Civil aviation wind shear risk prediction method and system

Abstract

The invention provides a civil aviation wind shear risk prediction method and system, and relates to the technical field of civil aviation risk prediction, and the method comprises the steps: obtaining historical civil aviation wind shear generation data; calculating the historical data based on a preset wind shear occurrence rate calculation formula to obtain historical wind shear occurrence rate data; performing data preprocessing on the historical wind shear occurrence rate data to obtain a training set and a verification set; optimizing the civil aviation wind shear risk prediction model based on an elitist genetic algorithm to obtain an optimized model; sending the training set and the verification set to the optimized model for training and verification to obtain a trained model; and performing wind shear risk prediction based on historical wind shear occurrence rate data and the trained model to obtain a prediction result. According to the method, an elitist strategy is adopted to ensure the retention of the optimal individual and the effectiveness of iterative operation, so that the prediction performance of the model is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of civil aviation risk prediction, and in particular to a method and system for predicting civil aviation wind shear risk. Background Art

[0002] At present, wind shear, as a sudden meteorological phenomenon, seriously threatens the safety of aviation during civil aviation flights. Wind shear usually occurs during the take-off and landing phases of aircraft, posing a great challenge to the control of aircraft and route safety. Existing wind shear risk prediction methods mainly rely on real-time analysis of meteorological radar and flight data, and make predictions through traditional statistical models or simple machine learning algorithms. However, these methods have major deficiencies in prediction accuracy and timeliness, and are difficult to cope with complex and changeable meteorological conditions, and often fail to provide timely and accurate warning information.

[0003] There is an urgent need for a civil aviation wind shear risk prediction method and system that provides timely and accurate warning information to solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for predicting wind shear risk in civil aviation to improve the above problems. In order to achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0005] In a first aspect, the present application provides a method for predicting wind shear risk in civil aviation, comprising:

[0006] Obtain historical civil aviation wind shear occurrence data;

[0007] The historical civil aviation wind shear occurrence data is calculated based on the preset wind shear occurrence rate calculation formula to obtain the historical civil aviation wind shear occurrence rate data;

[0008] Preprocessing the historical civil aviation wind shear incidence data to obtain a training set and a validation set of historical civil aviation wind shear;

[0009] Based on the preset elitist genetic algorithm, the preset civil aviation wind shear risk prediction model is optimized to obtain the optimized civil aviation wind shear risk prediction model;

[0010] Sending the training set and the validation set to the optimized civil aviation wind shear risk prediction model for training and validation to obtain a trained civil aviation wind shear risk prediction model;

[0011] Based on the historical civil aviation wind shear incidence data and the trained civil aviation wind shear risk prediction model, the civil aviation wind shear risk is predicted and the prediction results are obtained.

[0012] In a second aspect, the present application also provides a civil aviation wind shear risk prediction system, comprising:

[0013] An acquisition unit, used to acquire historical civil aviation wind shear occurrence data;

[0014] A calculation unit, used to calculate the historical civil aviation wind shear occurrence data based on a preset wind shear occurrence rate calculation formula to obtain the historical civil aviation wind shear occurrence rate data;

[0015] A processing unit, configured to perform data preprocessing on the historical civil aviation wind shear incidence data to obtain a training set and a validation set of historical civil aviation wind shear;

[0016] An optimization unit, used for optimizing a preset civil aviation wind shear risk prediction model based on a preset elitist genetic algorithm to obtain an optimized civil aviation wind shear risk prediction model;

[0017] A training unit, used for sending the training set and the verification set to the optimized civil aviation wind shear risk prediction model for training and verification, so as to obtain a trained civil aviation wind shear risk prediction model;

[0018] The prediction unit is used to predict the civil aviation wind shear risk based on the historical civil aviation wind shear occurrence rate data and the trained civil aviation wind shear risk prediction model to obtain a prediction result.

[0019] The beneficial effects of the present invention are:

[0020] The civil aviation wind shear risk prediction method based on elitist genetic algorithm optimization proposed in the present invention can significantly improve the accuracy and timeliness of wind shear risk prediction. Through dimensionless processing and entropy calculation of historical data, the wind shear incidence rate is accurately calculated, and on this basis, a training set and a validation set are constructed to ensure the scientificity and reliability of the data. The prediction model is optimized using an elitist genetic algorithm, and the fitness of the model is continuously improved through iterative selection, crossover and mutation operations, and finally the optimal prediction model is obtained. The optimized model can accurately predict the civil aviation wind shear risk and provide effective warning information, thereby greatly improving the safety of aviation flights.

