A multidimensional data mining and analysis system based on flight simulation

Abstract

The present invention relates to the field of data mining technology, and specifically to a multidimensional data mining and analysis system based on flight simulation. The system includes a flight trajectory characteristic analysis module, an action characteristic correlation analysis module, a key action offset prediction module, and a training task allocation module. In the present invention, by decomposing flight trajectory change parameters, extracting trajectory offset characteristic distribution, improving the accuracy of trajectory offset dynamic evaluation, significantly enhancing the ability to capture trajectory change patterns, analyzing the correlation between control torque changes and rudder surface offsets, quantifying the key correlation between actions and trajectories, laying the foundation for predicting the distribution range of high-frequency offset actions, combining trend analysis of action characteristic parameters, clarifying the offset direction and amplitude difference, optimizing rudder surface adjustment and control torque distribution, making training allocation meet requirements, and achieving comprehensive coverage of flight data from pattern discovery to task optimization, improving decision-making accuracy and training efficiency, and enhancing flight safety.

Description

Technical Field

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

[0002] The field of data mining technology involves extracting valuable knowledge and patterns from large amounts of data to assist in decision-making, predictive analysis, and pattern recognition. Through various algorithms and methods, such as classification, clustering, regression analysis, and association rule discovery, data mining can discover potential trends, associations, and patterns from structured or unstructured data. It is widely used in multiple industries, such as finance, healthcare, marketing, industry, aviation, etc. When processing complex and large-scale data sets, it can automatically identify important information in the data and provide support for decision-making. With the improvement of computing power and the continuous growth of data scale, the development of data mining technology is also deepening, promoting the realization and application of intelligent systems.

[0003] Among them, the multidimensional data mining and analysis system is a system that integrates multiple data mining technologies. It aims to extract valuable information from multi-dimensional and multi-source aviation data to support real-time decision-making and optimization. The system can analyze real-time data in flight simulation, identify anomalies or optimization space during flight, and help pilots make effective decisions during training and actual flight. It can not only provide retrospective analysis based on historical data, but also perform dynamic monitoring and decision-making recommendations based on real-time data, thereby improving the efficiency and accuracy of flight training and flight safety.

[0004] Existing technologies lack detailed processing in extracting flight trajectory characteristics from multidimensional data. The assessment of trajectory deviation mostly relies on simple analysis of overall trends, failing to deeply analyze the subtle patterns of trajectory changes, resulting in insufficient grasp of the dynamic characteristics of complex flight trajectories. In the analysis of the correlation between action and trajectory, existing methods mostly focus on the static correlation evaluation of a single variable, while ignoring the extraction of dynamic correlation characteristics and distribution characteristics, limiting the comprehensive analysis capability of key action characteristics and making it difficult to provide a sufficient basis for the prediction of high-frequency deviation actions. In the prediction of key action deviation and task matching, existing technologies mostly remain at a simple backtracking based on historical data, lacking dynamic monitoring and trend analysis of real-time data, resulting in insufficient accuracy and practicality in training task allocation, causing a disconnect between flight training and actual needs, affecting training effectiveness, and posing potential risks to flight safety. The distribution characteristics of high-frequency deviation actions cannot be accurately captured in flight training, resulting in insufficient correction of certain key actions, which in turn affects the scientific nature and safety of flight decisions. Summary of the Invention

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

[0006] In order to achieve the above object, the present invention adopts the following technical solution: A multidimensional data mining and analysis system based on flight simulation includes:

[0007] The flight trajectory characteristic analysis module decomposes the flight trajectory change parameters based on the flight trajectory data recorded by the flight simulation, analyzes the dynamic changes of the heading angle and acceleration, evaluates the trajectory deviation amplitude and variation range, obtains the trajectory deviation characteristic distribution results, and generates the flight trajectory deviation distribution results by comparing the flight attitude angles.

[0008] The motion characteristic correlation analysis module matches the deviation distribution influencing factors based on the flight trajectory deviation distribution results, analyzes the correlation between the control torque change and the control surface deviation, generates a motion deviation correlation matrix, extracts distribution characteristics, analyzes key motion characteristics, and generates motion key characteristic analysis results;

[0009] The key action offset prediction module identifies the distribution range of high-frequency offset actions based on the key action characteristic analysis results, analyzes the trend of action characteristic parameters, obtains the key action offset range, divides the differential categories according to the offset direction and amplitude, performs interval statistics and distribution analysis, and generates key action offset prediction results;

[0010] The training task allocation module analyzes the matching degree between the action characteristic data and the training task stage based on the key action offset prediction results, optimizes the training distribution of the rudder adjustment and control torque, and combines the task stage characteristics with the action correction characteristics to generate a multi-dimensional training allocation plan for flight simulation.

[0011] As a further solution of the present invention, the steps for obtaining the trajectory deviation characteristic distribution result are specifically as follows:

[0012] Based on the flight trajectory data recorded by the flight simulation, the heading angle and acceleration data points are extracted, the data at the time point is analyzed, the heading angle offset and acceleration change are identified, the offset and change parameters of each point in the flight trajectory are calculated, and a list of flight trajectory change parameters is generated;

[0013] Based on the flight trajectory change parameter list, performing trajectory deviation characteristic analysis, focusing on the frequency distribution and variation range of trajectory deviation, measuring the volatility and dispersion of deviation data points, and generating trajectory deviation volatility and dispersion evaluation results;

[0014] The trajectory deviation volatility and dispersion evaluation results are used to perform correlation analysis with the acceleration change data, using the formula:

[0015]

[0016] Identify the influence of acceleration and trajectory deviation and obtain the trajectory deviation characteristic distribution results;

[0017] Among them, C represents the distribution value of trajectory deviation characteristics, a i Represents the acceleration value of the i-th data point, Δθ i Represents the heading angle offset of the i-th data point, and n is the total number of data points.

[0018] As a further solution of the present invention, the steps for obtaining the flight trajectory deviation distribution result are specifically as follows:

[0019] Based on the trajectory deviation characteristic distribution result, the deviation angle data of the position points in the flight trajectory are extracted, the angle changes between adjacent position points are analyzed, the angle changes are sequenced based on the time axis, and the trajectory points are assigned time tags and reordered to obtain the flight trajectory deviation angle sequence;

[0020] Based on the flight trajectory offset angle sequence, the flight attitude angle is selected as a reference parameter, the difference between the offset angle and the attitude angle is calculated, the mapping relationship between the trajectory points and the difference is analyzed, the difference data is integrated, the time axis parameters are supplemented and classified and sorted, and a trajectory angle offset difference matrix is ​​generated;

[0021] Based on the trajectory angle offset difference matrix, the difference outliers and the corresponding position coordinates are extracted, and the trajectory space model is drawn in combination with the trajectory offset angle sequence. The outliers are annotated into the trajectory model, and the position relationship between the offset difference and the trajectory point is matched to generate the flight trajectory deviation distribution result.

