Unmanned aerial vehicle testing method, device and equipment

Abstract

The present invention provides an unmanned aerial vehicle (UAV) testing method, apparatus, and equipment, belonging to the field of UAV technology. These methods address the low efficiency, long testing time, high testing costs, and difficulty in ensuring accuracy of traditional UAV testing. The method comprises: generating a test command and sending it to the UAV; obtaining flight status data from the UAV; processing the flight status data to obtain performance data, including at least one of endurance, climb rate, maximum range, maximum altitude, and maximum flight speed; and inputting the flight status and performance data into a flight status test model for processing to obtain test data. This solution improves the efficiency and accuracy of UAV testing and reduces testing costs.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles, and in particular to a method, device and equipment for testing an unmanned aerial vehicle. Background Art

[0002] As the global low-altitude economy enters a period of rapid development, the application boundaries of unmanned aerial vehicles (UAVs) continue to expand. In commercial scenarios, emerging models such as urban air mobility (UAM) and emergency rescue are gradually being implemented. Statistics show that the number of registered commercial drones worldwide has increased by an average of 34% annually, but the accident rate has increased by 21% during the same period, exposing the technical limitations of existing testing systems.

[0003] The current mainstream drone testing system is still centered around manual operation, and its technical framework consists of three levels:

[0004] (1) Physical environment testing: Relying on open-air test sites and wind tunnel laboratories, flight data is obtained through repeated takeoffs and landings. A certain type of logistics drone needs to complete more than 300 takeoff and landing tests, which takes more than 45 days and cannot reproduce extreme weather conditions.

[0005] (2) Functional Verification Test: A script-controlled semi-automated test bench is used, but key steps such as sensor calibration and control parameter debugging still require manual intervention. Test data shows that differences in operator skills can cause navigation accuracy test results to fluctuate by as much as ±18%.

[0006] (3) Environmental adaptability testing: This test uses simple simulation devices to generate single-factor environments such as vibration and temperature changes, but lacks the ability to simulate multi-physics field coupling. A high-altitude scientific research drone failed to detect power attenuation under the combined operating conditions of "low temperature + low pressure," resulting in a mission failure rate of up to 37%.

[0007] As can be seen from this, traditional testing methods mainly rely on manual operation, which has problems such as low testing efficiency, long testing time, test results affected by human factors, and difficulty in ensuring accuracy. Therefore, an automated and high-precision UAV testing method is urgently needed. Summary of the Invention

[0008] The present invention provides a method, device and equipment for testing unmanned aerial vehicles, which solves the problems that traditional unmanned aerial vehicle testing methods mainly rely on manual operation, have low testing efficiency, long testing time, high testing costs, test results affected by human factors, and are difficult to ensure accuracy.

[0009] In order to solve the above technical problems, the technical solutions of the present invention are as follows:

[0010] An embodiment of the present invention provides a method for testing an unmanned aerial vehicle, comprising:

[0011] Generate test instructions and send them to the UAV;

[0012] Obtain flight status data of unmanned aerial vehicles;

[0013] processing the flight status data to obtain performance data, the performance data including at least one of endurance time, climb rate, maximum range, maximum flight altitude, and maximum flight speed;

[0014] The flight status data and the performance data are input into a flight status test model for processing to obtain test data.

[0015] Optionally, generating a test instruction and sending it to the unmanned aerial vehicle includes:

[0016] According to the preset route data, the waypoint coordinate data is obtained;

[0017] Obtaining flight speed control data and flight attitude angle control data according to the waypoint coordinate data;

[0018] A test instruction is generated according to the waypoint coordinate data, the flight speed control data and the flight attitude angle control data and is sent to the unmanned aerial vehicle.

[0019] Optionally, obtaining the flight status data of the unmanned aerial vehicle includes:

[0020] acquiring at least one of attitude data, altitude data, speed data, and battery status data of the UAV based on a plurality of sensors installed on the UAV;

[0021] performing abnormality detection processing on at least one of the posture data, the height data, the speed data, and the battery status data to obtain a plurality of detection data;

[0022] The plurality of detection data are combined and processed according to a preset format to obtain flight status data of the unmanned aerial vehicle.

[0023] Optionally, processing the flight status data to obtain performance data includes:

[0024] Obtaining a cruising time and a climbing rate according to the battery status data and the speed data;

[0025] Obtaining a maximum range based on the endurance time data and the speed data;

[0026] obtaining a maximum flight altitude according to the altitude data, the battery status data, and the speed data;

[0027] A maximum flight speed is obtained according to the battery status data and the attitude data.

[0028] Optionally, the flight status data and the performance data are input into a flight status test model for processing to obtain test data, including:

[0029] Processing the flight status data and the performance data to obtain an input vector;

[0030] The input vector is input into the flight state test model for processing to obtain test data; the flight state test model processes the input vector through a node function to obtain an intermediate result, and the intermediate result is subjected to deviation correction to obtain test data.

