Adaptive bias voltage optimization method based on MOS tube and related equipment

Abstract

The present invention relates to a method and related equipment for adaptive bias voltage optimization based on MOS tubes, which is applied to a gate drive circuit and includes the following steps: real-time monitoring of a target MOS tube in the operating state of the gate drive circuit to obtain operating parameters of the target MOS tube; based on a preset bias voltage demand prediction model, predicting the bias voltage demand of the target MOS tube based on the operating parameters to obtain a bias voltage demand value; performing digital signal processing on the bias voltage demand value to convert it into a control signal; and applying the control signal to the gate of the target MOS tube to dynamically adjust the operating state of the target MOS tube. This method solves the technical problem that a fixed bias voltage may cause overheating of the MOS tube or increased switching loss under extreme conditions, such as high temperature or heavy load.

Description

Technical Field

[0001] The present invention relates to the technical field of MOS tubes, and in particular to a method for optimizing an adaptive bias voltage based on a MOS tube and related equipment. Background Art

[0002] With the rapid advancement of electronic technology, high performance and low power consumption have become key design criteria for electronic devices. The increasing demand for extended battery life, particularly in portable devices and Internet of Things (IoT) applications, has driven in-depth research into power management technologies. MOS transistors, as one of the most fundamental and commonly used semiconductor components in modern electronic devices, play a crucial role in power management and signal transmission. However, traditional MOS transistors often utilize a fixed bias voltage. While simple and straightforward, this approach struggles to meet optimal performance requirements under varying operating conditions. In particular, a fixed bias voltage can lead to reduced efficiency and increased power consumption under varying load conditions or unstable operating environments.

[0003] Among existing solutions, some technologies have attempted to adjust the bias voltage of MOS transistors through external circuits in the hope of achieving better performance. However, these solutions typically require additional hardware, which not only increases system complexity and cost, but also suffers from slow response speeds and inability to achieve true real-time adjustment. Furthermore, due to the lack of effective bias voltage demand prediction models, existing adaptive bias voltage adjustment technologies often rely on empirical data or simple feedback mechanisms, limiting their applicability in complex and changing application scenarios. Therefore, developing a method that can automatically adjust the MOS transistor bias voltage based on actual operating conditions is particularly important.

[0004] To this end, a MOS transistor-based adaptive bias voltage optimization method is proposed. This method aims to address the shortcomings of traditional fixed bias voltage solutions and existing adaptive regulation technologies. By monitoring the operating parameters of the MOS transistor in real time and leveraging a pre-established bias voltage demand prediction model, the optimal bias voltage demand can be accurately predicted. The predicted value is then digitally processed, converted into a control signal, and applied to the MOS transistor's gate, enabling dynamic adjustment of its operating state. This method not only improves the efficiency and stability of the MOS transistor under various operating conditions but also effectively reduces unnecessary energy consumption, which is of great significance in promoting the development of more energy-efficient and intelligent electronic devices. Summary of the Invention

[0005] The main purpose of the present invention is to provide an adaptive bias voltage optimization method based on MOS tubes and related equipment, which solves the technical problem that under extreme conditions, such as high temperature or heavy load, a fixed bias voltage may cause MOS tube overheating or increased switching loss.

[0006] To achieve the above objectives, the present invention provides a method for optimizing an adaptive bias voltage based on a MOS transistor, which is applied to a gate drive circuit and includes the following steps:

[0007] Perform real-time monitoring on the target MOS transistor when the gate drive circuit is in operation, and obtain the operating parameters of the target MOS transistor;

[0008] Based on a preset bias voltage requirement prediction model, and based on the operating parameters, a bias voltage requirement prediction is performed on the target MOS transistor to obtain a bias voltage requirement value;

[0009] Performing digital signal processing on the bias voltage requirement value to convert it into a control signal;

[0010] The control signal is applied to the gate of the target MOS transistor to dynamically adjust the working state of the target MOS transistor.

[0011] Furthermore, the real-time monitoring of the target MOS transistor in the working state of the gate drive circuit to obtain the working parameters of the target MOS transistor includes:

[0012] Synchronously sampling the gate voltage, drain voltage, and drain current of the target MOS transistor in a gate drive circuit operating state to obtain an original electrical signal data set, wherein the circuit operating state includes the turn-on, amplification, and cut-off of the target MOS transistor;

[0013] Performing time series processing on the original electrical signal data set to obtain switching frequency and duty cycle information of the target MOS tube;

[0014] Scanning the surface temperature of the target MOS transistor to calculate the junction temperature data of the target MOS transistor;

[0015] Using a sliding window method, based on the switching frequency, duty cycle information, and junction temperature data, the operating parameter statistics of the target MOS transistor in different time periods are calculated; wherein the operating parameter statistics include an average gate-source voltage, an average drain-source voltage, and an average drain current;

[0016] A standard bias voltage is set based on the original electrical signal data set, the switching frequency, the duty cycle information, the junction temperature data, and the parameter statistics, and the original electrical signal data set, the switching frequency, the duty cycle information, the junction temperature data, the parameter statistics, and the standard bias voltage are used as operating parameters of the target MOS tube.

[0017] Furthermore, scanning the surface temperature of the target MOS transistor to calculate the junction temperature data of the target MOS transistor includes:

[0018] Performing non-contact temperature measurement on the surface of the target MOS tube using an infrared thermal imager to obtain a surface temperature distribution diagram of the target MOS tube;

[0019] Performing a temperature frequency domain analysis on the surface temperature distribution map using a Fourier transform algorithm to extract the temperature distribution frequency components;

[0020] Performing an inverse calculation of the internal heat distribution of the target MOS tube based on the temperature distribution frequency component using an inverse heat conduction model to obtain an internal temperature distribution diagram;

[0021] The junction temperature data of the target MOS tube is calculated based on the internal temperature distribution diagram using a thermal resistance network model.

[0022] Furthermore, the bias voltage requirement prediction model training process includes:

[0023] Step S31, obtaining historical operating parameters, preprocessing the historical operating parameters to obtain a feature vector set, and dividing the feature vector set into a training set and a standard bias voltage corresponding to the training set; wherein the training set includes an original electrical signal data set, switching frequency, duty cycle information, junction temperature data, and parameter statistics;

[0024] Step S32: inputting the training set into a preset initial bias voltage demand prediction model for calculation to obtain a bias voltage prediction value;

[0025] Step S33, comparing and calculating the standard bias voltage with the bias voltage prediction value to calculate a bias voltage error;

[0026] Step S34, determining whether the bias voltage error is within a preset bias voltage error range; if the bias voltage error is within the preset bias voltage error range, determining the initial bias voltage demand prediction model as the bias voltage demand prediction model;

[0027] Step S35: If the bias voltage error exceeds the preset bias voltage error range, the parameters in the initial bias voltage demand prediction model are adjusted, and steps S31 to S34 are repeated until the bias voltage output by the initial bias voltage demand prediction model is within the preset range to obtain a bias voltage demand prediction model.

