Multi-scene simulation and data evaluation method for unmanned aerial vehicle flight performance

Abstract

The present application relates to the technical field of unmanned aerial vehicles, and specifically relates to a method for simulating flight performance of unmanned aerial vehicles in multiple scenarios and evaluating data, comprising the following steps: firstly, a three-dimensional physical model of the unmanned aerial vehicle is established using computer-aided design, and aerodynamic and structural mechanics simulations are performed through computational fluid dynamics and finite element analysis; secondly, real-time meteorological data and terrain information are fused to simulate the flight performance of the unmanned aerial vehicle in complex flight environments; the simulation process is accelerated using high-performance computing, and machine learning algorithms are applied to optimize nonlinear parameters in the simulation model; finally, the actual flight data of the unmanned aerial vehicle is used for calibration, sensor data is processed through techniques such as Kalman filtering, the lift coefficient and drag coefficient are back-calculated, and a closed-loop optimization system is formed; this method can effectively improve simulation accuracy and adaptability in multiple scenarios, reduce the number of actual flight tests, reduce research and development costs and risks, and is suitable for performance evaluation and optimization of various unmanned aerial vehicles.

Description

Multi-scenario simulation and data evaluation methods for UAV flight performance Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) technology, and in particular to a method for multi-scenario simulation and data evaluation of UAV flight performance. Background Technology

[0002] With the rapid development of drone technology, drones have been widely used in various fields such as military, logistics, agriculture, and environmental monitoring. However, accurately evaluating the flight performance of drones in practical applications has become a significant technical challenge. Traditional flight performance evaluation methods mostly rely on actual flight tests, but this method is costly, risky, and difficult to comprehensively cover various flight conditions in complex flight environments. Therefore, flight performance evaluation methods based on computer simulation have gradually become a research focus. Through simulation technology, different flight scenarios can be simulated in a virtual environment, and the flight performance of drones can be predicted, significantly reducing the cost and risk of actual flight testing.

[0003] However, existing UAV simulation methods have several shortcomings. First, the simulation accuracy is insufficient, especially in aerodynamic and structural mechanics modeling. Simplified physical models are often used, neglecting important factors such as turbulence, complex terrain, and weather changes, leading to significant discrepancies between simulation results and actual flight performance. Second, existing simulation technologies lack sufficient adaptability to various scenarios, particularly when dealing with extreme flight conditions or complex environments (such as mountains and urban areas), making it difficult to simulate realistic flight dynamics. Finally, existing technologies have weak data verification and feedback mechanisms, failing to fully utilize actual flight data to calibrate and optimize simulation models, resulting in insufficient reliability of simulation results.

[0004] To address the aforementioned issues, this invention proposes a multi-scenario simulation and data evaluation method for UAV flight performance that combines high-precision aerodynamic simulation, structural mechanics simulation, real-time meteorological data fusion, and high-performance computing. By utilizing advanced simulation techniques such as computational fluid dynamics (CFD) and finite element analysis (FEM), and integrating machine learning optimization algorithms, this invention can accurately predict UAV flight performance in various complex environments. Furthermore, it uses actual flight data for calibration, forming a closed-loop optimization system, thereby improving the accuracy and adaptability of the simulation. This method provides strong technical support for UAV design, performance optimization, and safety assessment. Summary of the Invention

[0005] This invention proposes a multi-scenario simulation and data evaluation method for UAV flight performance, aiming to address the problems of insufficient simulation accuracy, lack of data verification, and limited multi-scenario application capabilities in existing technologies. By comprehensively utilizing high-precision modeling, environmental data fusion, high-performance computing, and machine learning techniques, this method can accurately simulate the performance of UAVs in complex flight environments, improving the reliability and practicality of simulation results.

[0006] Furthermore, this method begins by establishing a high-precision three-dimensional physical model of the UAV. Using computer-aided design (CAD) software, detailed models of the UAV's fuselage, wings, tail, and propellers are constructed, ensuring that the dimensions and shapes of each component are consistent with the actual UAV. For example, key parameters such as wing span, fuselage length, and propeller diameter are all set based on actual design data. This refined model lays the foundation for subsequent simulation analysis.