[0031] Optionally, the flight status test model is trained through the following process:

[0032] Obtain historical flight status data, historical performance data, and historical fault type data;

[0033] Summarizing the historical flight status data, the historical performance data, and the historical fault type data to obtain sample data;

[0034] Randomly sampling the sample data to obtain a training data set and a test sample data set;

[0035] Inputting the training data set into the flight state test model for processing to obtain a training result data set;

[0036] Comparing the training result data set with the test sample data set to obtain a comparison result;

[0037] According to the comparison result, the node function parameters of the flight status test model are adjusted to obtain a trained flight status test model.

[0038] Optionally, the method further includes:

[0039] Outputting a UAV test report, wherein the UAV test report includes: UAV performance data and test data.

[0040] An embodiment of the present invention further provides an unmanned aerial vehicle testing device, comprising:

[0041] A generation module, used for generating test instructions and sending them to the UAV;

[0042] An acquisition module is used to obtain the flight status data of the unmanned aerial vehicle;

[0043] The processing module is used to process the flight status data to obtain performance data; and input the flight status data and the performance data into a flight status test model for processing to obtain test data.

[0044] An embodiment of the present invention further provides a computing device, comprising: a processor and a memory storing a computer program, wherein the computer program executes the above method when executed by the processor.

[0045] An embodiment of the present invention further provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the above method.

[0046] The technical solution of the present invention includes at least the following effects:

[0047] The above-mentioned solution of the present invention generates test instructions and sends them to the UAV; obtains the UAV's flight status data; processes the flight status data to obtain performance data, including at least one of endurance time, climb rate, maximum range, maximum altitude, and maximum speed; and inputs the flight status and performance data into a flight status test model for processing to obtain test data. Compared to traditional manual testing methods, this solution improves test efficiency and coverage through digital processing and model-based evaluation. It can also dynamically adapt to the needs of different test scenarios, improving the efficiency and accuracy of UAV testing and reducing testing costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 is a flow chart of a method for testing an unmanned aerial vehicle provided by an embodiment of the present invention;

[0049] Figure 2 1 is a schematic diagram of the architecture of a flight state test model in an embodiment of the present invention;

[0050] Figure 3 is a structural diagram of an unmanned aerial vehicle testing device provided by an embodiment of the present invention;

[0051] Figure 4 It is a structural diagram of a computing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0053] like Figure 1 As shown, an embodiment of the present invention provides a method for testing an unmanned aerial vehicle, comprising:

[0054] Step 11: Generate a test command and send it to the UAV;

[0055] Step 12: Obtain flight status data of the UAV;

[0056] Step 13: Process the flight status data to obtain performance data, where the performance data includes at least one of endurance time, climb rate, maximum range, maximum flight altitude, and maximum flight speed;

[0057] Step 14: Input the flight status data and the performance data into a flight status test model for processing to obtain test data.

[0058] In this embodiment, the specific objectives of this test are first determined based on the design requirements and expected performance indicators of the UAV. For example, if the UAV's endurance is to be tested, the instructions may focus on having the aircraft fly for a long time at a specific speed and altitude; if the climb rate is to be tested, the instructions will require the aircraft to perform a rapid climb under different initial conditions. Based on the test objectives, detailed test instructions are designed. The instructions usually include the flight mission type (such as cruise, climb, landing, etc.), flight parameters (such as speed, altitude, heading, etc.), mission execution time, etc. For example, the instructions may require the aircraft to cruise in a straight line at a speed of 50m / s at an altitude of 1000m for 30 minutes, while collecting flight status data every 5 seconds; the designed instructions are encoded and packaged according to the communication protocol that the unmanned aerial vehicle can recognize to ensure that the instructions can be transmitted to the aircraft accurately; a reliable communication link is established with the unmanned aerial vehicle through wireless communication equipment; before sending the instructions, the communication link needs to be tested to ensure that the signal strength, stability and data transmission rate meet the requirements; the packaged test instructions are sent to the unmanned aerial vehicle through the communication link; during the transmission process, technical means such as checksum and retransmission mechanisms are used to ensure the integrity and accuracy of the instructions.

[0059] UAVs are equipped with a variety of sensors for real-time flight status data collection. Common sensors include inertial measurement units (IMUs, used to measure acceleration and angular velocity), barometers (used to measure altitude), pitot tubes (used to measure airspeed), and gyroscopes (used to measure attitude angles). The appropriate data collection frequency is set based on the test requirements and the dynamic characteristics of the aircraft. For flight status parameters that change at high speeds, such as acceleration and angular velocity, a higher collection frequency (such as 100 Hz or higher) may be required. For some parameters that change relatively slowly, such as altitude and airspeed, the collection frequency can be appropriately reduced (such as 10 Hz). The flight status data collected by the sensors is transmitted to the ground test equipment via the data link on the aircraft. The data link can use the same communication method as command transmission or a dedicated data transmission channel. After receiving the flight status data, the ground test equipment performs preliminary processing and storage on it. The processing content includes data verification and format conversion to ensure the accuracy and availability of the data. The storage method can use a database, file system, etc. to facilitate subsequent data processing and analysis.