[0022] As a further solution of the present invention, the step of obtaining the action offset correlation matrix is ​​specifically as follows:

[0023] Based on the flight trajectory deviation distribution results, analyzing the absolute change rates of the control torque change value and the control surface offset value, screening data points whose change rates exceed a threshold, and obtaining a control torque and control surface offset data set;

[0024] Using the control torque and rudder surface offset data set, the change value is extracted and the difference amplitude is analyzed to identify the correlation factor of the corresponding relationship of the data points. The formula is:

[0025]

[0026] Calculate the correlation score value of each set of data and generate a preliminary correlation score matrix;

[0027] Among them, R represents the correlation score value, α and β are the weight coefficients of control torque and rudder offset respectively, T k and S k represent the control torque and rudder surface offset in the kth data set, respectively, and v is the number of data sets;

[0028] Based on the preliminary correlation score matrix, a data group with a score higher than a preset threshold is selected, and the data group is standardized to generate a motion offset correlation matrix.

[0029] As a further solution of the present invention, the steps for obtaining the key characteristics analysis results of the action are specifically as follows:

[0030] Based on the motion offset correlation matrix, the motion offset values ​​are extracted and matched with the corresponding correlation parameters, the cumulative distribution of each motion offset value is analyzed, the cumulative distribution values ​​and the correlation parameters are classified and integrated, and the distribution intervals of the high-frequency correlation parameters and the motion offset are recorded to generate a motion distribution characteristic dataset;

[0031] Based on the action distribution characteristic dataset, the offset intervals of the associated parameter frequencies in the cumulative distribution are screened, and the action position data corresponding to the offset intervals are extracted. The offset characteristics of each group of actions are sorted by interval size based on the action position and offset characteristics, and the characteristic values ​​of the offset weights are marked to generate a key action characteristic grouping table;

[0032] Based on the key action characteristic grouping table, the distribution of weight characteristics in the action sequence is analyzed, the mapping relationship of the offset characteristic value is adjusted according to the position of the action sequence, and the mapped distribution characteristics are integrated to generate the action key characteristic analysis result.

[0033] As a further solution of the present invention, the step of obtaining the offset range of the key action is specifically as follows:

[0034] Based on the analysis results of the key characteristics of the action, the initial data set of the offset action distribution range is called, the key characteristic parameters of each action are analyzed, the trend range of parameter changes is analyzed, the peak offset point in the action characteristics is determined, and preliminary analysis data of the action characteristic offset is obtained;

[0035] Based on the preliminary analysis data of the motion characteristic offset, the distribution density of the motion offset points is calculated using the formula:

[0036]

[0037] Filter the set of offset points whose distribution density exceeds a preset threshold to obtain the distribution range of high-frequency offset points;

[0038] Where D is the distribution density value, P j is the weight of the offset point, W j is the feature weight of the action offset point, is the mean of the offset point weights, and m is the total number of offset points;

[0039] Based on the distribution range of the high-frequency offset points and superimposed with the motion characteristic trend range, the variation range of the characteristic parameters is analyzed, the motion offset influencing factor is introduced, and the key motion offset range is obtained.

[0040] As a further solution of the present invention, the steps for obtaining the key action offset prediction result are specifically as follows:

[0041] Based on the key action offset range, extract the values ​​of the action offset direction and amplitude, classify and label each action data according to the offset direction, assign the offset amplitude value to a continuous interval range, count the number of actions in each category, and generate a key action offset classification data set;

[0042] Based on the key action offset classification dataset, the number of actions within the differentiated amplitude range is counted for each group of data in the offset direction classification, and integrated classification is performed by offset direction. The quantitative differences of the differentiated offset directions within the amplitude range are compared to generate a key action offset distribution model.

[0043] Based on the key action offset distribution model, the interval data of the offset direction and amplitude distribution ratio are extracted, the action data are sorted in time series according to the interval distribution trend, the change range of the action offset direction and the amplitude interval in the future time period are predicted, and the key action offset prediction results are generated by combining the distribution trend and the predicted data.

[0044] As a further solution of the present invention, the steps for obtaining the multi-dimensional training allocation scheme for flight simulation are specifically as follows:

[0045] Based on the key action offset prediction results, a key action characteristic parameter set is extracted, including an action execution duration parameter, an action offset amplitude parameter, and an action execution accuracy parameter. By analyzing the characteristic weights of the matching parameters with the task stage, an initial set of key action characteristic parameters matching the task stage is generated;

[0046] Based on the initial set of key action characteristic parameters and task stage matching, the characteristic matching degree distribution value is calculated using the formula:

[0047]

[0048] Optimize the influence of the matching value on the rudder adjustment distribution and generate the optimized matching characteristic distribution matrix;

[0049] Among them, M c represents the distribution value of feature matching, T a Indicates the duration of action execution, D a Indicates the movement offset amplitude, P a Indicates the action execution accuracy, Q1 is the action offset weight parameter, and Q2 is the action accuracy weight parameter;

[0050] The optimized matching characteristic distribution matrix is ​​called, and the rationality of optimizing the control surface adjustment and the control torque distribution is analyzed and combined with the control torque distribution and the mission phase correction characteristics. By screening the optimal distribution combination, a multi-dimensional training allocation plan for flight simulation is generated.

[0051] Compared with the prior art, the advantages and positive effects of the present invention are:

[0052] In the present invention, by decomposing the changing parameters of the flight trajectory, deeply analyzing the dynamic changes of the heading angle and acceleration, and extracting the characteristic distribution results of the trajectory deviation, the dynamic evaluation of the trajectory deviation is made more accurate, and the ability to capture the law of flight trajectory changes is significantly improved. By further matching the influencing factors of the deviation distribution, the correlation between the control torque change and the rudder surface deviation is analyzed, the analytical depth of the action characteristics during flight is enhanced, the key correlation between the action and the trajectory is quantified, and the processing method of the action characteristic analysis is refined, so that the extraction of the action characteristic distribution and the dynamic evaluation of the key characteristics are more comprehensive, laying the foundation for accurately predicting the distribution range of high-frequency deviation actions. In the prediction of high-frequency motion offsets, a comprehensive analysis of the changing trends of motion characteristic parameters is conducted to further refine the offset range of key motions. Through interval statistics and distribution analysis, the differentiated categories of offset directions and amplitudes are clarified, making the dynamic capture of high-frequency offsets more practical and accurate. Combined with the matching analysis of the training mission stage, the distribution of rudder adjustment and control torque is optimized, making the training distribution of flight simulation more in line with actual needs, and realizing full-chain coverage of flight data from pattern discovery to task optimization, which not only improves the accuracy of real-time decision-making, but also enhances the scientific nature of training task allocation, thereby effectively improving flight safety and training efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 is a system flow chart of the present invention;

