Flight simulation system and method based on test data

Abstract

The present invention relates to the field of computer simulation technology, and specifically to a flight simulation system and method based on test data. The system includes an aircraft parameter calibration module, a mission environment correlation analysis module, a flight trajectory modeling module, and a control strategy optimization module. In the present invention, by extracting and correcting the power parameters, attitude parameters, and environmental variables of the aircraft test data, the accuracy and adaptability of the flight parameter data are improved, and the matching accuracy between the mission scenario and the test environment is significantly improved. By classifying and labeling trajectory points in a disturbance-intensive area and generating dynamic flight trajectory curves, the prediction and simulation capabilities of trajectories in complex flight environments are enhanced. Combined with the disturbance environment optimization control logic, the control scheme optimization driven by test data is completed, and the flight control accuracy and adaptability in complex scenarios are significantly improved. A closed loop from data calibration to control strategy optimization is achieved, and the mission execution capability and safety are enhanced, while reducing R&D and operational risks.

Description

Technical Field

[0001] The present invention relates to the technical field of computer simulation, and in particular to a flight simulation system and method based on test data. Background Art

[0002] The field of computer simulation technology uses computer models to imitate real systems or processes. It is widely used in engineering design, scientific research, education and training, and decision support. This technology simulates and predicts the dynamic behavior of complex systems by establishing mathematical models, physical models, or intelligent models, combined with computer algorithms and high-performance computing resources. Computer simulation technology is efficient, flexible, and safe, and can provide scientific basis and optimization support for research and development when real experimental conditions are difficult to achieve or costly. In complex scenarios such as aerospace, medical health, and energy management, this technology has shown great value and development potential.

[0003] Among them, the flight simulation system is a specific application of computer simulation technology in the aviation field. It is mainly used in scenarios such as pilot training, aircraft design verification and mission planning. The system helps pilots improve their operating skills by simulating the flight environment, aircraft characteristics and mission operation processes, supports the performance verification of aircraft in the design stage, and formulates the best plan for specific tasks. The flight simulation system has the advantages of low cost, low risk and strong repeatability, and has played an important role in ensuring flight safety, improving flight efficiency and reducing R&D costs.

[0004] When processing aircraft test data, existing technologies often rely on simple statistical or rule-based mapping methods for parameter calibration, limited by the integrity and consistency of the underlying data. This makes it difficult to effectively address the complex relationships between multiple variables, resulting in insufficient adaptability and reliability of test data in multiple environmental scenarios. When analyzing mission environments and disturbance factors, existing technologies often employ simple statistical or rule-based mapping methods, failing to fully consider the complex dynamic relationships between disturbance factors and mission data across different time periods. This can lead to limitations in matching environmental modeling with missions. Existing technologies also have limited capabilities for simulating the dynamic changes in flight trajectories and the distribution of disturbances, lacking the precise annotation and dynamic adjustment of disturbance-intensive areas, impacting the accuracy and adaptability of trajectory models. In terms of control strategy design, existing technologies often rely on pre-set control logic, lacking adaptability to complex environments and failing to fully leverage the dynamic correlations in test data for optimization. This results in reduced control accuracy, low mission execution efficiency, and increased safety risks in complex mission scenarios, while also increasing R&D costs and time consumption during aircraft design verification and mission planning. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a flight simulation system and method based on test data.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a flight simulation system based on test data includes:

[0007] The aircraft parameter calibration module extracts power parameters, attitude parameters, and test environment variables based on the basic aircraft test data, performs interpolation correction and flight phase parameter normalization, adjusts the change trend of the test environment variables, and generates a calibration flight parameter set;

[0008] The mission environment correlation analysis module extracts the aircraft mission data and the test environment disturbance factors based on the calibration flight parameter set, analyzes the variation range and correlation strength of the mission data and the disturbance factors in different time periods, generates a mission environment correlation matrix, screens the associated disturbance factors and sorts them by time series weight, and maps the disturbance distribution to the mission phase to generate a mission environment matching table;

[0009] The flight trajectory modeling module analyzes the three-dimensional position change characteristics of the trajectory points and the disturbance distribution area in the test data based on the mission environment matching table, generates a flight trajectory distribution result, classifies and labels the trajectory points in the disturbance-intensive area, and simulates the dynamic flight trajectory curve in combination with the disturbance data to generate a flight trajectory simulation model;

[0010] Based on the flight trajectory simulation model, the control strategy optimization module extracts the attitude point parameters and trajectory control variables in the simulated trajectory, optimizes the weight distribution of the control variables and attitude point time series, matches the disturbance environment, adjusts the flight control logic, defines flight instructions, and generates a flight control plan driven by test data.

[0011] As a further solution of the present invention, the step of obtaining the calibration flight parameter set is specifically as follows:

[0012] Based on the basic data of the aircraft test, the power parameters, attitude parameters and test environment variables are called, the change trend of the test environment variables is normalized in sections, the change rate in each section is calculated, and the weighted change rate set of the attitude parameters is obtained by mapping the change rate with the attitude parameters.

[0013] Call the weighted change rate set of the posture parameters, set the weight parameters of the segments and associate them with the weighted change rate, using the formula:

[0014]

[0015] Generate normalized parameter results for flight phase;

[0016] Among them, P norm Represents the normalized value of the flight phase parameter, V i is the weighted change rate of the posture parameters of the i-th segment, W iis the weight parameter, n represents the total number of segments;

[0017] Based on the normalized parameter results of the flight phase, the segmented normalized change rate set of the test environment variables is called, and the normalized parameters are dynamically corrected. By comparing the normalized differences of the parameters in each phase, adjusting the weight abnormal items, and eliminating data with large deviations, a calibrated flight parameter set is obtained.

[0018] As a further solution of the present invention, the step of obtaining the task environment association matrix is specifically as follows:

[0019] Based on the calibration flight parameter set, the aircraft mission data and the test environment disturbance factor are called, the variation range of the mission data and the disturbance factor is extracted in segments according to the time series, each variation value is normalized, and a preliminary variation range set of the mission data and the disturbance factor is generated by performing a preliminary weighted operation on the normalized data;

[0020] The preliminary variation range set of the task data and the disturbance factor is called, and the correlation strength between the task data and the disturbance factor within the time period is calculated using the formula:

[0021]

[0022] Generate a list of association strengths;

[0023] Among them, R represents the correlation strength value between task data and disturbance factor, T j is the task data variation range of the jth time period, E j is the range of disturbance factor variation in the jth time period, F j is the weighting coefficient of the jth time period, C is the smoothing adjustment parameter, and m represents the total number of time periods;

[0024] The correlation strength list is called to filter matrix elements whose correlation strength is higher than a set threshold within a time period, and the task environment correlation matrix is output by accumulating and integrating the correlation strength list row by row and column by column.