[0060] Since the flight status data collected by the sensor may contain noise and interference, it needs to be filtered; commonly used filtering methods include low-pass filtering, high-pass filtering, Kalman filtering, etc., to remove noise and improve data quality; the data collected by the sensor is calibrated to eliminate sensor errors; the calibration method can adopt laboratory calibration, on-site calibration, etc., and the appropriate calibration method is selected according to the characteristics of the sensor and the use environment; after the above processing, the flight status data can be used to calculate performance data, where the performance data includes at least one of the endurance time, climb rate, maximum range, maximum flight altitude, and maximum flight speed; for example, the climb rate is calculated based on the change data of the aircraft's altitude over time; the aircraft's endurance time is calculated by recording the time of the aircraft's take-off and landing.

[0061] The test model is trained using historical flight data and corresponding performance data. During the training process, the model parameters need to be adjusted so that the model can accurately predict the performance of the aircraft. The training data should cover as many flight conditions and aircraft states as possible to improve the generalization ability of the model. After the model training is completed, the flight state data and performance data are integrated to form a data format suitable for model input. For example, data from different sensors are arranged in time series, and performance data is added to the data as a label. In order to improve the training effect and prediction accuracy of the model, the input data is normalized and mapped to a specific interval. The integrated and normalized data is input into the trained flight state test model, and the model makes predictions based on the input data and outputs test data. The test data includes aircraft performance evaluation indicators (such as flight quality scores, reliability assessments, etc.) and fault warning information. After obtaining the performance data and test data, they can also be summarized and organized into a measurement report and output via a printer or display to timely reflect the current test results of the unmanned aerial vehicle.

[0062] This solution improves test efficiency and coverage through digital processing and model-based evaluation, and can dynamically adapt to the requirements of different test scenarios, thereby improving the efficiency and accuracy of UAV testing and reducing testing costs.

[0063] In an optional embodiment of the present invention, step 11 may include:

[0064] Step 111, obtaining waypoint coordinate data according to preset route data;

[0065] Step 112, obtaining flight speed control data and flight attitude angle control data based on the waypoint coordinate data;

[0066] Step 113 : generating a test instruction based on the waypoint coordinate data, the flight speed control data, and the flight attitude angle control data, and sending the instruction to the unmanned aerial vehicle.

[0067] In this embodiment, the preset route data refers to the route data pre-designed before the UAV is tested, including the starting point, end point, and intermediate key waypoints of the flight mission, which are usually expressed in coordinate forms such as latitude, longitude, and altitude. Based on the preset route data, the precise coordinate data of each waypoint can be extracted through a map service or flight planning software. The flight speed between each waypoint is calculated based on the distance between the waypoints, the time requirement of the flight mission, and the performance parameters of the UAV, including parameters such as average speed, maximum speed, and acceleration. The flight attitude angle includes the pitch angle, yaw angle, and roll angle, which determine the flight direction and attitude of the UAV. Based on the relative position relationship between the waypoints and the flight speed, the required flight attitude angle change between each waypoint can be calculated.

[0068] Specifically, according to the geographic coordinate conversion, the latitude and longitude coordinates are converted into plane coordinates:

[0069]

[0070] Where φ is the geographic latitude, λ is the geographic longitude, E is the plane easting coordinate, N is the plane northing coordinate, k0 is the projection scale factor, which is taken as 0.9996 in this example, f is the radius of curvature, T is the latitude function, C is the ellipsoid parameter, A is the meridian difference parameter; E0 is the easting offset; M is the meridian arc length; M0 is the meridian arc length of the central meridian

[0071] According to the waypoint sequence {p i =(x i ,y i ,z i )} n i＝1 , the track curve can be obtained according to the following formula:

[0072] S(t)=a i (tt i ) 3 +b i (tt i ) 2 +c i (tt i )+d i ,t∈[t i ,t i+1 ]

[0073] Where t is the normalized path parameter, t∈[0,1]; a i 、b i 、c i d i is the cubic polynomial coefficient matrix;

[0074] according to:

[0075]

[0076] Perform segmented speed planning; where m is the mass of the drone; g is the acceleration of gravity; γ is the climb angle; ρ is the air density; A is the windward area of ​​the drone; C rr is the rolling resistance coefficient; C D is the aerodynamic drag coefficient; v climb v is the climbing speed of the UAV; cruise is the cruising speed of the UAV; v descent is the descent speed of the UAV; v0 is the initial speed of the UAV when it descends; a safe is the safety acceleration of the drone when it descends; z is the initial height of the drone when it descends; z target is the target height of the UAV when it descends, μ is the equivalent rolling resistance coefficient; v is the airspeed of the UAV; P max The maximum available power of the UAV power system.

