A method, device, medium and product for predicting the sonic boom intensity of an aircraft

Abstract

The present application discloses a method, device, medium and product for predicting the sonic boom intensity of an aircraft, relating to the technical field of sonic boom prediction. The method obtains the surface pressure distribution data of the aircraft under different flight states based on the number and arrangement positions of the pressure measurement holes on the aircraft surface; obtains a data set of historical surface pressure distribution data and the corresponding ground sonic boom intensity of the historical surface pressure distribution data; trains a sonic boom prediction model based on the data set to determine a trained sonic boom prediction model; and inputs the surface pressure distribution data to be detected obtained in real time under the current flight state into the trained sonic boom prediction model to determine the ground sonic boom intensity corresponding to the surface pressure distribution data to be detected. The present application can predict the ground sonic boom intensity in real time and shorten the prediction time of the sonic boom intensity.

Description

Technical Field

[0001] This application relates to the technical field of sonic boom prediction, and particularly to a method, device, medium and product for predicting the sonic boom intensity of an aircraft. Background Art

[0002] When the speed of an aircraft exceeds the speed of sound, shock waves and expansion waves will be generated in its flow field. The sonic boom composed of two strong shock waves in the front and back formed when these wave systems propagate to the ground will cause harm to ground personnel, animals and buildings. Taking a passenger plane as an example, the sonic boom intensity generated during its supersonic cruise is as high as 108 PLdB, which is sufficient to shatter the glass of buildings.

[0003] To reduce the sonic boom intensity of an aircraft, the nose mute cone sonic boom suppression technology has been proposed internationally. By installing a retractable long rod-shaped mechanism composed of multiple cylinders and cones at the nose of the aircraft and extending this mechanism during supersonic flight, the strong bow shock wave at the nose is converted into several weak shock waves. However, due to the lack of a feedback mechanism in this process and the long prediction time of the sonic boom intensity, the sonic boom intensity cannot be predicted in real time and fed back to the control system, which may lead to ineffective sonic boom suppression and reduced impact on ground residents and the environment. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, medium and product for predicting the sonic boom intensity of an aircraft, which can solve the problem of poor sonic boom suppression effect caused by long sonic boom prediction time in the prior art.

[0005] To achieve the above purpose, this application provides the following solutions:

[0006] In the first aspect, this application provides a method for predicting the sonic boom intensity of an aircraft, including: obtaining the surface pressure distribution data of the aircraft under different flight states based on the number and arrangement positions of the pressure measurement holes on the aircraft surface; the parameters of the flight state include Mach number, Reynolds number, angle of attack and sideslip angle; obtaining a dataset of the historical surface pressure distribution data and the corresponding ground sonic boom intensity; based on the dataset, using the historical surface pressure distribution data as the input and the corresponding ground sonic boom intensity as the output, training a sonic boom prediction model to determine the trained sonic boom prediction model; the sonic boom prediction model is a deep neural network; inputting the to-be-detected surface pressure distribution data obtained in real time under the current flight state into the trained sonic boom prediction model to determine the ground sonic boom intensity corresponding to the to-be-detected surface pressure distribution data.

[0007] In the second aspect, this application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the method for predicting the sonic boom intensity of an aircraft described above.

[0008] In a third aspect, the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for predicting the sonic boom intensity of an aircraft described above is implemented.

[0009] In a fourth aspect, the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, the method for predicting the sonic boom intensity of an aircraft described above is implemented.

[0010] According to the specific embodiments provided by the present application, the following technical effects are disclosed in the present application:

