An absorbent electromagnetic parameter prediction method, system, device and medium

Abstract

The application discloses an absorbent electromagnetic parameter prediction method, system, device and medium, and relates to the technical field of material science. The method comprises the following steps: acquiring to-be-measured data; the to-be-measured data comprises frequency, particle size characteristics and physical heuristic characteristics; an electromagnetic parameter prediction model is constructed based on a multi-branch neural network; the multi-branch neural network comprises an input layer, a shared feature extraction layer, a branch layer, a deep connection layer and an output layer which are connected in sequence; the to-be-measured data is input into the electromagnetic parameter prediction model, and an electromagnetic parameter prediction result of an absorbent is output; the electromagnetic parameter prediction result comprises a dielectric constant real part, a dielectric constant imaginary part, a magnetic permeability real part and a magnetic permeability imaginary part. The application can improve the prediction accuracy of the electromagnetic parameters of the absorbent.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of material science, in particular to an electromagnetic parameter prediction method, system, device and medium for an absorbent. BACKGROUND

[0002] For electromagnetic wave absorbers, the most core index is its electromagnetic parameter. Generally, the related requirements of the standard test method for measuring relative complex permittivity and relative magnetic permeability of solid materials at microwave frequencies using coaxial air line (ASTM D7449M −22a) are referred to, and a vector network analyzer is combined with an air transmission line to measure the dielectric constant and magnetic permeability of the absorbent in a certain frequency range, such as a 0.5-18GHz frequency band. However, this testing process is relatively complex. On the one hand, the absorbent needs to be fully mixed with paraffin in a molten state, and then a sample suitable for being placed in the air transmission line is prepared. On the other hand, the calibration of the vector network analyzer and the testing process are also relatively strict. Relatively speaking, it is simpler and faster to measure the particle size distribution of the absorbent. For example, according to the requirements of GB / T 41949-2022, the particle size distribution parameters of the absorbent, including D10 / D50 / D90, specific surface area, and particle size distribution width, can be directly obtained by using a laser particle size analyzer. If the electromagnetic parameters can be accurately predicted by the particle size distribution parameters, the testing process can be simplified, and the research and preparation of the absorbent can be accelerated.

[0003] However, the traditional electromagnetic parameter prediction relies on physical simulation calculation, which is time-consuming and requires accurate material models. The existing machine learning method uses a single path network, which cannot effectively separate the physical mechanisms of dielectric / magnetic permeability, and the nonlinear relationship between the particle size distribution characteristics and the electromagnetic response is difficult to represent by a simple model. SUMMARY

[0004] The purpose of the present application is to provide an electromagnetic parameter prediction method, system, device and medium for an absorbent, which aims to solve or improve at least one of the above technical problems.

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

[0006] An electromagnetic parameter prediction method for an absorbent, comprising:

[0007] acquiring test data; the test data includes frequency, particle size characteristics and physical heuristic characteristics;

[0008] The electromagnetic parameter prediction model is constructed based on a multi-branch neural network; the multi-branch neural network comprises an input layer, a shared feature extraction layer, a branch layer, a deep connection layer and an output layer connected in sequence;

[0009] The to-be-tested data is input into the electromagnetic parameter prediction model, and an electromagnetic parameter prediction result of the absorbent is output; the electromagnetic parameter prediction result comprises a real part of a dielectric constant, an imaginary part of the dielectric constant, a real part of a magnetic permeability and an imaginary part of the magnetic permeability.

[0010] Optionally, the construction process of the electromagnetic parameter prediction model comprises:

[0011] The particle size characteristic data is loaded, and electromagnetic parameter data is integrated to obtain characteristic correlation data; the characteristic correlation data comprises electromagnetic parameters at all frequency points and corresponding particle size characteristics;

[0012] The characteristic correlation data is subjected to target separation, and original characteristics and corresponding target variables are labeled; the original characteristics are frequency and particle size characteristics; the target variables are a real part of a dielectric constant, an imaginary part of the dielectric constant, a real part of a magnetic permeability and an imaginary part of the magnetic permeability;

[0013] The physical heuristic characteristics are constructed based on the characteristic correlation data, and the physical heuristic characteristics are spliced with the original characteristics to obtain an updated training data set; the updated training data set comprises target variables corresponding to the spliced characteristic data set;

[0014] The updated training data set is input into the multi-branch neural network for network parameter optimization training, and the trained network is determined as the electromagnetic parameter prediction model.