[0025] As a further solution of the present invention, the step of obtaining the task environment matching table is specifically as follows:

[0026] Based on the task-environment correlation matrix, screening disturbance factors in the task that are correlated with the environment, identifying the impact ratio of each disturbance factor on task execution, and ranking the disturbance factors by weight, thereby obtaining a disturbance factor weight ranking table;

[0027] Based on the disturbance factor weight ranking table, the top-ranked disturbance factors are grouped one by one according to the time series, the time position of each disturbance factor is divided, the weight of the disturbance factor in the time node is calculated and accumulated and mapped to the task cycle time point to generate the disturbance factor time distribution table;

[0028] Based on the disturbance factor time distribution table, the task cycle is divided into multiple stages, the task stages are matched with the disturbance factor time distribution, the weighted sum of the disturbance factor weights within the stage is calculated, the task cycle disturbance distribution and the stage association relationship are integrated, and a task environment matching table is generated.

[0029] As a further solution of the present invention, the steps of obtaining the flight trajectory distribution result are specifically as follows:

[0030] According to the task environment matching table, the coordinate parameters of the three-dimensional trajectory points in the test data are extracted, the displacement change of the trajectory points in the three-dimensional space and the distribution characteristics of the disturbance area are analyzed by the coordinate parameters, the concentrated distribution of the disturbance range is determined by using the position parameters between the trajectory points, and the matching results of the trajectory point position change and the disturbance area are generated;

[0031] Based on the matching results of the trajectory point position change and the disturbance area, the position offset of the trajectory point in the disturbance area is analyzed, the disturbance influence parameter and position deviation are called, and the correction coefficient and nonlinear weight parameter are adjusted to adopt the formula:

[0032]

[0033] Calculate the corrected trajectory point positions and obtain the corrected trajectory position distribution results;

[0034] in, represents the corrected trajectory point position, X represents the original trajectory point position, δ is the position correction coefficient, D represents the distance from the trajectory point to the center of the disturbance area, ΔX represents the position deviation, ΔR represents the disturbance influence parameter, and γ is a nonlinear weight parameter that controls the correlation between the correction range and the position deviation;

[0035] Based on the position distribution result after trajectory correction, the disturbance area parameters and the target area parameters of the mission environment matching table are called, and the distribution density and concentration of the corrected trajectory points in the target area are analyzed. By statistically analyzing the distribution characteristics of the trajectory points, the coverage and range of the trajectory distribution area are determined to generate the flight trajectory distribution result.

[0036] As a further solution of the present invention, the steps of obtaining the flight trajectory simulation model are specifically as follows:

[0037] Based on the flight trajectory distribution results, the coordinates and time series of the trajectory points in the disturbance-intensive area are extracted, the trajectory points are grouped and counted according to the coordinate spacing, the coordinate value and time parameter density are called, the trajectory points in the high-density group are annotated, and a classification and annotation table of the trajectory points in the disturbance-intensive area is generated;

[0038] Based on the classification and annotation table of trajectory points in the disturbance-intensive area, the coordinate data and time nodes of the annotated trajectory points are extracted, the disturbance amplitude data are matched with the trajectory points, and the disturbance amplitudes between the trajectory points are linearly interpolated by calling the coordinate and time series parameters to construct a dynamic trajectory point distribution table of the disturbance data;

[0039] Based on the dynamic trajectory point distribution table of the disturbance data, the coordinate sequences of continuous dynamic trajectory points are connected, the trajectory curve is reorganized according to the time node sequence, the curve interval and direction change between trajectory points are adjusted, the dynamic trend of the curve is calibrated, and a flight trajectory simulation model is generated.

[0040] As a further solution of the present invention, the steps for obtaining the flight control solution driven by the test data are specifically as follows:

[0041] Based on the flight trajectory simulation model, the attitude point parameters in the simulation trajectory are extracted, and the three-dimensional coordinates and time series distribution of the attitude points are analyzed point by point. The attitude point parameters and trajectory control variables are called, and the change rate on the time axis is calculated. By comparing the change amount of each attitude point between consecutive time nodes, the time series change trend of the attitude point parameters is obtained;

[0042] According to the time series change trend of the attitude point parameters, the trajectory control variable parameters are called, and the response amplitude of the control variable and the attitude point change rate are adjusted through weight distribution optimization. The formula is:

[0043]

[0044] Calculate the time series weight value of the control variable and generate the optimized control variable and attitude point time series weight distribution results;

[0045] Among them, W k Represents the time series weight value of the control variable, P k Indicates the initial value of the control variable, Q k Indicates the rate of change of attitude points, T k represents the time threshold parameter, C k represents the trajectory disturbance correlation coefficient, α represents the time series distribution weight coefficient;

[0046] Based on the optimized control variables and attitude point time series weight distribution results, the disturbance environment parameters are matched, the matching degree of the control variables and the disturbance environment is analyzed, the flight control logic is optimized in combination with the attitude point time series distribution, the flight instructions are defined and the response amplitude of the control variables at the time nodes is adjusted to generate a flight control scheme driven by experimental data.

[0047] The flight simulation method based on test data is performed based on the above-mentioned flight simulation system based on test data, and includes the following steps:

[0048] S1: Based on the basic data of the aircraft test, the power parameters, attitude parameters and test environment variables are extracted, the sudden change data are eliminated, the attitude parameters are time-normalized, the abnormal fluctuation items and interference values are eliminated, and the calibration flight parameter set is generated;

[0049] S2: Based on the calibration flight parameter set, extract the aircraft mission data and the test environment disturbance factors, analyze the correlation coefficient and the variation range, sort the disturbance factors by time point, match the mission phase data, and generate a mission environment matching table;

[0050] S3: Based on the mission environment matching table, extract the three-dimensional position change parameters of the trajectory points, classify them into groups and assign them to disturbance areas, analyze the trend and density distribution of the trajectory points in the disturbance-intensive areas, match the disturbance weights of the time periods, and generate the flight trajectory distribution results;

[0051] S4: Based on the flight trajectory distribution results, extract the time series and attitude parameters of the trajectory points in the disturbance-intensive area, segmentally fit the trajectory point positions and attitude parameters, match the disturbance factor weights, and generate a flight trajectory simulation model;

[0052] S5: Based on the flight trajectory simulation model, extract attitude point parameters and trajectory control variables, numerically analyze the attitude point time series in segmented form, match the disturbance area time points, optimize and integrate the control variables and attitude point parameters, and generate a flight control plan driven by experimental data.

