A convolution and machine learning-based intelligent detection method for a tail wake region

Abstract

The application discloses a kind of based on convolution and machine learning's wake region intelligent detection method, belong to wake region boundary detection technical field.Solve the problem of low efficiency, poor universality and insufficient precision in the conventional wake region detection method in prior art;The application carries out standardization processing to wake rake pressure data, obtains normalized pressure coefficient vector;Based on convolution method, the local key features of pressure distribution curve are extracted, a multidimensional feature vector is constructed, and a feature matrix is generated;Select training samples to form label column vector;Based on sample set is divided into training set and validation set, select the optimal model as the wake region detection benchmark model;Intelligent prediction is carried out on the wake rake pressure data of new test train, and the wake region boundary is determined;Through incremental learning, the generalization ability of the model is continuously improved, and the performance of the wake region detection benchmark model is continuously iterated.The application effectively improves the accuracy of wake region boundary detection results, and can be applied to wind tunnel test.

Description

Technical Field

[0001] This invention relates to an intelligent method for detecting wake regions, and more particularly to an intelligent method for detecting wake regions based on convolution and machine learning, belonging to the field of wake region boundary detection technology. Background Technology

[0002] Wind tunnel testing, as a core tool for aerodynamic research and aircraft aerodynamic layout design, provides crucial data support for aircraft performance evaluation. In airfoil wind tunnel testing, the airfoil drag coefficient is a core parameter characterizing aerodynamic performance. Its accurate measurement relies on momentum-based drag measurement technology. This involves collecting static and total pressure distributions within the wake region using a fixed or continuously scanning wake measurement device, and calculating the drag coefficient based on the total pressure loss of the wake. In this process, the accurate determination of the wake region boundary directly determines the effectiveness of the drag integration region and is a critical prerequisite for ensuring the accuracy of drag measurement.

[0003] Existing technologies for wake zone boundary detection have significant limitations: First, manual interpretation relies on the experience of test personnel to subjectively determine the wake zone boundary, resulting in low efficiency and poor interpretation consistency, making it difficult to meet the demands of high-efficiency and batch testing in wind tunnels. Second, traditional data-driven methods, such as threshold methods, rely on core parameters (e.g., pressure threshold, gradient threshold) that are related to the test airfoil chord length, tail rake installation position (distance between front and rear), tail rake pressure measurement point density, and test Mach number. This means that calibrated parameters are not universally applicable to other test conditions, requiring parameter readjustment and optimization when the test object or conditions change, leading to high adaptation costs. Third, wake zone boundaries are often accompanied by local abrupt changes in the pressure distribution curve (e.g., sudden gradient changes, curvature inflections). Traditional wake zone boundary detection methods struggle to capture these subtle features, providing only a rough boundary range, which cannot meet the stringent requirements of high-precision drag measurement for boundary determination. Obtaining more accurate boundary values ​​significantly increases the number of parameters involved and complicates the calculation methods.

[0004] Therefore, there is an urgent need for an intelligent tail region detection method based on convolution and machine learning that combines high efficiency, universality, and high accuracy. Summary of the Invention

[0005] A brief overview of the invention is given below to provide a basic understanding of certain aspects of it. It should be understood that this overview is not an exhaustive summary of the invention. It is not intended to identify key or essential parts of the invention, nor is it intended to limit the scope of the invention. Its purpose is merely to present certain concepts in a simplified form as a prelude to the more detailed description that follows.

[0006] In view of this, in order to solve the problems of low efficiency, poor universality and insufficient accuracy of manual interpretation in the traditional wake region detection methods in the prior art, the present invention provides an intelligent wake region detection method based on convolution and machine learning.

[0007] The technical solution is as follows: An intelligent method for detecting trailing regions based on convolution and machine learning, comprising the following steps:

[0008] S1. Standardize the tail rake pressure measurement data to eliminate the influence of differences in test conditions on data characteristics and obtain a normalized pressure coefficient vector.

