A method, device and equipment for determining operating characteristic parameters of a Hall thruster

Abstract

This application provides a method, apparatus, and device for determining the operating characteristic parameters of a Hall thruster, relating to the field of Hall thruster control technology. The method includes: acquiring target operating parameters of the Hall thruster; inputting the target operating parameters into a pre-trained Hall thruster discharge oscillation prediction model to predict the time series data of the Hall thruster's operating parameters and the spatiotemporal distribution data of plasma in the Hall thruster's channel under the target operating parameters; wherein the Hall thruster discharge oscillation prediction model is trained using multiple historical simulation data; and analyzing the time series data and spatiotemporal distribution data of the operating parameters to obtain the operating characteristic parameters. This application can accurately and efficiently predict the time series data of the Hall thruster's operating parameters and the spatiotemporal distribution data of plasma, and extract accurate and reliable macroscopic and microscopic characteristic parameters.

Description

Technical Field

[0001] This application relates to the field of Hall thruster control technology, and more specifically, to a method, apparatus, and equipment for determining the operating characteristic parameters of a Hall thruster. Background Technology

[0002] There are two main types of models currently used for simulating Hall thrusters: one-dimensional quasi-neutral fluid models and their improved versions, and three-dimensional particle simulation models.

[0003] The one-dimensional quasi-neutral fluid model assumes that the plasma is electrically neutral on a macroscopic scale and that charged and neutral particles behave similarly. It considers the plasma's continuity, momentum, and energy equations to describe the temporal and spatial variations of macroscopic physical quantities such as density, velocity, and temperature under thruster operating conditions. While this model can simulate variations in thruster operating parameters, including the effects of magnetic field, discharge voltage, propellant flow rate, and pre-ionization rate on the amplitude and frequency of low-frequency discharge current oscillations, it suffers from limitations. It requires additional assumptions, cannot accurately obtain the plasma characteristics causing discharge oscillations or the microscopic influence of operating parameters on these oscillations, cannot predict discharge parameters, and cannot provide plasma distribution data.

[0004] The improved one-dimensional quasi-neutral fluid model treats plasma as a continuous medium, failing to capture the specific dynamics between microscopic particles. This results in inaccurate simulations when dealing with microscopic scales or describing inter-particle interactions. While it can explain the breathing oscillations to some extent, it requires additional assumptions, cannot self-consistently solve for the breathing oscillation behavior of plasma within the Hall thruster, and the assumption that electrons are distributed according to Maxwell's distribution within the Hall thruster is not always valid. Therefore, the results obtained contain significant errors and lack accuracy.

[0005] Three-dimensional particle simulation models require a large amount of computing resources to simulate particle motion, have high requirements for the simulation environment, and have long simulation running time. In addition, only one set of results can be obtained in a single simulation, resulting in low simulation efficiency. Although they can provide high-precision and high-resolution simulation physical information results, they also introduce a lot of unnecessary complexity and consume a lot of computing power and time costs. This is not worthwhile compared to the simulation effect of the Hall thruster breathing oscillation behavior obtained by the model. Summary of the Invention

[0006] The purpose of this application is to provide a method, apparatus, and device for determining the operating characteristic parameters of a Hall thruster, thereby solving the above-mentioned problems existing in the prior art. It can efficiently, accurately, and quickly extract time series data of predicted Hall thruster operating parameters and spatiotemporal distribution data of plasma in the channel, and extract discharge oscillation characteristic parameters.

[0007] Firstly, a method for determining the operating characteristic parameters of a Hall thruster is provided, the method including:

[0008] Obtain the target operating parameters of the Hall thruster;

[0009] The target operating condition parameters are input into a pre-trained Hall thruster discharge oscillation prediction model to predict the time series data of the operating parameters of the Hall thruster under the target operating condition parameters and the spatiotemporal distribution data of the plasma in the channel of the Hall thruster.

[0010] The Hall thruster discharge oscillation prediction model is trained using multiple historical simulation data; any historical simulation data includes: historical operating parameters, corresponding historical operating parameter time series data, and corresponding historical spatiotemporal distribution data.

[0011] The working parameter time series data and the spatiotemporal distribution data are analyzed to obtain the working characteristic parameters.

[0012] In an optional implementation, the target operating parameters include: the channel configuration, channel size, and wall material type of the Hall thruster, as well as the applied electric field parameters, magnetic field parameters, and cathode discharge current of the Hall thruster, and the type and flow rate of the neutral gas input into the Hall thruster;

[0013] The operating parameter time series data includes: discharge current time series data, thrust time series data, and physical field time series data;

[0014] The spatiotemporal distribution data of the plasma includes: particle density spatiotemporal distribution data, electron temperature axial spatiotemporal distribution data, and ion temperature axial spatiotemporal distribution data.

[0015] In an optional implementation, the time series data of the working parameters and the spatiotemporal distribution data are analyzed to obtain working characteristic parameters, including:

[0016] The first operating characteristic parameter is obtained by analyzing the discharge current time series data and the thrust time series data; wherein, the first operating characteristic parameter includes: the oscillation period of the discharge oscillation;

[0017] Extract the target physical field time series data and the target spatiotemporal distribution data within one oscillation period from the physical field time series data and the spatiotemporal distribution data, respectively.