[0028] Furthermore, the digital signal processing of the bias voltage requirement value to convert it into a control signal includes:

[0029] quantizing the continuous bias voltage requirement value to obtain a discrete quantized value;

[0030] Performing digital signal processing on the discrete quantized value to obtain a processed digital signal;

[0031] performing signal encoding on the processed digital signal to obtain an encoding control signal;

[0032] Inputting the coded control signal into a preset digital-to-analog converter for signal conversion to obtain an analog control signal;

[0033] The analog control signal is used as a control signal.

[0034] Furthermore, applying the control signal to the gate of the target MOS transistor to dynamically adjust the working state of the target MOS transistor includes:

[0035] Transmitting the control signal to the gate drive circuit to obtain a transmission control signal;

[0036] amplifying and shaping the transmission control signal through a gate drive circuit to obtain an amplified control signal;

[0037] Performing overvoltage and overcurrent protection on the amplified control signal through an amplifier in a gate drive circuit to obtain a protection control signal;

[0038] electrically isolating the protection control signal to obtain an isolation control signal;

[0039] performing signal buffering processing on the isolation control signal to obtain a buffered control signal;

[0040] The buffer control signal is applied to the gate of the target MOS transistor to dynamically adjust the working state of the target MOS transistor.

[0041] Furthermore, the amplifier in the gate drive circuit performs overvoltage and overcurrent protection on the amplified control signal to obtain a protection control signal, including:

[0042] performing spectrum decomposition on the amplified control signal to obtain a spectrum component set;

[0043] constructing a signal energy graph based on the set of spectral components to obtain signal energy information;

[0044] Determine whether the signal energy information has risk signal characteristics, and if so, perform feature extraction on the signal energy information to obtain a risk characteristic signal;

[0045] Analyzing the type of the risk characteristic signal through a preset analysis algorithm, and formulating a protection control signal strategy based on the type of the risk characteristic signal;

[0046] Through the protection control signal strategy, the amplifier in the gate drive circuit is used to perform overvoltage and overcurrent protection on the amplified control signal to obtain a protection control signal.

[0047] The present invention also provides an adaptive bias voltage optimization device based on a MOS tube, which is applied to a gate drive circuit and includes:

[0048] A monitoring module is used to monitor the target MOS transistor in real time when the gate drive circuit is in operation, and obtain the operating parameters of the target MOS transistor;

[0049] A prediction module, configured to predict the bias voltage requirement of the target MOS transistor based on the operating parameters based on a preset bias voltage requirement prediction model to obtain a bias voltage requirement value;

[0050] a conversion module, configured to perform digital signal processing on the bias voltage requirement value to convert it into a control signal;

[0051] The applying module is used to apply the control signal to the gate of the target MOS transistor to dynamically adjust the working state of the target MOS transistor.

[0052] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0053] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0054] The present invention provides an adaptive bias voltage optimization method for MOS transistors, comprising the following steps: real-time monitoring of a target MOS transistor in the operating state of a gate drive circuit to obtain operating parameters of the target MOS transistor; predicting the bias voltage requirement of the target MOS transistor based on the operating parameters using a preset bias voltage requirement prediction model to obtain a bias voltage requirement value; digitally processing the bias voltage requirement value to convert it into a control signal; and applying the control signal to the gate of the target MOS transistor to dynamically adjust the operating state of the target MOS transistor. The above-described technical measures address the technical problem that a fixed bias voltage may cause MOS transistor overheating or increased switching losses under extreme conditions, such as high temperature or heavy load. The adaptive bias voltage optimization method is capable of rapidly responding to actual operating conditions (such as temperature and current) of the MOS transistor, avoiding the risk of overheating or damage caused by a fixed bias voltage, and improving the stability and reliability of the MOS transistor and the entire circuit. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 1 is a schematic diagram of the steps of a method for optimizing an adaptive bias voltage based on a MOS tube in one embodiment of the present invention;

[0056] Figure 2 This is a structural block diagram of an adaptive bias voltage optimization device based on a MOS tube in one embodiment of the present invention;

[0057] Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0058] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0060] like Figure 1 As shown, Figure 1 This is a schematic diagram of the steps of a method for optimizing an adaptive bias voltage based on a MOS tube in one embodiment of the present invention;

[0061] In one embodiment of the present invention, a method for optimizing an adaptive bias voltage based on a MOS transistor is provided, which is applied to a gate drive circuit and includes the following steps:

[0062] Step S1 : monitoring the target MOS transistor in the working state of the gate drive circuit in real time to obtain the working parameters of the target MOS transistor.

[0063] Specifically, the process of monitoring a target MOSFET in real time while the gate drive circuit is operating and obtaining its operating parameters first involves building a monitoring system. This process requires installing a series of high-precision sensors or using built-in detection circuits to continuously track key MOSFET operating parameters, such as temperature, current, and voltage. These sensors or detection circuits must possess sufficient sensitivity and rapid response capabilities to ensure timely and accurate detection of changes in the MOSFET state. For example, in an electric vehicle's power management system, when the vehicle is accelerating, the current supplied by the battery to the motor suddenly increases. If this change can be monitored in real time through a built-in current sensor and quickly fed back to the control system, the gate drive voltage can be adjusted promptly to ensure that the MOSFET maintains efficient operation under these transient conditions, avoiding overheating and increased switching losses. Temperature sensors also play a crucial role, as MOSFET performance is significantly affected by temperature. Excessively high junction temperatures can lead to performance degradation or even damage in high-temperature environments. Therefore, by monitoring the MOSFET's operating temperature in real time and transmitting it, along with other operating parameters, as input signals to a microcontroller or dedicated chip, comprehensive monitoring of the MOSFET's operating state can be achieved, providing accurate data support for subsequent intelligent analysis and dynamic adjustments. In this way, even in complex and changing application environments such as electric vehicles, the MOS can always be ensured to be in the best working condition, thereby improving the energy efficiency and reliability of the entire system.

[0064] Step S2: Based on a preset bias voltage requirement prediction model and the operating parameters, a bias voltage requirement prediction is performed on the target MOS transistor to obtain a bias voltage requirement value.

