CN114660959B - Aircraft semi-physical simulation data completeness checking method - Google Patents

Abstract

The present invention relates to a method for checking the completeness of aircraft semi-physical simulation data, comprising: collecting aircraft semi-physical simulation data and aircraft field test data; the aircraft precision data comprises: aircraft semi-physical simulation data, and, aircraft field test data; generating a simulation data confidence interval statistical envelope diagram of the aircraft semi-physical simulation data according to an aircraft precision data confidence interval statistical envelope diagram generation strategy, and generating a field data confidence interval statistical envelope diagram of the aircraft field test data; if it is checked that the simulation data confidence interval statistical envelope diagram meets a preset completeness check condition, then it is determined that the aircraft semi-physical simulation data has completeness; the completeness check condition comprises: the coverage area of the simulation data confidence interval statistical envelope diagram can completely cover the coverage area of the field data confidence interval statistical envelope diagram. The present invention can effectively solve the problem of checking the completeness of semi-physical simulation data.

Description

A method for verifying data integrity of aircraft semi-physical simulation

Technical Field

The present invention relates to the technical field of semi-physical simulation, and in particular to a method for checking data integrity of aircraft semi-physical simulation.

Background Art

At present, field tests are mostly conducted under specific conditions, with a limited number of samples, which cannot fully cover the range of test conditions for equipment accuracy assessment. Semi-physical simulation tests have high credibility, and the conditions can be flexibly set, with a large number of samples. In order to improve the adequacy and credibility of aircraft accuracy assessment, the fusion of semi-physical simulation data and small sample field test data has become an effective way to improve equipment accuracy assessment, and the premise of fusion is to ensure the completeness and effectiveness of semi-physical simulation data.

At present, there are few research results on data completeness testing, and the methods that can be used for reference are usually for one-dimensional data, and mostly use statistical model analysis methods. The test data completeness test results are affected by the accuracy of statistical quantities such as sample mean and sample variance, as well as abnormal data, and are mostly suitable for small sample tests. They are not very applicable to large sample data such as semi-physical simulation data. At present, there is no mature method for reference for the completeness test of semi-physical simulation data.

Summary of the invention

In view of the above analysis, the present invention aims to provide a method for verifying the completeness of aircraft semi-physical simulation data, so as to solve the technical problem existing in the prior art that it is difficult to verify the completeness of semi-physical simulation data.

The technical solution provided by the present invention is:

The present invention provides a method for checking data integrity of aircraft semi-physical simulation, comprising:

Collect aircraft semi-physical simulation data and aircraft field test data;

According to the aircraft precision data confidence interval statistical envelope diagram generation strategy, a simulation data confidence interval statistical envelope diagram of the aircraft semi-physical simulation data and a field data confidence interval statistical envelope diagram of the aircraft field test data are generated; wherein the aircraft precision data includes the aircraft semi-physical simulation data and the aircraft field test data;

If it is verified that the confidence interval statistical envelope diagram of the simulation data meets the preset completeness verification condition, then it is determined that the aircraft semi-physical simulation data is complete;

The preset completeness test conditions include:

The coverage area of the statistical envelope diagram of the confidence interval of the simulation data can completely cover the coverage area of the statistical envelope diagram of the confidence interval of the field data.

Preferably, the preset integrity check condition also includes:

The ratio of the area covered by the statistical envelope diagram of the confidence interval of the simulation data to the area covered by the preset empirical statistical envelope diagram reaches a preset threshold.

Preferably, the strategy for generating the statistical envelope diagram of the aircraft accuracy data confidence interval includes:

Projecting the aircraft accuracy data into a two-dimensional rectangular coordinate system;

In the two-dimensional rectangular coordinate system, the longitudinal axis is equally divided in the horizontal axis direction to obtain a plurality of equally spaced intervals, each of which corresponds to the projection data of the aircraft precision data;

For the aircraft field test data, sample expansion processing is performed on the projection data in each equidistant interval to obtain sample expanded projection data of the aircraft field test data in each equidistant interval;

Respectively obtaining the confidence intervals of the projection data of the aircraft semi-physical simulation data and the sample expanded projection data in corresponding equidistant intervals;

According to a preset confidence interval envelope diagram endpoint determination strategy, the envelope diagram endpoints corresponding to the equidistant intervals corresponding to the projection data of the aircraft semi-physical simulation data are determined, and the envelope diagram endpoints are sequentially connected to form a first closed curve, wherein the first closed curve is the statistical envelope diagram of the simulation data confidence interval;

According to the preset confidence interval envelope endpoint determination strategy, the envelope endpoints corresponding to the equidistant intervals corresponding to the sample expanded projection data are determined, and the envelope endpoints are connected in sequence to form a second closed curve, which is the statistical envelope of the field data confidence interval.

