Gallium nitride-based class-e power amplifier electromagnetic heating method and system

Abstract

This invention relates to the field of chip encryption technology, and particularly to an electromagnetic heating method and system for a Gallium Nitride (GaN)-based Class E power amplifier. In this invention, by acquiring real-time resistance and temperature data, and combining this with the operating characteristics and ideal parameter information of the GaN device, a real-time resistance correction value is calculated. This allows for rapid response to temperature changes in the GaN device. Resistance and temperature subsets are then acquired and combined to obtain multiple temperature-resistance correlation groups, providing a data foundation for establishing an operating voltage prediction model. The model is then trained using historical data. Finally, the real-time resistance correction value and real-time temperature value are input into the corresponding operating voltage prediction model to obtain a simulated operating voltage value. Based on this simulated operating voltage value, the circuit containing the GaN device is adjusted, thereby bringing the operating voltage and current of the GaN device close to ideal values ​​to ensure stable power output.

Description

Technical Field

[0001] This invention relates to the field of semiconductor technology, and in particular to an electromagnetic heating method and system for a Gallium Nitride-based Class E power amplifier. Background Technology

[0002] Gallium nitride (GaN) is a wide-bandgap semiconductor material with excellent properties such as high electron mobility, high breakdown electric field, and high thermal conductivity. A Class E power amplifier based on GaN is a specific type of high-power amplifier made using GaN material. Through special circuit design and operating methods, it enables transistors to switch rapidly between on and off states, achieving high-efficiency power conversion at high frequencies, typically reaching 70%-90% or higher. The GaN power device is the core component, responsible for converting input electrical energy into high-frequency alternating current to provide the energy required for electromagnetic heating.

[0003] During the operation of gallium nitride (GaN) devices, their temperature fluctuates, causing changes in on-resistance. This means that under the same operating current, the voltage of the GaN device will also change, leading to variations in power consumption. These changes further affect the physical characteristics and operating state of the GaN device. Higher power consumption complicates the physical processes such as electron migration within the GaN device, generating additional thermal effects and affecting the electric field distribution within the device. This results in unstable responses when the device is turned on and off under control signals, making precise control of the signal by the Class E power amplifier unstable and hindering stable power output. Due to the unstable system power output, the heat received by the heated object also fluctuates, causing the electromagnetic heating system to fail to achieve the expected heating effect. Summary of the Invention

[0004] The main objective of this invention is to provide an electromagnetic heating method and system for a Gallium Nitride-based Class E power amplifier, aiming to solve the technical problems in the prior art.

[0005] This invention proposes an electromagnetic heating method for a Class E power amplifier based on gallium nitride, comprising:

[0006] Obtain device characteristic information of gallium nitride devices, and obtain operating characteristic information and ideal parameter information based on the device characteristic information;

[0007] Obtain the electrical parameter data of the circuit where the gallium nitride device is located, and obtain the real-time resistance data of the gallium nitride device based on the operating characteristic information and the electrical parameter data. The real-time resistance data includes the real-time resistance value and multiple historical resistance values.

[0008] The real-time temperature data of the gallium nitride device is obtained by a temperature sensor. The real-time temperature data includes the real-time temperature value and multiple historical temperature values. The real-time resistance correction value is obtained based on the operating characteristic information, ideal parameter information, real-time temperature value and real-time resistance value.

[0009] Based on the operating characteristic information, a resistance subset and a temperature subset are obtained, and a temperature-resistance association group is obtained based on the resistance subset and the temperature subset.

[0010] Based on the temperature-resistance correlation group, real-time resistance data, and real-time temperature data, a corresponding operating voltage prediction model is constructed, and the real-time resistance correction value and real-time temperature value are input into the corresponding operating voltage prediction model to obtain the simulated operating voltage value.

[0011] The circuit containing the gallium nitride device is adjusted according to the simulated operating voltage value to obtain the compensation adjustment electrical parameters, wherein the compensation adjustment electrical parameters include the compensation adjustment current value and the compensation adjustment voltage value, and the real-time output power of the gallium nitride device is obtained according to the compensation adjustment current value and the compensation adjustment voltage value.

[0012] Determine whether the real-time output power is greater than a preset power threshold;

[0013] If the real-time output power is greater than the preset power threshold, the electromagnetic heating effect is determined to be as expected.

[0014] If the real-time output power is not greater than the preset power threshold, it is determined that the electromagnetic heating effect has not met expectations. Then, the process returns to the step of constructing the corresponding working voltage prediction model based on the temperature-resistance correlation group, real-time resistance data, and real-time temperature data, until the electromagnetic heating effect meets expectations.

[0015] Preferably, the step of obtaining the real-time resistance data of the gallium nitride device based on the operating characteristic information and electrical parameter data includes:

[0016] The signal variation frequency and signal stability value of the gallium nitride device are obtained based on the aforementioned operating characteristic information;

[0017] Obtain the interference frequency and interference intensity of the electromagnetic device, and obtain the mean sample number based on the interference frequency, interference intensity, signal change frequency and signal stability value;

[0018] Based on the electrical parameter data, obtain multiple fluctuating voltage values ​​and multiple fluctuating current values ​​corresponding to each detection time;

[0019] Real-time voltage data is obtained based on multiple fluctuating voltage values ​​and the average number of samples, and real-time current data is obtained based on multiple fluctuating current values ​​and the average number of samples.

[0020] The corresponding real-time resistance data is obtained based on the real-time voltage data and the corresponding real-time current data.

[0021] Preferably, the step of comparing the standard temperature-resistance curve and the temperature-voltage change curve to obtain the resistance drift value of the gallium nitride device at the current temperature includes:

[0022] The steps for obtaining the real-time resistance correction value based on the operating characteristic information, ideal parameter information, real-time temperature value, and real-time resistance value include:

[0023] The material property coefficients of the gallium nitride device are obtained based on the aforementioned operating characteristic information;

[0024] The ideal temperature value and standard resistance value of the gallium nitride device are obtained based on the ideal parameter information, and the resistance drift value is obtained based on the real-time resistance value and the standard resistance value.

[0025] The resistance compensation value of the gallium nitride device is calculated based on the material property coefficient, resistance drift value, real-time temperature value, and ideal temperature value, wherein the calculation formula is:

[0026]

[0027] Among them, R c R represents the resistance compensation value. i α represents the resistance drift value, α represents the material property coefficient, T represents the real-time temperature value, and T0 represents the ideal temperature value.

[0028] The real-time resistance correction value is obtained based on the resistance compensation value and the real-time resistance value.

