A flow control method and related device for electric propulsion system

Abstract

The present application relates to a flow control method. To address the technical problems that the throttling structure of the existing flow control module is fixed and the product consistency is poor, the corresponding electric propulsion system is complex, and the operation of the open-loop control mode is complex, and performance degradation occurs after long-term operation, resulting in increased control errors, a flow control method and related devices for an electric propulsion system are provided. The real-time theoretical pressure difference between the first pressure detection component and the second pressure detection component in the flow control module is calculated by a flow calculation model. The flow calculation model is a model that adopts a numerical differentiation method, or the flow calculation model is a model based on a long-short-term memory model. The real-time pressure difference between the first pressure detection component and the second pressure detection component is obtained in real time. According to the deviation of the real-time pressure difference compared with the real-time theoretical pressure difference, the flow adjustment component is controlled and adjusted by a flow controller to perform closed-loop control.

Description

Technical Field

[0001] The present application relates to a flow control method, and specifically to a flow control method and related devices for an electric propulsion system. Background Art

[0002] With the development and maturity of space electric propulsion technology, its application areas have expanded from geostationary orbit satellites to deep space probes, medium orbit satellites, low orbit satellites and their constellations, ultra-low orbit spacecraft, manned space flight and on-orbit maintenance, etc., which has put forward increasingly higher requirements for the orbit prediction and control of modern satellite platforms.

[0003] The electric propulsion system consists of multiple modules, among which the flow control module is used to directly control the flow of propellant. The accuracy of flow control directly affects the thrust output accuracy and thrust stability of the electric thruster, making it one of the most important subsystems in the electric propulsion system. Existing flow control modules have the following main problems:

[0004] (1) Most flow control modules use fixed structure throttling, which requires electric heating or changing the inlet pressure to achieve flow regulation. At the same time, since the throttling device is made of special materials and processes, the product consistency is poor, which increases the complexity of the entire electric propulsion system.

[0005] (2) Most flow control modules use independent pressure control modules, which require gas containers, multiple shut-off valves, solenoid valves, etc., making the entire electric propulsion system too complex and bulky. In addition, other small flow control systems often have a small flow adjustment range.

[0006] (3) Existing flow control modules mostly use an open-loop control mode, requiring ground analysis of telemetry data to assess thrust and issue corresponding commands for thrust control and adjustment. However, the procedures for sending space commands are often complex and influenced by many factors, which greatly increases the complexity of operation. In addition, after long-term operation of the electric propulsion system, the performance of its components will deteriorate, resulting in increased errors in the flow control module. Summary of the Invention

[0007] This application addresses the technical problems that the existing flow control module has a fixed throttling structure and poor product consistency, the corresponding electric propulsion system is complex, the open-loop control mode has high operation complexity, and performance degradation after long-term operation, resulting in increased control errors. The application provides a flow control method and related devices for electric propulsion systems.

[0008] In order to achieve the above objectives, this application adopts the following technical solutions:

[0009] In a first aspect, the present application proposes a flow control method for an electric propulsion system, comprising:

[0010] The flow calculation model is used to calculate the real-time theoretical pressure difference between the first pressure detection element and the second pressure detection element in the flow control module; the flow control module includes a flow controller, and a first pressure detection element, a throttling device, a second pressure detection element, and a flow adjustment element arranged in sequence along the propellant flow path. The flow controller is respectively connected to the first pressure detection element, the second pressure detection element, and the flow adjustment element, and is used to obtain detection results of the first pressure detection element and the second pressure detection element, and control and adjust the flow adjustment element;

[0011] The flow calculation model is a model using a numerical differentiation method, which calculates the real-time theoretical pressure difference based on the flow rate change rate at the rear end of the flow regulating component and the real-time flow rate; or the flow calculation model is based on a long short-term memory model, the input of the flow calculation model is the flow rate change rate at the rear end of the flow regulating component and the real-time flow rate, and a sequence of theoretical pressure differences at multiple moments in a preset time period before the current moment, and the output is the real-time theoretical pressure difference;

[0012] obtaining a real-time pressure difference between the first pressure detecting component and the second pressure detecting component;

[0013] According to the deviation of the real-time pressure difference from the real-time theoretical pressure difference, the flow adjustment member is controlled and adjusted by the flow controller to perform closed-loop control.

