Pulse power supply system parameter selection method and system

Abstract

The invention discloses a pulse power supply system parameter selection method and system, and belongs to the technical field of pulse power supply systems, and the method comprises the following steps: S1, collecting state historical data of a pulse power supply system; s2, processing the historical state data of the pulse power supply system; s3, training an optimal pulse power supply system parameter selection numerical model; s4, selecting an optimal pulse power supply system parameter according to the energy output requirement of a user on the pulse power supply system; and S5, interface display: displaying the optimal pulse power supply system parameters to a user in a visual form. According to the invention, the problems that the pulse power supply system is poor in use effect and the performance and reliability of the pulse power supply system are reduced because the parameters of the pulse power supply system cannot be flexibly selected according to user requirements in the prior art are solved. The pulse power supply system parameters can be flexibly selected according to user requirements, the use effect of the pulse power supply system is improved, and the performance and reliability of the pulse power supply system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of pulse power supply systems, and in particular to a method and system for selecting parameters of a pulse power supply system. Background Art

[0002] Pulse power supply systems have been widely used in various application scenarios; however, different application scenarios have different parameter requirements for pulse power supply systems. Therefore, the parameter selection of pulse power supply systems is particularly important.

[0003] The Chinese patent with publication number CN118861604A discloses a life prediction method for a pulse power system, including: obtaining multiple life prediction values ​​of a pulse power supply to be tested in a current charge and discharge cycle according to multiple life prediction models, weighted summing the life prediction values ​​sorted according to a target arrangement, obtaining a life estimation value under the target arrangement, calculating the prediction accuracy of each life prediction value according to the size relationship between each life prediction value and the life of the pulse power supply to be tested in the previous charge and discharge cycle and the difference between each life prediction value and the life estimation value, sorting all life prediction values ​​according to the prediction accuracy to obtain a sequence, calculating the consistency of the sequence and the target arrangement, and taking the life estimation value under the arrangement with the greatest consistency as the life of the pulse power supply to be tested in the current charge and discharge cycle; the accuracy of life prediction of the pulse power supply is enhanced; however, the patent has the following defects: The existing technology cannot flexibly select the pulse power system parameters according to user needs, which makes the pulse power system have poor use effect and reduces the performance and reliability of the pulse power system. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for selecting parameters of a pulse power supply system, which can flexibly select parameters of the pulse power supply system according to user needs, improve the use effect of the pulse power supply system, and improve the performance and reliability of the pulse power supply system, thereby solving the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: A method for selecting parameters of a pulse power supply system comprises the following steps: S1. Data collection: Collect the energy output, pulse frequency, duty cycle, pulse width and voltage and current historical data of the pulse power supply system, and determine the pulse power supply system status historical data based on big data; S2. Data processing: cleaning, normalizing and integrating the pulse power system status historical data based on big data, and safely storing and backing up the integrated pulse power system status historical data; S3, Model training: Based on deep learning technology, actively learn the intrinsic relationship between pulse power system parameter selection and energy output, and train the optimal pulse power system parameter selection numerical model; S4, parameter selection: according to the user's energy output requirements for the pulse power system, the optimal pulse power system parameters are selected based on the optimal pulse power system parameter selection numerical model; S5. Interface display: Display the optimal pulse power system parameters to the user in a visual form.

[0006] Preferably, in S1, collecting the historical data of the pulse power system status based on big data includes: Based on the pulse power system history database, the energy output history of the pulse power system is collected to obtain the energy output history data of the pulse power system; Based on the pulse power system history database, the pulse frequency history of the pulse power system is collected to obtain the pulse frequency history data of the pulse power system; Based on the pulse power system history database, the duty cycle history of the pulse power system is collected to obtain the duty cycle history data of the pulse power system; Based on the pulse power system history database, the pulse width history of the pulse power system is collected to obtain the pulse width history data of the pulse power system; Based on the pulse power system history database, the voltage and current history of the pulse power system is collected to obtain the voltage and current history data of the pulse power system; Among them, based on the pulse power supply system energy output historical data, the pulse power supply system pulse frequency historical data, the pulse power supply system duty cycle historical data, the pulse power supply system pulse width historical data and the pulse power supply system voltage and current historical data, the pulse power supply system status historical data based on big data is determined.