[0018] The time series data of the target physical field are analyzed to obtain the changing trend of the physical field within one oscillation period;

[0019] The spatiotemporal distribution data of the target are analyzed to obtain the second working characteristic parameters; wherein, the second working characteristic parameters include: the variation trend of particle density within one oscillation cycle, the variation trend of electron temperature within one oscillation cycle, and the variation trend of ion temperature within one oscillation cycle;

[0020] The first working characteristic parameter, the changing trend of the physical field within one oscillation period, and the second working characteristic parameter are determined as the working characteristic parameters.

[0021] In an optional implementation, the discharge current time series data and thrust time series data are analyzed to obtain the first operating characteristic parameters, including:

[0022] Multiple first peak values ​​and first valley values ​​are extracted from the discharge current time series data;

[0023] Based on the extracted first peak values, the oscillation period of the discharge oscillation is determined;

[0024] Multiple second peak values ​​and second valley values ​​are extracted from the thrust time series data;

[0025] The first peak value, the first valley value, the second peak value, the second valley value, and the oscillation period are determined as the first working characteristic parameters.

[0026] In an optional implementation, the method further includes, before obtaining the target operating parameters of the Hall thruster:

[0027] Construct a one-dimensional full-particle numerical simulation model of the Hall thruster.

[0028] In an optional implementation, the method for obtaining the historical simulation data includes:

[0029] Retrieve multiple historical operating condition parameters configured;

[0030] For any historical operating condition parameter, the historical operating condition parameter is input into the one-dimensional full-particle numerical simulation model to perform discharge simulation, thereby obtaining the historical operating parameter time series data and the corresponding historical spatiotemporal distribution data.

[0031] In an optional implementation, the Hall thruster discharge oscillation prediction model includes:

[0032] The input layer is used to receive target operating condition parameters;

[0033] The feature embedding layer is used to extract features from the input target operating condition parameters to obtain a feature vector sequence and a first oscillation period;

[0034] The time series prediction layer is used to predict the time series of particle count and ionization rate within a preset time window based on the feature vector sequence input from the feature embedding layer; wherein the time length of the preset time window is greater than the first oscillation period.

[0035] The spatiotemporal distribution prediction layer is used to predict the spatiotemporal distribution data of plasma within a preset time window based on the feature vector sequence and the time series of particle numbers.

[0036] The working parameter prediction layer is used to predict the working parameter time series data within a preset time window based on the feature vector sequence, ionization rate time series, and particle density spatiotemporal distribution data.

[0037] The periodic verification layer is used to extract the second oscillation period, the third oscillation period, and the fourth oscillation period based on the time series of particle counts, the spatiotemporal distribution data of plasma, and the time series data of working parameters within a preset time window, respectively.

[0038] The output layer is used to output time series data of the operating parameters of the Hall thruster under the target operating conditions and spatiotemporal distribution data of the plasma in the channel of the Hall thruster when the difference between the first oscillation period, the second oscillation period, the third oscillation period and the fourth oscillation period is less than the configured threshold.

[0039] Secondly, a device for determining the operating characteristic parameters of a Hall thruster is provided, the device may include:

[0040] Acquisition unit, used to acquire target operating condition parameters of Hall thruster;

[0041] The prediction unit is used to input the target operating condition parameters into a pre-trained Hall thruster discharge oscillation prediction model to predict the time series data of the operating parameters of the Hall thruster under the target operating condition parameters and the spatiotemporal distribution data of the plasma in the channel of the Hall thruster; wherein, the Hall thruster discharge oscillation prediction model is trained using multiple historical simulation data; any historical simulation data includes: historical operating condition parameters and corresponding historical operating parameter time series data and corresponding historical spatiotemporal distribution data;

[0042] The analysis unit is used to analyze the time series data of the working parameters and the spatiotemporal distribution data to obtain the working characteristic parameters.

[0043] Thirdly, an electronic device is provided, which includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0044] Memory, used to store computer programs;

[0045] When a processor executes a program stored in memory, it implements any of the steps described in the first aspect above.

[0046] Fourthly, a computer-readable storage medium is provided, wherein a computer program is stored therein, and when executed by a processor, the computer program implements the steps of any of the methods described in the first aspect above.

[0047] This application utilizes a Hall thruster discharge oscillation prediction model to capture the nonlinear chaotic state inside the thruster during operation, simulating the relationship between target operating parameters and real-time plasma characteristics within the Hall thruster channel, thereby enabling the prediction of the motion behavior of each particle within the thruster over a future period. The Hall thruster discharge oscillation prediction model of this application employs a deep neural network, which can simulate complex plasma dynamics, improve prediction accuracy, and reduce computational requirements. Furthermore, as the amount of data increases, the model can continuously learn and optimize based on experience, obtaining the influence law of various factors on the axial breathing mode of the Hall thruster, thereby enabling the prediction of the motion state of each particle, and using this to regulate the operating parameters of the Hall thruster, thereby improving the thruster's performance and stability.

[0048] The one-dimensional full-particle numerical simulation model of this application can self-consistently solve the motion state of plasma in the channel, ensuring the accuracy and reliability of the simulation. At the same time, it provides an accurate and reliable dataset, and uses this dataset to train the Hall thruster discharge oscillation prediction model. While ensuring accuracy, it solves the pain points of high computing power requirements and long simulation time of particle models.