[0029] Preferably, the step of obtaining a resistance subset and a temperature subset based on the operating characteristic information, and obtaining a temperature-resistance correlation group based on the resistance subset and the temperature subset, includes:

[0030] Based on the operating characteristic information, temperature influence data and resistance influence data are obtained, and based on the temperature influence data, a first temperature influence threshold and a second temperature influence threshold are obtained.

[0031] Temperature subsets are obtained based on the first and second temperature influence thresholds;

[0032] Based on the resistance influence data, a first resistance influence threshold and a second resistance influence threshold are obtained, and a resistance partitioning subset is obtained based on the first resistance influence threshold and the second resistance influence threshold.

[0033] By arranging and combining the temperature subset and the resistance subset, multiple temperature-resistance correlation groups are obtained.

[0034] Preferably, the step of constructing a corresponding operating voltage prediction model based on the temperature-resistance correlation group, real-time resistance data, and real-time temperature data, and inputting the real-time resistance correction value and real-time temperature value into the corresponding operating voltage prediction model to obtain the simulated operating voltage value includes:

[0035] The real-time resistance data and real-time temperature data are paired together to obtain multiple temperature-resistance pairing groups;

[0036] The ideal voltage and ideal power values ​​of the gallium nitride device are obtained based on the ideal parameter information, and the corresponding simulated operating voltage value is obtained based on the ideal voltage value, ideal power value and multiple temperature-resistance pairing groups.

[0037] Based on the temperature-resistance pairing group and the simulated operating voltage value, construct the operating voltage prediction model for the corresponding temperature-resistance correlation group;

[0038] The historical resistance value and historical temperature value corresponding to each temperature-resistance pairing are sequentially input into the working voltage prediction model as a training set for training, and the remaining historical resistance value and historical temperature value are used as a validation set for validation, resulting in multiple prediction training results.

[0039] The model parameters of the working voltage prediction model are adjusted based on multiple prediction training results to obtain the working voltage prediction model.

[0040] The real-time resistance correction value and real-time temperature value are input into the working voltage prediction model of the corresponding temperature-resistance correlation group to obtain the simulated working voltage value.

[0041] Preferably, the step of adjusting the circuit containing the gallium nitride device based on the simulated operating voltage value to obtain the compensated and adjusted electrical parameters includes:

[0042] The voltage error value is obtained based on the simulated operating voltage value and the real-time voltage value;

[0043] A voltage adjustment signal is obtained based on the voltage error value, and the voltage adjustment element is adjusted according to the voltage adjustment signal to obtain a compensation adjustment voltage value;

[0044] The voltage divider resistor information of the circuit containing the gallium nitride device is obtained based on the electrical parameter data, and the voltage divider resistor is adjusted based on the voltage divider resistor information and the real-time resistance correction value to obtain the compensation adjustment resistor value.

[0045] The compensation adjustment current value is obtained based on the compensation adjustment voltage value and the compensation adjustment resistance value.

[0046] This application also provides an electromagnetic heating system for a gallium nitride-based Class E power amplifier, including:

[0047] The first acquisition module is used to acquire device characteristic information of gallium nitride devices, and acquire operating characteristic information and ideal parameter information based on the device characteristic information;

[0048] The second acquisition module is used to acquire electrical parameter data of the circuit where the gallium nitride device is located, and to acquire real-time resistance data of the gallium nitride device based on the operating characteristic information and electrical parameter data. The real-time resistance data includes real-time resistance value and multiple historical resistance values.

[0049] The third acquisition module is used to acquire real-time temperature data of the gallium nitride device based on the temperature sensor. The real-time temperature data includes real-time temperature value and multiple historical temperature values. The module also acquires real-time resistance correction value based on the operating characteristic information, ideal parameter information, real-time temperature value and real-time resistance value.

[0050] The partitioning module is used to obtain a resistance partitioning subset and a temperature partitioning subset based on the operating characteristic information, and to obtain a temperature-resistance association group based on the resistance partitioning subset and the temperature partitioning subset;

[0051] The prediction module is used to construct a corresponding working voltage prediction model based on the temperature-resistance correlation group, real-time resistance data and real-time temperature data, and input the real-time resistance correction value and real-time temperature value into the corresponding working voltage prediction model to obtain the simulated working voltage value.

[0052] The adjustment module is used to adjust the circuit where the gallium nitride device is located according to the analog value of the working voltage to obtain the compensation adjustment electrical parameters, wherein the compensation adjustment electrical parameters include the compensation adjustment current value and the compensation adjustment voltage value, and to obtain the real-time output power of the gallium nitride device according to the compensation adjustment current value and the compensation adjustment voltage value.

[0053] The judgment module is used to determine whether the real-time output power is greater than a preset power threshold.

[0054] If the real-time output power is greater than the preset power threshold, the electromagnetic heating effect is determined to be as expected.

[0055] If the real-time output power is not greater than the preset power threshold, it is determined that the electromagnetic heating effect has not met expectations. Then, the process returns to the step of constructing the corresponding working voltage prediction model based on the temperature-resistance correlation group, real-time resistance data, and real-time temperature data until the electromagnetic heating effect meets expectations.

[0056] Preferably, the partitioning module includes:

[0057] The first acquisition unit is used to acquire temperature influence data and resistance influence data based on the operating characteristic information, and to acquire a first temperature influence threshold and a second temperature influence threshold based on the temperature influence data.

[0058] The second acquisition unit is used to acquire a temperature partition subset based on the first temperature influence threshold and the second temperature influence threshold.

[0059] The third acquisition unit is used to acquire a first resistance influence threshold and a second resistance influence threshold based on the resistance influence data, and to acquire a resistance partitioning subset based on the first resistance influence threshold and the second resistance influence threshold.

[0060] The permutation and combination unit is used to permutate and combine the temperature partition subset and the resistance partition subset to obtain multiple temperature-resistance correlation groups.

[0061] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described electromagnetic heating method for a gallium nitride-based Class E power amplifier.

[0062] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described electromagnetic heating method for a gallium nitride-based Class E power amplifier.

