New power supply module surge suppression method

Abstract

The invention discloses a new power module surge suppression method, which comprises the following steps of: after judging that a current input voltage value reaches a peak value, determining whether a rectifying device is connected to a rectifying circuit or not by utilizing a dynamic change characteristic and trend between input voltage time sequence data and output voltage time sequence data in a preset time period, namely, executing a step 4; or returning to the step 2. Thus, the defects of a traditional fixed set value comparison and monitoring control mode can be avoided, effective surge suppression can be achieved under wider conditions, and then the stability and efficiency of the power module in the starting process can be improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent identification, and more specifically, to a new power module surge suppression method. Background Art

[0002] In modern power electronic systems, the power module is the core component of energy conversion, and its performance directly affects the stability and efficiency of the entire system. Especially in the startup phase, due to grid voltage fluctuations or changes in load characteristics, the power module is prone to generate large surge currents, which are potential hazards to the power module itself and the connected grid. Surge currents can not only damage the internal components of the power module, but may also cause the grid voltage to drop, affecting the normal operation of other equipment. Therefore, effectively suppressing the startup surge current has become one of the important research directions for improving the reliability of power modules and grid stability.

[0003] Chinese patent CN112953190A proposes a method for suppressing startup surges of a PFC power module, which can ensure that the auxiliary power supply can provide a stable operating power supply for the control unit by using a pre-charging circuit to charge the first capacitor at startup. After the control unit is running, it can detect the input voltage and output voltage in real time, and output a control signal to control the rectifier device according to these parameter characteristics to connect or disconnect the rectifier device, so that the PFC power module can avoid or suppress the startup surge when working. Therefore, it can achieve efficient surge suppression without using a surge switch while maintaining a small waveform distortion.

[0004] However, in the above-mentioned PFC power module startup surge suppression method, whether to connect the rectifier device to the rectifier circuit is determined by comparing whether the difference between the current input voltage and the output voltage exceeds a certain fixed first set value. If the set value is set too high, it may cause a delay in the connection time of the rectifier device, thereby prolonging the entire startup process and affecting the startup efficiency. On the contrary, if the set value is too low, the rectifier device may be connected before the input voltage reaches the peak value, increasing the risk of generating a large surge current during the startup process.

[0005] Therefore, an optimized new power module surge suppression scheme is desired. Summary of the invention

[0006] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a new power module surge suppression method, which, after determining that the current input voltage value has reached a peak value, uses the dynamic change characteristics and trends between the input voltage timing data and the output voltage timing data in a predetermined time period to determine whether to connect the rectifier device to the rectifier circuit, that is, to determine whether to execute step 4 or return to step 2. In this way, the defects of the traditional fixed set value comparison and monitoring control method can be avoided, and effective surge suppression can be achieved under a wider range of conditions, thereby helping to improve the stability and efficiency of the power module startup process.

[0007] According to one aspect of the present application, a new power module surge suppression method is provided, which includes:

[0008] Step 1: Make the auxiliary power supply work;

[0009] Step 2: Continuously collect output voltage value and input voltage value;

[0010] Step 3: after determining that the current input voltage value has reached the peak value, determine whether to execute step 4 or return to step 2 based on the time queue of the input voltage and the time queue of the output voltage in the predetermined time period;

[0011] Step 4: output a control signal to control the rectifier device of the power module to connect to the rectifier circuit to charge the first capacitor;

[0012] Step 5: If the current input voltage value is less than the difference between the current output voltage value and the preset threshold value, disconnect the rectifier device and return to step 3; if not, return to step 4;

[0013] Step 6: Determine whether the difference between the current input voltage value and the output voltage value is less than the predetermined threshold value. If so, keep the rectifier device in the on state so that the power module enters the normal working mode. If not, return to step 3 and continue input surge suppression.

[0014] Compared with the prior art, the new power module surge suppression method provided by the present application determines whether to connect the rectifier device to the rectifier circuit by using the dynamic change characteristics and trends between the input voltage timing data and the output voltage timing data in a predetermined time period after judging that the current input voltage value has reached the peak value, that is, to determine whether to execute step 4 or return to step 2. In this way, the defects of the traditional fixed set value comparison and monitoring control method can be avoided, and effective surge suppression can be achieved under a wider range of conditions, thereby helping to improve the stability and efficiency of the power module startup process. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0016] Figure 1 A flowchart of a new power module surge suppression method according to an embodiment of the present application;

[0017] Figure 2 A data flow diagram of a new power module surge suppression method according to an embodiment of the present application;

[0018] Figure 3 This is a flowchart of sub-step S3 of the new power module surge suppression method according to an embodiment of the present application. DETAILED DESCRIPTION

[0019] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0020] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0021] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0022] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. Meanwhile, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0023] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0024] In the technical solution of the present application, a new power module surge suppression method is proposed. Figure 1 Flow chart of a new power module surge suppression method according to an embodiment of the present application. Figure 2 Schematic diagram of data flow of a new power module surge suppression method according to an embodiment of the present application. Figure 1 and Figure 2 As shown, according to the new power module surge suppression method of the embodiment of the present application, the steps include: S1, making the auxiliary power supply work; S2, continuously collecting the output voltage value and the input voltage value; S3, after judging that the current input voltage value reaches the peak value, based on the time queue of the input voltage and the time queue of the output voltage in the predetermined time period, determine whether to execute step 4 or return to step 2; S4, output a control signal to control the rectifier device of the power module to connect to the rectifier circuit to charge the first capacitor; S5, if the current input voltage value is less than the difference between the current output voltage value and the preset threshold value, disconnect the rectifier device and return to step 3, if not, return to step 4; S6, judge whether the difference between the current input voltage value and the output voltage value is less than the preset threshold value, if so, keep the rectifier device in the open state so that the power module enters the normal working mode, if not, return to step 3 and continue to perform input surge suppression.

[0025] In particular, the S1 enables the auxiliary power supply to work. When the PFC power supply module is powered on, the auxiliary power supply first starts to work and provides power to the control unit. At this time, the control unit starts to run and selects or obtains a pre-set first setting value. This first setting value is a standard for judging whether the difference between the input voltage and the output voltage is safe.

[0026] It should be understood that in the startup process of the power module, making the auxiliary power supply work is a crucial first step. The main function of the auxiliary power supply is to provide the control system with necessary power supply when the main power supply has not yet established a stable output, ensuring that the control system can monitor and manage the startup process in time.

