An adaptive modulation method and system for electromagnetic frequency sensitive materials

Abstract

The application discloses an adaptive modulation method and system of electromagnetic frequency sensitive material, and relates to the technical field of digital signal transmission.The method comprises the following steps: acquiring a frequency parameter of a target electromagnetic wave; performing matching analysis on the frequency parameter, determining a target frequency range corresponding to the frequency parameter, and acquiring a real-time response parameter of the target electromagnetic wave; calculating and outputting a physical parameter adjustment amount of the electromagnetic frequency sensitive material based on a pre-trained modulation decision model; generating and applying a physical field regulation signal to the electromagnetic frequency sensitive material; and repeatedly performing the above steps until the error between the real-time response parameter and the required physical parameter of the expected response target is within a preset tolerance range, and the adaptive modulation cycle is completed.The technical problem of poor adaptability and fixed response of the existing electromagnetic sensitive material in a complex frequency band environment is solved.

Description

Technical Field

[0001] This application relates to the field of digital signal transmission technology, specifically to an adaptive modulation method and system for electromagnetic frequency sensitive materials. Background Technology

[0002] Modern electronic countermeasures and phased array radar systems place higher demands on their adaptability to the electromagnetic environment. However, the modulation of traditional electromagnetic frequency-sensitive materials often relies on preset fixed parameters or manual experience adjustments. When faced with complex and ever-changing electromagnetic spectrum environments, their response speed is slow, their adjustment accuracy is low, and it is difficult to match the dynamically changing electromagnetic wave characteristics in real time.

[0003] In addition, traditional modulation methods lack a closed-loop feedback mechanism, making it impossible to monitor and correct the actual response of the material in real time. This can easily lead to problems such as over- or under-adjustment of parameters, affecting the stability and reliability of the system. Summary of the Invention

[0004] This application provides an adaptive modulation method and system for electromagnetic frequency sensitive materials, which solves the technical problem that existing electromagnetic sensitive materials have fixed responses and poor adaptability in complex frequency band environments.

[0005] The technical solution to the above-mentioned technical problems in this application is as follows: In a first aspect, this application provides an adaptive modulation method for electromagnetic frequency-sensitive materials, the method comprising: Based on a miniature frequency sensor, the frequency parameters of the target electromagnetic wave are obtained; The frequency parameters are matched and analyzed based on a preset feature database to determine the target frequency band range corresponding to the frequency parameters and to obtain the real-time response parameters of the target electromagnetic wave. The frequency parameters and the real-time response parameters are input into a pre-trained modulation decision model, which calculates and outputs the adjustment amount of the physical parameters of the electromagnetic frequency sensitive material according to the preset expected response target. Based on the adjustment amount of the physical parameters of the electromagnetic frequency sensitive material, a physical field modulation signal is generated and applied to the electromagnetic frequency sensitive material. This process is repeated until the error between the real-time response parameter and the physical parameter required for the desired response target is within a preset tolerance range, thus completing the adaptive modulation cycle.

[0006] Secondly, this application provides an adaptive modulation system for electromagnetic frequency-sensitive materials, comprising: The parameter acquisition module is used to acquire the frequency parameters of the target electromagnetic wave based on a miniature frequency sensor. The parameter matching module is used to perform matching analysis on the frequency parameter based on a preset feature database, determine the target frequency band range corresponding to the frequency parameter, and obtain the real-time response parameters of the target electromagnetic wave. The model training module is used to input the frequency parameters and the real-time response parameters into a pre-trained modulation decision model. The modulation decision model calculates and outputs the adjustment amount of the physical parameters of the electromagnetic frequency sensitive material according to the preset expected response target. The modulation execution module is used to generate and apply a physical field control signal to the electromagnetic frequency sensitive material according to the adjustment amount of the physical parameters of the electromagnetic frequency sensitive material, and repeat the execution until the error between the real-time response parameter and the physical parameter required by the desired response target is within a preset tolerance range, thus completing the adaptive modulation cycle.