[0054] Figure 2 This is a flow chart of the trajectory deviation characteristic distribution results in the present invention;

[0055] Figure 3 This is a flow chart of the flight trajectory deviation distribution results in the present invention;

[0056] Figure 4 This is a flow chart of the action offset correlation matrix in the present invention;

[0057] Figure 5 This is a flow chart of the analysis results of the key characteristics of the action in the present invention;

[0058] Figure 6 This is a flow chart of the offset range of key actions in the present invention;

[0059] Figure 7This is a flow chart of the key action offset prediction results in the present invention;

[0060] Figure 8 The figure is a flow chart of the multi-dimensional training allocation scheme for flight simulation in the present invention. DETAILED DESCRIPTION

[0061] 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.

[0062] 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.

[0063] See also Figure 1 , a multidimensional data mining and analysis system based on flight simulation includes:

[0064] The flight trajectory characteristic analysis module decomposes the flight trajectory change parameters based on the flight trajectory data recorded by the flight simulation, analyzes the dynamic changes of the heading angle and acceleration, evaluates the trajectory deviation amplitude and variation range, obtains the trajectory deviation characteristic distribution results, and generates the flight trajectory deviation distribution results by comparing the flight attitude angles.

[0065] The motion characteristic correlation analysis module matches the influencing factors of the deviation distribution based on the flight trajectory deviation distribution results, analyzes the correlation between the control torque change and the rudder surface offset, generates the motion offset correlation matrix, extracts the distribution characteristics, analyzes the key motion characteristics, and generates the motion key characteristic analysis results;

[0066] The key action offset prediction module identifies the distribution range of high-frequency offset actions based on the analysis results of key action characteristics, analyzes the changing trend of action characteristic parameters, obtains the key action offset range, divides the differential categories according to the offset direction and amplitude, performs interval statistics and distribution analysis, and generates key action offset prediction results;

[0067] The training task allocation module analyzes the matching degree between the action characteristic data and the training task phase based on the key action offset prediction results, optimizes the training distribution of rudder adjustment and control torque, and combines the task phase characteristics with the action correction characteristics to generate a multi-dimensional training allocation plan for flight simulation.

[0068] The trajectory offset characteristic distribution results include offset amplitude distribution, change range distribution, and dynamic characteristic distribution. The flight trajectory deviation distribution results include heading angle deviation distribution, acceleration deviation distribution, and attitude angle deviation distribution. The action offset correlation matrix includes control torque change matrix, rudder offset correlation matrix, and action distribution characteristic matrix. The action key characteristic analysis results include key action distribution characteristics, action characteristic parameter changes, and key characteristic trend analysis. The key action offset range includes high-frequency offset action range, offset direction range, and offset amplitude range. The key action offset prediction results include offset interval distribution, action distribution statistics, and differentiated category classification. The multi-dimensional training allocation plan for flight simulation includes task stage matching distribution, rudder adjustment optimization distribution, and control torque distribution optimization.

[0069] See also Figure 2 ,The specific steps for obtaining the trajectory deviation characteristic distribution results are:

[0070] Based on the flight trajectory data recorded by the flight simulation, the heading angle and acceleration data points are extracted, the data at the time point is analyzed, the heading angle offset and acceleration change are identified, the offset and change parameters of each point in the flight trajectory are calculated, and a list of flight trajectory change parameters is generated;

[0071] Heading angle and acceleration data points are extracted from the flight simulation data. By parsing the raw data in the flight trajectory records, the corresponding heading angle and acceleration change parameters in the time series are extracted. The heading angle data is differentially calculated to obtain the offset between each time point. The angular amplitude change of the heading angle change value is used to calculate a list of each heading offset value in the time series. The acceleration data is integrated to accumulate the discrete acceleration values ​​in each time period to calculate a list of velocity changes in the corresponding time period. Combined with the heading angle offset value list, the two are matched and normalized by time point to eliminate interference caused by uneven time intervals or sampling frequency errors. The obtained normalized acceleration changes and heading angle offset values ​​are combined and stored. At the same time, the relative change rate of the offset direction and acceleration in each set of matched data is calculated to reflect the dynamic adjustment characteristics of the direction and speed in the flight trajectory. Finally, a list of flight trajectory change parameters is generated.

[0072] Based on the flight trajectory change parameter list, perform trajectory deviation characteristic analysis, focus on the frequency distribution and variation range of trajectory deviation, measure the volatility and dispersion of deviation data points, and generate trajectory deviation volatility and dispersion evaluation results;

[0073] The distribution characteristics of the heading angle offset and acceleration change data are analyzed. The offset amplitude values ​​are divided into intervals. The data points are divided into multiple amplitude intervals according to the offset size. The frequency distribution characteristics of each interval are statistically analyzed. The standard deviation and coefficient of variation of the offset amplitude are calculated. The volatility and dispersion of the offset amplitude in each interval are measured. By comparing the offset amplitude change trends in adjacent intervals, intervals with high volatility and high dispersion are screened. The acceleration change in each interval is further analyzed, and the maximum, minimum, and average values ​​of the acceleration data are calculated. The joint distribution characteristics of acceleration and offset are fitted and analyzed using the data in the interval to generate a joint distribution diagram of offset amplitude and acceleration. The calculation results are combined with the joint distribution diagram to organize the calculation results into trajectory offset volatility and dispersion assessment results.

[0074] The trajectory deviation volatility and dispersion evaluation results are used to perform correlation analysis with the acceleration change data, using the formula:

[0075]

[0076] Identify the influence of acceleration and trajectory deviation and obtain the trajectory deviation characteristic distribution results;

[0077] Among them, C represents the distribution value of trajectory deviation characteristics, a i Represents the acceleration value of the i-th data point, Δθ i represents the heading angle offset of the i-th data point, and n is the total number of data points;

[0078] The benefit of this formula is that by combining the product of the comprehensive acceleration and the heading angle offset with a normalized sum-of-squares calculation method, it reduces the impact of outliers on the overall result and ensures the stability and reliability of the offset characteristic calculation.