[0077] according to:

[0078]

[0079] Calculate the heading angle; where ψ is the heading angle, δ ψ is the magnetic declination correction term, x k 、x k+1 、y k 、y k+1 is the coordinate position of the drone.

[0080] according to:

[0081]

[0082] Calculate the roll angle; where φ is the roll angle, R is the instantaneous turning radius, and Δψ is the change in the angular direction between adjacent segments.

[0083] according to:

[0084]

[0085] Calculate the pitch angle; where θ is the pitch angle, θ trim is the trim angle correction.

[0086] The waypoint coordinate data, flight speed control data, and flight attitude angle control data are integrated into test instructions. These instructions include detailed information such as the flight path, speed curve, and attitude adjustment strategy. These test instructions are sent to the UAV via wireless communication technology. After receiving the instructions, the UAV will execute the flight mission according to the instructions.

[0087] In an optional embodiment of the present invention, step 12 may include:

[0088] Step 121, obtaining at least one of attitude data, altitude data, speed data, and battery status data of the UAV based on a plurality of sensors installed on the UAV;

[0089] Step 122, performing abnormality detection processing on at least one of the posture data, altitude data, speed data, and battery status data to obtain a plurality of detection data;

[0090] Step 123 , merging the plurality of detection data according to a preset format to obtain flight status data of the UAV.

[0091] In this embodiment, the unmanned aerial vehicle utilizes a variety of high-precision sensors installed thereon to capture key flight information in real time. These sensors include: attitude sensors, such as an inertial measurement unit composed of a combination of gyroscopes, accelerometers, and magnetometers, which are used to measure the pitch, yaw, roll, and other attitude parameters of the unmanned aerial vehicle, reflecting the spatial orientation and dynamic stability of the aircraft; altitude sensors, such as barometers, lidars, or ultrasonic sensors, which are used to accurately measure the vertical height of the aircraft relative to the ground to ensure flight safety and avoid collisions; speed sensors, such as pitot tubes and GPS receivers combined with algorithm calculations, provide real-time speed information of the aircraft, including ground speed, airspeed, etc., to assist in flight control and navigation; battery status monitoring sensors, which are used to monitor key parameters such as battery voltage, current, remaining power, and temperature to ensure the stability and safety of power supply during flight.

[0092] After obtaining the flight status data of the above-mentioned drone, the real-time data is compared with the preset safety range or threshold. Data outside the range is considered abnormal. After excluding the abnormal values, data that can truly reflect the current flight status of the drone can be obtained.

[0093] All data that has undergone anomaly detection is integrated to form a structured flight status data report. Specifically, the detected data is organized in a unified format, such as JSON or XML, to facilitate subsequent data storage, transmission, and analysis. At the same time, a precise time stamp is added to each piece of data to ensure its timeliness and traceability. The formatted data is packaged to form a data matrix, which consists of multiple vectors of the same dimension. Each vector contains elements such as the acquired UAV attitude data, altitude data, speed data, battery status data, and time stamp data.

[0094] In an optional embodiment proposed by the present invention, step 13 may include:

[0095] Step 131, obtaining the endurance time and the climbing rate according to the battery status data and the speed data;

[0096] Step 132, obtaining a maximum range based on the endurance time data and the speed data;

[0097] Step 133, obtaining a maximum flight altitude according to the altitude data, the battery status data, and the speed data;

[0098] Step 134 : Obtain a maximum flight speed based on the battery status data and the attitude data.

[0099] In this embodiment, the flight time of the UAV is related to the flight speed and battery status; the energy consumption of the UAV varies at different flight speeds. Generally speaking, when flying at high speeds, the motor needs to consume more electricity to overcome air resistance, and the energy consumption is relatively high; while at low speeds, the energy consumption is relatively low. For example, when the UAV flies at a speed of 10m / s, the motor power is 50W; while at a speed of 20m / s, the motor power may increase to 150W. Specifically, for fixed-wing UAVs, the following can be achieved:

[0100]

[0101] The endurance time is obtained, where T is the endurance time, E1 is the total energy of the battery, E1=Uq, q is the battery capacity, U is the voltage, P1 is the cruising power, m is the mass of the UAV, g is the acceleration of gravity, v is the cruising speed of the UAV, k is the lift-to-drag ratio of the UAV, and η is the motor efficiency.

[0102] From this we can get the maximum range of the UAV:

[0103] S=v·T

[0104] Where S is the maximum range of the UAV.

[0105] The formula for the climb rate of an unmanned aerial vehicle is:

[0106]

[0107] Among them, Λ is the climb rate of the UAV, P2 is the remaining power of the battery, P is the total power of the battery, and I is the operating current of the motor.

[0108] The formula for the maximum flight altitude is:

[0109]

[0110] Where ρ is the air density and A is the frontal area of ​​the UAV.

[0111] The formula for maximum flight speed is:

[0112]

[0113] Among them, C D is the drag coefficient, which is related to the aerodynamic design of the fuselage.