[0015] Optionally, the physical heuristic characteristics comprise an inverse of the frequency, a ratio of a particle size parameter D50 to a wavelength, a logarithm of a specific surface area, and a ratio of a particle size distribution width to a normalized D50.

[0016] Optionally, the shared feature extraction layer comprises a first fully connected layer, a first batch normalization layer, a first LeakyReLU activation layer and a Dropout layer connected in sequence; the first fully connected layer comprises 256 neurons, the first batch normalization layer adopts z-score for standardization processing of data, the first LeakyReLU activation layer adopts a negative slope of 0.2, and the Dropout layer adopts a dropout probability of 0.3.

[0017] Optionally, the branch layer comprises a dielectric constant branch and a magnetic permeability branch which have the same structure; the dielectric constant branch and the magnetic permeability branch each comprise two operation modules connected in sequence; each operation module comprises a fully connected layer, a batch normalization layer and a LeakyReLU activation layer;

[0018] Among them, the full connection layer in the first operation module of the two branches contains 128 neurons, the full connection layer in the second operation module contains 64 neurons, and the LeakyReLU activation layer in the two operation modules adopts a negative slope of 0.2.

[0019] The application further provides an absorbent electromagnetic parameter prediction system, comprising:

[0020] A data acquisition unit is configured to acquire to-be-measured data, wherein the to-be-measured data comprises frequency, particle size characteristics and physical heuristic characteristics.

[0021] A model construction unit is configured to construct an electromagnetic parameter prediction model based on a multi-branch neural network, wherein the multi-branch neural network comprises an input layer, a shared feature extraction layer, a deep connection layer and an output layer connected in sequence.

[0022] A parameter prediction unit is configured to input the to-be-measured data into the electromagnetic parameter prediction model and output an electromagnetic parameter prediction result of the absorbent, wherein the electromagnetic parameter prediction result comprises a real part of a dielectric constant, an imaginary part of the dielectric constant, a real part of magnetic permeability and an imaginary part of the magnetic permeability.

[0023] The application further provides an electronic device comprising a memory and a processor, wherein the memory is configured to store a computer program, and the processor is configured to execute the computer program to enable the electronic device to perform the absorbent electromagnetic parameter prediction method according to the above.

[0024] The application further provides a computer readable storage medium storing a computer program, wherein the computer program is configured to be executed by a processor to implement the absorbent electromagnetic parameter prediction method according to the above.

[0025] According to the embodiments of the application, the following technical effects are achieved:

[0026] The application discloses an absorbent electromagnetic parameter prediction method, system, device and medium, the method comprising: acquiring to-be-measured data; the to-be-measured data comprising frequency, particle size characteristics and physical heuristic characteristics; constructing an electromagnetic parameter prediction model based on a multi-branch neural network; the multi-branch neural network comprising an input layer, a shared feature extraction layer, a branch layer, a deep connection layer and an output layer connected in sequence; inputting the to-be-measured data into the electromagnetic parameter prediction model and outputting an electromagnetic parameter prediction result of the absorbent; the electromagnetic parameter prediction result comprising a real part of a dielectric constant, an imaginary part of the dielectric constant, a real part of magnetic permeability and an imaginary part of the magnetic permeability. The application can improve the prediction accuracy of the electromagnetic parameters of the absorbent. BRIEF DESCRIPTION OF DRAWINGS

[0027] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. 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 effort.

[0028] Figure 1 This is a flowchart illustrating the method for predicting the electromagnetic parameters of the absorbent in this embodiment;

[0029] Figure 2 This is a schematic diagram of the multi-branch neural network architecture in this embodiment;

[0030] Figure 3 This is a schematic diagram showing the particle size distribution parameters of the newly produced absorbent obtained by laser particle size analyzer in this embodiment;

[0031] Figure 4 This is a comparison chart of the predicted value and the actual measured value in this embodiment. Detailed Implementation

[0032] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0033] The purpose of this invention is to provide a method, system, device and medium for predicting the electromagnetic parameters of absorbents, in order to solve or improve at least one of the above-mentioned technical problems.

[0034] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0035] like Figure 1 As shown, the present invention provides a method for predicting the electromagnetic parameters of an absorbent, comprising:

[0036] Acquire the data to be tested; the data to be tested includes frequency, particle size characteristics and physically inspired characteristics.

[0037] An electromagnetic parameter prediction model is constructed based on a multi-branch neural network; the multi-branch neural network includes an input layer, a shared feature extraction layer, a branch layer, a deep connection layer, and an output layer connected in sequence.

