Airplane clear sky bumping prediction method, device, equipment, medium and product

Abstract

The invention discloses an aircraft clear sky bumping prediction method, device, equipment, medium and product, and relates to the field of aeronautical meteorology, the method comprises the following steps: obtaining a sample set, the sample set comprising a plurality of samples, one sample comprising bumping observation data when a sample aircraft flies at the same time and in the same space and values of meteorological data; calculating the value of each CAT diagnosis index according to the value of each meteorological data corresponding to the sample to obtain a CAT diagnosis value sequence corresponding to the sample; constructing a total data set according to the CAT diagnosis value sequence corresponding to each sample and the jolt observation data corresponding to each sample; sequentially performing data quality control, replacement of the bumping observation data with the turbulence label and oversampling processing on the total data set to obtain a data set; the W-KNN model is trained and verified through the data set to obtain a clear sky bumping prediction model, the clear sky bumping prediction model is used for predicting the clear sky bumping of the aircraft to be predicted, and the accuracy of the clear sky bumping prediction result can be improved.

Description

Technical Field

[0001] The present application relates to the field of aviation meteorology, and in particular to a method, device, equipment, medium and product for predicting clear-air turbulence of an aircraft. Background Art

[0002] With the intensification of climate change, the probability of clear air turbulence (CAT) in the future is increasing. CAT refers to turbulence that occurs in the absence of significant clouds or weather systems. It is composed of vortex airflows of different scales and changes over time. The direction of turbulence is from large scale to small scale. CAT is one of the dangerous meteorological phenomena in aviation. It poses a major threat to the safety of aircraft and is prone to cause clear air turbulence. Clear air turbulence can easily cause injuries to passengers and crew members. Therefore, it is very important to predict clear air turbulence. However, the existing methods for predicting clear air turbulence do not accurately predict the results. Summary of the invention

[0003] The purpose of this application is to provide an aircraft clear air turbulence prediction method, device, equipment, medium and product, which can improve the accuracy of clear air turbulence prediction results.

[0004] To achieve the above objectives, this application provides the following solutions:

[0005] In a first aspect, the present application provides a method for predicting clear-air turbulence of an aircraft, comprising:

[0006] Acquire a sample set, the sample set comprising a plurality of samples, one sample comprising turbulence observation data and values ​​of various meteorological data when the sample aircraft flies at the same time and in the same space;

[0007] For any sample, the values ​​of each CAT diagnostic index are calculated according to the values ​​of each meteorological data corresponding to the sample to obtain the CAT diagnostic value sequence corresponding to the sample;

[0008] The total data set is constructed based on the CAT diagnostic value sequence corresponding to each sample and the bump observation data corresponding to each sample;

[0009] The total data set is sequentially preprocessed and oversampled to obtain a data set; the preprocessing includes sequentially performing data quality control and replacing turbulence observation data with turbulence labels;

[0010] The W-KNN model is trained and verified using a data set to obtain a clear-air turbulence prediction model, which is used to predict clear-air turbulence of an aircraft to be predicted.

[0011] In a second aspect, the present application provides an aircraft clear air turbulence prediction device, comprising:

[0012] An acquisition module, used for acquiring a sample set, wherein the sample set includes a plurality of samples, and one sample includes turbulence observation data and values ​​of various meteorological data when the sample aircraft flies at the same time and the same space;

[0013] A CAT diagnostic value calculation module is used to calculate the values ​​of each CAT diagnostic index according to the values ​​of each meteorological data corresponding to the sample for any sample to obtain a CAT diagnostic value sequence corresponding to the sample;

[0014] A total data set construction module is used to construct a total data set according to the CAT diagnostic value sequence corresponding to each sample and the bump observation data corresponding to each sample;

[0015] A data set determination module, used for sequentially performing preprocessing and oversampling processing on the total data set to obtain a data set; the preprocessing includes sequentially performing data quality control and replacing turbulence observation data with turbulence labels;

[0016] The clear air turbulence prediction model determination module is used to train and verify the W-KNN model using a data set to obtain a clear air turbulence prediction model, wherein the clear air turbulence prediction model is used to predict the clear air turbulence of the aircraft to be predicted.

[0017] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described aircraft clear air turbulence prediction methods.

[0018] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described methods for predicting clear air turbulence.

[0019] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned aircraft clear air turbulence prediction methods.