[0027] Specifically, the auxiliary power supply usually takes the form of a switching power supply, because the switching power supply has the advantages of low power consumption, high efficiency, small size, light weight, and wide voltage regulation range. The core of the switching power supply is the converter, and common topologies include single-ended flyback and forward. For low-power applications, the single-ended flyback converter is widely used because of its simple structure and convenient multi-channel output. The basic structure of the auxiliary power supply includes input rectification and filtering, converter, transformer isolation, output rectification and filtering, feedback control and protection circuit. These parts work together to ensure that the auxiliary power supply can provide a stable and reliable power supply.

[0028] The AC input voltage is first converted into a DC voltage through a rectifier bridge. The rectifier bridge is usually composed of four diodes, which converts the AC power into pulsating DC power. This pulsating DC power also needs to be further filtered to reduce voltage fluctuations. The selection of filter capacitors needs to consider their capacity and withstand voltage value to ensure that they can effectively filter out ripples and provide stable DC voltage.

[0029] The rectified DC voltage is initially filtered by the filter capacitor to remove high-frequency ripples. The selection of the filter capacitor needs to consider its capacity and withstand voltage to ensure that it can effectively filter out ripples and provide a stable DC voltage. For example, for a 220VAC input, the rectified DC voltage is about 300V, and a 470μF / 400V electrolytic capacitor can be selected for filtering.

[0030] The filtered DC voltage is fed into the converter, and the DC voltage is converted into a high-frequency AC voltage through the switching action of the switch tube (such as MOSFET). The working principle of the converter is to change the frequency and duty cycle of the input voltage by controlling the conduction and cutoff of the switch tube, thereby achieving voltage conversion. The selection of the switch tube needs to consider factors such as its withstand voltage, on-resistance, switching speed and maximum current.

[0031] The high-frequency AC voltage is transformed and electrically isolated through a transformer. The primary and secondary sides of the transformer transfer energy through magnetic coupling to achieve voltage step-up or step-down. The design of the transformer needs to consider the core material, number of winding turns and insulation performance to ensure efficient and stable operation. For example, a transformer with a ferrite core can be selected with 100 primary turns and 20 and 40 secondary turns, corresponding to output voltages of 15V and 24V, respectively.

[0032] The low-voltage, high-frequency square wave on the secondary side of the transformer is then rectified into low-voltage DC power by a rectifier diode, and further filtered by a filter capacitor to output a stable DC voltage. The selection of rectifier diodes needs to consider their withstand voltage, current capability, and reverse recovery time to ensure efficient and reliable operation. For example, two fast recovery diodes with a withstand voltage of 100V and a maximum current of 1A can be selected for rectification of 15V and 24V outputs respectively. The selection of filter capacitors is equally important. Two 1000μF / 25V electrolytic capacitors can be selected for filtering of 15V and 24V outputs respectively to output a stable DC voltage.

[0033] Auxiliary power supply circuits usually include a feedback loop to monitor changes in the output voltage. Common feedback components include optocouplers and TL431. The feedback loop compares the monitored output voltage signal with the reference voltage, generates an error signal through the error amplifier, and then adjusts the duty cycle of the PWM controller to control the on-time of the switch tube, thereby achieving output voltage stability. For example, a PC817 optocoupler and a TL431 precision adjustable regulator can be selected to generate a reference voltage. The PWM controller can select a UC3842 PWM controller to generate a control signal.

[0034] In particular, the S2 continuously collects the output voltage value and the input voltage value. The control unit continuously collects the input voltage and the output voltage value. The input voltage is an AC voltage, which is converted into a DC voltage value by an isolated voltage sensor; the output voltage is a DC voltage, which is directly collected by a voltage divider circuit.

[0035] It should be understood that during the startup and operation of the power module, continuously collecting the output voltage and input voltage values ​​is a key step to ensure system stability and efficiency. By monitoring these voltage values ​​in real time, the control system can make timely adjustments to avoid inrush current and other abnormal situations.

[0036] In one example, in order to continuously collect output voltage values ​​and input voltage values, it is necessary to first configure appropriate hardware components. These components include voltage sensors, analog-to-digital converters (ADCs), microcontrollers (MCUs), and power supplies. Voltage sensors are used to measure input voltage and output voltage. Common sensors include resistor dividers, Hall effect sensors, and isolation amplifiers. The analog-to-digital converter (ADC) converts analog voltage signals into digital signals for processing by microcontrollers or other digital processing units. The microcontroller (MCU) is responsible for controlling the sampling process of the ADC and processing and analyzing the collected data. The power supply provides a stable power supply for the above components to ensure the normal operation of the system.

[0037] The input voltage is usually an AC voltage and needs to be collected through a series of steps. First, the AC voltage is converted into a pulsating DC voltage using a rectifier bridge. The rectifier bridge usually consists of four diodes that convert AC power into unidirectional pulsating DC power. For example, for a 220VAC input, the rectified DC voltage is about 300V. Next, the pulsating DC voltage is preliminarily filtered by a filter capacitor to reduce high-frequency ripple. The selection of the filter capacitor needs to consider its capacity and withstand voltage value to ensure that it can effectively filter out the ripple and provide a stable DC voltage. For example, a 470μF / 400V electrolytic capacitor can be selected for filtering.

[0038] Then, a resistor divider is used to reduce the high DC voltage to a range suitable for the ADC input. The design of the voltage divider needs to consider the voltage divider ratio and power consumption to ensure that the voltage signal after the voltage divider is stable and reliable. For example, a resistor divider with a voltage divider ratio of 1:10 is used to reduce the 300V DC voltage to 30V. To ensure the electrical safety of the system, an isolation amplifier or optocoupler can be used to isolate the input voltage signal from the control system. The isolation amplifier can provide electrical isolation to prevent interference on the high voltage side from affecting the control system. For example, an isolation amplifier can be selected to isolate the 30V voltage signal from the control system.

[0039] Finally, the divided voltage signal is sent to the ADC for sampling. The selection of the ADC needs to consider its resolution, sampling rate and accuracy to ensure that the voltage signal can be accurately collected. For example, an ADC with a 12-bit resolution and a sampling rate of 1kHz can be selected for sampling.

[0040] The output voltage is usually a DC voltage and can be directly collected. First, use a resistor divider to reduce the output voltage to a range suitable for ADC input. The design of the voltage divider needs to consider the voltage divider ratio and power consumption to ensure that the voltage signal after voltage division is stable and reliable. For example, a resistor divider with a voltage divider ratio of 1:2 is used to reduce the output voltage of 24V to 12V. Next, the voltage signal after voltage division is filtered by a filter capacitor to reduce noise interference. The selection of the filter capacitor needs to consider its capacity and withstand voltage value to ensure that it can effectively filter out noise and provide a stable voltage signal. For example, a 100μF / 25V electrolytic capacitor can be selected for filtering.