[0065] Specifically, the process of predicting the bias voltage requirement of the target MOS transistor based on the operating parameters using a preset bias voltage requirement prediction model to obtain the required bias voltage value is a key step in the adaptive bias voltage optimization method. In its implementation, it is first necessary to establish a prediction model that reflects the operating characteristics of the MOS transistor. This model is typically based on extensive experimental data and theoretical analysis, and can accurately predict the optimal bias voltage required by the MOS transistor under different operating conditions. For example, in an electric vehicle's power management system, when the system detects that the vehicle is accelerating and the current and temperature sensors detect an increase in current and temperature, respectively, these real-time operating parameters are immediately transmitted to a microcontroller or dedicated chip. The microcontroller then uses the preset bias voltage requirement prediction model, combined with the current operating parameters, to calculate the bias voltage value required for the MOS transistor to achieve optimal operating conditions under the current conditions. This model may include characteristic parameters such as on-resistance, switching time, and loss at different temperatures and currents, as well as their interrelationships. This model can comprehensively consider the influence of multiple factors and make more accurate predictions. In this way, even under transient conditions like vehicle acceleration, the system can quickly and accurately adjust the MOS bias voltage to ensure it always maintains optimal operating conditions. This not only improves overall system efficiency but also enhances reliability and safety. Furthermore, this model-based prediction approach can be flexibly adjusted to suit different MOS models and application scenarios, further enhancing the system's adaptability and versatility.

[0066] Step S3: performing digital signal processing on the bias voltage requirement value to convert it into a control signal.

[0067] Specifically, digital signal processing of the bias voltage requirement value to convert it into a control signal is a crucial step in achieving adaptive bias voltage optimization for MOS devices. In practice, the bias voltage requirement value obtained from the prediction model is an analog signal or an unprocessed numerical value. These values ​​must be converted into digital signals suitable for processing by a microcontroller or dedicated chip using digital signal processing techniques. For example, in an electric vehicle's power management system, after the system predicts the required bias voltage value for the MOS based on current operating parameters, this value is transmitted to the signal processing unit. The signal processing unit then performs a series of digital processing operations on this bias voltage requirement, including but not limited to analog-to-digital conversion (ADC), filtering, and quantization, to eliminate noise interference and improve signal accuracy and stability. This processed digital signal more accurately reflects the optimal bias voltage requirement of the MOS under current operating conditions.

[0068] These digital signals are then converted into specific control signals to adjust the actual output voltage of the gate drive circuit. This conversion process is typically performed by a digital signal processor (DSP) within the microcontroller. By executing a preset algorithm, the digital signals are converted into pulse-width modulation (PWM) signals or other control signals that can directly control the drive circuit. For example, during acceleration in an electric vehicle, if the prediction model determines that the MOS bias voltage needs to be increased to reduce switching losses, the signal processing unit generates a corresponding PWM signal. By adjusting the PWM signal's duty cycle, the output voltage of the gate drive circuit is altered, thereby dynamically adjusting the MOS bias voltage. This process requires not only high real-time performance but also guaranteed signal conversion accuracy to ensure that the MOS is always in optimal operating conditions. Through this digital signal processing and control signal conversion, the system can automatically and efficiently adjust the MOS bias voltage under various complex operating conditions, improving the overall efficiency of the power management system while also enhancing its reliability and adaptability. For example, when electric vehicles are driving at high speeds for long periods of time or frequently accelerating and decelerating, this adaptive bias voltage optimization method can effectively reduce energy loss and extend battery life, while protecting the MOS from damage due to overheating or overload, ensuring the safe and stable operation of the vehicle.

[0069] Step S4: applying the control signal to the gate of the target MOS transistor to dynamically adjust the working state of the target MOS transistor.

[0070] Specifically, applying the control signal to the gate of the target MOS transistor to dynamically adjust its operating state is the final and most critical step in the adaptive bias voltage optimization method. During this process, the bias voltage requirement, which has been converted from digital signal processing to a control signal, must be effectively transmitted to the MOS transistor's gate to precisely control its operating state. Specifically, the electric vehicle's power management system predicts the optimal bias voltage required by the MOS transistor based on current operating parameters and converts this requirement into a control signal through digital signal processing. These control signals are then fed into the gate drive circuit. The gate drive circuit amplifies these control signals and converts them to an appropriate voltage level, which is then applied directly to the MOS transistor's gate. For example, during acceleration, the system detects changes in current and temperature and, using a predictive model, calculates the need to increase the MOS transistor's bias voltage to reduce switching losses. At this point, the signal processing unit generates a control signal (e.g., a PWM signal) that is then transmitted to the gate drive circuit. Upon receiving these control signals, the gate drive circuit adjusts the output voltage based on the signal requirements and applies the new bias voltage to the MOS transistor's gate. This process requires extremely high real-time and precision to ensure that the MOS can respond quickly to transient changes and maintain optimal operating conditions. This allows the MOS bias voltage to be dynamically adjusted based on actual needs, even under complex operating conditions such as vehicle acceleration, deceleration, or hill climbing, thereby improving the overall efficiency and reliability of the power management system. Furthermore, this dynamic adjustment mechanism not only optimizes the MOS's performance under different operating conditions but also extends its service life to a certain extent. For example, under high temperatures or heavy loads, appropriately increasing the bias voltage can reduce MOS switching losses and prevent overheating damage. Under light loads or low temperatures, appropriately reducing the bias voltage can reduce unnecessary energy consumption and further improve system efficiency. Therefore, applying a control signal to the MOS gate not only enables precise control of the MOS's operating state but also improves the performance and stability of the entire power management system, ensuring safe and efficient operation of electric vehicles under various complex operating conditions.

[0071] In a specific embodiment, the real-time monitoring of the target MOS transistor in the working state of the gate drive circuit to obtain the working parameters of the target MOS transistor includes:

[0072] Synchronously sampling the gate voltage, drain voltage, and drain current of the target MOS transistor in a gate drive circuit operating state to obtain an original electrical signal data set, wherein the circuit operating state includes the turn-on, amplification, and cut-off of the target MOS transistor;

[0073] Performing time series processing on the original electrical signal data set to obtain switching frequency and duty cycle information of the target MOS tube;

[0074] Scanning the surface temperature of the target MOS transistor to calculate the junction temperature data of the target MOS transistor;

[0075] Using a sliding window method, based on the switching frequency, duty cycle information, and junction temperature data, the operating parameter statistics of the target MOS transistor in different time periods are calculated; wherein the operating parameter statistics include an average gate-source voltage, an average drain-source voltage, and an average drain current;

[0076] A standard bias voltage is set based on the original electrical signal data set, the switching frequency, the duty cycle information, the junction temperature data, and the parameter statistics, and the original electrical signal data set, the switching frequency, the duty cycle information, the junction temperature data, the parameter statistics, and the standard bias voltage are used as operating parameters of the target MOS tube.