[0011] The present application provides a method, device, medium and product for predicting the sonic boom intensity of an aircraft. First, historical surface pressure distribution data of the aircraft under different flight states is obtained in real time through pressure measurement holes on the aircraft surface; then, a data set of historical surface pressure distribution data and the corresponding ground sonic boom intensity is obtained. Further, the sonic boom prediction model can be effectively trained through the data set to obtain a trained prediction model. Based on the trained prediction model, an accurate mapping relationship between the historical surface pressure distribution data and the corresponding ground sonic boom intensity is established, improving the accuracy of subsequent ground sonic boom intensity prediction results; finally, through the surface pressure distribution data to be detected obtained in real time under the current flight state and the trained sonic boom prediction model, the ground sonic boom intensity corresponding to the surface pressure distribution data to be detected can be obtained in real time, accurately and quickly, and the sonic boom intensity predicted in real time is fed back to the control system, thereby effectively suppressing the sonic boom. It can be seen that the present application can predict the ground sonic boom intensity in real time, significantly shortening the prediction time of the sonic boom intensity. Description of the Drawings

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0013] Figure 1 It is a schematic flowchart of a method for predicting the sonic boom intensity of an aircraft provided in an embodiment of the present application.

[0014] Figure 2 It is a schematic diagram of the installation position of a pressure measurement hole on the aircraft surface provided in an embodiment of the present application.

[0015] Figure 3 It is a schematic diagram of the installation position of a pressure measurement hole on the aircraft nose and wing provided in an embodiment of the present application.

[0016] Figure 4 This is a schematic structural diagram of a sonic boom prediction model provided in an embodiment of the present application. Detailed implementation manners

[0017] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0018] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners.

[0019] As Figure 1 shown, the present application provides a method for predicting the sonic boom intensity of an aircraft, including step 101-step 104.

[0020] Step 101: Based on the number and arrangement positions of the pressure measurement holes on the aircraft surface, obtain the surface pressure distribution data of the aircraft under different flight states; the parameters of the flight state include Mach number, Reynolds number, angle of attack, and sideslip angle.

[0021] In some embodiments, before step 101, it further includes: for any aircraft configuration, determining the number and arrangement positions of the pressure measurement holes on the aircraft surface corresponding to the aircraft configuration; wherein, the aircraft configuration includes aircraft layout, wing shape, and fuselage size; pressure sensors are provided in the pressure measurement holes.

[0022] Among them, the number of the pressure measurement holes is at least 5.

[0023] Exemplarily, the pressure measurement holes are distributed in a cross shape at the nose of the aircraft, and one is arranged on each of the upper and lower surfaces of the leading edge of the wing.

[0024] In practical applications, 5 to 25 pressure measurement holes can be arranged on the nose and the leading edge surface of the wing of the aircraft. As Figure 2 and Figure 3 , one pressure measurement hole is arranged on each surface of the aircraft, and is identified by numbers 1 to 13. Among them, pressure measurement hole 1 is located at the vertex of the aircraft nose. The diameter of the pressure measurement hole is about 2 mm, it has little impact on the surface pressure of the aircraft. The surface pressure is measured by pressure sensors installed in the pressure measurement holes. Generally, at least 5 pressure measurement holes are required. Considering the need for redundant measurement, the number of pressure measurement holes is appropriately increased to improve fault tolerance. For aircraft with complex configurations, pressure measurement holes can be additionally arranged at the leading edge of the aircraft wing to improve the prediction accuracy. Exemplarily, the pressure measurement holes are distributed in a cross shape above and below the nose and leading edge of the wing of the aircraft.

[0025] Step 102: Obtain a data set of the historical surface pressure distribution data and the ground sonic boom intensity corresponding to the historical surface pressure distribution data.

[0026] In some embodiments, step 102 specifically includes steps 201 - 203.

[0027] Step 201: Obtain the sound pressure distribution data of the ground sonic boom corresponding to the historical surface pressure distribution data and the historical surface pressure distribution data.

[0028] Step 202: Based on the sound pressure distribution data of the ground sonic boom corresponding to the historical surface pressure distribution data and the Stevens Mark Ⅶ model, determine the ground sonic boom intensity corresponding to the historical surface pressure distribution data.

[0029] Step 203: Based on the historical surface pressure distribution data and the ground sonic boom intensity corresponding to the historical surface pressure distribution data, construct the data set.

[0030] In some embodiments, step 201 specifically includes: based on flight tests, obtain a data set of the historical surface pressure distribution data and the ground sonic boom intensity corresponding to the historical surface pressure distribution data; or, based on wind tunnel tests or computational fluid dynamics methods, obtain a data set of the historical surface pressure distribution data and the ground sonic boom intensity corresponding to the historical surface pressure distribution data.

