Method and system for predicting structural fatigue of unmanned aerial vehicle

Abstract

The invention relates to the technical field of unmanned aerial vehicle evaluation, in particular to an unmanned aerial vehicle structure fatigue prediction method and system, and the method comprises the steps: obtaining a sensor data set of a key structure part of an unmanned aerial vehicle; dynamically evaluating the data quality of the sensor data set, and dynamically adjusting a data cleaning preprocessing strategy according to an evaluation result; constructing a stress field model reflecting global stress distribution of the structure on the basis of the preprocessed sensor data set in combination with real-time flight environment parameters; and according to the stress field model and material fatigue characteristics, calculating a fatigue damage prediction value of each structural part. The objective of the invention is to improve the prediction precision of the fatigue damage of the unmanned aerial vehicle structure.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle (UAV) assessment, and in particular to a method and system for predicting the structural fatigue of an UAV. Background Art

[0002] With the development of the low-altitude economy, low-altitude security capabilities have become a core element in fostering new low-altitude productivity. For example, in densely populated urban low-altitude environments, electric vertical take-off and landing (eVTOL) vehicles, a key vehicle for future urban air transportation and logistics, have a direct bearing on public safety and urban economic stability. In this context, the large-scale application of unmanned aerial vehicles in low-altitude urban environments places even higher demands on structural health monitoring technology for real-time, precision, and intelligence.

[0003] At present, the mainstream methods for structural fatigue assessment of unmanned aerial vehicles in the industry mainly include regular visual inspection, local monitoring with strain gauges, and finite element simulation analysis. Although some advanced systems integrate flight data recorders and single strain sensors to achieve real-time acquisition of static stress in key parts and fatigue life estimation, they still have limitations. On the one hand, the threshold rules are mostly based on static design parameter settings and cannot dynamically adapt to the coupling of complex meteorological conditions and multi-source loads, which in turn affects the accuracy of structural fatigue prediction. On the other hand, existing stress field modeling methods mostly rely on local measurement data from a single sensor and lack effective representation of the global stress distribution of the structure, resulting in a significant error accumulation effect in fatigue damage prediction based on local stress data. It is difficult to meet the demand for high-precision structural fatigue prediction of unmanned aerial vehicles in urban low-altitude environments. Summary of the Invention

[0004] In order to improve the prediction accuracy of UAV structural fatigue damage, the present invention provides a UAV structural fatigue prediction method and system. The technical solutions adopted are as follows: The technical solution of the first aspect of the present invention provides a method for predicting structural fatigue of an unmanned aerial vehicle, the method comprising: Obtain sensor data sets of key structural parts of UAVs; Dynamically evaluate the data quality of the sensor data set and dynamically adjust the data cleaning preprocessing strategy based on the evaluation results; Based on the preprocessed sensor data set and combined with real-time flight environment parameters, a stress field model reflecting the global stress distribution of the structure is constructed; The fatigue damage prediction value of each structural part is calculated based on the stress field model and the fatigue characteristics of the material.

[0005] Furthermore, the data quality of the sensor data set is dynamically evaluated, including: Extract the signal-to-noise ratio and battery supply voltage of sensor data; The continuity analysis of the time series of sensor data is performed through a sliding time window to calculate the data mutation amplitude of adjacent sampling points; A sensor data health index is calculated according to the signal-to-noise ratio, the battery supply voltage, and the data mutation amplitude.

[0006] Furthermore, the data cleaning preprocessing strategy is dynamically adjusted based on the evaluation results, including: Compare the current data health index with the preset data quality threshold and calculate the real-time difference; generating a dynamic cleaning decision index based on the real-time difference, the historical difference accumulation, and the difference change rate; The data cleaning frequency is adjusted in real time according to the dynamic cleaning decision index.

[0007] Furthermore, based on the preprocessed sensor data set and combined with real-time flight environment parameters, a stress field model reflecting the global stress distribution of the structure is constructed, including: Deploy a sensor group at the target location of the UAV to collect static stress and dynamic vibration data; Combined with the wind speed and temperature parameters in the real-time flight environment, dynamic vibration amplification correction, aerodynamic load correction and thermal stress correction are performed on static stress; The corrected multi-source stress data are integrated to construct a stress field model reflecting the global stress distribution of the structure.

[0008] Furthermore, combined with the wind speed and temperature parameters in the real-time flight environment, dynamic vibration amplification correction, aerodynamic load correction and thermal stress correction are performed on the static stress, including: The vibration amplitude is measured by an accelerometer, and the static stress is compensated for by the dynamic amplification factor in combination with the material stiffness parameters; Calculate the quadratic growth effect of aerodynamic pressure on structural stress based on real-time wind speed and aerodynamic parameters; Based on the temperature change and the thermal expansion coefficient of the material, the superposition effect of thermal stress on the structural stress is calculated.