[0053] Compared with the prior art, the advantages and positive effects of the present invention are:

[0054] The present invention significantly improves the accuracy and adaptability of flight parameter data by extracting and interpolating the power parameters, attitude parameters, and test environment variables of basic aircraft test data. By analyzing the variation range and correlation strength of mission data and environmental disturbance factors in differentiated time periods, the matching accuracy between mission scenarios and test environments is significantly improved, resolving the problem of difficult quantification of parameter correlations in complex environments. By classifying and labeling trajectory points in disturbance-intensive areas and generating dynamic flight trajectory curves, the prediction and simulation capabilities of flight trajectories in complex flight environments are enhanced, making the trajectory model more adaptable and accurate in dynamic environments. In flight control strategy optimization, the flight control scheme is optimized based on test data by extracting attitude point parameters and control variables from simulated trajectories and adjusting the control logic based on the disturbance environment. This significantly improves the control accuracy and adaptability of the aircraft in complex mission scenarios, achieving a complete closed loop from data calibration, environmental correlation analysis, trajectory simulation, to control strategy optimization. With multidimensional data analysis and dynamic modeling as the core, the system significantly enhances the mission execution capability and safety performance of the aircraft in complex mission scenarios, while reducing the R&D and operational risks caused by the uncertainty of the test environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 is a system flow chart of the present invention;

[0056] Figure 2 A flowchart of calibrating a flight parameter set in the present invention;

[0057] Figure 3 It is a flow chart of the task environment association matrix in the present invention;

[0058] Figure 4 This is a flowchart of the task environment matching table in the present invention;

[0059] Figure 5 This is a flow chart of the flight trajectory distribution results in the present invention;

[0060] Figure 6 This is a flow chart of the flight trajectory simulation model in the present invention;

[0061] Figure 7 This is a flow chart of the experimental data-driven flight control scheme in the present invention. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0063] In the description of the present invention, it should be understood that the terms "length," "width," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," and the like, indicating positions or relationships, are based on the positions or relationships shown in the accompanying drawings and are intended only to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present invention. Furthermore, in the description of the present invention, "plurality" means two or more, unless otherwise expressly and specifically defined.

[0064] See also Figure 1 The present invention provides a technical solution: a flight simulation system based on test data includes:

[0065] The aircraft parameter calibration module extracts power parameters, attitude parameters, and test environment variables based on the basic aircraft test data, performs interpolation correction and flight phase parameter normalization, adjusts the change trend of the test environment variables, and generates a calibration flight parameter set;

[0066] The mission environment correlation analysis module extracts aircraft mission data and test environment disturbance factors based on the calibration flight parameter set, analyzes the variation range and correlation strength of mission data and disturbance factors in different time periods, generates a mission environment correlation matrix, screens the associated disturbance factors and sorts them by time series weight, and maps the disturbance distribution to the mission phase to generate a mission environment matching table;

[0067] The flight trajectory modeling module analyzes the three-dimensional position change characteristics of trajectory points and the disturbance distribution area in the test data based on the mission environment matching table, generates flight trajectory distribution results, classifies and labels trajectory points in the disturbance-intensive area, and simulates dynamic flight trajectory curves in combination with the disturbance data to generate a flight trajectory simulation model.

[0068] The control strategy optimization module is based on the flight trajectory simulation model, extracts the attitude point parameters and trajectory control variables in the simulated trajectory, optimizes the weight distribution of the control variables and attitude point time series, matches the disturbance environment, adjusts the flight control logic, defines flight instructions, and generates a flight control plan driven by test data.

[0069] The calibration flight parameter set includes power parameters, attitude parameters, test environment variables, and flight phase parameters. The mission environment association matrix includes the mission data variation range, disturbance factor variation range, and correlation strength. The mission environment matching table includes the associated disturbance factors, disturbance distribution areas, and time series weights. The flight trajectory distribution results include three-dimensional position change characteristics, disturbance-intensive areas, and trajectory point classification and labeling. The flight trajectory simulation model includes dynamic flight trajectory curves and disturbance-intensive area distribution. The test data-driven flight control scheme includes control variable optimization distribution, attitude point parameter weight distribution, and flight control logic adjustment.

[0070] See also Figure 2 ,The specific steps for obtaining the calibration flight parameter set are:

[0071] Based on the basic data of the aircraft test, the power parameters, attitude parameters and test environment variables are called, the change trend of the test environment variables is normalized in sections, the change rate in each section is calculated, and the weighted change rate set of the attitude parameters is obtained by mapping the change rate with the attitude parameters.

[0072] The dynamic parameters, attitude parameters and test environment variables of different time periods in the test data record library are called, and the test environment variable data are segmented according to the time series. The change amplitude and change rate of the data in each segment are calculated. The maximum and minimum values of the segmented data are firstly differentially calculated, and then the change range is divided by the time span to obtain the change rate of each segment. Subsequently, the change rate is mapped to the interval [0, 1] using a normalization function. The normalized segmented environmental variable data is accumulated to obtain the normalized segmented change trend result. Then, the acceleration, angular velocity and height data in the attitude parameter data set are called, and the normalized change trend of each segment is associated with the attitude parameter data point. The weighted change rate of the attitude parameter in the corresponding time period is extracted to generate a set of weighted change rates of the attitude parameters.

[0073] Call the weighted change rate set of posture parameters, set the weight parameters of the segments and associate them with the weighted change rate using the formula:

[0074]

[0075] Generate normalized parameter results for flight phase;

[0076] Among them, P norm Represents the normalized value of the flight phase parameter, V i is the weighted change rate of the posture parameters of the i-th segment, W i is the weight parameter, n represents the total number of segments;

[0077] The benefit of the formula is that by introducing the absolute value of the weight parameter and the weighted change rate of the posture parameter, and combining the segmented normalization results with square root normalization, it improves the uneven distribution of parameter weights and enhances the calculation flexibility and accuracy of normalization.