[0020] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0021] The present application provides a method, device, equipment, medium and product for predicting clear-air turbulence of an aircraft. The numerical value of each CAT diagnostic index is calculated according to the value of each meteorological data corresponding to the sample to obtain a CAT diagnostic value sequence corresponding to the sample; a total data set is constructed according to the CAT diagnostic value sequence corresponding to each sample and the turbulence observation data corresponding to each sample; the total data set is subjected to data quality control, turbulence observation data is replaced with turbulence labels and oversampling processing in sequence to obtain a data set; the W-KNN model is trained and verified using the data set to obtain a clear-air turbulence prediction model, and the clear-air turbulence prediction model is used to predict the clear-air turbulence of the aircraft to be predicted; the traditional method needs to define a turbulence threshold before predicting turbulence, and the turbulence threshold is not uniform and mainly depends on climate model data, and the turbulence intensity predicted by the traditional empirical model or its derived integrated CAT forecast model is inconsistent for aircraft models of different weights, so the traditional turbulence prediction method is affected by the turbulence threshold and the different aircraft models, resulting in inaccurate prediction results. To this end, ICAO stipulates that the eddy dissipation rate (EDR) is used as a turbulence measurement indicator, but with the challenges related to data quality control and the inherent limitations of physical models, the accuracy of EDR estimates has also been affected. The clear air turbulence prediction method proposed in the present invention does not require the application of turbulence thresholds and aircraft model data, so it will not be affected by different turbulence thresholds and aircraft models, thereby improving the accuracy of clear air turbulence prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 This is an application environment diagram of an aircraft clear sky turbulence prediction method in one embodiment of the present application;

[0024] Figure 2 A schematic diagram of a flow chart of a method for predicting clear-air turbulence of an aircraft provided in one embodiment of the present application;

[0025] Figure 3 A flowchart of using an aircraft clear-air turbulence prediction method to predict A320 aircraft according to an embodiment of the present application;

[0026] Figure 4 Validate the ROC curve of the A320 test dataset for the W-KNN model;

[0027] Figure 5 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0029] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0030] Although a variety of CAT diagnostic indices have been developed, since different indices focus on different factors, the forecast effects of clear air turbulence in different regions, seasons and causes will also be different. Therefore, it is particularly important to improve the index forecast algorithm to make it more suitable for predicting clear air turbulence under different conditions. This improvement will help improve flight safety and reduce the risks and losses caused by turbulent events. Based on this, the present application provides an aircraft clear air turbulence prediction method. The aircraft clear air turbulence prediction method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send a sample set to the server 104. After the server 104 receives the sample set, for any sample, the server 104 calculates the value of each CAT diagnostic index according to the value of each meteorological data corresponding to the sample to obtain the CAT diagnostic value sequence corresponding to the sample; constructs a total data set according to the CAT diagnostic value sequence corresponding to each sample and the turbulence observation data corresponding to each sample; pre-processes and oversamples the total data set in sequence to obtain a data set; the pre-processing includes sequentially performing data quality control and replacing turbulence observation data with turbulence labels; the W-KNN model is trained and verified using the data set to obtain a clear air turbulence prediction model. The server 104 can feed back the obtained clear air turbulence prediction model to the terminal 102. In addition, in some embodiments, the aircraft clear-air turbulence prediction method may also be implemented independently by the server 104 or the terminal 102. For example, the terminal 102 may directly perform an aircraft clear-air turbulence prediction for a sample set, or the server 104 may obtain a sample set from a data storage system and perform an aircraft clear-air turbulence prediction for the sample set.

[0031] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0032] In an exemplary embodiment, Figure 2 As shown, a method for predicting clear-air turbulence of an aircraft is provided. The method is executed by a computer device, and specifically can be executed by a computer device such as a terminal or a server alone, or can be executed by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate the method, which includes the following steps. Among them:

[0033] Step 201, obtain a sample set, the sample set includes multiple samples, one sample includes turbulence observation data and values ​​of various meteorological data when the sample aircraft flies at the same time and the same space. The meteorological data is meteorological data with FL≥200, including: temperature, longitudinal wind speed, latitudinal wind speed, vertical wind speed, gravity potential and other meteorological factors.