[0009] Furthermore, based on the stress field model and material fatigue characteristics, the fatigue damage prediction value of each structural part is calculated, including: According to the corresponding relationship between the stress amplitude and fatigue life of the material, a curve model reflecting the stress amplitude and life characteristics is established; Based on the stress amplitudes of each flight output by the stress field model and the number of cycles of historical flight missions, the cumulative fatigue damage value of each structural part is calculated.

[0010] Furthermore, based on the stress amplitude output by the stress field model and in combination with the number of historical flight cycles, the cumulative fatigue damage value of each structural part is calculated, including: According to the stress amplitude during each flight, the curve model reflecting the stress amplitude and life characteristics is matched to obtain the corresponding fatigue life; The cumulative fatigue damage value is obtained by adding up the ratio of the number of flight cycles to the corresponding fatigue life.

[0011] Furthermore, the method further comprises: Based on the fatigue damage prediction value, combined with flight history data, environmental parameter records and structural damage repair records, a multi-dimensional damage assessment system is constructed; generating a dynamic correction factor to adjust the fatigue damage prediction value based on real-time monitored flight environment dynamic parameters and mission load intensity; Generate graded maintenance recommendations based on adjusted fatigue damage predictions.

[0012] Furthermore, the method further comprises: When the fatigue damage prediction value exceeds a preset safety threshold, an airworthiness deviation warning is triggered; The unmanned aerial vehicles with the airworthiness deviation warning will be included in the abnormal aircraft control list, and grounding orders will be issued to the unmanned aerial vehicles included in the control list until the control is lifted after the maintenance verification is completed.

[0013] The technical solution of the second aspect of the present invention provides an unmanned aerial vehicle structural fatigue prediction system, which adopts the unmanned aerial vehicle structural fatigue prediction method described in the technical solution of the first aspect of the present invention, and the system includes: a data acquisition module configured to acquire a sensor data set of a structural part of the UAV; a data preprocessing module configured to dynamically evaluate the data quality of the sensor data set and dynamically adjust the data cleaning preprocessing strategy according to the evaluation results; The stress field distribution module is configured to construct a stress field model reflecting the global stress distribution of the structure based on the preprocessed sensor data set and combined with real-time flight environment parameters; The fatigue damage prediction module is configured to calculate the fatigue damage prediction value of each structural part according to the stress field model and the fatigue characteristics of the material.

[0014] The present invention has the following beneficial effects: The UAV structural fatigue prediction method provided by the present invention dynamically optimizes the sensor data preprocessing strategy, combines real-time flight environment parameters to construct a global stress field model, and integrates material fatigue characteristics analysis, with the aim of improving the accuracy and reliability of structural fatigue damage prediction. First, through the deployment of multi-source sensors in key structural parts and dynamic data quality assessment, high-precision modeling of the stress field under complex working conditions is achieved. The integration of static stress, dynamic vibration stress, aerodynamic load, and thermal stress coupled corrections breaks through the limitations of traditional single sensor local monitoring and comprehensively perceives the global stress distribution of the structure. Combining material fatigue life characteristics with historical load cycle data, the cumulative damage value is dynamically calculated, and the remaining life of key parts can be accurately predicted. This method can identify potential fatigue risks in real time and support proactive maintenance decisions, thereby effectively extending the service life of UAVs, ensuring the safety of low-altitude urban operations, and providing key technical support for the large-scale application of new low-altitude vehicles such as eVTOL. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 A flow chart of a method for predicting structural fatigue of an unmanned aerial vehicle provided by one embodiment of the present invention; Figure 2 A schematic diagram of the structure of an unmanned aerial vehicle structural fatigue prediction system provided by one embodiment of the present invention; Figure 3 A schematic diagram of a flow chart for handling airworthiness deviations provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0017] To further illustrate the technical means and effectiveness of the present invention in achieving its intended objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementation, structure, features, and effectiveness of a method and system for predicting structural fatigue in an unmanned aerial vehicle (UAV) according to the present invention. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] The specific scheme of the method and system for predicting structural fatigue of an unmanned aerial vehicle provided by the present invention is described in detail below with reference to the accompanying drawings.