[0063] The beneficial effects of this invention are as follows: By analyzing the operating characteristic information and ideal parameter information of gallium nitride (GaN) devices, subsequent operations can be based on the essential characteristics of GaN devices and closely follow their actual conditions. Then, based on the electrical parameter data of the circuit containing the GaN device and the operating characteristic information of the GaN device, real-time resistance data of the GaN device is obtained. Since temperature is the main factor affecting the resistance change of GaN devices, obtaining real-time temperature data of the GaN device can reflect the historical and current heating status of the GaN device. Then, based on the obtained operating characteristic information, ideal parameter information, real-time temperature value, and real-time resistance value, a real-time resistance correction value is calculated. This compensation mechanism based on real-time data can quickly respond to temperature changes, thereby improving the circuit's adaptability. Next, resistance subsets and temperature subsets are obtained separately. After arranging and combining the resistance subsets and temperature subsets, multiple temperature-resistance correlation groups are obtained. Different temperature-resistance correlation groups can reflect the inherent relationship between different temperature change ranges and different resistance change ranges, providing a data foundation for establishing an operating voltage prediction model. Then, based on the temperature-resistance correlation groups and real-time... A corresponding operating voltage prediction model is constructed using resistance data and real-time temperature data. Then, the real-time resistance correction value and real-time temperature value are input into the corresponding operating voltage prediction model. Based on the relationship between temperature and resistance, the operating voltage prediction model predicts the required operating voltage (simulated operating voltage) for the gallium nitride (GaN) device under the current real-time resistance correction value and real-time temperature value. Next, the circuit containing the GaN device is adjusted according to the simulated operating voltage value to obtain compensation adjustment electrical parameters. By adjusting the circuit containing the GaN device using these compensation adjustment electrical parameters, the operating voltage and current of the GaN device can be brought close to ideal values ​​to ensure stable device performance. Finally, the real-time output power of the GaN device is calculated using the compensation adjustment current value and the compensation adjustment voltage value. The real-time output power directly reflects the energy conversion efficiency of the device under the current operating state. Comparing the real-time output power with a preset power threshold allows for a direct assessment of whether the electromagnetic heating effect meets expectations. If the heating effect does not meet expectations, the operating voltage prediction model is reconstructed and adjusted to form a closed-loop feedback control system. By continuously optimizing the circuit parameters, the expected heating effect is achieved. Attached Figure Description

[0064] Figure 1 This is a schematic diagram of a method flow according to an embodiment of this application.

[0065] Figure 2 This is a schematic diagram of the system structure according to an embodiment of this application.

[0066] Figure 3 This is a schematic diagram of the internal structure of a computer device according to an embodiment of this application.

[0067] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0068] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0069] like Figures 1-3 As shown, this application provides an electromagnetic heating method for a gallium nitride-based Class E power amplifier, comprising:

[0070] S1. Obtain the device characteristic information of the gallium nitride device, and obtain the operating characteristic information and ideal parameter information based on the device characteristic information;

[0071] S2. Obtain the electrical parameter data of the circuit where the gallium nitride device is located, and obtain the real-time resistance data of the gallium nitride device based on the operating characteristic information and electrical parameter data. The real-time resistance data includes the real-time resistance value and multiple historical resistance values.

[0072] S3. Obtain real-time temperature data of the gallium nitride device based on the temperature sensor. The real-time temperature data includes the real-time temperature value and multiple historical temperature values. Obtain the real-time resistance correction value based on the operating characteristic information, ideal parameter information, real-time temperature value and real-time resistance value.

[0073] S4. Obtain a resistance subset and a temperature subset based on the operating characteristic information, and obtain a temperature-resistance association group based on the resistance subset and the temperature subset;

[0074] S5. Construct a corresponding working voltage prediction model based on the temperature-resistance correlation group, real-time resistance data, and real-time temperature data, and input the real-time resistance correction value and real-time temperature value into the corresponding working voltage prediction model to obtain the simulated working voltage value;

[0075] S6. Adjust the circuit containing the gallium nitride device according to the simulated working voltage value to obtain the compensation adjustment electrical parameters, wherein the compensation adjustment electrical parameters include the compensation adjustment current value and the compensation adjustment voltage value, and obtain the real-time output power of the gallium nitride device according to the compensation adjustment current value and the compensation adjustment voltage value.

[0076] S7. Determine whether the real-time output power is greater than a preset power threshold.

[0077] If the real-time output power is greater than the preset power threshold, the electromagnetic heating effect is determined to be as expected.

[0078] If the real-time output power is not greater than the preset power threshold, it is determined that the electromagnetic heating effect has not met expectations. Then, the process returns to the step of constructing the corresponding working voltage prediction model based on the temperature-resistance correlation group, real-time resistance data, and real-time temperature data, until the electromagnetic heating effect meets expectations.