[0079] The acceleration data extracted from the flight trajectory record are 0.8, 1.2, 1.0, 1.5, 1.3 and the heading angle offset data are 0.05, 0.04, 0.03, 0.06, 0.05]. The acceleration data is calculated by the 6-DOF motion equation and its unit is m / s 2 ,The data is filtered to remove the interference value, and the heading angle offset data is calculated by the 6-degree-of-freedom motion equation. The unit is radian and the sampling time interval is 1 second;

[0080] The numerator part is calculated as:

[0081] The calculation of the denominator is:

[0082]

[0083] The final calculation is

[0084] The results show that the comprehensive offset characteristic distribution value is 0.1068, which represents the degree of dynamic coupling between acceleration and heading angle offset, and can directly reflect the characteristic results of the comprehensive offset trend in the trajectory offset characteristic distribution.

[0085] See also Figure 3 ,The specific steps for obtaining the flight trajectory deviation distribution results are:

[0086] Based on the trajectory offset characteristic distribution results, the offset angle data of the position points in the flight trajectory are extracted, the angle changes between adjacent position points are analyzed, the angle changes are sequenced based on the time axis, and the trajectory points are assigned time tags and reordered to obtain the flight trajectory offset angle sequence;

[0087] By dividing the flight path into multiple sampling points with equal time intervals, the offset angle of each sampling point is analyzed separately, and the offset change between adjacent position points is recorded. Based on the absolute value of the angle change, the angle change sequence on the time axis is constructed in combination with the time parameter. The time mark of each position point is assigned a unique value according to the order of position change, ensuring that all data can be strictly sorted according to the time dimension to avoid data overlap or loss. All offset angle data are rearranged according to the time axis, and the rate of change between two consecutive time points is calculated. The rate of change is obtained by dividing the angle difference by the time difference, so as to ensure that the trend of the offset angle changing over time can be captured. Through this processing, the flight trajectory offset angle is serialized and sorted, and a directional mark is added in the analysis to distinguish different offset directions. The flight trajectory offset angle sequence is constructed by combining each segment of serialized data and output in the form of a list to complete the structured conversion of the flight trajectory offset data.

[0088] Based on the flight trajectory offset angle sequence, the flight attitude angle is selected as the reference parameter, the difference between the offset angle and the attitude angle is calculated, the mapping relationship between the trajectory points and the difference is analyzed, the difference data is integrated, the time axis parameters are supplemented and classified and sorted, and the trajectory angle offset difference matrix is ​​generated;

[0089] The attitude angle data of the trajectory points are extracted and linear interpolation processing is performed on them to ensure the continuity and accuracy of the attitude angle in the time dimension. The difference between the offset angle and the attitude angle is calculated point by point, and the two sets of data are matched one by one. A new angle difference sequence is generated according to the time mark, and the difference and its corresponding trajectory point position data are integrated and stored in matrix form. The mapping relationship between the trajectory points and the differences is deeply analyzed. The difference threshold range is set based on the data distribution characteristics, and the difference points exceeding the range are marked. To further supplement the time dimension parameters of the angle difference data, the time mark is added to the difference matrix, and the trajectory points are reordered according to the size of the difference, thereby generating a trajectory angle offset difference matrix. In this way, the fusion processing of the angle offset characteristics and the flight attitude characteristics is completed, which can effectively reflect the differences in trajectory offset and flight attitude changes in different time periods, and form a multi-dimensional classification and sorting result among the trajectory points, time, and difference.

[0090] Based on the trajectory angle offset difference matrix, the outlier points and their corresponding position coordinates are extracted. The trajectory space model is drawn in combination with the trajectory offset angle sequence. The outliers are annotated into the trajectory model, and the relationship between the offset difference and the trajectory point position is matched to generate the flight trajectory deviation distribution result.

[0091] The difference anomalies in the angle deviation that exceed the threshold range are extracted, and the corresponding trajectory point position coordinates are extracted. Combined with the changing trend of the trajectory offset angle sequence, the trajectory offset angle of the anomaly point is spatially fitted using the interpolation method, and a trajectory space model containing the offset angle and position coordinates is constructed. In the model, all trajectory points are visualized according to their position coordinates and offset angle distribution to ensure that the model can accurately display the overall characteristics of the angle offset. For the marked anomaly points, they are embedded in the model, and position coordinate marks and offset angle difference range information are added to each anomaly point to distinguish the relationship between the anomaly point and the trajectory point. The distribution density between all offset differences and trajectory point positions is calculated, and the offset characteristics of the flight trajectory in space are described by density changes. The specific mapping relationship between the offset difference and the trajectory point position is matched according to the model, and the flight trajectory deviation distribution result is output to intuitively reflect the offset characteristics and risk distribution area of ​​the flight trajectory in space.

[0092] See also Figure 4 , the steps for obtaining the action offset correlation matrix are as follows:

[0093] Based on the flight trajectory deviation distribution results, the absolute change rates of the control torque change value and the rudder surface offset value are analyzed, and the data points whose change rates exceed the threshold are filtered to obtain the control torque and rudder surface offset data sets;

[0094] By calling the control torque change value and rudder offset value corresponding to each time node in the flight trajectory record file, two groups of data are extracted respectively and a data set is constructed. The absolute change rate of the control torque change value and the rudder offset value is calculated. The specific formula of the change rate is extracted and the absolute change rate value of each group of data is calculated point by point for the data group. Based on the calculation results, data points with a change rate greater than the specified threshold are gradually filtered out. The specific correspondence between the control torque change value and the rudder offset value is re-matched from the valid data points. Missing values ​​or abnormal points in the data are eliminated or replaced to avoid the influence of invalid data on subsequent calculations. By sorting and classifying the matching relationships in the remaining valid data points, it is ensured that each group of matching data has a clear calculation basis and validity. Finally, the control torque and rudder offset data group is output.

[0095] Using the control torque and rudder offset data set, we extract the change value and analyze the difference amplitude, identify the correlation factor of the corresponding relationship between the data points, and use the formula:

[0096]

[0097] Calculate the correlation score value of each set of data and generate a preliminary correlation score matrix;

[0098] Among them, R represents the correlation score value, α and β are the weight coefficients of control torque and rudder offset respectively, T k and S k represent the control torque and rudder surface offset in the kth data set, respectively, and v is the number of data sets;

[0099] The formula is beneficial in that it introduces weight parameters to weight the control torque and rudder offset data, which can more carefully reflect the proportion of their influence on the correlation score. At the same time, by processing the numerator and denominator, it ensures that the final score value can adapt to the data distribution of different sample sizes.

[0100] Calculate the absolute value of some data: Assume that the data set contains 5 groups of data, T1 = 3.2, T2 = 5.1, T3 = 2.8, T4 = 4.6, T5 = 3.9, S1 = 1.7, S2 = 2.5, S3 = 2.3, S4 = 3.1, S5 = 2.8, and calculate the weighted absolute value of each group of data respectively;

[0101] Set the weight parameters: α = 0.6, β = 0.4, corresponding to the control torque and rudder offset weights respectively, and the importance of the two parameters is reflected through weight distribution;

[0102] Enter the formula to calculate:

[0103] Compute the inner sum:

[0104] Final result: R=3.344;

[0105] The results show that the average correlation score between the control torque and the rudder surface offset data is 3.344, and the score matrix can be used to further analyze the comprehensive impact of the two parameters on the overall deviation.