[0007] Furthermore, in the aerodynamic simulation, computational fluid dynamics (CFD) software is used to simulate the airflow around the UAV. By setting boundary conditions such as flight speed, angle of attack, and air density, aerodynamic parameters such as lift and drag of the UAV under different flight conditions are calculated. To more accurately simulate the turbulence effects in the actual flight environment, the standard k-ε turbulence model is adopted. This process helps us understand the aerodynamic performance of the UAV under various flight conditions, providing data support for design optimization.

[0008] Furthermore, structural mechanics simulations are performed. Using finite element analysis (FEM) software, aerodynamic loads obtained from aerodynamic simulations are applied to the structural model of the UAV to analyze the stress and deformation of the UAV under flight loads. By selecting appropriate material properties (such as the elastic modulus and Poisson's ratio of carbon fiber composites), the strength and safety of the UAV structure can be evaluated, potential stress concentration areas can be identified, and the reliability of the structural design can be ensured.

[0009] Furthermore, this method integrates multi-source environmental data. By accessing real-time meteorological data, such as wind speed, wind direction, temperature, and humidity, it can simulate the flight performance of UAVs under real weather conditions. Simultaneously, a high-precision terrain model of the flight area is obtained using a Geographic Information System (GIS), and the terrain data is imported into the simulation environment to assess the impact of terrain undulations on airflow and UAV flight performance. This integration of environmental data makes the simulation results more closely resemble reality.

[0010] Furthermore, to address the massive computational demands of high-precision simulations, this method incorporates high-performance computing techniques. By utilizing GPU parallel computing, complex simulation tasks are divided into multiple subtasks, which are then distributed across different computing cores for simultaneous computation, significantly reducing simulation time. For example, with GPU acceleration, simulation computation time can be reduced from tens of hours to several hours, greatly improving work efficiency.

[0011] Furthermore, this method also applies machine learning algorithms to optimize the simulation model. By collecting historical flight data of the UAV under different flight conditions, a deep neural network model is trained to optimize key parameters in the simulation model, such as the lift coefficient and drag coefficient. The machine learning model can better capture nonlinear and complex flight dynamics, improving the adaptability and prediction accuracy of the simulation model.

[0012] Furthermore, data verification and model calibration are performed. Multiple sensors, such as inertial measurement units (IMUs), GPS, and pitot tubes, are installed on the UAV to collect flight data in real time. This data is processed and analyzed, comparing the actual flight data with simulation results to calculate key parameters in the simulation model and calibrate the model. This process forms a closed-loop optimization system, continuously improving the accuracy of the simulation model.

[0013] The beneficial effects of this invention are:

[0014] First, by employing high-precision aerodynamic and structural mechanics simulations, combined with real-time meteorological data and complex terrain modeling, this invention can accurately predict the flight performance of UAVs under various flight environments. Compared to traditional simulation methods, this invention significantly improves simulation accuracy and more realistically reflects the flight performance of UAVs in complex environments. Furthermore, the use of high-performance computing technology accelerates the simulation process, greatly reducing the simulation time and improving simulation efficiency.

[0015] Secondly, this invention establishes a closed-loop optimization system by introducing machine learning algorithms and calibrating the simulation model using actual flight data. This system continuously optimizes the simulation model through multiple iterations, ensuring that the error between the simulation results and actual flight data is minimized, thereby improving the reliability of the simulation results. This approach not only reduces the number and cost of actual flight tests but also enhances the adaptability of UAVs in complex scenarios, providing strong technical support for UAV design optimization and performance evaluation. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for this invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 is a schematic diagram of the closed-loop process of multi-scenario flight simulation and result calibration according to an embodiment of the present invention;

[0018] Figure 2 is a schematic diagram of the overall system architecture according to an embodiment of the present invention;

[0019] Figure 3 is a schematic diagram of the actual flight data acquisition system architecture according to an embodiment of the present invention;

[0020] Figure 4 is a schematic diagram of environmental data fusion according to an embodiment of the present invention. Detailed Implementation

[0021] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. It should also be noted that, to make the embodiments more comprehensive, the following embodiments are the best and preferred embodiments, and those skilled in the art can use other alternative methods to implement some well-known technologies; moreover, the accompanying drawings are only for more specific description of the embodiments and are not intended to specifically limit the present invention.