[0020] See also Figure 1 , which shows a flow chart of a method for predicting structural fatigue of an unmanned aerial vehicle provided by one embodiment of the present invention, the method comprising: Step S100: Obtain sensor data sets for key structural parts of the UAV; specifically, the sensors include but are not limited to strain gauges, accelerometers, UAV data recording systems, GPS / Beidou receivers, barometers, and lidars; for strain gauges, they can be installed at key structural parts such as the center of gravity, engine brackets, main wing beams, half of the wingspan, and the root of the vertical tail according to the stress characteristics of the measuring parts, to measure the strain of each part and thereby obtain static stress data; accelerometers collect dynamic vibration data; the UAV data recording system can be installed in the equipment cabin to collect, store, and preliminarily process various sensor data; the GPS / Beidou receiver can be installed on the top of the fuselage to ensure accurate acquisition of the UAV's position, speed, and attitude information; the barometer is used to measure atmospheric pressure and to infer data such as flight altitude; the lidar reasonably adjusts the installation angle according to monitoring requirements to detect obstacles and other information in the flight environment.

[0021] Step S200: Dynamically evaluate the data quality of the sensor data set and dynamically adjust the data cleaning preprocessing strategy based on the evaluation results. Because traditional data cleaning methods use fixed rules or simple thresholds, they cannot cope with data changes in different UAV flight environments and sensor health conditions, and their adaptive capabilities are insufficient. Therefore, this implementation requires evaluating the sensor data quality before data cleaning, and then dynamically selecting a cleaning strategy based on the data quality. Step S200 specifically includes: Step S210: Extract the signal-to-noise ratio and battery supply voltage of the sensor data; specifically, for the data of each sensor, use a suitable algorithm to calculate its signal-to-noise ratio; taking the strain gauge as an example, within a stable measurement period, the average power of the signal is compared with the average power of the noise. The signal and noise components can be separated by filtering the signal, and then the power ratio is calculated, and then the logarithm is converted into a signal-to-noise ratio; the battery supply voltage can be directly read from the data recording system of the unmanned aerial vehicle. The voltage data will be recorded in the data recording system in real time, reflecting the power supply status of the sensor at different times.

[0022] The continuity analysis of the time series of sensor data is performed through a sliding time window, and the data mutation amplitude of adjacent sampling points is calculated. Specifically, according to the characteristics and change frequency of the sensor data, an appropriate sliding time window size can be selected. Within each sliding time window, the data mutation amplitude can be expressed as: Where, Indicates the amplitude of data mutation. The larger the value, the less smooth the data change and the worse the continuity. Indicates the sampling point number in the time series; as the time window slides, the number of points in each window is calculated in turn. value; The sensor data health index is calculated based on the signal-to-noise ratio, battery supply voltage, and data mutation amplitude. The sensor data health index can be expressed as: Where, Indicates the data health index of the sensor; represents the signal-to-noise ratio; Indicates the magnitude of data mutation; Indicates the battery supply voltage; Indicates the moment; Represents the first weight coefficient, which is used to reflect the impact of the signal-to-noise ratio on data quality; Represents the second weight coefficient, which is used to reflect the impact of data mutation amplitude on data quality; represents the third weight coefficient, which is used to reflect the impact of battery supply voltage on data quality; This embodiment extracts the signal-to-noise ratio and battery supply voltage of sensor data, performs continuity analysis on the time series of sensor data, calculates the amplitude of data mutation, and calculates the sensor data health index based on these factors. This allows for a comprehensive and dynamic assessment of the quality of sensor data. This approach fully considers the data changes of unmanned aerial vehicles under different flight environments and sensor health conditions, overcoming the problem of weak adaptability of traditional data cleaning methods. Obtaining an accurate sensor data health index provides a basis for the subsequent dynamic selection of appropriate data cleaning preprocessing strategies based on data quality, helping to improve the pertinence and effectiveness of data cleaning, thereby enhancing the accuracy and reliability of unmanned aerial vehicle structural fatigue prediction.

[0023] Step S220: Compare the data health index at the current moment with the preset data quality threshold and calculate the real-time difference; specifically, after calculating the sensor data health index at each moment according to step S210, the preset data quality threshold is used to compare the data health index at the current moment with the preset data quality threshold. The threshold can be pre-set based on factors such as the UAV flight mission requirements, sensor performance, and data processing experience, and is used to measure whether the sensor data meets the quality standards of subsequent analysis; the sensor data health index at the current moment and preset data quality thresholds Compare and calculate the real-time difference, which reflects the gap between the current sensor data quality and the expected quality standard; Based on the real-time difference, the accumulated historical difference, and the rate of change of the difference, a dynamic cleaning decision index is generated; and according to the dynamic cleaning decision index, the data cleaning frequency is adjusted in real time; wherein the dynamic cleaning decision index can be expressed as: Where, Represents the sensor dynamic cleaning decision index. The larger the value, the more serious the data quality problem is, and a more frequent cleaning strategy is required. Indicates the preset data quality threshold; Indicates the step length; represents the proportionality coefficient; represents the integral coefficient; In order to calculate the historical difference accumulation, the formula needs to record the real-time difference at each moment since the start of monitoring, and then calculate the differential coefficient. Get the historical difference accumulation; Indicates the rate of change of the difference; the values ​​of the proportional coefficient, integral coefficient, and differential coefficient are usually determined based on the characteristics of the UAV system, data processing experience, and experimental optimization, and are used to adjust the weights of the real-time difference, historical difference accumulation, and difference change rate in the decision index; Then, the data cleaning frequency is adjusted in real time according to the calculated dynamic cleaning decision index; Threshold ranges correspond to different data cleaning frequencies, dynamically adjusting the cleaning frequency based on actual data quality. This dynamic adjustment strategy overcomes the limitations of traditional fixed cleaning rules. When data quality is good, unnecessary cleaning operations are reduced, saving computing resources. When data quality issues arise or deteriorates, the cleaning frequency is promptly increased to ensure reliable data quality for subsequent analysis.