[0009] S2. Based on the normalized pressure coefficient vector, extract the local key features of the pressure distribution curve using the convolution method, construct a multi-dimensional feature vector, and generate a feature matrix;

[0010] S3. Select tail rake pressure data from previous test runs as training samples, assign wake region judgment labels to the feature matrix, and form a label column vector;

[0011] S4. Divide the sample set constructed based on the feature matrix and label column vector into a training set and a validation set. Use a supervised classification algorithm to train the training set, evaluate the model performance through the validation set, and select the optimal model as the benchmark model for wake region detection.

[0012] S5. Based on the wake zone detection benchmark model, intelligently predict the tail rake pressure data of the new test train and determine the wake zone boundary;

[0013] S6. By incrementally learning, the generalization ability of the model is continuously improved, and the performance of the baseline model for wake region detection is continuously iterated, thereby further improving the accuracy of the wake region boundary.

[0014] Furthermore, step S1 includes the following steps:

[0015] S11. Collect raw data from the tail rake pressure measurement points. The tail rake includes... The pressure measurement point, the first The spatial coordinates of the pressure measurement points are: Its unit is m, and the measured pressure is Its unit is Pa;

[0016] S12. Based on the incoming flow parameters from step S11, calculate the first... Pressure coefficient at each pressure measuring point ;

[0017] In S12, the first Pressure coefficient at each pressure measuring point Represented as:

[0018]

[0019] in, The static pressure of the incoming flow is expressed in Pa. The pressure is the flow pressure, and its unit is Pa;

[0020] S13. Normalize the spatial coordinates of the pressure measurement points to obtain normalized coordinates based on the airfoil chord length c. and for the first Pressure coefficient at each pressure measuring point Normalization is performed to obtain the normalized pressure coefficient vector. ;

[0021] In S13, the normalized coordinates Represented as:

[0022]

[0023] Normalized pressure coefficient vector Represented as:

[0024]

[0025]

[0026]

[0027] in, For the first Pressure coefficient at each pressure measuring point The minimum value, For the first Pressure coefficient at each pressure measuring point The maximum value.

[0028] Furthermore, step S2 includes the following steps:

[0029] S21. For the normalized pressure coefficient vector Local feature extraction is performed using differential convolution kernels to obtain first-order differential features. and second-order differential features ;

[0030] In S21, a first-order difference convolution kernel is used. Convolution is performed on the interval [-1, 0, 1] to obtain the first-order differential features of each point. It is used to characterize the pressure curve in the first... gradient at a point ;

[0031] The h-th element of the first-order differential eigenvector is represented as:

[0032]

[0033] in, Normalized pressure coefficient vector The item, , ,and It is an integer;

[0034] Using second-order difference convolution kernel Convolution is performed on the region [1,−2,1] to obtain the second-order differential features of each point. It is used to characterize the pressure curve in the first... The curvature of a point ;

[0035] Second-order differential eigenvector The h-th element is represented as:

[0036]

[0037] S22. Based on the characteristics of first-order differentials and second-order differential features Generate a single measurement point feature vector;

[0038] In S22, the first A twelve-dimensional feature row vector is constructed from each pressure measurement point. It is divided into three categories. The first category is the basic feature: one-dimensional feature row vector. , For the incoming Mach number, the two-dimensional feature row vector , For airfoil angle of attack, three-dimensional characteristic row vector Four-dimensional feature row vectors The second type is first-order differential neighborhood features: five-dimensional feature row vectors. Six-dimensional feature row vector Seven-dimensional feature row vector Eight-dimensional feature row vectors Nine-dimensional feature row vector The third category is the second-order differential neighborhood feature: , , ;

[0039] For edge pressure measurement points (without complete neighboring points), their missing first / second-order differential features are filled with zero values;

[0040] S23. Construct a global feature matrix for all Repeat step S22 at each pressure measurement point to generate... 3D feature matrix , Features.

[0041] Furthermore, step S3 includes the following steps:

[0042] S31. For the first test, the tail rake pressure measurement data from the test trains conducted in the early stage of the test were selected as training samples;

[0043] S32. A semi-intelligent screening method combined with manual verification is adopted to accurately determine the location of the wake region of each pressure measurement point in the sample, and a wake region determination label is set, that is, a label for the pressure measurement point in the wake region. Pressure measurement points in non-wake regions are labeled. This forms a label column vector. .