[0022] It should be noted that the use of terms such as "an embodiment," "an embodiment," "an exemplary embodiment," and "some embodiments" in the specification indicates that the described embodiment may include a specific feature, structure, or characteristic, but not every embodiment necessarily includes that specific feature, structure, or characteristic. Furthermore, when a specific feature, structure, or characteristic is described in connection with an embodiment, implementing such a feature, structure, or characteristic in conjunction with other embodiments (whether explicitly described or not) should be within the knowledge of those skilled in the art.

[0023] Generally, terms can be understood at least partly from their use in context. For example, depending at least partly on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in a singular sense, or a combination of features, structures, or characteristics in a plural sense. Additionally, the term "based on" can be understood not necessarily to convey an exclusive set of factors, but rather, alternatively, depending at least partly on the context, to allow for the presence of other factors that are not necessarily explicitly described.

[0024] To better illustrate the multi-scenario simulation and data evaluation method for UAV flight performance of the present invention, the present invention will be described in detail below with reference to specific embodiments. These embodiments are intended to help those skilled in the art better understand and implement the present invention, but do not limit the scope of protection of the present invention.

[0025] This invention provides a multi-scenario simulation and data evaluation method for UAV flight performance, aiming to improve the accuracy and reliability of UAV flight performance evaluation. This method achieves performance evaluation of UAVs in complex flight environments by establishing a high-precision simulation model, fusing multi-source environmental data, applying high-performance computing and machine learning algorithms, and strengthening data verification and model calibration. The method of this invention will be described in detail below.

[0026] As shown in Figures 1 to 4

[0027] I. Establishing a high-precision simulation model

[0028] 1. Construction of 3D Physical Model

[0029] 1.1 Establishment of the geometric model

[0030] Use computer-aided design (CAD) software (such as SolidWorks) to create a 3D physical model of the fixed-wing UAV. The model should accurately reflect the actual structure and dimensions of the UAV, including the following components:

[0031] Wings: The wingspan is set at 2 meters, with an elliptical airfoil and a chord length that gradually decreases from 0.5 meters at the root to 0.2 meters at the tip.

[0032] The fuselage is 1.5 meters long, with an elliptical cross-section and a maximum diameter of 0.3 meters. The streamlined design reduces drag.

[0033] Tail fins: including horizontal tail fins and vertical tail fins. The horizontal tail fin has a wingspan of 0.6 meters and the vertical tail fin has a height of 0.3 meters.

[0034] Propeller: diameter set at 30 cm, number of blades 2, pitch 10 inches.

[0035] 1.2 Mesh Generation

[0036] After establishing the geometric model, mesh the model using meshing software (such as ANSYS Meshing). The specific steps are as follows:

[0037] Classification type: Unstructured tetrahedral meshes are used to accommodate complex geometries.

[0038] Grid density: A denser grid is used in critical areas (such as the leading edge, trailing edge, and near the propeller), with a minimum grid size of 1 mm; a coarser grid, up to 50 mm, is used in areas far from the fuselage.

[0039] Total number of grid cells: controlled between 5 million and 10 million cells to balance simulation accuracy and computational resources.

[0040] II. Aerodynamic Simulation

[0041] 1. Simulation settings

[0042] 2.1 Software Selection

[0043] Aerodynamic simulations were performed using the computational fluid dynamics (CFD) software ANSYS Fluent.

[0044] 2.2 Physical Model Setup

[0045] Fluid model: Select a three-dimensional, steady-state, incompressible flow model.

[0046] Turbulence model: The standard k-ε turbulence model is adopted, which is suitable for external flows at high Reynolds numbers.

[0047] Air properties: density

[0048] Dynamic viscosity Pa s

[0049] 2. Boundary Condition Setting

[0050] 2.3 Entry Boundary

[0051] Speed ​​entry: Set flight speed m / s

[0052] Turbulence intensity: set to 5%

[0053] Turbulent viscosity ratio: set to 10

[0054] 2.4 Export Boundary

[0055] Pressure outlet: set to ambient static pressure Pa

[0056] 2.5 Wall conditions

[0057] Drone surface: set to a non-slip wall (speed zero), hot wall temperature set to ambient temperature. K

[0058] Ground: If simulating low-altitude flight, the ground is set as a moving wall with the same speed as free flow to simulate the ground effect.

[0059]

[0060] 2.6 Numerical Methods

[0061] Pressure-velocity coupling: using the SIMPLE algorithm

[0062] Discrete scheme: Second-order upwind scheme, to improve computational accuracy.