[0024] Step S300: Based on the preprocessed sensor data set and combined with real-time flight environment parameters, a stress field model reflecting the global stress distribution of the structure is constructed; specifically, the UAV will experience various stress cycles during flight, such as takeoff, landing, maneuvering, etc., which will cause material fatigue; the regular fatigue damage detection method cannot adapt to the complex and changeable working environment of the UAV and the demand for more intelligent and adaptive fatigue prediction methods, and the traditional body equipped with a single sensor can only measure local stress and cannot be globally modeled, resulting in misjudgment of structural failure risk, and the coupled influence of the flight environment on the structural stress is not combined, and the model accuracy is low.

[0025] Step S300 specifically includes: Step S310: Deploy a sensor array at target locations on the UAV to collect static stress and dynamic vibration data. Specifically, in the sensor array configuration, strain gauges and accelerometers are installed at key locations on the aircraft body, and combined with the aircraft's own sensors to obtain real-time wind speed and temperature during flight. The installation locations of the strain gauges and accelerometers include but are not limited to: Center of gravity: The center of gravity of an unmanned aerial vehicle is the center point of the aircraft's mass distribution. The balance and stability of an unmanned aerial vehicle are closely related to the position of the center of gravity. Engine bracket: The engine bracket is the structural part that supports the engine of an unmanned aerial vehicle. Measuring the strain here can evaluate the impact of the engine on the structure of the unmanned aerial vehicle when it is working. Main wing spar: The main wing spar is the main load-bearing component in the structure of an unmanned aerial vehicle and is located in the central wing box. Measuring the strain here can help understand the structural state of the wing box during flight. Half of the wingspan: Half of the wingspan refers to the middle position of the unmanned aerial vehicle wing from the wing root to the wingtip. The strain here can be used to evaluate the bending and torsion of the wing during flight. Vertical tail root: The vertical tail is the vertical stabilizing surface of the tail of the unmanned aerial vehicle. Measuring the strain here helps understand the stress condition of the tail structure during flight. During flight, the strain gauge collects real-time static stress data from various target locations, while the accelerometer collects dynamic vibration data. Simultaneously, the aircraft's own wind speed sensor and temperature sensor acquire real-time wind speed and temperature data, respectively. This data is recorded at a specific sampling frequency and stored in the data acquisition system. Combined with the sensor data quality assessment and cleaning preprocessing in step S200, this ensures that the collected data is high-quality, reliable, and truly reflects the actual state of the UAV.