[0078] Assume that the number of segments is n=3, and the weighted change rate of the posture parameter V i ={0.2, 0.4, 0.5}, weight parameter W i ={0.6, 0.8, 1.0};

[0079] Calculate the molecular part:

[0080] Calculate the denominator:

[0081]

[0082]

[0083] Combined denominators:

[0084] Substituting into the formula:

[0085] This result shows that the calculated P norm =0.45 is the normalized calibration parameter value, which represents the intermediate result after weighted normalization of the segment posture parameters and weight parameters, and can be used to further dynamically correct the parameter distribution of each segment.

[0086] Based on the normalized parameter results of the flight phase, the segmented normalized change rate set of the test environment variables is called to dynamically calibrate the normalized parameters. By comparing the normalized differences of the parameters in each phase, adjusting the weighted abnormal items, and eliminating data with large deviations, a calibrated flight parameter set is obtained.

[0087] First, by performing segmented difference operations on the normalized parameter results, the normalized difference values between each segment are extracted. Then, a threshold range is set to judge the extracted results item by item, and the segmented parameter sets whose deviations exceed the threshold are screened. The segmented change rate data of the test environment variables are called, and the segmented parameters with deviations are dynamically adjusted. The deviation item data are redistributed by introducing a dynamic correction coefficient, and the deviation item data are evenly distributed to adjacent segments. At the same time, data cleaning is performed on the segmented data set after weight adjustment, and abnormal data points that deviate from the normal distribution range are eliminated. The adjusted normalized parameter difference values are recalculated, and the adjusted normalized parameter data are merged with the remaining segmented normalized parameter sets. Finally, the output calibrated flight parameter set is sorted out.

[0088] See also Figure 3, the specific steps for obtaining the task-environment association matrix are:

[0089] Based on the calibration flight parameter set, the aircraft mission data and the test environment disturbance factors are called, and the variation range of the mission data and the disturbance factors is extracted in segments according to the time series. The variation value of each segment is normalized, and a preliminary variation range set of the mission data and the disturbance factors is generated through preliminary weighted operation on the normalized data.

[0090] First, the time series is divided into several time windows. The maximum and minimum values of the task data and the disturbance factor in each time period are extracted, and the difference between the two in the time period is calculated respectively. Then, the variation range is normalized and the variation range of the task data and the disturbance factor is mapped to the interval [0, 1]. The normalization process is completed by dividing the difference by the maximum data amplitude in the time period to generate a set of normalized variation values for each time period. Then, the normalized data is subjected to segmented accumulation processing. By continuous summation over the time series, the cumulative variation trend of the task data and the disturbance factor is obtained. At the same time, the segmented data is weighted by time weight to adjust the contribution of each segment of data in the final variation range set to ensure the correlation integrity of the variation range set in the time period dimension. Finally, a preliminary variation range set of the task data and the disturbance factor is formed for the next step of correlation strength analysis.

[0091] Call the preliminary change range set of task data and disturbance factors, and calculate the correlation strength between task data and disturbance factors within the time period using the formula:

[0092]

[0093] Generate a list of association strengths;

[0094] Among them, R represents the correlation strength value between task data and disturbance factor, T j is the task data variation range of the jth time period, E j is the range of disturbance factor variation in the jth time period, F j is the weighting coefficient of the jth time period, C is the smoothing adjustment parameter, and m represents the total number of time periods;

[0095] The benefit of this formula is that by introducing time period weighting coefficients and smoothing adjustment parameters, the dynamic change characteristics of task data and disturbance factors are quantified into calculable correlation strengths, thereby enhancing the accuracy of correlation assessment between data.

[0096] Assume that the number of time periods m = 3, and the task data variation range T j ={1.2, 0.8, 1.0}, the disturbance factor variation range E j ={0.9, 1.1, 0.7}, time period weighting coefficient Fj ={0.6, 0.8, 0.5}, smoothing adjustment parameter C = 0.1;

[0097] Calculate the molecular part:

[0098]

[0099] Calculate the denominator:

[0100]

[0101] Substituting into the formula:

[0102] The results show that the calculated R = 0.501 is the correlation strength value between the task data and the disturbance factor, indicating that the dynamic change characteristics of the two within the time period have a medium-intensity correlation, which serves as the core calculation result for generating the correlation matrix.

[0103] Call the correlation strength list, filter the matrix elements whose correlation strength is higher than the set threshold within the time period, and output the task environment correlation matrix by accumulating and integrating the correlation strength list row by row and column by column;

[0104] The correlation strength data of each time period is screened. First, a correlation strength threshold is set, and all elements in the correlation list are judged one by one. The matrix elements with correlation strength greater than the threshold are screened out, and their position index in the time period is recorded. Then, the matrix elements that meet the conditions are aggregated in rows and columns, and the screened correlation strength values are accumulated in the order of rows and columns to form the row cumulative data and column cumulative data of the matrix. Then, the row cumulative data and the column cumulative data are further merged to generate a high correlation data set between the task data and the disturbance factor in the time series. Finally, through the segmented sorting and reorganization operations of the time period data, the task environment correlation matrix is output as the overall correlation result of the task data and the disturbance factor.

[0105] See also Figure 4 , the specific steps for obtaining the task environment matching table are:

[0106] Based on the task-environment correlation matrix, the disturbance factors in the task that are correlated with the environment are screened, the impact ratio of each disturbance factor on task execution is identified, the disturbance factors are weighted and ranked, and a disturbance factor weight ranking table is obtained;

[0107] Based on the real-world mission environment data from flight experiments, by setting specific correlation thresholds, we compare multiple variables in the mission environment, such as wind speed, air pressure changes, temperature and humidity gradients, and other disturbance factors, one by one, to quantify their degree of interference with mission completion. For example, in a flight experiment, if the impact of wind speed disturbances on route deviation is greater than 10%, we mark this disturbance factor as a significant interference parameter. We analyze the scope and intensity of each disturbance factor's impact one by one, and by observing changes in mission completion, such as flight path stability and target arrival time deviation, we determine the proportion of each disturbance factor's impact on mission completion. Based on the impact proportions, we assign weights to the disturbance factors according to their significance. Using the aggregated results of real-world flight data, we generate a weight ranking table for the disturbance factors. This weight ranking is then imported into the mission association model, laying the foundation for subsequent grouping and time series analysis.