[0014] In a second aspect, the present application proposes a flow control system for an electric propulsion system, comprising:

[0015] a flow calculation module, configured to calculate the real-time theoretical pressure difference between the first pressure detection element and the second pressure detection element in the flow control module using a flow calculation model; the flow control module includes a flow controller, and a first pressure detection element, a throttling device, a second pressure detection element, and a flow adjustment element sequentially arranged along the propellant flow path; the flow controller is connected to the first pressure detection element, the second pressure detection element, and the flow adjustment element, respectively, and is configured to obtain detection results from the first pressure detection element and the second pressure detection element, and to control and adjust the flow adjustment element;

[0016] The flow calculation model is a model using a numerical differentiation method, which calculates the real-time theoretical pressure difference based on the flow rate change rate at the rear end of the flow regulating component and the real-time flow rate; or the flow calculation model is based on a long short-term memory model, the input of the flow calculation model is the flow rate change rate at the rear end of the flow regulating component and the real-time flow rate, and a sequence of theoretical pressure differences at multiple moments in a preset time period before the current moment, and the output is the real-time theoretical pressure difference;

[0017] A detection module, configured to obtain in real time the real-time pressure difference between the first pressure detection component and the second pressure detection component;

[0018] The control module is used to control and adjust the flow adjustment element through the flow controller according to the deviation of the real-time pressure difference compared with the real-time theoretical pressure difference to perform closed-loop control.

[0019] In a third aspect, the present application proposes an electronic device comprising: a memory, one or more processors; the memory is coupled to the processor; wherein computer program code is stored in the memory, and the computer program code comprises computer instructions, and when the computer instructions are executed by the processor, the electronic device performs the steps of the above-mentioned flow control method for the electric propulsion system.

[0020] In a fourth aspect, the present application proposes a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned flow control method for an electric propulsion system are implemented.

[0021] Compared with the prior art, this application has the following beneficial effects:

[0022] The present application proposes a flow control method for an electric propulsion system, and builds a flow control module. The flow control module includes a flow controller, and a first pressure detection part, a throttling device, a second pressure detection part, and a flow regulating part arranged in sequence along the propellant flow path. The flow controller is connected to the first pressure detection part, the second pressure detection part, and the flow regulating part respectively, and is used to obtain the detection results of the first pressure detection part and the second pressure detection part, and to control and regulate the flow regulating part. The real-time theoretical pressure difference between the first pressure detection part and the second pressure detection part in the flow control module is calculated with the help of a flow calculation model. By analyzing the deviation of the real-time pressure difference compared with the real-time theoretical pressure difference, the flow regulating part is controlled and regulated by the flow controller to perform closed-loop control. The flow controller of the present application uses a throttling device, which effectively simplifies the overall complexity, reduces hardware costs and energy consumption while ensuring stability, and improves integration and reliability. In addition, the flow calculation model of the present application is a model that uses a numerical differentiation method, or is based on a long-short-term memory model. When it is based on a long-short-term memory model, the input is the flow change rate and real-time flow at the back end of the flow regulating component, as well as the theoretical pressure difference sequence at multiple moments in a preset time period before the current moment. It not only effectively captures the direct impact of the flow change rate and flow on the pressure difference, but also deeply explores the complex nonlinear relationship in the pressure difference change curve, thereby improving the accuracy and robustness of flow prediction.