[0106] Based on the preliminary correlation score matrix, data groups with scores higher than a preset threshold are selected, and the data groups are normalized to generate an action offset correlation matrix;

[0107] By calling the specific numerical values ​​of each group of correlation scores in the preliminary scoring matrix, the scoring matrix is ​​compared one by one with the preset threshold, and the qualified data groups are screened according to the rule that the score value is higher than the preset threshold. The qualified matching data groups are called and the standardized processing results of each group of data are calculated. The score value range is processed to unify all score values ​​into the standard range to prevent deviations in subsequent calculations due to differences in data ranges. By further grouping and integrating the normalized score values, the data is reorganized into a standardized matrix form and the action offset correlation matrix is ​​output.

[0108] See also Figure 5 ,The steps for obtaining the results of the key characteristics of the action are as follows:

[0109] Based on the motion offset correlation matrix, the motion offset values ​​are extracted and matched with the corresponding correlation parameters. The cumulative distribution of each motion offset value is analyzed, the cumulative distribution values ​​and the correlation parameters are classified and integrated, and the distribution intervals of high-frequency correlation parameters and motion offsets are recorded to generate a motion distribution characteristic dataset.

[0110] Each action offset value is compared one by one according to the category of the associated parameters to form a mapping relationship. The cumulative distribution of the mapped action offset values ​​is calculated, and the increasing cumulative results of the offset values ​​are used as distribution indicators to generate a cumulative distribution sequence. The cumulative distribution values ​​are classified and integrated with the corresponding associated parameters. The cumulative distribution range and frequency density under different associated parameter categories are calculated to determine the distribution characteristics of high-frequency associated parameters, and the distribution range of high-frequency parameters and corresponding action offset values ​​is recorded. For each offset value within the distribution range, the action time series is used to reorder them to ensure that the interval mapping relationship between the offset value and the associated parameter is accurately expressed. Based on the distribution range of the offset value, the offset cumulative value of each group of high-frequency associated parameters is extracted, and the action distribution characteristic data set is output to further characterize the distribution law and characteristic trend of the action offset.

[0111] Based on the action distribution characteristic dataset, the offset intervals of the associated parameter frequencies in the cumulative distribution are screened, and the action position data corresponding to the offset intervals are extracted. Based on the action position and offset characteristics, the offset characteristics of each group of actions are sorted by interval size, and the characteristic values ​​of the offset weights are marked to generate a key action characteristic grouping table;

[0112] The associated parameters whose cumulative frequency exceeds a specific interval are marked as high-offset characteristic parameters, and the action position data corresponding to the high-frequency offset interval are further extracted. By analyzing the action position within the offset interval, the offset range and frequency characteristics of each action are summarized. Combined with the distribution interval information generated in the distribution characteristic data set, the offset characteristics of the actions are sorted. The interval size is used as the sorting standard, and the action offset is output in descending order. For the actions within the high-frequency offset interval, the offset characteristic value is calculated, and the corresponding offset weight value is generated and marked in the data table. The weight value is matched and integrated with the interval range to form a group with action position, offset characteristic and weight value. According to the size of the weight characteristic value, the key actions are marked as characteristic-significant actions. At the same time, the distribution range of high-offset actions and ordinary actions is clearly distinguished, and a key action characteristic grouping table is generated to illustrate the offset weight of each group of actions in different position intervals and its impact on the overall distribution.

[0113] Based on the key action characteristic grouping table, the distribution of weight characteristics in the action sequence is analyzed, the mapping relationship of the offset characteristic value is adjusted according to the position of the action sequence, and the mapped distribution characteristics are integrated to generate the key characteristic analysis results of the action;

[0114] By matching the position of the action sequence with the offset weight characteristics of the key actions, an action offset characteristic distribution map is constructed. In the distribution map, the mapping relationship of the offset characteristic values ​​is readjusted according to the weight characteristic values ​​of the actions, so that the offset characteristics of high-weight actions can more accurately reflect their impact on the action sequence. During the adjustment process, the characteristics of each group of key actions are mapped to their corresponding timeline positions to form a dynamic change curve of the offset characteristic values. Combined with the adjusted distribution characteristic values, each group of actions in the action sequence is reclassified according to the characteristic distribution to ensure that the distribution map can clearly reflect the offset characteristics and weight distribution characteristics of the actions. Finally, the adjusted distribution characteristics are integrated to present the distribution of key actions in the sequence in the form of a visual chart, generating the action key characteristic analysis results to describe the spatial distribution of the offset characteristic values ​​in the action sequence and their dynamic influence relationship.

[0115] See also Figure 6 ,The specific steps for obtaining the offset range of key actions are:

[0116] Based on the analysis results of the key characteristics of the action, the initial data set of the offset action distribution range is called, the key characteristic parameters of each action are analyzed, the trend range of parameter changes is analyzed, the peak offset point in the action characteristics is determined, and the preliminary analysis data of the action characteristic offset is obtained;

[0117] First, time series information is extracted from the action sequence to obtain the continuous amplitude change data of the action at different time points. At the same time, the speed change rate of the action is calculated. The speed change rate can be calculated by dividing the displacement difference of adjacent time points by the time interval. The amplitude change range of the action is further extracted in combination with the amplitude data. Finally, the maximum and minimum amplitude values ​​of each action and its corresponding time points and frequency characteristics are counted. By comparing the relative differences between the parameters and the mean of the characteristic range and the upper and lower thresholds, the peak change point of each action is calculated and its change curve is extracted. Key characteristic parameters are selected based on the peak characteristics. By judging whether the characteristic peak change point meets the key offset characteristic conditions of the parameter, the conditions include the amplitude peak being several times greater than the mean, the absolute value of the speed direction change exceeding a certain amplitude threshold, etc., the set of peak change points that meet the conditions is taken as the offset point in the action characteristics to obtain preliminary analysis data of the action characteristic offset.

[0118] Based on the preliminary analysis data of motion characteristic offset, the distribution density of motion offset points is calculated using the formula:

[0119]

[0120] Filter the set of offset points whose distribution density exceeds a preset threshold to obtain the distribution range of high-frequency offset points;

[0121] Where D is the distribution density value, P j is the weight of the offset point, W j is the feature weight of the action offset point, is the mean of the offset point weights, and m is the total number of offset points;

[0122] The formula is beneficial in that it combines weight distribution and standard deviation to calculate distribution density, effectively screening high-frequency excursion points and accurately quantifying their distribution density, thereby further improving the recognition accuracy of high-frequency excursion actions and the ability to capture data characteristics.