[0049] This application reveals the discharge oscillation mechanism and the influence mechanism of various operating parameters on the operating characteristic parameters, enabling the prediction of the plasma motion inside the thruster over a period of time. This has good application prospects in the prediction of Hall thruster performance indicators and real-time operation control.

[0050] The Hall thruster discharge oscillation prediction model of this application predicts the working parameter time series data and plasma spatiotemporal distribution data through multiple prediction layers. This not only makes the prediction more accurate, but also keeps the microscopic and macroscopic characteristics of the particles consistent, resulting in more realistic and reliable prediction results.

[0051] Amplitude, period, peak value, and trough value;

[0052] The smaller the amplitude, the closer the peak and trough values ​​are, the better; Attached Figure Description

[0053] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 A flowchart illustrating a method for determining the operating characteristic parameters of a Hall thruster, provided in an embodiment of this application;

[0055] Figure 2 A schematic diagram of a device for determining the working characteristic parameters of a Hall thruster provided in an embodiment of this application;

[0056] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0057] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0058] The method for determining the operating characteristic parameters of a Hall thruster provided in this application can be applied to a server or a terminal with strong computing power. The server can be a physical server, a server cluster composed of multiple physical servers, or a distributed system. It can also be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. The terminal can be a user equipment (UE) such as a mobile phone, smartphone, laptop, digital radio receiver, personal digital assistant (PDA), tablet computer (PAD), handheld device, in-vehicle device, wearable device, computing device, or other processing device connected to a wireless modem, mobile station (MS), mobile terminal, etc. The terminal and server can be directly or indirectly connected via wired or wireless communication methods, which is not limited herein.

[0059] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Furthermore, the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0060] Figure 1 This is a flowchart illustrating a method for determining the operating characteristic parameters of a Hall thruster, as provided in an embodiment of this application. Figure 1 As shown, the method may include:

[0061] Step S110: Obtain the target operating parameters of the Hall thruster; input the target operating parameters into the pre-trained Hall thruster discharge oscillation prediction model to predict the time series data of the operating parameters of the Hall thruster under the target operating parameters and the spatiotemporal distribution data of the plasma in the channel of the Hall thruster.

[0062] In this embodiment, the target operating parameters include: the channel configuration, channel size, and wall material type of the Hall thruster, as well as the applied electric field parameters, magnetic field parameters, cathode discharge current, and the type and flow rate of neutral gas input into the Hall thruster.

[0063] In this embodiment of the application, the Hall thruster discharge oscillation prediction model is trained using multiple historical simulation data; any historical simulation data includes: historical operating condition parameters and corresponding historical operating parameter time series data and corresponding historical spatiotemporal distribution data.

[0064] In this embodiment, the time series data of the working parameters includes: discharge current time series data, thrust time series data, and physical field time series data; the spatiotemporal distribution data of the plasma includes: particle density spatiotemporal distribution data, electron temperature axial spatiotemporal distribution data, and ion temperature axial spatiotemporal distribution data; wherein, the particle density spatiotemporal distribution data includes: electron density spatiotemporal distribution data, ion density spatiotemporal distribution data, and atomic density spatiotemporal distribution data.

[0065] In this embodiment, the Hall thruster discharge oscillation prediction model employs a multi-task learning deep neural network, which can quickly simulate parameters such as current during thruster operation based on set environmental conditions and operating parameters. This significantly improves simulation efficiency and decouples the complex relationship between thruster performance and various input parameters, addressing the pain points of high platform computing power requirements and long simulation execution time for full particle models. Simultaneously, the multi-task learning deep neural network can predict multiple types of data at the same time. By sharing underlying feature inputs, it can help the Hall thruster discharge oscillation prediction model better extract common features across tasks, improving the model's generalization ability.

[0066] In this embodiment of the application, the Hall thruster discharge oscillation prediction model includes:

[0067] The input layer is used to receive target operating condition parameters;

[0068] The feature embedding layer is used to extract features from the input target operating condition parameters to obtain a feature vector sequence and a first oscillation period;

[0069] The time series prediction layer is used to predict the time series of particle count and ionization rate within a preset time window based on the feature vector sequence input from the feature embedding layer; wherein the time length of the preset time window is greater than the first oscillation period.

[0070] The spatiotemporal distribution prediction layer is used to predict the spatiotemporal distribution data of plasma within a preset time window based on the feature vector sequence and the time series of particle numbers.

[0071] The working parameter prediction layer is used to predict the working parameter time series data within a preset time window based on the feature vector sequence, ionization rate time series, and particle density spatiotemporal distribution data.

[0072] The periodic verification layer is used to extract the second oscillation period, the third oscillation period, and the fourth oscillation period based on the time series of particle counts, the spatiotemporal distribution data of plasma, and the time series data of working parameters within a preset time window, respectively.

[0073] The output layer is used to output time series data of the operating parameters of the Hall thruster under the target operating conditions and spatiotemporal distribution data of the plasma in the channel of the Hall thruster when the difference between the first oscillation period, the second oscillation period, the third oscillation period and the fourth oscillation period is less than the configured threshold.

[0074] In this embodiment of the application, the periodic verification layer is further used for:

[0075] When the difference between the first, second, third, and fourth oscillation periods is not less than the configured threshold, the average oscillation period is calculated based on the first, second, third, and fourth oscillation periods. Feedback results are generated based on the differences between the first, second, third, fourth, and average oscillation periods. The feedback results are then sent to the feature embedding layer, time series prediction layer, spatiotemporal distribution prediction layer, and working parameter prediction layer, respectively, so that the feature embedding layer, time series prediction layer, spatiotemporal distribution prediction layer, and working parameter prediction layer can re-extract or predict features based on the feedback results and corresponding inputs to obtain new output data and new oscillation periods, until the difference between the obtained oscillation periods is less than the configured threshold.