[0023] The present application also proposes a flow control system for an electric propulsion system, an electronic device and a computer storage medium, which have all the advantages of the above-mentioned flow control method for an electric propulsion system. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0025] Figure 1 A flow chart of a flow control method for an electric propulsion system according to the present application;

[0026] Figure 2 This is a connection diagram of the flow control module;

[0027] Figure 3 A connection diagram for ground calibration using the flow control method for electric propulsion systems of this application;

[0028] Figure 4 This is a schematic diagram of a flow control system for an electric propulsion system of the present application;

[0029] Figure 5 This is a schematic diagram of a practical application of the electric propulsion system of the present application. DETAILED DESCRIPTION

[0030] To make the objectives, technical solutions, and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Generally, the components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations.

[0031] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for protection, but merely represents selected embodiments of the present application. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments in the present application without creative work are within the scope of protection of the present application.

[0032] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0033] In the description of the embodiments of the present application, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. appear, the orientation or position relationship indicated is based on the orientation or position relationship shown in the accompanying drawings, or the orientation or position relationship in which the product of the invention is usually placed when in use. This is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation. Therefore, it should not be understood as a limitation on the present application. In addition, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0034] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0035] In the description of the embodiments of this application, it should also be noted that, unless otherwise expressly specified or limited, the terms "disposed," "installed," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to internal connections between two components. Those skilled in the art can understand the specific meanings of the above terms in this application based on specific circumstances.

[0036] With the continuous development and increasing maturity of space electric propulsion technology, its application has significantly expanded beyond geostationary orbit satellites to a wider range of areas. It is no longer limited to traditional geosynchronous orbit satellites, but is now widely used in deep space probes, medium-orbit satellites, low-orbit satellites and their constellations, ultra-low-orbit spacecraft, manned space flight, and on-orbit maintenance. This expansion of application not only demonstrates the powerful adaptability and flexibility of electric propulsion technology, but also places higher and more stringent requirements on the orbit prediction and control of modern satellite platforms.

[0037] In modern satellite platforms, orbit prediction and control are crucial for ensuring that satellites operate along their planned trajectories and complete their missions. As the application of electric propulsion technology continues to expand, the orbital environment faced by satellite platforms becomes more complex and dynamic, placing increasing demands on the accuracy and stability of orbit prediction and control. This necessitates that researchers continuously optimize and improve orbit prediction and control algorithms to adapt to the new challenges presented by electric propulsion technology.

[0038] As the core system for achieving satellite orbit control and attitude adjustment, the performance of the electric propulsion system directly affects the satellite's operating performance and mission completion quality. The electric propulsion system is composed of multiple modules, mainly including gas cylinders, pressure control modules, flow control modules and electric thrusters, among which the flow control module plays a vital role. The flow control module is directly responsible for controlling the conduction and cutoff of the propellant. The control accuracy of the flow control module directly affects the thrust output accuracy and thrust stability of the electric thruster. The working principle of the electric propulsion system is to first convert the inert gas into charged ions, and then accelerate and eject these ions to generate propulsion, thereby completing tasks such as attitude control, orbit correction and orbit maintenance of the spacecraft. The existing flow control modules mainly have the following problems:

[0039] 1. Currently, most flow control modules employ fixed-structure throttling, utilizing tiny holes or flow channels. These require flow regulation through methods such as electrical heating or changing inlet pressure, and valves used to open and close the propellant. These methods utilize porous materials, throttling orifices, capillaries, and other methods. Due to the use of electrical heating, this method typically has a long response time and a narrow flow adjustment range. Furthermore, since throttling devices are often manufactured using specialized materials and processes, product consistency is poor, further increasing the control complexity of the entire electric propulsion system.

[0040] 2. Currently, many flow control modules use independent pressure control modules, which require air containers, multiple shutoff valves, and solenoid valves, making the entire electric propulsion system too complex and bulky. Other small flow control systems also often have a very narrow flow adjustment range.