[0077] Specifically, real-time monitoring of the target MOS transistor in the gate drive circuit's operating state to obtain the target MOS transistor's operating parameters involves synchronously sampling the target MOS transistor's gate voltage, drain voltage, and drain current in the gate drive circuit's operating state to obtain a raw electrical signal dataset. The circuit's operating state includes the target MOS transistor's on, amplified, and cutoff states. In an electric vehicle's power management system, this process first requires high-precision sensors or built-in detection circuits. For example, when the electric vehicle is accelerating, the system activates sensors to synchronously sample the MOS transistor's gate voltage, drain voltage, and drain current. These sensors must possess high precision and fast response capabilities to ensure accurate and real-time capture of the MOS transistor's electrical signals in different operating states. After synchronous sampling, these electrical signals form a raw electrical signal dataset containing the gate voltage, drain voltage, and drain current. Next, this raw electrical signal dataset undergoes time-series processing to obtain the target MOS transistor's switching frequency and duty cycle information. This process is typically performed by a microcontroller or dedicated chip, which extracts the MOS transistor's switching frequency and duty cycle through time-domain analysis of the collected electrical signals. For example, during an electric vehicle's acceleration, the system calculates the switching frequency and duty cycle of the MOS transistor based on the collected electrical signal data set. This is crucial for understanding the MOS's operating state. The switching frequency reflects the number of times the MOS transistor switches on and off per unit time, while the duty cycle represents the proportion of time the MOS transistor is on during each cycle. These two parameters are important for evaluating the MOS's operating efficiency and losses. Simultaneously, the surface temperature of the target MOS transistor is scanned to calculate its junction temperature. This process is typically accomplished using temperature sensing devices such as infrared temperature sensors or thermocouples. For example, in an electric vehicle's power management system, when the system detects a change in the MOS transistor's operating temperature, it activates a temperature sensor to scan the MOS's surface temperature and calculates its junction temperature using a thermal model. Junction temperature is a crucial parameter for evaluating MOS thermal performance. Excessively high junction temperatures can lead to performance degradation or even damage, so real-time monitoring of junction temperature data is crucial for protecting the MOS transistor. A sliding window method is then used to calculate the operating parameter statistics of the target MOS transistor over different time periods based on the switching frequency, duty cycle information, and junction temperature data. The operating parameter statistics include the average gate-source voltage, the average drain-source voltage, and the average drain current. The sliding window method is a commonly used data processing method that performs statistical analysis on data within a certain time window to smooth out short-term fluctuations and extract more stable operating parameters. For example, during the acceleration of an electric vehicle, the system uses the sliding window method to process the MOS switching frequency, duty cycle information, and junction temperature data to calculate the average gate-source voltage, average drain-source voltage, and average drain current over different time periods.These statistical values ​​can more accurately reflect the performance variations of the MOS in actual operation, providing a basis for subsequent optimization control. Finally, a standard bias voltage is set based on the raw electrical signal dataset, switching frequency, duty cycle information, junction temperature data, and parameter statistics. This data, along with the standard bias voltage, is then used as the operating parameter of the target MOS transistor. This process is typically performed by a control algorithm in a microcontroller, which comprehensively analyzes all of the above data to calculate the optimal bias voltage for the MOS under the current operating conditions. For example, during the acceleration of an electric vehicle, the system sets a standard bias voltage based on all collected data to ensure that the MOS is always in optimal operating condition during acceleration. This standard bias voltage is stored in the system and serves as basic data for subsequent control. Through this series of real-time monitoring and data analysis, the system can comprehensively and accurately understand the operating status of the MOS, providing reliable data support for dynamically adjusting the MOS bias voltage. This not only improves the efficiency and reliability of the power management system but also ensures that the MOS is always in optimal operating condition in complex and changing application environments, extending its service life and reducing maintenance costs.

[0078] In a specific embodiment, scanning the surface temperature of the target MOS transistor to calculate the junction temperature data of the target MOS transistor includes:

[0079] Performing non-contact temperature measurement on the surface of the target MOS tube using an infrared thermal imager to obtain a surface temperature distribution diagram of the target MOS tube;

[0080] Performing a temperature frequency domain analysis on the surface temperature distribution map using a Fourier transform algorithm to extract the temperature distribution frequency components;

[0081] Performing an inverse calculation of the internal heat distribution of the target MOS tube based on the temperature distribution frequency component using an inverse heat conduction model to obtain an internal temperature distribution diagram;

[0082] The junction temperature data of the target MOS tube is calculated based on the internal temperature distribution diagram using a thermal resistance network model.

[0083] Specifically, the surface temperature of the target MOS tube is scanned to calculate the junction temperature data of the target MOS tube, including performing non-contact temperature measurement on the surface of the target MOS tube using an infrared thermal imager to obtain a surface temperature distribution map of the target MOS tube. In the power management system of an electric vehicle, this process first requires using an infrared thermal imager to perform non-contact temperature measurement on the surface of the MOS. The infrared thermal imager can capture the temperature distribution of the MOS surface in real time and accurately, generating a detailed surface temperature distribution map. For example, during the acceleration process of an electric vehicle, the system will activate the infrared thermal imager to scan the surface of the MOS, record the temperature values ​​at each location, and form a high-resolution temperature distribution map. This temperature distribution map can intuitively display the temperature changes on the MOS surface, providing basic data for subsequent temperature analysis. Next, the surface temperature distribution map is subjected to temperature frequency domain analysis using the Fourier transform algorithm to extract the temperature distribution frequency component. Fourier transform is a commonly used signal processing technology that can convert time domain signals into frequency domain signals, thereby extracting the frequency components in the signal. In this example, the system converts the collected surface temperature distribution into a frequency domain signal and uses a Fourier transform algorithm to extract the frequency components of the temperature distribution. These frequency components reflect the spatial variation of temperature and are important for understanding the heat conduction process within the MOS transistor. For example, using the Fourier transform, the system can identify the primary frequency components in the MOS surface temperature distribution. These components may correspond to the heat conduction paths and rates within different regions within the MOS transistor. Then, using an inverse heat conduction model, the system performs an inverse calculation of the internal heat distribution of the target MOS transistor based on the frequency components of the temperature distribution, generating an internal temperature distribution map. The inverse heat conduction model is a mathematical model based on physical principles that uses a known surface temperature distribution and heat conduction equations to inversely calculate the internal temperature distribution of the MOS transistor. In the power management system of an electric vehicle, the system uses the inverse heat conduction model, combined with the temperature distribution frequency components extracted by the Fourier transform, to perform an inverse calculation of the internal heat distribution. This process can infer the temperature distribution of each part within the MOS transistor and generate an internal temperature distribution map. For example, through the inverse heat conduction model, the system can calculate the hot spot location and temperature gradient inside the MOS. This information is very important for evaluating the thermal performance of the MOS and potential overheating risks. Finally, the junction temperature data of the target MOS tube is calculated based on the internal temperature distribution map using the thermal resistance network model. The thermal resistance network model is a simplified but effective heat conduction model. By abstracting the heat conduction path inside the MOS into a series of thermal resistances and thermal capacitances, the junction temperature of the MOS can be easily calculated. In this example, the system will use the thermal resistance network model, combined with the internal temperature distribution map, to calculate the junction temperature data of the MOS. Junction temperature data is a key parameter for evaluating the thermal performance of the MOS. Excessively high junction temperature will cause the performance of the MOS to degrade or even damage it.For example, through the thermal resistance network model, the system can calculate the junction temperature of the MOS under the current operating conditions. If the junction temperature exceeds the preset safety threshold, the system will adjust the bias voltage in time to reduce the temperature of the MOS and ensure its safe operation. Through this series of temperature scanning and analysis processes, the system can fully and accurately grasp the temperature distribution of the MOS, providing reliable data support for the dynamic adjustment of the bias voltage of the MOS. This can not only improve the efficiency and reliability of the power management system, but also ensure that the MOS is always in the best working state in complex and changing application environments, extend its service life, and reduce maintenance costs. For example, during the acceleration process of electric vehicles, the system can adjust the bias voltage of the MOS in time through this series of temperature monitoring and analysis to ensure that it still maintains an efficient and safe working state under high load conditions.