[0041] To ensure the electrical safety of the system, an isolation amplifier or optocoupler can be used to isolate the output voltage signal from the control system. For example, an isolation amplifier can be selected to isolate the 12V voltage signal from the control system. Finally, the voltage signal after voltage division is sent to the ADC for sampling. The selection of ADC needs to consider its resolution, sampling rate and accuracy to ensure that the voltage signal can be accurately collected. For example, an ADC with 12-bit resolution and a sampling rate of 1kHz can be selected for sampling. The selection of sampling frequency needs to consider multiple factors. First, according to the Nyquist theorem, the sampling frequency should be at least twice the highest frequency of the signal to avoid aliasing. For example, for an AC input voltage of 50Hz, the sampling frequency can be selected as 1kHz to ensure that the changes in the voltage waveform can be accurately captured. Secondly, the sampling frequency should be high enough to ensure that the control system can respond to voltage changes in a timely manner. For example, for systems that require fast response, the sampling frequency can be increased to 5kHz or higher. Finally, the sampling frequency cannot be too high so as not to exceed the processing capacity of the processor. For example, for a microcontroller with limited processing power, the sampling frequency can be appropriately reduced to ensure the real-time nature of data processing.

[0042] In order to reduce noise interference, the collected data can be filtered. Common filtering methods include low-pass filtering, average filtering and median filtering. Low-pass filters can remove high-frequency noise and retain low-frequency signals. The design of low-pass filters needs to consider the cutoff frequency and order to ensure the filtering effect. For example, a second-order low-pass filter with a cutoff frequency of 100Hz can be selected. The average filter reduces the impact of random noise by averaging the data of multiple sampling points. The design of the average filter needs to consider the window size to balance the filtering effect and response speed. For example, an average filter with a window size of 10 can be selected. The median filter sorts the data of multiple sampling points, takes the middle value, and removes the impact of outliers. The design of the median filter needs to consider the window size to balance the filtering effect and response speed. For example, a median filter with a window size of 5 can be selected.

[0043] In order to facilitate subsequent processing and analysis, the collected data can be stored in the memory or transmitted to the host computer through the communication interface. Common data storage and transmission methods include internal storage, external storage and communication interface. Internal storage stores data in the RAM or Flash of the microcontroller, which is suitable for short-term storage and local processing. For example, the data of the last 100 sampling points can be stored in RAM for real-time analysis. External storage stores data in external memory such as SD card or EEPROM, which is suitable for long-term storage and offline analysis. For example, daily voltage data can be stored in an SD card for subsequent analysis. The communication interface transmits data to the host computer through communication interfaces such as UART, SPI, I2C or CAN, which is suitable for remote monitoring and real-time analysis. For example, voltage data can be transmitted to the host computer through the UART interface for real-time display and recording.

[0044] In particular, in S3, after judging that the current input voltage value has reached the peak value, based on the time queue of the input voltage and the time queue of the output voltage in the predetermined time period, it is determined whether to execute step 4 or return to step 2. In step 3, by continuously monitoring the change of the input voltage, when the input voltage reaches the peak value within a cycle, the next operation is controlled. This step is to ensure that the comparison is made when the input voltage is the highest, because it is most likely to generate a large surge current at this time. The original scheme is to compare whether the difference between the current input voltage and the output voltage is greater than the first set value. If the difference is greater than the first set value, it means that the input voltage is higher than the output voltage, and there is a risk of generating a large surge current, so the next step is executed; if the difference is less than the first set value, it means that the input voltage is relatively low, and the input voltage continues to be monitored and collected. However, an improper setting value will affect the stability and efficiency of the startup process, and may even cause startup failure. Therefore, in the technical solution of the present application, it is expected that after judging that the current input voltage value has reached the peak value, the dynamic change characteristics and trends between the input voltage timing data and the output voltage timing data in the predetermined time period are used to determine whether to connect the rectifier device to the rectifier circuit, that is, to determine whether to execute step 4 or return to step 2. Specifically, after the current input voltage value reaches the peak value, the time queue data of the input voltage and the output voltage are used, and the data processing and analysis algorithm based on artificial intelligence and deep learning is introduced in the back end to analyze the time queue data of the input voltage and the output voltage, so as to learn and capture the time series fine-grained comparison interaction feature representation between the multi-scale time series semantics of the input voltage and the multi-scale time series semantics of the output voltage, so as to achieve more accurate capture and analysis of the time series dynamic characteristics between the input voltage and the output voltage, and then make a state judgment based on the feature representation to decide whether to execute step 4 or return to step 2. In a specific example of the present application, Figure 3As shown, the S3 includes: S31, respectively performing sequence encoding on the time queue of the input voltage and the time queue of the output voltage to obtain multi-scale timing implicit coding features of the input voltage and multi-scale timing implicit coding features of the output voltage; S32, performing feature interaction comparison processing on the multi-scale timing implicit coding features of the input voltage and the multi-scale timing implicit coding features of the output voltage using external knowledge modulation to obtain input voltage-output voltage timing comparison fine-grained interaction features; S33, performing state judgment based on the input voltage-output voltage timing comparison fine-grained interaction features to determine whether to execute step 4 or return to step 2.

[0045] Specifically, the S31, respectively, performs sequence encoding on the time queue of the input voltage and the time queue of the output voltage to obtain the multi-scale time series implicit coding features of the input voltage and the multi-scale time series implicit coding features of the output voltage. Considering that the input voltage and the output voltage have the dynamic change characteristics and trends of the time series in the time dimension, the dynamic characteristics of this time series not only exist in the time series dependency in a short period of time, but also in the long-term change trend. Based on this, in order to be able to more fully capture the time series dynamic characteristics of the input voltage and the output voltage, so as to help more comprehensively understand the time series dynamic characteristics of the input voltage and the output voltage, and provide a more accurate basis for predicting future voltage changes and state discrimination tasks, in the technical solution of the present application, the time queue of the input voltage and the time queue of the output voltage in the predetermined time period are further input into the sequence encoder based on the RNN-LSTM hybrid model to obtain the multi-scale time series implicit coding vector of the input voltage and the multi-scale time series implicit coding vector of the output voltage. It is worth mentioning that in the sequence encoder based on the RNN-LSTM hybrid model, the RNN can process the time queue data of the input voltage and the time queue data of the output voltage, and capture the temporal dependency of the input voltage and the output voltage respectively. This is very useful for analyzing the dynamic changes of the input voltage and the output voltage, because these voltage values ​​are continuous and correlated in time. LSTM is particularly good at dealing with long-term dependency problems. It can effectively remember the feature information of the input voltage and the output voltage respectively in the long-term dependency association, which is very important for capturing the long-term trend of the input voltage and the output voltage. This multi-scale analysis helps to understand the dynamic characteristics of the input voltage and the output voltage more comprehensively, so as to more accurately predict future voltage changes, and it can also improve the robustness and generalization ability of the model under different working conditions, which is crucial for judging whether to connect the rectifier device to the rectifier circuit to improve the stability of the power module startup process.