Preferably, the step of respectively obtaining the confidence intervals of the projection data of the aircraft semi-physical simulation data and the sample expanded projection data in corresponding equidistant intervals comprises:

Calculate the mean and standard deviation of the projection data of the semi-physical simulation data of the aircraft or the sample expanded projection data in the horizontal axis direction in the corresponding equidistant interval, and calculate the confidence interval of the projection data of the semi-physical simulation data of the aircraft or the sample expanded projection data in the horizontal axis direction in the corresponding equidistant interval according to the mean and standard deviation in the horizontal axis direction, and obtain the corresponding confidence interval of the corresponding equidistant interval in the horizontal axis direction;

Calculate the mean and standard deviation of the projection data of the semi-physical simulation data of the aircraft or the sample expanded projection data in the longitudinal axis direction of the two-dimensional plane rectangular coordinate system in the corresponding equidistant interval; calculate the confidence interval of the projection data of the semi-physical simulation data of the aircraft or the sample expanded projection data in the longitudinal axis direction in the corresponding equidistant interval based on the mean and standard deviation in the longitudinal axis direction, and obtain the corresponding confidence interval in the longitudinal axis direction of the corresponding equidistant interval.

Preferably, the preset confidence interval envelope diagram endpoint determination strategy includes:

A pair of parallel lines on the vertical axis are drawn through the two endpoints of the confidence interval corresponding to the corresponding equidistant interval in the horizontal direction, and a pair of parallel lines on the horizontal axis are drawn through the two endpoints of the confidence interval corresponding to the corresponding equidistant interval in the vertical direction. The two pairs of parallel lines intersect respectively to obtain four intersection points, and the four intersection points are determined as the endpoints of the envelope diagram corresponding to the corresponding equidistant interval.

Preferably, in the two-dimensional rectangular coordinate system, dividing the longitudinal axis into equal intervals in the horizontal axis direction comprises:

The Sturges group distance partitioning method is used to perform the equal distance partitioning.

Preferably, the aircraft accuracy data is three-dimensional data, and the method further comprises:

Performing dimensionality reduction processing on the aircraft accuracy data includes:

Before projecting the aircraft precision data into the two-dimensional plane rectangular coordinate system, a spatial rectangular coordinate system is established to obtain three two-dimensional plane coordinate systems;

The aircraft precision data is projected into each two-dimensional plane coordinate system respectively.

Preferably, the generating of a statistical envelope diagram of a confidence interval of simulation data that can reflect the distribution characteristics of the semi-physical simulation data of the aircraft, and the generating of a statistical envelope diagram of a confidence interval of field data that can reflect the distribution characteristics of the field test data of the aircraft include:

In each two-dimensional plane coordinate system, a statistical envelope diagram of the confidence interval of simulation data and a statistical envelope diagram of the confidence interval of expanded data are generated accordingly.

Preferably, the preset completeness test condition that the statistical envelope diagram of the confidence interval of the simulation data can completely cover the statistical envelope diagram of the confidence interval of the extended data includes:

The statistical envelope diagram of the confidence interval of the simulation data in each two-dimensional plane coordinate system can completely cover the statistical envelope diagram of the confidence interval of the extended data in the corresponding two-dimensional plane coordinate system;

The ratio of the area covered by the confidence interval statistical envelope diagram of the simulation data in the preset completeness test condition to the area covered by the preset empirical statistical envelope diagram reaches a preset threshold value, including:

The ratio of the area covered by the confidence interval statistical envelope diagram of the simulation data in each two-dimensional plane coordinate system to the area covered by the preset empirical statistical envelope diagram in the corresponding two-dimensional plane coordinate system reaches a preset threshold.