[0034] Step 202: For any sample, the values ​​of each CAT diagnostic index are calculated according to the values ​​of each meteorological data corresponding to the sample to obtain the CAT diagnostic value sequence corresponding to the sample. The CAT diagnostic index includes 8 indices: eddy dissipation rate (EDR), Richardson number (Ri), Ellrod turbulence index (Ellrod1), relative vorticity square (VOSQ), nonlinear balance equation residual (UBF), vertical wind shear (VWS), horizontal temperature gradient (TEMPG) and Brown energy dissipation index (Brown2). Table 1 is the detailed information of the above 8 indices, including the weight WG corresponding to each index. s .

[0035] Table 1 8 CAT diagnoses and their corresponding weights

[0036]

[0037] EDR Index C kp is the Kolmogorov-Prandtl constant, ε is the eddy dissipation, ε(z) is the eddy dissipation of the aircraft at a given height z, TKE(z) is the turbulent kinetic energy of the aircraft at a given height z, TKE is the turbulent kinetic energy of the aircraft, u' and w' are the disturbances of the zonal and vertical wind components at the aircraft's location, It represents the average value of -u'w'. U is the total wind speed, N is the Brunt-Vaisala frequency, x is the longitude of the aircraft, y is the latitude of the aircraft, is the Laplace operator, Φ is the potential, J() is the Jacob operator, f and β are the Coriolis parameters and their latitudinal derivatives, ζ a is the absolute vorticity of the aircraft, S V is the vertical wind shear at the aircraft's location, ζ is the aircraft's relative vorticity, u is the aircraft's location's meridional wind, v is the aircraft's location's zonal wind, and T is the aircraft's location's temperature.

[0038] Step 203: construct a total data set according to the CAT diagnostic value sequence corresponding to each sample and the bump observation data corresponding to each sample.

[0039] Step 204, preprocessing and oversampling the total data set in sequence to obtain a data set; the preprocessing includes sequentially performing data quality control (deleting duplicate values ​​and missing values) and replacing turbulence observation data with turbulence labels.

[0040] Step 205, using the data set to train and verify the W-KNN model to obtain a clear-air turbulence prediction model, wherein the clear-air turbulence prediction model is used to predict the clear-air turbulence of the aircraft to be predicted.

[0041] Implementing the above steps 201 to 205 can improve the accuracy of the clear air turbulence prediction results.

[0042] In another exemplary embodiment of the present application, a total data set is constructed according to the CAT diagnostic value sequence corresponding to each sample and the bump observation data corresponding to each sample, specifically including:

[0043] The CAT diagnostic value sequence corresponding to each sample is interpolated (implemented using the 'RegularGridInterpolator' function in python, which is essentially a bilinear interpolation and vertical interpolation method to unify the resolution of meteorological data and observation data) to obtain the numerical sequence of the CAT diagnostic index corresponding to each sample after interpolation.

[0044] The total data set is constructed based on the numerical sequence of the CAT diagnostic index after interpolation processing corresponding to each sample and the bumpy observation data corresponding to each sample.

[0045] In practical applications, the operations of replacing turbulence observation data with turbulence labels include:

[0046] (1) Use regular expressions to convert the turbulence intensity characters recorded in the turbulence observation data into digital labels, for example: NEG (negative) → 0, LGT (light) → 1, LGT-MOD → 2, MOD → 3, MOD-SEV → 4, SEV → 5, where MOD (moderate) and SEV (severe).

[0047] (2) Define turbulence labels used to characterize different turbulence intensities. Turbulence label 0 represents no turbulence events, i.e., 0 in (1). Turbulence label 1 represents moderate or greater turbulence events, i.e., 3 to 5 in (1), as shown in formula (1):

[0048]

[0049] (3) Convert the digital labels into turbulent labels according to the definition in (2).

[0050] In practical applications, oversampling is performed using the Synthetic Minority Over-sampling Technique (SMOTE) algorithm to handle sample class imbalance. The specific steps are as follows:

[0051] (1) For each sample point x (CAT diagnostic value sequence and turbulence label corresponding to the sample) in the minority class (the turbulence label is 0), calculate the distance between the sample point and other sample points y in the minority class to obtain K nearest neighbors. Usually, the Euclidean distance is used, and the formula is as follows:

[0052]

[0053] Among them, n represents the total number of features, F xj represents the value of x on the jth feature, F yj represents the value of y on the jth feature, where the feature here refers to the 8 CAT diagnoses.