[0046] Specifically, in S32, the input voltage multi-scale time series implicit coding features and the output voltage multi-scale time series implicit coding features are subjected to feature interactive comparison processing using external knowledge modulation to obtain input voltage-output voltage time series comparison fine-grained interactive features. It should be understood that since the input voltage multi-scale time series implicit coding vector and the output voltage multi-scale time series implicit coding vector respectively contain multi-scale time series dynamic feature information about the input voltage and the output voltage in the time dimension, however, since the input voltage and the output voltage not only have their own time series dynamic characteristics in the time dimension, that is, the voltage data at the current time point will be affected by the time series changes of the previous voltage, and there is also interactive information and dynamic correlation between the voltage time series semantics between the two. Therefore, in order to be able to perform fine-grained interactive comparison of the input voltage multi-scale time series features and the output voltage multi-scale time series features, thereby providing more refined support for subsequent state discrimination and decision-making, in the technical solution of the present application, the input voltage multi-scale time series implicit coding features and the output voltage multi-scale time series implicit coding features are further subjected to feature interactive comparison processing using external knowledge modulation to obtain input voltage-output voltage time series comparison fine-grained interactive features. In particular, the feature interactive comparison processing using external knowledge modulation can further capture the tiny but important interactive information between the input voltage multi-scale time series features and the output voltage multi-scale time series features. This fine-grained interactive information helps to more accurately understand the dynamic relationship between the input voltage and the output voltage, thereby providing more refined support for subsequent state discrimination tasks and decisions. It is worth mentioning that in the process of feature interactive comparison processing using external knowledge modulation, not only the interaction and comparison information of the time series multi-scale features between the input voltage and the output voltage are strengthened, but also these interactions are optimized by integrating external knowledge. External knowledge can come from the experience of domain experts, historical data, etc. This knowledge is effectively integrated into the interactive comparison process of the timing characteristics of the input voltage and output voltage through the attention mechanism, which enables better understanding and processing of complex state discrimination tasks in different scenarios and improves its performance in practical applications. In other words, this enhanced generalization ability enables the model to maintain high accuracy and stability when facing different working conditions and power grid environments, providing reliable data support for subsequent control decisions.

[0047] In an embodiment of the present application, the specific steps of performing feature interaction comparison processing on the input voltage multi-scale time series implicit coding features and the output voltage multi-scale time series implicit coding features using external knowledge modulation include: first, fine-grained feature interaction and optimization representation are performed on the input voltage multi-scale time series implicit coding vector and the output voltage multi-scale time series implicit coding vector to obtain an external knowledge optimized input voltage-output voltage time series fine-grained feature interaction matrix. That is, in a specific example of the present application, the input voltage multi-scale time series implicit coding vector and the output voltage multi-scale time series implicit coding vector are first subjected to fine-grained feature interaction to obtain an input voltage-output voltage time series fine-grained feature interaction matrix; then, the input voltage-output voltage time series fine-grained feature interaction matrix is ​​passed through an attention unit based on external knowledge to obtain the external knowledge optimized input voltage-output voltage time series fine-grained feature interaction matrix.

[0048] More specifically, the input voltage multi-scale time series implicit coding vector and the output voltage multi-scale time series implicit coding vector are subjected to fine-grained feature interaction and optimization representation using the following fine-grained feature interaction optimization formula to obtain an external knowledge optimized input voltage-output voltage time series fine-grained feature interaction matrix; wherein the fine-grained feature interaction optimization formula is:

[0049]

[0050] Wherein, V1 and V2 are the multi-scale time series implicit coding vector of the input voltage and the multi-scale time series implicit coding vector of the output voltage, respectively. p is the input voltage-output voltage timing comparison fine-grained feature interaction matrix, M k and M v represents the first external knowledge attention learnable memory parameter matrix and the second external knowledge attention learnable memory parameter matrix, norm(·) represents the normalization function, M y Optimizing the input voltage-output voltage timing fine-grained feature interaction matrix for external knowledge.

[0051] Next, based on the external knowledge, the input voltage-output voltage timing fine-grained feature interaction matrix is ​​optimized, and the input voltage multi-scale timing implicit coding vector and the output voltage multi-scale timing implicit coding vector are modulated respectively to obtain the optimized input voltage multi-scale timing implicit coding vector and the optimized output voltage multi-scale timing implicit coding vector. That is, in a specific example of the present application, the input voltage-output voltage timing fine-grained feature interaction matrix is ​​first optimized based on the external knowledge to perform fine-grained modulation optimization on the input voltage multi-scale timing implicit coding vector to obtain the optimized input voltage multi-scale timing implicit coding vector; and then, based on the external knowledge to optimize the input voltage-output voltage timing fine-grained feature interaction matrix, the output voltage multi-scale timing implicit coding vector is fine-grained modulated and optimized to obtain the optimized output voltage multi-scale timing implicit coding vector.

[0052] Among them, based on the external knowledge optimization of the input voltage-output voltage timing fine-grained feature interaction matrix, the input voltage multi-scale timing implicit coding vector is fine-grained modulated and optimized to obtain the optimized input voltage multi-scale timing implicit coding vector, including: linearly transforming the input voltage multi-scale timing implicit coding vector to obtain an input voltage multi-scale timing query feature vector and an input voltage multi-scale timing value feature vector; using the external knowledge optimization of the input voltage-output voltage timing fine-grained feature interaction matrix as a key matrix, inputting the input voltage multi-scale timing query feature vector, the input voltage multi-scale timing value feature vector and the key matrix into a fine-grained modulation module based on a Transformer structure to obtain the optimized input voltage multi-scale timing implicit coding vector; using And, based on the external knowledge optimized input voltage-output voltage timing fine-grained feature interaction matrix, the output voltage multi-scale timing implicit coding vector is fine-grained modulated and optimized to obtain the optimized output voltage multi-scale timing implicit coding vector, including: linearly transforming the output voltage multi-scale timing implicit coding vector to obtain an output voltage multi-scale timing query feature vector and an output voltage multi-scale timing value feature vector; using the external knowledge optimized input voltage-output voltage timing fine-grained feature interaction matrix as a key matrix, inputting the output voltage multi-scale timing query feature vector, the output voltage multi-scale timing value feature vector and the key matrix into the Transformer-based fine-grained modulation module to obtain the optimized output voltage multi-scale timing implicit coding vector.