[0007] Preferably, in S2, the pulse power system status historical data based on big data is processed, including: Clean the historical data of pulse power system status based on big data based on data cleaning tools; Among them, checking and identifying duplicate values, missing values ​​and abnormal values ​​in the pulse power system status historical data based on big data, and processing the duplicate values, missing values ​​and abnormal values ​​in the pulse power system status historical data based on big data; For duplicate values, delete them directly; for missing values, delete the data records containing missing values ​​or use the mean value to replace the missing values; for outliers, delete the data records containing outliers or use the median to replace outliers.

[0008] Preferably, in S2, processing the pulse power system status historical data based on big data also includes: Based on the ‌Z-score standardization method, the pulse power system status historical data based on big data is normalized to unify the pulse power system status historical data based on big data, remove the dimensional differences between the pulse power system status historical data based on big data, and determine the standardized pulse power system status historical data; The standardized pulse power supply system status historical data is integrated and processed, and the standardized pulse power supply system status historical data is integrated into a unified data view, and the integrated pulse power supply system status historical data is checked to check whether the integrated pulse power supply system status historical data is missing. After passing the inspection, the integrated pulse power supply system status historical data is securely stored and backed up.

[0009] Preferably, in S3, training an optimal pulse power system parameter selection numerical model includes: Dividing the pulse power system state historical data into a training set and a test set; Based on deep learning technology, the deep learning model is trained with a training set, so that the deep learning model actively learns the intrinsic relationship between the pulse power system parameter selection and energy output, and then trains the pulse power system parameter selection numerical model; Based on the test set, the performance test of the numerical model for selecting the parameters of the pulse power supply system is carried out to determine whether the numerical model for selecting the parameters of the pulse power supply system can achieve the expected effect; When the pulse power system parameter selection numerical model cannot achieve the expected effect, the parameters and structure of the pulse power system parameter selection numerical model are adjusted, and the adjusted pulse power system parameter selection numerical model is continuously iterated and optimized to determine the optimal pulse power system parameter selection numerical model.

[0010] Preferably, in S4, selecting the optimal pulse power system parameters includes: Obtain the optimal pulse power system parameter selection numerical model, and deploy the optimal pulse power system parameter selection numerical model in the actual pulse power system parameter selection environment; According to the user's demand for the energy output of the pulse power supply system, the pulse power supply system parameters are predicted and analyzed based on the optimal pulse power supply system parameter selection numerical model. The optimal pulse power supply system parameters are selected by online adjustment and adaptive regulation of the pulse power supply system parameters.

[0011] Preferably, in S5, displaying the optimal pulse power system parameters to the user includes: Provide a user interface to display the optimal pulse power system parameters to users in a visual form, and track the user's pulse power system usage in real time, obtain user feedback and parameter selection test results, and continuously adjust and optimize the pulse power system parameters based on user feedback and parameter selection test results to make it better adapt to different scenarios and user needs.

[0012] Preferably, the pulse power system parameter selection method further includes: Fault detection: A fault detection circuit with a memristor is set up to sense power system faults using the resistance change characteristics of the memristor. When the resistance change of the memristor exceeds the set resistance change threshold, the protection mechanism is triggered. Adaptive protection: Set up an adaptive control algorithm based on memristor, implement dynamic adjustment of power system parameters according to the resistance change of memristor and the real-time status of the power system, and realize adaptive protection of the power system; Intelligent control: Integrate an intelligent control unit with a microcontroller or a programmable logic chip (FPGA) into the power supply system, combine the fault detection circuit with a memristor with the microcontroller or the programmable logic chip (FPGA), and use the resistance change characteristics of the memristor. The intelligent control unit sets the control logic through software to achieve intelligent control of the power supply system; Parameter optimization: Set up a high-frequency circuit connected to the fault detection circuit. According to the load changes of the power supply system, use the high-frequency characteristics of the memristor in the fault detection circuit to dynamically adjust the resistance value of the memristor to optimize the high-frequency performance of the power supply.