[0114] In an optional embodiment of the present invention, step 14 may include:

[0115] Step 141: Process the flight status data and the performance data to obtain an input vector;

[0116] Step 142: Input the input vector into the flight status test model for processing to obtain test data; the flight status test model processes the input vector through a node function to obtain an intermediate result, and performs deviation correction on the intermediate result to obtain test data.

[0117] In this embodiment, the flight status data obtained after anomaly detection and the performance data obtained through calculation total 13 categories of key feature data, resulting in a 13-dimensional input vector. These 13 categories of key feature data are arranged in a certain order into an input vector, which is then input into a flight status test model for processing. The flight status test model is a model built based on mathematical algorithms and machine learning techniques that processes the input vector, simulates the flight status of the unmanned aerial vehicle, and outputs corresponding test data. This model is trained with a large amount of training data to ensure that it accurately reflects the actual flight conditions of the aircraft. The node function is a core component of the flight status test model. It calculates the intermediate results based on the various features in the input vector according to certain rules and algorithms. The design of the node function depends on the purpose and requirements of the test. For example, if the test focuses on the stability of the aircraft, the node function may focus more on attitude data and acceleration data; if the test focuses on the endurance of the aircraft, the node function may focus more on battery status data and flight time data. Due to reasons such as model simplification, data incompleteness, and interference from environmental factors, the intermediate results obtained by the node function may be biased. For example, the model may not take into account certain complex aerodynamic effects, or there may be certain errors in the data collection and transmission process. These will cause the intermediate results to deviate from the actual situation. In order to obtain more accurate test data, the intermediate results need to be corrected for deviations to obtain the test data.

[0118] In an optional embodiment of the present invention, the flight state test model is trained through the following process:

[0119] Step 151, obtaining historical flight status data, historical performance data, and historical fault type data;

[0120] Step 152: summarizing the historical flight status data, the historical performance data, and the historical fault type data to obtain sample data;

[0121] Step 153: randomly extract the sample data to obtain a training data set and a test sample data set;

[0122] Step 154: input the training data set into the flight state test model for processing to obtain a training result data set;

[0123] Step 155: Compare the training result dataset with the test sample dataset to obtain a comparison result;

[0124] Step 156: Adjust the node function parameters of the flight status test model according to the comparison result to obtain a trained flight status test model.

[0125] In this embodiment, historical flight status data, historical performance data, and historical fault type data are first acquired. The historical flight status data records various status information of the UAV during past flights. For example, the time-varying curve of flight altitude can reflect the vertical position of the UAV during different flight phases. Flight speed data, including horizontal and vertical speeds, can reflect the speed and direction of the UAV's movement. Attitude angle data, such as pitch, roll, and yaw, can describe the UAV's spatial posture in the air. Historical performance data includes various performance indicators of the UAV. For example, engine power output data reflects the engine's operating capacity under different operating conditions; battery power consumption data can help understand the UAV's endurance; indicators such as the UAV's maximum climb rate and maximum level flight speed directly reflect the UAV's performance limits. Historical fault type data records various fault conditions that occurred during past UAV flights. For example, engine failure may manifest as an abnormal power drop or excessive vibration; sensor failure may lead to inaccurate data collection; and communication failure may affect information transmission between the UAV and the ground control station. Each fault type has a corresponding fault feature description, such as the time of fault occurrence, fault phenomenon, fault code, etc. These data help analyze the causes and patterns of faults.

[0126] After obtaining the historical flight status data, the historical performance data and the historical fault type data, it is necessary to summarize and process the historical flight status data, the historical performance data and the historical fault type data to obtain sample data.

[0127] Examine the acquired historical data to remove noise, errors, and missing values. For example, sensor failures or signal interference may result in some abnormal data points, which can affect model training and need to be removed. Missing values ​​can be addressed using methods such as interpolation and mean filling. Correlate and integrate different types of data. For example, align flight status data, performance data, and fault type data by timestamp so that each data set represents complete information about the aircraft at a specific moment. This establishes intrinsic connections between the data. Extract features from the integrated data that are important for flight status testing and fault diagnosis. For example, calculate the rate of change of flight status data (such as the rate of change of speed or attitude angle) to reflect the dynamic characteristics of the aircraft. Calculate the ratios of performance indicators (such as the power-to-weight ratio) based on performance data to evaluate the aircraft's performance efficiency. These features serve as model inputs for training and testing the flight status test model. Based on the extracted features, divide the data into independent samples. Each sample contains a set of input features (such as flight status features, performance features) and a corresponding output label (such as fault type or no-fault identification).

[0128] To obtain training and test sample datasets, the sample data can be randomly sampled. This ensures that the training and test sample datasets are representative and reflect the overall distribution of the sample data. This prevents overfitting or underfitting during model training and improves the model's generalization capabilities. Sample data is typically divided into training and test sample datasets in a specific ratio, with common ratios such as 7:3 and 8:2. For example, if there are 1,000 samples and they are divided in a 7:3 ratio, the training dataset will contain 700 samples and the test sample dataset will contain 300 samples.