[0053] More specifically, based on the external knowledge, the input voltage-output voltage timing fine-grained feature interaction matrix is ​​optimized, and the input voltage multi-scale timing implicit coding vector and the output voltage multi-scale timing implicit coding vector are modulated respectively by the following modulation formula to obtain an optimized input voltage multi-scale timing implicit coding vector and an optimized output voltage multi-scale timing implicit coding vector; wherein the modulation formula is:

[0054]

[0055] Among them, W 1q and b 1q They represent the input voltage multi-scale time series query weight matrix and the input voltage multi-scale time series query bias vector, W 1v and b 1v They represent the weight matrix of the multi-scale time series value of the input voltage and the bias vector of the multi-scale time series value of the input voltage, respectively. is the matrix multiplication, V 1q and V 1v are the input voltage multi-scale time series query feature vector and the input voltage multi-scale time series value feature vector, respectively. T is the matrix transpose, d1 is V 1q , softmax(·) represents the softmax function, V′1 is the optimized input voltage multi-scale time series implicit encoding vector, W 2q and b 2q They represent the output voltage multi-scale time series query weight matrix and the output voltage multi-scale time series query bias vector, W 2v and b 2v They represent the output voltage multi-scale time series value weight matrix and the output voltage multi-scale time series value bias vector, V 2q and V 2v are the output voltage multi-scale time series query feature vector and the output voltage multi-scale time series value feature vector, d2 is V 2q , V′2 is the optimized output voltage multi-scale time series implicit coding vector.

[0056] Furthermore, the optimized input voltage multi-scale time series implicit coding vector and the optimized output voltage multi-scale time series implicit coding vector are semantically contrasted and associated coded to obtain an input voltage-output voltage time series contrast fine-grained interactive feature vector as the input voltage-output voltage time series contrast fine-grained interactive feature. That is, in a specific example of the present application, the position point-by-position point division between the optimized input voltage multi-scale time series implicit coding vector and the optimized output voltage multi-scale time series implicit coding vector is calculated to obtain the input voltage-output voltage time series contrast fine-grained interactive feature vector.

[0057] More specifically, the optimized input voltage multi-scale time series implicit coding vector and the optimized output voltage multi-scale time series implicit coding vector are semantically contrasted and associated coded using the following semantic contrast association coding formula to obtain an input voltage-output voltage time series contrast fine-grained interactive feature vector; wherein the semantic contrast association coding formula is:

[0058]

[0059] Among them, V s The input voltage-output voltage timing comparison fine-grained interaction feature vector.

[0060] Specifically, the S33 performs state discrimination based on the input voltage-output voltage timing comparison fine-grained interaction feature to determine whether to execute step 4 or return to step 2. That is, in a specific example of the present application, the input voltage-output voltage timing comparison fine-grained interaction feature vector is input into a state discriminator based on a classifier to obtain a discrimination result, and the discrimination result is used to indicate whether to execute step 4 or return to step 2. In other words, the classification process is performed using the timing fine-grained comparison interaction semantic features between the input voltage and the output voltage, so as to perform state judgment to decide whether to execute step 4 or return to step 2. In this way, a more intelligent new power module surge suppression control can be achieved, which can avoid the defects of the traditional fixed set value comparison to determine whether to connect the rectifier device to the rectifier circuit, and then can achieve effective surge suppression under a wider range of conditions, which helps to improve the stability of the power module startup process.

[0061] In one example, in order to determine whether the next operation is to execute step 4 or return to step 2, a state discriminator based on a classifier can be used. Specifically, a large amount of input voltage and output voltage data is collected, and the correct operation corresponding to each set of data is marked (execute step 4 or return to step 2). For example, when the difference between the input voltage and the output voltage is less than a preset threshold, it is marked as executing step 4; otherwise, it is marked as returning to step 2. The data is divided into a training set and a test set. The training set is used to train the classifier, and the test set is used to evaluate the performance of the classifier.

[0062] In the technical solution of the present application, the input voltage multi-scale time series implicit coding vector and the output voltage multi-scale time series implicit coding vector respectively represent the multi-scale time series correlation characteristics of the input voltage and the output voltage. When performing fine-grained feature interaction based on external knowledge modulation, the time series multi-scale load type of the input voltage and the output voltage will make the fine-grained modulation of the external knowledge difficult, resulting in insufficient representation of the long-distance fine-grained interaction response, thereby reducing the expression effect of the input voltage-output voltage time series comparison fine-grained interaction feature vector, affecting the accuracy of the discrimination result obtained by its input classifier-based state discriminator.

[0063] Therefore, in one example, when the input voltage-output voltage timing sequence comparison fine-grained interactive feature vector is input into a state discriminator based on a classifier, the input voltage-output voltage timing sequence comparison fine-grained interactive feature vector is optimized, and the optimization includes the following steps:

[0064] Arranging the eigenvalues ​​of the input voltage-output voltage timing comparison fine-grained interaction eigenvector in ascending order to form an input voltage-output voltage timing comparison fine-grained interaction sequence encoding vector;

[0065] In response to the absolute value of the difference between the i-th eigenvalue and the i+1-th eigenvalue of the input voltage-output voltage timing comparison fine-grained interactive sequential encoding vector being less than or equal to the distance difference hyperparameter ε, a weighted sum between the i-th eigenvalue and the i+1-th eigenvalue is calculated as the optimized i+1-th eigenvalue v′ i+1 =ω1×v i +ω2×v i+1 , where v i and v i+1 They respectively represent the i-th eigenvalue and the i+1-th eigenvalue of the input voltage-output voltage time series contrast fine-grained interactive sequential encoding vector, ω1 represents a first weighted hyperparameter, and ω2 represents a second weighted hyperparameter;

[0066] In response to the input voltage-output voltage timing comparison, the absolute value of the difference between the i-th eigenvalue and the i+1-th eigenvalue of the fine-grained interactive sequential encoding vector is greater than the distance difference hyperparameter ε:

[0067] Calculate the square root of the sum of squares of all eigenvalues ​​of the input voltage-output voltage timing contrast fine-grained interaction eigenvector Among them, v1, v2 and v n respectively represent the first, second and nth eigenvalues ​​of the input voltage-output voltage timing contrast fine-grained interaction eigenvector;

[0068] The square root root is multiplied by 2 and then divided by the square of the length of the input voltage-output voltage timing comparison fine-grained interaction feature vector to obtain the input voltage-output voltage timing comparison fine-grained interaction space primitive value base=2×root / L 2 , where L represents the length of the input voltage-output voltage timing comparison fine-grained interaction feature vector;

[0069] After multiplying the input voltage-output voltage timing comparison fine-grained interaction space primitive value by the i-th eigenvalue, the weighted subtraction between the product and the i+1th eigenvalue is calculated to obtain the optimized i+1th eigenvalue v i+1 ′=ω3×vi ×base-ω4×v i+1 , where ω3 represents the third weighted hyperparameter, and ω4 represents the fourth weighted hyperparameter;

[0070] Based on v′1=v1, where v′1 represents the first eigenvalue of the optimized input voltage-output voltage timing contrast fine-grained interaction eigenvector, the i+1th eigenvalue v of the combined optimization is i+1 ′ to obtain the optimized input voltage-output voltage timing comparison fine-grained interaction feature vector.