[0108] Based on the disturbance factor weight ranking table, the top disturbance factors are grouped one by one according to the time series, and the time position of each disturbance factor is divided. The weight of the disturbance factor in the time node is calculated and accumulated and mapped to the task cycle time point to generate the disturbance factor time distribution table;

[0109] Combining the interaction between mission timing and environmental disturbances in flight test data, the impact occurrence time of each disturbance factor is combined with the weight change trend, and the changes in wind speed disturbances in different time periods within the flight simulation mission cycle are observed. The disturbance factors are grouped into early, middle and late stages according to the weight value. For example, wind speed may have the greatest impact on the route within the first 10 minutes of flight, while air pressure changes significantly interfere with altitude maintenance in the second half of the flight mission. The two need to be grouped into different time series. Based on this, the weighted cumulative value of the disturbance factor at each time node is calculated, the cumulative disturbance intensity at each time point is summarized, and it is mapped to the specific time point within the mission cycle to generate a time distribution table of the disturbance factor. This time distribution table not only reflects the disturbance law during the mission execution process, but also provides a data-based theoretical basis for the design of subsequent control strategies for the mission.

[0110] Based on the disturbance factor time distribution table, the task cycle is divided into multiple stages. The task stages are matched with the disturbance factor time distribution. The weighted sum of the disturbance factor weights within the stage is calculated. The relationship between the task cycle disturbance distribution and the stage is integrated to generate a task environment matching table.

[0111] Combined with the mission cycle division standards in the flight test data, such as the three stages of takeoff, cruise, and landing, the key objectives of each mission stage are clarified. By analyzing the time distribution table, the disturbance factors and their cumulative weights in different stages are matched one by one, and the main interference factors in the stage and their influence degree are determined. Taking the cruise stage of flight simulation as an example, if it is found that the cumulative weight of wind speed disturbance and air pressure change in this stage exceeds 70%, it is necessary to focus on the interference effect of these two types of disturbance factors in the cruise stage. When calculating the weighted sum of the disturbance factor weights in the stage, it is necessary to linearly superimpose each disturbance item according to the actual influence ratio of the disturbance factor, and summarize the total interference value of each stage. After integrating the mission cycle disturbance distribution and the stage correlation relationship, a mission environment matching table is generated. This matching table can intuitively reflect the key disturbances in each mission stage and their position and intensity relationship in the mission cycle, providing data support for flight mission interference control and stage optimization.

[0112] See also Figure 5 ,The specific steps for obtaining the flight trajectory distribution results are:

[0113] According to the task environment matching table, the coordinate parameters of the three-dimensional trajectory points in the test data are extracted. The displacement change of the trajectory points in the three-dimensional space and the distribution characteristics of the disturbance area are analyzed through the coordinate parameters. The concentrated distribution of the disturbance range is judged by using the position parameters between the trajectory points, and the matching results of the trajectory point position change and the disturbance area are generated.

[0114] The initial coordinate value and spatial distribution of each trajectory point are analyzed step by step, the spatial position information between adjacent trajectory points is called, and the spatial displacement change between trajectory points is obtained through differential operation. Based on the timestamp parameters of each trajectory point, the change trend of the trajectory point in three-dimensional space is judged. The cumulative distribution of the displacement of the trajectory point is further analyzed. By comparing the change patterns of different trajectory points on the time axis, the displacement data is matched with the disturbance area parameters, the concentrated distribution range of the disturbance area is extracted, and the correspondence analysis of the trajectory points and the disturbance area parameters is performed. The concentration degree of the trajectory points in each disturbance area is calculated. Combined with the three-dimensional spatial position information, the matching results of the trajectory point position change and the disturbance area are generated, providing the required input for subsequent correction and modeling.

[0115] Based on the matching results of the trajectory point position change and the disturbance area, the position offset of the trajectory point in the disturbance area is analyzed, the disturbance influence parameters and position deviation are called, and the correction coefficient and nonlinear weight parameters are adjusted. The formula is used:

[0116]

[0117] Calculate the corrected trajectory point positions and obtain the corrected trajectory position distribution results;

[0118] in, represents the corrected trajectory point position, X represents the original trajectory point position, δ is the position correction coefficient, D represents the distance from the trajectory point to the center of the disturbance area, ΔX represents the position deviation, ΔR represents the disturbance influence parameter, and γ is a nonlinear weight parameter that controls the correlation between the correction range and the position deviation;

[0119] The benefit of this formula is that it introduces position deviation and disturbance influence parameters, and adjusts the correction range through the weight γ, thereby achieving accurate correction of the trajectory points;

[0120] Given the original trajectory point position X = 10.5, the distance from the trajectory point to the center of the disturbance area D = 2.0, the position deviation |ΔX| = 0.5, the disturbance influence parameter ΔR = 4.0, the correction coefficient δ = 1.2, and the weight parameter γ = 2, substitute the parameters into the formula:

[0121]

[0122] The result shows that the corrected trajectory point position is 12.375. By calculating the correction formula, the position of the trajectory point in the disturbance area is adjusted, and the corrected trajectory point distribution data required for subsequent modeling is further provided.

[0123] Based on the position distribution results after trajectory correction, call the disturbance area parameters and the target area parameters in the mission environment matching table, analyze the distribution density and concentration of the corrected trajectory points in the target area, and judge the coverage and range of the trajectory distribution area by statistically analyzing the distribution characteristics of the trajectory points to generate the flight trajectory distribution results;

[0124] First, the position data after trajectory correction is classified and analyzed. Each trajectory point is spatially divided according to its position distribution. The coordinate density parameters of each corrected trajectory point in three-dimensional space are calculated. For each trajectory point, its spatial concentration is judged by the distribution pattern of adjacent points. The distribution boundary and coverage of the target area are further extracted. The deviation between the density parameters of the trajectory points and the distribution boundary of the target area is compared. The spatial attribution of the trajectory points is corrected using the disturbance area parameters. The distribution characteristics of the judgment area are accumulated, and the distribution density of the trajectory points in the target area is counted one by one. The distribution of the trajectory points and the coverage of the target area are evaluated, providing the data support required for trajectory modeling.