[0021] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 It is a schematic diagram of the flow chart of the method for predicting wind shear risk in civil aviation described in an embodiment of the present invention;

[0024] Figure 2 Schematic diagram of the structure of the civil aviation wind shear risk prediction system described in an embodiment of the present invention.

[0025] In the figure: 701, acquisition unit; 702, calculation unit; 703, processing unit; 704, optimization unit; 705, training unit; 706, prediction unit; 7021, first processing subunit; 7022, first calculation subunit; 7023, second calculation subunit; 7024, third calculation subunit; 7031, second processing subunit; 7032, third processing subunit; 7041, fourth processing subunit; 7042, fourth calculation subunit; 7043, fifth processing subunit; 7044, sixth processing subunit; 7045, seventh processing subunit; 7046, eighth processing subunit; 7047, ninth processing subunit; 70451, first iteration subunit; 70452, second iteration subunit. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0027] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0028] Embodiment 1:

[0029] This embodiment provides a method for predicting civil aviation wind shear risk.

[0030] See also Figure 1 , the figure shows that the method includes step S1, step S2, step S3, step S4, step S5 and step S6.

[0031] Step S1, obtaining historical civil aviation wind shear occurrence data;

[0032] It can be understood that this step obtains historical civil aviation wind shear occurrence data including the specific time, location, impact degree and response measures of the event, and forms a complete historical civil aviation wind shear data set by comprehensively collecting and organizing the above data, providing a basis for subsequent analysis and prediction.

[0033] Step S2, calculating the historical civil aviation wind shear occurrence data based on a preset wind shear occurrence rate calculation formula to obtain the historical civil aviation wind shear occurrence rate data;

[0034] It can be understood that this step can more accurately evaluate the impact of various factors on the occurrence of wind shear through the calculation of entropy value and difference coefficient, thereby calculating a more accurate wind shear incidence rate, quantifying and analyzing complex historical data, and obtaining specific wind shear incidence rate data, which is convenient for subsequent model training and prediction. In this step, step S2 includes step S21, step S22, step S23 and step S24.

[0035] Step S21, performing dimensionless processing on the historical civil aviation wind shear occurrence data to obtain dimensionless civil aviation wind shear occurrence data;

[0036] It can be understood that this step eliminates the dimensional differences of the historical civil aviation wind shear occurrence data by performing dimensionless processing on the historical civil aviation wind shear occurrence data.

[0037] Step S22, calculating the dimensionless civil aviation wind shear occurrence data based on a preset entropy value calculation formula and a difference coefficient calculation formula to obtain an entropy value and a difference coefficient of the civil aviation wind shear occurrence data;

[0038] It can be understood that the entropy value calculation formula in this step is used to measure the degree of disorder of the data, while the difference coefficient is used to measure the difference between the data. The entropy value calculation formula is as follows:

[0039]

[0040] Among them, i represents the i-th year, j represents the j-th indicator, P ijrepresents the characteristic proportion of the i-th year under the j-th indicator, x ij represents the evaluation index value of the i-th year under the j-th index, x' ij Represents x ij The derivative of .

[0041]

[0042] Among them, e j represents the entropy value of the jth indicator, n represents the nth year, i represents the i-th year, P ij It represents the characteristic proportion of the i-th year under the j-th indicator.

[0043] The calculation formula of the coefficient of difference is as follows:

[0044] gj=1-ej

[0045] Among them, g j represents the difference coefficient of the jth indicator, e j Represents the entropy value of the jth indicator.

[0046] Step S23, determining the evaluation index weight of the historical civil aviation wind shear occurrence data based on the entropy value and the difference coefficient of the civil aviation wind shear occurrence data;

[0047] It can be understood that the calculation formula of the evaluation index weight in this step is as follows:

[0048]

[0049] Among them, α j represents the evaluation index weight of the jth index, g j It represents the difference coefficient of the j-th indicator, and m means there are m indicators.