[0063] Convergence criterion: residuals less than

[0064] 4. Calculation and Result Analysis

[0065] 2.7 Calculation Process

[0066] Initialization: The initial velocity across the field is set at 30 m / s, and the direction is the same as the inlet velocity.

[0067] Number of iterations: Generally, 1000 to 5000 iterations are required, depending on the convergence results.

[0068] 2.8 Result Extraction

[0069] Lift coefficient and drag coefficient Calculation:

[0070]

[0071] in:

[0072] The lift force acting on the drone is a force perpendicular to the direction of the incoming flow, which is automatically calculated by the software.

[0073] The resistance experienced by the drone is the force along the direction of the incoming flow.

[0074] Pressure distribution and velocity field: Extract the pressure coefficient distribution and velocity vector of the flow field on the surface of the UAV to analyze its aerodynamic characteristics.

[0075] III. Structural Mechanics Simulation

[0076] 1. Simulation settings

[0077] 3.1 Software Selection

[0078] Structural mechanics simulation was performed using the finite element analysis (FEM) software ANSYS Mechanical.

[0079] 3.2 Material Properties

[0080] Wing and fuselage materials: carbon fiber composite materials

[0081] elastic modulus GPa

[0082] Poisson's ratio

[0083] density

[0084] 2. Loads and Constraints

[0085] 3.3 Load Application

[0086] Aerodynamic loads: The pressure distribution obtained from CFD simulation is imported into the structural model as surface loads.

[0087] Inertial load: Considering the weight of the UAV, the acceleration due to gravity in the gravitational field. m / .

[0088] 3.4 Constraints

[0089] Fixed support: Since the drone is free and unrestrained in flight, there is no need to add support to simulate the force conditions under flight conditions.

[0090] Add fixed supports. However, to prevent rigid body movement, displacement constraints can be applied at a certain point on the fuselage.

[0091] 3. Solution and Result Analysis

[0092] 3.5 Solver Settings

[0093] Analysis type: Static analysis

[0094] Solver control: Default settings

[0095] 3.6 Result Extraction

[0096] Stress analysis: Extract the stress distribution of the wing and fuselage, focusing on the maximum principal stress and equivalent stress (von Mist).

[0097] Deformation analysis: Observe the deformation of the structure to ensure that the deformation is within the allowable range.

[0098] 3.7 Security Assessment

[0099] Strength check: Ensure the maximum stress is less than the allowable stress of the material, and calculate the safety factor.

[0100]

[0101] in,

[0102] IV. Integration of Multi-Source Environmental Data

[0103] 1. Introduction of real-time meteorological data

[0104] 4.1 Data Acquisition

[0105] Obtain real-time weather data for the flight area from meteorological data APIs (such as OpenWeatherMap), including

[0106] Wind speed: 10m / s

[0107] Wind direction: Southwest (225°)

[0108] Temperature: 20°C

[0109] Humidity: 70%

[0110] 4.2 Simulation Adjustment

[0111] Wind speed and direction: In the CFD simulation, the inlet velocity is adjusted to the composite incoming flow velocity, taking into account the combination of flight speed and wind speed.

[0112] Temperature and humidity: The density and viscosity of the air are adjusted according to the standard atmospheric model.

[0113] 2. Integration of terrain data

[0114] 4.3 Terrain Model Acquisition

[0115] Use GIS software (such as ArcGIS) to acquire digital elevation model (DEM) data of the flight area and generate a three-dimensional terrain model.

[0116] 4.4 The Influence of Topography on Airflow

[0117] Terrain Import: Import the terrain model into the CFD simulation environment as the bottom boundary of the computational domain.

[0118] Grid generation: Refine the grid on the terrain surface to capture the impact of terrain details on airflow.

[0119] Simulation run: Rerun the CFD simulation to observe the airflow changes caused by terrain undulations, such as eddies and updrafts.

[0120] V. Applying high-performance computing and machine learning to optimize models

[0121] High-performance computing acceleration

[0122] 5.1 GPU Parallel Computing

[0123] Hardware configuration: High-performance computing server equipped with NVIDIA Tesla V100 GPUs, each with 5120 CUDA cores.

[0124] Parallel strategy: Utilize CUDA parallel computing to divide the computation domain into multiple subdomains, with each subdomain being computed by a GPU core.