[0031] In practical applications, a large amount of historical surface pressure distribution data of the aircraft surface and the corresponding ground sonic boom intensity are obtained. Each data sample can be represented as , where represents the pressure value at the th pressure measurement hole in the test or simulation record of the th flight state, is the number of pressure measurement holes; represents the ground sonic boom intensity corresponding to the historical surface pressure distribution data of this group of flight states. In some embodiments, step 201 further includes obtaining the sound pressure distribution data of the ground sonic boom corresponding to the historical surface pressure distribution data and the historical surface pressure distribution data based on wind tunnel tests or computational fluid dynamics methods, specifically including steps 301 - 303.

[0032] Step 301: Define the near-field region and the far-field region; the near-field region is the space within three times the fuselage length of the aircraft; the far-field region is the space outside the near-field region.

[0033] Step 302: In the near-field region, obtain the historical surface pressure distribution data and the near-field sound pressure distribution data of the near-field region through the wind tunnel test or the computational fluid dynamics.

[0034] Step 303: Based on the near-field sound pressure distribution data and the acoustic model, determine the sound pressure distribution data of the ground sonic boom corresponding to the historical surface pressure distribution data.

[0035] In some embodiments, step 303 specifically includes: determining the sound pressure distribution data of the ground sonic boom corresponding to the historical surface pressure distribution data according to the near-field sound pressure distribution data and the generalized Burgers equation; wherein, the acoustic model includes the generalized Burgers equation.

[0036] The calculation formula of the generalized Burgers equation is:

[0037] .

[0038] Wherein, is the sound pressure distribution data of the ground sonic boom; is the sound tube area; is the sound ray length; and are the ambient atmospheric density and the speed of sound respectively; is the nonlinear coefficient; is the diffusion coefficient; is the th sound speed increment of the molecule; is the delay time of the sound pressure waveform; is the integration variable; is the th relaxation time of the molecule.

[0039] Specifically, select a combination of multiple flight states and different aircraft configurations as the initial conditions to obtain the pressure distribution at the pressure measurement holes on the surface of the aircraft and the corresponding sound pressure distribution data under different flight states.

[0040] Among them, flight tests are used to measure the pressure distribution at the pressure measurement holes and the sound pressure distribution data of the ground sonic boom under selected flight conditions; a hybrid prediction method that separately considers the near field and the far field can also be used. Specifically, in the near field region, wind tunnel tests or computational fluid dynamics methods are used to obtain the surface pressure distribution data and the near field sound pressure distribution data at the pressure measurement holes on the aircraft surface. The near field sound pressure distribution data is used as the input of the far field acoustic model, and then acoustic models such as the generalized Burgers equation or the generalized Tricomi equation are solved to obtain the sound pressure distribution data of the ground sonic boom.

[0041] Among them, under maneuvering flight conditions, the generalized Tricomi equation is used for solution, and this equation takes into account the focused sonic boom phenomenon generated during maneuvers.

[0042] In some embodiments, step 202 specifically includes: performing a Fourier transform on the sound pressure distribution data of the ground sonic boom corresponding to the historical surface pressure distribution data based on the Stevens Mark VII model to determine the sound pressure level of each frequency band; according to the sound pressure levels of each frequency band, using the loudness index curve to determine the loudness of each frequency band; according to , determine the total loudness; where is the maximum value in the loudness index; is the th frequency band loudness; is the total loudness; F is the masking factor; according to , determine the total loudness level; where is the total response level; take the total loudness level as the ground sonic boom intensity corresponding to the historical surface pressure distribution data.

[0043] Among them, Stevens' Mark VII model uses the 1 / 3 octave band sound pressure level with a center frequency of 3150 Hz as a reference, uses the loudness generated at 32 dB above the center frequency as the basic measurement unit, the loudness increases with the 2 / 3 power of the sound pressure, and whenever the sound pressure level increases by 9 dB, the loudness value doubles.