[0044] Furthermore, step S4 includes the following steps:

[0045] S41. Divide the data into feature matrices. With label column vector The sample set was divided into a training set and a validation set in a 7:3 ratio.

[0046] S42. A supervised classification algorithm is used to train the model on the training set, and the model performance is evaluated using the validation set;

[0047] S43. Determine accuracy using the validation set. As a threshold for model effectiveness, the optimal model is selected, i.e., accuracy. The highest-performing model is used as the benchmark model for wake region detection;

[0048]

[0049] in, This represents the number of samples that are both actually wheezes and predicted to be wheezes. This represents the number of samples that are actually non-wheeze regions and are predicted to be non-wheeze regions. This represents the number of samples that are actually wake regions but are predicted to be non-wake regions. This represents the number of samples that are actually non-whet regions but are predicted to be whet regions.

[0050] Furthermore, step S5 includes the following steps:

[0051] S51. Repeat steps S1-S2 for the tail rake pressure data of the new test run to generate a new feature matrix. ;

[0052] S52. Transform the new feature matrix Input the wake region detection benchmark model determined in step S4, and output the wake region judgment label for each pressure measurement point. ;

[0053] S53. Determine the label based on the wake region of each pressure measurement point. Based on the distribution characteristics, the critical point where it transitions from 0 to 1 is extracted as the boundary of the wake region.

[0054] Furthermore, step S6 includes the following steps:

[0055] S61. Perform result verification, manually review the boundary of the wake region output in step S5, and identify misjudged labels;

[0056] S62. Correct the misclassified labels, and merge the new samples containing the new feature matrix and the corrected labels into the historical sample set to obtain the updated sample set;

[0057] S63. Repeat step S4 to train the baseline model for wake region detection based on the updated sample set, generate an optimized model, and achieve continuous iteration of model performance.

[0058] The beneficial effects of the present invention are as follows: The present invention realizes intelligent and high-precision determination of the boundary of the wake region and improves the adaptability of the method to different test conditions. Attached Figure Description

[0059] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings:

[0060] Figure 1 This is a flowchart illustrating an intelligent method for detecting trail regions based on convolution and machine learning.

[0061] Figure 2 This is a schematic diagram comparing the normalized pressure coefficient and the wake region label of this invention. Detailed Implementation

[0062] To make the technical solutions and advantages of the embodiments of the present invention clearer, the exemplary embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not an exhaustive list of all embodiments. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0063] refer to Figure 1 and Figure 2 This embodiment describes an intelligent method for detecting tail regions based on convolution and machine learning, specifically including the following steps:

[0064] S1. Standardize the tail rake pressure measurement data to eliminate the influence of differences in test conditions on data characteristics and obtain a normalized pressure coefficient vector.

[0065] S2. Based on the normalized pressure coefficient vector, extract the local key features of the pressure distribution curve using the convolution method, construct a multi-dimensional feature vector, and generate a feature matrix;

[0066] S3. Select tail rake pressure data from previous test runs as training samples, assign wake region judgment labels to the feature matrix, and form a label column vector;

[0067] S4. Divide the sample set constructed based on the feature matrix and label column vector into a training set and a validation set. Use a supervised classification algorithm to train the training set, evaluate the model performance through the validation set, and select the optimal model as the benchmark model for wake region detection.

[0068] S5. Based on the wake zone detection benchmark model, intelligently predict the tail rake pressure data of the new test train and determine the wake zone boundary;

[0069] S6. By incrementally learning, the generalization ability of the model is continuously improved, and the performance of the baseline model for wake region detection is continuously iterated, thereby further improving the accuracy of the wake region boundary.