[0076] In this embodiment, the period verification layer compares and verifies the oscillation period obtained by direct training and prediction of the feature embedding layer with the oscillation period obtained by prediction of the time series prediction layer, the spatiotemporal distribution prediction layer, and the working parameter prediction layer. Through feedback adjustment, the oscillation period obtained by the aforementioned prediction model reaches a certain accuracy range and is equal to that of the prediction model, thereby ensuring the accuracy of the model prediction results and significantly improving the reliability and dynamic adaptability of the prediction model.

[0077] In this embodiment, based on the feature vector sequence extracted by the feature embedding layer, a time series of particle numbers of electrons, ions, and atoms is generated by the time series prediction layer. The particle number sequence is extracted from the particle number time series (removing explicit time features; the training model extracts the implicit oscillation period through the number sequence, providing a basis for judgment for the period comparison verification layer). The particle number time series and the feature vector sequence are used as input parameters of the spatiotemporal distribution prediction layer. The spatiotemporal distribution sequence of particle density of electrons, ions, and atoms is generated by the spatiotemporal distribution prediction layer. The density spatial distribution sequence is extracted from the particle density spatiotemporal distribution sequence (removing explicit time features; the training model extracts the implicit oscillation period through the number density sequence, providing a basis for judgment for the period comparison verification layer). The density spatial distribution sequence and the feature vector sequence are used as input parameters of the working parameter prediction layer.

[0078] In the embodiments of this application, the Hall thruster discharge oscillation prediction model can output time series data of working parameters and spatiotemporal distribution data of plasma within one oscillation cycle, or it can output time series data of working parameters and spatiotemporal distribution data of plasma within multiple oscillation cycles.

[0079] In the embodiments of this application, the feature embedding layer can first perform appropriate embedding for different types of inputs; for example, for different neutral gas flow rates or electromagnetic field strengths, they can be mapped to a high-dimensional space through the embedding layer, so that the neural network can effectively process a variety of input features.

[0080] In this embodiment, since the discharge parameters of the Hall thruster change dynamically, a time series processing module is needed to predict the time-varying parameters during the discharge process. Multiple LSTM / GRU layers are used to capture the time-varying patterns during the discharge process, and the output time series provides a basis for subsequent analysis. Furthermore, the introduction of a time attention mechanism helps the network focus more on time periods that have a greater impact on the prediction results. This helps improve the modeling ability for both short-term and long-term dependencies.

[0081] In this embodiment, considering the complex spatial distribution of plasma within the thruster channel, a convolutional neural network is used to extract spatial features for the spatiotemporal distribution data of plasma, and combined with time series information to model the spatiotemporal dynamics. By combining the LSTM / GRU of the time series module with the aforementioned spatial module, joint modeling of the plasma spatiotemporal distribution can be achieved.

[0082] In this embodiment, the operating parameter prediction layer, based on the aforementioned predicted discharge parameters and plasma distribution, performs post-processing on the obtained data to estimate the thruster's operating performance (such as thrust, specific impulse, efficiency, etc.). By extracting the aforementioned spatiotemporal features, a fully connected layer is used to map them to the final operating performance evaluation data. This module can output various performance indicators of the thruster.

[0083] In this embodiment, the Hall thruster current oscillation discharge oscillation prediction model incorporates the physical model of the Hall thruster (such as the influence of electric and magnetic fields on particles) during training, introducing physical constraints into the network training process. These physical constraints help the neural network avoid physically unreasonable results during training, thereby improving the accuracy and reliability of predictions. Specifically, this involves adding residual terms from the physical equations to the loss function, which can be expressed as:

[0084] ;

[0085] in, This represents the prediction error term. Representing physical constraint terms, using weighting coefficients λ The effects of the two balancing terms are considered. The prediction error term measures the difference between the model's predicted values ​​and the actual observed values, and is commonly expressed as mean squared error (MSE) or mean absolute error (MAE). The physical constraint term (residual term) measures whether the model's prediction results conform to physical laws. The residuals are calculated using physical equations (such as the effects of electric and magnetic fields on particles) to ensure that the prediction results are physically reasonable.

[0086] In this embodiment, the Hall thruster current oscillation discharge oscillation prediction model employs adaptive learning rate and meta-learning during training. Meta-learning allows a model to learn how to effectively update network parameters. For different operating conditions, the meta-learning method can better adapt to new input conditions, thereby improving the model's flexibility and robustness. Combining the adaptive learning rate method can accelerate the training process and reduce reliance on large amounts of data.

[0087] In this embodiment of the application, the Hall thruster current oscillation prediction model is trained using multiple historical simulation data; specifically, any historical simulation data includes: historical operating parameter time series data and historical spatiotemporal distribution data of plasma characteristic parameters.

[0088] This application uses a Hall thruster current oscillation prediction model to predict macroscopic performance parameters such as discharge and thrust, as well as microscopic plasma characteristic parameters, based on target operating condition parameters. This effectively improves simulation efficiency while maintaining good prediction accuracy. Furthermore, by training the Hall thruster discharge oscillation prediction model with historical simulation data, the model learns the correlation between historical operating condition parameters, corresponding historical operating parameter time series data, and historical spatiotemporal distribution data of plasma characteristic parameters, further improving prediction accuracy and efficiency.