[0071] In this way, in order to address the problem of insufficient global semantic search representation capability of the feature set of the input voltage-output voltage timing contrast fine-grained interaction feature vector under a predetermined eigenvalue sequential distribution due to a long distance exceeding a predetermined local distribution interval threshold, a high-dimensional feature space primitive representation based on self-inner product fusion of the input voltage-output voltage timing contrast fine-grained interaction feature vector is used to capture the complex structure of the global network interaction of its eigenvalues, thereby reconstructing the dynamic semantic search relationship between the eigenvalues ​​of the input voltage-output voltage timing contrast fine-grained interaction feature vector by simulating scale-based high-dimensional feature space potential primitives, so as to achieve encoding reconstruction of the real sequence distribution behavior of the input voltage-output voltage timing contrast fine-grained interaction feature vector under a long distance, improve the encoding expression effect of the input voltage-output voltage timing contrast fine-grained interaction feature vector, and improve the accuracy of the discrimination result obtained by its input into a classifier-based state discriminator.

[0072] In particular, the S4 outputs a control signal to control the rectifier device of the power module to access the rectifier circuit to charge the first capacitor. During the startup and operation of the power module, outputting a control signal to control the rectifier device to access the rectifier circuit to charge the first capacitor is a key step to ensure system stability and efficiency. By accurately controlling the access timing of the rectifier device, surge current can be effectively avoided to ensure smooth startup of the power module.

[0073] In order to realize the output control signal, control the rectifier device to access the rectifier circuit, and charge the first capacitor, appropriate hardware components need to be configured. These components include a microcontroller (MCU), a drive circuit, a rectifier device, and a first capacitor. The microcontroller is responsible for generating a control signal to control the connection and disconnection of the rectifier device. The drive circuit is used to amplify the control signal of the microcontroller and drive the rectifier device. The rectifier device is used to convert AC voltage into DC voltage. Common rectifier devices include MOSFET, IGBT, and diodes. The first capacitor is used to store electrical energy to ensure the stability of the output voltage. It usually has a large capacity to absorb the surge current during startup.

[0074] In one example, first, the microcontroller initializes the ADC and timer, and sets the sampling frequency and sampling interval. For example, the sampling frequency is set to 1kHz and the sampling interval is set to 1ms. Then, the microcontroller continuously collects the values ​​of the input voltage and the output voltage through the ADC and stores the data in the RAM. Next, the collected data is filtered to reduce noise interference. Common filtering methods include low-pass filtering, average filtering, and median filtering. For example, a second-order low-pass filter with a cutoff frequency of 100Hz can be used to filter the data. Finally, the filtered data is stored in the RAM for subsequent analysis and control. Next, according to system requirements, the thresholds of the input voltage and the output voltage are set. For example, the threshold of the input voltage is set to 300V and the threshold of the output voltage is set to 22V. The microcontroller compares the collected voltage value with the preset threshold in real time to determine whether the access condition is met. For example, when the input voltage reaches 300V and the output voltage is lower than 22V, the access condition is triggered.

[0075] The microcontroller calculates the voltage change trend based on the collected voltage value. For example, the difference between the input voltage and the output voltage is calculated to determine the voltage change trend. Based on the voltage change trend and the preset conditions, it is determined whether the rectifier device needs to be connected. For example, when the input voltage reaches the peak value and the difference between the output voltage and the input voltage is less than the preset threshold, the connection condition is triggered.

[0076] When the access conditions are met, the microcontroller generates a control signal and outputs it to the drive circuit through the IO port. The control signal is usually a high or low level signal used to control the on and off of the drive circuit. The drive circuit amplifies the control signal of the microcontroller and drives the rectifier device to access the rectifier circuit. For example, the drive circuit amplifies the control signal of the microcontroller and drives the gate of the MOSFET to turn it on.

[0077] After the rectifier device is connected to the rectifier circuit, the AC voltage is converted into a DC voltage to charge the first capacitor. For example, when the MOSFET is turned on, the AC voltage is converted into a DC voltage through the rectifier bridge to charge the first capacitor of 470μF / 400V. The microcontroller continuously monitors the voltage value across the first capacitor through the ADC to determine whether the charging is completed. When the voltage across the first capacitor reaches the preset value, the microcontroller generates a disconnect signal and disconnects the rectifier device through the drive circuit to prevent overcharging.

[0078] In particular, in S5, if the current input voltage value is less than the difference between the current output voltage value and the preset threshold value, the rectifier device is disconnected and the process returns to step 3. If not, the process returns to step 4. In the early stage of startup of the power module, the input voltage gradually increases and the output voltage gradually builds up. In order to prevent surge current caused by excessive input voltage, it is necessary to connect the rectifier device at an appropriate time to charge the first capacitor. At the same time, in some cases, it is necessary to disconnect the rectifier device to prevent overcharging or other abnormal conditions. Therefore, a precise control logic is required to determine when to connect and disconnect the rectifier device.

[0079] In one example, the microcontroller continuously collects the values ​​of input voltage and output voltage through ADC and monitors voltage changes in real time. Specifically, the microcontroller collects the values ​​of input voltage and output voltage through ADC and stores the data in RAM. In order to reduce noise interference, the collected data is filtered. Common filtering methods include low-pass filtering, average filtering and median filtering. For example, a second-order low-pass filter with a cutoff frequency of 100Hz can be used to filter the data. The filtered data is stored in RAM for subsequent analysis and control.

[0080] The microcontroller compares the collected voltage value with the preset threshold in real time to determine whether the access condition is met. Specifically, the collected voltage value is compared with the preset threshold to determine whether the access condition is met. For example, when the input voltage reaches 300V and the output voltage is lower than 22V, the access condition is triggered. Based on the voltage change trend and preset conditions, it is further determined whether the rectifier device needs to be connected. For example, when the input voltage reaches the peak value and the difference between the output voltage and the input voltage is less than the preset threshold, the access condition is triggered.