[0013] Preferably, the intelligent control includes: Construct a memristor state model using the following memristor state formula: In the above formula, represents the state function of the memristor; express The state of the memristor at that moment; express The current at the moment; and is the characteristic parameter of the memristor; Using the state of the memristor As a feedback signal, the error signal is obtained by comparing it with the set target output value. ; According to the state of the memristor and error signal , the control signal is obtained using the following calculation formula: In the above formula, Indicates control signal; Indicates time; and represent the gain factors of proportional, integral, differential and memristor state feedback respectively; The intelligent control unit obtains the control signal and implements intelligent control of the power supply system according to the control signal.

[0014] According to another aspect of the present invention, a pulse power system parameter selection system is provided, which is used to implement a pulse power system parameter selection method as described above, comprising: Data acquisition module, used to collect historical data of pulse power system status based on big data; Data processing module, used for cleaning, normalizing and integrating the historical data of pulse power system status based on big data; Model training module, used to train the optimal pulse power system parameter selection numerical model based on deep learning technology; A parameter selection module, used for selecting optimal pulse power system parameters based on an optimal pulse power system parameter selection numerical model; The interface display module is used to provide a user interface and display the optimal pulse power system parameters to the user in a visual form.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention determines the pulse power system status historical data based on big data by collecting the energy output, pulse frequency, duty cycle, pulse width and voltage and current historical data of the pulse power system, cleans, normalizes and integrates the pulse power system status historical data based on big data, and safely stores and backs up the integrated pulse power system status historical data. Based on deep learning technology, the intrinsic relationship between pulse power system parameter selection and energy output is actively learned, and the optimal pulse power system parameter selection numerical model is trained. According to the user's energy output demand for the pulse power system, the pulse power system parameters are predicted and analyzed based on the optimal pulse power system parameter selection numerical model. The pulse power system parameters are adjusted online and adaptively adjusted to select the optimal pulse power system parameters. The pulse power system parameters can be flexibly selected according to user needs, the use effect of the pulse power system is improved, and the performance and reliability of the pulse power system are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flow chart of a method for selecting parameters of a pulse power supply system of the present invention; Figure 2 It is a module diagram of the pulse power system parameter selection system of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] In order to solve the problem that the existing pulse power system parameters cannot be flexibly selected according to user needs, resulting in poor use of the pulse power system and reduced performance and reliability of the pulse power system, please refer to Figure 1-Figure 2 , this embodiment provides the following technical solutions: A method for selecting parameters of a pulse power supply system comprises the following steps: S1. Data collection: Collect the energy output, pulse frequency, duty cycle, pulse width and voltage and current historical data of the pulse power supply system, and determine the pulse power supply system status historical data based on big data; In this embodiment, the historical data of the pulse power system status based on big data is collected, including: Based on the pulse power system history database, the energy output history of the pulse power system is collected to obtain the energy output history data of the pulse power system; Based on the pulse power system history database, the pulse frequency history of the pulse power system is collected to obtain the pulse frequency history data of the pulse power system; Based on the pulse power system history database, the duty cycle history of the pulse power system is collected to obtain the duty cycle history data of the pulse power system; Based on the pulse power system history database, the pulse width history of the pulse power system is collected to obtain the pulse width history data of the pulse power system; Based on the pulse power system history database, the voltage and current history of the pulse power system is collected to obtain the voltage and current history data of the pulse power system; Among them, based on the pulse power supply system energy output historical data, the pulse power supply system pulse frequency historical data, the pulse power supply system duty cycle historical data, the pulse power supply system pulse width historical data and the pulse power supply system voltage and current historical data, the pulse power supply system status historical data based on big data is determined.