[0084] In a specific embodiment, the process of training the bias voltage requirement prediction model includes:

[0085] Step S31, obtaining historical operating parameters, preprocessing the historical operating parameters to obtain a feature vector set, and dividing the feature vector set into a training set and a standard bias voltage corresponding to the training set; wherein the training set includes an original electrical signal data set, switching frequency, duty cycle information, junction temperature data, and parameter statistics;

[0086] Step S32: inputting the training set into a preset initial bias voltage demand prediction model for calculation to obtain a bias voltage prediction value;

[0087] Step S33, comparing and calculating the standard bias voltage with the bias voltage prediction value to calculate a bias voltage error;

[0088] Step S34, determining whether the bias voltage error is within a preset bias voltage error range; if the bias voltage error is within the preset bias voltage error range, determining the initial bias voltage demand prediction model as the bias voltage demand prediction model;

[0089] Step S35: If the bias voltage error exceeds the preset bias voltage error range, the parameters in the initial bias voltage demand prediction model are adjusted, and steps S31 to S34 are repeated until the bias voltage output by the initial bias voltage demand prediction model is within the preset range to obtain a bias voltage demand prediction model.

[0090] Specifically, the bias voltage requirement prediction model training process includes multiple steps that collectively ensure the model can accurately predict the optimal bias voltage of the MOS under different operating conditions. First, step S31 involves obtaining historical operating parameters and preprocessing them to obtain a feature vector set. This feature vector set is then divided into a training set and the standard bias voltage corresponding to the training set. In an electric vehicle power management system, this process first requires extracting various MOS operating parameters from historical operating data, including raw electrical signal data sets, switching frequency, duty cycle information, junction temperature data, and parameter statistics. This data requires preprocessing, such as noise removal, missing value filling, and normalization, to ensure data quality and consistency. The preprocessed data is then constructed into a feature vector set, which is then divided into a training set and a validation set. The training set includes all of the aforementioned feature vectors, while the standard bias voltage is based on the best known bias voltage value from the historical data. Next, step S32 inputs the training set into a preset initial bias voltage requirement prediction model for calculation to obtain the predicted bias voltage value. This process typically uses machine learning algorithms such as neural networks, support vector machines, or decision trees. The initial bias voltage requirement prediction model is an untrained model, requiring internal parameter adjustments based on data from the training set. For example, in an electric vehicle's power management system, the system inputs the feature vectors from the training set into the initial bias voltage requirement prediction model. The model then calculates the corresponding bias voltage prediction value based on these feature vectors. Then, in step S33, the bias voltage error is calculated based on the standard bias voltage and the predicted bias voltage value. This process evaluates the model's prediction accuracy. The system compares the bias voltage prediction value output by the model with the corresponding standard bias voltage in the training set and calculates the error between the two. This error can be measured using metrics such as mean squared error (MSE) and mean absolute error (MAE). For example, in an electric vehicle's power management system, the system calculates the error between the bias voltage prediction value and the standard bias voltage for each sample and aggregates these error values ​​to obtain an overall error metric. Next, in step S34, it determines whether the bias voltage error is within a preset bias voltage error range. If the bias voltage error is within the preset bias voltage error range, the initial bias voltage demand prediction model is determined as the bias voltage demand prediction model. The preset bias voltage error range is a threshold used to determine whether the model's prediction is accurate enough. If the error is within an acceptable range, it means that the model has been trained to a satisfactory level and can be directly used in practical applications. For example, in the power management system of an electric vehicle, if the error index of the model is lower than the preset threshold, the system will determine the current initial bias voltage demand prediction model as the final bias voltage demand prediction model, which is used to predict the optimal bias voltage of the MOS in real time.If the bias voltage error exceeds the preset bias voltage error range, the system proceeds to step S35, where the parameters in the initial bias voltage demand prediction model are adjusted. Steps S31 to S34 are repeated until the bias voltage output by the initial bias voltage demand prediction model is within the preset range, thereby obtaining a bias voltage demand prediction model. This process is an iterative training process for the model, where the prediction error is gradually reduced by continuously adjusting the model parameters until the preset error range is met. For example, in an electric vehicle power management system, if the model error index exceeds a preset threshold, the system adjusts the model parameters, such as the learning rate and weights, and then retrains and verifies the model until the prediction error falls within an acceptable range. This process may require multiple iterations until the model's prediction performance reaches optimal levels. Through this series of training and optimization processes, the system can establish an accurate bias voltage demand prediction model that can predict the optimal bias voltage of the MOS in real time under different operating conditions, thereby improving the efficiency and reliability of the power management system. For example, during acceleration in an electric vehicle, the system uses a trained bias voltage demand prediction model to adjust the MOS bias voltage in real time based on current operating parameters, ensuring efficient and safe operation under high load conditions. This not only improves overall system performance but also extends the MOS's service life and reduces maintenance costs.

[0091] In a specific embodiment, the step of performing digital signal processing on the bias voltage requirement value to convert it into a control signal includes:

[0092] quantizing the continuous bias voltage requirement value to obtain a discrete quantized value;

[0093] Performing digital signal processing on the discrete quantized value to obtain a processed digital signal;

[0094] performing signal encoding on the processed digital signal to obtain an encoding control signal;

[0095] Inputting the coded control signal into a preset digital-to-analog converter for signal conversion to obtain an analog control signal;

[0096] The analog control signal is used as a control signal.