[0123] P j Indicates the weight of the offset point. This value is calculated by comprehensively calculating the parameters of the three dimensions in the offset characteristics. The calculation method is P j =a1·A j +a2·F j +a3·S j , where A j is the amplitude characteristic value, F j is the frequency characteristic value, Sj is the velocity characteristic value. The setting basis of weight coefficients a1, a2, and a3 is the influence of the three on the offset characteristics in the actual data. Specifically, the weight ratio is determined by analyzing the significance index of the offset point of the data set. The weight value satisfies a1+a2+a3=1, W j It represents the feature weight of the action offset point, which is calculated by normalizing the frequency distribution. The formula is: is the mean of the offset point weights, and the formula is

[0124] Substitute the parameter values ​​and set m=3. The characteristic values ​​of the three groups of offset points are:

[0125] The first group A1=5, F1=3, S1=4;

[0126] The second group has A2=6, F2=4, S2=3;

[0127] The third group A3=7, F3=5, S3=2;

[0128] Weight coefficients a1 = 0.4, a2 = 0.3, a3 = 0.3:

[0129] Calculate the weight P of each offset point j :

[0130] P1=0.4·5+0.3·3+0.3·4=4.3;

[0131] P2=0.4·6+0.3·4+0.3·3=4.9;

[0132] P3=0.4·7+0.3·5+0.3·2=5.5;

[0133] Calculate the offset point feature weight W j :

[0134] W1=3 / (3+4+5)=0.25;

[0135] W2=4 / (3+4+5)=0.33;

[0136] W3=5 / (3+4+5)=0.42;

[0137] Calculate the mean

[0138] Calculate the distribution density D:

[0139]

[0140] The result shows that the distribution density value is 5.89, which means that the distribution density of the offset points in the current data set is relatively high, and the high-frequency offset area can be accurately identified and the distribution range of the high-frequency offset points can be generated.

[0141] Based on the distribution range of high-frequency offset points and superimposed with the trend range of motion characteristics, the variation range of characteristic parameters is analyzed, the motion offset influencing factors are introduced, and the key motion offset range is obtained;

[0142] Through the superposition process, the action characteristic parameters within the trend range are normalized. The normalization process includes standardizing the parameters of the three dimensions of amplitude characteristic, speed characteristic and frequency characteristic respectively. The maximum and minimum values ​​of each parameter are normalized to the standard range through the transformation of the logarithmic function. The parameters within the standard range are mapped to the unit interval for standardization. The normalization operation is performed, and the normalization result is used as the benchmark parameter for superposition to calculate the change interval of each action characteristic trend range. Further, by setting the judgment standard of whether the change interval exceeds the offset influence factor, the superimposed parameter set is screened, and finally the key offset influence factor set in the parameter change interval is obtained to generate the key action offset range.

[0143] See also Figure 7 ,The steps to obtain the key action offset prediction results are as follows:

[0144] Based on the key action offset range, the values ​​of the action offset direction and amplitude are extracted, each action data is classified and labeled according to the offset direction, the offset amplitude value is assigned to a continuous interval range, the number of actions in each category is counted, and a key action offset classification dataset is generated;

[0145] The directional data for each motion offset is defined as the angle of deviation from the trajectory reference direction, with positive values ​​representing clockwise offsets and negative values ​​representing counterclockwise offsets. The offset directional data for each motion group is categorized and labeled, and the motion data is divided into multiple classification groups based on directionality, such as "clockwise offset group" and "counterclockwise offset group." The offset amplitude data for each motion is divided into continuous intervals, with amplitude values ​​assigned according to interval ranges. The size of each interval is set to a fixed amplitude difference to ensure the continuity and comparability of the amplitude of all motion offset data. Within each classification group, motions within the same amplitude interval are counted, and the number of motions within different amplitude intervals within each directional classification is recorded. By integrating the motion statistics for all classification groups, a key motion offset classification dataset is generated, which includes offset direction, amplitude interval, and number of motions. This dataset can intuitively reflect the distribution patterns of motion offsets in terms of direction and amplitude, providing a data foundation for subsequent offset distribution analysis.

[0146] Based on the key action offset classification dataset, the number of actions within the differential amplitude range is counted for each group of data in the offset direction classification, and then integrated and classified by offset direction. The quantitative differences of the differential offset directions within the amplitude range are compared to generate the key action offset distribution model.

[0147] The number of movements in the amplitude intervals in each direction classification is accurately compared. During the statistical process, the cumulative number of movements in each amplitude interval in each offset direction is first calculated, and then the number of movements in the same amplitude interval in different direction classifications is horizontally compared. The interval ranges with significant differences are marked, and the amplitude intervals are integrated with the offset directions to generate a direction-amplitude distribution diagram that reflects the difference in the number of movements. By analyzing this distribution diagram, the concentration and sparseness of the number of movements in each amplitude range in the differentiated offset directions can be clearly identified. The distribution relationship between each group of offset directions and amplitude ranges is deeply integrated, and finally a key movement offset distribution model is generated. This model contains a complete mapping relationship between direction, amplitude and number of movements, and can reflect the differences and similarities in movement distribution under different directions and amplitudes, providing an important basis for subsequent trend analysis.

[0148] Based on the key action offset distribution model, we extract interval data of offset direction and amplitude distribution ratio, sort the action data in time series according to the interval distribution trend, predict the change range of action offset direction and amplitude interval in the future time period, and generate key action offset prediction results by combining the distribution trend and predicted data.

[0149] The number of actions in each offset direction and amplitude interval is dynamically sorted through the time axis, and the action data is continuously processed according to the time series to ensure that the distribution ratio can reflect the law of change over time. During the processing, the distribution trend of the offset direction is fitted, and combined with the proportional change of the amplitude interval, the change range of the action offset direction and the dynamic distribution of the amplitude interval in the future time period are predicted. By constructing a time series trend graph of the offset direction and amplitude, the trend range of each offset direction and amplitude in the future time period is clarified. Combined with the predicted data, the distribution density of the action offset in the future time period is estimated, and the range of the high-frequency interval and the low-frequency interval is output. The distribution trend is integrated with the predicted data to generate the key action offset prediction result. The result intuitively presents the direction change trend and amplitude distribution range of the action offset in the future time period, providing strong support for flight trajectory adjustment and abnormal action warning.