[0050] Step S24: Calculate historical civil aviation wind shear occurrence rate data based on the historical civil aviation wind shear occurrence data and the evaluation index weight of the historical civil aviation wind shear occurrence data.

[0051] It can be understood that in this step, the formula for calculating the historical civil aviation wind shear incidence data is as follows:

[0052]

[0053] Where A represents the historical civil aviation wind shear occurrence rate, α j represents the weight of the first evaluation index, and B represents the frequency of historical civil aviation wind shear.

[0054] Step S3, preprocessing the historical civil aviation wind shear incidence data to obtain a training set and a validation set of historical civil aviation wind shear;

[0055] It can be understood that this step uses enough historical data for model training through reasonable data classification to improve the learning ability of the model; at the same time, the model is evaluated through the validation set to ensure the generalization ability and prediction accuracy of the model. In this step, step S3 includes step S31 and step S32.

[0056] Step S31, normalizing the historical civil aviation wind shear incidence data according to a preset formula to obtain normalized data;

[0057] It can be understood that this step processes the data at the same scale through normalization, ensuring the stability and convergence of the model training. The normalization formula is as follows:

[0058]

[0059] Where i represents the i-th dimension feature, i = 1, 2, ..., n, n is the number of eigenvalues; y i ' is the value before normalization, y i is the normalized value; min(y i ) is the minimum value of the feature before normalization of the i-th dimension, max(y i ) is the maximum value of the i-th dimension feature before normalization.

[0060] Step S32: classify the normalized data according to preset time points, wherein the normalized data before the preset time point is used as training set data, and the normalized data after the preset time point is used as verification set data.

[0061] It can be understood that this step fully utilizes the existing data resources by dividing the historical data into training sets and validation sets, provides scientific data support for model training and validation, and ensures the reliability of the model in practical applications.

[0062] Step S4, optimizing the preset civil aviation wind shear risk prediction model based on the preset elitist genetic algorithm to obtain an optimized civil aviation wind shear risk prediction model;

[0063] It can be understood that this step can find a set of optimal hyperparameter configurations through the optimization of the genetic algorithm, greatly improving the prediction accuracy and stability of the model. The elitist strategy ensures that the best individuals can be passed on to the next generation, effectively avoiding the algorithm from falling into the local optimal solution and improving the global search capability. In this step, step S4 includes step S41, step S42, step S43 and step S44.

[0064] Step S41, initializing the population and parameters of the preset civil aviation wind shear risk prediction model, wherein at least two individuals are randomly generated based on the preset civil aviation wind shear risk prediction model, each individual represents a set of hyperparameter configurations of the civil aviation wind shear risk prediction model, and the maximum number of iterations, crossover rate, mutation rate and elitism strategy information of the genetic algorithm are set to obtain the initialized parameters;

[0065] It can be understood that this step covers a wide range of hyperparameter combinations through the randomly generated initial population, ensuring the diversity of the search space and increasing the possibility of finding the global optimal solution.

[0066] Step S42: sending the initialized parameters to a preset fitness function for calculation to obtain a fitness function value;

[0067] It can be understood that this step is calculated through the fitness function, and the quality of each individual is quantified, which is convenient for subsequent selection, crossover and mutation operations. The fitness function in this step is as follows:

[0068] P=LSTM_LOSS(n,h,batch,ep,lr)

[0069] Among them, LSTM_LOSS is the loss function of LSTM, n is the number of hidden layers of LSTM network of LSTM input; h is the size of each hidden layer; batch is the batch size, that is, the number of samples trained in each batch; ep is the number of training rounds; lr is the learning rate.

[0070] Step S43, retaining the individual corresponding to the highest calculated fitness function value as the elite individual, and judging whether the number of iterations reaches the preset maximum number of iterations, if so, calculating according to the preset calculation formula of the optimal individual to obtain the optimal individual;

[0071] It can be understood that this step ensures the stable transmission of the optimal solution in the iterative process by selecting elite individuals, avoiding the loss of excellent genes due to genetic operations. The calculation formula of the optimal individual in this step is as follows:

[0072]

[0073] Among them, P(select P o ) represents the optimal individual, f(P o ) represents the fitness value of the oth individual, f(P q ) represents the fitness value of the qth individual, and N represents the number of N individuals.