[0097] Specifically, the digital signal processing of the bias voltage requirement value to convert it into a control signal includes quantizing the continuous bias voltage requirement value to obtain a discrete quantized value. In an electric vehicle power management system, this process first requires converting the continuous bias voltage requirement value obtained from the prediction model into a discrete digital form. For example, when the system predicts the required bias voltage for the MOS based on current operating parameters, this bias voltage requirement value is a continuous analog signal. To facilitate subsequent digital signal processing, an analog-to-digital converter (ADC) is required to convert this continuous analog signal into a discrete digital signal. The quantization process typically involves mapping the continuous voltage value to a set of discrete numerical values, for example, mapping the voltage range of 0 to 5V to integer values ​​from 0 to 255. This converts the continuous bias voltage requirement value into a discrete quantized value. Next, digital signal processing is performed on the discrete quantized value to obtain a processed digital signal. This process is typically performed by a microcontroller or digital signal processor (DSP). The purpose of digital signal processing is to further optimize and filter the signal to improve signal accuracy and stability. For example, the system can use digital filters (such as low-pass or high-pass filters) to remove noise and interference from the quantized values. Other digital signal processing operations, such as signal smoothing and de-jittering, can also be performed to ensure that the final control signal accurately reflects the bias voltage requirements of the MOS. For example, during acceleration in an electric vehicle, the system digitally filters the received discrete quantized values ​​to eliminate fluctuations caused by sensor noise or external interference, thereby obtaining a more stable processed digital signal. The processed digital signal is then encoded to produce an encoded control signal. Signal encoding converts the processed digital signal into a format suitable for transmission and control. For example, the system can use pulse-width modulation (PWM) encoding to convert the processed digital signal into a series of signals with varying pulse widths. These pulse signals can be directly used to control the gate drive circuit of the MOS. The duty cycle of the PWM signal reflects the required bias voltage, and by adjusting the duty cycle, the output voltage of the gate drive circuit can be precisely controlled. For example, in an electric vehicle's power management system, the system encodes the processed digital signal into a PWM signal that accurately reflects the required bias voltage of the MOS. Finally, the coded control signal is input into a pre-set digital-to-analog converter for signal conversion, yielding an analog control signal. A digital-to-analog converter (DAC) converts digital signals into analog signals for use in the drive circuit. For example, the coded PWM signal is input into the DAC, which converts it into a continuous analog voltage signal. This analog voltage signal can be directly applied to the MOS gate, enabling precise control of the MOS bias voltage.For example, during the acceleration of an electric vehicle, the system inputs the encoded PWM signal into the DAC, which converts the digital signal into a continuous analog voltage signal. This analog voltage signal is then applied to the gate of the MOS, enabling dynamic adjustment of the MOS bias voltage. Through this series of digital signal processing and conversion processes, the system can accurately convert the continuous bias voltage requirement value obtained from the prediction model into a control signal suitable for the MOS gate drive. This not only ensures that the MOS is always in optimal working condition under different operating conditions, but also improves the overall efficiency and reliability of the power management system. For example, during the acceleration of an electric vehicle, through this series of signal processing and conversion, the system can adjust the MOS bias voltage in real time, ensuring that it maintains an efficient and safe operating state under high load conditions, thereby improving the performance and stability of the entire power management system.

[0098] In a specific embodiment, applying the control signal to the gate of the target MOS transistor to dynamically adjust the working state of the target MOS transistor includes:

[0099] Transmitting the control signal to the gate drive circuit to obtain a transmission control signal;

[0100] amplifying and shaping the transmission control signal through a gate drive circuit to obtain an amplified control signal;

[0101] Performing overvoltage and overcurrent protection on the amplified control signal through an amplifier in a gate drive circuit to obtain a protection control signal;

[0102] electrically isolating the protection control signal to obtain an isolation control signal;

[0103] performing signal buffering processing on the isolation control signal to obtain a buffered control signal;

[0104] The buffer control signal is applied to the gate of the target MOS transistor to dynamically adjust the working state of the target MOS transistor.

[0105] Specifically, applying the control signal to the gate of the target MOS transistor to dynamically adjust the operating state of the target MOS transistor includes transmitting the control signal to the gate drive circuit to obtain a transmission control signal. In an electric vehicle power management system, this process first requires transmitting the analog control signal output from the digital-to-analog converter to the gate drive circuit. For example, after the system obtains the analog control signal through digital signal processing and digital-to-analog conversion, this signal is transmitted to the gate drive circuit. The purpose of transmitting the control signal is to ensure that the control signal reaches the gate drive circuit intact, providing a reliable foundation for subsequent signal processing. Next, the gate drive circuit amplifies and shapes the transmission control signal to obtain an amplified control signal. The gate drive circuit typically includes an amplifier and a shaping circuit to enhance the amplitude of the control signal and improve the signal waveform quality. For example, during acceleration of an electric vehicle, the gate drive circuit amplifies the received transmission control signal to ensure that the signal has sufficient driving power to control the MOS gate. Simultaneously, the shaping circuit ensures that the signal waveform meets the operating requirements of the MOS, for example, by making the edges of the PWM signal steeper to reduce switching losses. The amplified control signal is then protected against overvoltage and overcurrent by an amplifier in the gate drive circuit, generating a protection control signal. Overvoltage and overcurrent protection are important measures to ensure the safe operation of the MOS. The amplifier in the gate drive circuit is typically equipped with overvoltage and overcurrent protection, automatically cutting off or limiting the signal if the control signal exceeds a safe range. For example, if the system detects excessive gate voltage or excessive current, the amplifier immediately takes protective measures to prevent damage to the MOS due to overvoltage or overcurrent. The protection control signal ensures that the MOS is protected from excessive voltage or current shocks under all circumstances, thereby improving system reliability and safety. Next, the protection control signal is electrically isolated to generate an isolated control signal. Electrical isolation prevents electrical interference between the high-voltage and low-voltage sides, ensuring safe system operation. Gate drive circuits typically use isolation components such as optocouplers or transformers to achieve electrical isolation. For example, in the power management system of an electric vehicle, the gate drive circuit isolates the protection control signal using an optocoupler to ensure that the high-voltage side signal does not interfere with the low-voltage side control circuit. Isolating the control signal not only improves system safety but also enhances its anti-interference capabilities. The isolation control signal is then buffered to produce a buffered control signal. The purpose of signal buffering is to further enhance the signal's drive capability and stability. The buffer in the gate drive circuit can provide additional current drive capability, ensuring that the signal can reliably drive the MOS gate. For example, the buffer further amplifies and stabilizes the received isolation control signal to ensure that the signal's amplitude and waveform meet the MOS operating requirements.The buffered control signal ensures that the MOS gate voltage remains stable under different operating conditions, thereby improving MOS performance. Finally, the buffered control signal is applied to the gate of the target MOS transistor to dynamically adjust its operating state. This process is the final step in the entire control chain. By applying the buffered control signal to the MOS gate, precise control of the MOS bias voltage can be achieved. For example, during acceleration in an electric vehicle, the system applies the buffered control signal to the MOS gate to dynamically adjust the MOS bias voltage, ensuring efficient and safe operation under high load conditions. Through this series of signal processing and control, the system can accurately adjust the MOS operating state in real time, improving the overall efficiency and reliability of the power management system, extending the MOS service life, and reducing maintenance costs. Through this series of steps, the system can accurately apply the bias voltage requirement value obtained from the prediction model to the MOS gate through digital signal processing, transmission, amplification, protection, isolation, and buffering, achieving dynamic adjustment of the MOS operating state. This not only ensures that the MOS is always in optimal operating condition under different operating conditions, but also improves the performance and stability of the entire power management system. For example, during the acceleration of an electric vehicle, the system can adjust the bias voltage of the MOS in real time through this series of control steps to ensure that it remains efficient and safe under high load conditions, thereby improving the performance and reliability of the entire power management system.

