CN115795282B - Shock tube dynamic pressure reconstruction method, device, electronic equipment and storage medium - Google Patents

Abstract

The invention provides a shock tube dynamic pressure reconstruction method, device, electronic equipment and storage medium. The method includes: acquiring initial dynamic pressure response signals, including vibration signals and response signals; based on variational mode decomposition method and experience The modal decomposition method preprocesses the vibration signal and the response signal to obtain the preprocessed signal and the component signals of the signal in different frequency bands; then the relationship between each component signal obtained according to the correlation coefficient and the preprocessed signal and the denoised vibration signal Construct the training set; build the initial inverse sensor network model based on the Bi-LSTM neural network model, iteratively train the initial inverse sensor network model based on the training set, and obtain the target inverse sensor network model; reconstruct the shock wave using the target inverse sensor network model The dynamic pressure of the shock tube is obtained to obtain the dynamic pressure reconstruction signal of the target shock tube. The shock tube dynamic pressure reconstruction method provided by the present invention can more reasonably and accurately reconstruct the shock tube dynamic pressure signal.

Description

Shock tube dynamic pressure reconstruction method, device, electronic equipment and storage medium

Technical Field

The present invention relates to the field of measurement and testing technology, and in particular to a shock tube dynamic pressure reconstruction method, device, electronic equipment and storage medium.

Background Art

Shock tube dynamic pressure is widely used in explosion testing, medical instruments, material impact testing, aero engines and other fields. In actual measurement, the stable duration of dynamic pressure is generally from a few milliseconds to more than ten milliseconds. The generation of shock tube dynamic pressure is a transient dynamic process, which not only makes the test environment complex but also difficult to control, making it difficult to accurately estimate the dynamic pressure signal, which seriously affects the measurement accuracy of the dynamic pressure signal.

Existing methods all regard the dynamic pressure generated by the shock tube as an ideal step pressure, that is, the amplitude of the dynamic pressure is constant. However, the amplitude of the dynamic pressure generated by the actual shock tube fluctuates over time. Using a constant amplitude to characterize the dynamic pressure of the shock tube has certain idealized assumptions, which will inevitably lead to unreasonable characterization results. In addition, during the operation of the shock tube, when the incident shock wave reaches the end face of the low-pressure chamber, it will generate impact vibration. The pressure sensor installed on the end face will be excited by the dynamic pressure signal and the vibration signal at the same time. The collected pressure sensor output signal is a mixed signal of the dynamic pressure response and the vibration response. The existing method does not consider the influence of the vibration response, resulting in inaccurate dynamic pressure amplitude estimation results.

In summary, the existing technology does not consider the fluctuation characteristics of the shock tube dynamic pressure signal and the influence of the impact vibration on the dynamic pressure reconstruction result when reconstructing the shock tube dynamic pressure, resulting in the lack of rationality and accuracy of the dynamic pressure amplitude estimation result.

Summary of the invention

In view of this, it is necessary to provide a shock tube dynamic pressure reconstruction method, device, electronic device and storage medium to solve the technical problem that when reconstructing the shock tube dynamic pressure in the prior art, the fluctuation characteristics of the shock tube dynamic pressure signal and the influence of the impact vibration on the dynamic pressure reconstruction result are not considered, resulting in the lack of rationality and accuracy of the dynamic pressure amplitude estimation result.

In order to solve the above technical problems, on the one hand, the present invention provides a shock tube dynamic pressure reconstruction method, comprising:

Acquiring an initial dynamic pressure response signal, wherein the initial dynamic pressure response signal includes a vibration signal and a response signal;

Preprocessing the vibration signal and the response signal based on a variational mode decomposition method and an empirical mode decomposition method to obtain a denoised vibration signal, a preprocessed response signal, and component signals of the preprocessed response signal in different frequency bands;

Constructing a training set according to the correlation between the component signals of different frequency bands and the denoised vibration signal and the preprocessed response signal;

Building an initial inverse sensor network model based on the Bi-LSTM neural network model, iteratively training the initial inverse sensor network model based on the training set, and obtaining a target inverse sensor network model;

The real-time dynamic pressure response signal is acquired and input into the target inverse sensing network model after the preprocessing operation, so as to obtain the target shock tube dynamic pressure reconstruction signal.

In some possible implementations, the preprocessing operation on the vibration signal and the response signal based on the variational mode decomposition method and the empirical mode decomposition method to obtain a denoised vibration signal, a preprocessed response signal, and component signals of the preprocessed response signal in different frequency bands includes:

Decomposing the vibration signal based on a variational mode decomposition method to obtain a plurality of vibration mode components, respectively calculating correlation coefficients between the plurality of vibration mode components and the vibration signal, removing high-frequency noise components, and obtaining the denoised vibration signal;

Decomposing the response signal based on a variational mode decomposition method to obtain a plurality of response mode components, and reconstructing the plurality of response mode components based on a sensor ringing frequency to obtain a plurality of reconstructed signals;

Decomposing the plurality of reconstructed signals based on an empirical mode decomposition method to obtain a plurality of reconstructed signal intrinsic mode function components;

respectively calculating correlation coefficients between the plurality of reconstructed signal intrinsic mode function components and the denoised vibration signal, wherein the reconstructed signal corresponding to the reconstructed signal intrinsic mode function component having the largest correlation coefficient with the denoised vibration signal is the preprocessed response signal;

The preprocessed response signal is decomposed based on an empirical mode decomposition method to obtain component signals of the preprocessed response signal in different frequency bands.

In some possible implementations, constructing a training set according to the correlations between the component signals in different frequency bands and the denoised vibration signal and the preprocessed response signal respectively includes:

Calculating the correlation coefficients between the component signals of different frequency bands and the preprocessed response signal and the denoised vibration signal respectively, and taking the component signal with the largest correlation coefficient with the preprocessed response signal among the component signals of different frequency bands as the ringing component signal;

The component signals of the component signals of different frequency bands, except for the ringing frequency component, whose correlation coefficient values with the denoised vibration signal are less than a set threshold, are taken as noise component signals, and the noise component signals are removed to obtain denoised response signals, reconstructed response signals, vibration-related component signals and trend signals;

The training set is constructed based on the reconstructed response signal, the vibration-related component signal and the trend component signal.