[0074] Among them, the formula for selecting the number of elite individuals is as follows:

[0075]

[0076] Among them, N elite represents the number of elite individuals, E represents the elite probability, Indicates rounding down.

[0077] Step S44: sending the optimal individual to a preset civil aviation wind shear risk prediction model for processing to obtain an optimized civil aviation wind shear risk prediction model.

[0078] It can be understood that this step can significantly improve the prediction performance of the model and reduce the prediction error by applying the optimal hyperparameter configuration, thereby improving the accuracy and stability of the model. The retrained model can better adapt to the data, improve the performance of the model in practical applications, and ensure the effectiveness and reliability of the model.

[0079] It can be understood that step S43 includes step S45, step S46 and step S47.

[0080] Step S45: If the number of iterations does not reach the preset number of iterations, all individuals except the elite individuals are genetically operated to obtain a descendant population after the genetic operation;

[0081] It can be understood that this step can generate new individuals in each generation through genetic operations, accelerate convergence to the global optimal solution, and improve the optimization efficiency of the algorithm. In this step, step S45 includes step S451 and step S452.

[0082] Step S451: If the number of iterations does not reach the preset number of iterations, all individuals except the elite individuals are subjected to a selection operation, wherein all individuals except the elite individuals are selected according to a preset selection formula to obtain individuals that need to be subjected to a crossover mutation operation;

[0083] It can be understood that this step retains individuals with high fitness through selection operations, ensures that good genes are transmitted in the population, and improves the overall performance of the algorithm.

[0084] Step S452: Perform gene exchange and mutation operations on the individuals that need to undergo crossover and mutation operations according to preset crossover and mutation steps to obtain at least two offspring individuals after crossover and mutation, and aggregate all offspring individuals after crossover and mutation to obtain an offspring population after genetic operation.

[0085] It can be understood that this step can generate new gene combinations through crossover and mutation operations, explore new solution spaces, and avoid the population from falling into local optimality.

[0086] Step S46, adding the elite individuals to the offspring population after the genetic operation to merge and obtain regenerated population information;

[0087] It can be understood that this step ensures that the optimal gene will not be lost due to genetic operations by retaining the elite individuals in each generation, thereby improving the stability of the algorithm.

[0088] Step S47, sending the regenerated population information to a preset fitness function for calculation, and repeatedly selecting elite individuals and performing genetic operations until a preset number of iterations is reached to obtain the optimal individual.

[0089] It can be understood that each iteration of this step optimizes the population through selection, crossover and mutation operations to improve the prediction ability and accuracy of the model. The retention of elite individuals ensures that the optimal solution will not be lost, enhancing the stability and convergence of the algorithm.

[0090] Step S5, sending the training set and the validation set to the optimized civil aviation wind shear risk prediction model for training and validation, to obtain a trained civil aviation wind shear risk prediction model;

[0091] It can be understood that this step ensures that the optimized model can effectively learn on the training data and perform well on the validation data through training and validation, and has good generalization ability. The evaluation process of the validation set can help identify potential problems of the model, such as overfitting or underfitting, so as to make appropriate adjustments to improve model stability.

[0092] Step S6: predicting the civil aviation wind shear risk based on the historical civil aviation wind shear incidence data and the trained civil aviation wind shear risk prediction model to obtain a prediction result.

[0093] It is understandable that the model trained in this step can make accurate risk predictions based on historical data and provide reliable information about future wind shear risks. The prediction results can help airlines or meteorological departments make scientific decisions, improve flight arrangements and safety measures, and reduce the impact of wind shear on flight safety. Through the prediction data, measures can also be taken in advance to prevent and respond to wind shear risks, optimize risk management processes, and enhance the safety of civil aviation operations.

[0094] Embodiment 2:

[0095] like Figure 2 As shown, this embodiment provides a civil aviation wind shear risk prediction system, see Figure 2 The system includes an acquisition unit 701 , a calculation unit 702 , a processing unit 703 , an optimization unit 704 , a training unit 705 and a prediction unit 706 .

[0096] An acquisition unit 701 is used to acquire historical civil aviation wind shear occurrence data;

[0097] The calculation unit 702 is used to calculate the historical civil aviation wind shear occurrence data based on a preset wind shear occurrence rate calculation formula to obtain the historical civil aviation wind shear occurrence rate data;

[0098] The computing unit 702 includes a first processing subunit 7021 , a first computing subunit 7022 , a second computing subunit 7023 , and a third computing subunit 7024 .