[0079] As described in steps S1-S7 above, gallium nitride (GaN) is a wide-bandgap semiconductor material with excellent properties such as high electron mobility, high breakdown electric field, and high thermal conductivity. A GaN-based Class E power amplifier is a specific type of high-power amplifier made from GaN material. Through special circuit design and operating methods, it enables transistors to switch rapidly between on and off states, achieving high-efficiency power conversion at high frequencies, typically reaching 70%-90% or higher. The GaN power device is the core component, responsible for converting input electrical energy into high-frequency alternating current to provide the energy required for electromagnetic heating. During the operation of gallium nitride (GaN) devices, their temperature fluctuates, causing changes in on-resistance. This means that under the same operating current, the voltage of the GaN device will also change, leading to variations in power consumption. These changes further affect the physical characteristics and operating state of the GaN device. Higher power consumption complicates the physical processes such as electron migration within the GaN device, generating additional thermal effects and affecting the electric field distribution within the device. This results in unstable responses when the device is turned on and off under control signals, making precise control of the signal by the Class E power amplifier unstable and hindering stable power output. Due to the unstable system power output, the heat received by the heated object also fluctuates, causing the electromagnetic heating system to fail to achieve the expected heating effect. In this invention, operating characteristic information and ideal parameter information are obtained based on the device characteristic information of gallium nitride (GaN) devices. Device characteristic information refers to information related to the various physical and electrical properties inherent in the GaN device itself, such as material properties and manufacturing process parameters. By analyzing this information, the operating characteristic information extracted refers to the performance and behavioral patterns of the GaN device in actual operating circuits, such as the signal change frequency and signal stability during operation. Ideal parameter information refers to the various parameter values ​​that the GaN device should possess under ideal operating conditions, such as ideal operating temperature, ideal resistance, and ideal output power. This is achieved by understanding the inherent characteristics of gallium nitride devices. Starting from this point, subsequent operations can be closely tailored to the actual situation of the gallium nitride (GaN) device, improving the pertinence and accuracy of subsequent adjustment methods. Next, based on the electrical parameter data of the circuit containing the GaN device and the operating characteristics of the GaN device, real-time resistance data of the GaN device is obtained. The electrical parameter data refers to the specific values ​​of various electrical-related parameters in the circuit containing the GaN device, such as voltage, current, resistance, power, frequency, and phase. Real-time resistance data refers to a series of resistance-related data acquired in real time during the operation of the GaN device, including the real-time resistance value and multiple historical resistance values. The real-time resistance value refers to the resistance value of the GaN device acquired at the current moment.Historical resistance values ​​refer to the resistance values ​​of gallium nitride (GaN) devices acquired at different times in the past. Since temperature is the primary factor affecting the resistance changes of GaN devices, acquiring real-time temperature data can reflect the historical and current heat generation of the GaN device. Real-time temperature data refers to a series of temperature-related data collected in real time during the operation of the GaN device, including the real-time temperature value and multiple historical temperature values. The real-time temperature value is the actual temperature of the GaN device measured by a temperature sensor at the current moment, while historical temperature values ​​are temperature records of the GaN device measured at different points in the past. Then, by acquiring operating characteristic information, ideal parameter information, real-time temperature values, and... Real-time resistance value calculation involves determining a real-time resistance correction value, which is a calculated value obtained after compensating for the real-time resistance. This compensation mechanism based on real-time data can quickly respond to temperature changes, thereby improving the circuit's adaptability. Then, resistance subsets and temperature subsets are obtained separately. The resistance subsets are defined as resistance ranges that have the same impact on the gallium nitride device based on different resistance values. The temperature subsets are defined as temperature ranges that have the same impact on the gallium nitride device based on different temperature values. Combining the resistance and temperature subsets yields multiple temperature-resistance correlation groups. These temperature-resistance correlation groups refer to groups of different resistance values... Multiple sets of relationships are obtained by matching different temperature subsets with the resistance subset. Different temperature-resistance correlation sets can reflect the inherent relationship between different temperature ranges and different resistance ranges, providing a data foundation for establishing an operating voltage prediction model. Then, based on the temperature-resistance correlation sets, real-time resistance data, and real-time temperature data, a corresponding operating voltage prediction model is constructed. Then, the real-time resistance correction value and real-time temperature value are input into the corresponding operating voltage prediction model. The operating voltage prediction model can predict the operating voltage required by the gallium nitride device under the current real-time resistance correction value and real-time temperature value, i.e., the simulated operating voltage value. The simulated operating voltage value refers to the value calculated by the model. The simulated estimated operating voltage of the gallium nitride (GaN) device under the current state is obtained. Then, the circuit containing the GaN device is adjusted based on this simulated operating voltage to obtain compensation adjustment electrical parameters. These compensation adjustment electrical parameters are electrical parameters obtained after adjusting the circuit containing the GaN device, mainly including compensation adjustment current and compensation adjustment voltage values. This allows the operating voltage and current of the GaN device to approach ideal values, thus ensuring stable device performance. Finally, the real-time output power of the GaN device is calculated using the compensation adjustment current and compensation adjustment voltage values. The real-time output power refers to the actual power value output to the load by the GaN device after a series of parameter adjustments and circuit control.Real-time output power directly reflects the energy conversion efficiency of the device under its current operating state. Comparing the real-time output power with a preset power threshold allows for a direct assessment of whether the electromagnetic heating effect meets expectations. If the heating effect falls short, the system reconstructs and adjusts the operating voltage prediction model, forming a closed-loop feedback control system that continuously optimizes circuit parameters until the desired heating effect is achieved.

[0080] In one embodiment, step S2, which involves obtaining the real-time resistance data of the gallium nitride device based on the operating characteristic information and electrical parameter data, includes:

[0081] S21. Obtain the signal variation frequency and signal stability value of the gallium nitride device based on the operating characteristic information;

[0082] S22. Obtain the interference frequency and interference intensity of the electromagnetic device, and obtain the mean sample size based on the interference frequency, interference intensity, signal change frequency, and signal stability value. The calculation formula is as follows:

[0083]

[0084] Where N represents the number of mean samples, a represents the proportion constant, and f d The frequency of signal variation is represented by ω1, the first coefficient is represented by C, the stable value of the signal is represented by ω2, and the second coefficient is represented by f. n ω3 represents the interference frequency, I represents the interference intensity, ω4 represents the fourth coefficient, and b represents the offset of the base sample number.

[0085] S23. Obtain multiple fluctuating voltage values ​​and multiple fluctuating current values ​​corresponding to each detection time based on the electrical parameter data;

[0086] S24. Obtain the corresponding real-time voltage data based on the multiple fluctuating voltage values ​​and the average number of samples, and obtain the corresponding real-time current data based on the multiple fluctuating current values ​​and the average number of samples.

[0087] S25. Obtain the corresponding real-time resistance data based on the real-time voltage data and the corresponding real-time current data.

[0088] As described in steps S21-S25 above, this invention obtains the signal variation frequency and signal stability value of the gallium nitride (GaN) device. The signal variation frequency refers to the number of times the electrical signal of the GaN device changes periodically per unit time during operation, and the signal stability value refers to a relatively fixed value that the electrical signal of the GaN device approaches and maintains when it is in a stable operating state. Furthermore, the invention obtains the interference frequency and interference intensity of the electromagnetic device. The interference frequency refers to the frequency of the interference signal generated by the electromagnetic device in the electromagnetic environment where the GaN device is located, and the interference intensity is a value used to measure the degree of influence of electromagnetic interference on the GaN device. In the circuit environment where the GaN device is located, the electromagnetic device generates electromagnetic interference, affecting the voltage and electrical stability of the GaN device. The accuracy of current measurement is affected by interference frequency and intensity, which can describe the detailed characteristics of such interference. The mean sample size is calculated using a specific formula based on the acquired values. The mean sample size refers to the number of samples selected for averaging real-time voltage and current data. Using the mean sample size effectively suppresses the influence of electromagnetic interference when acquiring real-time voltage and current data, improving data accuracy and reliability. When using the above formula, it is known that a higher signal frequency means more changes in the signal per unit time. To accurately capture the signal's changing characteristics, more samples are needed for mean calculation. The first coefficient represents the sensitivity of the sample size to frequency changes. A higher stability value indicates a more stable signal. For stable signals, a relatively smaller number of samples is required. The second coefficient represents the degree to which the sample number is affected by signal stability. The ratio of interference frequency to signal variation frequency reflects their relative relationship. When the interference frequency is much higher than the signal variation frequency, the variation of the interference signal within the signal period is relatively more complex. To accurately distinguish between the signal and interference, a larger number of samples is needed for mean calculation to filter out the influence of interference. The third coefficient represents the degree to which the sample number is affected by the relative relationship between interference frequency and signal variation frequency. Similarly, the greater the interference intensity, the more severe the interference's impact on the signal. To accurately extract signal features in a strong interference environment, a larger number of samples is needed for mean calculation. The four coefficients represent the degree to which the sample size is affected by the interference intensity. In summary, this formula establishes a model that can reasonably calculate the mean sample size by comprehensively considering the logical relationship between various parameters and the mean sample size. This model is designed to meet the needs of processing electrical data of gallium nitride devices under different operating conditions. High-speed sampling chips have rapid sampling capabilities and can sample the same voltage signal multiple times in a very short time. For example, the sampling frequency of high-speed ADC chips can reach the GHz level, enabling multiple sampling of input voltage and current signals within a very short time interval, such as a few nanoseconds or even less. These voltage and current data collected in a very short time are regarded as multiple voltage and current data at the same moment.The fluctuating voltage and fluctuating current values ​​are obtained. The fluctuating voltage value refers to the value collected at the same time to calculate the voltage at a specific moment, and the fluctuating current value refers to the value collected at the same time to calculate the current at a specific moment. For example, if multiple fluctuating voltage values ​​at a certain moment are 4.0V, 4.1V, 4.0V, 4.2V, 4.1V, 4.1V, and 4.0V, and the average sample size is 5, then the 5 fluctuating voltage values ​​in the middle position are selected from the multiple fluctuating voltage values, and the average is calculated to obtain the real-time voltage value at this moment. The calculation result is: (4. (1V + 4.0V + 4.2V + 4.1V + 4.1V) / 5 = 4.1V. Similarly, the real-time current value at this specific moment can be calculated. Through the above calculation method, relatively stable and accurate real-time voltage and current data can be obtained. This eliminates voltage and current fluctuations caused by interference and other factors, resulting in electrical parameter values ​​that better reflect the actual operating state of the device. Finally, based on Ohm's law, the real-time resistance value at this specific moment is calculated using the real-time voltage and current values. The resistance values ​​corresponding to multiple historical moments and the resistance value corresponding to the current moment together constitute the real-time resistance data.

