficiency; , These represent the kinetic energy levels of the predicted state and the current state, respectively. , These respectively characterize the work done on the predicted resistance and the actual resistance; S4.

3. Design the flight characteristic loss term function. By considering the influence of Mach number on aerodynamic characteristics and evaluating the accuracy of lift, drag, and moment predictions, a comprehensive evaluation index for flight quality is constructed by introducing characteristic length and aerodynamic parameters. The expression for the flight characteristic loss term function is as follows: in, The Mach number effect coefficient, This is the torque weighting coefficient. , These represent the predicted aerodynamic intensity level and the actual aerodynamic intensity level, respectively. , These respectively characterize the predicted torque level and the actual torque level; S4.

4. Design a stability loss term function. By evaluating three aspects—height variation, static stability, and dynamic stability—a complete stability evaluation system is constructed. The expression for the stability loss term function is: in, As a high-impact coefficient, For stability weighting coefficients, and These represent the mechanical energy level of the predicted state and the mechanical energy level of the current state, respectively. and These represent the predicted stability moment level and the actual stability moment level, respectively. This is the static stability coefficient; Characteristic energy factor; The characteristic torque factor; S4.

5. Construct a loss function for a UAV aerodynamic deceleration control prediction model, which is a composite loss function including a velocity loss term, a flight characteristic loss term, and a stability loss term.

4. The method for safety assessment of aerodynamic deceleration control of a UAV according to claim 3, characterized in that, The input feature parameter data of the UAV aerodynamic deceleration control prediction model after normalization in step S5 and the output index data of the UAV aerodynamic deceleration control prediction model obtained in step S3 are divided into training set and test set in a ratio of 8:

2.

5. The method for safety assessment of aerodynamic deceleration control of an unmanned aerial vehicle (UAV) according to claim 4, characterized in that, The specific implementation method of step S7 includes the following steps: S7.

1. Taking into account both aerodynamic efficiency and deceleration intensity, the stability and safety assessment index is obtained, expressed as: in, As a stability and safety assessment indicator, aerodynamic efficiency coefficient, The deceleration intensity adjustment coefficient is determined by expert experience or design specifications, and the aerodynamic efficiency is adopted. The deceleration intensity is characterized by the square of the ratio of the deceleration rate to the predicted airspeed. S7.

2. Based on the air brake deflection angle X 13 and the deceleration parachute deployment area X 14 Considering the structural load influence during the deceleration process of the deceleration device, the structural load safety assessment index is obtained, expressed as: in, As a structural load safety assessment indicator, The influence coefficient of the basic load. This is the load distribution factor for the device. The dynamic load adjustment coefficient is determined by expert experience or design specifications. This represents the maximum deflection angle of the air brake plate. This represents the maximum deployed area of ​​the deceleration parachute. The maximum dynamic pressure should be determined with reference to expert experience or design specifications. S7.

3. Flight envelope evaluation during deceleration considers speed, angle of attack limit, and dynamic pressure changes, resulting in a flight envelope safety evaluation index, expressed as: in, For flight envelope safety indicators, This is the speed limit factor. This is the angle-of-attack limiting factor. The dynamic pressure limit factor is determined by expert experience or design specifications. To limit speed, For maximum angle of attack, The maximum dynamic pressure should be determined with reference to expert experience or design specifications. S7.

4. Based on the energy loss rate during the deceleration process, and considering the impact of energy dissipation on system stability and control effectiveness, the energy management safety index is obtained, expressed as: in, For energy management safety indicators, For the maximum energy loss rate, The maximum deceleration rate should be determined with reference to expert experience or design specifications. The energy loss coefficient, The deceleration efficiency coefficient is determined by expert experience or design specifications. S7.

5. The coordinated operation of actuators involved in deceleration, including ailerons, rudder, elevator, dedicated deceleration device, air brakes, drag chute, and engine power regulation, to obtain control input safety indicators. The expression is: Where i = 9, 10, 11, 12; The maximum allowable values ​​for the corresponding input parameters i=9, 10, 11, and 12 should be determined with reference to expert experience or design specifications. , These are the coordination coefficients for conventional control surfaces and special deceleration devices, determined with reference to expert experience or design specifications. S7.

6. Taking into account changes in atmospheric parameters and wind field disturbances, obtain the environmental adaptability safety index. The expression is: in, The atmospheric parameter influence coefficient, This is the wind field disturbance coefficient, determined by expert experience or design specifications; The atmospheric parameter coupling index. The wind direction deviation attenuation coefficient is determined by expert experience or design specifications. Standard air density; Standard atmospheric pressure; The wind speed is determined with reference to expert experience, historical data, or design specifications. S7.

7. Based on steps S7.1-S7.6, and considering that when the structural load exceeds a certain threshold, the safety factor is rapidly reduced through exponential decay to prevent structural overload, and a comprehensive safety assessment index is obtained. ; S7.

8. Classify the comprehensive safety assessment indicators obtained in step S7.7 and provide corresponding safety level recommendations: when In the safe operating zone, continuously monitor various indicators and record performance data; when For areas of concern, the monitoring frequency of indicators will be increased, and early warnings will be issued when problems are detected by predicting performance trend changes. when This is a warning zone. At this point, the aerodynamic deceleration is too rapid, and it is necessary to reduce the deceleration intensity, strengthen manual monitoring, and prepare an emergency plan. when This is a danger zone; the deceleration procedure must be terminated immediately, the situation restored to safety, and the emergency procedure activated. in, , , These are the critical comprehensive safety assessment indicators corresponding to the safe operation zone, attention zone, warning zone, and danger zone.

6. A safety assessment system for aerodynamic deceleration control of unmanned aerial vehicles (UAVs), characterized in that, It includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed, implements the steps of a safety assessment method for aerodynamic deceleration control of an unmanned aerial vehicle as described in any one of claims 1-5.

Images