[0007] This application provides one or more technical solutions, which have at least the following technical effects or advantages: This application provides an adaptive modulation method and system for electromagnetically frequency-sensitive materials. First, a miniature frequency sensor collects the frequency parameters of the target electromagnetic wave in real time, providing initial input for subsequent modulation. Second, a preset feature database is used to match and analyze the acquired frequency parameters. By comparing the center frequency with the threshold ranges of each frequency band in the database, the target frequency band range is determined. A distributed array of miniature response sensors is then used to simultaneously collect the material's real-time response parameters within this frequency band, achieving comprehensive perception of the material's current state. Third, the frequency parameters and real-time response parameters are input into a pre-trained modulation decision model. Based on a preset desired response target, these are quantified into specific target response parameter thresholds. The difference between the real-time response parameters and the target threshold is calculated, and the required adjustment amount of the material's physical parameters to compensate for this difference is output. Finally, an appropriate physical field control method is selected based on the type of adjustment amount, and a corresponding physical field control signal is generated and applied to the electromagnetically frequency-sensitive material. Through a closed-loop feedback control mechanism, the control signal is continuously corrected until the error between the real-time response parameters and the physical parameters required for the desired response target falls within a preset tolerance range, thus completing the entire adaptive modulation cycle.

[0008] Through the above technical solution, this application realizes the dynamic response and adaptive adjustment of electromagnetic frequency sensitive materials to complex frequency band environments, effectively solving the problems of fixed response and poor adaptability in traditional modulation methods. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 This is a flowchart illustrating an adaptive modulation method for electromagnetic frequency-sensitive materials provided in an embodiment of this application. Figure 2 This is a schematic diagram of the structure of an adaptive modulation system for electromagnetic frequency sensitive materials provided in an embodiment of this application.

[0011] The components represented by each number in the attached diagram are explained below: Parameter acquisition module 11, parameter matching module 12, model training module 13, modulation execution module 14. Detailed Implementation

[0012] This application provides an adaptive modulation method and system for electromagnetic frequency sensitive materials, which addresses the technical problem of fixed response and poor adaptability of existing electromagnetic sensitive materials in complex frequency band environments.

[0013] Example 1, as Figure 1 As shown, this application provides an adaptive modulation method for electromagnetic frequency-sensitive materials, including: S10: Based on a miniature frequency sensor, acquire the frequency parameters of the target electromagnetic wave; The frequency parameters include the center frequency and the frequency bandwidth.

[0014] In this embodiment, a miniature frequency sensor array is first deployed on the surface or near-field region of an electromagnetic frequency sensitive material. The array consists of multiple miniaturized frequency detection units and can operate stably within a working temperature range of -40°C to 85°C. The sampling frequency can reach 1MHz, ensuring the capture of rapidly changing target electromagnetic wave frequency parameters.

[0015] When the target electromagnetic wave acts on the sensor array, the sensor converts the electromagnetic wave signal into an electrical signal through the principle of electromagnetic induction. After filtering, amplification and analog-to-digital conversion by the signal conditioning circuit, the center frequency and frequency bandwidth of the electromagnetic wave are extracted.

[0016] For example, if the target electromagnetic wave is a radar signal, the sensor can identify its center frequency in the X-band, i.e., 8-12 GHz, such as 10.5 GHz, and simultaneously obtain its frequency bandwidth of 500 MHz.

[0017] S20: Based on a preset feature database, perform matching analysis on the frequency parameter to determine the target frequency band range corresponding to the frequency parameter, and obtain the real-time response parameters of the target electromagnetic wave; The preset feature database includes a center frequency range from low frequency to millimeter wave, standard response parameter reference values, and initial configuration schemes for material physical parameters.

[0018] In this embodiment of the application, the preset feature database is constructed by conducting a large number of experimental tests on the response characteristics of electromagnetic frequency sensitive materials at different frequency bands, including the low frequency band from 300MHz to the millimeter wave band of 300GHz, and each frequency band is divided into a center frequency threshold range.

[0019] For example, the threshold range of the low frequency band can be set as sub-ranges such as 300MHz-1GHz, 1GHz-2GHz, 2GHz-3GHz, etc. Each sub-range corresponds to a set of standard response parameter reference values, such as a reflection coefficient reference value of -20dB, a transmission coefficient reference value of 0.1, an impedance matching degree reference value of 0.95, and an electromagnetic loss factor reference value of 0.05. At the same time, the initial configuration scheme of physical parameters such as dielectric constant, permeability, and conductivity of the material in this frequency band is also included.

[0020] After obtaining the center frequency of the target electromagnetic wave in step S10, the center frequency is compared with the center frequency threshold range of each frequency band in the preset feature database one by one. If the center frequency falls within the threshold range of a certain preset frequency band, then the band is determined as the target frequency band range.

[0021] Furthermore, after determining the target frequency band range, a distributed micro-response sensor array is activated. These micro-response sensors are uniformly distributed across different regions of the electromagnetically sensitive material. The distributed micro-response sensors employ highly sensitive electromagnetic induction elements, enabling them to synchronously acquire real-time response parameters of the electromagnetically sensitive material.