[0089] In this embodiment of the application, before obtaining the target operating condition parameters of the Hall thruster, it is also necessary to construct a one-dimensional full-particle numerical simulation model of the Hall thruster; obtain multiple configured historical operating condition parameters; for any historical operating condition parameter, input the historical operating condition parameter into the one-dimensional full-particle numerical simulation model to perform discharge simulation, and obtain the historical operating parameter time series data and the corresponding historical spatiotemporal distribution data corresponding to the historical operating condition parameter.

[0090] In practical applications, the basic idea of ​​plasma particle simulation is to achieve real-time simulation of the entire discharge development process by tracking the motion and forces acting on charged particles. To reduce computational load, macroparticles are typically used to represent multiple real particles moving together. These particles share common coordinates and velocities, and their charge-to-mass ratio is equal to that of real particles. Particle simulation methods are based on first-principles equations, neglecting fewer aspects of actual physical processes. Therefore, they can most realistically reflect the actual interaction between charged particles and electromagnetic fields, directly simulate the microscopic motion of electrons and ions, capture inter-particle interactions and nonlinear effects, achieve self-consistent solutions to the influence of electric and magnetic fields on plasma, and capture the coupling effect between electromagnetic fields and particle motion.

[0091] In this embodiment of the application, the method for constructing a one-dimensional full-particle numerical simulation model of a Hall thruster includes:

[0092] The channel configuration, channel size, wall material type, applied electric field parameters, magnetic field parameters, cathode discharge current, and neutral gas type and flow rate input into the Hall thruster are obtained. Based on the channel configuration, channel size, and wall material type, an initial one-dimensional full-particle numerical simulation model of the Hall thruster is constructed. Based on the magnetic field parameters, the spatial distribution sequence data of the magnetic field are determined.

[0093] Based on the cathode discharge current, calculate the number of electrons entering the Hall thruster discharge channel in each time step; based on the type of neutral gas input into the Hall thruster, obtain the collision cross-section data corresponding to that type of working fluid from the configured database; based on the flow rate of the neutral gas input into the Hall thruster, calculate the number of atoms and atomic velocity entering the discharge channel in each time step.

[0094] Based on the spatial distribution sequence data of the magnetic field, the parameters of the applied electric field, the number of electrons, the collision cross-section data, the number of atoms, and the atomic velocity, the initial one-dimensional full-particle numerical simulation model is adjusted to obtain the one-dimensional full-particle numerical simulation model of the Hall thruster.

[0095] In another embodiment of this application, the method for constructing a one-dimensional full-particle numerical simulation model of a Hall thruster may further include:

[0096] Obtain the geometric configuration, magnetic field configuration, initial electric field distribution, cathode discharge current, working fluid type, and corresponding working fluid mass flow rate of the Hall thruster; based on the geometric configuration, construct the initial one-dimensional full-particle numerical simulation model of the Hall thruster; based on the magnetic field configuration, determine the spatial distribution sequence data of the magnetic field; based on the initial electric field distribution, determine the electric field parameters.

[0097] Based on the cathode discharge current, calculate the number of electrons entering the Hall thruster discharge channel in each time step; based on the type of working medium, obtain the collision cross-section data corresponding to that type of working medium from the configured database; based on the mass flow rate of the working medium, calculate the number of atoms and atomic velocity entering the discharge channel in each time step.

[0098] Based on the spatial distribution sequence data of the magnetic field, electric field parameters, number of electrons, collision cross-section data, number of atoms, and atomic velocity, the initial one-dimensional full-particle numerical simulation model was adjusted to obtain the one-dimensional full-particle numerical simulation model of the Hall thruster.

[0099] In this embodiment of the application, after obtaining the one-dimensional full-particle numerical simulation model of the Hall thruster, dynamic simulation is performed based on the input historical operating parameters, specifically including:

[0100] Based on the historical cathode discharge current in the historical operating parameters, calculate and allocate the number of electrons entering the discharge channel at each time step; based on the historical neutral gas type and historical flow rate in the input Hall thruster, calculate and allocate the number and velocity of atoms entering the discharge channel at each time step.

[0101] Discharge simulations were performed based on the number of electrons, the number of atoms, and the velocity. The corresponding physical quantities were statistically analyzed and updated on the grid cells of the one-dimensional full-particle numerical simulation model to obtain historical working parameter time series data and corresponding historical spatiotemporal distribution data.

[0102] In the embodiments of this application, the working medium is a specific type of gas or substance used in Hall thrusters, which can be effectively accelerated to generate thrust after ionization; the type of working medium is related to the collision cross section; and is used to calculate the probability of collision between particles, atomic mass, and atomic radius.

[0103] In this embodiment, the magnetic field spatial distribution sequence data remains unchanged during thruster operation (i.e., static magnetic field); the magnetic field spatial distribution sequence data includes, but is not limited to, magnetic field strength, direction, and its three-dimensional spatial distribution within the discharge channel. The initial electric field distribution is the initial electric field distribution sequence data at the start of the Hall thruster; due to the dynamic behavior of electrons and ions, the initial electric field distribution changes in real time. Therefore, the initial electric field distribution sequence data only reflects the electric field state at the start of the thruster.