[0150] See also Figure 8 ,The steps for obtaining the multi-dimensional training allocation scheme for ,flight simulation are as follows:

[0151] Based on the key action offset prediction results, the key action characteristic parameter set is extracted, including the action execution duration parameter, action offset amplitude parameter, and action execution accuracy parameter. By analyzing the characteristic weights of the matching parameters with the task stage, the initial set of key action characteristic parameters matching the task stage is generated;

[0152] First, the original data of action offset prediction is analyzed and divided into multiple time intervals corresponding to the task stage. The changing trend of the action execution time in each interval is analyzed to extract the action execution time parameters. Then, the action offset amplitude is normalized. Combined with the standard deviation interval of the maximum and minimum amplitude values, the part with significant offset fluctuation is selected, the abnormal data is eliminated and the final offset amplitude is calculated. Then, through the measurement standardization of execution accuracy, the accuracy measurement data is converted into characteristic parameter values ​​that conform to the model. The offset amplitude, execution time and execution accuracy are weighted and calculated to obtain the preliminary matching relationship between the task stage and the action characteristics. This matching relationship is expressed in matrix form for subsequent further optimization calculations, and finally an initial set of key action characteristic parameters and task stage matching is generated.

[0153] Based on the initial set of key action characteristic parameters and task stage matching, the characteristic matching degree distribution value is calculated using the formula:

[0154]

[0155] Optimize the influence of the matching value on the rudder adjustment distribution and generate the optimized matching characteristic distribution matrix;

[0156] Among them, M c represents the distribution value of feature matching, T a Indicates the duration of action execution, D a Indicates the movement offset amplitude, P a Indicates the action execution accuracy, Q1 is the action offset weight parameter, and Q2 is the action accuracy weight parameter;

[0157] The formula is beneficial in that it improves the accuracy of matching calculations by introducing action precision parameters and adjusting weights. It also ensures a balanced distribution by combining action execution duration and the sum of squared offsets. The weights can be dynamically adjusted based on data characteristics, enhancing calculation flexibility.

[0158] Action execution time parameter T a =5.4, obtained by measuring the actual operation time in the flight simulation task point by point and calculating the average value;

[0159] Motion offset amplitude parameter D a =3.2, obtained by calculating the difference of the action position offset in the simulation data and taking the mean of its fluctuation range;

[0160] Action execution accuracy parameter P a =0.85, obtained by standardizing the action execution data and calculating the average of the deviation ratios for each action execution;

[0161] The offset weight parameter Q1=1.2 is set according to the weight distribution curve after analyzing the influence of the historical action offset amplitude at different task stages;

[0162] The accuracy weight parameter Q2=0.8 is obtained by analyzing the historical data distribution relationship of accuracy in task feature matching and normalizing it;

[0163] Calculate the molecular part:

[0164] T a ·P a =5.4·0.85=4.59, D a ·Q1=3.2·1.2=3.84, |4.59-3.84|=0.75;

[0165] Calculate the denominator:

[0166]

[0167] Calculate the characteristic matching distribution value:

[0168] The results show that the characteristic matching degree distribution value M c =0.1186 can quantify the weight influence in the optimized matching characteristic distribution and serve as a reference for the subsequent control surface adjustment distribution.

[0169] The optimized matching characteristic distribution matrix is ​​called up, and combined with the control torque distribution and mission phase correction characteristics, the rationality of optimizing the control surface adjustment and control torque distribution is analyzed. By screening the optimal distribution combination, a multi-dimensional training allocation plan for flight simulation is generated;

[0170] First, the parameter subset most relevant to the current mission phase objectives is extracted from the optimized characteristic distribution matrix. The matrix then filters the characteristic weights corresponding to each parameter combination row by row, and sets characteristic thresholds to eliminate non-compliant subsets. The filtered subset is then cross-mapped with the matrix in the control torque distribution model. Through linear adjustments to the control torque distribution matrix, the corrective effects of each parameter on rudder adjustment are calculated. The filtered characteristic weights are then dynamically modified sequentially, gradually updating the weight values ​​and matrix content for each data set. Finally, the results for the matching characteristic combinations in the matrix are accumulated and categorized based on the corrected characteristic weights for the mission phase, generating a multidimensional training allocation plan for flight simulation. This multidimensional training allocation plan primarily utilizes data collected from flight simulations, using multidimensional data mining techniques to optimize flight training tasks. Specifically, the plan relies on in-depth analysis of flight trajectories, assessment of the correlation between maneuvers and trajectories, and prediction of deviations based on maneuver characteristics. This complex analysis and prediction allows for more precise training task allocation, improving the efficiency and safety of flight training while also enabling pilots to conduct more targeted training for specific flight maneuvers and trajectory deviations. In practice, multi-dimensional training allocation plans specifically include adjustments to training subjects. For example, based on flight data analysis, the allocation of rudder adjustments and control torque training can be adjusted to ensure that each training session targets the pilot's weaknesses and upcoming flight challenges. This system not only improves the adaptability of individual training but also enhances overall training quality, making training more relevant to the various situations likely to be encountered in actual flight.

[0171] 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 multidimensional data mining and analysis system based on flight simulation, characterized in that: The system comprises: The flight trajectory characteristic analysis module decomposes the flight trajectory change parameters based on the flight trajectory data recorded by the flight simulation, analyzes the dynamic changes of the heading angle and acceleration, evaluates the trajectory deviation amplitude and variation range, obtains the trajectory deviation characteristic distribution results, and generates the flight trajectory deviation distribution results by comparing the flight attitude angles. The steps for obtaining the trajectory deviation characteristic distribution result are specifically as follows: Based on the flight trajectory data recorded by the flight simulation, the heading angle and acceleration data points are extracted, the data at the time point is analyzed, the heading angle offset and acceleration change are identified, the offset and change parameters of each point in the flight trajectory are calculated, and a list of flight trajectory change parameters is generated; Based on the flight trajectory change parameter list, performing trajectory deviation characteristic analysis, focusing on the frequency distribution and variation range of trajectory deviation, measuring the volatility and dispersion of deviation data points, and generating trajectory deviation volatility and dispersion evaluation results; The trajectory deviation volatility and dispersion evaluation results are used to perform correlation analysis with the acceleration change data, using the formula: Identify the influence of acceleration and trajectory deviation and obtain the trajectory deviation characteristic distribution results; Among them, C represents the distribution value of trajectory deviation characteristics, a i Represents the acceleration value of the i-th data point, Δθ i represents the heading angle offset of the i-th data point, and n is the total number of data points; The motion characteristic correlation analysis module matches the deviation distribution influencing factors based on the flight trajectory deviation distribution results, analyzes the correlation between the control torque change and the control surface deviation, generates a motion deviation correlation matrix, extracts distribution characteristics, analyzes key motion characteristics, and generates motion key characteristic analysis results; The steps for obtaining the action offset correlation matrix are specifically as follows: Based on the flight trajectory deviation distribution results, analyzing the absolute change rates of the control torque change value and the control surface offset value, screening data points whose change rates exceed a threshold, and obtaining a control torque and control surface offset data set; Using the control torque and rudder surface offset data set, the change value is extracted and the difference amplitude is analyzed to identify the correlation factor of the corresponding relationship of the data points. The formula is: Calculate the correlation score value of each set of data and generate a preliminary correlation score matrix; Among them, R represents the correlation score value, α and β are the weight coefficients of control torque and rudder offset respectively, T k and S k represent the control torque and rudder surface offset in the kth data set, respectively, and v is the number of data sets; Based on the preliminary correlation score matrix, selecting a data group with a score higher than a preset threshold, performing normalization on the data group, and generating an action offset correlation matrix; The key action offset prediction module identifies the distribution range of high-frequency offset actions based on the key action characteristic analysis results, analyzes the trend of action characteristic parameters, obtains the key action offset range, divides the differential categories according to the offset direction and amplitude, performs interval statistics and distribution analysis, and generates key action offset prediction results; The training task allocation module analyzes the matching degree between the action characteristic data and the training task stage based on the key action offset prediction results, optimizes the training distribution of the rudder adjustment and control torque, and combines the task stage characteristics with the action correction characteristics to generate a multi-dimensional training allocation plan for flight simulation.