[0070] Furthermore, step S1 includes the following steps:

[0071] S11. Collect raw data from the tail rake pressure measurement points. The tail rake includes... The pressure measurement point, the first The spatial coordinates of the pressure measurement points are: Its unit is m, and the measured pressure is Its unit is Pa;

[0072] S12. Based on the incoming flow parameters from step S11, calculate the first... Pressure coefficient at each pressure measuring point ;

[0073] In S12, the first Pressure coefficient at each pressure measuring point Represented as:

[0074]

[0075] in, The static pressure of the incoming flow is expressed in Pa. The pressure is the flow pressure, and its unit is Pa;

[0076] S13. Normalize the spatial coordinates of the pressure measurement points to obtain normalized coordinates based on the airfoil chord length c. and for the first Pressure coefficient at each pressure measuring point Normalization is performed to obtain the normalized pressure coefficient vector. ;

[0077] In S13, the normalized coordinates Represented as:

[0078]

[0079] Normalized pressure coefficient vector Represented as:

[0080]

[0081]

[0082]

[0083] in, For the first Pressure coefficient at each pressure measuring point The minimum value, For the first Pressure coefficient at each pressure measuring point The maximum value.

[0084] Specifically, the standardization process includes collecting raw data from the tail rake pressure measurement points, calculating the pressure coefficient, location coordinates, and normalizing the pressure coefficient data.

[0085] Furthermore, step S2 includes the following steps:

[0086] S21. For the normalized pressure coefficient vector Local feature extraction is performed using differential convolution kernels to obtain first-order differential features. and second-order differential features ;

[0087] In S21, a first-order difference convolution kernel is used. Convolution is performed on the interval [-1, 0, 1] to obtain the first-order differential features of each point. It is used to characterize the pressure curve in the first... gradient at a point ;

[0088] The h-th element of the first-order differential eigenvector is represented as:

[0089]

[0090] in, Normalized pressure coefficient vector No. item, , ,and It is an integer;

[0091] Using second-order difference convolution kernel Convolution is performed on the region [1,−2,1] to obtain the second-order differential features of each point. It is used to characterize the pressure curve in the first... The curvature of a point ;

[0092] Second-order differential eigenvector The h-th element is represented as:

[0093]

[0094] S22. Based on the characteristics of first-order differentials and second-order differential features Generate a single measurement point feature vector;

[0095] In S22, the first A twelve-dimensional feature row vector is constructed from each pressure measurement point. It is divided into three categories. The first category is the basic feature: one-dimensional feature row vector. , For the incoming Mach number, the two-dimensional feature row vector , For airfoil angle of attack, three-dimensional characteristic row vector Four-dimensional feature row vectors The second type is first-order differential neighborhood features: five-dimensional feature row vectors. Six-dimensional feature row vector Seven-dimensional feature row vector Eight-dimensional feature row vectors Nine-dimensional feature row vector (The second category covers the first-order differential features of the current point and its two left and right neighbors); the third category is the second-order differential neighborhood features: , , (The third category covers the second-order differential features of the current point and one neighboring point on each side).

[0096] For edge pressure measurement points (without complete neighboring points), their missing first / second-order differential features are filled with zero values;

[0097] S23. Construct a global feature matrix for all Repeat step S22 at each pressure measurement point to generate... 3D feature matrix , Features.

[0098] Specifically, the method extracts key local features of the pressure distribution curve based on convolution, including using first-order and second-order difference convolution kernels to extract local features for the normalized pressure coefficient vector.

[0099] Furthermore, step S3 includes the following steps:

[0100] S31. For the first test, the tail rake pressure measurement data from the test trains conducted in the early stage of the test were selected as training samples;

[0101] S32. A semi-intelligent screening method combined with manual verification is adopted to accurately determine the location of the wake region of each pressure measurement point in the sample, and a wake region determination label is set, that is, the pressure measurement point label of the wake region (including the boundary). Pressure measurement points in non-wake regions are labeled. This forms a label column vector. .

[0102] Furthermore, step S4 includes the following steps:

[0103] S41. Divide the data into feature matrices. With label column vector The sample set was divided into a training set and a validation set in a 7:3 ratio.