[0125] See also Figure 6 ,The specific steps for obtaining the flight trajectory simulation model are:

[0126] Based on the flight trajectory distribution results, the coordinates and time series of the trajectory points in the disturbance-intensive area are extracted, the trajectory points are grouped and counted according to the coordinate spacing, the coordinate value and time parameter density are called, the trajectory points in the high-density group are annotated, and a classification and annotation table of the trajectory points in the disturbance-intensive area is generated;

[0127] Based on actual flight data, the system identifies the disturbance characteristics of densely populated trajectory areas during flight missions, screens the collected flight trajectory point data, and uses the spatial distribution and time series of trajectory point coordinates as a benchmark to identify areas with high disturbance intensity. For example, by observing the spatial aggregation of trajectory points, it determines whether the coordinate spacing of trajectory points in a certain area is less than a certain threshold. The trajectory points are then classified and grouped according to their continuity on the time axis, marking the density changes of trajectory points within the time period. After completing the group statistics, the distribution characteristics of the trajectory points are annotated based on the coordinates and time parameter density of each group of trajectory points. The trajectory points in the densely populated disturbance area are classified by annotation, and a classification and annotation table of trajectory points in the densely populated disturbance area is finally formed. This table directly reflects the distribution pattern of trajectory points in the flight simulation mission and helps to analyze the interference mechanism of high-density disturbance areas on flight trajectories.

[0128] Based on the classification and annotation table of trajectory points in the disturbance-intensive area, the coordinate data and time nodes of the annotated trajectory points are extracted, the disturbance amplitude data are matched with the trajectory points, and the disturbance amplitude between the trajectory points is linearly interpolated by using the coordinate and time series parameters to construct a dynamic trajectory point distribution table of the disturbance data;

[0129] According to the mission timeline of the flight simulation test, the spatial coordinates and time parameters of the trajectory points are segmented and extracted, and the matching is completed in combination with the disturbance amplitude data. The position of each trajectory point in the time series is observed and associated with its corresponding disturbance amplitude data. The matching is performed point by point to ensure the precise correspondence between the disturbance amplitude and the trajectory point coordinates and time series. By calling the time series and coordinate value parameters of the trajectory points, the disturbance amplitude between the trajectory points is interpolated to construct a dynamic trajectory distribution model of the disturbance data. For example, the trajectory point data between two consecutive time nodes is selected, and the disturbance amplitude change between the two points is supplemented by linear interpolation to generate a dynamic trajectory point distribution table of the disturbance data. This table can reflect the dynamic changes in the disturbance intensity of the trajectory points during the flight mission, providing key data support for trajectory analysis and model calibration.

[0130] Based on the dynamic trajectory point distribution table of disturbance data, the coordinate sequence of continuous dynamic trajectory points is connected, the trajectory curve is reorganized according to the time node sequence, the curve interval and direction change between trajectory points are adjusted, the dynamic trend of the curve is calibrated, and the flight trajectory simulation model is generated;

[0131] Based on the time series of trajectory points, the trajectory curves are connected point by point and reorganized to show the dynamic change trend of the flight trajectory. The spatial coordinates of the trajectory points are linearly connected, and the overall shape of the trajectory curve is constructed in the order of time nodes. During the connection process, it is necessary to combine the curve interval and direction changes between trajectory points, and make adjustments for areas that deviate significantly from the standard trajectory to ensure the smoothness and continuity of the trajectory curve, calibrate the dynamic trend of each curve segment, and optimize the connection method by analyzing the distribution pattern and change direction of the trajectory points segment by segment to make it more accurately reflect the actual distribution characteristics of the flight trajectory. Finally, a flight trajectory simulation model is generated, which can visualize the impact of disturbances in the test data and provide a dynamic simulation basis for flight trajectory optimization.

[0132] See also Figure 7 ,The specific steps for obtaining the flight control solution driven by test data are as follows:

[0133] Based on the flight trajectory simulation model, the attitude point parameters in the simulation trajectory are extracted, and the three-dimensional coordinates and time series distribution of the attitude points are analyzed point by point. The attitude point parameters and trajectory control variables are called, and the change rate on the time axis is calculated. By comparing the change amount of each attitude point between consecutive time nodes, the time series change trend of the attitude point parameters is obtained;

[0134] By analyzing the three-dimensional coordinate data of each posture point point by point and associating the coordinate value with the time series, the spatial position change of the posture point between consecutive time nodes is called, the displacement change of each posture point in the time dimension is calculated, and the change is differentially calculated based on the time interval to obtain the displacement rate and spatial trajectory parameters between the posture points. Then, the posture point parameters and time nodes are segmented, and the displacement rate and change trend are accumulated according to the time series. The time response deviation of adjacent posture points is compared with the accumulated results to determine the change trend and cumulative characteristics of the posture points at different time nodes. The offset characteristics of the trajectory point parameters distributed over time are further analyzed, and the time series change characteristics and the spatial change parameters of the posture points are comprehensively processed to extract the time series change law and cumulative change trend of the posture points. Finally, the time series change trend of the posture point parameters is generated to provide data support for the subsequent optimization of trajectory control variables.

[0135] According to the time series change trend of the attitude point parameters, the trajectory control variable parameters are called, and the response amplitude of the control variable and the attitude point change rate are adjusted through weight distribution optimization. The formula is:

[0136]

[0137] Calculate the time series weight value of the control variable and generate the optimized control variable and attitude point time series weight distribution results;

[0138] Among them, W k Represents the time series weight value of the control variable, P k Indicates the initial value of the control variable, Q k Indicates the rate of change of attitude points, T k represents the time threshold parameter, C k represents the trajectory disturbance correlation coefficient, α represents the time series distribution weight coefficient;

[0139] The benefit of the formula is that by introducing the time threshold parameter and the disturbance correlation coefficient, the response amplitude of the control variable at the time node and the change rate of the posture point are comprehensively considered, and the time series distribution logic of the weight is optimized;

[0140] Parameter acquisition and value assignment:

[0141] P k : Initial value of control variable, obtained by extracting control input data from flight test, set P k =5.0;

[0142] Q k : The rate of change of the attitude point is calculated by the spatial coordinate difference and time interval of adjacent time nodes, and Q is taken k =7.0;

[0143] T k : Time threshold parameter, defined as the reference time for response control, taken as T k =4.0;

[0144] C k : Trajectory disturbance correlation coefficient, obtained through simulation calculation of disturbance environment and analysis of feedback parameters, C k =2.0;

[0145] α: time series weight coefficient, obtained by coupling analysis of time node distribution and control parameters, set to α = 3.0;

[0146] Substitute into the formula for calculation:

[0147] W k =(5.0+|7.0-4.0|)·2.0 3.0

[0148] W k =(5.0+3.0)·8.0

[0149] W k =8.0·8.0=64.0

[0150] This result shows that the time series weight W kIt is 64.0, which represents the optimized weight distribution of the control variables at the current time node. The optimized weight distribution result will be used to match the time series relationship between the posture point parameters and the control variables.