[0081] When the access conditions are met, the microcontroller generates a control signal, which is output to the drive circuit through the IO port, and drives the rectifier device to access the rectifier circuit. Specifically, when the access conditions are met, the microcontroller generates a control signal, which is output to the drive circuit through the IO port. The control signal is usually a high-level or low-level signal used to control the on and off of the drive circuit. The drive circuit amplifies the control signal of the microcontroller and drives the rectifier device to access the rectifier circuit. For example, the drive circuit amplifies the control signal of the microcontroller and drives the gate of the MOSFET to turn it on.

[0082] After the rectifier device is connected to the rectifier circuit, the AC voltage is converted into a DC voltage to charge the first capacitor. Specifically, after the rectifier device is connected to the rectifier circuit, the AC voltage is converted into a DC voltage to charge the first capacitor. For example, when the MOSFET is turned on, the AC voltage is converted into a DC voltage through the rectifier bridge to charge the first capacitor of 470μF / 400V. The microcontroller continuously monitors the voltage value across the first capacitor through the ADC to determine whether the charging is completed. For example, the voltage value across the first capacitor is collected through the ADC to determine whether the charging is completed.

[0083] In order to prevent overcharging or other abnormal conditions, it is necessary to disconnect the rectifier device at an appropriate time. Specifically, the microcontroller collects the current input voltage value and output voltage value through the ADC. Calculate the difference between the current output voltage value and the preset threshold. For example, if the preset threshold is 22V and the current output voltage value is 24V, the difference is 24V-22V=2V. Compare the current input voltage value with the calculated difference. For example, if the current input voltage value is 290V, the difference is 2V, that is, 290V<(24V-2V)=22V. If the current input voltage value is less than the difference between the current output voltage value and the preset threshold, the microcontroller generates a disconnection signal and disconnects the rectifier device through the drive circuit. For example, when 290V<22V, a disconnection signal is generated to drive the gate of the MOSFET to turn it off. After disconnecting the rectifier device, return to step 3 and re-perform threshold comparison and state judgment. If the current input voltage value is not less than the difference between the current output voltage value and the preset threshold, return to step 4, continue to generate control signals, maintain the access state of the rectifier device, and continue to charge the first capacitor.

[0084] In particular, the S6 determines whether the difference between the current input voltage value and the output voltage value is less than the predetermined threshold value. If so, the rectifier device is kept in the on state so that the power module enters the normal working mode. If not, return to step 3 to continue input surge suppression. In one example, taking a typical PFC power module as an example, the specific implementation steps of the S6 are as follows: First, initialize the microcontroller, set the sampling frequency to 1kHz, and the sampling interval to 1ms. According to system requirements, the input voltage threshold is set to 300V, the output voltage threshold is set to 22V, and the preset threshold difference is 10V. The microcontroller continuously collects the values ​​of the input voltage and the output voltage through the ADC and stores the data in the RAM. The collected data is low-pass filtered to reduce noise interference. The filtered data is stored in the RAM for subsequent analysis and control. The microcontroller compares the collected voltage value with the preset threshold in real time to determine whether the access condition is met. For example, when the input voltage reaches 300V and the output voltage is lower than 22V, the access condition is triggered. According to the voltage change trend and the preset conditions, it is further determined whether the rectifier device needs to be connected. For example, when the input voltage reaches a peak value and the difference between the output voltage and the input voltage is less than a preset threshold, the access condition is triggered. When the access condition is met, the microcontroller generates a control signal and outputs it to the drive circuit through the IO port. The drive circuit amplifies the control signal of the microcontroller and drives the gate of the MOSFET to turn it on. After the MOSFET is turned on, the AC voltage is converted into a DC voltage to charge the first capacitor of 470μF / 400V. The microcontroller continuously monitors the voltage value across the first capacitor through the ADC to determine whether the charging is completed. In order to ensure that the power module can smoothly transition to the normal working mode, the microcontroller collects the current input voltage value and output voltage value through the ADC. Calculate the difference between the current output voltage value and the preset threshold. For example, the preset threshold is 22V, and the current output voltage value is 24V, then the difference is 24V-22V=2V. Compare the current input voltage value with the calculated difference. For example, the current input voltage value is 300V, and the difference is 2V, that is, 300V>(24V-2V)=22V. If the difference between the current input voltage value and the output voltage value is less than the preset threshold, keep the rectifier device in the on state, so that the power module enters the normal working mode. Specifically, when 300V-24V<10V, keep the gate of the MOSFET in the on state, so that the power module enters the normal working mode. At this time, the output voltage of the power module has stabilized and can supply power normally. If the difference between the current input voltage value and the output voltage value is not less than the preset threshold, return to step 3 and continue input surge suppression. Specifically, when 300V-24V>10V, generate a disconnect signal to drive the gate of the MOSFET to turn it off, return to step 3, and continue input surge suppression.At this time, the power module continues to monitor the changes in input voltage and output voltage, waiting for the right time to connect to the rectifier device again.

[0085] In summary, the new power module surge suppression method according to the embodiment of the present application is explained, which, after determining that the current input voltage value has reached the peak value, uses the dynamic change characteristics and trends between the input voltage timing data and the output voltage timing data in a predetermined time period to determine whether to connect the rectifier device to the rectifier circuit, that is, to determine whether to execute step 4 or return to step 2. In this way, the defects of the traditional fixed set value comparison and monitoring control method can be avoided, and effective surge suppression can be achieved under a wider range of conditions, thereby helping to improve the stability and efficiency of the power module startup process.

[0086] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A new power module surge suppression method, characterized in that: include: Step 1: Make the auxiliary power supply work; Step 2: Continuously collect output voltage value and input voltage value; Step 3: after determining that the current input voltage value has reached the peak value, determine whether to execute step 4 or return to step 2 based on the time queue of the input voltage and the time queue of the output voltage in the predetermined time period; Step 4: output a control signal to control the rectifier device of the power module to connect to the rectifier circuit to charge the first capacitor; Step 5: If the current input voltage value is less than the difference between the current output voltage value and the preset threshold value, disconnect the rectifier device and return to step 3; if not, return to step 4; Step 6: Determine whether the difference between the current input voltage value and the output voltage value is less than the predetermined threshold value. If so, keep the rectifier device in the on state so that the power module enters the normal working mode. If not, return to step 3 and continue input surge suppression.