[0125] Acceleration effect: Simulation time is reduced from the traditional 30 hours to 6 hours, improving computational efficiency.

[0126] Machine learning model optimization

[0127] 5.2 Dataset Preparation

[0128] Training data: Collect historical data of the UAV under different flight conditions, including flight speed, angle of attack, wind speed, and lift coefficient. and drag coefficient Data volume: Must contain at least 1000 sets of valid data.

[0129] 5.3 Model Construction

[0130] Algorithm selection: Deep Neural Network (DNN) model is adopted.

[0131] Network structure:

[0132] Input layer: flight speed, angle of attack, wind speed; Hidden layers: 3 layers, 128 neurons per layer, ReLU activation function; Output layer: lift coefficient. and drag coefficient The activation function is a linear function.

[0133] 5.4 Model Training; Loss Function:

[0134]

[0135] Optimization algorithm: The Adam optimizer is used, and the learning rate is set to 0.001.

[0136] Training rounds: 1000 rounds of iterative training, monitoring the convergence of the loss function.

[0137] 5.5 Model Validation

[0138] Validation set: 20% of the dataset is allocated as the validation set.

[0139] Evaluation metrics: Calculate the mean squared error (MSE) and coefficient of determination (...).

[0140] Coefficient of determination:

[0141]

[0142]

[0143] in, For the true value, For predicted values, This is the average of the true values.

[0144] VI. Data Validation and Model Calibration: Actual Flight Data Acquisition 6.1 Sensor Configuration

[0145] IMU (Inertial Measurement Unit): Measures the drone's acceleration and angular velocity, with a sampling frequency of 100Hz. GPS Module: Records the drone's position information with an accuracy within 1 meter. Pitot Tube: Measures the drone's relative airspeed with an accuracy of 0.1 m / s. 6.2 Data Recording

[0146] Flight conditions: Test flights were conducted under different speeds, angles of attack, and environmental conditions to collect multiple sets of data.

[0147] Data storage: Data is stored in real time using an onboard data logger or transmitted wirelessly to a ground station.

[0148] Data Processing: 6.3 Kalman Filtering

[0149] Filtering purpose: To remove sensor noise and improve data accuracy.

[0150] Filtering model: State vector: ,in For speed, For the angle of attack, Let be the pitch angle. State transition equation:

[0151]

[0152] Observation equation:

[0153]

[0154] Noise assumption: and It is Gaussian white noise.

[0155] Filtering steps:

[0156] predict:

[0157]

[0158]

[0159]

[0160]

[0161]

[0162] 3. Simulation model calibration

[0163] 6.4 Parameter Inversion

[0164] Calculation of lift coefficient:

[0165]

[0166] in, , Vertical acceleration, from IMU data. Drag coefficient calculation:

[0167]

[0168] in, , This refers to horizontal acceleration. 6.5 Model Adjustment

[0169] Comparative analysis: The actual calculations obtained... and Compare the values ​​with the simulation model's predictions. Parameter adjustment: If the error exceeds a predetermined threshold (e.g., 5%), adjust the aerodynamic parameters in the simulation model and re-perform the CFD simulation. VII. Closed-Loop Optimization and Multi-Scenario Simulation

[0170] 1. Closed-loop optimization process

[0171] 7.1 Iterative Process

[0172] step:

[0173] 2. Flight Test Data Acquisition: Obtain actual flight data. 3. Data Processing and Calibration: Calculate actual... and 4. Model Update: Update the simulation model parameters. 5. Resimulate: Perform a new simulation calculation.

[0174] Number of iterations: Typically, 3-5 iterations are required, depending on the model's convergence. 2. Multi-scenario simulation and evaluation 7.2 Flight scenario setting

[0175] Scenario 1: High wind speed conditions, wind speed 20 m / s, wind direction changes randomly. Scenario 2: High angle of attack flight, angle of attack reaching 15°, simulating climb and dive. Scenario 3: Complex terrain, such as mountains and canyons, with drastic terrain undulations. 7.3 Simulation and Analysis

[0176] Performance metrics: lift, drag, pitch moment, sideslip force, etc. Stability assessment: Analyzing the flight stability of the UAV in different scenarios, such as whether stall, sideslip, or other adverse phenomena occur. Handling capability assessment: Evaluating the UAV's response speed, control precision, etc. 7.4 Application of Results

[0177] Design optimization: Based on the simulation results, the structure and control system of the UAV are optimized, such as adjusting the wing airfoil and increasing the stabilizer area.