[0089] In one embodiment, step S3, which involves obtaining the real-time resistance correction value based on the operating characteristic information, ideal parameter information, real-time temperature value, and real-time resistance value, includes:

[0090] S31. Obtain the material characteristic coefficients of the gallium nitride device based on the operating characteristic information;

[0091] S32. Obtain the ideal temperature value, standard resistance value, and ideal voltage value of the gallium nitride device based on the ideal parameter information, and obtain the resistance drift value based on the real-time resistance value and the standard resistance value;

[0092] S33. Calculate the resistance compensation value of the gallium nitride device based on the material characteristic coefficient, resistance drift value, real-time temperature value, and ideal temperature value, wherein the calculation formula is:

[0093]

[0094] Among them, R c R represents the resistance compensation value. i α represents the resistance drift value, α represents the material property coefficient, T represents the real-time temperature value, and T0 represents the ideal temperature value.

[0095] S34. Obtain the real-time resistance correction value based on the resistance compensation value and the real-time resistance value.

[0096] As described in steps S31-S34 above, in this invention, the material characteristic coefficient of the gallium nitride (GaN) device is obtained. The material characteristic coefficient is a parameter reflecting the influence of the physical properties of the GaN material on resistance. Different material characteristic coefficients result in different degrees of resistance change with temperature. Next, the ideal temperature value and standard resistance value of the GaN device are obtained. The ideal temperature value refers to the temperature at which the GaN device is considered most suitable and standard for operation. The standard resistance value refers to the resistance value of the GaN device under specific standard conditions (such as standard temperature, standard voltage, etc.). Then, the resistance drift value is obtained by the difference between the real-time resistance value and the standard resistance value. The resistance drift value refers to the difference between the real-time resistance value of the GaN device and the standard resistance value. The difference between the resistance values ​​reflects how the resistance of a gallium nitride (GaN) device changes relative to its resistance under standard conditions due to temperature variations during actual operation. Its magnitude and direction help determine the trend and extent of resistance change. Then, based on the obtained values, a resistance compensation value is calculated using a specific formula. This compensation value is a correction amount calculated to compensate for resistance deviations caused by temperature, used to adjust the real-time resistance value. Finally, the sum of the compensation value and the real-time resistance value is obtained to arrive at the real-time resistance correction value. This correction value is the value obtained after correcting the real-time resistance value, thereby correcting the real-time resistance of the GaN device to make it closer to the true resistance value it should have under ideal conditions.

[0097] In one embodiment, step S4, which involves obtaining a resistance subset and a temperature subset based on the operating characteristic information, and obtaining a temperature-resistance association group based on the resistance subset and the temperature subset, includes:

[0098] S41. Obtain temperature influence data and resistance influence data based on the operating characteristic information, and obtain a first temperature influence threshold and a second temperature influence threshold based on the temperature influence data.

[0099] S42. Obtain a temperature partitioning subset based on the first temperature influence threshold and the second temperature influence threshold;

[0100] S43. Obtain a first resistance influence threshold and a second resistance influence threshold based on the resistance influence data, and obtain a resistance partitioning subset based on the first resistance influence threshold and the second resistance influence threshold;

[0101] S44. Arrange and combine the temperature partition subset and the resistance partition subset to obtain multiple temperature-resistance correlation groups.