[0104] In the embodiments of this application, there is a linear relationship between the cathode current and the number of electrons entering the discharge channel, so that the number of electrons at each time step can be accurately determined based on the cathode current.

[0105] In this embodiment of the application, the statistical updating of corresponding physical quantities on the grid cells of the one-dimensional all-particle numerical simulation model includes:

[0106] Based on the collision cross-section data, the plasma reaction was calculated, and the spatiotemporal distribution sequence of atomic numbers was obtained;

[0107] The Monte Carlo Collisions (MCC) method is used to process collisions between electrons, ions, and neutral gases to calculate the probability and frequency of different types of collisions and to update the velocity, energy, and other properties of particles.

[0108] By solving the Poisson equation with finite difference discretization, the spatial distribution sequence of electric potential is calculated, and the corresponding spatiotemporal distribution of electric field, i.e., physical field time series data, is calculated based on the electric potential distribution.

[0109] The particle-in-cell (PIC) discretization method is used, and the Boris method based on Newton's laws of motion is used to drive electrons, ions, and atoms to update their positions and velocities.

[0110] Particle parameters are deposited onto the grid, and the spatiotemporal distributions of particle number density, electron temperature axial spatiotemporal distribution, and ion temperature axial spatiotemporal distribution corresponding to the current time step are statistically obtained.

[0111] The number of electrons reaching the anode boundary at each time step is counted to obtain the discharge current time series data; the number and velocity of ions reaching the cathode boundary at each time step are counted to obtain the thrust time series data.

[0112] In this embodiment of the application, the number and velocity of ions reaching the cathode boundary at each time step are counted to obtain thrust time series data, including:

[0113] Under the action of an electric field, the velocity of the ions after acceleration is calculated; using self-consistent boundary conditions, the number of ions reaching the cathode boundary is counted at each time step; based on the velocity and number of ions, the thrust is calculated to obtain historical thrust time series data.

[0114] In this embodiment of the application, particle parameters are deposited onto a mesh, and the spatiotemporal distributions of particle number density, electron temperature axial spatiotemporal distribution, and ion temperature axial spatiotemporal distribution corresponding to the current time step are statistically obtained, including:

[0115] Based on time-step propulsion of electrons, ions, and atoms, the Boris method (a leapfrog scheme based on Newton's laws of motion) is used to calculate particle acceleration under an electric field and deflection under a magnetic field. The velocity of each particle is calculated based on the force, and the particle's position after one time step is obtained from the particle velocity. Particle parameters are deposited onto a grid using the cloud-in-cell (CIC) method. The time series of particle numbers and the spatiotemporal distribution of particle number density for the current time step are statistically obtained. By statistically calculating the velocities of electrons in each grid corresponding to each time step within the computational domain, the historical temperature axial spatiotemporal distribution data of electrons are obtained. Similarly, by statistically calculating the velocities of ions in each grid corresponding to each time step within the computational domain, the historical temperature axial spatiotemporal distribution data of ions are obtained.

[0116] In this embodiment of the application, the Monte Carlo Collisions (MCC) method is used to handle collisions between electrons, ions, and neutral gas, including:

[0117] Based on the interpolated collision cross-section data, the probability of occurrence of different types of collisions (such as elastic collisions, excitation collisions, ionization collisions, momentum exchange collisions, charge exchange collisions, etc.) in each grid cell is calculated within each time step; the collision frequency is obtained by counting the number of different types of collisions occurring in each time step.

[0118] The Monte Carlo method is used to perform random sampling to determine whether a collision occurs and the specific type of collision; the particle's velocity, energy, and other properties are updated based on the collision type.

[0119] The number of different types of collisions at each time step, especially ionizing collisions, is counted to obtain time series data of ionization rate;

[0120] By statistically analyzing the changes in the number of particles after a collision, we obtain the spatiotemporal distribution data of particle number density for electrons, ions, and neutral atoms.

[0121] By statistically analyzing the velocity distribution of particles after a collision, the spatiotemporal distribution of electron and ion temperatures can be calculated.

[0122] Step S120: Analyze the time series data and spatiotemporal distribution data of the working parameters to obtain the working characteristic parameters.

[0123] In the embodiments of this application, the oscillation period of the discharge oscillation, the first peak value, the first valley value, the second peak value, the second valley value, the change trend of particle density within one oscillation period, the change trend of electron temperature within one oscillation period, and the change trend of ion temperature within one oscillation period are all included. Specifically, the first peak value is the peak value of the discharge oscillation, the first valley value is the valley value of the discharge oscillation, the second peak value is the peak value of the thrust, and the second valley value is the valley value of the thrust.

[0124] In this embodiment of the application, the time series data and spatiotemporal distribution data of the working parameters are analyzed to obtain the working characteristic parameters, including:

[0125] Multiple first peak values ​​and first valley values ​​are extracted from the discharge current time series data; the oscillation period of the discharge oscillation is determined based on the extracted multiple first peak values; multiple second peak values ​​and second valley values ​​are extracted from the thrust time series data; the first peak value, first valley value, second peak value, second valley value and oscillation period are determined as the first working characteristic parameter;

[0126] The target physical field time series data and target spatiotemporal distribution data within one oscillation cycle are extracted from the physical field time series data and target spatiotemporal distribution data, respectively. The target physical field time series data is analyzed to obtain the changing trend of the physical field within one oscillation cycle. The target spatiotemporal distribution data is analyzed to obtain the second working characteristic parameter. The first working characteristic parameter, the changing trend of the physical field within one oscillation cycle, and the second working characteristic parameter are determined as the working characteristic parameters.