[0178] Flight Strategy Formulation: Based on the simulation results of different scenarios, formulate corresponding flight plans and countermeasures. VIII. Visualization and Report Generation 1. Visualization of Simulation Results 8.1 Software Tools

[0179] 8.2 Graphical Display

[0180] Flow field visualization: using ANSYS CFD-Post or Tecplot software. Structural result visualization: using the post-processing tools included with ANSYS Mechanical. Isobars and isobaric surfaces: displaying the pressure distribution on the UAV surface. Streamlines and vector diagrams: showing the direction and velocity of airflow. Stress cloud diagrams: displaying the stress distribution of structural components and identifying high-stress areas. Deformation diagrams: displaying structural deformation, with magnified deformation for better observation.

[0181] 2. Report Generation

[0182] 8.3 Report Content

[0183] Simulation setup: Detailed explanation of the simulation boundary conditions, model parameters, and calculation methods.

[0184] Results analysis includes numerical results and visualizations to evaluate the performance of the UAV.

[0185] Optimization suggestions: Based on simulation and actual data, propose improvements to the design and operation.

[0186] 8.4 Format and Output

[0187] Document format: PDF or Word format, including table of contents, chapters and appendices.

[0188] Chart clarity: Ensure all charts are high resolution for easy reading and display.

[0189] IX. Precautions

[0190] 9.1 Data Accuracy

[0191] Sensor calibration: All sensors are calibrated before data acquisition to ensure accurate and reliable data.

[0192] Data backup: Real-time backup of collected data to prevent data loss.

[0193] 9.2 Computing Resources

[0194] Hardware requirements: High-performance computing requires sufficient hardware support, and computing resources should be planned in advance.

[0195] Software Licensing: Ensure that all software used has a valid license.

[0196] 9.3 Security

[0197] Flight test safety: During actual flight tests, comply with flight regulations and ensure the safety of personnel and equipment.

[0198] Data security: Protecting the confidentiality of data and preventing unauthorized access.

[0199] This invention encompasses any substitutions, modifications, equivalent methods, and solutions made within the spirit and scope of this invention. To provide the public with a thorough understanding of this invention, specific details are described in detail in the following preferred embodiments; however, those skilled in the art will fully understand the invention even without these details. Furthermore, to avoid unnecessary misunderstanding of the essence of this invention, well-known methods, processes, procedures, components, and circuits are not described in detail.