[0022] Specifically, step S20 in the method includes: The center frequency is compared with the center frequency threshold range of each frequency band in the preset feature database. If the center frequency is within the threshold range of the preset frequency band, the frequency band is taken as the target frequency band range. A distributed micro-response sensor array is used to synchronously collect real-time response parameters of electromagnetic frequency sensitive materials within the target frequency band. These real-time response parameters include reflection coefficient, transmission coefficient, impedance matching degree, and electromagnetic loss factor.

[0023] In this embodiment of the application, the target frequency band range is first determined by comparing the center frequency with the threshold range of each frequency band in the preset feature database.

[0024] For example, if the center frequency is 10.5 GHz, and it falls within the threshold range of 8-12 GHz in the X-band after comparison, then the X-band is the target frequency band range.

[0025] Secondly, a distributed micro-response sensor array is activated. This array consists of eight distributed micro-response sensors that employ highly sensitive electromagnetic induction elements to synchronously acquire real-time response parameters of the material within the target frequency band, including reflection coefficient, transmission coefficient, impedance matching degree, and electromagnetic loss factor.

[0026] Specifically, the real-time acquisition of the reflection coefficient is achieved through a vector network analyzer, which measures the proportion of energy reflected by the material to the incident electromagnetic wave. The value ranges from 0 to 1. The smaller the value, the less energy is reflected, and the better the material's absorption or transmission effect on electromagnetic waves.

[0027] The transmission coefficient is obtained by measuring the ratio of the intensity of electromagnetic waves after passing through the material to the incident intensity. It is also measured in the range of 0 to 1. The larger the value, the stronger the transmission performance of the material.

[0028] Impedance matching degree is calculated by measuring the proximity of the material's input impedance to the free space impedance. Under ideal matching conditions, its value is 1. The closer the value is to 1, the better the impedance matching effect and the higher the energy transmission efficiency.

[0029] The electromagnetic loss factor takes into account both the dielectric loss and magnetic loss of a material, reflecting the degree of energy loss during the propagation of electromagnetic waves within the material. The larger the loss factor, the faster the energy dissipates.

[0030] S30: Input the frequency parameters and the real-time response parameters into the pre-trained modulation decision model. The modulation decision model calculates and outputs the adjustment amount of the physical parameters of the electromagnetic frequency sensitive material according to the preset expected response target. In this embodiment, the pre-trained modulation decision model is constructed based on a deep learning algorithm. Its training samples are derived from the response data of electromagnetic frequency sensitive materials under different frequency bands and different physical parameter configurations, including experimental samples from low frequency to millimeter wave bands.

[0031] The input layer of the model receives the frequency parameters obtained in step S10 and the real-time response parameters collected in step S20. The hidden layer performs feature extraction and nonlinear mapping on the input data through a multilayer perceptron. The output layer calculates and outputs the physical parameter adjustment amounts of the electromagnetic frequency sensitive material according to the preset expected response target, including the dielectric constant adjustment amount, magnetic permeability adjustment amount and electrical conductivity adjustment amount.

[0032] Furthermore, the preset expected response target is set according to the actual application scenario. For example, in the electronic warfare scenario, the expected response target may be set as reflection coefficient ≤ -30dB and impedance matching degree ≥ 0.98; in the phased array radar system, the transmission coefficient ≥ 0.9 and electromagnetic loss factor ≤ 0.02 are required.

[0033] Specifically, the modulation decision model first quantifies the preset expected response target into a specific target response parameter threshold, then calculates the difference between the real-time response parameter and the target threshold, adjusts the internal weights of the model through the backpropagation algorithm, and finally outputs the physical parameter adjustment amount that can compensate for the difference.

[0034] Specifically, training the modulation decision model includes: Construct a training dataset, which includes the response parameters of the electromagnetic frequency-sensitive material under known frequency parameters and the known physical parameter adjustments applied to achieve a given response target; The initial model is trained using the frequency parameter sample set and the response parameter sample set as model inputs and the physical parameter adjustment amount as supervision labels. The trained model was validated using an independent test dataset to obtain the pre-trained modulation decision model.

[0035] In this embodiment, firstly, a training dataset is constructed. This dataset is obtained by simulating the material response characteristics under different electromagnetic spectrum environments in a laboratory setting. Specifically, an electromagnetic wave covering the 300MHz to 300GHz frequency band is generated using a signal generator. By changing the physical parameters of the electromagnetic frequency-sensitive material, such as the dielectric constant, permeability, and conductivity, the corresponding frequency parameters and real-time response parameters are synchronously acquired using a vector network analyzer and a distributed sensor array. For each known combination of frequency and response parameters, the amount of physical parameter adjustment that enables the material to achieve the preset response target is determined through theoretical calculations and experimental debugging, and then divided into a training sample set and a validation sample set in an 8:2 ratio.