Preferably, for the aircraft field test data, performing sample expansion processing on the projection data in each equidistant interval includes:

Using the Bootstrap method to perform the sample expansion process

In the technical solution provided by the embodiment of the present invention, the inventor, based on his own research, determines whether the semi-physical simulation data meets the completeness requirements by establishing a completeness verification criterion, verifies the completeness of the data by drawing a confidence interval statistical envelope diagram of the data, generates a simulation data confidence interval statistical envelope diagram that can reflect the distribution characteristics of the aircraft semi-physical simulation data, and generates a field data confidence interval statistical envelope diagram that can reflect the distribution characteristics of the aircraft field test data, and verifies the completeness of the aircraft semi-physical simulation data according to preset completeness verification conditions, thereby effectively solving the problem of completeness verification of semi-physical simulation data.

In the present invention, the above-mentioned technical solutions can also be combined with each other to achieve more preferred combination solutions. Other features and advantages of the present invention will be described in the subsequent description, and some advantages can become obvious from the description, or can be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained through the contents particularly pointed out in the description and the drawings.

BRIEF DESCRIPTION OF THE DRAWINGS

The drawings are only for the purpose of illustrating particular embodiments and are not to be considered limiting of the present invention. Like reference symbols denote like components throughout the drawings.

FIG1 is a flow chart of a method for checking data integrity of aircraft semi-physical simulation in an embodiment of the present invention;

FIG2 is an example diagram of projecting three-dimensional aircraft accuracy data onto a two-dimensional plane in an embodiment of the present invention;

FIG3 is an example diagram of equally spaced division of the z-axis based on projection data in an embodiment of the present invention;

FIG4 is an example diagram of a sample expanded based on Bootstrap in an embodiment of the present invention;

5 is an example diagram of determining the endpoints of an envelope diagram corresponding to a certain equidistant interval in an embodiment of the present invention;

6 is a statistical envelope diagram of confidence intervals of external field data on the xoz plane according to an embodiment of the present invention;

FIG7 is an example diagram of dividing an envelope diagram for area calculation in an embodiment of the present invention;

8 is an example diagram of an envelope of completeness of aircraft semi-physical simulation data in an embodiment of the present invention;

FIG. 9 is an example diagram of an envelope of incomplete aircraft semi-physical simulation data in an embodiment of the present invention.

DETAILED DESCRIPTION

The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used to illustrate the principles of the present invention together with the embodiments of the present invention.

The embodiment of the present invention provides a method for checking the data integrity of a semi-physical simulation of an aircraft. Referring to FIG1 , FIG1 is a flow chart of the method for checking the data integrity of a semi-physical simulation of an aircraft in the embodiment of the present invention. The flow may include the following steps:

Step 101: Collect aircraft semi-physical simulation data and aircraft field test data.

Specifically, the aircraft semi-physical simulation data includes: aircraft simulation space landing point data; the aircraft field test data may include: aircraft space landing point data Step 102: Generate a statistical envelope diagram of the confidence interval of the aircraft semi-physical simulation data and generate a statistical envelope diagram of the confidence interval of the aircraft field test data according to the strategy for generating the statistical envelope diagram of the confidence interval of the aircraft accuracy data.

Among them, the statistical envelope diagram of the confidence interval of the aircraft semi-physical simulation data can reflect the distribution characteristics of the aircraft semi-physical simulation data, and the statistical envelope diagram of the confidence interval of the aircraft field test data can reflect the distribution characteristics of the aircraft field test data.

In the embodiment of the present invention, the aircraft accuracy data includes: aircraft semi-physical simulation data, and aircraft field test data.

Step 103: If it is verified that the statistical envelope diagram of the confidence interval of the simulation data meets the preset completeness verification conditions, the aircraft semi-physical simulation data is determined to be complete. The preset completeness verification conditions include: the coverage area of the statistical envelope diagram of the confidence interval of the simulation data can completely cover the coverage area of the statistical envelope diagram of the confidence interval of the field data.

In order to further verify the completeness of the aircraft semi-physical simulation data, the preset completeness check conditions that can be set in the embodiment of the present invention may further include:

The ratio of the area covered by the statistical envelope diagram of the simulation data confidence interval to the area covered by the preset empirical statistical envelope diagram reaches a preset threshold, and the preset threshold can be set at about 80%, wherein the preset empirical statistical envelope diagram is a pre-estimated polygonal area reflecting the statistical envelope of the simulation data confidence interval, which can be obtained in advance based on experimental experience.