[0054] (2) According to the sample imbalance ratio, a sampling ratio is set to determine the sampling rate. For x, a number of sample points are randomly selected from K' neighbors. Assume that the selected neighbor is x*.

[0055] (3) For each randomly selected neighbor x*, use the following formula to construct a new sample point with x:

[0056] x new =x+rand(0,1)*(x * -x) (3)

[0057] Among them, x newFor the new sample point, rand(0,1) generates a random number between 0 and 1, which determines the proportion of the step in the direction of x*.

[0058] In another exemplary embodiment of the present application, a clear-air turbulence prediction model is obtained by training and verifying the W-KNN model using a data set, specifically including:

[0059] The data set is divided into a training set and a test set. The random seed number is set, and the data set is divided into a training set and a test set according to the random seed number in a ratio of 8:2. Setting the same random seed number can ensure that the data is consistent each time the data set is divided, so that the evaluation results of the model can be reproduced.

[0060] The W-KNN model is trained and verified using a test set and a training set to obtain a clear-air turbulence prediction model, wherein the clear-air turbulence prediction model is used to predict clear-air turbulence of an aircraft to be predicted.

[0061] In another exemplary embodiment of the present application, the W-KNN model is trained and verified using a test set and a training set to obtain a clear-air turbulence prediction model, specifically including:

[0062] The training set is standardized to obtain a standardized training set. Only the training set is standardized to avoid directly standardizing all data sets, which may cause data information leakage. The purpose of standardization is to eliminate the dimensional differences between different features, scale the data features, and improve the performance of the W-KNN algorithm. The following formula is used to standardize the data Z-score: Where z is the normalized value; x is the original data value; μ is the mean of the data; and σ is the standard deviation of the data.

[0063] The standardized training set was processed using 10-fold cross validation to estimate the hyperparameter values ​​of the W-KNN model. The hyperparameters include: "n_neighbors" (i.e., K value), "weights" (weight function), "algorithm" (neighbor search algorithm), "leaf_size" (leaf node size), and "p" (distance metric parameter).

[0064] The W-KNN model determined by the hyperparameter values ​​was verified using standardized training sets and test sets to obtain the clear air turbulence prediction model.

[0065] In another exemplary embodiment of the present application, a 10-fold cross validation is used to process the standardized training set to estimate the hyperparameter values ​​of the W-KNN model, specifically including:

[0066] In the random search algorithm, set up 10-fold cross validation to search for the optimal hyperparameter values: pre-set a list of hyperparameter values, such as the number of neighbors "n_neighbors": range(100); weight function "weights": ['uniform', 'distance']; KNN search algorithm for accelerating the nearest neighbor search "algorithm": ['auto', 'ball_tree', 'kd_tree']; leaf node size "leaf_size": [10, 20, 30, 40] for controlling the construction of KD trees and ball trees, which can affect query speed and memory consumption; distance metric parameter "p": [1, 2, 3, 4, 5], etc.; then divide the standardized training set into 10 subsets of equal size, 9 of which are used to train the model and one subset is used to test the model. Repeat this process 10 times, each time selecting a different subset as the 10-fold cross validation test set, and the rest as the 10-fold cross validation training set, and find the hyperparameter value that can make the model perform best through network search.

[0067] In another exemplary embodiment of the present application, a W-KNN model determined by a standardized training set and a test set is used to verify the hyperparameter value to obtain a clear air turbulence prediction model, which specifically includes:

[0068] The standardized training set is used to predict the turbulence label of each sample in the test set to obtain the predicted turbulence label of each sample in the test set.

[0069] The predicted turbulence labels of each sample in the test set and the turbulence labels of each sample in the test set are used to verify the W-KNN model determined by the hyperparameter values ​​to obtain the clear air turbulence prediction model.

[0070] In another exemplary embodiment of the present application, the turbulence label of each sample in the test set is predicted by using a standardized training set to obtain a predicted turbulence label of each sample in the test set, specifically including:

[0071] For any sample in the test set, the Manhattan distance between the CAT diagnostic value sequence corresponding to the sample and the CAT diagnostic value sequence corresponding to each sample in the standardized training set is calculated to obtain a distance sequence.

[0072] All Manhattan distances in the distance sequence are sorted from small to large to obtain a sorted distance sequence.