[0026] Step S320: Combined with the wind speed and temperature parameters in the real-time flight environment, dynamic vibration amplification correction, aerodynamic load correction, and thermal stress correction are performed on the static stress; specifically, the steps include: Measuring vibration amplitude with an accelerometer , which reflects the amplification of high-frequency vibration or instantaneous impact on static stress; the dynamic amplification coefficient compensation of static stress is performed in combination with the material stiffness parameter, which can be expressed as , It represents the dynamic sensitivity coefficient, which can be determined based on the fatigue characteristics of the material and the structural stiffness. This step takes into account the stress increase caused by factors such as vibration during the flight of the aircraft. Based on real-time wind speed and aerodynamic parameters, the quadratic growth effect of aerodynamic pressure on structural stress is calculated; specifically, aerodynamic parameters include air density , drag coefficient And the frontal area A, calculate the correlation coefficient of the aerodynamic coupling system: , which reflects the square growth effect of aerodynamic pressure caused by increasing wind speed. Calculate the quadratic growth effect of aerodynamic pressure on structural stress, that is, , which reflects the effect of wind speed on the structural stress of the aircraft; According to the temperature change and the thermal expansion coefficient of the material, the superposition effect of thermal stress on the structural stress is calculated; specifically, the real-time temperature T is recorded and the reference temperature is set. , calculate the temperature change ; Determine the thermal stress coefficient based on the elastic and thermal expansion characteristics of the material , calculate the superposition effect of thermal stress on structural stress, that is , taking into account the thermal stress caused by temperature changes on the expansion or contraction of the material; Step S330: Fusing the corrected multi-source stress data to construct a stress field model reflecting the global stress distribution of the structure; this can be expressed as: Where, represents the global stress value; Indicates that the static stress is measured by the strain gauge; Represents the dynamic sensitivity coefficient, which is determined by the material fatigue characteristics and structural stiffness; It is measured by accelerometer and reflects the amplification of static stress caused by high-frequency vibration or instantaneous impact; Indicates the aerodynamic coupling system and air density , drag coefficient , the correlation coefficient of the windward area A, that is , which is used to reflect that the increase in wind speed causes the aerodynamic pressure to increase in a square manner; Indicates real-time wind speed; represents the thermal stress coefficient, which is determined by the elasticity and thermal expansion of the material; Indicates the temperature change; It is used to correct nonlinear coupling effects not considered in the model and is dynamically adjusted through machine learning or experimental data; Finally, based on the calculated total stress at each target location, combined with the structural characteristics and geometric information of the UAV, a stress field model reflecting the global stress distribution of the structure is constructed using methods such as finite element analysis. This model can intuitively display the stress distribution of various parts of the UAV during flight, providing a foundation for subsequent fatigue prediction and structural assessment. This embodiment deploys a sensor array at key locations on the UAV to collect static stress and dynamic vibration data. This data is then combined with wind speed and temperature parameters in the real-time flight environment to perform multi-faceted corrections to the static stresses. Ultimately, this multi-source correction is integrated to construct a stress field model reflecting the global stress distribution of the structure. This method overcomes the limitations of traditional single sensors that can only measure local stress and fail to consider the effects of flight environment coupling, enabling accurate calculation of the stress distribution of key parts of the airframe during flight. By comprehensively considering multiple factors such as dynamic vibration, aerodynamic loads, and thermal stress, the model's accuracy and reliability are improved, providing a more comprehensive and accurate basis for structural fatigue prediction of UAVs.

[0027] Step S400: Calculating fatigue damage prediction values ​​of various structural parts according to the stress field model and material fatigue characteristics; Step S400 specifically includes: Step S410: Based on the relationship between the material's stress amplitude and fatigue life, a curve model is established to reflect the stress amplitude-life characteristics. Specifically, for key materials used in unmanned aerial vehicles, fatigue testing can be conducted by subjecting material samples to cyclic loading tests at different stress amplitude levels. The number of cycles until fatigue failure is recorded for each sample. This data reflects the material's fatigue life at different stress amplitudes. After collecting a large amount of fatigue test data, a mathematical fitting method, such as the least squares method, is used to establish a curve model reflecting the relationship between stress amplitude and fatigue life. For example, an SN curve (stress-cycle number curve) can intuitively demonstrate the variation in fatigue life of a material under different stress amplitudes. In practical applications, an appropriate function form, such as a power function or exponential function, can be selected to fit the curve based on the material properties and test data. By continuously adjusting the function parameters, the model can be optimized to fit the test data, thereby accurately reflecting the material's stress amplitude-life characteristics.

[0028] Step S420: Calculate the cumulative fatigue damage value of each structural component based on the stress amplitude values ​​for each flight output by the stress field model and the number of cycles in historical flight missions. Specifically, extract the stress amplitude values ​​for each structural component during each flight from the stress field model constructed in step S300. Simultaneously, the number of cycles for each flight is obtained through the UAV's data recording system. The number of cycles can be defined based on the characteristics of the flight mission. For example, a complete takeoff, flight, and landing process can be considered a cycle, or cycles can be defined based on specific flight maneuvers. For each flight stress amplitude, a search and match is performed based on the curve model established in step S410 to obtain the corresponding fatigue life Since the curve model reflects the fatigue life characteristics of the material under different stress amplitudes, the corresponding fatigue life prediction value can be obtained from the model according to the stress amplitude. The final cumulative fatigue damage value can be expressed as: Where, Indicates cumulative fatigue damage; Indicates the total number of flights; Indicates the Number of flight cycles; Indicates the The fatigue life of the material under the stress amplitude of each flight; during the calculation process, starting from the first flight, the ratio of the number of flight cycles to the corresponding fatigue life is calculated in sequence, and these ratios are accumulated. As the number of flights increases, the cumulative fatigue damage value is continuously updated to reflect the fatigue damage level of each structural part of the unmanned aerial vehicle in real time; if the cumulative damage is close to 1, it means that fatigue fracture is about to occur in a certain part of the structure. If it is calculated that the cumulative damage after 100 flights is 0.3, then it can be predicted that the remaining life is about 70% of the flight cycle; The high-quality sensor data obtained in this embodiment, the stress field model constructed, and the fatigue properties of the material are used to establish a curve model of stress amplitude and life characteristics, and the cumulative fatigue damage value is calculated in combination with the stress amplitude and number of cycles of each flight. This can accurately assess the fatigue damage status of various structural parts of the unmanned aerial vehicle at different flight stages. This allows operators to understand the health status of the key structures of the unmanned aerial vehicle in real time and predict the risk of structural fatigue fracture in advance. In this way, when the cumulative fatigue damage is close to 1, the parts that are about to undergo fatigue fracture can be repaired or replaced in a timely manner, effectively avoiding flight accidents caused by structural fatigue failure, greatly improving the flight safety and reliability of the unmanned aerial vehicle, and ensuring the smooth progress of the flight mission. It also helps to reasonably arrange maintenance plans and reduce operating costs.