[0019] S2. Data processing: cleaning, normalizing and integrating the pulse power system status historical data based on big data, and safely storing and backing up the integrated pulse power system status historical data; In this embodiment, the pulse power system status historical data based on big data is processed, including: Clean the historical data of pulse power system status based on big data based on data cleaning tools; Among them, checking and identifying duplicate values, missing values ​​and abnormal values ​​in the pulse power system status historical data based on big data, and processing the duplicate values, missing values ​​and abnormal values ​​in the pulse power system status historical data based on big data; For duplicate values, delete them directly; for missing values, delete the data records containing missing values ​​or use the average value to replace the missing values; for outliers, delete the data records containing outliers or use the median to replace outliers; Based on the ‌Z-score standardization method, the pulse power system status historical data based on big data is normalized to unify the pulse power system status historical data based on big data, remove the dimensional differences between the pulse power system status historical data based on big data, and determine the standardized pulse power system status historical data; The standardized pulse power supply system status historical data is integrated and processed, and the standardized pulse power supply system status historical data is integrated into a unified data view, and the integrated pulse power supply system status historical data is checked to check whether the integrated pulse power supply system status historical data is missing. After passing the inspection, the integrated pulse power supply system status historical data is securely stored and backed up.

[0020] S3, Model training: Based on deep learning technology, actively learn the intrinsic relationship between pulse power system parameter selection and energy output, and train the optimal pulse power system parameter selection numerical model; In this embodiment, training an optimal pulse power system parameter selection numerical model includes: Dividing the pulse power system state historical data into a training set and a test set; Based on deep learning technology, the deep learning model is trained with a training set, so that the deep learning model actively learns the intrinsic relationship between the pulse power system parameter selection and energy output, and then trains the pulse power system parameter selection numerical model; Based on the test set, the performance test of the numerical model for selecting the parameters of the pulse power supply system is carried out to determine whether the numerical model for selecting the parameters of the pulse power supply system can achieve the expected effect; When the pulse power system parameter selection numerical model cannot achieve the expected effect, the parameters and structure of the pulse power system parameter selection numerical model are adjusted, and the adjusted pulse power system parameter selection numerical model is continuously iterated and optimized to determine the optimal pulse power system parameter selection numerical model.

[0021] S4, parameter selection: according to the user's energy output requirements for the pulse power system, the optimal pulse power system parameters are selected based on the optimal pulse power system parameter selection numerical model; In this embodiment, the optimal pulse power system parameters are selected, including: Obtain the optimal pulse power system parameter selection numerical model, and deploy the optimal pulse power system parameter selection numerical model in the actual pulse power system parameter selection environment; According to the user's demand for the energy output of the pulse power supply system, the pulse power supply system parameters are predicted and analyzed based on the optimal pulse power supply system parameter selection numerical model. The optimal pulse power supply system parameters are selected by online adjustment and adaptive regulation of the pulse power supply system parameters.

[0022] It should be noted that the adaptive adjustment of the pulse power supply system parameters based on the model predictive control method can achieve precise control of the behavior of the pulse power supply system by predicting the state and input signal of the pulse power supply system and adjusting its parameters online.

[0023] S5. Interface display: Display the optimal pulse power system parameters to the user in a visual form.

[0024] In this embodiment, the optimal pulse power system parameters are displayed to the user, including: Provide a user interface to display the optimal pulse power system parameters to users in a visual form, and track the user's pulse power system usage in real time, obtain user feedback and parameter selection test results, and continuously adjust and optimize the pulse power system parameters based on user feedback and parameter selection test results to make it better adapt to different scenarios and user needs.