[0151] Based on the optimized control variables and attitude point time series weight distribution results, the disturbance environment parameters are matched and the matching degree between the control variables and the disturbance environment is analyzed. The flight control logic is optimized in combination with the attitude point time series distribution. The flight instructions are defined and the response amplitude of the control variables at the time nodes is adjusted to generate a flight control plan driven by test data.

[0152] The time response data of the attitude points are compared and analyzed using the disturbance environment parameters. The response amplitudes of the control variable parameters at each time node are gradually adjusted. The relationship between the control amplitude and the attitude point changes at each time node is calculated through segmented time domain processing. The matching degree between the disturbance environment and the control variables is optimized using the time series distribution characteristics. The time domain distribution characteristics of the time node parameters are analyzed one by one, and the optimized control variable parameters are mapped to the time domain data of the attitude points. The weighted response amplitudes at each time node are compared, and the control variable response parameters in the time series distribution are gradually adjusted. The response logic of the flight commands is defined. By optimizing the matching of the attitude point time series distribution with the disturbance environment parameters, a flight control plan driven by test data is generated. A flight control plan is a systematic strategy designed to dynamically adjust the aircraft's attitude and speed to adapt to environmental disturbances, ensuring flight stability and efficiency. This plan includes the aircraft's preset flight path, attitude adjustments, speed control, and necessary emergency response commands. By optimizing the matching of the attitude point time series distribution with the disturbance environment parameters, a flight control plan driven by test data is generated, enabling the aircraft to maintain optimal flight performance under various environmental conditions.

[0153] The flight simulation method based on test data is performed based on the above-mentioned flight simulation system based on test data, and includes the following steps:

[0154] S1: Based on the basic data of the aircraft test, the power parameters, attitude parameters and test environment variables are extracted, the sudden change data are eliminated, the attitude parameters are time-normalized, the abnormal fluctuation items and interference values are eliminated, and the calibration flight parameter set is generated;

[0155] S2: Based on the calibration flight parameter set, extract the aircraft mission data and the test environment disturbance factors, analyze the correlation coefficient and the variation range, sort the disturbance factors by time point, match the mission phase data, and generate the mission environment matching table;

[0156] S3: Based on the mission environment matching table, the three-dimensional position change parameters of the trajectory points are extracted, the points are grouped and classified into disturbance areas, the trend and density distribution of the trajectory points in the disturbance-intensive areas are analyzed, the disturbance weights of the time periods are matched, and the flight trajectory distribution results are generated;

[0157] S4: Based on the flight trajectory distribution results, the time series and attitude parameters of the trajectory points in the disturbance-intensive area are extracted, the trajectory point positions and attitude parameters are fitted piecewise, the disturbance factor weights are matched, and the flight trajectory simulation model is generated;

[0158] S5: Based on the flight trajectory simulation model, extract attitude point parameters and trajectory control variables, numerically analyze the attitude point time series in segmented form, match the time points in the disturbance area, optimize and integrate the control variables and attitude point parameters, and generate a flight control plan driven by experimental data.

[0159] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A flight simulation system based on test data, characterized in that: The system comprises: The aircraft parameter calibration module extracts power parameters, attitude parameters, and test environment variables based on the basic aircraft test data, performs interpolation correction and flight phase parameter normalization, adjusts the change trend of the test environment variables, and generates a calibration flight parameter set; The mission environment correlation analysis module extracts the aircraft mission data and the test environment disturbance factors based on the calibration flight parameter set, analyzes the variation range and correlation strength of the mission data and the disturbance factors in different time periods, generates a mission environment correlation matrix, screens the associated disturbance factors and sorts them by time series weight, and maps the disturbance distribution to the mission phase to generate a mission environment matching table; The flight trajectory modeling module analyzes the three-dimensional position change characteristics of the trajectory points and the disturbance distribution area in the test data based on the mission environment matching table, generates a flight trajectory distribution result, classifies and labels the trajectory points in the disturbance-intensive area, and simulates the dynamic flight trajectory curve in combination with the disturbance data to generate a flight trajectory simulation model; Based on the flight trajectory simulation model, the control strategy optimization module extracts the attitude point parameters and trajectory control variables in the simulated trajectory, optimizes the weight distribution of the control variables and attitude point time series, matches the disturbance environment, adjusts the flight control logic, defines flight instructions, and generates a flight control plan driven by test data.

2. The flight simulation system based on test data according to claim 1, characterized in that: The steps for obtaining the calibration flight parameter set are specifically as follows: Based on the basic data of the aircraft test, the power parameters, attitude parameters and test environment variables are called, the change trend of the test environment variables is normalized in sections, the change rate in each section is calculated, and the weighted change rate set of the attitude parameters is obtained by mapping the change rate with the attitude parameters. Call the weighted change rate set of the posture parameters, set the weight parameters of the segments and associate them with the weighted change rate, using the formula: Generate normalized parameter results for flight phase; Among them, P norm Represents the normalized value of the flight phase parameter, V i is the weighted change rate of the posture parameters of the i-th segment, W i is the weight parameter, n represents the total number of segments; Based on the normalized parameter results of the flight phase, the segmented normalized change rate set of the test environment variables is called, and the normalized parameters are dynamically corrected. By comparing the normalized differences of the parameters in each phase, adjusting the weight abnormal items, and eliminating data with large deviations, a calibrated flight parameter set is obtained.

3. The flight simulation system based on test data according to claim 2, characterized in that: The steps for obtaining the task environment association matrix are specifically as follows: Based on the calibration flight parameter set, the aircraft mission data and the test environment disturbance factor are called, the variation range of the mission data and the disturbance factor is extracted in segments according to the time series, each variation value is normalized, and a preliminary variation range set of the mission data and the disturbance factor is generated by performing a preliminary weighted operation on the normalized data; The preliminary variation range set of the task data and the disturbance factor is called, and the correlation strength between the task data and the disturbance factor within the time period is calculated using the formula: Generate a list of strengths of association; Among them, R represents the correlation strength value between task data and disturbance factor, T j is the task data variation range of the jth time period, E j is the range of disturbance factor variation in the jth time period, F j is the weighting coefficient of the jth time period, C is the smoothing adjustment parameter, and m represents the total number of time periods; The correlation strength list is called to filter matrix elements whose correlation strength is higher than a set threshold within a time period, and the task environment correlation matrix is output by accumulating and integrating the correlation strength list row by row and column by column.