2. The multidimensional data mining and analysis system based on flight simulation according to claim 1, characterized in that: The steps for obtaining the flight trajectory deviation distribution result are specifically as follows: Based on the trajectory deviation characteristic distribution result, the deviation angle data of the position points in the flight trajectory are extracted, the angle changes between adjacent position points are analyzed, the angle changes are sequenced based on the time axis, and the trajectory points are assigned time tags and reordered to obtain the flight trajectory deviation angle sequence; Based on the flight trajectory offset angle sequence, the flight attitude angle is selected as a reference parameter, the difference between the offset angle and the attitude angle is calculated, the mapping relationship between the trajectory points and the difference is analyzed, the difference data is integrated, the time axis parameters are supplemented and classified and sorted, and a trajectory angle offset difference matrix is ​​generated; Based on the trajectory angle offset difference matrix, the difference outliers and the corresponding position coordinates are extracted, and the trajectory space model is drawn in combination with the trajectory offset angle sequence. The outliers are annotated into the trajectory model, and the position relationship between the offset difference and the trajectory point is matched to generate the flight trajectory deviation distribution result.

3. The multidimensional data mining and analysis system based on flight simulation according to claim 1, characterized in that: The steps for obtaining the analysis results of the key characteristics of the action are specifically as follows: Based on the motion offset correlation matrix, the motion offset values ​​are extracted and matched with the corresponding correlation parameters, the cumulative distribution of each motion offset value is analyzed, the cumulative distribution values ​​and the correlation parameters are classified and integrated, and the distribution intervals of the high-frequency correlation parameters and the motion offset are recorded to generate a motion distribution characteristic dataset; Based on the action distribution characteristic dataset, the offset intervals of the associated parameter frequencies in the cumulative distribution are screened, and the action position data corresponding to the offset intervals are extracted. The offset characteristics of each group of actions are sorted by interval size based on the action position and offset characteristics, and the characteristic values ​​of the offset weights are marked to generate a key action characteristic grouping table; Based on the key action characteristic grouping table, the distribution of weight characteristics in the action sequence is analyzed, the mapping relationship of the offset characteristic value is adjusted according to the position of the action sequence, and the mapped distribution characteristics are integrated to generate the action key characteristic analysis result.

4. The multidimensional data mining and analysis system based on flight simulation according to claim 3, characterized in that: The steps for obtaining the offset range of the key action are specifically as follows: Based on the analysis results of the key characteristics of the action, the initial data set of the offset action distribution range is called, the key characteristic parameters of each action are analyzed, the trend range of parameter changes is analyzed, the peak offset point in the action characteristics is determined, and preliminary analysis data of the action characteristic offset is obtained; Based on the preliminary analysis data of the motion characteristic offset, the distribution density of the motion offset points is calculated using the formula: Filter the set of offset points whose distribution density exceeds a preset threshold to obtain the distribution range of high-frequency offset points; Where D is the distribution density value, P j is the weight of the offset point, W j is the feature weight of the action offset point, P is the mean of the offset point weights, and m is the total number of offset points; Based on the distribution range of the high-frequency offset points and superimposed with the motion characteristic trend range, the variation range of the characteristic parameters is analyzed, the motion offset influencing factor is introduced, and the key motion offset range is obtained.

5. The multidimensional data mining and analysis system based on flight simulation according to claim 4, characterized in that: The steps for obtaining the key action offset prediction result are specifically as follows: Based on the key action offset range, extract the values ​​of the action offset direction and amplitude, classify and label each action data according to the offset direction, assign the offset amplitude value to a continuous interval range, count the number of actions in each category, and generate a key action offset classification data set; Based on the key action offset classification dataset, the number of actions within the differentiated amplitude range is counted for each group of data in the offset direction classification, and integrated classification is performed by offset direction. The quantitative differences of the differentiated offset directions within the amplitude range are compared to generate a key action offset distribution model. Based on the key action offset distribution model, the interval data of the offset direction and amplitude distribution ratio are extracted, the action data are sorted in time series according to the interval distribution trend, the change range of the action offset direction and the amplitude interval in the future time period are predicted, and the key action offset prediction results are generated by combining the distribution trend and the predicted data.

6. The multidimensional data mining and analysis system based on flight simulation according to claim 5, characterized in that: The steps for obtaining the multi-dimensional training allocation scheme for flight simulation are specifically as follows: Based on the key action offset prediction results, a key action characteristic parameter set is extracted, including an action execution duration parameter, an action offset amplitude parameter, and an action execution accuracy parameter. By analyzing the characteristic weights of the matching parameters with the task stage, an initial set of key action characteristic parameters matching the task stage is generated; Based on the initial set of key action characteristic parameters and task stage matching, the characteristic matching degree distribution value is calculated using the formula: Optimize the influence of the matching value on the rudder adjustment distribution and generate the optimized matching characteristic distribution matrix; Among them, M c represents the distribution value of feature matching, T a Indicates the duration of action execution, D a Indicates the movement offset amplitude, P a Indicates the action execution accuracy, Q1 is the action offset weight parameter, and Q2 is the action accuracy weight parameter; The optimized matching characteristic distribution matrix is ​​called, and the rationality of optimizing the control surface adjustment and the control torque distribution is analyzed and combined with the control torque distribution and the mission phase correction characteristics. By screening the optimal distribution combination, a multi-dimensional training allocation plan for flight simulation is generated.

Images