[0106] In a specific embodiment, performing overvoltage and overcurrent protection on the amplified control signal through an amplifier in the gate drive circuit to obtain a protection control signal includes:

[0107] performing spectrum decomposition on the amplified control signal to obtain a spectrum component set;

[0108] constructing a signal energy graph based on the set of spectral components to obtain signal energy information;

[0109] Determine whether the signal energy information has risk signal characteristics, and if so, perform feature extraction on the signal energy information to obtain a risk characteristic signal;

[0110] Analyzing the type of the risk characteristic signal through a preset analysis algorithm, and formulating a protection control signal strategy based on the type of the risk characteristic signal;

[0111] Through the protection control signal strategy, the amplifier in the gate drive circuit is used to perform overvoltage and overcurrent protection on the amplified control signal to obtain a protection control signal.

[0112] Specifically, performing overvoltage and overcurrent protection on the amplified control signal through the amplifier in the gate drive circuit to obtain a protection control signal includes performing spectral decomposition on the amplified control signal to obtain a set of spectral components. In an electric vehicle power management system, this process first requires spectral analysis of the amplified control signal output from the gate drive circuit amplifier. Spectral decomposition is a signal processing technique that converts time-domain signals into frequency-domain signals, thereby revealing the signal's frequency composition. For example, the system uses a fast Fourier transform (FFT) algorithm to perform spectral decomposition on the amplified control signal to obtain a set of spectral components containing different frequency components. These spectral component sets help the system identify high-frequency noise, harmonics, and other potential interference components in the signal. Next, a signal energy graph is constructed based on the spectral component set to obtain signal energy information. A signal energy graph is a visualization tool that displays the energy distribution of a signal at different frequencies. By constructing a signal energy graph, the system can more intuitively understand the energy distribution of the amplified control signal and identify possible abnormal signals. For example, during acceleration of an electric vehicle, the system constructs a signal energy graph based on the spectral component set to analyze the energy distribution of the signal at different frequencies. Abnormally high energy at certain frequencies may indicate the presence of noise or interference in the signal. The system then determines whether the signal energy information exhibits risk signal characteristics. If so, it performs feature extraction on the signal energy information to generate a risk signature signal. This process involves analyzing the abnormal energy distribution in the signal energy graph to identify possible risk signal characteristics. For example, the system sets certain thresholds. If the energy at a certain frequency exceeds the preset threshold, the system deems the signal at that frequency to be potentially risky. Once risk signal characteristics are detected, the system further performs feature extraction to extract specific characteristics such as frequency, amplitude, and duration to form a risk signature signal. For example, if the system detects abnormally high energy in a certain high-frequency band, it may extract detailed characteristics of this frequency band for subsequent analysis. Next, the system uses a pre-set analysis algorithm to analyze the type of the risk signature signal and formulates a protection control signal strategy based on the risk signature signal type. The pre-set analysis algorithm can use the extracted risk signature signal to identify the specific fault type, such as overvoltage, overcurrent, or high-frequency noise. For example, the system uses a classification algorithm (such as a support vector machine or decision tree) to classify the risk signature signal and determine its specific type. Once the risk signature signal type is determined, the system develops a corresponding protection control signal strategy based on the pre-set protection strategy. For example, if an overvoltage signal is detected, the system develops a strategy to reduce the gate drive voltage; if an overcurrent signal is detected, the system develops a strategy to limit the gate drive current. Finally, using the protection control signal strategy, the amplifier in the gate drive circuit performs overvoltage and overcurrent protection on the amplified control signal, generating a protection control signal.This process applies the developed protection control signal strategy to the actual gate drive circuit. The amplifier then appropriately adjusts the amplified control signal to achieve overvoltage and overcurrent protection. For example, if the system detects an overvoltage signal, the amplifier reduces the gate drive voltage to prevent damage to the MOS due to excessive gate voltage. If an overcurrent signal is detected, the amplifier limits the gate drive current to prevent overheating. Through these protection measures, the system ensures that the MOS operates safely under various operating conditions. Through this series of steps, the system comprehensively analyzes and protects the amplified control signal, ensuring that the MOS operates optimally and safely under various operating conditions. For example, during acceleration in an electric vehicle, the system uses spectral decomposition, signal energy graph construction, risk signature signal extraction, analysis algorithms, and protection control signal strategies to promptly detect and address potential overvoltage and overcurrent risks, ensuring that the MOS maintains efficient and safe operation under high load conditions, thereby improving the performance and reliability of the entire power management system.

[0113] The above describes the adaptive bias voltage optimization method based on MOS tube in the embodiment of the present invention. The following describes the adaptive bias voltage optimization device based on MOS tube in the embodiment of the present invention. Figure 2 In one embodiment of the present invention, an adaptive bias voltage optimization device based on a MOS tube includes:

[0114] The monitoring module 21 is used to monitor the target MOS transistor in the working state of the gate drive circuit in real time to obtain the working parameters of the target MOS transistor;

[0115] A prediction module 22 is configured to predict the bias voltage requirement of the target MOS transistor based on the operating parameters based on a preset bias voltage requirement prediction model to obtain a bias voltage requirement value;

[0116] a conversion module 23, configured to perform digital signal processing on the bias voltage requirement value to convert it into a control signal;

[0117] The applying module 24 is configured to apply the control signal to the gate of the target MOS transistor to dynamically adjust the working state of the target MOS transistor.

[0118] In this embodiment, for the specific implementation of each unit in the above device embodiment, please refer to the above method embodiment, which will not be repeated here.

[0119] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided, wherein the internal structure of the computer device can be as follows: Figure 3As shown. The computer device includes a processor, memory, display screen, input device, network interface and database connected via a system bus. The processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above method is implemented.

[0120] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0121] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the above-described method when executed by a processor. It is understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0122] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware using a computer program. 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 above-described method embodiments. Any reference to memory, storage, database, or other media provided herein and used 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 various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM.

[0123] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, apparatus, article, or method comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, apparatus, article, or method. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, apparatus, article, or method comprising the element.