[0044] Among them, the two values of 32 and 9 are artificially set according to experimental data. The basis for the values of 32 and 9 is: ① Stevens' Mark VII method uses the 1 / 3 octave band sound pressure level with a center frequency of 3150 Hz as a reference and uses the loudness generated at 32 dB above the center frequency as the basic measurement unit. ② The loudness increases with the 2 / 3 power of the sound pressure, and whenever the sound pressure level increases by 9 dB, the loudness value doubles.

[0045] Specifically, to evaluate the ground sonic boom intensity, the Stevens Mark VII model is used to convert the sound pressure distribution data of the ground sonic boom into the total loudness level. First, based on the sound pressure distribution data of the ground sonic boom, the time-domain signal of the ground sonic boom is obtained. The fast Fourier transform is performed on the time-domain signal of the ground sonic boom to convert the time-domain signal into a frequency-domain signal, and the sound pressure level of each frequency band is obtained. According to the sound pressure level of the center frequency of each frequency band, the loudness of the th frequency band is determined, and then the total loudness can be calculated according to the total loudness calculation formula.

[0046] Step 103: Based on the data set, using the historical surface pressure distribution data as the input and the ground sonic boom intensity corresponding to the historical surface pressure distribution data as the output, train the sonic boom prediction model to determine the trained sonic boom prediction model.

[0047] Among them, the sonic boom prediction model is constructed based on deep learning.

[0048] In some embodiments, step 103 specifically includes: inputting the data set of the historical surface pressure distribution data and the ground sonic boom intensity corresponding to the historical surface pressure distribution data into the sonic boom prediction model, and training the parameters of the sonic boom prediction model with the goal of minimizing the loss value to determine the trained sonic boom prediction model; among them, the loss value is determined based on the predicted value and the true value; the predicted value is the predicted ground sonic boom intensity corresponding to the historical surface pressure distribution data output after the sonic boom prediction model inputs the data set of the historical surface pressure distribution data and the ground sonic boom intensity corresponding to the historical surface pressure distribution data; the true value is the ground sonic boom intensity corresponding to the historical surface pressure distribution data in the data set; the parameters of the sonic boom prediction model include weights and biases.

[0049] Specifically, a deep neural network (DNN) is used as the sonic boom prediction model. A deep neural network is a deep learning model composed of multiple neuron layers. Among them, the weights and biases are the weights and biases of the neuron layers. Each neuron layer receives the output of the previous layer as the input and calculates the output through a series of non-linear transformations and weight adjustments. Among them, the neural network takes the pressure value at the pressure tap position as the input, with a total of variables, being the number of pressure taps.

[0050] Among them, a deep neural network is selected as the method for constructing the deep learning model. The deep neural network includes an input layer, multiple hidden layers, and an output layer, as shown in Figure 4As shown, it is possible to achieve the mapping from the pressure distribution on the aircraft surface to the ground sonic boom intensity through multi-level non-linear mapping. The deep neural network uses the training set for feature learning. During the training process, the number of training epochs and batch size are set and adjusted as needed to ensure effective learning of the model and avoid overfitting.

[0051] Among them, the specific process of training the sonic boom prediction model to establish the mapping relationship between the pressure distribution on the aircraft surface and the ground sonic boom intensity is as follows.

[0052] First, the obtained data set is standardized and normalized to eliminate the influence of different dimensions and data ranges on the training of the sonic boom prediction model.

[0053] Then, the data set is used to train the sonic boom prediction model. Deep learning can establish the mapping relationship between input and output by learning a large amount of data. During the training process, first, the predicted value is output based on forward propagation, and then the loss is calculated. The mean square error is used as the loss function, and its expression is:

[0054] .