[0099] The first processing subunit 7021 is used to perform dimensionless processing on the historical civil aviation wind shear occurrence data to obtain dimensionless civil aviation wind shear occurrence data;

[0100] The first calculation subunit 7022 is used to calculate the dimensionless civil aviation wind shear occurrence data based on a preset entropy value calculation formula and a difference coefficient calculation formula to obtain the entropy value and the difference coefficient of the civil aviation wind shear occurrence data;

[0101] The second calculation subunit 7023 is used to determine the evaluation index weight of the historical civil aviation wind shear occurrence data based on the entropy value and the difference coefficient of the civil aviation wind shear occurrence data;

[0102] The third calculation subunit 7024 is used to calculate and obtain the historical civil aviation wind shear occurrence rate data based on the historical civil aviation wind shear occurrence data and the evaluation index weight of the historical civil aviation wind shear occurrence data.

[0103] The processing unit 703 is used to perform data preprocessing on the historical civil aviation wind shear incidence data to obtain a training set and a validation set of historical civil aviation wind shear;

[0104] The processing unit 703 includes a second processing sub-unit 7031 and a third processing sub-unit 7032 .

[0105] The second processing subunit 7031 is used to normalize the historical civil aviation wind shear incidence data according to a preset formula to obtain normalized data;

[0106] The third processing subunit 7032 is used to classify the normalized data according to preset time points, wherein the normalized data before the preset time point is used as training set data, and the normalized data after the preset time point is used as verification set data.

[0107] The optimization unit 704 is used to optimize the preset civil aviation wind shear risk prediction model based on the preset elitist genetic algorithm to obtain an optimized civil aviation wind shear risk prediction model;

[0108] The optimization unit 704 includes a fourth processing subunit 7041 , a fourth calculation subunit 7042 , a fifth processing subunit 7043 and a sixth processing subunit 7044 .

[0109] The fourth processing subunit 7041 is used to initialize the population and parameters of the preset civil aviation wind shear risk prediction model, wherein at least two individuals are randomly generated based on the preset civil aviation wind shear risk prediction model, each individual represents a set of hyperparameter configurations of the civil aviation wind shear risk prediction model, and the maximum number of iterations, crossover rate, mutation rate and elitism strategy information of the genetic algorithm are set to obtain the initialized parameters;

[0110] The fourth calculation subunit 7042 is used to send the initialized parameters to a preset fitness function for calculation to obtain a fitness function value;

[0111] The fifth processing subunit 7043 is used to retain the individual corresponding to the calculated highest fitness function value as an elite individual, and determine whether its iteration number reaches a preset maximum iteration number. If so, calculate according to a preset calculation formula of the optimal individual to obtain the optimal individual;

[0112] The sixth processing subunit 7044 is used to send the optimal individual to a preset civil aviation wind shear risk prediction model for processing to obtain an optimized civil aviation wind shear risk prediction model.

[0113] The fifth processing sub-unit 7043 further includes a seventh processing sub-unit 7045 , an eighth processing sub-unit 7046 and a ninth processing sub-unit 7047 .

[0114] The seventh processing subunit 7045 is used for performing genetic operations on all individuals except elite individuals to obtain a descendant population after genetic operations if the number of iterations does not reach the preset number of iterations;

[0115] The eighth processing subunit 7046 is used to add the elite individuals to the offspring population after the genetic operation to merge them and obtain the regenerated population information;

[0116] The ninth processing subunit 7047 is used to send the regenerated population information to a preset fitness function for calculation, and repeatedly select elite individuals and perform genetic operations until a preset number of iterations is reached to obtain the optimal individual.

[0117] The seventh processing sub-unit 7045 includes a first iterative sub-unit 70451 and a second iterative sub-unit 70452 .

[0118] The first iteration subunit 70451 is used for, if the number of iterations does not reach the preset number of iterations, performing a selection operation on all individuals except the elite individuals, wherein all individuals except the elite individuals are selected according to a preset selection formula to obtain individuals that need to be subjected to a crossover mutation operation;

[0119] The second iterative subunit 70452 is used to perform gene exchange and mutation operations on individuals that need to undergo crossover and mutation operations according to preset crossover and mutation steps to obtain at least two offspring individuals after crossover and mutation, and to aggregate all offspring individuals after crossover and mutation to obtain an offspring population after genetic operations.