[0025] Based on the above embodiment, the pulse power system parameter selection method further includes: Fault detection: A fault detection circuit with a memristor is set up to sense power system faults using the resistance change characteristics of the memristor. When the resistance change of the memristor exceeds the set resistance change threshold, the protection mechanism is triggered. Adaptive protection: Set up an adaptive control algorithm based on memristor, implement dynamic adjustment of power system parameters according to the resistance change of memristor and the real-time status of the power system, and realize adaptive protection of the power system; Intelligent control: Integrate an intelligent control unit with a microcontroller or a programmable logic chip (FPGA) into the power supply system, combine the fault detection circuit with a memristor with the microcontroller or the programmable logic chip (FPGA), and use the resistance change characteristics of the memristor. The intelligent control unit sets the control logic through software to achieve intelligent control of the power supply system; Parameter optimization: Set up a high-frequency circuit connected to the fault detection circuit. According to the load changes of the power supply system, use the high-frequency characteristics of the memristor in the fault detection circuit to dynamically adjust the resistance value of the memristor to optimize the high-frequency performance of the power supply.

[0026] Specifically, by using a nonlinear element with memory characteristics, such as a memristor, its resistance value can be dynamically changed according to the amount of charge passing through the memristor. This characteristic makes memristors have great potential in the intelligent control of power systems. Traditional power control systems usually rely on fixed PID controllers or digital signal processors (DSPs), which are difficult to cope with complex and changing load conditions and environmental interference. The introduction of memristors can achieve more efficient and flexible adaptive control through their dynamic resistance characteristics and memory capabilities. This solution dynamically adjusts the output of the power system through the real-time state feedback and adaptive algorithm of the memristor, improving the stability, efficiency and response speed of the power system; this solution can be applied to a variety of scenarios such as DC-DC converters, AC-DC power supplies, and battery management systems.

[0027] Based on the above embodiment, the intelligent control includes: Construct a memristor state model using the following memristor state formula: In the above formula, represents the state function of the memristor; express The state of the memristor at that moment; express The current at the moment; and is the characteristic parameter of the memristor; Using the state of the memristor As a feedback signal, the error signal is obtained by comparing it with the set target output value. ; According to the state of the memristor and error signal , the control signal is obtained using the following calculation formula: In the above formula, Indicates control signal; Indicates time; and represent the gain factors of proportional, integral, differential and memristor state feedback respectively; The intelligent control unit obtains the control signal and implements intelligent control of the power supply system according to the control signal.

[0028] Specifically, dynamic and adaptive control is achieved by introducing memristor state feedback; the adjustment accuracy and response speed of the system are significantly improved through the design of the memristor array; combined with the control signal algorithm that takes the error signal into consideration, dynamic optimization of the control parameters is achieved, improving the adaptability and robustness of the system; the global stability of the system is ensured, avoiding the oscillation and divergence problems common in traditional control systems; this scheme uses the dynamic resistance characteristics and memory capacity of the memristor to construct a closed-loop feedback control system, and the state of the memristor is As a feedback signal, it is compared with the target output value and the resistance value of the memristor is dynamically adjusted through an adaptive algorithm, thereby achieving precise control of the power supply output.

[0029] In order to better demonstrate the pulse power system parameter selection principle, this embodiment provides a pulse power system parameter selection system, which is used to implement a pulse power system parameter selection method as described above, including: Data acquisition module, used to collect historical data of pulse power system status based on big data; Data processing module, used for cleaning, normalizing and integrating the historical data of pulse power system status based on big data; Model training module, used to train the optimal pulse power system parameter selection numerical model based on deep learning technology; A parameter selection module, used for selecting optimal pulse power system parameters based on an optimal pulse power system parameter selection numerical model; The interface display module is used to provide a user interface and display the optimal pulse power system parameters to the user in a visual form.