[0104] S42. Use supervised classification algorithms (including but not limited to decision trees, logistic regression, and support vector machines) to train the training set and evaluate the model performance using the validation set;

[0105] S43. Determine accuracy using the validation set. As a threshold for model effectiveness, the optimal model is selected, i.e., accuracy. The highest-performing model is used as the benchmark model for wake region detection;

[0106]

[0107] in, This represents the number of samples that are both actually wheezes and predicted to be wheezes. This represents the number of samples that are actually non-wheeze regions and are predicted to be non-wheeze regions. This represents the number of samples that are actually wake regions but are predicted to be non-wake regions. This represents the number of samples that are actually non-whet regions but are predicted to be whet regions.

[0108] Furthermore, step S5 includes the following steps:

[0109] S51. Repeat steps S1-S2 for the tail rake pressure data of the new test run to generate a new feature matrix. ;

[0110] S52. Transform the new feature matrix Input the wake region detection benchmark model determined in step S4, and output the wake region judgment label for each pressure measurement point. ;

[0111] S53. Determine the label based on the wake region of each pressure measurement point. Based on the distribution characteristics, the critical point where it transitions from 0 to 1 is extracted as the boundary of the wake region.

[0112] Furthermore, step S6 includes the following steps:

[0113] S61. Perform result verification, manually review the boundary of the wake region output in step S5, and identify misjudged labels;

[0114] S62. Correct the misclassified labels, and merge the new samples containing the new feature matrix and the corrected labels into the historical sample set to obtain the updated sample set;

[0115] S63. Repeat step S4 to train the baseline model for wake region detection based on the updated sample set, generate an optimized model, and achieve continuous iteration of model performance.

[0116] Although the invention has been described with reference to a limited number of embodiments, those skilled in the art will understand from the foregoing description that other embodiments are conceivable within the scope of the invention described herein. Furthermore, it should be noted that the language used in this specification has been chosen primarily for readability and instructional purposes, and not for the purpose of interpreting or limiting the subject matter of the invention. Therefore, many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the appended claims. The disclosure of the invention is illustrative and not restrictive, and the scope of the invention is defined by the appended claims.

Claims

1. A method for intelligent detection of trail regions based on convolution and machine learning, characterized in that, Includes the following steps: S1. Standardize the tail rake pressure measurement data to eliminate the influence of differences in test conditions on data characteristics and obtain a normalized pressure coefficient vector. S2. Based on the normalized pressure coefficient vector, extract the local key features of the pressure distribution curve using the convolution method, construct a multi-dimensional feature vector, and generate a feature matrix; S3. Select tail rake pressure data from previous test runs as training samples, assign wake region judgment labels to the feature matrix, and form a label column vector; S4. Divide the sample set constructed based on the feature matrix and label column vector into a training set and a validation set. Use a supervised classification algorithm to train the training set, evaluate the model performance through the validation set, and select the optimal model as the benchmark model for wake region detection. S5. Based on the wake zone detection benchmark model, intelligently predict the tail rake pressure data of the new test train and determine the wake zone boundary; S6. By incrementally learning, the generalization ability of the model is continuously improved, and the performance of the baseline model for wake region detection is continuously iterated, thereby further improving the accuracy of the wake region boundary. S5 includes the following steps: S51. Repeat steps S1-S2 for the tail rake pressure data of the new test run to generate a new feature matrix. ; S52. Transform the new feature matrix Input the wake region detection benchmark model determined in step S4, and output the wake region judgment label for each pressure measurement point. ; S53. Determine the label based on the wake region of each pressure measurement point. Based on the distribution characteristics, the critical point where it transitions from 0 to 1 is extracted as the boundary of the wake region.

2. The intelligent tail region detection method based on convolution and machine learning according to claim 1, characterized in that, S1 includes the following steps: S11. Collect raw data from the tail rake pressure measurement points. The tail rake includes... The pressure measurement point, the first The spatial coordinates of the pressure measurement points are: Its unit is m, and the measured pressure is Its unit is Pa; S12. Based on the incoming flow parameters from step S11, calculate the first... Pressure coefficient at each pressure measuring point ; In S12, the first Pressure coefficient at each pressure measuring point Represented as: in, The static pressure of the incoming flow is expressed in Pa. The pressure is the flow pressure, and its unit is Pa; S13. Normalize the spatial coordinates of the pressure measurement points to obtain normalized coordinates based on the airfoil chord length c. and for the first Pressure coefficient at each pressure measuring point Normalization is performed to obtain the normalized pressure coefficient vector. ; In S13, the normalized coordinates Represented as: Normalized pressure coefficient vector Represented as: in, For the first Pressure coefficient at each pressure measuring point The minimum value, For the first Pressure coefficient at each pressure measuring point The maximum value.