[0055] Among them, represents the ground sonic boom intensity (true value) in the data set obtained from previous simulations or tests, represents the predicted value output by the sonic boom prediction model, represents the number of samples, represents the th sample. The lower the

[0056] value means the higher the prediction accuracy of the deep neural network on the training set, and it will have better model generalization ability without overfitting. Furthermore, after calculating the loss value, the deep neural network updates the weights using the backpropagation algorithm. First, the gradient of the loss function with respect to each weight is calculated according to the chain rule to understand the sensitivity of the loss to the weight change, and the gradient descent algorithm is used to update the weights. By inputting a sufficient number of training sets, the above learning process is repeated, and the weights are continuously adjusted to minimize the value. Among them, during the training process, hyperparameters such as the learning rate, the number of network layers, and the number of neurons in each layer can be adjusted to optimize the performance of the model.

[0057] As Figure 4 shown, by arranging pressure measurement holes at different positions on the aircraft head, the airflow is introduced to the surface of the pressure sensors inside the aircraft, and the pressure sensors measure the data of the pressure distribution on the aircraft surface. The surface pressure distribution data is transmitted into the deep neural network through the input layer, and the predicted sonic boom intensity is output using the trained prediction model.

[0058] Step 104: Input the surface pressure distribution data to be detected obtained in real time under the current flight state into the trained sonic boom prediction model, and determine the ground sonic boom intensity corresponding to the surface pressure distribution data to be detected.

[0059] In recent years, deep learning has been widely used in the field of aerodynamics. For example, existing research has established a mapping relationship between the surface pressure distribution of a large number of aircraft and flight state data, thereby achieving the goal of using the surface pressure distribution of an aircraft to calculate the current flight state. Thus, by arranging pressure measurement holes on the aircraft surface to obtain surface pressure distribution data, and combining the surface pressure distribution of a large number of aircraft with the ground sonic boom intensity under the corresponding state, it is entirely possible to construct an efficient prediction model from the aircraft surface pressure distribution to the ground sonic boom intensity based on deep learning to significantly shorten the time required for sonic boom prediction.

[0060] In an exemplary embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the above method is implemented.

[0061] 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 method is implemented.

[0062] 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 method is implemented.

[0063] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. 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 methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. 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 (ReRdM), magnetoresistive random access memory (MRdM), ferroelectric random access memory (FRdM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RdM) or external cache memory, etc. By way of illustration and not limitation, RdM can be in various forms, such as static random access memory (SRdM) or dynamic random access memory (DRdM), etc.

[0064] In the embodiments provided in the present application, the databases involved can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. In the embodiments provided in the present application, the processors involved can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0065] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, 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, it should be considered as the scope recorded in this specification.

[0066] In this article, specific examples are used to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A method for predicting the intensity of an aircraft sonic boom, characterized in that: include: Based on the number and arrangement positions of pressure measuring holes on the aircraft surface, historical surface pressure distribution data of the aircraft under different flight states are obtained; the parameters of the flight state include Mach number, Reynolds number, angle of attack and sideslip angle; Acquiring the historical surface pressure distribution data and a data set of ground sonic boom intensity corresponding to the historical surface pressure distribution data specifically includes: Acquiring the historical surface pressure distribution data and the sound pressure distribution data of the ground sonic boom corresponding to the historical surface pressure distribution data, including: defining a near field area and a far field area; the near field area is a space three times the fuselage length of the aircraft; the far field area is a space outside the near field area; in the near field area, acquiring the historical surface pressure distribution data and the near field sound pressure distribution data of the near field area through wind tunnel tests or computational fluid dynamics; determining the sound pressure distribution data of the ground sonic boom corresponding to the historical surface pressure distribution data based on the near field sound pressure distribution data and an acoustic model, using the near field sound pressure distribution data as an input of the acoustic model to the far field acoustic model, so as to obtain the sound pressure distribution data of the ground sonic boom; Based on the sound pressure distribution data of the ground sonic boom corresponding to the historical surface pressure distribution data and the Stevens Mark VII model, determining the intensity of the ground sonic boom corresponding to the historical surface pressure distribution data, specifically comprising: performing Fourier transform on the sound pressure distribution data of the ground sonic boom corresponding to the historical surface pressure distribution data based on the Stevens Mark VII model to determine the sound pressure level of each frequency band; according to the sound pressure level of each frequency band, using a loudness index curve to determine the loudness of each frequency band; according to , determine the total loudness; where, is the maximum value in the loudness index; For the frequency band loudness; is the total loudness; F is the shielding factor; , determine the total loudness level; where, is the total response level; and the total loudness level is used as the ground sonic boom intensity corresponding to the historical surface pressure distribution data; constructing the data set based on the historical surface pressure distribution data and the ground sonic boom intensity corresponding to the historical surface pressure distribution data; Based on the data set, taking the historical surface pressure distribution data as input and the ground sonic boom intensity corresponding to the historical surface pressure distribution data as output, training a sonic boom prediction model, and determining a trained sonic boom prediction model; The pressure distribution data of the surface to be detected acquired in real time under the current flight state is input into the trained sonic boom prediction model to determine the ground sonic boom intensity corresponding to the pressure distribution data of the surface to be detected.