[0129] Specifically, the flight status data and performance data of the UAV at time i can be expressed as vector X i To indicate that X i ={x i1 , x i2 ,…,x ij}={v i , ψ i ,φ i ,θ i , h i , U i , I i , T i , S i , Λ i , h maxi , v maxi , t i}; The test result at this moment can be expressed as Y i ={y i1 ,y i2 ,…,y ij}, then {X i , Y i} constitutes a sample;

[0130] After obtaining the training dataset and test sample dataset, the training dataset is input into the flight status test model for processing to produce a training result dataset. The flight status test model is a machine learning-based model consisting of an input layer, a hidden layer, and an output layer. The input layer receives sample features from the training dataset, the hidden layer performs nonlinear transformation and feature extraction on the input features, and the output layer provides the model's prediction results. The model processing process includes sequentially inputting each sample from the training dataset into the flight status test model. Based on the input features, the model calculates and processes them using node functions, passing information layer by layer, ultimately obtaining a prediction result for each sample at the output layer. These prediction results constitute the training result dataset. Node function parameters determine how the model processes and maps input features. Different parameter values ​​will result in different model outputs for the same input. During training, these parameters need to be continuously adjusted to ensure that the model's predictions are as close as possible to the true labels.

[0131] Specifically, first the input vector X i Perform normalization:

[0132]

[0133] Where, X max is the maximum value of a sample index; X min It is the minimum value of a sample indicator.

[0134] The input layer of the flight status test model passes through the first node function:

[0135]

[0136] Get the output of the input layer and input it to the hidden layer; the hidden layer passes through the second node function:

[0137]

[0138] Get the output result of the hidden layer and input it to the output layer; the output layer passes through the third node function:

[0139]

[0140] The output result of the flight state test model is obtained. The output result of the model is the test data. The test data is also a multidimensional vector, in which the elements represent the time of fault occurrence, fault phenomenon, fault code, fault type, etc. j 、V j is the preset weight, r j ,λ j is the preset threshold.

[0141] The output layer correction error is:

[0142] d i =(o 2j -y j )y j (1-y j )

[0143] The hidden layer correction error is:

[0144]

[0145] The preset weights and thresholds are updated according to the correction error to obtain:

[0146] V j+1 =V j +ad i y j

[0147] r j+1 =r j +ad i

[0148] ω j+1 =ω j +be j x i

[0149] λ j+1 =λ j +be j

[0150] Where: a, b are the corresponding learning speeds, 0 <a<1,0<b<1。

[0151] The predicted category of each sample in the training dataset is compared with the corresponding true category in the test dataset, and metrics such as classification accuracy, recall, and F1 value are calculated. After training j learning samples, when the network's global error is less than a limit, the network's output approximates historical fault type data, and training ends, resulting in a trained flight status test model.

[0152] A specific embodiment of the unmanned aerial vehicle testing method provided by the embodiment of the present invention is:

[0153] Step 1: According to the preset route data, the longitude and latitude coordinates are converted into plane coordinates to obtain waypoint coordinate data; according to the waypoint coordinate data, the flight speed control data and the flight attitude angle control data are obtained; according to the waypoint coordinate data, the flight speed control data and the flight attitude angle control data, a test instruction is generated and sent to the unmanned aerial vehicle.

[0154] Step 2, obtaining attitude data, altitude data, speed data, and battery status data of the UAV based on multiple sensors installed on the UAV; obtaining at least one of the attitude data, altitude data, speed data, and battery status data of the UAV based on multiple sensors installed on the UAV; obtaining at least one of the attitude data, altitude data, speed data, and battery status data of the UAV based on multiple sensors installed on the UAV;

[0155] Step 3: Obtain the endurance time and climb rate based on the battery status data and the speed data; obtain the maximum range based on the endurance time data and the speed data; obtain the maximum flight altitude based on the altitude data, the battery status data and the speed data; and obtain the maximum flight speed based on the battery status data and the attitude data.

[0156] Step 4: Process the flight status data and the performance data to obtain an input vector, wherein the i-th input vector can be expressed as: X i ={x i1 , x i2 ,…,x ij}={v i , ψ i ,φ i ,θ i , h i , U i , I i , T i , S i , Λ i , h maxi , v maxi , t i The input vector is input into the flight state test model for processing to obtain test data, wherein the flight state test model is a neural network including an input layer, a hidden layer, and an output layer, such as Figure 2 As shown; the specific process of data processing includes:

[0157] First, the input vector X i Perform normalization:

[0158]

[0159] Where, Xmax is the maximum value of a sample index; X min It is the minimum value of a sample indicator.