[0038] The to-be-tested data is input into the electromagnetic parameter prediction model, and an electromagnetic parameter prediction result of the absorbent is output; the electromagnetic parameter prediction result includes a real part of a dielectric constant, an imaginary part of the dielectric constant, a real part of magnetic permeability, and an imaginary part of the magnetic permeability.

[0039] As a specific implementation, the electromagnetic parameter prediction model includes an input layer, a shared feature extraction layer, a branch layer, a deep connection layer, and an output layer connected in sequence, wherein:

[0040] The input layer receives feature data, and the input size is the number of features; the input dimension is the original features and the physical heuristic features (about 15-20 features in total), including frequency, D10 / D50 / D90, specific surface area, particle size distribution width, and added physical heuristic features.

[0041] The shared feature extraction layer includes a fully connected layer 1, a batch normalization layer 1, a LeakyReLU activation layer 1, and a Dropout layer connected in sequence, wherein the fully connected layer 1 includes 256 neurons, the batch normalization layer 1 performs standardization processing on the data using z-score, the LeakyReLU activation layer 1 uses a negative slope of 0.2, and the Dropout layer has a dropout probability of 0.3.

[0042] The branch layer includes a dielectric constant branch and a magnetic permeability branch connected with the shared layer respectively, wherein the dielectric constant branch focuses on learning dielectric constant related features using particle size distribution characteristics (such as D50 / specific surface area), and focuses on dielectric mechanisms such as interfacial polarization and electronic displacement, and includes a fully connected layer 2, a batch normalization layer 2, a LeakyReLU activation layer 2, a fully connected layer 3, a batch normalization layer 3, and a LeakyReLU activation layer 3 connected in sequence; the magnetic permeability branch focuses on distribution width indicators for learning magnetic permeability related features, and focuses on magnetic properties such as magnetic moment precession and eddy current loss, and includes a fully connected layer 4, a batch normalization layer 4, a LeakyReLU activation layer 4, a fully connected layer 5, a batch normalization layer 5, and a LeakyReLU activation layer 5 connected in sequence; the fully connected layer 2 and the fully connected layer 4 each include 128 neurons, the fully connected layer 3 and the fully connected layer 5 each include 64 neurons, and the LeakyReLU activation layer 2, the LeakyReLU activation layer 3, the LeakyReLU activation layer 4, and the LeakyReLU activation layer 5 each use a negative slope of 0.2.

[0043] The deep connection layer includes two inputs connected with the dielectric constant branch and the magnetic permeability branch respectively, retains branch-specific features while realizing information fusion, and outputs to an output fully connected layer of the output layer.

[0044] The output layer includes an output fully connected layer and a regression layer, wherein the output fully connected layer contains 4 neurons corresponding to 4 outputs, and the output fully connected layer is connected to the regression layer, and the regression layer calculates a mean square error loss.

[0045] The input features include frequency, particle size characteristics, and added physical heuristic features; and the output includes four continuous values representing the real part of the dielectric constant, the imaginary part of the dielectric constant, the real part of the magnetic permeability, and the imaginary part of the magnetic permeability, respectively.

[0046] The particle size characteristics include D10 / D50 / D90, specific surface area, particle size distribution width, etc.; and the added physical heuristic features include frequency reciprocal, particle size wavelength ratio, surface area to volume ratio, and particle size distribution width index.

[0047] The particle size wavelength ratio is defined as D50 / (300 / f), wherein f corresponds to the frequency value.

[0048] The surface area to volume ratio is defined as log (SSA+1×10-6), wherein SSA corresponds to the "specific surface area" in Table 1.

[0049] The particle size distribution width index is defined as span / ((D50 - D50_mean) / D50_std), wherein span corresponds to the "distribution width" in Table 1, and D50_mean and D50_std correspond to the mean and standard deviation of the particle size parameter D50.

[0050] The standardization of the data refers to subtracting the mean and dividing by the standard deviation.

[0051] Based on the above technical solution, the specific processing procedure is provided as shown below.

[0052] Step 1: Load particle size characteristic data. Read the particle size characteristic data table and obtain the sample quantity.

[0053] Step 2: Load and integrate electromagnetic parameter data.

[0054] Check whether the number of electromagnetic parameter files is consistent with the number of particle size characteristic samples; traverse each sample, find the corresponding electromagnetic parameter file according to the file name, and read it; verify that the electromagnetic parameter file contains necessary columns; merge the particle size characteristics of each sample with the electromagnetic parameter data by repeatedly adding the particle size characteristics of the sample for each row of electromagnetic parameter data; and finally obtain a large table containing electromagnetic parameters at all frequency points and corresponding particle size characteristics.