In some possible implementations, the trend component signal corresponds to the amplitude of the target shock tube dynamic pressure reconstruction signal, and can reflect the amplitude characteristics of the target shock tube dynamic pressure reconstruction signal.

In some possible implementations, the iteratively training the initial inverse sensor network model based on the training set to obtain the target inverse sensor network model includes:

Constructing a first training set input of an initial inverse sensor network model based on the reconstructed response signal, constructing a second training set input of an initial inverse sensor network model based on the vibration-related component, and constructing a training set output of an initial inverse sensor network model based on the trend component signal;

After setting the number of hidden layers and hyperparameters of the initial inverse sensor network model, iteratively training the initial inverse sensor network model based on the constructed training set;

When the output loss rate of the initial inverse sensor network model is lower than a set loss threshold, the target inverse sensor network model is obtained.

In some possible implementations, after setting the number of hidden layers and hyperparameters of the initial inverse sensing network model, iteratively training the initial inverse sensing network model based on the constructed training set includes:

Setting the number of initial hidden layers of the initial inverse sensing network model, wherein the hidden layer includes a number of neuron units;

Setting hyperparameters of the initial inverse sensor network model, the hyperparameters comprising: optimizer parameters, learning rate, sequence length, and training rounds;

During the iterative training process, the initial hidden layer number, optimizer parameters, learning rate, sequence length and training rounds of the initial inverse sensor network model are adjusted, and the weights and biases of each neuron unit node inside the hidden layer are determined, so that the output of the initial inverse sensor network model minimizes the output root mean square error and reaches the set loss threshold, thereby completing the iterative training process of the initial inverse sensor network model.

In some possible implementations, the real-time dynamic pressure response signal is input into the target inverse sensing network model after the preprocessing operation to obtain a target shock tube dynamic pressure reconstruction signal, including:

Acquire a real-time dynamic pressure response signal of a shock tube sensor, and perform the preprocessing operation on the real-time response signal to obtain the denoised vibration signal and the denoised response signal corresponding to the real-time dynamic pressure response signal;

The denoised vibration signal and denoised response signal corresponding to the real-time dynamic pressure response signal are input into the target inverse sensing network model to obtain the target inverse sensing network model output, and the output is divided by the pressure sensor amplification factor and sensitivity to obtain the target shock tube dynamic pressure reconstruction signal.

On the other hand, the present invention also provides a shock tube dynamic pressure reconstruction device, comprising:

A signal acquisition module, used to acquire an initial dynamic pressure response signal, wherein the initial dynamic pressure response signal includes a vibration signal and a response signal;

A signal processing module, used for performing a preprocessing operation on the vibration signal and the response signal based on a variational mode decomposition method and an empirical mode decomposition method to obtain a denoised vibration signal, a preprocessed response signal, and component signals of the preprocessed response signal in different frequency bands;

A signal construction module, used for constructing a training set according to the correlation between the component signals of different frequency bands and the denoised vibration signal and the preprocessed response signal;

A model training module, used for constructing an initial inverse sensor network model based on the Bi-LSTM neural network model, and iteratively training the initial inverse sensor network model based on the training set to obtain a target inverse sensor network model;

The target reconstruction module is used to obtain the real-time dynamic pressure response signal and input the signal into the target inverse sensing network model after performing the preprocessing operation to obtain the target shock tube dynamic pressure reconstruction signal.

On the other hand, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the shock tube dynamic pressure reconstruction method described in the above implementation method is implemented.

Finally, the present invention also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the shock tube dynamic pressure reconstruction method described in the above implementation manner is implemented.

The beneficial effect of adopting the above-mentioned embodiment is as follows: the shock tube dynamic pressure reconstruction method provided by the present invention, on the one hand, utilizes the variational mode decomposition method and the empirical mode decomposition method to decompose and reconstruct the response signal and the vibration signal, and comprehensively considers the correlation between each component signal and the response signal and the vibration signal, and considers the fluctuation of the actual dynamic pressure amplitude generated by the shock tube over time and the influence of the vibration signal, so that the preprocessed data has higher rationality and accuracy; on the other hand, the inverse sensing network model constructed based on the Bi-LSTM neural network reconstructs the dynamic pressure of the shock tube by adopting bidirectional input, so that the model extracts the signal features more meticulously, further improving the rationality and accuracy of the dynamic pressure reconstruction of the shock tube.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

FIG1 is a schematic flow chart of an embodiment of a shock tube dynamic pressure reconstruction method provided by the present invention;

FIG. 2 is a schematic diagram of a flow chart of an embodiment of step S102 in FIG. 1 provided by the present invention;

FIG3 is a schematic diagram of a flow chart of an embodiment of step S103 in FIG1 provided by the present invention;

FIG4 is a schematic diagram of a flow chart of an embodiment of step S104 in FIG1 provided by the present invention;

FIG5 is a schematic diagram of an embodiment of raw sensor measurement data provided by the present invention;

FIG6 is a schematic diagram of an embodiment of constructing training set data provided by the present invention;

FIG7 is a schematic diagram of an embodiment of a model training result provided by the present invention;

FIG8 is a schematic diagram of an embodiment of a dynamic pressure reconstruction signal provided by the present invention;

FIG9 is a schematic flow chart of an embodiment of a shock tube dynamic pressure reconstruction device provided by the present invention;

FIG. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

DETAILED DESCRIPTION

The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

It should be understood that the schematic drawings are not drawn to scale. The flow chart used in the present invention shows the operations implemented according to some embodiments of the present invention. It should be understood that the operations of the flow chart can be implemented out of order, and the steps without logical context can be reversed or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flow chart under the guidance of the content of the present invention, and can also remove one or more operations from the flow chart.

Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and/or processor systems and/or microcontroller systems.

Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

Before describing the embodiments, the following definitions are given for the relevant terms:

Shock tube: Shock tube is the core equipment for pressure sensor calibration, which is used to generate plane shock waves. The so-called shock wave is a sudden change in pressure at a certain point in the gas, and the pressure wave propagates at high speed. The speed of the wave is related to the strength of the pressure change. The greater the pressure change, the higher the wave speed. During the propagation process, when the wavefront reaches a certain place, the gas pressure, density and temperature there will suddenly change; before the wavefront arrives, the gas will not be disturbed by the wave; after the wavefront passes, the temperature and pressure of the gas behind the wavefront are higher than those in front of the wavefront, and the gas particles flow in the direction of the wavefront, and their speed is lower than the speed of the wavefront.

Bi-LSTM neural network: Bidirectional long short-term memory neural network. Bi-LSTM neural network is a doubly fed neural network consisting of two independent long short-term memory (LSTM) neural networks. The input sequence is input into the two long short-term memory networks in forward order and reverse order respectively, and then feature extraction is performed.

Variational mode decomposition method: (Variational mode decomposition, VMD) is an adaptive, completely non-recursive modal variation and signal processing method. This technology has the advantage of being able to determine the number of modal decompositions. Its adaptability is reflected in determining the number of modal decompositions of a given sequence according to actual conditions. In the subsequent search and solution process, it can adaptively match the optimal center frequency and limited bandwidth of each mode, and can achieve effective separation of intrinsic modal components (IMFs), frequency domain division of signals, and then obtain effective decomposition components of a given signal, and finally obtain the optimal solution to the variational problem. It overcomes the problems of endpoint effects and modal component aliasing in the EMD method, and has a more solid mathematical theoretical foundation. It can reduce the non-stationarity of time series with high complexity and strong nonlinearity, and decompose to obtain relatively stable subsequences containing multiple different frequency scales. It is suitable for non-stationary sequences. The core idea of VMD is to construct and solve variational problems.

Empirical Mode Decomposition (EMD) is a signal processing method in the time-frequency domain that decomposes signals based on the time scale characteristics of the data itself, without presetting any basis functions. EMD has obvious advantages in processing non-stationary and nonlinear data, and is suitable for analyzing non-linear and non-stationary signal sequences with a high signal-to-noise ratio. The key to this method is empirical mode decomposition, which decomposes complex signals into a finite number of intrinsic mode functions (IMFs). The decomposed IMF components contain local characteristic information of the original signal at different time scales.

Based on the description of the above technical terms, the commonly used reconstruction methods of dynamic pressure in the prior art are theoretical calculation method and inverse reconstruction method. The theoretical calculation method uses the propagation characteristics of the incident shock wave in the shock tube and the motion shock wave formula to establish a theoretical amplitude calculation model for the dynamic pressure of the shock tube, and obtains the amplitude of the dynamic pressure of the shock tube by measuring the initial temperature and initial pressure of the low-pressure chamber of the shock tube, as well as the propagation speed of the incident shock wave; the inverse reconstruction method first estimates the trend of the pressure sensor response signal, obtains the stable interval of the trend signal, and then obtains the stable value of the response signal, and finally divides the stable value of the response signal by the sensitivity of the sensor and the acquisition amplification factor to obtain the stable value of the dynamic pressure signal of the shock tube. However, when reconstructing the dynamic pressure of the shock tube, the prior art does not consider the fluctuation characteristics of the dynamic pressure signal of the shock tube and the influence of the impact vibration on the dynamic pressure reconstruction result, resulting in the lack of rationality and accuracy of the dynamic pressure amplitude estimation result. The present invention aims to propose a shock tube dynamic pressure reconstruction method with higher rationality and accuracy.

The specific embodiments are described in detail below. It should be noted that the description order of the following embodiments is not intended to limit the preferred order of the embodiments.

Embodiments of the present invention provide a shock tube dynamic pressure reconstruction method, device, electronic equipment and storage medium.

As shown in FIG. 1 , FIG. 1 is a flow chart of an embodiment of a shock tube dynamic pressure reconstruction method provided by the present invention, and the shock tube dynamic pressure reconstruction method comprises:

S101, obtaining an initial dynamic pressure response signal, wherein the initial dynamic pressure response signal includes a vibration signal and a response signal;

S102, performing a preprocessing operation on the vibration signal and the response signal based on a variational mode decomposition method and an empirical mode decomposition method to obtain a denoised vibration signal, a preprocessed response signal, and component signals of the preprocessed response signal in different frequency bands;

S103, constructing a training set according to the correlation between the component signals of different frequency bands and the denoised vibration signal and the preprocessed response signal;

S104, constructing an initial inverse sensor network model based on the Bi-LSTM neural network model, and iteratively training the initial inverse sensor network model based on the training set to obtain a target inverse sensor network model;

S105, acquiring a real-time dynamic pressure response signal and performing the preprocessing operation thereon, and then inputting the signal into the target inverse sensing network model to obtain a target shock tube dynamic pressure reconstruction signal.

Compared with the prior art, the shock tube dynamic pressure reconstruction method provided by the embodiment of the present invention, on the one hand, utilizes the variational mode decomposition method and the empirical mode decomposition method to decompose and reconstruct the response signal and the vibration signal, and comprehensively considers the correlation between each component signal and the response signal and the vibration signal, and considers the fluctuation of the actual dynamic pressure amplitude generated by the shock tube over time and the influence of the vibration signal, so that the preprocessed data has higher rationality and accuracy. On the other hand, the inverse sensing network model constructed based on the Bi-LSTM neural network reconstructs the dynamic pressure of the shock tube by adopting bidirectional input, so that the model extracts the signal features more meticulously, further improving the rationality and accuracy of the dynamic pressure reconstruction of the shock tube.

Furthermore, in some embodiments of the present invention, in step S101, when obtaining the initial response signal of the shock tube sensor, since during the operation of the shock tube, the incident shock wave will generate impact vibration when it reaches the end face of the low-pressure chamber, the pressure sensor installed on the end face will be excited by the dynamic pressure signal and the vibration signal at the same time, and the collected output signal of the pressure sensor is a mixed signal of the dynamic pressure response and the vibration response. The vibration signal can be collected separately using an acceleration sensor, so the initial response signal includes the vibration signal and the response signal.