3. The intelligent tail region detection method based on convolution and machine learning according to claim 2, characterized in that, S2 includes the following steps: S21. For the normalized pressure coefficient vector Local feature extraction is performed using differential convolution kernels to obtain first-order differential features. and second-order differential features ; In S21, a first-order difference convolution kernel is used. Convolution is performed on the interval [-1, 0, 1] to obtain the first-order differential features of each point. It is used to characterize the pressure curve in the first... gradient at a point ; The h-th element of the first-order differential eigenvector is represented as: in, Normalized pressure coefficient vector No. item, , ,and It is an integer; Using second-order difference convolution kernel Convolution is performed on the region [1,−2,1] to obtain the second-order differential features of each point. It is used to characterize the pressure curve in the first... The curvature of a point ; Second-order differential eigenvector The h-th element is represented as: S22. Based on the characteristics of first-order differentials and second-order differential features Generate a single measurement point feature vector; In S22, the first A twelve-dimensional feature row vector is constructed from each pressure measurement point. It is divided into three categories. The first category is the basic feature: one-dimensional feature row vector. , For the incoming Mach number, the two-dimensional feature row vector , For airfoil angle of attack, three-dimensional characteristic row vector Four-dimensional feature row vectors The second type is first-order differential neighborhood features: five-dimensional feature row vectors. Six-dimensional feature row vector Seven-dimensional feature row vector Eight-dimensional feature row vectors Nine-dimensional feature row vector The third category is the second-order differential neighborhood feature: , , ; For edge pressure measurement points, the missing first / second derivative features are filled with zero values; S23. Construct a global feature matrix for all Repeat step S22 at each pressure measurement point to generate... 3D feature matrix , Features.

4. The intelligent tail region detection method based on convolution and machine learning according to claim 3, characterized in that, S3 includes the following steps: S31. For the first test, the tail rake pressure measurement data from the test trains conducted in the early stage of the test were selected as training samples; S32. A semi-intelligent screening method combined with manual verification is adopted to accurately determine the location of the wake region of each pressure measurement point in the sample, and a wake region determination label is set, that is, a label for the pressure measurement point in the wake region. Pressure measurement points in non-wake regions are labeled. This forms a label column vector. .

5. The intelligent detection method for trail regions based on convolution and machine learning according to claim 4, characterized in that, S4 includes the following steps: S41. Divide the data into feature matrices. With label column vector The sample set was divided into a training set and a validation set in a 7:3 ratio. S42. A supervised classification algorithm is used to train the model on the training set, and the model performance is evaluated using the validation set; S43. Determine accuracy using the validation set. As a threshold for model effectiveness, the optimal model is selected, i.e., accuracy. The highest-performing model is used as the benchmark model for wake region detection; in, This represents the number of samples that are both actually wheezes and predicted to be wheezes. This represents the number of samples that are actually non-wheeze regions and are predicted to be non-wheeze regions. This represents the number of samples that are actually wake regions but are predicted to be non-wake regions. This represents the number of samples that are actually non-whet regions but are predicted to be whet regions.

6. The intelligent detection method for trail regions based on convolution and machine learning according to claim 5, characterized in that, S6 includes the following steps: S61. Perform result verification, manually review the boundary of the wake region output in step S5, and identify misjudged labels; S62. Correct the misclassified labels, and merge the new samples containing the new feature matrix and the corrected labels into the historical sample set to obtain the updated sample set; S63. Repeat step S4 to train the baseline model for wake region detection based on the updated sample set, generate an optimized model, and achieve continuous iteration of model performance.

Images