[0030] It should be noted that the energy output, pulse frequency, duty cycle, pulse width and voltage and current historical data of the pulse power supply system are collected through the data acquisition module to determine the pulse power supply system status historical data based on big data. The pulse power supply system status historical data based on big data is cleaned, normalized and integrated through the data processing module, and the integrated pulse power supply system status historical data is safely stored and backed up. The intrinsic relationship between the pulse power supply system parameter selection and energy output is actively learned through the model training module, and the optimal pulse power supply system parameter selection numerical model is trained. The parameter selection module predicts and analyzes the pulse power supply system parameters based on the optimal pulse power supply system parameter selection numerical model according to the user's energy output requirements for the pulse power supply system. The pulse power supply system parameters are adjusted online and adaptively adjusted to select the optimal pulse power supply system parameters. The pulse power supply system parameters can be flexibly selected according to user needs, the use effect of the pulse power supply system is improved, and the performance and reliability of the pulse power supply system are improved.

[0031] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0032] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for selecting parameters of a pulse power supply system, characterized in that: The steps include: S1. Data collection: Collect the energy output, pulse frequency, duty cycle, pulse width and voltage and current historical data of the pulse power supply system, and determine the pulse power supply system status historical data based on big data; S2. Data processing: cleaning, normalizing and integrating the pulse power system status historical data based on big data, and safely storing and backing up the integrated pulse power system status historical data; S3, Model training: Based on deep learning technology, actively learn the intrinsic relationship between pulse power system parameter selection and energy output, and train the optimal pulse power system parameter selection numerical model; S4, parameter selection: according to the user's energy output requirements for the pulse power system, the optimal pulse power system parameters are selected based on the optimal pulse power system parameter selection numerical model; S5. Interface display: Display the optimal pulse power system parameters to the user in a visual form.

2. A pulse power system parameter selection method as claimed in claim 1, characterized in that: In S1, historical data of the pulse power system status based on big data is collected, including: Based on the pulse power system history database, the energy output history of the pulse power system is collected to obtain the energy output history data of the pulse power system; Based on the pulse power system history database, the pulse frequency history of the pulse power system is collected to obtain the pulse frequency history data of the pulse power system; Based on the pulse power system history database, the duty cycle history of the pulse power system is collected to obtain the duty cycle history data of the pulse power system; Based on the pulse power system history database, the pulse width history of the pulse power system is collected to obtain the pulse width history data of the pulse power system; Based on the pulse power system history database, the voltage and current history of the pulse power system is collected to obtain the voltage and current history data of the pulse power system; Among them, based on the pulse power supply system energy output historical data, the pulse power supply system pulse frequency historical data, the pulse power supply system duty cycle historical data, the pulse power supply system pulse width historical data and the pulse power supply system voltage and current historical data, the pulse power supply system status historical data based on big data is determined.

3. A pulse power system parameter selection method as claimed in claim 2, characterized in that: In S2, the pulse power system status historical data based on big data is processed, including: Clean the historical data of pulse power system status based on big data based on data cleaning tools; Among them, checking and identifying duplicate values, missing values ​​and abnormal values ​​in the pulse power system status historical data based on big data, and processing the duplicate values, missing values ​​and abnormal values ​​in the pulse power system status historical data based on big data; For duplicate values, delete them directly; for missing values, delete the data records containing missing values ​​or use the mean value to replace the missing values; for outliers, delete the data records containing outliers or use the median to replace outliers.

4. A pulse power system parameter selection method as claimed in claim 3, characterized in that: In the above S2, the historical data of the pulse power system state based on big data is processed, and further includes: Based on the ‌Z-score standardization method, the pulse power system status historical data based on big data is normalized to unify the pulse power system status historical data based on big data, remove the dimensional differences between the pulse power system status historical data based on big data, and determine the standardized pulse power system status historical data; The standardized pulse power supply system status historical data is integrated and processed, and the standardized pulse power supply system status historical data is integrated into a unified data view, and the integrated pulse power supply system status historical data is checked to check whether the integrated pulse power supply system status historical data is missing. After passing the inspection, the integrated pulse power supply system status historical data is securely stored and backed up.