[0041] 3. Currently, most flow control modules utilize an open-loop control mode, requiring ground-based analysis of telemetry data to assess thrust and issue corresponding commands for thrust control and adjustment. However, sending commands in space often involves complex procedures and numerous influencing factors, increasing the complexity of the overall operation. Furthermore, long-term operation of electric propulsion systems can lead to performance degradation of the pressure reducing valve and solenoid valve, resulting in issues such as an inability to maintain thrust over the long term. When using electric propulsion systems, potential errors in the pressure reducing valve are generally ignored, with only the pressure gauges at the rear end of the valve and at the high-pressure end being the focus. This neglects the fact that the pressure differential near the pressure reducing element (solenoid valve or throttling device) has a more direct and precise impact on flow. Furthermore, the few flow control modules currently utilizing closed-loop control also suffer from issues such as a narrow adjustment range and high errors.

[0042] Based on the above situation, the present application proposes a flow control method and related devices for an electric propulsion system. The present application is described in detail below with reference to embodiments and drawings.

[0043] like Figure 1FIG. 1 is a flow chart of a flow control method for an electric propulsion system of the present application, which may include:

[0044] S101, calculate the real-time theoretical pressure difference between the first pressure detection component and the second pressure detection component in the flow control module through the flow calculation model; the flow control module includes a flow controller, and a first pressure detection component, a throttling device, a second pressure detection component and a flow regulating component arranged in sequence along the propellant flow path, the flow controller is respectively connected to the first pressure detection component, the second pressure detection component and the flow regulating component, and is used to obtain the detection results of the first pressure detection component and the second pressure detection component, and control and adjust the flow regulating component.

[0045] Among them, the flow calculation model is a model that adopts the numerical differentiation method, and calculates the real-time theoretical pressure difference based on the flow change rate at the back end of the flow regulating component and the real-time flow; or, the flow calculation model is based on the long short-term memory model, and the input of the flow calculation model is the flow change rate at the back end of the flow regulating component and the real-time flow, as well as a sequence of theoretical pressure differences at multiple moments in a preset time period before the current moment, and the output is the real-time theoretical pressure difference.

[0046] It should be noted that this application proposes two flow calculation models that are applicable to different application scenarios. In scenarios where flow changes are relatively stable or predictable, the model based on the numerical differentiation method can be used. The long-short-term memory model can process time series data and use historical data to predict future trends, thereby more accurately predicting the real-time theoretical pressure difference.

[0047] S102: Acquire the real-time pressure difference between the first pressure detection component and the second pressure detection component in real time.

[0048] Obtaining the real-time pressure difference between the first pressure detection component and the second pressure detection component is a feedback link in the closed-loop control, which is used to compare the difference between the actual value and the theoretical value.

[0049] S103, according to the deviation of the real-time pressure difference compared with the real-time theoretical pressure difference, the flow regulating element is controlled and adjusted by the flow controller to perform closed-loop control.

[0050] In practice, if the real-time pressure difference is greater than the real-time theoretical pressure difference, the actual flow rate may be too low, and the flow rate can be increased by controlling the flow control element. Conversely, if the real-time pressure difference is less than the real-time theoretical pressure difference, the actual flow rate may be too high, and the flow rate can be reduced by controlling the flow control element. The flow controller sends a control signal to the flow control element based on the control strategy, and the flow control element adjusts its operating state based on the received control signal, thereby achieving precise control of the flow rate.

[0051] The above-mentioned flow control method for electric propulsion systems has the advantages of fast response speed and high control accuracy, and is suitable for electric propulsion systems with high flow control requirements.

[0052] like Figure 2 The figure shows a connection diagram of the flow control module. The flow regulating part adopts a flow regulating valve. Figure 2 In the figure, P1 and P2 represent the first pressure detection component and the second pressure detection component, respectively. The flow control module is connected between the pressure control module and the final outlet of the electric propulsion system. The pressure control module is connected to the outlet of the gas cylinder. The inlet of the flow control module receives a stable pressure source provided by the pressure control module. As an example, the throttling device can adopt a bangbang valve with fixed parameters, a throttle hole, a pressure reducing valve, a needle valve, or other devices with throttling functions. The flow regulating valve can adopt a bangbang valve or a proportional solenoid valve. The flow controller can use an MCU (Microcontroller Unit) or an FPGA (Field-Programmable Gate Array) as a central processing unit. The main function of the flow controller is to process the pressure data returned by the first and second pressure detection components and to drive the flow regulating component.