[0127] In this embodiment of the application, the second working characteristic parameters include: the variation trend of particle density within one oscillation cycle, the variation trend of electron temperature within one oscillation cycle, and the variation trend of ion temperature within one oscillation cycle.

[0128] Corresponding to the above method, this application also provides a device for determining the operating characteristic parameters of a Hall thruster, such as... Figure 2 As shown, the device for determining the operating characteristic parameters of the Hall thruster includes:

[0129] Acquisition unit 210 is used to acquire the target operating condition parameters of the Hall thruster;

[0130] The prediction unit 220 is used to input the target operating condition parameters into a pre-trained Hall thruster discharge oscillation prediction model to predict the time series data of the Hall thruster's operating parameters under the target operating condition parameters and the spatiotemporal distribution data of the plasma in the Hall thruster's channel. The Hall thruster discharge oscillation prediction model is trained using multiple historical simulation data. Each historical simulation data includes: historical operating condition parameters and corresponding historical operating parameter time series data and corresponding historical spatiotemporal distribution data.

[0131] Analysis unit 230 is used to analyze the time series data and spatiotemporal distribution data of working parameters to obtain working characteristic parameters.

[0132] The functions of each functional unit in the device for determining the working characteristic parameters of the Hall thruster provided in the above embodiments of this application can be implemented through the above method steps. Therefore, the specific working process and beneficial effects of each unit in the device for determining the working characteristic parameters of the Hall thruster provided in the embodiments of this application will not be repeated here.

[0133] This application also provides an electronic device, such as... Figure 3 As shown, it includes a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340.

[0134] Memory 330 is used to store computer programs;

[0135] When the processor 310 executes the program stored in the memory 330, it performs the following steps:

[0136] Obtain the target operating parameters of the Hall thruster;

[0137] The target operating condition parameters are input into a pre-trained Hall thruster discharge oscillation prediction model to predict the time series data of the operating parameters of the Hall thruster under the target operating condition parameters and the spatiotemporal distribution data of the plasma in the channel of the Hall thruster.

[0138] The Hall thruster discharge oscillation prediction model is trained using multiple historical simulation data; any historical simulation data includes: historical operating parameters, corresponding historical operating parameter time series data, and corresponding historical spatiotemporal distribution data.

[0139] The working parameter time series data and the spatiotemporal distribution data are analyzed to obtain the working characteristic parameters.

[0140] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0141] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0142] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0143] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0144] The implementation methods and beneficial effects of the various components of the electronic device in the above embodiments for solving the problem can be found in [reference needed]. Figure 1 The steps in the illustrated embodiments are used to implement the electronic device. Therefore, the specific working process and beneficial effects of the electronic device provided in this application will not be repeated here.

[0145] In another embodiment provided in this application, a computer-readable storage medium is also provided, which stores instructions that, when executed on a computer, cause the computer to perform the method for determining the operating characteristic parameters of any of the Hall thrusters in the above embodiments.

[0146] In another embodiment provided in this application, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute the method for determining the operating characteristic parameters of any of the Hall thrusters in the above embodiments.

[0147] Those skilled in the art will understand that the embodiments in this application can be provided as methods, systems, or computer program products. Therefore, the embodiments in this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments in this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0148] This application describes embodiments of methods, apparatus (systems), and computer program products according to embodiments of this application with reference to flowchart illustrations and / or block diagrams. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0149] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0150] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0151] Although preferred embodiments have been described in this application, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of this application.

[0152] Obviously, those skilled in the art can make various modifications and variations to the embodiments of this application without departing from the spirit and scope of the embodiments of this application. Therefore, if these modifications and variations to the embodiments of this application fall within the scope of the claims in this application and their equivalents, then this application also intends to include these modifications and variations.

Claims

1. A method for determining the operating characteristic parameters of a Hall thruster, characterized in that, The method includes: Obtain the target operating parameters of the Hall thruster; The target operating condition parameters are input into a pre-trained Hall thruster discharge oscillation prediction model to predict the time series data of the operating parameters of the Hall thruster under the target operating condition parameters and the spatiotemporal distribution data of the plasma in the channel of the Hall thruster. The Hall thruster discharge oscillation prediction model is trained using multiple historical simulation data; any historical simulation data includes: historical operating parameters, corresponding historical operating parameter time series data, and corresponding historical spatiotemporal distribution data. The working parameter time series data and the spatiotemporal distribution data are analyzed to obtain the working characteristic parameters; The Hall thruster discharge oscillation prediction model includes: The input layer is used to receive target operating condition parameters; The feature embedding layer is used to extract features from the input target operating condition parameters to obtain a feature vector sequence and a first oscillation period; The time series prediction layer is used to predict the time series of particle count and ionization rate within a preset time window based on the feature vector sequence input from the feature embedding layer; wherein the time length of the preset time window is greater than the first oscillation period. The spatiotemporal distribution prediction layer is used to predict the spatiotemporal distribution data of plasma within a preset time window based on the feature vector sequence and the time series of particle numbers. The working parameter prediction layer is used to predict the working parameter time series data within a preset time window based on the feature vector sequence, ionization rate time series, and particle density spatiotemporal distribution data. The periodic verification layer is used to extract the second oscillation period, the third oscillation period, and the fourth oscillation period based on the time series of particle counts, the spatiotemporal distribution data of plasma, and the time series data of working parameters within a preset time window, respectively. The output layer is used to output time series data of the operating parameters of the Hall thruster under the target operating conditions and spatiotemporal distribution data of the plasma in the channel of the Hall thruster when the difference between the first oscillation period, the second oscillation period, the third oscillation period and the fourth oscillation period is less than the configured threshold.