2. The method for predicting aircraft sonic boom intensity according to claim 1, characterized in that: Based on the number and arrangement positions of the pressure measuring holes on the aircraft surface, before obtaining the surface pressure distribution data of the aircraft under different flight states, the following steps are also included: For any aircraft configuration, determine the number and arrangement positions of pressure measuring holes on the aircraft surface corresponding to the aircraft configuration; Wherein, the aircraft includes a variety of aircraft configurations; the aircraft configuration includes aircraft layout, wing shape and fuselage size; and a pressure sensor is provided in the pressure measuring hole.

3. The method for predicting aircraft sonic boom intensity according to claim 1, characterized in that: Acquiring the historical surface pressure distribution data and the sound pressure distribution data of the ground sonic boom corresponding to the historical surface pressure distribution data also includes: Based on the flight test, the historical surface pressure distribution data and the sound pressure distribution data of the ground sonic boom corresponding to the historical surface pressure distribution data are obtained.

4. The method for predicting aircraft sonic boom intensity according to claim 1, characterized in that: Based on the data set, taking the historical surface pressure distribution data as input and taking the ground sonic boom intensity corresponding to the historical surface pressure distribution data as output, training a sonic boom prediction model, and determining a trained sonic boom prediction model specifically includes: Inputting the historical surface pressure distribution data and a data set of ground sonic boom intensity corresponding to the historical surface pressure distribution data into the sonic boom prediction model, training the parameters of the sonic boom prediction model with the goal of minimizing the loss value, and determining the trained sonic boom prediction model; Wherein, the loss value is determined based on the predicted value and the true value; the predicted value is the predicted ground sonic boom intensity corresponding to the historical surface pressure distribution data output after the sonic boom prediction model inputs the historical surface pressure distribution data and the data set of the ground sonic boom intensity corresponding to the historical surface pressure distribution data; the true value is the ground sonic boom intensity corresponding to the historical surface pressure distribution data in the data set; the parameters of the sonic boom prediction model include weights and biases.

5. The method for predicting aircraft sonic boom intensity according to claim 1, characterized in that: Determining the sound pressure distribution data of the ground sonic boom corresponding to the historical surface pressure distribution data based on the near-field sound pressure distribution data and the acoustic model specifically includes: Determining the sound pressure distribution data of the ground sonic boom corresponding to the historical surface pressure distribution data according to the near-field sound pressure distribution data and the generalized Burgers equation; wherein the acoustic model includes the generalized Burgers equation; The calculation formula of the generalized Burgers equation is: ； in, It is the sound pressure distribution data of ground sonic boom; is the area of ​​the acoustic tube; is the length of the sound ray; and are the ambient atmospheric density and the speed of sound, respectively; is the nonlinear coefficient; is the diffusion coefficient; For the The sound velocity increment of the molecule; is the delay time of the sound pressure waveform; is the integration variable; For the The relaxation time of a molecule.

6. 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 sonic boom intensity prediction method according to any one of claims 1 to 5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for predicting the intensity of aircraft sonic booms according to any one of claims 1 to 5 is implemented.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for predicting the intensity of aircraft sonic booms according to any one of claims 1 to 5 is implemented.

Images