2. The new power module surge suppression method according to claim 1 is characterized in that: The step 3 comprises: Sequentially encoding the time queue of the input voltage and the time queue of the output voltage respectively to obtain a multi-scale time series implicit coding feature of the input voltage and a multi-scale time series implicit coding feature of the output voltage; Performing feature interactive contrast processing using external knowledge modulation on the input voltage multi-scale time series implicit coding features and the output voltage multi-scale time series implicit coding features to obtain input voltage-output voltage time series contrast fine-grained interactive features; A state judgment is performed based on the input voltage-output voltage timing comparison fine-grained interaction characteristics to determine whether to execute step 4 or return to step 2.

3. The new power module surge suppression method according to claim 2 is characterized in that: The time queue of the input voltage and the time queue of the output voltage are respectively sequence-encoded to obtain an input voltage multi-scale time series implicit coding vector and an output voltage multi-scale time series implicit coding vector, including: inputting the time queue of the input voltage and the time queue of the output voltage into a sequence encoder based on an RNN-LSTM hybrid model respectively to obtain an input voltage multi-scale time series implicit coding vector as the input voltage multi-scale time series implicit coding feature and an output voltage multi-scale time series implicit coding vector as the output voltage multi-scale time series implicit coding feature.

4. The new power module surge suppression method according to claim 3 is characterized in that: The input voltage multi-scale time series implicit coding features and the output voltage multi-scale time series implicit coding features are subjected to feature interactive comparison processing using external knowledge modulation to obtain input voltage-output voltage time series comparison fine-grained interactive features, including: Performing fine-grained feature interaction and optimization representation on the input voltage multi-scale time series implicit coding vector and the output voltage multi-scale time series implicit coding vector to obtain an external knowledge optimized input voltage-output voltage time series fine-grained feature interaction matrix; Optimizing the input voltage-output voltage timing fine-grained feature interaction matrix based on the external knowledge, modulating the input voltage multi-scale timing implicit coding vector and the output voltage multi-scale timing implicit coding vector respectively to obtain an optimized input voltage multi-scale timing implicit coding vector and an optimized output voltage multi-scale timing implicit coding vector; The optimized input voltage multi-scale timing implicit coding vector and the optimized output voltage multi-scale timing implicit coding vector are semantically contrasted and associated coded to obtain an input voltage-output voltage timing contrast fine-grained interaction feature vector as the input voltage-output voltage timing contrast fine-grained interaction feature.

5. The new power module surge suppression method according to claim 4 is characterized in that: The input voltage multi-scale time series implicit coding vector and the output voltage multi-scale time series implicit coding vector are subjected to fine-grained feature interaction and optimized representation to obtain an external knowledge optimized input voltage-output voltage time series fine-grained feature interaction matrix, including: Performing fine-grained feature interaction on the input voltage multi-scale time series implicit coding vector and the output voltage multi-scale time series implicit coding vector to obtain an input voltage-output voltage time series fine-grained feature interaction matrix; The input voltage-output voltage timing fine-grained feature interaction matrix is ​​passed through an attention unit based on external knowledge to obtain the external knowledge optimized input voltage-output voltage timing fine-grained feature interaction matrix.

6. The new power module surge suppression method according to claim 5 is characterized in that: Based on the external knowledge, the input voltage-output voltage time series fine-grained feature interaction matrix is ​​optimized, and the input voltage multi-scale time series implicit coding vector and the output voltage multi-scale time series implicit coding vector are modulated respectively to obtain an optimized input voltage multi-scale time series implicit coding vector and an optimized output voltage multi-scale time series implicit coding vector, including: Optimizing the input voltage-output voltage timing fine-grained feature interaction matrix based on the external knowledge to perform fine-grained modulation optimization on the input voltage multi-scale timing implicit coding vector to obtain the optimized input voltage multi-scale timing implicit coding vector; Based on the external knowledge, the input voltage-output voltage timing fine-grained feature interaction matrix is ​​optimized to perform fine-grained modulation optimization on the output voltage multi-scale timing implicit coding vector to obtain the optimized output voltage multi-scale timing implicit coding vector.

7. The new power module surge suppression method according to claim 6 is characterized in that: Optimizing the input voltage-output voltage time series fine-grained feature interaction matrix based on the external knowledge to perform fine-grained modulation optimization on the input voltage multi-scale time series implicit coding vector to obtain the optimized input voltage multi-scale time series implicit coding vector, including: Performing a linear transformation on the input voltage multi-scale time series implicit coding vector to obtain an input voltage multi-scale time series query feature vector and an input voltage multi-scale time series value feature vector; The external knowledge is used to optimize the input voltage-output voltage timing fine-grained feature interaction matrix as a key matrix, and the input voltage multi-scale timing query feature vector, the input voltage multi-scale timing value feature vector and the key matrix are input into a fine-grained modulation module based on a Transformer structure to obtain the optimized input voltage multi-scale timing implicit coding vector.

8. The new power module surge suppression method according to claim 7, characterized in that: Optimizing the input voltage-output voltage timing fine-grained feature interaction matrix based on the external knowledge to perform fine-grained modulation optimization on the output voltage multi-scale timing implicit coding vector to obtain the optimized output voltage multi-scale timing implicit coding vector, including: Performing a linear transformation on the output voltage multi-scale time series implicit coding vector to obtain an output voltage multi-scale time series query feature vector and an output voltage multi-scale time series value feature vector; The external knowledge-optimized input voltage-output voltage timing fine-grained feature interaction matrix is ​​used as a key matrix, and the output voltage multi-scale timing query feature vector, the output voltage multi-scale timing value feature vector and the key matrix are input into the Transformer-based fine-grained modulation module to obtain the optimized output voltage multi-scale timing implicit coding vector.

9. The new power module surge suppression method according to claim 8, characterized in that: The optimized input voltage multi-scale timing implicit coding vector and the optimized output voltage multi-scale timing implicit coding vector are semantically contrasted and associated coded to obtain an input voltage-output voltage timing contrast fine-grained interaction feature vector as the input voltage-output voltage timing contrast fine-grained interaction feature, including: calculating the position point-by-position point division between the optimized input voltage multi-scale timing implicit coding vector and the optimized output voltage multi-scale timing implicit coding vector to obtain the input voltage-output voltage timing contrast fine-grained interaction feature vector.

10. The new power module surge suppression method according to claim 9, characterized in that: Based on the input voltage-output voltage timing comparison fine-grained interaction features, state discrimination is performed to determine whether to execute step 4 or return to step 2, including: inputting the input voltage-output voltage timing comparison fine-grained interaction feature vector into a classifier-based state discriminator to obtain a discrimination result, and the discrimination result is used to indicate whether to execute step 4 or return to step 2.

Images