It should be noted that in step S105, the real-time response signal of the shock tube sensor is obtained and preprocessed by using the empirical mode decomposition method and variational mode decomposition method in step S102 to preprocess the real-time response signal.

Further, in some embodiments of the present invention, as shown in FIG. 2 , FIG. 2 is a flow chart of an embodiment of step S102 in FIG. 1 provided by the present invention, and step S102 includes:

S201, decomposing the vibration signal based on a variational mode decomposition method to obtain a plurality of vibration mode components, respectively calculating correlation coefficients between the plurality of vibration mode components and the vibration signal, removing high-frequency noise components, and obtaining the denoised vibration signal;

S202, decomposing the response signal based on a variational mode decomposition method to obtain a plurality of response mode components, and reconstructing the plurality of response mode components based on a sensor ringing frequency to obtain a plurality of reconstructed signals;

S203, decomposing the multiple reconstructed signals based on an empirical mode decomposition method to obtain multiple reconstructed signal intrinsic mode function components;

S204, respectively calculating the correlation coefficients between the plurality of reconstructed signal intrinsic mode function components and the denoised vibration signal, wherein the reconstructed signal corresponding to the reconstructed signal intrinsic mode function component having the largest correlation coefficient with the denoised vibration signal is the preprocessed response signal;

S205 . Decompose the preprocessed response signal based on an empirical mode decomposition method to obtain component signals of the preprocessed response signal in different frequency bands.

Further, as shown in FIG. 3 , FIG. 3 is a flow chart of an embodiment of step S103 in FIG. 1 provided by the present invention, and step S103 includes:

S301, respectively calculating the correlation coefficients between the component signals of different frequency bands and the preprocessed response signal and the denoised vibration signal, and taking the component signal of the component signals of different frequency bands having the largest correlation coefficient with the preprocessed response signal as the ringing component signal;

S301, taking component signals of the component signals of different frequency bands, except for the ringing frequency component, whose correlation coefficient values with the denoised vibration signal are less than a set threshold as noise component signals, and removing the noise component signals to obtain denoised response signals, reconstructed response signals, vibration-related component signals and trend signals;

S301 , constructing the training set based on the reconstructed response signal, the vibration-related component signal and the trend component signal.

The trend component signal corresponds to the amplitude of the target shock tube dynamic pressure reconstruction signal, and can reflect the amplitude characteristics of the target shock tube dynamic pressure reconstruction signal.

进行分解，VMD可将振动信号

分解为k个窄带bimfs，表示为

，其中心频率为

，

和

可通过求解变分问题得到：In a specific embodiment of the present invention, the vibration signal is first decomposed using a variational mode decomposition method.

VMD can decompose the vibration signal

Decomposed into k narrowband bimfs, expressed as

, whose center frequency is

,

and

It can be obtained by solving the variational problem:

(1)

(1)

(2)

(2)

表示求偏导，

表示狄拉克分布函数，

分别对应分解后第k个模态分量和中心频率。in,

represents partial derivative,

represents the Dirac distribution function,

They correspond to the kth modal component and center frequency after decomposition respectively.

及其对应的中心频率

，如下：The quadratic penalty function and Lagrangian operator are used to solve the above constrained optimization problem, and the alternating direction method of Lagrangian operator is used to calculate the decomposed mode

and its corresponding center frequency

,as follows:

(3)

(3)

(4)

(4)

分别对应

的傅里叶变换。In the formula,

Corresponding to

The Fourier transform of .

可表示为：The obtained vibration modal components

It can be expressed as:

(5)

(5)

表示k个模态分量。In the formula,

represents k modal components.

与各振动模态分量

之间的相关系数CC，如下：Get the calculated vibration signal

And each vibration mode component

The correlation coefficient CC between them is as follows:

(6)

(6)

和

表示振动信号和第i个模态分量对应的离散信号；

和

分别表示

和

的平均值；N为信号长度。In the formula,

and

Represents the discrete signal corresponding to the vibration signal and the i-th modal component;

and

Respectively

and

The average value of; N is the signal length.

，可表示为：According to the meaning of the correlation coefficient, the component with a correlation coefficient less than 0.2 is taken as the noise component signal and removed to obtain the denoised vibration signal.

, which can be expressed as:

(7)

(7)

为高频噪声分量。In the formula,

is the high frequency noise component.

分解为K个响应模态分量

，首先将中心频率小于等于传感器振铃频率的几个分量进行重构，得到基信号

；剩余分量依据中心频率大小依次加入到基信号中进行信号重构，基信号

以及重构信号

表达式为：Furthermore, the response signal is transformed into

Decomposed into K response mode components

First, reconstruct several components whose center frequency is less than or equal to the sensor ringing frequency to obtain the base signal

; The remaining components are added to the base signal in turn according to the center frequency for signal reconstruction.

And reconstruct the signal

The expression is:

(8)

(8)

(9)

(9)

；

；

代表第J个重构信号。In the formula,

;

;

Represents the Jth reconstructed signal.

The above reconstructed signals are processed in sequence using the empirical mode decomposition method to obtain a series of narrowband components, which are called intrinsic mode functions.

Each intrinsic mode function must satisfy the following two conditions: (1) the number of extreme points and zero-crossing points in the entire data set is equal or differs by at most one; (2) at any time, the mean of the upper envelope estimated by the local maximum point and the lower envelope estimated by the local minimum point is zero.