[0160] The input layer of the flight status test model passes through the first node function:

[0161]

[0162] Get the output of the input layer and input it to the hidden layer; the hidden layer passes through the second node function:

[0163]

[0164] Get the output result of the hidden layer and input it to the output layer; the output layer passes through the third node function:

[0165]

[0166] The output result of the flight state test model is obtained. The output result of the model is the test data. The test data is also a multidimensional vector, in which the elements represent the time of fault occurrence, fault phenomenon, fault code, fault type, etc. j 、V j is the preset weight, r j ,λ j is the preset threshold.

[0167] The technical solution proposed by the present invention generates test instructions and sends them to the UAV, obtaining its flight status data in real time. This data is then processed to obtain at least one of the key performance data, including flight time, climb rate, maximum range, maximum flight altitude, and maximum flight speed, thereby achieving a comprehensive quantitative assessment of the UAV's performance. Furthermore, the present invention also inputs both flight status data and performance data into a flight status test model for processing, utilizing the model's comprehensive analysis capabilities to obtain more accurate and comprehensive test data. This technical solution not only improves the automation level of the testing process and reduces human intervention, but also provides strong support for the optimization and improvement of UAV performance through a data-driven approach, helping to enhance the overall performance and reliability of the UAV.

[0168] like Figure 3 As shown, an embodiment of the present invention further provides an unmanned aerial vehicle testing device 30, comprising:

[0169] A generating module 31 is used to generate a test instruction and send it to the UAV;

[0170] An acquisition module 32 is used to obtain flight status data of the UAV;

[0171] The processing module 33 is used to process the flight status data to obtain performance data; the flight status data and the performance data are input into a flight status test model for processing to obtain test data.

[0172] Optionally, the generating module 31 is specifically configured to:

[0173] According to the preset route data, the waypoint coordinate data is obtained;

[0174] Obtaining flight speed control data and flight attitude angle control data according to the waypoint coordinate data;

[0175] A test instruction is generated according to the waypoint coordinate data, the flight speed control data and the flight attitude angle control data and is sent to the unmanned aerial vehicle.

[0176] Optionally, the acquisition module 32 is specifically configured to:

[0177] acquiring at least one of attitude data, altitude data, speed data, and battery status data of the UAV based on a plurality of sensors installed on the UAV;

[0178] performing abnormality detection processing on at least one of the posture data, the height data, the speed data, and the battery status data to obtain a plurality of detection data;

[0179] The plurality of detection data are combined and processed according to a preset format to obtain flight status data of the unmanned aerial vehicle.

[0180] Optionally, the processing module 33 is specifically configured to:

[0181] Obtaining a cruising time and a climbing rate according to the battery status data and the speed data;

[0182] Obtaining a maximum range based on the endurance time data and the speed data;

[0183] obtaining a maximum flight altitude according to the altitude data, the battery status data, and the speed data;

[0184] A maximum flight speed is obtained according to the battery status data and the attitude data.

[0185] Optionally, the processing module 33 is further specifically configured to:

[0186] Processing the flight status data and the performance data to obtain an input vector;

[0187] The input vector is input into the flight state test model for processing to obtain test data; the flight state test model processes the input vector through a node function to obtain an intermediate result, and the intermediate result is subjected to deviation correction to obtain test data.

[0188] Optionally, the flight status test model is trained through the following process:

[0189] Obtain historical flight status data, historical performance data, and historical fault type data;

[0190] Summarizing the historical flight status data, the historical performance data, and the historical fault type data to obtain sample data;

[0191] Randomly sampling the sample data to obtain a training data set and a test sample data set;

[0192] Inputting the training data set into the flight state test model for processing to obtain a training result data set;

[0193] Comparing the training result data set with the test sample data set to obtain a comparison result;

[0194] According to the comparison result, the node function parameters of the flight status test model are adjusted to obtain a trained flight status test model.

[0195] Optionally, the device 30 further includes:

[0196] The output module 34 is configured to output a UAV test report, wherein the UAV test report includes performance data and test data of the UAV.

[0197] It should be noted that this device is a device corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0198] like Figure 4 As shown, an embodiment of the present invention further provides a computing device 40, comprising a processor 41, a memory 42, and a program or instruction stored in the memory 42 and executable on the processor 41. When executed by the processor 41, the program or instruction implements the various processes of the above-mentioned UAV testing method embodiment and can achieve the same technical effects. To avoid repetition, the details are not described here. It should be noted that the computing device in the embodiment of the present invention includes the above-mentioned mobile electronic devices and non-mobile electronic devices.

[0199] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0200] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0201] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0202] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0203] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0204] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard disk, ROM, RAM, a magnetic disk, or an optical disk.

[0205] In addition, it should be noted that, in the apparatus and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. Moreover, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order, and some steps can be performed in parallel or independently of each other. For those of ordinary skill in the art, it will be understood that all or any steps or components of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in hardware, firmware, software or a combination thereof, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

[0206] Therefore, the purpose of the present invention can also be achieved by running a program or a group of programs on any computing device. The computing device can be a well-known general-purpose device. Therefore, the purpose of the present invention can also be achieved simply by providing a program product containing program code for implementing the method or device. That is to say, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but do not necessarily need to be performed in chronological order. Certain steps can be performed in parallel or independently of each other.