[0053] like Figure 3 The figure shows a connection diagram for ground calibration using the flow control method for electric propulsion systems of the present application. In this embodiment, a mechanical pressure reducing valve is used as a pressure control module, and the output air path of the flow control module is connected to a flow meter for detecting the real-time flow at the rear end of the flow regulating component of the flow control module. The rear end of the flow meter is connected to the vacuum system via a flange. The real-time flow detected by the flow meter and the real-time pressure difference collected by the flow controller in the flow control module are transmitted back to the host computer, and then the real-time theoretical pressure difference can be calculated by the flow calculation model, and the deviation of the real-time pressure difference from the real-time theoretical pressure difference can be compared to obtain the required adjustment amount and send it to the flow controller.

[0054] As an embodiment of the present application, there are two methods for constructing a flow calculation model, specifically:

[0055] 1. The flow calculation model is a model that uses the numerical differentiation method.

[0056] According to the working principle of general differential pressure flowmeters, taking into account the dynamic changes in flow, the relationship between the pressure difference in the pipeline and the flow rate can be described by the following formula:

[0057]

[0058] in, for The real-time theoretical pressure difference at each moment, is the flow rate change coefficient, is the flow rate change rate, is the instantaneous flow coefficient, for Real-time traffic at all times, To set the sampling frequency or a multiple of the sampling frequency.

[0059] In this embodiment, the formula representing the relationship between the pressure difference in the pipeline and the flow rate can be corrected and approximated in the following three ways:

[0060] (1) Calculate the flow rate change rate using the numerical differentiation method:

[0061]

[0062] (2) Since the satellite platform has high requirements for the selection of software and hardware, different pressure detection components may have certain manufacturing tolerances and measurement errors, and the hardware circuit may have deviations in the process of processing signals. The pressure detection components need to be calibrated before use. In order to correct the errors that may be caused by the above operations to ensure the accuracy of flow calculation, the linear correction coefficient k3 is introduced, that is:

[0063]

[0064] (3) Satellites may experience different temperature conditions at different orbital positions and operational stages. Considering the possible reasons that may cause the temperature of the entire satellite platform or flow control module to fluctuate, and thus cause the working fluid density to change, combined with the relationship between density and pressure in the ideal gas state equation, 、 and Taking the temperature into account, it can be rewritten as: , , ,but:

[0065]

[0066] in, is the first temperature coefficient, is the current temperature, is the first temperature constant coefficient, is the second temperature coefficient, is the second temperature constant coefficient, is the third temperature coefficient, is the third temperature constant coefficient.

[0067] In practical applications, the above-mentioned revised formula can be selected according to actual conditions.

[0068] It should be noted that to All of them can be obtained through fitting methods.

[0069] 2. The traffic calculation model is based on the long short-term memory model.

[0070] Considering the complexity, using traditional traffic calculation models may have some drawbacks:

[0071] (1) The pressure control module converts the high-pressure gas in the cylinder into a low-pressure source with a stable output. However, due to the influence of the pressure reducing valve body structure, a pulsating flow with a period of less than 0.1 Hz appears in the gas circuit, and the pulsating period and amplitude are related to the flow rate, making the calculation There is a lot of noise interference in the process, and the traditional flow calculation model may not be able to filter out this interference well.

[0072] (3) The structure of the flow control module is essentially to measure the flow through the two ends of the throttling device. In the process of converting it to the final output flow, hysteresis or noise interference may occur. The traditional flow calculation model cannot handle these hysteresis or noise interference in a timely manner.

[0073] In summary, traffic is not only related to the current There is also a more complex nonlinear relationship with the change curve of the real-time pressure difference between the first pressure detection part and the second pressure detection part over a period of time. Therefore, this embodiment constructs a flow calculation model that combines linear and time series. Solve. The details are as follows:

[0074] First construct the linear term:

[0075]

[0076] in, is the linear output term, is the first parameter of the linear output term, is the second parameter of the linear output term, is the third parameter of the linear output item. As before, if the influence of temperature is considered, 、 and Rewrite it in temperature-dependent form.