In the technical solution provided by the embodiment of the present invention, the inventor, based on his own research, establishes completeness verification criteria to determine whether the semi-physical simulation data meets the completeness requirements, and uses the confidence interval statistical envelope diagram of the data to verify the completeness of the data. By generating a simulation data confidence interval statistical envelope diagram that can reflect the distribution characteristics of the aircraft semi-physical simulation data, and generating a field data confidence interval statistical envelope diagram that can reflect the distribution characteristics of the aircraft field test data, and verifying the completeness of the aircraft semi-physical simulation data according to preset completeness verification conditions, the problem of completeness verification of semi-physical simulation data can be effectively solved.

In the embodiment of the present invention, the strategy for generating the statistical envelope diagram of the confidence interval of the aircraft accuracy data may specifically include the following steps:

S1: Projecting the aircraft accuracy data into a two-dimensional rectangular coordinate system;

S2: In the two-dimensional rectangular coordinate system, the longitudinal axis is divided into equal intervals in the horizontal axis direction to obtain a plurality of equal intervals, each of which corresponds to the projection data of the aircraft accuracy data;

S3: for the aircraft field test data, performing sample expansion processing on the projection data in each equidistant interval to obtain sample expanded projection data of the aircraft field test data in each equidistant interval;

S4: respectively obtaining the confidence intervals of the projection data of the aircraft semi-physical simulation data and the sample expanded projection data in corresponding equidistant intervals;

S51: according to a preset confidence interval envelope diagram endpoint determination strategy, determine the envelope diagram endpoints corresponding to the equidistant intervals corresponding to the projection data of the aircraft semi-physical simulation data, and sequentially connect the envelope diagram endpoints to form a first closed curve, wherein the first closed curve is the statistical envelope diagram of the simulation data confidence interval;

S52: According to a preset confidence interval envelope diagram endpoint determination strategy, determine the envelope diagram endpoints corresponding to the equidistant intervals corresponding to the sample expanded projection data, and sequentially connect each envelope diagram endpoint to form a second closed curve, which is the confidence interval statistical envelope diagram of the field data.

The strategy for generating the statistical envelope diagram of the confidence interval of the aircraft accuracy data in the embodiment of the present invention is further described below.

In the specific application of the present invention, if the aircraft precision data is two-dimensional data, the aircraft precision data can be directly projected into a pre-established two-dimensional plane rectangular coordinate system; in actual applications, the aircraft precision data may be three-dimensional data, and it is necessary to perform dimensionality reduction processing on the aircraft precision data. For the above step S1, the specific method may include:

Before projecting the aircraft precision data into the two-dimensional plane rectangular coordinate system, a three-dimensional space rectangular coordinate system is established to obtain three two-dimensional plane coordinate systems;

Project the aircraft precision data into each two-dimensional plane coordinate system respectively.

See Figure 2, which is an example diagram of projecting three-dimensional aircraft accuracy data onto a two-dimensional plane in an embodiment of the present invention. In Figure 2, the aircraft accuracy data is projected onto three two-dimensional planes, the xoy plane, the yoz plane, and the xoz plane, respectively, to achieve dimensionality reduction. In this application, the specific drawing process of the statistical envelope diagram of the confidence interval of the aircraft accuracy data within the xoz plane is explained by taking the projection of the three-dimensional aircraft accuracy data onto the xoz plane as an example.

In the specific implementation of the present invention, for the above step S2, considering that the aircraft accuracy data basically obeys the normal distribution within the error allowable range, and considering the sample size of the data, in order to ensure that the final confidence interval statistical envelope diagram is not distorted, the selection method of the group distance and number of groups of the optimal histogram in the histogram theory is adopted, that is, the Sturges group distance division method is used to divide the vertical axis into equal intervals in the horizontal axis direction. Assuming that the sample size of the aircraft accuracy data is m, and the number of groups obtained by equally dividing the vertical axis is k, then according to the Sturges group distance division method, there are:

k≈1+3.322ln m.

See Figure 3, which is an example diagram of equally spaced division of the z-axis based on projection data in an embodiment of the present invention. Figure 3 shows 7 equally spaced intervals, each equally spaced interval is marked with a serial number as shown in the figure. In actual applications, there may be more equally spaced intervals.