[0029] Preferably, the method further comprises: Step S500: Multi-dimensional preventive maintenance assessment and decision-making; specifically, since the occurrence of fatigue damage is a multi-factorial process, it is not only affected by stress amplitude, but also includes factors such as the flight history of the aircraft, the flight environment, the aging of the material itself, possible collision damage, etc.; this embodiment establishes a multi-dimensional damage assessment system, which comprehensively considers the cumulative fatigue damage caused by stress amplitude, flight environment factors, and historical repair records of local structural damage. Through loading analysis of different tasks, it considers the accelerated effect of high-load tasks on fatigue.

[0030] Step S500 specifically includes: Step S510: Based on the fatigue damage prediction values, combined with flight history data, environmental parameter records, and structural damage repair records, a multi-dimensional damage assessment system is constructed. Specifically, fatigue damage prediction values ​​for each structural component are obtained from step S400, and flight history data is collected. This data is from the UAV's data recording system and covers information such as flight time, flight mileage, and flight mode (such as the proportion of time spent in different phases such as takeoff, cruising, and landing). Environmental parameter records are obtained, including temperature, humidity, and wind speed. These data are collected and stored by various onboard environmental sensors. In addition, structural damage repair records are compiled, including details such as the location, type, repair time, and repair method of each damage. A comprehensive assessment model is then established, using the fatigue damage prediction values, flight history data, environmental parameter records, and structural damage repair records as input parameters. For example, the neural network model in the machine learning algorithm can be used to fuse these multi-source data; for example, the flight time and mileage in the flight history data can reflect the intensity of aircraft usage and serve as a characteristic dimension of the model; the temperature and humidity in the environmental parameters will affect the fatigue performance of the material and serve as another characteristic dimension; the structural damage repair records are converted into recognizable features of the model through encoding and other methods; by training this model, it can learn the complex relationship between these factors and fatigue damage, thereby building a multi-dimensional damage assessment system.

[0031] Step S520: Generate a dynamic correction factor based on the real-time monitored flight environment dynamic parameters and mission load intensity to adjust the fatigue damage prediction value. Specifically, this embodiment can utilize various sensors on the UAV, such as meteorological sensors, accelerometers, stress sensors, etc., to monitor the flight environment dynamic parameters and mission load intensity in real time. For example, meteorological sensors can be used to monitor whether strong turbulence is encountered. If strong turbulence is detected, stress sensors can be used to obtain the real-time stress response of the aircraft. By analyzing this data, the degree of impact of the current flight conditions on fatigue damage can be determined. For unforeseen operational limit conditions, based on the characteristics of extreme flight missions, such as high-overload maneuvering flights, the additional fatigue damage caused by the mission to the structure is analyzed, and a corresponding correction factor is calculated to make the fatigue damage prediction value more consistent with the actual situation. Then, corresponding dynamic correction factor calculation rules are formulated according to different flight conditions. Finally, the calculated dynamic correction factor is applied to the fatigue damage prediction value to adjust it.

[0032] Step S530: Generate graded maintenance recommendations based on the adjusted fatigue damage prediction value. Specifically, a multi-dimensional damage assessment system accurately assesses the fatigue damage of the UAV structure, instantly generating maintenance recommendations. These recommendations are then communicated to the UAV operator and the urban low-altitude airspace regulatory authorities. The maintenance recommendations can be generated based on the adjusted fatigue damage prediction value to establish graded maintenance standards. For example, based on the fatigue damage prediction value range, a determination of minor damage may lead to a recommendation for regular inspection and maintenance; a determination of moderate damage may lead to a recommendation for local structural inspection and repair; and a determination of severe damage may lead to an immediate suspension of flight for comprehensive repair or replacement of relevant components. The maintenance recommendations are then transmitted to the UAV operator's management platform and the monitoring system of the urban low-altitude airspace regulatory authorities via wireless communication technologies, such as 5G networks. Based on the recommendations, the UAV operator can promptly schedule maintenance work for the UAV to ensure safe operation of the aircraft. Urban low-altitude airspace regulatory authorities can monitor the maintenance status of the UAV to ensure urban low-altitude flight safety.