[0036] Secondly, using the frequency parameter sample set and the response parameter sample set as the input vectors for the model's input layer, and the physical parameter adjustment amount as the supervision label, an initial model based on a multilayer perceptron is constructed. This model contains three hidden layers with 128, 64, and 32 neurons per layer, respectively. The ReLU activation function is used, and the output layer uses a linear activation function to directly output the adjustment amount. During training, mean squared error is used as the loss function, and the model weights are iteratively updated using the Adam optimizer. The initial learning rate is set to 0.001, decaying by 10% every 50 epochs, and the number of iterations is set to 500 epochs until the loss function converges or the maximum number of iterations is reached.

[0037] Finally, the trained model is validated using an independent test dataset, and the mean absolute error (MAE) between the physical parameter adjustments output by the model and the actual required adjustments is calculated. If the MAE is within the preset error range, such as dielectric constant adjustment ≤ 0.1, permeability adjustment ≤ 0.05, and conductivity adjustment ≤ 1e-4 S / m, the model training is complete, and a pre-trained modulation decision model is obtained. If the target is not met, retraining is performed by increasing the amount of training data, adjusting the number of network layers or neurons, and optimizing the learning rate strategy until the model performance meets the requirements. For example, in the X-band 8-12GHz test, the average error of the dielectric constant adjustment output by the model can be controlled within 0.08.

[0038] Among them, based on the preset expected response target, the adjustment amount of the physical parameters of the electromagnetic frequency sensitive material is calculated and output, including: The desired response target is quantified into a target response parameter threshold; Calculate the difference between the real-time response parameter and the target response parameter threshold; The frequency parameters and the difference are input into the modulation decision model, and the model outputs the material physical parameter adjustment amount required to compensate for the difference. The material physical parameter adjustment amount includes at least one of dielectric constant adjustment amount, magnetic permeability adjustment amount, or electrical conductivity adjustment amount.

[0039] In this embodiment of the application, firstly, according to the needs of the specific application scenario, the preset expected response target is converted into a quantifiable target response parameter threshold.

[0040] For example, in the application scenario of stealth materials, if the desired response target is "to achieve low detectability in the X-band", then the threshold of the quantized target response parameters can be set to reflectance coefficient ≤ -35dB and impedance matching degree ≥ 0.99; in the scenario of microwave absorbing materials, the threshold of the target response parameters can be set to electromagnetic loss factor ≥ 0.8 and transmission coefficient ≤ 0.05.

[0041] Secondly, calculate the difference between the real-time response parameters and the target response parameter thresholds mentioned above. For example, if the real-time reflection coefficient is -25dB and the target threshold is -35dB, the difference between the two is 10dB, indicating that the reflection energy of the current material is too high and the reflection needs to be reduced by adjusting the physical parameters.

[0042] Next, the frequency parameters obtained in step S10 and the calculated difference are used as input data and input into the pre-trained modulation decision model. The model outputs the material physical parameter adjustment amount that can compensate for the difference through the mapping relationship formed by internal training.

[0043] For example, to reduce the reflection coefficient from -25dB to -35dB, the model output dielectric constant needs to be increased by 0.5 and the permeability needs to be decreased by 0.2. If the impedance matching degree is lower than the target threshold, the output conductivity may need to be finely adjusted by 0.01S / m. The adjustment amount can be one or more combinations of dielectric constant, permeability, and conductivity.

[0044] S40: Based on the adjustment amount of the physical parameters of the electromagnetic frequency sensitive material, generate and apply a physical field control signal to the electromagnetic frequency sensitive material, repeat the process until the error between the real-time response parameter and the physical parameter required by the desired response target is within a preset tolerance range, and complete the adaptive modulation cycle.

[0045] In this embodiment, a multiphysics control unit is integrated to generate and apply physical field control signals. The corresponding control method can be selected according to the type of physical parameter adjustment. After applying the control signal, the process returns to step S10 to re-acquire the frequency parameters of the target electromagnetic wave and the real-time response parameters of the material, and then repeats the parameter matching, model calculation, and control signal application process.

[0046] This cycle continues until the error between the real-time response parameters and the parameter thresholds corresponding to the expected response target falls within the preset tolerance range, such as reflection coefficient error ≤ 1dB, impedance matching error ≤ 0.02, electromagnetic loss factor error ≤ 0.05, etc. At this point, the adaptive modulation process terminates, and the electromagnetic frequency sensitive material reaches the optimal response state under the current electromagnetic environment.