[0120] A training unit 705 is used to send the training set and the verification set to the optimized civil aviation wind shear risk prediction model for training and verification, so as to obtain a trained civil aviation wind shear risk prediction model;

[0121] The prediction unit 706 is used to predict the civil aviation wind shear risk based on the historical civil aviation wind shear occurrence rate data and the trained civil aviation wind shear risk prediction model to obtain a prediction result.

[0122] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0123] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0124] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for predicting wind shear risk in civil aviation, characterized in that: include: Obtain historical civil aviation wind shear occurrence data; The historical civil aviation wind shear occurrence data is calculated based on the preset wind shear occurrence rate calculation formula to obtain the historical civil aviation wind shear occurrence rate data; Preprocessing the historical civil aviation wind shear incidence data to obtain a training set and a validation set of historical civil aviation wind shear; Based on the preset elitist genetic algorithm, the preset civil aviation wind shear risk prediction model is optimized to obtain the optimized civil aviation wind shear risk prediction model; Sending the training set and the validation set to the optimized civil aviation wind shear risk prediction model for training and validation to obtain a trained civil aviation wind shear risk prediction model; Based on the historical civil aviation wind shear incidence data and the trained civil aviation wind shear risk prediction model, the civil aviation wind shear risk is predicted and the prediction results are obtained.

2. The method for predicting civil aviation wind shear risk according to claim 1, characterized in that ,The historical civil aviation wind shear occurrence data is calculated based on the preset wind shear occurrence rate calculation formula, including: The historical civil aviation wind shear occurrence data is processed dimensionlessly to obtain dimensionless civil aviation wind shear occurrence data; Based on the preset entropy value calculation formula and difference coefficient calculation formula, the dimensionless civil aviation wind shear occurrence data is calculated to obtain the entropy value and difference coefficient of the civil aviation wind shear occurrence data; Determine the evaluation index weight of the historical civil aviation wind shear occurrence data based on the entropy value and the difference coefficient of the civil aviation wind shear occurrence data; The historical civil aviation wind shear occurrence data and the evaluation index weight calculation of the historical civil aviation wind shear occurrence data are used to obtain the historical civil aviation wind shear occurrence rate data.

3. The method for predicting civil aviation wind shear risk according to claim 1, characterized in that , the historical civil aviation wind shear incidence data is preprocessed to obtain a training set and a validation set of historical civil aviation wind shear, including: The historical civil aviation wind shear incidence data is normalized according to a preset formula to obtain normalized data; The normalized data is classified according to preset time points, wherein the normalized data before the preset time point is used as the training set data, and the normalized data after the preset time point is used as the verification set data.

4. The method for predicting civil aviation wind shear risk according to claim 1, characterized in that ,Based on the preset elitist genetic algorithm, the preset civil aviation wind shear risk prediction model is optimized, including: Initializing the population and parameters of the preset civil aviation wind shear risk prediction model, wherein at least two individuals are randomly generated based on the preset civil aviation wind shear risk prediction model, each individual represents a set of hyperparameter configurations of the civil aviation wind shear risk prediction model, and setting the maximum number of iterations, crossover rate, mutation rate and elitism strategy information of the genetic algorithm to obtain the initialized parameters; Sending the initialized parameters to a preset fitness function for calculation to obtain a fitness function value; The individual corresponding to the highest calculated fitness function value is retained as the elite individual, and its iteration number is judged whether it reaches the preset maximum iteration number. If it reaches it, it is calculated according to the preset calculation formula of the optimal individual to obtain the optimal individual; The optimal individual is sent to a preset civil aviation wind shear risk prediction model for processing to obtain an optimized civil aviation wind shear risk prediction model.

5. The method for predicting civil aviation wind shear risk according to claim 4, characterized in that , the individual corresponding to the calculated highest fitness function value is retained as an elite individual, and judging whether the number of iterations reaches a preset number of iterations, further comprising: If the number of iterations does not reach the preset number of iterations, all individuals except the elite individuals will be genetically manipulated to obtain the offspring population after genetic manipulation; Adding the elite individuals to the offspring population after the genetic operation to merge them, and obtaining the regenerated population information; The regenerated population information is sent to a preset fitness function for calculation, and the elite individuals are selected and the genetic operation is performed repeatedly until a preset number of iterations is reached to obtain the optimal individual.