In the embodiment of the present invention, for the aircraft field test data, the sample size is usually small. In order to reflect the statistical characteristics of the aircraft field test data, it is necessary to expand the field small sample data. Since there is no available prior information, the Bayesian sample expansion method is not applicable, while the bootstrap method does not require prior information and can obtain new samples by resampling the small sample data, thereby converting the small sample problem into a large sample, and the amount of calculation is small. Therefore, in the specific implementation of the present invention, the Bootstrap method is used for sample expansion processing.

See Figure 4, which is an example diagram of expanding samples based on Bootstrap in an embodiment of the present invention. Take the expansion of projection data in k=3 equally spaced intervals as an example, where the projection data in k=3 equally spaced intervals are projection data of native sample data, and assume that the observation value is X=( _x1 , _x2 , ..., _xn ), where n is the number of samples in k=3 equally spaced intervals, and establish the empirical distribution function _Fn (x) of the sample based on X=( _x1 , _x2 , ..., _xn ), and then expand N groups of regenerated samples based on the empirical distribution function _Fn (x) as follows: For details, please refer to the following content:

Step 1: Take η = rand(1), rand(1) can randomly generate any decimal in [0, 1];

Step 2: Define P = η(n-1), M = [P], [·] means rounding to the nearest integer, M represents the subscript after the original sample data is sorted, and there are:

Step 3: The generation method of the regenerated sample is:

in, is the sample data of Bootstrap resampling, X _(M) and X _(M+1) are the original sample data. For the specific content of Bootstrap expansion samples, please refer to the relevant technical literature, and this application will not repeat them. After expansion, the N groups of regenerated samples are obtained as That is, the sample expanded projection data within the k=3 equidistant interval.

In the embodiment of the present invention, the above step S4 may specifically include:

Calculate the mean and standard deviation of the projection data of the semi-physical simulation data of the aircraft or the sample expanded projection data in the horizontal axis direction in the corresponding equidistant interval, and calculate the confidence interval of the projection data of the semi-physical simulation data of the aircraft or the sample expanded projection data in the horizontal axis direction in the corresponding equidistant interval according to the mean and standard deviation in the horizontal axis direction, and obtain the corresponding confidence interval of the corresponding equidistant interval in the horizontal axis direction;

Calculate the mean and standard deviation of the projection data of the semi-physical simulation data of the aircraft or the sample expanded projection data in the longitudinal axis direction of the two-dimensional plane rectangular coordinate system in the corresponding equidistant interval; calculate the confidence interval of the projection data of the semi-physical simulation data of the aircraft or the sample expanded projection data in the longitudinal axis direction in the corresponding equidistant interval based on the mean and standard deviation in the longitudinal axis direction, and obtain the corresponding confidence interval in the longitudinal axis direction of the corresponding equidistant interval.

In the embodiment of the present invention, the k=3 equally spaced intervals of regenerated samples (sample expanded projection data) are obtained by calculating the Bootstrap expanded samples. Taking the confidence interval in the horizontal direction as an example, the process of obtaining the confidence interval of the projection data of the aircraft semi-physical simulation data or the sample expansion projection data in the corresponding equidistant interval is as follows:

according to Compute the bootstrap statistic:

in, is the mean of the j-th group of reproduced samples, mean(X) is the mean of the original samples, and R _m (j) is the mean error of the j-th group of reproduced samples; is the standard deviation of the j-th group of reproduced samples, std(X) is the standard deviation of the original samples, and R _s (j) is the standard deviation error of the j-th group of reproduced samples;

Calculate the mean μ* and standard deviation σ ^* of the reproduced samples in k=3 equally spaced intervals in the horizontal direction:

Where, mean(R _m ) is the mean of the mean errors of N groups of reproduced samples, and mean(R _s ) is the mean of the standard deviation errors of N groups of reproduced samples;

Calculate the confidence interval of the reproduced sample in the horizontal direction within k=3 equally spaced intervals:

I _X = [μ ^* -3σ ^* , μ ^* +3σ ^* ];

In the embodiment of the present invention, considering that the aircraft intensive reading data conforms to the normal distribution, 99.7% of the data can be covered within the interval of 6σ ^* . Therefore, in the specific implementation of the present invention, the interval I _X = [μ ^* -3σ ^* , μ ^* +3σ ^* ] is taken as the confidence interval.

The calculation of the confidence interval in the longitudinal direction is similar and will not be repeated. In addition, for the semi-physical simulation data of the aircraft, since it is a known quantity, the calculation of the relevant confidence interval is similar to the calculation of the confidence interval mentioned above and will not be repeated.