[0055] Step 3: Data preprocessing.

[0056] Separate features (X) and targets (Y), where X includes frequency and all particle size features (as shown in Table 1), and Y includes four target variables; Standardize the data to get standardized features and targets, while saving the mean and standard deviation.

[0057] Step 4: Construct physical-inspired features.

[0058] On the basis of the original features, four physical-inspired features are constructed: the inverse of frequency (to simulate the resonance effect), the ratio of particle size parameter D50 to wavelength, the logarithm of specific surface area (plus a very small constant to avoid log 0), and the ratio of particle size distribution width to normalized D50, where normalization means subtracting the mean and dividing by the standard deviation; Then concatenate these new features with the standardized original features to get the feature `X_combined`.

[0059] Step 5: Build and train the neural network model.

[0060] Build a multi-branch neural network, as shown in Figure 2 , including:

[0061] Input layer: feature input layer, input size is the number of columns of `X_combined`.

[0062] Shared layer: fully connected layer (256 nodes) -> batch normalization -> LeakyReLU activation -> Dropout (0.3).

[0063] Two branches: Branch 1 is the dielectric constant prediction path, including: fully connected (128 nodes) -> batch normalization -> LeakyReLU -> fully connected (64 nodes) -> batch normalization -> LeakyReLU; Branch 2 is the magnetic permeability prediction path, including: fully connected (128 nodes) -> batch normalization -> LeakyReLU -> fully connected (64 nodes) -> batch normalization -> LeakyReLU.

[0064] Deep connection layer: connect the outputs of the two branches in depth.

[0065] Output layer: fully connected layer (4 nodes corresponding to 4 targets) -> regression layer.

[0066] The training settings include:

[0067] Manually divide the training set and validation set, with the validation set accounting for 15% of the weight; use the Adam optimizer, maximum 500 rounds, batch size 512; learning rate initially 0.001, multiplied by 0.5 every 100 rounds; use the manually divided validation set for validation; after training is complete, save the model as well as the standardization parameters and particle size data;

[0068] Step 6: Model validation and visualization.

[0069] Randomly select 3 samples, load the actual electromagnetic parameters for each sample, prepare the input data including original features and physical heuristic features, and standardize; predict with the trained model; draw a comparison chart of actual value and predicted value, and save the image.

[0070] Step 7: Evaluate model performance.

[0071] Predict the entire data set, calculate the determination coefficient R² and the root mean square error RMSE for each target variable; save the data required for analysis. The determination coefficient R² is a relatively comprehensive evaluation index, which takes into account the difference between the predicted value and the true value of the model, and its value range is [0, 1], the closer to 1 indicates the better the prediction effect of the model; while the root mean square error RMSE directly represents the numerical size of the average difference between the predicted value and the true value of the model.

[0072] More than 100 groups of test data were used to train the model, and a desktop computer with a CPU of 12th Gen Intel(R) Core(TM) i5-12400F (2.50 GHz) and 32G RAM was used, which took about 1 minute. After completing the model training, first, a plurality of training data were applied to carry out testing, and then for the newly produced absorbent products, the particle size distribution parameters obtained by the laser particle size analyzer were used to predict the electromagnetic parameters of the absorbent, and the predicted values were compared with the actual electromagnetic parameter measurement values. The particle size distribution parameter results of the newly produced absorbent tested by the laser particle size analyzer are shown in Table 1, the predicted values and the actual measurement values are shown in Table 2, and the comparison of the predicted values and the actual measurement values is shown in Figure 1. Figure 3 The parameters used in the prediction are shown in Table 1, the comparison of the predicted values and the actual measurement values is shown in Table 2, and the comparison of the predicted values and the actual measurement values is shown in Figure 1. Figure 4 Overall, R²=0.99 and RMSE=0.21, indicating that the predicted values are highly consistent with the actual measurement values.

[0073]

[0074] The embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other.