[0102] As described in steps S41-S44 above, this invention acquires temperature influence data and resistance influence data. Temperature influence data refers to various data including the impact of temperature on the operating characteristics of gallium nitride (GaN) devices, and resistance influence data refers to various data including the impact of resistance on the operating characteristics of GaN devices. These data help to understand the relevant patterns and mechanisms of temperature and resistance in the operating characteristics of GaN devices. Then, a first temperature influence threshold and a second temperature influence threshold are obtained using the temperature influence data. These thresholds are lower limits for distinguishing the degree of influence of high and low temperatures on GaN devices. For example, a temperature below the first temperature influence threshold can be considered... A constant temperature has a relatively small impact on gallium nitride (GaN) devices. Temperatures between the first and second temperature influence thresholds have a moderate impact on GaN devices, while temperatures above the second temperature influence threshold have a significant impact. Similarly, the first and second resistance influence thresholds are obtained using resistance influence data. These thresholds represent the lower limits that differentiate the degree of influence of resistance on GaN devices. Then, multiple historical temperature values ​​are divided into temperature subsets based on the set first and second temperature influence thresholds, and multiple historical resistance values ​​are divided into resistance subsets based on the set first and second resistance influence thresholds. This allows for the initial classification and organization of temperature and resistance data, grouping temperature and resistance values ​​with similar levels of influence together. For example, assuming the first temperature influence threshold is 18℃ and the second is 28℃, the resulting temperature subsets include low-influence, medium-influence, and high-influence temperature sets. The low-influence temperature set includes temperatures ≤18℃, the medium-influence temperature set includes temperatures between 18℃ and 28℃, and the high-influence temperature set includes temperatures ≥28℃. Similarly, assuming the first resistance influence threshold is 10Ω and the second is 15Ω, the resulting resistance subsets include low-influence, medium-influence, and high-influence resistance sets. The low-influence resistance set includes resistance values ​​≤10Ω. The medium-influence resistance set is defined as resistance values ​​between 10Ω and 15Ω, and the high-influence resistance set is defined as resistance values ​​≥ 15Ω. Then, the temperature and resistance subsets are permuted and combined to obtain temperature-resistance correlation groups, such as: low-influence temperature-low-influence resistance group, low-influence temperature-medium-influence resistance group, low-influence temperature-high-influence resistance group, medium-influence temperature-low-influence resistance group, medium-influence temperature-medium-influence resistance group, medium-influence temperature-high-influence resistance group, high-influence temperature-low-influence resistance group, high-influence temperature-medium-influence resistance group, and high-influence temperature-high-influence resistance group. This permutation and combination method comprehensively considers all possible correlations between different temperature ranges and different resistance ranges, forming multiple temperature-resistance correlation groups.A complete data structure is provided for further research on the relationship between temperature and resistance.

[0103] In one embodiment, step S5, which involves constructing a corresponding operating voltage prediction model based on the temperature-resistance correlation group, real-time resistance data, and real-time temperature data, and inputting the real-time resistance correction value and real-time temperature value into the corresponding operating voltage prediction model to obtain the simulated operating voltage value, includes:

[0104] S51. Pair the real-time resistance data and real-time temperature data to obtain multiple temperature-resistance pairing groups;

[0105] S52. Obtain the ideal voltage and ideal power values ​​of the gallium nitride device based on the ideal parameter information, and obtain the corresponding simulated operating voltage value based on the ideal voltage value, ideal power value, and multiple temperature-resistance pairing groups;

[0106] S53. Construct a working voltage prediction model for the corresponding temperature-resistance correlation group based on the temperature-resistance pairing group and the simulated working voltage value;

[0107] S54. The historical resistance value and historical temperature value corresponding to each temperature-resistance pairing group are sequentially input into the working voltage prediction model as a training set for training, and the remaining historical resistance value and historical temperature value are used as a validation set for validation to obtain multiple prediction training results.

[0108] S55. Adjust the model parameters of the working voltage prediction model based on the multiple prediction training results to obtain the working voltage prediction model.

[0109] S56. Input the real-time resistance correction value and real-time temperature value into the working voltage prediction model of the corresponding temperature-resistance correlation group to obtain the working voltage simulation value.

[0110] As described in steps S51-S56 above, in this invention, the real-time acquired resistance data and temperature data are paired to form a temperature-resistance pairing group. The purpose of this pairing is to correlate temperature and resistance information at the same moment to facilitate subsequent analysis of their relationship with the operating voltage. Then, by combining the ideal voltage value, ideal power value, and the temperature-resistance pairing group, the simulated operating voltage value under different temperature-resistance combinations can be calculated. The calculation formula is as follows: These simulation values ​​provide an initial data foundation for the subsequent construction of the operating voltage prediction model, helping the model understand the possible range of operating voltage values ​​under different conditions. Assuming the operating voltage prediction model for the low-influence temperature-low-influence resistance group is: V = β0 + β a *T+β b*R+∈, this model aims to reveal the intrinsic mathematical relationship between temperature, resistance, and operating voltage. Through learning and analysis of existing data, it provides a computational framework for subsequent operating voltage prediction. Then, the historical resistance values, historical temperature values, and simulated operating voltage values ​​corresponding to half of the temperature-resistance pairings that conform to the low-impact temperature-low-impact resistance pattern are used as the training set and input into the operating voltage prediction model for training. The remaining half of the historical resistance values ​​and historical temperature values ​​are used as the validation set for validation, resulting in multiple prediction training results. Subsequently, the model parameters of the operating voltage prediction model are adjusted based on these multiple prediction training results, resulting in the operating voltage prediction model: V=β0+β c *T+β d *R+∈, by continuously adjusting the model parameters, the model can perform well on both the training and validation sets, providing a basis for model optimization. Finally, the real-time resistance correction value and real-time temperature value are input into the working voltage prediction model of the corresponding temperature-resistance correlation group. The model can calculate the simulated working voltage value under the current conditions based on the learned rules, providing a reference for actual circuit control and performance evaluation.

[0111] In one embodiment, step S6, which adjusts the circuit containing the gallium nitride device based on the analog operating voltage value to obtain the compensated and adjusted electrical parameters, includes:

[0112] S61. Obtain the voltage error value based on the simulated working voltage value and the real-time voltage value;

[0113] S62. Obtain a voltage adjustment signal based on the voltage error value, and adjust the voltage adjustment element according to the voltage adjustment signal to obtain a compensation adjustment voltage value;

[0114] S63. Obtain the voltage divider resistor information of the circuit where the gallium nitride device is located based on the electrical parameter data, and adjust the voltage divider resistor based on the voltage divider resistor information and the real-time resistance correction value to obtain the compensation adjustment resistor value.

[0115] S64. Obtain the compensation adjustment current value based on the compensation adjustment voltage value and the compensation adjustment resistance value.

[0116] As described in steps S61-S64 above, this invention obtains a voltage error value by comparing the simulated working voltage value and the real-time voltage value. The voltage error value refers to the difference between the simulated working voltage value and the real-time voltage value. The voltage error value clearly indicates the degree of deviation between the actual circuit voltage and the expected simulated voltage. Then, a voltage adjustment signal is generated based on the voltage error value. This voltage adjustment signal is a control signal generated based on the voltage error value, used to control the voltage adjustment element to adjust the circuit voltage, thereby obtaining a compensation adjustment voltage value. The compensation adjustment voltage value refers to the voltage value across the gallium nitride device obtained after adjusting the voltage adjustment element. Next, the voltage divider resistor information of the circuit containing the gallium nitride device is obtained based on the electrical parameter data. The voltage divider resistor information refers to various parameter information related to the voltage divider resistor in the circuit containing the gallium nitride device, such as the resistance value and power of the voltage divider resistor. This information is then combined with the real-time resistance correction value to adjust the voltage divider resistor, resulting in a compensation adjustment resistor value. This compensation adjustment resistor value takes into account the real-time resistance correction value of the gallium nitride device and the voltage division requirements of the circuit. The adjusted voltage divider resistor value is used to adjust the voltage division in the circuit, making the voltage distribution more reasonable and meeting the circuit's operating requirements. Finally, the compensation adjustment current value is calculated based on the compensation adjustment voltage value and the compensation adjustment resistor value, obtaining the current situation of the entire circuit after voltage and resistance adjustment, ensuring that the current in the circuit also reaches a suitable state.