[0124] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for optimizing the adaptive bias voltage of a MOS tube, characterized in that: Applied to the gate drive circuit, including the following steps: Perform real-time monitoring on the target MOS transistor when the gate drive circuit is in operation, and obtain the operating parameters of the target MOS transistor; Based on a preset bias voltage requirement prediction model, and based on the operating parameters, a bias voltage requirement prediction is performed on the target MOS transistor to obtain a bias voltage requirement value; Performing digital signal processing on the bias voltage requirement value to convert it into a control signal; Applying the control signal to the gate of the target MOS transistor to dynamically adjust the working state of the target MOS transistor; The real-time monitoring of the target MOS transistor in the working state of the gate drive circuit to obtain the working parameters of the target MOS transistor includes: Synchronously sampling the gate voltage, drain voltage, and drain current of the target MOS transistor in a gate drive circuit operating state to obtain an original electrical signal data set, wherein the circuit operating state includes the turn-on, amplification, and cut-off of the target MOS transistor; Performing time series processing on the original electrical signal data set to obtain switching frequency and duty cycle information of the target MOS tube; Scanning the surface temperature of the target MOS transistor to calculate the junction temperature data of the target MOS transistor; Using a sliding window method, based on the switching frequency, duty cycle information, and junction temperature data, the operating parameter statistics of the target MOS transistor in different time periods are calculated; wherein the operating parameter statistics include an average gate-source voltage, an average drain-source voltage, and an average drain current; A standard bias voltage is set based on the original electrical signal data set, the switching frequency, the duty cycle information, the junction temperature data, and the parameter statistics, and the original electrical signal data set, the switching frequency, the duty cycle information, the junction temperature data, the parameter statistics, and the standard bias voltage are used as operating parameters of the target MOS tube.

2. The method for optimizing the adaptive bias voltage based on a MOS tube according to claim 1, wherein: Scanning the surface temperature of the target MOS transistor to calculate the junction temperature data of the target MOS transistor includes: Performing non-contact temperature measurement on the surface of the target MOS tube using an infrared thermal imager to obtain a surface temperature distribution diagram of the target MOS tube; Performing a temperature frequency domain analysis on the surface temperature distribution map using a Fourier transform algorithm to extract the temperature distribution frequency components; Performing an inverse heat distribution calculation on the target MOS tube based on the temperature distribution frequency component using an inverse heat conduction model to obtain an internal temperature distribution diagram; The junction temperature data of the target MOS tube is calculated based on the internal temperature distribution diagram using a thermal resistance network model.

3. The method for optimizing the adaptive bias voltage based on a MOS transistor according to claim 1, wherein: The bias voltage requirement prediction model training process includes: Step S31, obtaining historical operating parameters, preprocessing the historical operating parameters to obtain a feature vector set, and dividing the feature vector set into a training set and a standard bias voltage corresponding to the training set; wherein the training set includes an original electrical signal data set, switching frequency, duty cycle information, junction temperature data, and parameter statistics; Step S32: inputting the training set into a preset initial bias voltage demand prediction model for calculation to obtain a bias voltage prediction value; Step S33, comparing and calculating the standard bias voltage with the bias voltage prediction value to calculate a bias voltage error; Step S34, determining whether the bias voltage error is within a preset bias voltage error range; if the bias voltage error is within the preset bias voltage error range, determining the initial bias voltage demand prediction model as the bias voltage demand prediction model; Step S35: If the bias voltage error exceeds the preset bias voltage error range, the parameters in the initial bias voltage demand prediction model are adjusted, and steps S31 to S34 are repeated until the bias voltage output by the initial bias voltage demand prediction model is within the preset range to obtain a bias voltage demand prediction model.

4. The method for optimizing the adaptive bias voltage based on a MOS transistor according to claim 1, wherein: The performing digital signal processing on the bias voltage requirement value to convert it into a control signal includes: quantizing the continuous bias voltage requirement value to obtain a discrete quantized value; Performing digital signal processing on the discrete quantized value to obtain a processed digital signal; performing signal encoding on the processed digital signal to obtain an encoding control signal; Inputting the coded control signal into a preset digital-to-analog converter for signal conversion to obtain an analog control signal; The analog control signal is used as a control signal.

5. The method for optimizing the adaptive bias voltage based on MOS tube according to claim 1, characterized in that: Applying the control signal to the gate of the target MOS transistor to dynamically adjust the working state of the target MOS transistor includes: Transmitting the control signal to the gate drive circuit to obtain a transmission control signal; amplifying and shaping the transmission control signal through a gate drive circuit to obtain an amplified control signal; Performing overvoltage and overcurrent protection on the amplified control signal through an amplifier in a gate drive circuit to obtain a protection control signal; electrically isolating the protection control signal to obtain an isolation control signal; performing signal buffering processing on the isolation control signal to obtain a buffered control signal; The buffer control signal is applied to the gate of the target MOS transistor to dynamically adjust the working state of the target MOS transistor.

6. The method for optimizing the adaptive bias voltage based on MOS transistor according to claim 5, characterized in that: The step of performing overvoltage and overcurrent protection on the amplified control signal through an amplifier in the gate drive circuit to obtain a protection control signal includes: performing spectrum decomposition on the amplified control signal to obtain a spectrum component set; constructing a signal energy graph based on the set of spectral components to obtain signal energy information; Determine whether the signal energy information has risk signal characteristics, and if so, perform feature extraction on the signal energy information to obtain a risk characteristic signal; Analyzing the type of the risk characteristic signal through a preset analysis algorithm, and formulating a protection control signal strategy based on the type of the risk characteristic signal; Through the protection control signal strategy, the amplifier in the gate drive circuit is used to perform overvoltage and overcurrent protection on the amplified control signal to obtain a protection control signal.

7. An adaptive bias voltage optimization device based on MOS tube, characterized in that: Applied to gate drive circuits, including: A monitoring module is used to monitor the target MOS transistor in real time when the gate drive circuit is in operation, and obtain the operating parameters of the target MOS transistor; A prediction module, configured to predict the bias voltage requirement of the target MOS transistor based on the operating parameters based on a preset bias voltage requirement prediction model to obtain a bias voltage requirement value; a conversion module, configured to perform digital signal processing on the bias voltage requirement value to convert it into a control signal; an applying module, configured to apply the control signal to the gate of the target MOS transistor to dynamically adjust the working state of the target MOS transistor; The real-time monitoring of the target MOS transistor in the working state of the gate drive circuit to obtain the working parameters of the target MOS transistor includes: Synchronously sampling the gate voltage, drain voltage, and drain current of the target MOS transistor in a gate drive circuit operating state to obtain an original electrical signal data set, wherein the circuit operating state includes the turn-on, amplification, and cut-off of the target MOS transistor; Performing time series processing on the original electrical signal data set to obtain switching frequency and duty cycle information of the target MOS tube; Scanning the surface temperature of the target MOS transistor to calculate the junction temperature data of the target MOS transistor; Using a sliding window method, based on the switching frequency, duty cycle information, and junction temperature data, the operating parameter statistics of the target MOS transistor in different time periods are calculated; wherein the operating parameter statistics include an average gate-source voltage, an average drain-source voltage, and an average drain current; A standard bias voltage is set based on the original electrical signal data set, the switching frequency, the duty cycle information, the junction temperature data, and the parameter statistics, and the original electrical signal data set, the switching frequency, the duty cycle information, the junction temperature data, the parameter statistics, and the standard bias voltage are used as operating parameters of the target MOS tube.

8. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

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

Images