The basic steps of decomposition are as follows:

的局部极小值点和局部极大值点；Step (1): Identify the reconstructed signal

The local minimum and local maximum points of ;

的下包络线

和上包络线

，计算上包络线和下包络线的均值为：Step (2): Use cubic spline curves to connect all local minimum points and local maximum points respectively, and obtain

The lower envelope of

and upper envelope

, calculate the mean of the upper envelope and the lower envelope as:

(10)

(10)

中减去

，得到差值信号为：Step (3): From the signal

Minus

, the difference signal is:

(11)

(11)

满足本征模态函数的两个条件，则

为

的第一个本征模态函数分量；否则，令

，重复步骤(1)至步骤(3)计算过程k次，直到得到的

满足本征模态函数的两个条件，此时

的第一个本征模态函数分量

为：if

If the two conditions of the eigenmode function are met, then

for

The first eigenmode function component of ; otherwise, let

Repeat steps (1) to (3) k times until the obtained

The two conditions of the eigenmode function are met, then

The first intrinsic mode function component of

for:

(12)

(12)

中减去

，得到残余信号

为Step (4): Reconstruct the signal from

Minus

, and the residual signal is obtained

for

(13)

(13)

，重复步骤(1)到步骤(4)计算过程i次，得到第i个本征模态函数分量为：make

, repeat steps (1) to (4) for i times, and get the i-th intrinsic mode function component as:

(14)

(14)

成为单调函数或者只包含一个极值点，此时从

中无法再分解出本征模态函数分量。综合式(13)和式(14)，重构信号

表示为:Continue the above decomposition process until the final residual component

Become a monotonic function or contain only one extreme point.

The intrinsic mode function components can no longer be decomposed. Combining equations (13) and (14), the reconstructed signal

Expressed as:

(15)

(15)

被分解为个h个重构信号的本征模态函数分量IMF和一个残余分量，并且这些分量的频段由高到低变化。Therefore, the reconstructed signal

It is decomposed into h intrinsic mode function components IMF of the reconstructed signal and a residual component, and the frequency bands of these components change from high to low.

与去噪振动信号

之间的相关系数，找到其中的最大相关系数，其对应的重构信号即为预处理信号

。如下：Calculate all component signals obtained by the empirical mode decomposition method

With denoised vibration signal

The correlation coefficient between them is found, and the corresponding reconstructed signal is the preprocessed signal

.as follows:

(16)

(16)

，

为

分解的本征模态分量

为趋势分量。In the formula,

,

for

Decomposed eigenmode components

is the trend component.

和

；将

中相关系数最大的分量信号作为振铃分量信号，并为最大保留振动信号成分，将

中除振铃频率分量外，数值小于0.1的分量信号作为噪声分量信号，予以剔除，得到压力传感器重构响应信号

和去噪响应信号

。如下：Based on the idea of retaining the vibration signal components to the greatest extent, the correlation coefficients between each imf(t) component signal and the preprocessed signal and the denoised vibration signal are calculated respectively, which can be expressed as

and

;Will

The component signal with the largest correlation coefficient is taken as the ringing component signal, and the vibration signal component is retained as the maximum.

Except for the ringing frequency component, the component signal with a value less than 0.1 is treated as a noise component signal and removed to obtain the reconstructed response signal of the pressure sensor.

and the denoised response signal

.as follows:

(17)

(17)

(18)

(18)

为振动相关分量信号，

，其中

。In the formula,

is the vibration related component signal,

,in

.

The embodiment of the present invention decomposes and reconstructs the response signal and the vibration signal by using the variational mode decomposition method and the empirical mode decomposition method, and comprehensively considers the correlation between each component signal and the response signal and the vibration signal, and also considers the fluctuation of the actual dynamic pressure amplitude generated by the shock tube over time and the influence of the vibration signal, so that the preprocessed data has higher rationality and accuracy.

Further, in some embodiments of the present invention, as shown in FIG. 4 , FIG. 4 is a flow chart of an embodiment of step S104 in FIG. 1 provided by the present invention, and step S103 includes:

S401, constructing a first training set input of an initial inverse sensor network model based on the reconstructed response signal, constructing a second training set input of an initial inverse sensor network model based on the vibration-related component, and constructing a training set output of an initial inverse sensor network model based on the trend component signal;

S402, after setting the number of hidden layers and hyper parameters of the initial inverse sensor network model, iteratively training the initial inverse sensor network model based on the constructed training set;

S403: When the output loss rate of the initial inverse sensor network model is lower than a set loss threshold, the target inverse sensor network model is obtained.

Wherein, step S402 specifically includes:

Setting the number of initial hidden layers of the initial inverse sensing network model, wherein the hidden layer includes a number of neuron units;

Setting hyperparameters of the initial inverse sensor network model, the hyperparameters comprising: optimizer parameters, learning rate, sequence length, and training rounds;

During the iterative training process, the initial hidden layer number, optimizer parameters, learning rate, sequence length and training rounds of the initial inverse sensor network model are adjusted, and the weights and biases of each neuron unit node inside the hidden layer are determined, so that the output of the initial inverse sensor network model minimizes the output root mean square error and reaches the set loss threshold, thereby completing the iterative training process of the initial inverse sensor network model.

In a specific embodiment of the present invention, the variational mode decomposition method and the empirical mode decomposition method are performed on the initial response signal of the shock tube to obtain the relevant data required for constructing the inverse sensing network model training set, the first training set input of the inverse sensing network is constructed by the reconstructed response signal of the pressure sensor, the second training set input of the inverse sensing network is constructed by the vibration-related components, and the inverse sensing network training set output is constructed by the trend component signal.

Among them, the initial inverse sensing network model based on the Bi-LSTM neural network is established, which mainly includes three parts: setting the number of hidden layers, hyperparameter setting and learning and training.

The hidden layer performs the function of information transmission within the neural network, that is, the information transmitted by the input layer is processed by multiple hidden layers to obtain the output layer; the hidden layer is composed of several neural units, and a working neural unit is composed of a forget gate, an input gate, a temporary cell state, a cell state, an output gate, and a hidden layer state. Among them, the forget gate determines how much of the cell state of the previous moment is retained to the current moment, the input gate determines how much of the network input at the current moment is saved to the cell state, the temporary cell state and the input gate work together to update the cell state, the cell state provides the update of the next cell state, and the output gate works together with the hidden layer state and the cell state to provide the update of the next cell hidden layer state. The working principle is as follows:

(19)

(19)

(20)

(20)

(21)

(twenty one)

(22)

(twenty two)

(23)

(twenty three)

(24)

(twenty four)

、

、

、

、

、

分别为遗忘门、输入门、临时细胞状态、细胞状态、输出门和隐层状态，

为权重、

为偏置。Where:

,

,

,

,

,

They are forget gate, input gate, temporary cell state, cell state, output gate and hidden layer state.