[0047] The process of generating and applying a physical field modulation signal to the electromagnetic frequency sensitive material based on the adjustment amount of the physical parameters of the electromagnetic frequency sensitive material includes: Select the physical field control method based on the type of adjustment of the material's physical parameters; The physical field manipulation method includes applying at least one of a temperature field, an electric field, a magnetic field, a stress field, or a light field; During the application of the physical field control signal, the actual changes in the material's physical parameters are monitored in real time and compared with the adjustment amount of the material's physical parameters. The physical field control signal is then dynamically corrected through closed-loop feedback control.

[0048] In this embodiment, firstly, according to the specific type of material physical parameter adjustment, the corresponding physical field control method is selected. For example, when it is necessary to adjust the dielectric constant, temperature field control or electric field control can be used: temperature field control is achieved through a micro heating element or a semiconductor cooler, controlling the material temperature in the range of -40℃ to 150℃, and using the temperature sensitivity of the material dielectric constant to achieve parameter adjustment.

[0049] Secondly, during the application of physical field control signals, a high-precision physical parameter monitoring module is integrated to track the actual changes in material physical parameters in real time. For example, a dielectric spectrometer is used to monitor changes in dielectric constant in real time, with a resolution of 0.01; a vibrating sample magnetometer is used to monitor changes in magnetic permeability, with an accuracy of 0.001 H / m; and a four-probe resistor is used to monitor changes in conductivity, with a measurement accuracy of 1e-6 S / m.

[0050] Furthermore, the monitored actual changes are compared in real time with the physical parameter adjustments output by the modulation decision model, and the deviation between the two is calculated. If the deviation exceeds the preset control threshold, such as dielectric constant deviation > 0.05 or permeability deviation > 0.02, the intensity, frequency, or duration of the physical field control signal is dynamically corrected using a PID closed-loop feedback algorithm.

[0051] For example, when the actual dielectric constant adjustment amount only reaches 80% of the target value, the heating power of the temperature field is automatically increased or the electric field application time is extended until the deviation between the actual change amount and the target adjustment amount falls within the preset tolerance range, such as the deviation ≤ 0.02, to ensure that the material physical parameters accurately meet the modulation requirements.

[0052] Specifically, during the application of the physical field control signal, the actual changes in the material's physical parameters are monitored in real time and compared with the adjustment amounts of the material's physical parameters. The physical field control signal is then dynamically corrected through closed-loop feedback control, including: An adaptive PID control algorithm is adopted, using the difference between the actual change in the material's physical parameters and the target adjustment amount as input; Calculate the proportional coefficient of the current error, the cumulative integral of the historical error, and the differential coefficient of the error change rate, and dynamically adjust the intensity, frequency, or duration of the physical field control signal.

[0053] In this embodiment, an adaptive PID control algorithm is first adopted, using the difference between the actual change in the material physical parameters and the target adjustment amount output by the model as the core input. Based on traditional PID control, this algorithm introduces a fuzzy logic or neural network adaptive mechanism, which can adjust the control parameters in real time according to the magnitude of the error, the trend of change, and the dynamic characteristics of the system.

[0054] Specifically, when the absolute value of the error is large, the algorithm automatically increases the proportional coefficient to speed up the response and decreases the integral coefficient to avoid integral saturation. When the error enters the preset transition range, the proportional coefficient is dynamically reduced and the integral coefficient is increased to eliminate steady-state error. The algorithm also predicts the error change trend through the differential coefficient to suppress overshoot in advance.

[0055] Furthermore, the proportional coefficient of the current error, the cumulative integral of the historical error, and the differential coefficient of the rate of change of error are calculated, including: When the absolute value of the error exceeds the first preset threshold, the proportional coefficient is increased. When the absolute value of the error is between the first preset threshold and the second preset threshold and the error change rate is positive, decrease the proportional coefficient and increase the integral coefficient. When the absolute value of the error is less than the second preset threshold, the integral coefficient is reduced and the derivative coefficient is increased.

[0056] In this embodiment of the application, firstly, a first preset threshold is set to 30% of the target adjustment amount, and a second preset threshold is set to 10% of the target adjustment amount.

[0057] For example, if the target dielectric constant adjustment is 1.0, then the first preset threshold is 0.3 and the second preset threshold is 0.1. When the absolute value of the difference between the actual change and the target adjustment is greater than 0.3, it is determined to be in a state of large deviation. At this time, the proportional coefficient is automatically increased from the initial value of 0.5 to 0.8 to enhance the strength of the control signal and quickly reduce the error.