[0033] See also Figure 3 As shown, the method further includes: Step S600: Handling airworthiness deviation; specifically, when the fatigue damage prediction value exceeds the preset safety threshold, an airworthiness deviation warning is triggered; the unmanned aerial vehicle with the airworthiness deviation warning is included in the abnormal aircraft control list, and the unmanned aerial vehicle included in the control list is grounded until the control is released after the maintenance verification is completed. Figure 3 As shown, before the UAV is put into use, a preset safety threshold of the fatigue damage prediction value can be determined based on the design standards, material properties, flight mission requirements and relevant airworthiness regulations of the aircraft, combined with the calculation method of the fatigue damage prediction value in step S400. This threshold is a key indicator for ensuring the safe flight of the UAV and represents the maximum degree of fatigue damage that each structural part of the aircraft can withstand under normal flight conditions.

[0034] During the flight of the UAV, the fatigue damage prediction calculation in step S400 is continuously executed to obtain real-time fatigue damage prediction values ​​for each structural component. The urban low-altitude integrated information platform receives this data in real time and compares it with preset safety thresholds. If the fatigue damage prediction value exceeds the preset safety threshold, the platform immediately triggers an airworthiness deviation warning. After the warning is triggered, the urban low-altitude integrated information platform automatically adds the UAV with airworthiness deviation to the Capability Deviation UAV List (CDUL). The platform records relevant information about the UAV, such as the aircraft number, model, operator, current location, and the specific location and severity of the fatigue damage warning, to ensure precise control of the aircraft. The information platform then uses wireless communication technology to simultaneously send information to the UAV operator and the urban low-altitude regulatory authorities. The information sent to the UAV operator explicitly includes a grounding order, requiring the UAV to immediately cease flight missions. Upon receiving the grounding order, the UAV operator arranges for maintenance personnel to repair the aircraft. During the maintenance process, maintenance personnel can repair fatigue damaged areas or replace damaged components based on the maintenance recommendations generated by the multi-dimensional preventive maintenance assessment and decision-making in step S500. After the maintenance is completed, the aircraft needs to be verified for maintenance. The verification methods may include ground testing, simulated flight testing, etc., to ensure that the structural strength and performance of the aircraft are restored to safety standards. After the verification is passed, the operator submits an application for lifting the control to the Urban Low-altitude Integrated Information Platform. After verifying that the maintenance verification information is correct, the platform will remove the aircraft from the abnormal aircraft control list and restore its normal flight qualifications. If the Urban Low-altitude Integrated Information Platform issues a notification but does not receive a maintenance response from the drone operator within the specified time, the urban low-altitude regulatory department will continue to implement measures to stop the operation of the aircraft in the CDUL at low altitudes in the city until a maintenance response is received and the maintenance verification is completed, and then the operating restrictions on the aircraft will be lifted.

[0035] This implementation forms a complete safety and security closed loop, effectively preventing UAVs with severe fatigue damage from continuing to fly, reducing the risk of flight accidents, ensuring safe and orderly low-altitude flight in cities, and protecting the personal safety of residents and urban infrastructure. Through clear management and control processes and maintenance verification requirements, the overall safety and reliability of UAVs is improved.

[0036] See also Figure 2 , which shows a schematic structural diagram of an unmanned aerial vehicle structural fatigue prediction system provided by one embodiment of the present invention, the system comprising: a data acquisition module configured to acquire a sensor data set of a structural part of the UAV; a data preprocessing module configured to dynamically evaluate the data quality of the sensor data set and dynamically adjust the data cleaning preprocessing strategy according to the evaluation results; The stress field distribution module is configured to construct a stress field model reflecting the global stress distribution of the structure based on the preprocessed sensor data set and combined with real-time flight environment parameters; The fatigue damage prediction module is configured to calculate the fatigue damage prediction value of each structural part according to the stress field model and the fatigue characteristics of the material.

[0037] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0038] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A method for predicting structural fatigue of an unmanned aerial vehicle, characterized in that: The method comprises: Obtain sensor data sets of key structural parts of UAVs; Dynamically evaluate the data quality of the sensor data set and dynamically adjust the data cleaning preprocessing strategy based on the evaluation results; Based on the preprocessed sensor data set and combined with real-time flight environment parameters, a stress field model reflecting the global stress distribution of the structure is constructed; The fatigue damage prediction value of each structural part is calculated based on the stress field model and the fatigue characteristics of the material.