In the embodiment of the present invention, in the above steps S51 and S52, the preset confidence interval envelope diagram endpoint determination strategy includes:

A pair of parallel lines on the vertical axis are drawn through the two endpoints of the confidence interval corresponding to the corresponding equidistant interval in the horizontal direction, and a pair of parallel lines on the horizontal axis are drawn through the two endpoints of the confidence interval corresponding to the corresponding equidistant interval in the vertical direction. The two pairs of parallel lines intersect respectively to obtain four intersection points, and the four intersection points are determined as the endpoints of the envelope diagram corresponding to the corresponding equidistant interval.

See FIG5 , which is an example diagram of determining the endpoints of the envelope diagram corresponding to a certain equidistant interval in an embodiment of the present invention. In FIG5 , assume that the two endpoints of the confidence interval on the horizontal axis x direction on the equidistant interval are point A and point B respectively. Point B The two endpoints of the confidence interval in the z direction of the vertical axis are point C Point D Then draw a pair of parallel lines through point A and point B on the z-axis, and draw a pair of parallel lines through point C and point D on the x-axis. The two pairs of parallel lines intersect at four points. These four points: point E, point F, point G, and point H are the endpoints of the envelope diagram corresponding to the equidistant interval.

Find the endpoints of the envelope diagram corresponding to each equidistant interval, and connect these envelope diagram endpoints in sequence with line segments to form the first or second closed curve, then the first or second closed curve is the confidence interval statistical envelope diagram of the corresponding data. For the semi-physical simulation data of the aircraft, the statistical envelope diagram of the confidence interval of the simulation data is obtained; for the field test data of the aircraft, the statistical envelope diagram of the confidence interval of the field data is obtained. See Figure 6, which is a statistical envelope diagram of the confidence interval of the field data on the xoz plane in an embodiment of the present invention. In practical applications, for three-dimensional data, it is necessary to generate a statistical envelope diagram of the confidence interval of the simulation data and a statistical envelope diagram of the confidence interval of the expanded data in each two-dimensional plane coordinate system.

In an embodiment of the present invention, based on the generated statistical envelope diagram of the confidence interval of the aircraft accuracy data, the completeness check of the semi-physical simulation data of the aircraft is performed. Usually, the amount of aircraft field test data is small, and the area of the corresponding confidence interval statistical envelope diagram is often small, but the envelope diagram can reflect the distribution range of the real landing point data. Correspondingly, the amount of aircraft semi-physical simulation data is relatively large, and the area of the corresponding confidence interval statistical envelope diagram is often large. If the larger simulation data confidence interval envelope cannot completely cover the smaller field data confidence interval statistical envelope, it means that some extreme points of the semi-physical simulation data are not reflected in the limited number of simulations, that is, the data is incomplete, and the test conditions need to be supplemented so that the confidence interval envelope of the supplemented semi-physical simulation data can completely envelop the field test data. For the case where the aircraft accuracy data is three-dimensional data, it is required that the statistical envelope diagram of the confidence interval of the simulation data in each two-dimensional plane coordinate system can completely cover the statistical envelope diagram of the confidence interval of the expanded data in the corresponding two-dimensional plane coordinate system; and it is required that the ratio of the area covered by the statistical envelope diagram of the confidence interval of the simulation data in each two-dimensional plane coordinate system to the area covered by the preset empirical statistical envelope diagram in the corresponding two-dimensional plane coordinate system reaches a preset threshold.

See Figure 7, which is an example diagram of dividing the envelope diagram for area calculation in an embodiment of the present invention. The calculation principle of the envelope diagram area can refer to the following calculation formula:

This calculation formula takes the simulation data confidence interval statistical envelope diagram and the empirical statistical envelope diagram generated in the xoz surface as an example to calculate the simulation data confidence interval statistical envelope diagram area A _b and the empirical statistical envelope diagram area A _z :

If A _b /A _z ≥ρ, ρ is the preset threshold, such as 80% as mentioned above, the semi-physical simulation data is considered to have high completeness and no additional data is needed, and it can directly participate in subsequent research;

If A _b /A _z ＜ρ, it means that the semi-physical simulation data coverage is insufficient and additional data are needed before participating in subsequent research.