[0073] The turbulence labels of each sample corresponding to the first K Manhattan distances of the sorted distance sequence in the standardized training set are selected to obtain the turbulence label set; K is the K value in the W-KNN model determined by the hyperparameter value.

[0074] The turbulence label set is processed by using a weighted voting method to obtain the predicted turbulence label of the sample.

[0075] This application utilizes the advantages of the weighted K nearest neighbor (W-KNN) algorithm, which is non-parametric and considers feature weights, to effectively capture clear-air turbulence and improve prediction accuracy.

[0076] The present application also provides an embodiment of applying the aircraft clear air turbulence prediction method provided in the above embodiment to an A320 aircraft, such as Figure 3 As shown, the specific steps are:

[0077] Step A1: Obtain A320 aircraft turbulence observation data for a certain region for consecutive years, such as pilot reports or aircraft onboard data.

[0078] Step A2: Filter and download meteorological data with the same spatiotemporal characteristics as the data in step A1, and then calculate the value of the CAT diagnostic index through the above meteorological data to obtain a CAT diagnostic value sequence.

[0079] Step A3: The above CAT diagnostic value sequence uses the time, pressure altitude layer, longitude and latitude in the pilot report data as the target interpolation point through bilinear interpolation and vertical interpolation methods, and uses the RegularGridInterpolator function to obtain the numerical unified spatiotemporal characteristics of the 8 CAT diagnostic indexes at each point, and then the turbulence intensity field in the turbulence observation data and the numerical sequence of the CAT diagnostic index after interpolation are combined into a total data set R. R is a two-dimensional matrix containing 13 columns of data, that is, a set consisting of the time, altitude, longitude and latitude, the numerical sequence of the CAT diagnostic index after interpolation, and the turbulence intensity field obtained by the above method.

[0080] Step A4: Perform quality control on the total data set (remove duplicate values ​​and missing values) to avoid affecting the predictive performance of the model, and then use regular expressions to convert the turbulence intensity into numbers. Specifically, use the python 're' library to convert the characters recording the turbulence intensity level in the pilot report data into digital labels, such as: 'NEG'→0, 'LGT'→1, 'LGT-MOD'→2, 'MOD'→3, 'MOD-SEV'→4, 'SEV'→5, 'EXT'→6.

[0081] Step A5: Define turbulence labels for characterizing different turbulence intensities. Turbulence label 0 represents no turbulence event, i.e., 0 in step A4; turbulence label 1 represents moderate or greater turbulence events, i.e., 3 to 6 in step A4, as shown in formula (1).

[0082] Step A6: Convert the digital labels into turbulent labels according to the definition in step A5.

[0083] Step A7: The processed total data set obtained in step A6 is subjected to oversampling processing using the SMOTE algorithm to obtain a data set.

[0084] Step A8: Then set the ratio of training set to test set to 8:2, and divide the data set into training set and test set according to the ratio.

[0085] Step A9: Use a standardized method to normalize the training set to obtain a standardized training set.

[0086] Step A10: Use 10-fold cross validation to divide the standardized training set into 10 subsets of equal size, 9 of which are used to train the model and 1 subset is used to test the model. Repeat this process 10 times, each time selecting a different subset as the 10-fold cross validation test set and the rest as the 10-fold cross validation training set.

[0087] Step A11: Establish a clear air turbulence prediction model based on the W-KNN algorithm.

[0088] Step A12: Preset parameter value list, such as number of neighbors "n_neighbors": range(100); weight function "weights": ['uniform', 'distance']; KNN search algorithm for accelerating nearest neighbor search "algorithm": ['auto', 'ball_tree', 'kd_tree']; leaf node size "leaf_size": [10, 20, 30, 40] for controlling the construction of KD tree and ball tree, which can affect query speed and memory consumption ]; distance measurement parameter "p": [1,2,3,4,5], etc., then train the model according to the 10-fold cross-validation training set data in step A10, and then test the trained model using the 10-fold cross-validation test set data in step A10; find the parameters that can make the model perform best through network search; research has found that when n_neighbors (ie, K value) = 27, weights = distance, algorithm = kd_tree, leaf_size = 20, and p = 1, the model has a better prediction effect.

[0089] Step A13: Evaluate the model obtained in step A12 using the test set in step A7.