[0075] The principles and implementation modes of the present application are described by applying specific examples in this paper. The above description of the embodiments is only to help understand the core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range will be changed. In view of the above, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A method of predicting the electromagnetic parameters of an absorber, characterized in that, The method comprises the steps of: acquiring test data; the test data comprises frequency, particle size characteristics and physical heuristic characteristics; constructing an electromagnetic parameter prediction model based on a multi-branch neural network; the multi-branch neural network comprises an input layer, a shared feature extraction layer, a branch layer, a deep connection layer and an output layer connected in sequence; the branch layer comprises a dielectric constant branch and a magnetic permeability branch which are of the same structure; inputting the test data into the electromagnetic parameter prediction model, and outputting electromagnetic parameter prediction results of the absorbent; the electromagnetic parameter prediction results comprise a real part of a dielectric constant, an imaginary part of the dielectric constant, a real part of a magnetic permeability and an imaginary part of the magnetic permeability; the construction process of the electromagnetic parameter prediction model comprises: loading particle size characteristic data, and integrating electromagnetic parameter data to obtain characteristic correlation data; the characteristic correlation data comprises electromagnetic parameters at all frequency points and corresponding particle size characteristics; performing target separation on the characteristic correlation data, and labeling original characteristics and corresponding target variables; the original characteristics are frequency and particle size characteristics; the target variables are a real part of a dielectric constant, an imaginary part of the dielectric constant, a real part of a magnetic permeability and an imaginary part of the magnetic permeability; constructing physical heuristic characteristics based on the characteristic correlation data, and splicing the physical heuristic characteristics with the original characteristics to obtain an updated training data set; the updated training data set comprises target variables corresponding to the spliced characteristic data set; inputting the updated training data set into the multi-branch neural network for network parameter optimization training, and determining the trained network as the electromagnetic parameter prediction model.

2. The method of claim 1, wherein, The physical heuristic characteristics comprise the reciprocal of frequency, the ratio of particle size parameter D50 to wavelength, the logarithm of specific surface area, and the ratio of particle size distribution width to normalized D50.

3. The method of claim 1, wherein, The shared feature extraction layer comprises a fully connected layer 1, a batch normalization layer 1, a LeakyReLU activation layer 1 and a Dropout layer connected in sequence; the fully connected layer 1 comprises 256 neurons; the batch normalization layer 1 adopts z-score standardization processing on data; the LeakyReLU activation layer 1 adopts a negative slope of 0.2; and the Dropout layer adopts a dropout probability of 0.

3.

4. The method of claim 1, wherein, The dielectric constant branch and the magnetic permeability branch each comprise two operation modules connected in sequence; each operation module comprises a fully connected layer, a batch normalization layer and a LeakyReLU activation layer; The fully connected layer in the first operation module of the two branches comprises 128 neurons; the fully connected layer in the second operation module comprises 64 neurons; and the LeakyReLU activation layer in the two operation modules each adopts a negative slope of 0.

2.

5. An absorbent electromagnetic parameter prediction system characterized by, The method comprises the steps of: a data acquisition unit is configured to acquire test data; the test data comprises frequency, particle size characteristics and physical heuristic characteristics; a model construction unit is configured to construct an electromagnetic parameter prediction model based on a multi-branch neural network; the multi-branch neural network comprises an input layer, a shared feature extraction layer, a branch layer, a deep connection layer and an output layer connected in sequence; the branch layer comprises a dielectric constant branch and a magnetic permeability branch which are of the same structure; A parameter prediction unit is configured to input the to-be-tested data into the electromagnetic parameter prediction model and output electromagnetic parameter prediction results of the absorbent, the electromagnetic parameter prediction results including a real part of a dielectric constant, an imaginary part of the dielectric constant, a real part of magnetic permeability, and an imaginary part of the magnetic permeability. The construction process of the electromagnetic parameter prediction model includes: loading particle size characteristic data and integrating electromagnetic parameter data to obtain characteristic correlation data, the characteristic correlation data including electromagnetic parameters at all frequency points and corresponding particle size characteristics; performing target separation on the characteristic correlation data and labeling original characteristics and corresponding target variables, the original characteristics being frequency and particle size characteristics, and the target variables being a real part of a dielectric constant, an imaginary part of the dielectric constant, a real part of magnetic permeability, and an imaginary part of the magnetic permeability; constructing physical heuristic characteristics based on the characteristic correlation data, splicing the physical heuristic characteristics with the original characteristics to obtain an updated training data set, and the updated training data set including target variables corresponding to the spliced characteristic data set; inputting the updated training data set into the multi-branch neural network for network parameter optimization training, and determining the trained network as the electromagnetic parameter prediction model.

6. An electronic device, comprising: An electronic device includes a memory for storing a computer program and a processor, the processor running the computer program to enable the electronic device to perform the absorbent electromagnetic parameter prediction method according to any one of claims 1-4.

7. A computer readable storage medium characterized in that, The computer program is stored in the memory and is executed by the processor to implement the absorbent electromagnetic parameter prediction method according to any one of claims 1-4.

Images