[0058] When the absolute value of the error is between 0.1 and 0.3, that is, 10% < error ≤ 30% and the error change rate is positive, the proportional coefficient is reduced to 0.4, while the integral coefficient is increased from 0.2 to 0.5. The error is gradually eliminated through cumulative integration, and the trend of further expansion of the error is suppressed.

[0059] When the absolute value of the error is less than 0.1, that is, when the error is ≤10%, it is close to steady state. At this time, the integral coefficient is reduced to 0.1 to avoid overshoot, while the derivative coefficient is increased from 0.1 to 0.3. By controlling the derivative of the error change rate, the error trend can be predicted in advance, smooth adjustment can be achieved, and the final stability can be ensured at the target adjustment amount.

[0060] For example, when adjusting the permeability, if the target adjustment amount is 0.5H / m, and the actual change is monitored to be 0.3H / m (error 0.2H / m), which is greater than the first preset threshold of 0.15H / m, the intensity of the magnetic field control signal is increased. When the actual change reaches 0.45H / m (error 0.05H / m), which is less than the second preset threshold of 0.05H / m, the magnetic field intensity is fine-tuned through differential control, so that the permeability is finally stabilized within the range of 0.5H / m ± 0.005H / m.

[0061] In summary, compared with the prior art, this application realizes the adaptive dynamic modulation of electromagnetic frequency sensitive materials in complex electromagnetic environments by constructing a closed-loop mapping relationship of "frequency parameter - response parameter - physical parameter adjustment amount".

[0062] First, the modulation decision model constructed using a multilayer perceptron can deeply explore the nonlinear relationship between frequency parameters and material response characteristics, combined with a preset quantization threshold for the desired response target. In summary, the embodiments of this application have at least the following technical effects: This application provides an adaptive modulation method for electromagnetically sensitive materials. First, a miniature frequency sensor collects the frequency parameters of the target electromagnetic wave in real time, providing initial input for subsequent modulation. Second, a preset feature database is used to match and analyze the acquired frequency parameters. By comparing the center frequency with the threshold ranges of each frequency band in the database, the target frequency band range is determined. A distributed array of miniature response sensors is then used to simultaneously collect the material's real-time response parameters within this frequency band, achieving comprehensive perception of the material's current state. Third, the frequency parameters and real-time response parameters are input into a pre-trained modulation decision model. Based on a preset desired response target, these are quantified into specific target response parameter thresholds. The difference between the real-time response parameters and the target threshold is calculated, and the required adjustment amount of the material's physical parameters to compensate for this difference is output. Finally, an appropriate physical field control method is selected based on the type of adjustment amount, and a corresponding physical field control signal is generated and applied to the electromagnetically sensitive material. Through a closed-loop feedback control mechanism, the control signal is continuously corrected until the error between the real-time response parameters and the physical parameters required for the desired response target falls within a preset tolerance range, thus completing the entire adaptive modulation cycle.

[0063] Through the above technical solution, this application realizes the dynamic response and adaptive adjustment of electromagnetic frequency sensitive materials to complex frequency band environments, effectively solving the problems of fixed response and poor adaptability in traditional modulation methods.

[0064] Example 2, as Figure 2 As shown, based on the same inventive concept as the adaptive modulation method for electromagnetic frequency sensitive materials provided in Embodiment 1, this application also provides an adaptive modulation system for electromagnetic frequency sensitive materials, including: The parameter acquisition module 11 is used to acquire the frequency parameters of the target electromagnetic wave based on the miniature frequency sensor. The parameter matching module 12 is used to perform matching analysis on the frequency parameter based on a preset feature database, determine the target frequency band range corresponding to the frequency parameter, and obtain the real-time response parameters of the target electromagnetic wave. Model training module 13 is used to input the frequency parameters and the real-time response parameters into a pre-trained modulation decision model. The modulation decision model calculates and outputs the adjustment amount of the physical parameters of the electromagnetic frequency sensitive material according to the preset expected response target. The modulation execution module 14 is used to generate and apply a physical field control signal to the electromagnetic frequency sensitive material according to the adjustment amount of the physical parameters of the electromagnetic frequency sensitive material, and repeat the execution until the error between the real-time response parameter and the physical parameter required by the desired response target is within the preset tolerance range, thus completing the adaptive modulation cycle.

[0065] Furthermore, in one embodiment of the application, the frequency parameters include the center frequency and the frequency bandwidth.

[0066] Furthermore, in one embodiment of the application, the preset feature database includes a center frequency range from low frequency to millimeter wave, standard response parameter reference values, and initial configuration schemes for material physical parameters.