For weight,

For bias.

Hyperparameter setting is to set the optimizer, learning rate, sequence length, training rounds, etc.

Neural network learning is to determine the weights and biases of each neural unit node in the hidden layer based on training samples. Neural network training is to find suitable weights and biases to minimize the output root mean square error. When the model output loss rate is lower than the given loss threshold, the identification of the inverse sensor network model is completed and the target inverse sensor network model is obtained.

It should be noted that when establishing the inverse sensor network model, the hyperparameters in the inverse sensor network, including the number of hidden unit layers, learning rate, learning descent rate, optimizer and number of training times, are adjusted so that the model output loss rate is lower than the set loss threshold to complete the identification of the inverse sensor network model.

The embodiment of the present invention constructs an inverse sensing network model based on a bidirectional long short-term memory neural network, and performs iterative training through a training set to determine the number of hidden layers and hyperparameters of the neural network, so that the loss rate of the model output is reduced, and the accuracy and rationality of the shock tube reconstructing the dynamic pressure are further improved.

Further, in some embodiments of the present invention, step S105 includes:

Acquire a real-time response signal of a shock tube sensor, and perform the preprocessing operation on the real-time response signal to obtain the denoised vibration signal and the denoised response signal corresponding to the real-time response signal;

The denoised vibration signal and denoised response signal corresponding to the real-time response signal are input into the target inverse sensing network model to obtain the target inverse sensing network model output, and the output is divided by the pressure sensor amplification factor and sensitivity to obtain the target shock tube dynamic pressure reconstruction signal.

In a specific embodiment of the present invention, for the real-time acquired shock tube sensor response signal, the same empirical mode decomposition method and variational mode decomposition method in the above embodiment are used to preprocess the real-time response signal, and the obtained denoised response signal and denoised vibration signal are used as the input of the target inverse sensing network model. The output of the model is divided by the pressure sensor amplification factor and sensitivity to obtain the target shock tube dynamic pressure reconstruction signal, wherein the relationship between the dynamic pressure reconstruction signal and the output of the inverse sensing network model is:

(24)

(twenty four)

为放大系数，S为灵敏度。In the formula,

is the amplification factor and S is the sensitivity.

The inverse sensing network model constructed based on the Bi-LSTM neural network in the embodiment of the present invention reconstructs the dynamic pressure of the shock tube by adopting bidirectional input, so that the model extracts signal features more carefully, further improving the rationality and accuracy of the dynamic pressure reconstruction of the shock tube.

In order to more intuitively reflect the rationality and accuracy of the shock tube dynamic pressure reconstruction method provided by the present invention, the dynamic pressure response data and vibration signal data generated by the shock tube system are measured by ENDEVCO 8510B PR pressure sensor and YA1102 ICP acceleration sensor for analysis, wherein the pressure sensor sensitivity is 0.16V/MPa, the amplification factor is 50, and the data sampling frequency is 5MHz, and dynamic pressure reconstruction is performed:

The original measurement data of the ENDEVCO 8510B PR pressure sensor and the YA1102 ICP acceleration sensor are shown in FIG5 , which is a schematic diagram of an embodiment of the original measurement data of the sensor provided by the present invention.

The response signal and the vibration signal in FIG5 are processed using the same empirical mode decomposition method and variational mode decomposition method as in the above embodiment to obtain the inverse sensing network training set as shown in FIG6 , which is a schematic diagram of an embodiment of constructing training set data provided by the present invention.

The training result of the target inverse sensor network model obtained by iterative training of the training set in FIG6 is shown in FIG7 , which is a schematic diagram of an embodiment of the model training result provided by the present invention.

The dynamic pressure reconstruction signal obtained by using the target inverse sensing network model obtained in FIG. 7 is shown in FIG. 8 , which is a schematic diagram of an embodiment of the dynamic pressure reconstruction signal provided by the present invention.

It can be seen from Figures 5 to 8 above that the shock tube dynamic pressure reconstruction signal obtained by the shock tube dynamic pressure reconstruction method provided by an embodiment of the present invention takes into account the influence of the vibration signal and the time-varying characteristics of the dynamic pressure amplitude of the shock tube. This makes the shock tube dynamic pressure reconstruction signal more reasonably and accurately restore the dynamic pressure signal generated by the shock tube.

In order to better implement the shock tube dynamic pressure reconstruction method in the embodiment of the present invention, on the basis of the shock tube dynamic pressure reconstruction method, the embodiment of the present invention also provides a shock tube dynamic pressure reconstruction device, as shown in FIG9 , the shock tube dynamic pressure reconstruction device 900 includes:

A signal acquisition module 901 is used to acquire an initial dynamic pressure response signal, wherein the initial dynamic pressure response signal includes a vibration signal and a response signal;

The signal processing module 902 is used to perform a preprocessing operation on the vibration signal and the response signal based on a variational mode decomposition method and an empirical mode decomposition method to obtain a denoised vibration signal, a preprocessed response signal, and component signals of the preprocessed response signal in different frequency bands;

A signal construction module 903, configured to construct a training set according to the correlation between the component signals of different frequency bands and the denoised vibration signal and the preprocessed response signal;

A model training module 904 is used to construct an initial inverse sensor network model based on the Bi-LSTM neural network model, and iteratively train the initial inverse sensor network model based on the training set to obtain a target inverse sensor network model;

The target reconstruction module 905 is used to obtain the real-time dynamic pressure response signal and input the signal into the target inverse sensing network model after performing the preprocessing operation to obtain the target shock tube dynamic pressure reconstruction signal.