[0077] Then, a sequence item based on LSTM (Long Short-Term Memory) is constructed to capture the relationship between the flow sequence and the pressure difference. The output of LSTM is passed through a fully connected layer and an activation function as the final output of the sequence output item:

[0078]

[0079] in, For activation function, for example, ReLu (Rectified Linear Unit, linear rectification function) can be used. is the fully connected layer parameter matrix in the long short-term memory model, is the hidden state output by the long short-term memory model, is the bias vector, is a long short-term memory neural network unit, It is a theoretical pressure difference sequence of multiple moments in a preset time period before the current moment. The function of the long short-term memory neural network unit is to Learning, extracting temporal features and generating hidden states The hidden state It can capture both long-term dependencies and short-term dynamic changes. The sequence length is ,but .

[0080] Finally, the linear output term and sequence output items Merge the output. Since the influence range of sequence output items is smaller than that of linear output items, the weight parameter is introduced :

[0081]

[0082] When the traffic calculation model is trained, the loss function can use the mean square error, that is:

[0083]

[0084] in, is the loss function, is the number of training samples, for The real-time actual pressure difference at the moment, for The real-time theoretical pressure difference at each moment, For the Sampling moments.

[0085] To ensure effective training and good generalization of the traffic calculation model, it's important to choose the optimization function and apply appropriate regularization techniques. This example uses the Adam (Adaptive Moment Estimation) optimizer and adds a dropout regularization layer between the LSTM layer and the fully connected layer to prevent overfitting and enhance the generalization of the traffic calculation model.

[0086] After determining the structure of the traffic calculation model, you can start dividing the data set, as well as training and tuning the traffic calculation model. Once the traffic calculation model performs well on the validation set and test set, you can deploy the trained traffic calculation model to achieve more precise control.

[0087] In practical applications, the following methods can be used to control flow:

[0088] (1) Waiting for the set flow value: The electric propulsion system cyclically waits for the instruction to change the set flow value. If it changes, the flow-related parameters of the flow calculation model are updated, and then the real-time theoretical pressure difference between the first pressure detection component and the second pressure detection component in the flow control module is calculated by the flow calculation model.

[0089] (2) Obtain the real-time pressure difference between the first pressure detection component and the second pressure detection component in real time, and determine whether the deviation of the real-time pressure difference from the real-time theoretical pressure difference is within the specified range. If so, do not perform any operation and continue to wait for the set flow value. If not, adjust the valve parameters using the PID (Proportional-Integral-Derivative) method until the deviation of the real-time pressure difference from the real-time theoretical pressure difference is within the specified range.

[0090] In practical applications, the real-time pressure difference between the first pressure detection component and the second pressure detection component can be monitored for a long time, and fine-tuning can be performed in time to ensure that the flow rate is always within the set range during long-term operation.

[0091] like Figure 4 The figure shows a schematic diagram of a flow control system for an electric propulsion system of the present application. It may include:

[0092] a flow calculation module, configured to calculate the real-time theoretical pressure difference between the first pressure detection element and the second pressure detection element in the flow control module using a flow calculation model; the flow control module includes a flow controller, and a first pressure detection element, a throttling device, a second pressure detection element, and a flow adjustment element sequentially arranged along the propellant flow path; the flow controller is connected to the first pressure detection element, the second pressure detection element, and the flow adjustment element, respectively, and is configured to obtain detection results from the first pressure detection element and the second pressure detection element, and to control and adjust the flow adjustment element;

[0093] The flow calculation model is a model using a numerical differentiation method, which calculates the real-time theoretical pressure difference based on the flow rate change rate at the rear end of the flow regulating component and the real-time flow rate; or the flow calculation model is based on a long short-term memory model, the input of the flow calculation model is the flow rate change rate at the rear end of the flow regulating component and the real-time flow rate, and a sequence of theoretical pressure differences at multiple moments in a preset time period before the current moment, and the output is the real-time theoretical pressure difference;

[0094] A detection module, configured to obtain in real time the real-time pressure difference between the first pressure detection component and the second pressure detection component;

[0095] The control module is used to control and adjust the flow adjustment element through the flow controller according to the deviation of the real-time pressure difference compared with the real-time theoretical pressure difference to perform closed-loop control.