[0200] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for multi-scenario simulation and data evaluation of UAV flight performance, characterized in that, The process includes the following steps: Step 1, 3D Physical Model Construction: A 3D geometric model of the UAV is built using computer-aided design (CAD) software. This model includes the fuselage, wings, tail, and propeller components, ensuring that the model reflects the actual geometric dimensions of the UAV. Based on the UAV's design parameters, the wingspan is set to 2 meters, the fuselage length to 1.5 meters, and the propeller diameter to 30 centimeters. This geometric model is used for aerodynamic and structural mechanics analysis in subsequent simulations. Step 2, Aerodynamic Simulation: Computational Fluid Dynamics (CFD) simulation software is used. Flight speed, angle of attack, and air density parameters are input, with the flight speed set to 30 m / s, the angle of attack range set to -5°C to 15°, and the air density set to 1.225 kg / m³. 3 The standard k-ε model in turbulence models is used to simulate the turbulent airflow around the UAV; the Navier-Stokes equations are solved to calculate the airflow distribution on the UAV surface, and the lift and drag coefficients are output; the lift coefficient of the UAV at different angles of attack is obtained through CFD simulation. and drag coefficient Step 3: Structural Mechanics Simulation: Use finite element analysis (FEM) simulation software to perform structural mechanics simulation, applying the aerodynamic loads obtained from the CFD simulation to the three-dimensional geometric model of the UAV; select material parameters and input flight loads and boundary conditions; calculate the structural stress and strain of the UAV under flight loads, output the stress concentration area and deformation, and evaluate the safety of the structural design; Step 4: Integrate Real-Time Environmental Data: Obtain real-time meteorological data from external meteorological data sources, including wind speed of 10 m / s, wind direction of northeast, temperature of 20°C, and humidity of 60%, and input this data into the CFD simulation software; use geographic information systems... A high-precision terrain model of the flight area is obtained from a GIS system. A 3D terrain map of the flight area is generated using a Digital Elevation Model (DEM). The terrain model is then imported into a CFD simulation environment to analyze the impact of terrain undulations on airflow and UAV flight performance. Step 5: High-performance computing and machine learning optimization: GPU parallel computing is used to accelerate CFD and FEM simulation tasks. The simulation tasks are divided into multiple sub-tasks and allocated to GPU cores for parallel computing to improve simulation speed. The aerodynamic parameters of the UAV simulation model are optimized using the Deep Neural Network (DNN) algorithm from machine learning. The neural network parameters are optimized by minimizing the following loss function: Step 6, Data Validation and Calibration: The model is trained using the backpropagation algorithm and actual flight data to improve accuracy under nonlinear flight conditions. An inertial measurement unit (IMU), GPS module, and pitot tube are installed on the UAV to collect its position, velocity, acceleration, and airflow velocity data during flight. A Kalman filter is used to process the flight data, removing noise and outliers. The update equation is as follows: in, This is the state estimate. For measured values, Kalman gain; lift coefficient calculated using actual flight data. The lift force is calculated using the following formula: Among them, lift , For the quality of drones, It is the acceleration due to gravity. For flight speed, air density, The wing area is used for simulation. Step 7: Closed-loop optimization of the simulation model: The simulation model that has been verified and calibrated by actual data is reused for simulation. The model parameters are iteratively optimized until the error between the simulation results and the actual flight data is less than a predetermined threshold. The simulation and data calibration process is repeated until a high-precision UAV flight performance evaluation model is obtained.

2. The method for multi-scenario simulation and data evaluation of UAV flight performance according to claim 1, characterized in that, In the establishment of the three-dimensional physical model, the wingspan is set to 2 meters, the fuselage length to 1.5 meters, and the propeller diameter to 30 centimeters. Specific parameters can be adjusted according to the actual design documents of the UAV.

3. The method for multi-scenario simulation and data evaluation of UAV flight performance according to claim 1, characterized in that, The CFD simulation process uses the standard k-ε turbulence model to simulate the turbulence effect of airflow, so as to more accurately simulate the aerodynamic performance of the UAV under different angles of attack and wind speeds.

4. The method for multi-scenario simulation and data evaluation of UAV flight performance according to claim 1, characterized in that, The high-performance computing utilizes GPU parallel computing technology to divide the simulation task into 64 parallel computing units, which are then computed simultaneously on multiple GPU cores, reducing the simulation computation time from 30 hours to 6 hours.

5. The method for multi-scenario simulation and data evaluation of UAV flight performance according to claim 1, characterized in that, The terrain model is constructed by generating a digital elevation model (DEM) using GIS data and importing it into a simulation environment to analyze the impact of terrain undulations in the flight area on the flight performance of the UAV.

6. The method for multi-scenario simulation and data evaluation of UAV flight performance according to claim 1, characterized in that, The machine learning optimization process uses a deep neural network (DNN) algorithm to train the lift and drag coefficients in historical flight data, and then uses a backpropagation algorithm to adjust the neural network parameters to improve the adaptability and accuracy of the simulation model.

7. The method for multi-scenario simulation and data evaluation of UAV flight performance according to claim 1, characterized in that, During the data verification and calibration process, data is collected from actual flights and processed using a Kalman filter to back-calculate the aerodynamic parameters in the simulation model. The model is then iteratively calibrated multiple times to ensure that the error between the simulation results and the actual data is less than 1.1%.

8. The method for multi-scenario simulation and data evaluation of UAV flight performance according to claim 1, characterized in that, By inputting various meteorological parameters and terrain models, different simulation scenarios are generated to simulate the flight performance of drones under different airflow and terrain conditions, with wind speeds ranging from 5 m / s to 20 m / s and angles of attack ranging from -10° to 20°.

9. The method for multi-scenario simulation and data evaluation of UAV flight performance according to claim 1, characterized in that, The closed-loop optimization simulation model generates the flight performance curve of the UAV after reaching a set error threshold through multiple data feedbacks and model iterations, and provides flight strategy suggestions for different scenarios.

Images