4. The flight simulation system based on test data according to claim 3, characterized in that: The steps for obtaining the task environment matching table are specifically as follows: Based on the task-environment correlation matrix, screening disturbance factors in the task that are correlated with the environment, identifying the impact ratio of each disturbance factor on task execution, and ranking the disturbance factors by weight, thereby obtaining a disturbance factor weight ranking table; Based on the disturbance factor weight ranking table, the top-ranked disturbance factors are grouped one by one according to the time series, the time position of each disturbance factor is divided, the weight of the disturbance factor in the time node is calculated and accumulated and mapped to the task cycle time point to generate the disturbance factor time distribution table; Based on the disturbance factor time distribution table, the task cycle is divided into multiple stages, the task stages are matched with the disturbance factor time distribution, the weighted sum of the disturbance factor weights within the stage is calculated, the task cycle disturbance distribution and the stage association relationship are integrated, and a task environment matching table is generated.

5. The flight simulation system based on test data according to claim 4, characterized in that: The steps for obtaining the flight trajectory distribution result are specifically as follows: According to the task environment matching table, the coordinate parameters of the three-dimensional trajectory points in the test data are extracted, the displacement change of the trajectory points in the three-dimensional space and the distribution characteristics of the disturbance area are analyzed by the coordinate parameters, the concentrated distribution of the disturbance range is determined by using the position parameters between the trajectory points, and the matching results of the trajectory point position change and the disturbance area are generated; Based on the matching results of the trajectory point position change and the disturbance area, the position offset of the trajectory point in the disturbance area is analyzed, the disturbance influence parameter and position deviation are called, and the correction coefficient and nonlinear weight parameter are adjusted to adopt the formula: Calculate the corrected trajectory point positions and obtain the corrected trajectory position distribution results; in, represents the corrected trajectory point position, X represents the original trajectory point position, δ is the position correction coefficient, D represents the distance from the trajectory point to the center of the disturbance area, ΔX represents the position deviation, ΔR represents the disturbance influence parameter, and γ is a nonlinear weight parameter that controls the correlation between the correction range and the position deviation; Based on the position distribution result after trajectory correction, the disturbance area parameters and the target area parameters of the mission environment matching table are called, and the distribution density and concentration of the corrected trajectory points in the target area are analyzed. By statistically analyzing the distribution characteristics of the trajectory points, the coverage and range of the trajectory distribution area are determined to generate the flight trajectory distribution result.

6. The flight simulation system based on test data according to claim 5, characterized in that: The steps for obtaining the flight trajectory simulation model are specifically as follows: Based on the flight trajectory distribution results, the coordinates and time series of the trajectory points in the disturbance-intensive area are extracted, the trajectory points are grouped and counted according to the coordinate spacing, the coordinate value and time parameter density are called, the trajectory points in the high-density group are annotated, and a classification and annotation table of the trajectory points in the disturbance-intensive area is generated; Based on the classification and annotation table of trajectory points in the disturbance-intensive area, the coordinate data and time nodes of the annotated trajectory points are extracted, the disturbance amplitude data are matched with the trajectory points, and the disturbance amplitudes between the trajectory points are linearly interpolated by calling the coordinate and time series parameters to construct a dynamic trajectory point distribution table of the disturbance data; Based on the dynamic trajectory point distribution table of the disturbance data, the coordinate sequences of continuous dynamic trajectory points are connected, the trajectory curve is reorganized according to the time node sequence, the curve interval and direction change between trajectory points are adjusted, the dynamic trend of the curve is calibrated, and a flight trajectory simulation model is generated.

7. The flight simulation system based on test data according to claim 6, characterized in that: The steps for obtaining the flight control solution driven by the test data are specifically as follows: Based on the flight trajectory simulation model, the attitude point parameters in the simulation trajectory are extracted, and the three-dimensional coordinates and time series distribution of the attitude points are analyzed point by point. The attitude point parameters and trajectory control variables are called, and the change rate on the time axis is calculated. By comparing the change amount of each attitude point between consecutive time nodes, the time series change trend of the attitude point parameters is obtained; According to the time series change trend of the attitude point parameters, the trajectory control variable parameters are called, and the response amplitude of the control variable and the attitude point change rate are adjusted through weight distribution optimization. The formula is: Calculate the time series weight value of the control variable and generate the optimized control variable and attitude point time series weight distribution results; Among them, W k Represents the time series weight value of the control variable, P k Indicates the initial value of the control variable, Q k Indicates the rate of change of attitude points, T k represents the time threshold parameter, C k represents the trajectory disturbance correlation coefficient, α represents the time series distribution weight coefficient; Based on the optimized control variables and attitude point time series weight distribution results, the disturbance environment parameters are matched, the matching degree of the control variables and the disturbance environment is analyzed, the flight control logic is optimized in combination with the attitude point time series distribution, the flight instructions are defined and the response amplitude of the control variables at the time nodes is adjusted to generate a flight control scheme driven by experimental data.

8. A flight simulation method based on test data, characterized in that: The flight simulation system based on test data according to any one of claims 1 to 7 comprises the following steps: Based on the basic data of the aircraft test, the power parameters, attitude parameters and test environment variables are extracted, the sudden change data are eliminated, the attitude parameters are time-normalized, the abnormal fluctuation items and interference values are eliminated, and the calibration flight parameter set is generated; Extracting aircraft mission data and test environment disturbance factors based on the calibration flight parameter set, analyzing correlation coefficients and variation ranges, sorting disturbance factors by time point, matching mission phase data, and generating a mission environment matching table; Based on the mission environment matching table, the three-dimensional position change parameters of the trajectory points are extracted, the points are grouped and classified into disturbance areas, the trend and density distribution of the trajectory points in the disturbance-intensive areas are analyzed, the disturbance weights of the time periods are matched, and the flight trajectory distribution results are generated; Based on the flight trajectory distribution results, the time series and attitude parameters of the trajectory points in the disturbance-intensive area are extracted, the trajectory point positions and attitude parameters are fitted in sections, the disturbance factor weights are matched, and a flight trajectory simulation model is generated; Based on the flight trajectory simulation model, attitude point parameters and trajectory control variables are extracted, the attitude point time series is numerically segmented and analyzed, the disturbance area time points are matched, the control variables and attitude point parameters are optimized and integrated, and a flight control scheme driven by experimental data is generated.

Images