The shock tube dynamic pressure reconstruction device 900 provided in the above embodiment can implement the technical solution described in the above shock tube dynamic pressure reconstruction method embodiment. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above shock tube dynamic pressure reconstruction method embodiment, which will not be repeated here.

As shown in FIG10 , the present invention also provides an electronic device 1000. The electronic device 1000 includes a processor 1001, a memory 1002, and a display 1003. FIG10 only shows some components of the electronic device 1000, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

In some embodiments, the processor 1001 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 1002, such as the shock tube dynamic pressure reconstruction program in the present invention.

In some embodiments, the processor 1001 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 1001 may be local or remote. In some embodiments, the processor 1001 may be implemented in a cloud platform. In one embodiment, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.

In some embodiments, the memory 1002 may be an internal storage unit of the electronic device 1000, such as a hard disk or memory of the electronic device 1000. In other embodiments, the memory 1002 may also be an external storage device of the electronic device 1000, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 1000.

Furthermore, the memory 1002 may include both an internal storage unit of the electronic device 1000 and an external storage device. The memory 1002 is used to store application software installed in the electronic device 1000 and various data.

In some embodiments, the display 1003 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 1003 is used to display information on the electronic device 1000 and to display a visual user interface. The components 1001-1003 of the electronic device 1000 communicate with each other via a system bus.

In one embodiment, when the processor 1001 executes the shock tube dynamic pressure reconstruction program in the memory 1002, the following steps may be implemented:

Acquiring an initial dynamic pressure response signal, wherein the initial dynamic pressure response signal includes a vibration signal and a response signal;

Preprocessing the vibration signal and the response signal based on a variational mode decomposition method and an empirical mode decomposition method to obtain a denoised vibration signal, a preprocessed response signal, and component signals of the preprocessed response signal in different frequency bands;

Constructing a training set according to the correlation between the component signals of different frequency bands and the denoised vibration signal and the preprocessed response signal;

Building an initial inverse sensor network model based on the Bi-LSTM neural network model, iteratively training the initial inverse sensor network model based on the training set, and obtaining a target inverse sensor network model;

The real-time dynamic pressure response signal is acquired and input into the target inverse sensing network model after the preprocessing operation, so as to obtain the target shock tube dynamic pressure reconstruction signal.

It should be understood that: when the processor 1001 executes the shock tube dynamic pressure reconstruction program in the memory 1002, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.

Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 1000 mentioned, and the electronic device 1000 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 1000 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

Accordingly, an embodiment of the present application also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, it can implement the steps or functions of the shock tube dynamic pressure reconstruction method provided in the above-mentioned method embodiments.

Those skilled in the art can understand that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

The above is a detailed introduction to the shock tube dynamic pressure reconstruction method, device, electronic device and storage medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the idea of the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims (7)

1. The shock tube dynamic pressure reconstruction method is characterized by comprising the following steps of:

acquiring an initial dynamic pressure response signal, wherein the initial dynamic pressure response signal comprises a vibration signal and a response signal;

preprocessing the vibration signal and the response signal based on a variation modal decomposition method and an empirical modal decomposition method to obtain a denoising vibration signal, a preprocessing response signal and component signals of the preprocessing response signal in different frequency bands;

constructing a training set according to the correlation between the component signals of different frequency bands and the denoising vibration signal and the preprocessing response signal respectively;

constructing an initial inverse sensing network model based on the Bi-LSTM neural network model, and iteratively training the initial inverse sensing network model based on the training set to obtain a target inverse sensing network model;

acquiring a real-time dynamic pressure response signal, inputting the real-time dynamic pressure response signal into the target inverse sensing network model after the preprocessing operation, and obtaining a target shock tube dynamic pressure reconstruction signal;

the preprocessing operation is performed on the vibration signal and the response signal based on the variation modal decomposition method and the empirical modal decomposition method to obtain a denoising vibration signal, a preprocessing response signal and component signals of the preprocessing response signal in different frequency bands, and the preprocessing method comprises the following steps:

Decomposing the vibration signal based on a variation mode decomposition method to obtain a plurality of vibration mode components, respectively calculating correlation coefficients of the vibration mode components and the vibration signal, and removing high-frequency noise components to obtain the denoising vibration signal;

decomposing the response signals based on a variation modal decomposition method to obtain a plurality of response modal components, and reconstructing the plurality of response modal components based on sensor ringing frequency to obtain a plurality of reconstructed signals;

decomposing the plurality of reconstructed signals based on an empirical mode decomposition method to obtain a plurality of reconstructed signal eigenmode function components;

calculating correlation coefficients of the plurality of reconstructed signal eigenmode function components and the denoising vibration signal respectively, wherein a reconstructed signal corresponding to the reconstructed signal eigenmode function component with the largest correlation coefficient of the denoising vibration signal is the preprocessing response signal;

decomposing the preprocessing response signal based on an empirical mode decomposition method to obtain component signals of the preprocessing response signal in different frequency bands;

the constructing a training set according to the correlation between the component signals of the different frequency bands and the denoising vibration signal and the preprocessing response signal respectively comprises the following steps:

Calculating correlation coefficients between the component signals of different frequency bands and the preprocessing response signals and the denoising vibration signals respectively, and taking the component signal with the largest correlation coefficient with the preprocessing response signals in the component signals of different frequency bands as a ringing component signal;

taking a component signal, except for a ringing frequency component, of the component signals in different frequency bands, of which the correlation coefficient value with a denoising vibration signal is smaller than a set threshold value as a noise component signal, and removing the noise component signal to obtain a denoising response signal, a reconstruction response signal, a vibration correlation component signal and a trend component signal;

constructing the training set based on the reconstructed response signal, the vibration-related component signal, and the trend component signal;

the training set based on the training iteration training of the initial inverse sensor network model, to obtain a target inverse sensor network model, includes:

constructing a first training set input of an initial inverse sensing network model based on the reconstruction response signal, constructing a second training set input of the initial inverse sensing network model based on the vibration related component, and taking the trend component signal as an output of the initial inverse sensing network model;

after setting the hidden layer number and super parameters of the initial inverse sensor network model, carrying out iterative training on the initial inverse sensor network model based on the constructed training set;

And when the output loss rate of the initial inverse sensor network model is lower than a set loss threshold value, obtaining the target inverse sensor network model.