Refer to Figure 8, which is an envelope example diagram of the completeness of the aircraft semi-physical simulation data in the embodiment of the present invention. Refer to Figure 9, which is an envelope example diagram of the incompleteness of the aircraft semi-physical simulation data in the embodiment of the present invention. In practical applications, the envelope diagram is usually as shown in Figure 6, with irregularities, and Figures 8 and 9 are only used as examples to illustrate under what circumstances the aircraft semi-physical simulation data is complete. In Figures 8 and 9, the data corresponding to the empirical statistical envelope diagram are such as empirical estimation data, the data corresponding to the simulation data confidence interval statistical envelope diagram are aircraft semi-physical simulation data, and the data corresponding to the field data confidence interval statistical envelope diagram are aircraft field test data.

In Figure 8, the coverage area of the statistical envelope diagram of the confidence interval of the simulation data can completely cover the coverage area of the statistical envelope diagram of the confidence interval of the field data, and the ratio of the area covered by the statistical envelope diagram of the confidence interval of the simulation data to the area covered by the empirical statistical envelope diagram reaches 80%. In this case, it can be determined that the semi-physical simulation data of the aircraft is complete.

However, in Figure 9, the statistical envelope diagram of the confidence interval of the simulation data cannot completely cover the statistical envelope diagram of the confidence interval of the field data. There is an intersection between the two. Therefore, it can be determined that the semi-physical simulation data of the aircraft is not complete.

To summarize, in the technical solution provided in the embodiment of the present invention, the inventor, based on his own research, verifies the completeness of the data by drawing a statistical envelope diagram of the confidence interval of the data, generates a statistical envelope diagram of the confidence interval of the simulation data that can reflect the distribution characteristics of the semi-physical simulation data of the aircraft, and generates a statistical envelope diagram of the confidence interval of the field data that can reflect the distribution characteristics of the field test data of the aircraft, and verifies the completeness of the semi-physical simulation data of the aircraft according to preset completeness verification conditions, thereby effectively solving the problem of completeness verification of semi-physical simulation data.

Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims (10)

1. The method for checking the completeness of the semi-physical simulation data of the aircraft is characterized by comprising the following steps of:

Acquiring semi-physical simulation data of an aircraft and outfield test data of the aircraft;

Generating a simulation data confidence interval statistical envelope map of the aircraft semi-physical simulation data and an outfield data confidence interval statistical envelope map of the aircraft outfield test data according to an aircraft precision data confidence interval statistical envelope map generating strategy; the aircraft precision data comprise the aircraft semi-physical simulation data and the aircraft outfield test data;

if the confidence interval statistical envelope diagram of the simulation data meets the preset completeness checking condition, judging that the semi-physical simulation data of the aircraft has completeness;

The preset completeness check condition comprises:

The simulation data confidence interval statistical envelope map coverage area can completely cover the outfield data confidence interval statistical envelope map coverage area.

2. The method for checking the completeness of semi-physical simulation data of an aircraft according to claim 1, wherein the preset completeness checking condition further comprises:

And the ratio of the area covered by the simulation data confidence interval statistical envelope graph to the coverage area of the preset experience statistical envelope graph reaches a preset threshold.

3. The aircraft semi-physical simulation data integrity verification method of claim 1 or 2, wherein said aircraft accuracy data confidence interval statistical envelope map generation strategy comprises:

projecting the aircraft precision data into a two-dimensional plane rectangular coordinate system;

In the two-dimensional plane rectangular coordinate system, equally dividing the longitudinal axis in the transverse axis direction to obtain a plurality of equidistant intervals, wherein projection data corresponding to the aircraft precision data in each equidistant interval;

Sample expansion processing is carried out on the projection data in each equidistant interval for the aircraft outfield test data, so as to obtain sample expansion projection data of the aircraft outfield test data in each equidistant interval;

Respectively obtaining the projection data of the aircraft semi-physical simulation data and the confidence interval of the sample expansion projection data in the corresponding equidistant interval;

Determining envelope graph endpoints corresponding to equidistant intervals corresponding to projection data of the aircraft semi-physical simulation data according to a preset confidence interval envelope graph endpoint determination strategy, sequentially connecting the envelope graph endpoints to form a first closed curve, wherein the first closed curve is the simulation data confidence interval statistical envelope graph;

And determining envelope endpoints corresponding to equidistant intervals corresponding to the sample extended projection data according to a preset confidence interval envelope endpoint determination strategy, sequentially connecting the envelope endpoints to form a second closed curve, wherein the second closed curve is the external field data confidence interval statistical envelope.