[0090] (1) Let L be the training set L = {(Xi, yi), i = 1, ... n}, where Xi is the numerical sequence of the interpolated CAT diagnostic index corresponding to the i-th sample, and yi is the turbulence label corresponding to the i-th sample.

[0091] (2) Let Y be the numerical sequence of the interpolated CAT diagnostic index corresponding to any sample in the test set. The Manhattan distance from Y to each Xi in L in (1) is calculated as follows:

[0092]

[0093] Where N represents the total number of CAT diagnostic indexes in the numerical sequence of CAT diagnostic indexes after interpolation processing, Y s represents the value of the sth CAT diagnostic index in Y, X is Represents the value of the sth CAT diagnostic index in Xi.

[0094] (3) Sort the distances obtained from (2) from small to large, select the turbulence labels yi corresponding to the first K Manhattan distances to obtain the turbulence label set, and find the K neighborhoods P containing the CAT samples to be classified. k :

[0095]

[0096] (4) The receiver operating characteristic curve (ROC) is constructed using the known steps, and then the corresponding weight WG of the sth CAT diagnostic index is calculated using formula (7): s :

[0097]

[0098] Among them, AUC s Represents the area under the receiver operating characteristic curve (ROC) corresponding to the sth CAT diagnostic index.

[0099] The receiver operating characteristic (ROC) curve consists of 1-PODn (x-axis) and PODy (y-axis), which is calculated by counting the detection probability (PODy) of the predicted turbulence label as 1 and the detection probability (PODn) of the predicted turbulence label as 0 in the test set. When the model outputs a probability, different judgment thresholds will produce different PODy and 1-PODn. By plotting the PODy and 1-PODn points under multiple judgment thresholds and connecting these points, the ROC curve can be obtained.

[0100] (5) According to formula (8), the weighted voting method is used to process the turbulence label set to obtain the predicted turbulence label y corresponding to Y:

[0101]

[0102] Among them I c (s i ) indicates the category to which the i-th sample belongs, as shown below:

[0103]

[0104] Among them, c1 represents a turbulent event of moderate or above intensity, and c2 represents a turbulent event without any intensity.

[0105] (6) Model performance evaluation: The AUC value under the ROC curve is selected as the evaluation index of the clear air turbulence prediction model obtained in step A12.

[0106] The working principle of ROC is that as the judgment threshold changes, the ROC curve shows the relationship between PODy and 1-PODn. The closer the curve is to the upper left corner (the closer it is to 1, 0.5 is a random guess), the more perfect the prediction effect. The AUC value of the ROC curve is ultimately used as the performance skill score for turbulence forecasting. For each threshold, PODy and PODn can be defined as:

[0107]

[0108] Where a: the number of samples whose turbulence label is predicted to be positive and whose actual turbulence label is positive, b: the number of samples whose turbulence label is predicted to be positive but whose actual turbulence label is negative, c: the number of samples whose turbulence label is predicted to be negative but whose actual turbulence label is positive, d: the number of samples whose turbulence label is predicted to be negative and whose actual turbulence label is negative.

[0109] Figure 4 This is the ROC curve of the A320 test data set validated by the W-KNN model. The dotted line represents random guessing, and the area under the ROC curve (AUC) value reaches 0.97, indicating that the model has good classification prediction ability.

[0110] Furthermore, the maximum true skill statistics (TSS) score of each model, also known as the Hanssen-Kuipers (HK) discriminant, was calculated and defined as TSS = PODy + PODn-1. Its value range is -1 to 1, 1 means that the diagnostic model has perfect skill in classification prediction, and a value less than 0 represents a negative discrimination skill (0 means no skill). The area under the ROC curve (AUC) and the true skill score (MaxTSS) of different models predicting CAT are shown in Table 2.

[0111] Table 2 Area under the ROC curve (AUC) and true skill score (MaxTSS) of different models predicting CAT

[0112]

[0113] Table 2 shows the prediction evaluation of each forecast model for the selected A320 recorded clear air turbulence events. Weighted K-nearest neighbor (W-KNN), random forest (RF) and ensemble forecast model (CATavg) represent different forecast methods. The table compares the Max TSS values ​​obtained from different diagnostic model forecast methods. Among the single diagnostic models, the Ellrod1 index and the UBF index have the highest (0.272) and lowest (0.095) Max TSS values, respectively.