2. The method for predicting structural fatigue of an unmanned aerial vehicle according to claim 1, wherein: Dynamically evaluating the data quality of the sensor data set includes: Extract the signal-to-noise ratio and battery supply voltage of sensor data; The continuity analysis of the time series of sensor data is performed through a sliding time window to calculate the data mutation amplitude of adjacent sampling points; A sensor data health index is calculated according to the signal-to-noise ratio, the battery supply voltage, and the data mutation amplitude.

3. The method for predicting structural fatigue of an unmanned aerial vehicle according to claim 2, wherein: Dynamically adjust data cleaning and preprocessing strategies based on evaluation results, including: Compare the current data health index with the preset data quality threshold and calculate the real-time difference; generating a dynamic cleaning decision index based on the real-time difference, the historical difference accumulation, and the difference change rate; The data cleaning frequency is adjusted in real time according to the dynamic cleaning decision index.

4. The method for predicting structural fatigue of an unmanned aerial vehicle according to claim 1, wherein: Based on the preprocessed sensor data set and combined with real-time flight environment parameters, a stress field model reflecting the global stress distribution of the structure is constructed, including: Deploy a sensor group at the target location of the UAV to collect static stress and dynamic vibration data; Combined with the wind speed and temperature parameters in the real-time flight environment, dynamic vibration amplification correction, aerodynamic load correction and thermal stress correction are performed on static stress; The corrected multi-source stress data are integrated to construct a stress field model reflecting the global stress distribution of the structure.

5. The method for predicting structural fatigue of an unmanned aerial vehicle according to claim 4, wherein: Combined with the wind speed and temperature parameters in the real-time flight environment, dynamic vibration amplification correction, aerodynamic load correction and thermal stress correction are performed on static stress, including: The vibration amplitude is measured by an accelerometer, and the static stress is compensated for by the dynamic amplification factor in combination with the material stiffness parameters; Calculate the quadratic growth effect of aerodynamic pressure on structural stress based on real-time wind speed and aerodynamic parameters; Based on the temperature change and the thermal expansion coefficient of the material, the superposition effect of thermal stress on the structural stress is calculated.

6. The method for predicting structural fatigue of an unmanned aerial vehicle according to claim 1, wherein: Based on the stress field model and material fatigue properties, the fatigue damage prediction value of each structural part is calculated, including: According to the corresponding relationship between the stress amplitude and fatigue life of the material, a curve model reflecting the stress amplitude and life characteristics is established; Based on the stress amplitudes of each flight output by the stress field model and the number of cycles of historical flight missions, the cumulative fatigue damage value of each structural part is calculated.

7. The method for predicting structural fatigue of an unmanned aerial vehicle according to claim 6, wherein: Based on the stress amplitude output by the stress field model and the number of historical flight cycles, the cumulative fatigue damage value of each structural part is calculated, including: According to the stress amplitude during each flight, the curve model reflecting the stress amplitude and life characteristics is matched to obtain the corresponding fatigue life; The cumulative fatigue damage value is obtained by adding up the ratio of the number of flight cycles to the corresponding fatigue life.

8. The method for predicting structural fatigue of an unmanned aerial vehicle according to any one of claims 1 to 7, wherein: The method further comprises: Based on the fatigue damage prediction value, combined with flight history data, environmental parameter records and structural damage repair records, a multi-dimensional damage assessment system is constructed; generating a dynamic correction factor to adjust the fatigue damage prediction value based on real-time monitored flight environment dynamic parameters and mission load intensity; Generate graded maintenance recommendations based on adjusted fatigue damage predictions.

9. The method for predicting structural fatigue of an unmanned aerial vehicle according to claim 8, wherein: The method further comprises: When the fatigue damage prediction value exceeds a preset safety threshold, an airworthiness deviation warning is triggered; The unmanned aerial vehicles with the airworthiness deviation warning will be included in the abnormal aircraft control list, and grounding orders will be issued to the unmanned aerial vehicles included in the control list until the control is lifted after the maintenance verification is completed.

10. Unmanned aerial vehicle structural fatigue prediction system, characterized in that: The method for predicting structural fatigue of an unmanned aerial vehicle according to any one of claims 1 to 9 is adopted, wherein the system comprises: a data acquisition module configured to acquire a sensor data set of a structural part of the UAV; a data preprocessing module configured to dynamically evaluate the data quality of the sensor data set and dynamically adjust the data cleaning preprocessing strategy according to the evaluation results; The stress field distribution module is configured to construct a stress field model reflecting the global stress distribution of the structure based on the preprocessed sensor data set and combined with real-time flight environment parameters; The fatigue damage prediction module is configured to calculate the fatigue damage prediction value of each structural part according to the stress field model and the fatigue characteristics of the material.

Images