6. A civil aviation wind shear risk prediction system, characterized in that: include: An acquisition unit, used to acquire historical civil aviation wind shear occurrence data; A calculation unit, used to calculate the historical civil aviation wind shear occurrence data based on a preset wind shear occurrence rate calculation formula to obtain the historical civil aviation wind shear occurrence rate data; A processing unit, configured to perform data preprocessing on the historical civil aviation wind shear incidence data to obtain a training set and a validation set of historical civil aviation wind shear; An optimization unit, used for optimizing a preset civil aviation wind shear risk prediction model based on a preset elitist genetic algorithm to obtain an optimized civil aviation wind shear risk prediction model; A training unit, used for sending the training set and the verification set to the optimized civil aviation wind shear risk prediction model for training and verification, so as to obtain a trained civil aviation wind shear risk prediction model; The prediction unit is used to predict the civil aviation wind shear risk based on the historical civil aviation wind shear occurrence rate data and the trained civil aviation wind shear risk prediction model to obtain a prediction result.

7. The civil aviation wind shear risk prediction system according to claim 6, characterized in that: The computing unit comprises: The first processing subunit is used to perform dimensionless processing on the historical civil aviation wind shear occurrence data to obtain dimensionless civil aviation wind shear occurrence data; The first calculation subunit is used to calculate the dimensionless civil aviation wind shear occurrence data based on a preset entropy value calculation formula and a difference coefficient calculation formula to obtain the entropy value and the difference coefficient of the civil aviation wind shear occurrence data; A second calculation subunit is used to determine the evaluation index weight of the historical civil aviation wind shear occurrence data based on the entropy value and the difference coefficient of the civil aviation wind shear occurrence data; The third calculation subunit is used to calculate and obtain the historical civil aviation wind shear occurrence rate data based on the historical civil aviation wind shear occurrence data and the evaluation index weight of the historical civil aviation wind shear occurrence data.

8. The civil aviation wind shear risk prediction system according to claim 6, characterized in that: The processing unit comprises: The second processing subunit is used to normalize the historical civil aviation wind shear incidence data according to a preset formula to obtain normalized data; The third processing subunit is used to classify the normalized data according to preset time points, wherein the normalized data before the preset time point is used as training set data, and the normalized data after the preset time point is used as verification set data.

9. The civil aviation wind shear risk prediction system according to claim 6, characterized in that: The optimization unit comprises: The fourth processing subunit is used to initialize the population and parameters of the preset civil aviation wind shear risk prediction model, wherein at least two individuals are randomly generated based on the preset civil aviation wind shear risk prediction model, each individual represents a set of hyperparameter configurations of the civil aviation wind shear risk prediction model, and the maximum number of iterations, crossover rate, mutation rate and elitism strategy information of the genetic algorithm are set to obtain the initialized parameters; A fourth calculation subunit, used for sending the initialized parameters to a preset fitness function for calculation to obtain a fitness function value; The fifth processing subunit is used to retain the individual corresponding to the highest calculated fitness function value as an elite individual, and determine whether its iteration number reaches a preset maximum iteration number. If it reaches, calculate according to a preset calculation formula of the optimal individual to obtain the optimal individual; The sixth processing subunit is used to send the optimal individual to a preset civil aviation wind shear risk prediction model for processing to obtain an optimized civil aviation wind shear risk prediction model.

10. The civil aviation wind shear risk prediction system according to claim 9, characterized in that: After the fifth processing subunit, it includes: The seventh processing subunit is used for performing genetic operations on all individuals except elite individuals to obtain a descendant population after genetic operations if the number of iterations does not reach a preset number of iterations; An eighth processing subunit is used to add the elite individuals to the offspring population after the genetic operation to merge them and obtain regenerated population information; The ninth processing subunit is used to send the regenerated population information to a preset fitness function for calculation, and repeatedly select elite individuals and perform genetic operations until a preset number of iterations is reached to obtain the optimal individual.

Images