[0114] It is worth noting that the ensemble forecast model has a higher TSS value in turbulence prediction compared to the single diagnostic model. This is because the ensemble forecast improves the statistical performance by combining multiple turbulence generation mechanisms. Compared with the random forest and ensemble forecast models, the weighted K nearest neighbor (W-KNN) forecast model showed the highest TSS value in diagnosing moderate or greater turbulence events and no turbulence events. Specifically, the TSS value of the W-KNN forecast model increased from 0.315 of the ensemble forecast model to 0.825.

[0115] Compared with the ensemble prediction model, the W-KNN prediction model has a smaller computational cost and the prediction runtime efficiency is improved by 1.5 to 1.7 times. Through experimental comparison, the computational time of the ensemble prediction method increases linearly with the number of individual diagnoses used.

[0116] In general, the W-KNN prediction model not only ensures high prediction accuracy, but also significantly improves the computational efficiency, providing an effective technical means for the real-time prediction of clear air turbulence. In summary, the aircraft clear air turbulence prediction method provided in this embodiment greatly improves the ability to capture CAT, providing a safety guarantee for coping with the intensification of clear air turbulence in the future. It can also provide practical reference for pilots flying A320 aircraft before takeoff, thereby improving the aviation safety factor and reducing economic costs. This has important practical significance for ensuring the safety and efficiency of civil aviation transportation.

[0117] This application comprehensively considers the impact of factors such as horizontal and vertical wind shear, horizontal and vertical temperature gradients, and local temperature changes on CAT intensity, thereby increasing the accuracy of turbulence prediction. At the same time, the W-KNN algorithm with optimized parameters is used for model training, which reduces the model complexity and training time, and can obtain the prediction results of aircraft clear air turbulence more quickly. The oversampling technology of the SMOTE algorithm is used to process the data set to avoid the impact of the imbalance problem of data sample categories on the performance of the model, thereby improving the accuracy and reliability of the model.

[0118] Based on the same inventive concept, the embodiment of the present application also provides an aircraft clear air turbulence prediction device for implementing the above-mentioned aircraft clear air turbulence prediction method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more embodiments of the aircraft clear air turbulence prediction device provided below can refer to the limitations of the aircraft clear air turbulence prediction method above, and will not be repeated here.

[0119] In an exemplary embodiment, a device for predicting clear-air turbulence of an aircraft is provided, comprising:

[0120] The acquisition module is used to acquire a sample set, wherein the sample set includes multiple samples, and one sample includes turbulence observation data and values ​​of various meteorological data when the sample aircraft flies at the same time and the same space.

[0121] A CAT diagnostic value calculation module is used to calculate the values ​​of each CAT diagnostic index according to the values ​​of each meteorological data corresponding to the sample for any sample to obtain a CAT diagnostic value sequence corresponding to the sample;

[0122] The total data set construction module is used to construct the total data set according to the CAT diagnosis value sequence corresponding to each sample and the bump observation data corresponding to each sample.

[0123] The data set determination module is used to sequentially perform preprocessing and oversampling processing on the total data set to obtain a data set; the preprocessing includes sequentially performing data quality control and replacing turbulence observation data with turbulence labels.

[0124] The clear air turbulence prediction model determination module is used to train and verify the W-KNN model using a data set to obtain a clear air turbulence prediction model, wherein the clear air turbulence prediction model is used to predict the clear air turbulence of the aircraft to be predicted.

[0125] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 5As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store aircraft clear air turbulence prediction data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for predicting aircraft clear air turbulence is implemented.

[0126] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above-mentioned method embodiments when executing the computer program.

[0127] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the above-mentioned method embodiments are implemented.

[0128] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the above-mentioned method embodiments are implemented.

[0129] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0130] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0131] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0132] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0133] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for predicting clear-air turbulence of an aircraft, characterized in that: The aircraft clear sky turbulence prediction method comprises: Acquire a sample set, the sample set comprising a plurality of samples, one sample comprising turbulence observation data and values ​​of various meteorological data when the sample aircraft flies at the same time and in the same space; For any sample, the values ​​of each CAT diagnostic index are calculated according to the values ​​of each meteorological data corresponding to the sample to obtain the CAT diagnostic value sequence corresponding to the sample; The total data set is constructed based on the CAT diagnostic value sequence corresponding to each sample and the bump observation data corresponding to each sample; The total data set is sequentially preprocessed and oversampled to obtain a data set; the preprocessing includes sequentially performing data quality control and replacing turbulence observation data with turbulence labels; The W-KNN model is trained and verified using a data set to obtain a clear-air turbulence prediction model, which is used to predict clear-air turbulence of an aircraft to be predicted.