[0067] In one embodiment, the parameter matching module 12 is specifically used for: The center frequency is compared with the center frequency threshold range of each frequency band in the preset feature database. If the center frequency is within the threshold range of the preset frequency band, the frequency band is taken as the target frequency band range. A distributed micro-response sensor array is used to synchronously collect real-time response parameters of electromagnetic frequency sensitive materials within the target frequency band. These real-time response parameters include reflection coefficient, transmission coefficient, impedance matching degree, and electromagnetic loss factor.

[0068] Furthermore, the modulation decision model is trained, including: Construct a training dataset, which includes the response parameters of the electromagnetic frequency-sensitive material under known frequency parameters and the known physical parameter adjustments applied to achieve a given response target; The initial model is trained using the frequency parameter sample set and the response parameter sample set as model inputs and the physical parameter adjustment amount as supervision labels. The trained model was validated using an independent test dataset to obtain the pre-trained modulation decision model.

[0069] Furthermore, based on the preset desired response target, the adjustment amount of the physical parameters of the electromagnetic frequency sensitive material is calculated and output, including: The desired response target is quantified into a target response parameter threshold; Calculate the difference between the real-time response parameter and the target response parameter threshold; The frequency parameters and the difference are input into the modulation decision model, and the model outputs the material physical parameter adjustment amount required to compensate for the difference. The material physical parameter adjustment amount includes at least one of dielectric constant adjustment amount, magnetic permeability adjustment amount, or electrical conductivity adjustment amount.

[0070] Further, in one embodiment, generating and applying a physical field modulation signal to the electromagnetic frequency sensitive material based on the adjustment amount of the physical parameters of the electromagnetic frequency sensitive material includes: Select the physical field control method based on the type of adjustment of the material's physical parameters; The physical field manipulation method includes applying at least one of a temperature field, an electric field, a magnetic field, a stress field, or a light field; During the application of the physical field control signal, the actual changes in the material's physical parameters are monitored in real time and compared with the adjustment amount of the material's physical parameters. The physical field control signal is then dynamically corrected through closed-loop feedback control.

[0071] Furthermore, during the application of the physical field control signal, the actual changes in the material's physical parameters are monitored in real time and compared with the adjustment amounts of the material's physical parameters. The physical field control signal is then dynamically corrected through closed-loop feedback control, including: An adaptive PID control algorithm is adopted, using the difference between the actual change in the material's physical parameters and the target adjustment amount as input; Calculate the proportional coefficient of the current error, the cumulative integral of the historical error, and the differential coefficient of the error change rate, and dynamically adjust the intensity, frequency, or duration of the physical field control signal.

[0072] Further, in one embodiment, calculating the proportionality coefficient of the current error, the cumulative integral of the historical error, and the differential coefficient of the rate of change of error includes: When the absolute value of the error exceeds the first preset threshold, the proportional coefficient is increased. When the absolute value of the error is between the first preset threshold and the second preset threshold and the error change rate is positive, decrease the proportional coefficient and increase the integral coefficient. When the absolute value of the error is less than the second preset threshold, the integral coefficient is reduced and the derivative coefficient is increased.

Claims

1. An adaptive modulation method for electromagnetic frequency-sensitive materials, characterized in that, The method includes: Based on a miniature frequency sensor, the frequency parameters of the target electromagnetic wave are obtained; The frequency parameters are matched and analyzed based on a preset feature database to determine the target frequency band range corresponding to the frequency parameters and to obtain the real-time response parameters of the target electromagnetic wave. The frequency parameters and the real-time response parameters are input into a pre-trained modulation decision model, which calculates and outputs the adjustment amount of the physical parameters of the electromagnetic frequency sensitive material according to the preset expected response target. Based on the adjustment amount of the physical parameters of the electromagnetic frequency sensitive material, a physical field modulation signal is generated and applied to the electromagnetic frequency sensitive material. This process is repeated until the error between the real-time response parameter and the physical parameter required for the desired response target is within a preset tolerance range, thus completing the adaptive modulation cycle.

2. The adaptive modulation method for an electromagnetic frequency-sensitive material according to claim 1, characterized in that, Frequency parameters include center frequency and frequency bandwidth.

3. The adaptive modulation method for an electromagnetic frequency-sensitive material according to claim 1, characterized in that, The preset feature database contains center frequency ranges from low frequency to millimeter wave, standard response parameter reference values, and initial configuration schemes for material physical parameters.