[0117] This application also provides an electromagnetic heating system for a gallium nitride-based Class E power amplifier, including:

[0118] The first acquisition module is used to acquire device characteristic information of gallium nitride devices, and acquire operating characteristic information and ideal parameter information based on the device characteristic information;

[0119] The second acquisition module is used to acquire electrical parameter data of the circuit where the gallium nitride device is located, and to acquire real-time resistance data of the gallium nitride device based on the operating characteristic information and electrical parameter data. The real-time resistance data includes real-time resistance value and multiple historical resistance values.

[0120] The third acquisition module is used to acquire real-time temperature data of the gallium nitride device based on the temperature sensor. The real-time temperature data includes real-time temperature value and multiple historical temperature values. The module also acquires real-time resistance correction value based on the operating characteristic information, ideal parameter information, real-time temperature value and real-time resistance value.

[0121] The partitioning module is used to obtain a resistance partitioning subset and a temperature partitioning subset based on the operating characteristic information, and to obtain a temperature-resistance association group based on the resistance partitioning subset and the temperature partitioning subset;

[0122] The prediction module is used to construct a corresponding working voltage prediction model based on the temperature-resistance correlation group, real-time resistance data and real-time temperature data, and input the real-time resistance correction value and real-time temperature value into the corresponding working voltage prediction model to obtain the simulated working voltage value.

[0123] The adjustment module is used to adjust the circuit where the gallium nitride device is located according to the analog value of the working voltage to obtain the compensation adjustment electrical parameters, wherein the compensation adjustment electrical parameters include the compensation adjustment current value and the compensation adjustment voltage value, and to obtain the real-time output power of the gallium nitride device according to the compensation adjustment current value and the compensation adjustment voltage value.

[0124] The judgment module is used to determine whether the real-time output power is greater than a preset power threshold.

[0125] If the real-time output power is greater than the preset power threshold, the electromagnetic heating effect is determined to be as expected.

[0126] If the real-time output power is not greater than the preset power threshold, it is determined that the electromagnetic heating effect has not met expectations. Then, the process returns to the step of constructing the corresponding working voltage prediction model based on the temperature-resistance correlation group, real-time resistance data, and real-time temperature data, until the electromagnetic heating effect meets expectations.

[0127] In one embodiment, the partitioning module includes:

[0128] The first acquisition unit is used to acquire temperature influence data and resistance influence data based on the operating characteristic information, and to acquire a first temperature influence threshold and a second temperature influence threshold based on the temperature influence data.

[0129] The second acquisition unit is used to acquire a temperature partition subset based on the first temperature influence threshold and the second temperature influence threshold.

[0130] The third acquisition unit is used to acquire a first resistance influence threshold and a second resistance influence threshold based on the resistance influence data, and to acquire a resistance partitioning subset based on the first resistance influence threshold and the second resistance influence threshold.

[0131] The permutation and combination unit is used to permutate and combine the temperature partition subset and the resistance partition subset to obtain multiple temperature-resistance correlation groups.

[0132] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described electromagnetic heating method for a gallium nitride-based Class E power amplifier.

[0133] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described electromagnetic heating method for a gallium nitride-based Class E power amplifier.

[0134] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media provided in this application and in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0135] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, apparatus, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0136] The above description is merely a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. An electromagnetic heating method for a Class E power amplifier based on gallium nitride, characterized in that, include: Obtain device characteristic information of gallium nitride devices, and obtain operating characteristic information and ideal parameter information based on the device characteristic information; Obtain the electrical parameter data of the circuit where the gallium nitride device is located, and obtain the real-time resistance data of the gallium nitride device based on the operating characteristic information and the electrical parameter data. The real-time resistance data includes the real-time resistance value and multiple historical resistance values. The real-time temperature data of the gallium nitride device is obtained by a temperature sensor. The real-time temperature data includes the real-time temperature value and multiple historical temperature values. The real-time resistance correction value is obtained based on the operating characteristic information, ideal parameter information, real-time temperature value and real-time resistance value. Based on the operating characteristic information, a resistance subset and a temperature subset are obtained, and a temperature-resistance association group is obtained based on the resistance subset and the temperature subset. Based on the temperature-resistance correlation group, real-time resistance data, and real-time temperature data, a corresponding operating voltage prediction model is constructed, and the real-time resistance correction value and real-time temperature value are input into the corresponding operating voltage prediction model to obtain the simulated operating voltage value. The circuit containing the gallium nitride device is adjusted according to the simulated operating voltage value to obtain the compensation adjustment electrical parameters, wherein the compensation adjustment electrical parameters include the compensation adjustment current value and the compensation adjustment voltage value, and the real-time output power of the gallium nitride device is obtained according to the compensation adjustment current value and the compensation adjustment voltage value. Determine whether the real-time output power is greater than a preset power threshold; If the real-time output power is greater than the preset power threshold, the electromagnetic heating effect is determined to be as expected. If the real-time output power is not greater than the preset power threshold, it is determined that the electromagnetic heating effect has not met expectations. Then, the process returns to the step of constructing the corresponding working voltage prediction model based on the temperature-resistance correlation group, real-time resistance data, and real-time temperature data, until the electromagnetic heating effect meets expectations.

2. The electromagnetic heating method for a Class E power amplifier based on gallium nitride according to claim 1, characterized in that, The step of obtaining the real-time resistance data of the gallium nitride device based on the operating characteristic information and electrical parameter data includes: The signal variation frequency and signal stability value of the gallium nitride device are obtained based on the aforementioned operating characteristic information; Obtain the interference frequency and interference intensity of the electromagnetic device, and obtain the mean sample number based on the interference frequency, interference intensity, signal change frequency and signal stability value; Based on the electrical parameter data, obtain multiple fluctuating voltage values ​​and multiple fluctuating current values ​​corresponding to each detection time; Real-time voltage data is obtained based on multiple fluctuating voltage values ​​and the average number of samples, and real-time current data is obtained based on multiple fluctuating current values ​​and the average number of samples. The corresponding real-time resistance data is obtained based on the real-time voltage data and the corresponding real-time current data.