[0096] like Figure 5 As shown, it is a schematic diagram of an actual use of the electric propulsion system of the present application. Figure 5 Here, P1 and P2 represent the first pressure detection component and the second pressure detection component, respectively. Taking the application in the satellite platform as an example, the satellite computer, the power processing unit (PPCU) and the flow controller are connected in a bidirectional manner in sequence. The satellite computer issues a flow control instruction, which is sent to the flow controller via the power processing unit. Conversely, the detection results of the first pressure detection component and the second pressure detection component received by the flow controller, as well as the deviation result of the real-time pressure difference analyzed by the flow controller compared with the real-time theoretical pressure difference, can also be fed back to the satellite computer via the power processing unit. The rear end of the flow control valve is connected to the Hall thruster and then to the space environment.

[0097] It should be noted that in the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the system embodiments described above are merely schematic. For example, the division of each module is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules can be combined or integrated into another device, or some features can be ignored or not executed. The modules described as separate components may or may not be physically separated. The components displayed as modules may be one physical unit or multiple physical units, that is, they may be located in one place, or they may be distributed in multiple different places. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0098] In addition, the modules in the various embodiments of the present invention may be integrated into a single processing unit, each module may exist physically separately, or two or more modules may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0099] An embodiment of the present application also provides an electronic device, which may include one or more processors, memories, and communication interfaces.

[0100] The memory, the communication interface, and the processor are coupled together. For example, the memory, the communication interface, and the processor may be coupled together via a bus.

[0101] The communication interface is used to transmit data with other devices. The memory stores computer program code. The computer program code includes computer instructions that, when executed by a processor, cause the electronic device to perform the steps of the aforementioned flow control method for an electric propulsion system.

[0102] Among them, the processor can be a processor or a controller, for example, a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can implement or execute the various exemplary logic blocks, modules and circuits described in conjunction with the contents of this disclosure. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The processor can be used to support electronic devices in executing the method steps provided in the above embodiments.

[0103] The bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The above buses may be divided into an address bus, a data bus, a control bus, etc.

[0104] An embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned flow control method for an electric propulsion system are implemented.

[0105] The computer-readable storage medium involved in this application includes random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs (Compact Disc Read-Only Memory), or any other form of storage medium known in the technical field.

[0106] The above are merely preferred embodiments of the present application and are not intended to limit the present application. Those skilled in the art will readily appreciate that various modifications and variations are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A flow control method for an electric propulsion system, characterized in that: include: Calculate the real-time theoretical pressure difference between the first pressure detection component and the second pressure detection component in the flow control module through the flow calculation model; The flow control module includes a flow controller, and a first pressure detection element, a throttling device, a second pressure detection element, and a flow adjustment element arranged in sequence along the propellant flow path. The flow controller is connected to the first pressure detection element, the second pressure detection element, and the flow adjustment element, respectively, and is used to obtain detection results of the first pressure detection element and the second pressure detection element, and control and adjust the flow adjustment element. The flow calculation model is a model using a numerical differentiation method, which calculates the real-time theoretical pressure difference based on the flow rate change rate at the rear end of the flow regulating component and the real-time flow rate; or the flow calculation model is based on a long short-term memory model, the input of the flow calculation model is the flow rate change rate at the rear end of the flow regulating component and the real-time flow rate, and a sequence of theoretical pressure differences at multiple moments in a preset time period before the current moment, and the output is the real-time theoretical pressure difference; obtaining a real-time pressure difference between the first pressure detecting component and the second pressure detecting component; According to the deviation of the real-time pressure difference from the real-time theoretical pressure difference, the flow adjustment member is controlled and adjusted by the flow controller to perform closed-loop control.