2. The shock tube dynamic pressure reconstruction method of claim 1 wherein the trend component signal corresponds to the target shock tube dynamic pressure reconstruction signal amplitude.

3. The shock tube dynamic pressure reconstruction method according to claim 1, wherein after setting the hidden layer number and the super parameter of the initial inverse sensor network model, performing iterative training on the initial inverse sensor network model based on the constructed training set comprises:

setting an initial hidden layer number of the initial inverse sensing network model, wherein the hidden layer comprises a plurality of neuron units;

setting super parameters of the initial inverse sensor network model, wherein the super parameters comprise: optimizer parameters, learning rate, sequence length and training rounds;

and in the iterative training process, the initial hidden layer number, the optimizer parameters, the learning rate, the sequence length and the training rounds of the initial inverse sensor network model are adjusted, the weight and the bias of each neuron unit node in the hidden layer are determined, the output root mean square error of the initial inverse sensor network model is enabled to be minimum, the set loss threshold is reached, and the iterative training process of the initial inverse sensor network model is completed.

4. The shock tube dynamic pressure reconstruction method as set forth in claim 3 wherein said obtaining a dynamic pressure real-time response signal and inputting said pre-processing operation into said target inverse sensor network model to obtain a target shock tube dynamic pressure reconstruction signal comprises:

acquiring a real-time dynamic pressure response signal of the shock tube sensor, and performing the preprocessing operation on the real-time response signal to obtain a denoising vibration signal and a denoising response signal corresponding to the real-time dynamic pressure response signal;

and inputting the denoising vibration signal and the denoising response signal corresponding to the real-time dynamic pressure response signal into the target inverse sensing network model to obtain target inverse sensing network model output, and dividing the output by the amplification factor and the sensitivity of the pressure sensor to obtain the target shock tube dynamic pressure reconstruction signal.

5. A shock tube dynamic pressure reconstruction device, comprising:

the signal acquisition module is used for acquiring an initial dynamic pressure response signal, wherein the initial dynamic pressure response signal comprises a vibration signal and a response signal;

the signal processing module is used for preprocessing the vibration signal and the response signal based on a variation modal decomposition method and an empirical modal decomposition method to obtain a denoising vibration signal, a preprocessing response signal and component signals of the preprocessing response signal in different frequency bands;

The signal construction module is used for constructing a training set according to the correlation between the component signals of the different frequency bands and the denoising vibration signal and the preprocessing response signal respectively;

the model training module is used for constructing an initial inverse sensing network model based on the Bi-LSTM neural network model, and iteratively training the initial inverse sensing network model based on the training set to obtain a target inverse sensing network model;

the target reconstruction module is used for acquiring a real-time dynamic pressure response signal, inputting the real-time dynamic pressure response signal into the target inverse sensing network model after the preprocessing operation, and obtaining a target shock tube dynamic pressure reconstruction signal;

the preprocessing operation is performed on the vibration signal and the response signal based on the variation modal decomposition method and the empirical modal decomposition method to obtain a denoising vibration signal, a preprocessing response signal and component signals of the preprocessing response signal in different frequency bands, and the preprocessing method comprises the following steps:

decomposing the vibration signal based on a variation mode decomposition method to obtain a plurality of vibration mode components, respectively calculating correlation coefficients of the vibration mode components and the vibration signal, and removing high-frequency noise components to obtain the denoising vibration signal;

decomposing the response signals based on a variation modal decomposition method to obtain a plurality of response modal components, and reconstructing the plurality of response modal components based on sensor ringing frequency to obtain a plurality of reconstructed signals;

Decomposing the plurality of reconstructed signals based on an empirical mode decomposition method to obtain a plurality of reconstructed signal eigenmode function components;

calculating correlation coefficients of the plurality of reconstructed signal eigenmode function components and the denoising vibration signal respectively, wherein a reconstructed signal corresponding to the reconstructed signal eigenmode function component with the largest correlation coefficient of the denoising vibration signal is the preprocessing response signal;

decomposing the preprocessing response signal based on an empirical mode decomposition method to obtain component signals of the preprocessing response signal in different frequency bands;

the constructing a training set according to the correlation between the component signals of the different frequency bands and the denoising vibration signal and the preprocessing response signal respectively comprises the following steps:

calculating correlation coefficients between the component signals of different frequency bands and the preprocessing response signals and the denoising vibration signals respectively, and taking the component signal with the largest correlation coefficient with the preprocessing response signals in the component signals of different frequency bands as a ringing component signal;

taking a component signal, except for a ringing frequency component, of the component signals in different frequency bands, of which the correlation coefficient value with a denoising vibration signal is smaller than a set threshold value as a noise component signal, and removing the noise component signal to obtain a denoising response signal, a reconstruction response signal, a vibration correlation component signal and a trend component signal;

Constructing the training set based on the reconstructed response signal, the vibration-related component signal, and the trend component signal;

the training set based on the training iteration training of the initial inverse sensor network model, to obtain a target inverse sensor network model, includes:

constructing a first training set input of an initial inverse sensing network model based on the reconstruction response signal, constructing a second training set input of the initial inverse sensing network model based on the vibration related component, and taking the trend component signal as an output of the initial inverse sensing network model;

after setting the hidden layer number and super parameters of the initial inverse sensor network model, carrying out iterative training on the initial inverse sensor network model based on the constructed training set;

and when the output loss rate of the initial inverse sensor network model is lower than a set loss threshold value, obtaining the target inverse sensor network model.

6. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the shock tube dynamic pressure reconstruction method according to any one of claims 1 to 4 when the program is executed by the processor.

7. A computer readable storage medium having stored thereon a computer program, which when executed by a processor, implements a shock tube dynamic pressure reconstruction method according to any one of claims 1 to 4.

Images