2. The method for predicting clear-air turbulence according to claim 1, characterized in that: The total data set is constructed based on the CAT diagnostic value sequence corresponding to each sample and the bump observation data corresponding to each sample, including: Performing interpolation processing on the CAT diagnostic value sequence corresponding to each sample to obtain the numerical sequence of the CAT diagnostic index after interpolation processing corresponding to each sample; The total data set is constructed based on the numerical sequence of the CAT diagnostic index after interpolation processing corresponding to each sample and the bumpy observation data corresponding to each sample.

3. The method for predicting clear-air turbulence according to claim 1, characterized in that: The W-KNN model is trained and verified using the data set to obtain a clear air turbulence prediction model, which includes: Dividing the data set into a training set and a test set; The W-KNN model is trained and verified using a test set and a training set to obtain a clear-air turbulence prediction model, wherein the clear-air turbulence prediction model is used to predict clear-air turbulence of an aircraft to be predicted.

4. The method for predicting clear-air turbulence according to claim 3, characterized in that: The W-KNN model is trained and verified using the test set and training set to obtain a clear air turbulence prediction model, which includes: The training set is standardized to obtain a standardized training set; The standardized training set was processed using 10-fold cross validation to estimate the hyperparameter values ​​of the W-KNN model; The W-KNN model determined by the hyperparameter values ​​was verified using standardized training sets and test sets to obtain the clear air turbulence prediction model.

5. The method for predicting clear-air turbulence according to claim 4, characterized in that: The W-KNN model with the determined hyperparameter values ​​was verified using standardized training sets and test sets to obtain a clear-air turbulence prediction model, including: The standardized training set is used to predict the turbulence label of each sample in the test set to obtain the predicted turbulence label of each sample in the test set; The predicted turbulence labels of each sample in the test set and the turbulence labels of each sample in the test set are used to verify the W-KNN model determined by the hyperparameter values ​​to obtain the clear air turbulence prediction model.

6. The method for predicting clear-air turbulence according to claim 5, characterized in that: The standardized training set is used to predict the turbulence labels of each sample in the test set to obtain the predicted turbulence labels of each sample in the test set, including: For any sample in the test set, the Manhattan distance between the CAT diagnostic value sequence corresponding to the sample and the CAT diagnostic value sequence corresponding to each sample in the standardized training set is calculated to obtain a distance sequence; Sorting all Manhattan distances in the distance sequence from small to large to obtain a sorted distance sequence; The turbulence labels of each sample corresponding to the first K Manhattan distances of the sorted distance sequence in the standardized training set are selected to obtain the turbulence label set; K is the K value in the W-KNN model determined by the hyperparameter value; The turbulence label set is processed by using a weighted voting method to obtain the predicted turbulence label of the sample.

7. An aircraft clear sky turbulence prediction device, characterized in that: The aircraft clear sky turbulence prediction device comprises: An acquisition module, used for acquiring a sample set, wherein the sample set includes a plurality of samples, and one sample includes turbulence observation data and values ​​of various meteorological data when the sample aircraft flies at the same time and the same space; A CAT diagnostic value calculation module, for calculating the values ​​of each CAT diagnostic index according to the values ​​of each meteorological data corresponding to the sample for any sample, to obtain a CAT diagnostic value sequence corresponding to the sample; A total data set construction module is used to construct a total data set according to the CAT diagnostic value sequence corresponding to each sample and the bump observation data corresponding to each sample; A data set determination module, used for sequentially performing preprocessing and oversampling processing on the total data set to obtain a data set; the preprocessing includes sequentially performing data quality control and replacing turbulence observation data with turbulence labels; The clear air turbulence prediction model determination module is used to train and verify the W-KNN model using a data set to obtain a clear air turbulence prediction model, wherein the clear air turbulence prediction model is used to predict the clear air turbulence of the aircraft to be predicted.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the aircraft clear air turbulence prediction method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the aircraft clear air turbulence prediction method described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the aircraft clear air turbulence prediction method described in any one of claims 1 to 6 is implemented.

Images