5. A pulse power system parameter selection method as claimed in claim 4, characterized in that: In S3, training an optimal pulse power system parameter selection numerical model includes: Dividing the pulse power system state historical data into a training set and a test set; Based on deep learning technology, the deep learning model is trained with a training set, so that the deep learning model actively learns the intrinsic relationship between the pulse power system parameter selection and energy output, and then trains the pulse power system parameter selection numerical model; Based on the test set, the performance test of the numerical model for selecting the parameters of the pulse power supply system is carried out to determine whether the numerical model for selecting the parameters of the pulse power supply system can achieve the expected effect; When the pulse power system parameter selection numerical model cannot achieve the expected effect, the parameters and structure of the pulse power system parameter selection numerical model are adjusted, and the adjusted pulse power system parameter selection numerical model is continuously iterated and optimized to determine the optimal pulse power system parameter selection numerical model.

6. A pulse power system parameter selection method as claimed in claim 5, characterized in that: In S4, the optimal pulse power system parameters are selected, including: Obtain the optimal pulse power system parameter selection numerical model, and deploy the optimal pulse power system parameter selection numerical model in the actual pulse power system parameter selection environment; According to the user's demand for the energy output of the pulse power supply system, the pulse power supply system parameters are predicted and analyzed based on the optimal pulse power supply system parameter selection numerical model. The optimal pulse power supply system parameters are selected by online adjustment and adaptive regulation of the pulse power supply system parameters.

7. A pulse power system parameter selection method as claimed in claim 6, characterized in that: In S5, the optimal pulse power system parameters are displayed to the user, including: Provide a user interface to display the optimal pulse power system parameters to users in a visual form, and track the user's pulse power system usage in real time, obtain user feedback and parameter selection test results, and continuously adjust and optimize the pulse power system parameters based on user feedback and parameter selection test results to make it better adapt to different scenarios and user needs.

8. A pulse power system parameter selection method as claimed in claim 1, characterized in that: Also includes: Fault detection: A fault detection circuit with a memristor is set up to sense power system faults using the resistance change characteristics of the memristor. When the resistance change of the memristor exceeds the set resistance change threshold, the protection mechanism is triggered. Adaptive protection: Set up an adaptive control algorithm based on memristor, implement dynamic adjustment of power system parameters according to the resistance change of memristor and the real-time status of the power system, and realize adaptive protection of the power system; Intelligent control: Integrate an intelligent control unit with a microcontroller or programmable logic chip into the power supply system, combine the fault detection circuit with a memristor with the microcontroller or programmable logic chip, and use the resistance change characteristics of the memristor. The intelligent control unit sets the control logic through software to achieve intelligent control of the power supply system; Parameter optimization: Set up a high-frequency circuit connected to the fault detection circuit. According to the load changes of the power supply system, use the high-frequency characteristics of the memristor in the fault detection circuit to dynamically adjust the resistance value of the memristor to optimize the high-frequency performance of the power supply.

9. A pulse power system parameter selection method as claimed in claim 8, characterized in that: The intelligent control comprises: Construct a memristor state model using the following memristor state formula: In the above formula, represents the state function of the memristor; express The state of the memristor at that moment; express The current at the moment; and is the characteristic parameter of the memristor; Using the state of the memristor As a feedback signal, the error signal is obtained by comparing it with the set target output value. ; According to the state of the memristor and error signal , the control signal is obtained using the following calculation formula: In the above formula, Indicates control signal; Indicates time; and represent the gain factors of proportional, integral, differential and memristor state feedback respectively; The intelligent control unit obtains the control signal and implements intelligent control of the power supply system according to the control signal.

10. A pulse power system parameter selection system, used to implement a pulse power system parameter selection method as claimed in any one of claims 1 to 9, characterized in that: include: Data acquisition module, used to collect historical data of pulse power system status based on big data; Data processing module, used for cleaning, normalizing and integrating the historical data of pulse power system status based on big data; Model training module, used to train the optimal pulse power system parameter selection numerical model based on deep learning technology; A parameter selection module, used for selecting optimal pulse power system parameters based on an optimal pulse power system parameter selection numerical model; The interface display module is used to provide a user interface and display the optimal pulse power system parameters to the user in a visual form.

Images