[0207] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for testing an unmanned aerial vehicle, characterized in that: include: Generate test instructions and send them to the UAV; Obtain flight status data of unmanned aerial vehicles; processing the flight status data to obtain performance data, the performance data including at least one of endurance time, climb rate, maximum range, maximum flight altitude, and maximum flight speed; Inputting the flight status data and the performance data into a flight status test model for processing to obtain test data; The step of obtaining the flight status data of the unmanned aerial vehicle includes: acquiring at least one of attitude data, altitude data, speed data, and battery status data of the UAV based on a plurality of sensors installed on the UAV; performing abnormality detection processing on at least one of the posture data, the height data, the speed data, and the battery status data to obtain a plurality of detection data; Merging and processing the plurality of detection data according to a preset format to obtain flight status data of the unmanned aerial vehicle; The flight status data is processed to obtain performance data, including: Obtaining a cruising time and a climbing rate according to the battery status data and the speed data; Obtaining a maximum range based on the endurance time data and the speed data; obtaining a maximum flight altitude according to the altitude data, the battery status data, and the speed data; obtaining a maximum flight speed according to the battery status data and the attitude data; The flight status data and the performance data are input into a flight status test model for processing to obtain test data, including: Processing the flight status data and the performance data to obtain an input vector; Inputting the input vector into the flight state test model for processing to obtain test data; the flight state test model processes the input vector through a node function to obtain an intermediate result, and performing deviation correction on the intermediate result to obtain test data; The flight state test model is trained through the following process: Obtain historical flight status data, historical performance data, and historical fault type data; Summarizing the historical flight status data, the historical performance data, and the historical fault type data to obtain sample data; Randomly sampling the sample data to obtain a training data set and a test sample data set; Inputting the training data set into the flight state test model for processing to obtain a training result data set; Comparing the training result data set with the test sample data set to obtain a comparison result; According to the comparison result, the node function parameters of the flight status test model are adjusted to obtain a trained flight status test model.

2. The unmanned aerial vehicle testing method according to claim 1, characterized in that: The generating of the test instruction and sending it to the unmanned aerial vehicle comprises: According to the preset route data, the waypoint coordinate data is obtained; Obtaining flight speed control data and flight attitude angle control data according to the waypoint coordinate data; A test instruction is generated according to the waypoint coordinate data, the flight speed control data and the flight attitude angle control data and is sent to the unmanned aerial vehicle.

3. The unmanned aerial vehicle testing method according to claim 1, wherein: The method further comprises: Outputting a UAV test report, wherein the UAV test report includes: UAV performance data and test data.

4. An unmanned aerial vehicle testing device, characterized in that: include: A generation module, used for generating test instructions and sending them to the UAV; An acquisition module is used to obtain the flight status data of the unmanned aerial vehicle; a processing module, configured to process the flight status data to obtain performance data; and input the flight status data and the performance data into a flight status test model for processing to obtain test data; The step of obtaining the flight status data of the unmanned aerial vehicle includes: acquiring at least one of attitude data, altitude data, speed data, and battery status data of the UAV based on a plurality of sensors installed on the UAV; performing abnormality detection processing on at least one of the posture data, the height data, the speed data, and the battery status data to obtain a plurality of detection data; Merging and processing the plurality of detection data according to a preset format to obtain flight status data of the unmanned aerial vehicle; The flight status data is processed to obtain performance data, including: Obtaining a cruising time and a climbing rate according to the battery status data and the speed data; Obtaining a maximum range based on the endurance time data and the speed data; obtaining a maximum flight altitude according to the altitude data, the battery status data, and the speed data; obtaining a maximum flight speed according to the battery status data and the attitude data; The flight status data and the performance data are input into a flight status test model for processing to obtain test data, including: Processing the flight status data and the performance data to obtain an input vector; Inputting the input vector into the flight state test model for processing to obtain test data; the flight state test model processes the input vector through a node function to obtain an intermediate result, and performing deviation correction on the intermediate result to obtain test data; The flight state test model is trained through the following process: Obtain historical flight status data, historical performance data, and historical fault type data; Summarizing the historical flight status data, the historical performance data, and the historical fault type data to obtain sample data; Randomly sampling the sample data to obtain a training data set and a test sample data set; Inputting the training data set into the flight state test model for processing to obtain a training result data set; Comparing the training result data set with the test sample data set to obtain a comparison result; According to the comparison result, the node function parameters of the flight status test model are adjusted to obtain a trained flight status test model.

5. A computing device, characterized in that include: A processor and a memory storing a computer program, wherein when the computer program is executed by the processor, the method according to any one of claims 1 to 3 is performed.

6. A computer-readable storage medium, characterized in that The device stores instructions, which, when executed on a computer, enable the computer to execute the method according to any one of claims 1 to 3.

Images