4. A method of aircraft semi-physical simulation data integrity verification according to claim 3, wherein said separately determining confidence intervals of projection data of said aircraft semi-physical simulation data and said sample extended projection data in corresponding equidistant intervals comprises:

Calculating the mean value and standard deviation of the projection data of the aircraft semi-physical simulation data or the sample expansion projection data in the horizontal axis direction in the corresponding equidistant interval, and calculating the confidence interval of the projection data of the aircraft semi-physical simulation data or the sample expansion projection data in the horizontal axis direction in the corresponding equidistant interval according to the mean value and standard deviation in the horizontal axis direction to obtain the confidence interval corresponding to the equidistant interval in the horizontal axis direction;

And calculating the mean value and standard deviation of the projection data of the aircraft semi-physical simulation data or the sample expansion projection data in the longitudinal axis direction of the two-dimensional plane rectangular coordinate system in the corresponding equidistant interval, and calculating the confidence interval of the projection data of the aircraft semi-physical simulation data or the sample expansion projection data in the longitudinal axis direction in the corresponding equidistant interval according to the mean value and standard deviation in the longitudinal axis direction to obtain the confidence interval corresponding to the longitudinal axis direction in the corresponding equidistant interval.

5. The method for checking the completeness of aircraft semi-physical simulation data according to claim 4, wherein the preset confidence interval envelope map endpoint determination strategy comprises:

and a pair of parallel lines taking two endpoints of the confidence interval corresponding to the equidistant interval in the direction of the horizontal axis as a vertical axis, a pair of parallel lines taking two endpoints of the confidence interval corresponding to the equidistant interval in the direction of the vertical axis as a horizontal axis, and two pairs of parallel lines respectively intersecting to obtain four intersection points, wherein the four intersection points are determined to be the endpoints of the envelope map corresponding to the corresponding equidistant interval.

6. The method for checking the completeness of the semi-physical simulation data of the aircraft according to claim 3, wherein the equidistant division of the longitudinal axis in the transverse axis direction in the two-dimensional plane rectangular coordinate system comprises:

the equidistant partitioning is done using Sturges group distance partitioning.

7. The method for checking the completeness of aircraft semi-physical simulation data according to claim 3, wherein the aircraft precision data is three-dimensional data, and the method further comprises:

Performing dimension reduction processing on the aircraft precision data, wherein the dimension reduction processing comprises the following steps:

Before the aircraft precision data are projected into a two-dimensional plane rectangular coordinate system, a space rectangular coordinate system is established, and three two-dimensional plane coordinate systems are obtained;

the aircraft accuracy data are projected into each two-dimensional planar coordinate system.

8. The method of claim 7, wherein generating a simulated data confidence interval statistical envelope map that embodies the aircraft semi-physical simulated data distribution characteristics, and generating a outfield data confidence interval statistical envelope map that embodies the aircraft outfield test data distribution characteristics comprises:

and correspondingly generating a simulation data confidence interval statistical envelope map and an extended data confidence interval statistical envelope map in each two-dimensional plane coordinate system.

9. The aircraft semi-physical simulation data completeness verification method of claim 8, wherein said simulation data confidence interval statistical envelope map in said preset completeness verification condition is capable of completely covering said extended data confidence interval statistical envelope map comprises:

The simulated data confidence interval statistical envelope map in each two-dimensional plane coordinate system can completely cover the expanded data confidence interval statistical envelope map in the corresponding two-dimensional plane coordinate system;

The step of obtaining the ratio of the area covered by the simulation data confidence interval statistical envelope map to the coverage area of the preset experience statistical envelope map in the preset completeness test condition to reach a preset threshold value comprises the following steps:

The ratio of the area covered by the simulation data confidence interval statistical envelope map in each two-dimensional plane coordinate system to the coverage area of the preset experience statistical envelope map in the corresponding two-dimensional plane coordinate system reaches a preset threshold.

10. A method of aircraft semi-physical simulation data integrity verification according to claim 3, wherein said sample expansion processing of projection data within each equidistant interval for said aircraft outfield test data comprises:

And using a Bootstrap method to perform sample expansion processing.