2. The method as described in claim 1, characterized in that, The target operating parameters include: the channel configuration, channel size and wall material type of the Hall thruster, as well as the applied electric field parameters, magnetic field parameters, cathode discharge current of the Hall thruster, and the type and flow rate of the neutral gas input into the Hall thruster; The operating parameter time series data includes: discharge current time series data, thrust time series data, and physical field time series data; The spatiotemporal distribution data of the plasma includes: particle density spatiotemporal distribution data, electron temperature axial spatiotemporal distribution data, and ion temperature axial spatiotemporal distribution data.

3. The method as described in claim 2, characterized in that, The time series data of the operating parameters and the spatiotemporal distribution data are analyzed to obtain the operating characteristic parameters, including: The first operating characteristic parameter is obtained by analyzing the discharge current time series data and the thrust time series data; wherein, the first operating characteristic parameter includes: the oscillation period of the discharge oscillation; Extract the target physical field time series data and the target spatiotemporal distribution data within one oscillation period from the physical field time series data and the spatiotemporal distribution data, respectively. The time series data of the target physical field are analyzed to obtain the changing trend of the physical field within one oscillation period; The spatiotemporal distribution data of the target are analyzed to obtain the second working characteristic parameters; wherein, the second working characteristic parameters include: the variation trend of particle density within one oscillation cycle, the variation trend of electron temperature within one oscillation cycle, and the variation trend of ion temperature within one oscillation cycle; The first working characteristic parameter, the changing trend of the physical field within one oscillation period, and the second working characteristic parameter are determined as the working characteristic parameters.

4. The method as described in claim 3, characterized in that, Analysis of discharge current time series data and thrust time series data yields the first operating characteristic parameters, including: Multiple first peak values ​​and first valley values ​​are extracted from the discharge current time series data; Based on the extracted first peak values, the oscillation period of the discharge oscillation is determined; Multiple second peak values ​​and second valley values ​​are extracted from the thrust time series data; The first peak value, the first valley value, the second peak value, the second valley value, and the oscillation period are determined as the first working characteristic parameters.

5. The method as described in claim 1, characterized in that, Before obtaining the target operating parameters of the Hall thruster, the method further includes: Construct a one-dimensional full-particle numerical simulation model of the Hall thruster.

6. The method as described in claim 5, characterized in that, The method for obtaining the historical simulation data includes: Retrieve multiple historical operating condition parameters configured; For any historical operating condition parameter, the historical operating condition parameter is input into the one-dimensional full-particle numerical simulation model to perform discharge simulation, thereby obtaining the historical operating parameter time series data and the corresponding historical spatiotemporal distribution data.

7. A device for determining the operating characteristic parameters of a Hall thruster, characterized in that, The device includes: Acquisition unit, used to acquire target operating condition parameters of Hall thruster; The prediction unit is used to input the target operating condition parameters into a pre-trained Hall thruster discharge oscillation prediction model to predict the time series data of the operating parameters of the Hall thruster under the target operating condition parameters and the spatiotemporal distribution data of the plasma in the channel of the Hall thruster; wherein, the Hall thruster discharge oscillation prediction model is trained using multiple historical simulation data; any historical simulation data includes: historical operating condition parameters and corresponding historical operating parameter time series data and corresponding historical spatiotemporal distribution data; The Hall thruster discharge oscillation prediction model includes: The input layer is used to receive target operating condition parameters; The feature embedding layer is used to extract features from the input target operating condition parameters to obtain a feature vector sequence and a first oscillation period; The time series prediction layer is used to predict the time series of particle count and ionization rate within a preset time window based on the feature vector sequence input from the feature embedding layer; wherein the time length of the preset time window is greater than the first oscillation period. The spatiotemporal distribution prediction layer is used to predict the spatiotemporal distribution data of plasma within a preset time window based on the feature vector sequence and the time series of particle numbers. The working parameter prediction layer is used to predict the working parameter time series data within a preset time window based on the feature vector sequence, ionization rate time series, and particle density spatiotemporal distribution data. The periodic verification layer is used to extract the second oscillation period, the third oscillation period, and the fourth oscillation period based on the time series of particle counts, the spatiotemporal distribution data of plasma, and the time series data of working parameters within a preset time window, respectively. The output layer is used to output time series data of the operating parameters of the Hall thruster under the target operating condition parameters and spatiotemporal distribution data of the plasma in the channel of the Hall thruster when the difference between the first oscillation period, the second oscillation period, the third oscillation period and the fourth oscillation period is less than the configured threshold. The analysis unit is used to analyze the time series data of the working parameters and the spatiotemporal distribution data to obtain the working characteristic parameters.

8. An electronic device, characterized in that, The electronic device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method of any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method described in any one of claims 1-6.

Images