4. The adaptive modulation method for an electromagnetic frequency-sensitive material according to claim 1, characterized in that, Based on a preset feature database, the frequency parameter is matched and analyzed to determine the target frequency band range corresponding to the frequency parameter, and the real-time response parameters of the target electromagnetic wave are obtained, including: The center frequency is compared with the center frequency threshold range of each frequency band in the preset feature database. If the center frequency is within the threshold range of the preset frequency band, the frequency band is taken as the target frequency band range. A distributed micro-response sensor array is used to synchronously collect real-time response parameters of electromagnetic frequency sensitive materials within the target frequency band. These real-time response parameters include reflection coefficient, transmission coefficient, impedance matching degree, and electromagnetic loss factor.

5. The adaptive modulation method for an electromagnetic frequency-sensitive material according to claim 1, characterized in that, Training the modulation decision model includes: Construct a training dataset, which includes the response parameters of the electromagnetic frequency-sensitive material under known frequency parameters and the known physical parameter adjustments applied to achieve a given response target; The initial model is trained using the frequency parameter sample set and the response parameter sample set as model inputs and the physical parameter adjustment amount as supervision labels. The trained model was validated using an independent test dataset to obtain the pre-trained modulation decision model.

6. The adaptive modulation method for an electromagnetic frequency-sensitive material according to claim 5, characterized in that, Based on the preset desired response target, calculate and output the adjustment amount of the physical parameters of the electromagnetic frequency sensitive material, including: The desired response target is quantified into a target response parameter threshold; Calculate the difference between the real-time response parameter and the target response parameter threshold; The frequency parameters and the difference are input into the modulation decision model, and the model outputs the material physical parameter adjustment amount required to compensate for the difference. The material physical parameter adjustment amount includes at least one of dielectric constant adjustment amount, magnetic permeability adjustment amount, or electrical conductivity adjustment amount.

7. The adaptive modulation method for an electromagnetic frequency-sensitive material according to claim 1, characterized in that, Based on the adjustment amount of the physical parameters of the electromagnetic frequency sensitive material, a physical field modulation signal is generated and applied to the electromagnetic frequency sensitive material, including: Select the physical field control method based on the type of adjustment of the material's physical parameters; The physical field manipulation method includes applying at least one of a temperature field, an electric field, a magnetic field, a stress field, or a light field; During the application of the physical field control signal, the actual changes in the material's physical parameters are monitored in real time and compared with the adjustment amount of the material's physical parameters. The physical field control signal is then dynamically corrected through closed-loop feedback control.

8. The adaptive modulation method for an electromagnetic frequency-sensitive material according to claim 7, characterized in that, During the application of the physical field control signal, the actual changes in the material's physical parameters are monitored in real time and compared with the adjustment amounts of the material's physical parameters. The physical field control signal is then dynamically corrected through closed-loop feedback control, including: An adaptive PID control algorithm is adopted, using the difference between the actual change in the material's physical parameters and the target adjustment amount as input; Calculate the proportional coefficient of the current error, the cumulative integral of the historical error, and the differential coefficient of the error change rate, and dynamically adjust the intensity, frequency, or duration of the physical field control signal.

9. The adaptive modulation method for an electromagnetic frequency-sensitive material according to claim 8, characterized in that, Calculate the proportionality coefficient of the current error, the cumulative integral of the historical error, and the differential coefficient of the rate of change of error, including: When the absolute value of the error exceeds the first preset threshold, the proportional coefficient is increased. When the absolute value of the error is between the first preset threshold and the second preset threshold and the error change rate is positive, decrease the proportional coefficient and increase the integral coefficient. When the absolute value of the error is less than the second preset threshold, the integral coefficient is reduced and the derivative coefficient is increased.

10. An adaptive modulation system for an electromagnetic frequency-sensitive material, characterized in that, An adaptive modulation method for an electromagnetic frequency-sensitive material according to any one of claims 1-9 includes: The parameter acquisition module is used to acquire the frequency parameters of the target electromagnetic wave based on a miniature frequency sensor. The parameter matching module is used to perform matching analysis on the frequency parameter based on a preset feature database, determine the target frequency band range corresponding to the frequency parameter, and obtain the real-time response parameters of the target electromagnetic wave. The model training module is used to input the frequency parameters and the real-time response parameters into a pre-trained modulation decision model. The modulation decision model calculates and outputs the adjustment amount of the physical parameters of the electromagnetic frequency sensitive material according to the preset expected response target. The modulation execution module is used to generate and apply a physical field control signal to the electromagnetic frequency sensitive material according to the adjustment amount of the physical parameters of the electromagnetic frequency sensitive material, and repeat the execution until the error between the real-time response parameter and the physical parameter required by the desired response target is within a preset tolerance range, thus completing the adaptive modulation cycle.

Images