3. The electromagnetic heating method for a Class E power amplifier based on gallium nitride according to claim 1, characterized in that, The step of obtaining the real-time resistance correction value based on the operating characteristic information, ideal parameter information, real-time temperature value, and real-time resistance value includes: The material property coefficients of the gallium nitride device are obtained based on the aforementioned operating characteristic information; The ideal temperature value and standard resistance value of the gallium nitride device are obtained based on the ideal parameter information, and the resistance drift value is obtained based on the real-time resistance value and the standard resistance value. The resistance compensation value of the gallium nitride device is obtained based on the material property coefficient, resistance drift value, real-time temperature value, and ideal temperature value. The real-time resistance correction value is obtained based on the resistance compensation value and the real-time resistance value.

4. The electromagnetic heating method for a Class E power amplifier based on gallium nitride according to claim 1, characterized in that, The steps of obtaining resistance subsets and temperature subsets based on the operating characteristic information, and obtaining temperature-resistance association groups based on the resistance subsets and temperature subsets, include: Based on the operating characteristic information, temperature influence data and resistance influence data are obtained, and based on the temperature influence data, a first temperature influence threshold and a second temperature influence threshold are obtained. Temperature subsets are obtained based on the first and second temperature influence thresholds; Based on the resistance influence data, a first resistance influence threshold and a second resistance influence threshold are obtained, and a resistance partitioning subset is obtained based on the first resistance influence threshold and the second resistance influence threshold. By arranging and combining the temperature subset and the resistance subset, multiple temperature-resistance correlation groups are obtained.

5. The electromagnetic heating method for a Class E power amplifier based on gallium nitride according to claim 1, characterized in that, The step of constructing a corresponding operating voltage prediction model based on the temperature-resistance correlation group, real-time resistance data, and real-time temperature data, and inputting the real-time resistance correction value and real-time temperature value into the corresponding operating voltage prediction model to obtain the simulated operating voltage value includes: The real-time resistance data and real-time temperature data are paired together to obtain multiple temperature-resistance pairing groups; The ideal voltage and ideal power values ​​of the gallium nitride device are obtained based on the ideal parameter information, and the corresponding simulated operating voltage value is obtained based on the ideal voltage value, ideal power value and multiple temperature-resistance pairing groups. Based on the temperature-resistance pairing group and the simulated operating voltage value, construct the operating voltage prediction model for the corresponding temperature-resistance correlation group; The historical resistance value and historical temperature value corresponding to each temperature-resistance pairing are sequentially input into the working voltage prediction model as a training set for training, and the remaining historical resistance value and historical temperature value are used as a validation set for validation, resulting in multiple prediction training results. The model parameters of the working voltage prediction model are adjusted based on multiple prediction training results to obtain the working voltage prediction model. The real-time resistance correction value and real-time temperature value are input into the working voltage prediction model of the corresponding temperature-resistance correlation group to obtain the simulated working voltage value.

6. The electromagnetic heating method for a Class E power amplifier based on gallium nitride according to claim 1, characterized in that, The step of adjusting the circuit containing the gallium nitride device based on the simulated operating voltage value to obtain the compensated electrical parameters includes: The voltage error value is obtained based on the simulated operating voltage value and the real-time voltage value; A voltage adjustment signal is obtained based on the voltage error value, and the voltage adjustment element is adjusted according to the voltage adjustment signal to obtain a compensation adjustment voltage value; The voltage divider resistor information of the circuit containing the gallium nitride device is obtained based on the electrical parameter data, and the voltage divider resistor is adjusted based on the voltage divider resistor information and the real-time resistance correction value to obtain the compensation adjustment resistor value. The compensation adjustment current value is obtained based on the compensation adjustment voltage value and the compensation adjustment resistance value.

7. An electromagnetic heating system for a Class E power amplifier based on gallium nitride, characterized in that, include: The first acquisition module is used to acquire device characteristic information of gallium nitride devices, and acquire operating characteristic information and ideal parameter information based on the device characteristic information; The second acquisition module is used to acquire electrical parameter data of the circuit where the gallium nitride device is located, and to acquire real-time resistance data of the gallium nitride device based on the operating characteristic information and electrical parameter data. The real-time resistance data includes real-time resistance value and multiple historical resistance values. The third acquisition module is used to acquire real-time temperature data of the gallium nitride device based on the temperature sensor. The real-time temperature data includes real-time temperature value and multiple historical temperature values. The module also acquires real-time resistance correction value based on the operating characteristic information, ideal parameter information, real-time temperature value and real-time resistance value. The partitioning module is used to obtain a resistance partitioning subset and a temperature partitioning subset based on the operating characteristic information, and to obtain a temperature-resistance association group based on the resistance partitioning subset and the temperature partitioning subset; The prediction module is used to construct a corresponding working voltage prediction model based on the temperature-resistance correlation group, real-time resistance data and real-time temperature data, and input the real-time resistance correction value and real-time temperature value into the corresponding working voltage prediction model to obtain the simulated working voltage value. The adjustment module is used to adjust the circuit where the gallium nitride device is located according to the analog value of the working voltage to obtain the compensation adjustment electrical parameters, wherein the compensation adjustment electrical parameters include the compensation adjustment current value and the compensation adjustment voltage value, and to obtain the real-time output power of the gallium nitride device according to the compensation adjustment current value and the compensation adjustment voltage value. The judgment module is used to determine whether the real-time output power is greater than a preset power threshold. If the real-time output power is greater than the preset power threshold, the electromagnetic heating effect is determined to be as expected. If the real-time output power is not greater than the preset power threshold, it is determined that the electromagnetic heating effect has not met expectations. Then, the process returns to the step of constructing the corresponding working voltage prediction model based on the temperature-resistance correlation group, real-time resistance data, and real-time temperature data, until the electromagnetic heating effect meets expectations.

8. The electromagnetic heating system for a Class E power amplifier based on gallium nitride according to claim 7, characterized in that, The partitioning module includes: The first acquisition unit is used to acquire temperature influence data and resistance influence data based on the operating characteristic information, and to acquire a first temperature influence threshold and a second temperature influence threshold based on the temperature influence data. The second acquisition unit is used to acquire a temperature partition subset based on the first temperature influence threshold and the second temperature influence threshold. The third acquisition unit is used to acquire a first resistance influence threshold and a second resistance influence threshold based on the resistance influence data, and to acquire a resistance partitioning subset based on the first resistance influence threshold and the second resistance influence threshold. The permutation and combination unit is used to permutate and combine the temperature partition subset and the resistance partition subset to obtain multiple temperature-resistance correlation groups.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images