2. The flow control method for an electric propulsion system according to claim 1, characterized in that: The flow calculation model is a model using a numerical differentiation method; The formula of the flow calculation model is: in, for The real-time theoretical pressure difference at each moment, is the flow rate change coefficient, is the flow rate change rate, is the instantaneous flow coefficient, for Real-time traffic at all times, is the linear correction coefficient, To set the sampling frequency or a multiple of the sampling frequency.

3. The flow control method for an electric propulsion system according to claim 1, characterized in that: The flow calculation model is a model using a numerical differentiation method; The formula of the flow calculation model is: in, is the first temperature coefficient, is the current temperature, is the first temperature constant coefficient, is the second temperature coefficient, is the second temperature constant coefficient, is the third temperature coefficient, is the third temperature constant coefficient.

4. The flow control method for an electric propulsion system according to claim 1, characterized in that: The flow calculation model is based on the long short-term memory model; The formula of the flow calculation model is: in, is the linear output term, is the weight parameter, is the sequence output item; The linear output term Calculated based on the flow rate change rate and real-time flow rate of the rear end of the flow regulating element; the sequence output item It is calculated based on the theoretical pressure difference sequence at multiple moments in a preset time period before the current moment.

5. The flow control method for an electric propulsion system according to claim 4, characterized in that: The linear output term The calculation formula is: in, is the first parameter of the linear output term, is the second parameter of the linear output term, is the third parameter of the linear output term, For time; The sequence output The calculation formula is: in, is the activation function, is the fully connected layer parameter matrix in the long short-term memory model, is the hidden state output by the long short-term memory model, is the bias vector.

6. The flow control method for an electric propulsion system according to claim 5, characterized in that: The hidden state output by the long short-term memory model The calculation formula is: include: in, represents a long short-term memory neural network unit, It is a sequence of theoretical pressure differences at multiple moments in a preset time period before the current moment.

7. The flow control method for an electric propulsion system according to claim 6, characterized in that: A Dropout layer is provided between the long short-term memory layer and the fully connected layer of the long short-term memory model; The loss function formula used in the long short-term memory model training is: in, is the loss function, is the number of training samples, for The real-time actual pressure difference at the moment, for The real-time theoretical pressure difference at each moment, For the Sampling moments.

8. A flow control system for an electric propulsion system, characterized in that: include: A flow calculation module, configured to calculate a real-time theoretical pressure difference between the first pressure detection component and the second pressure detection component in the flow control module through a flow calculation model; The flow control module includes a flow controller, and a first pressure detection element, a throttling device, a second pressure detection element, and a flow adjustment element arranged in sequence along the propellant flow path. The flow controller is connected to the first pressure detection element, the second pressure detection element, and the flow adjustment element, respectively, and is used to obtain detection results of the first pressure detection element and the second pressure detection element, and control and adjust the flow adjustment element. The flow calculation model is a model using a numerical differentiation method, which calculates the real-time theoretical pressure difference based on the flow rate change rate at the rear end of the flow regulating component and the real-time flow rate; or the flow calculation model is based on a long short-term memory model, the input of the flow calculation model is the flow rate change rate at the rear end of the flow regulating component and the real-time flow rate, and a sequence of theoretical pressure differences at multiple moments in a preset time period before the current moment, and the output is the real-time theoretical pressure difference; A detection module, configured to obtain in real time the real-time pressure difference between the first pressure detection component and the second pressure detection component; The control module is used to control and adjust the flow adjustment element through the flow controller according to the deviation of the real-time pressure difference compared with the real-time theoretical pressure difference to perform closed-loop control.

9. An electronic device, characterized in that: include: A memory, one or more processors; the memory is coupled to the processor; wherein the memory stores computer program code, the computer program code includes computer instructions, and when the computer instructions are executed by the processor, the electronic device performs the steps of the flow control method for an electric propulsion system as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the flow control method for an electric propulsion system according to any one of claims 1 to 7.

Images