Satellite micro-vibration suppression method, system, equipment and medium
By combining variational mode decomposition and echo state network prediction model with PID control, effective suppression of satellite micro-vibrations was achieved, solving the phase error problems caused by filter parameter mismatch and sensor delay in traditional methods, and improving the stability and robustness of satellite optical communication.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-01-15
- Publication Date
- 2026-04-10
AI Technical Summary
Traditional PID methods suffer from filter parameter mismatch and adaptive failure in satellite micro-vibration suppression. Furthermore, the time delay of sensor signals in the feedforward path causes phase errors, which weakens the compensation effect.
A time-series prediction model is trained using variational mode decomposition and echo state network. The micro-vibration signal is decomposed into multiple intrinsic mode components through a sliding window mechanism. The PID method is then combined with feedforward and feedback compensation signals to drive the fast steering mirror, thereby achieving micro-vibration suppression.
It effectively overcomes the problems of filter parameter mismatch and adaptive failure in traditional methods, significantly reduces micro-vibration fluctuations, and improves the stability and robustness of satellite optical communication.
Smart Images
Figure CN121841476A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of satellite communication technology, and in particular to a method, system, device and medium for suppressing satellite micro-vibrations. Background Technology
[0002] Satellite optical communication boasts high bandwidth, low latency, and strong anti-interference capabilities. However, due to external perturbations and the influence of internal satellite components, the satellite platform experiences micro-vibrations. These micro-vibrations further cause jitter or even deviation of the beam at the receiver, severely impacting the pointing and tracking stability of satellite optical communication, and consequently affecting the performance of the communication link. Therefore, developing an efficient and reliable micro-vibration suppression scheme is of great significance for improving the stability and robustness of satellite optical communication.
[0003] Currently, satellite micro-vibration suppression mainly relies on a Fast Steering Mirror (FSM) combined with Proportional Integral Derivative (PID) closed-loop control for optical path compensation. However, traditional PID methods suffer from poor frequency selectivity and lack of adaptability when dealing with narrowband harmonics and multi-frequency composite disturbances. While adaptive filter feedforward control can improve suppression capabilities as a supplementary solution, its performance is heavily dependent on the convergence of the filter, and mismatch in filter parameters or failure of the adaptive mechanism will significantly reduce the overall performance of the satellite micro-vibration suppression system. Furthermore, the time delay in sensor signals within the feedforward path can induce phase errors, further weakening the compensation effect. Summary of the Invention
[0004] The purpose of this invention is to provide a satellite micro-vibration suppression method, system, device, and medium, which can solve the problems of filter parameter mismatch and adaptive failure in PID method feedforward control through adaptive filter, as well as the problem of weakened compensation effect caused by phase error due to sensor signal delay in the feedforward path of PID method.
[0005] To address the aforementioned technical problems, embodiments of the present invention provide a satellite micro-vibration suppression method, comprising the following steps: Acquire micro-vibration signals from the satellite; The variational mode decomposition method is used to decompose the micro-vibration signal to obtain multiple intrinsic mode components that reflect the vibration characteristics of different frequency bands in the micro-vibration signal. Each intrinsic mode component is input into the corresponding time-series prediction model trained based on the echo state network. The time-series prediction model uses a sliding window mechanism to divide each intrinsic mode component into multiple signal components. The dynamic characteristics of satellite micro-vibration reflected by the corresponding intrinsic mode component are obtained through multiple signal components, so as to predict the micro-vibration signal of the satellite in the future. The micro-vibration signals of the satellite in the future multi-step prediction corresponding to all intrinsic mode components are superimposed as the feedforward compensation signal. Combined with the feedback compensation signal obtained by the PID method to suppress the satellite micro-vibration, the satellite micro-vibration is suppressed together.
[0006] Optionally, the step of inputting each intrinsic mode component into the corresponding time-series prediction model trained based on the echo state network includes: Based on the vibration characteristics of the corresponding frequency band in the micro-vibration signal reflected by each intrinsic mode component, the degree of influence of each intrinsic mode component on the satellite's operational performance is determined. Based on the degree of influence of each intrinsic mode component on satellite operation performance, the main intrinsic mode components whose influence on satellite operation performance is greater than a preset threshold are extracted from multiple intrinsic mode components; The main intrinsic mode components are input into the time series prediction model trained based on the echo state network.
[0007] Optionally, the time-series prediction model is obtained by training the echo state network using a random search algorithm.
[0008] Optionally, acquiring the satellite's micro-vibration signal includes: Micro-vibration signals of satellites were obtained based on the power spectrum characteristics of the SILEX system.
[0009] Optionally, the step of using the satellite's micro-vibration signals for the next N steps corresponding to all predicted intrinsic mode components as feedforward compensation signals, combined with the feedback compensation signals obtained using the PID method to suppress satellite micro-vibrations, to jointly suppress satellite micro-vibrations includes: By using feedforward compensation signals and feedback compensation signals, the fast steering mirror (FSM) of the satellite micro-vibration suppression system is jointly driven to suppress satellite micro-vibrations.
[0010] Optionally, the method further includes: The satellite's micro-vibration signal after micro-vibration suppression was acquired, and the corresponding probability density function and cumulative distribution function were constructed. The suppression performance of satellite micro-vibrations is evaluated based on the constructed probability density function and cumulative distribution function.
[0011] Embodiments of the present invention also provide a satellite micro-vibration suppression system, comprising: The data acquisition module is used to acquire the satellite's micro-vibration signals; The data decomposition module is used to decompose the micro-vibration signal using the variational mode decomposition method to obtain multiple intrinsic mode components that reflect the vibration characteristics of different frequency bands in the micro-vibration signal. The data prediction module is used to input each intrinsic mode component into the corresponding time-series prediction model trained based on the echo state network. The time-series prediction model uses a sliding window mechanism to divide each intrinsic mode component into multiple signal components, and obtains the dynamic characteristics of satellite micro-vibration reflected by the corresponding intrinsic mode component through multiple signal components, so as to predict the micro-vibration signal of the satellite in the future. The vibration suppression module is used to superimpose the micro-vibration signals of the satellite in the future multi-step prediction corresponding to all intrinsic mode components as a feedforward compensation signal, and combine it with the feedback compensation signal obtained by the PID method to suppress the satellite micro-vibration, so as to jointly suppress the satellite micro-vibration.
[0012] Embodiments of the present invention also provide a computer device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the above-described satellite micro-vibration suppression method.
[0013] Embodiments of the present invention also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described satellite micro-vibration suppression method.
[0014] The satellite micro-vibration suppression method provided by this invention has at least the following beneficial effects: This invention trains a time-series prediction model based on an echo state network. This model uses historical multi-step micro-vibration signals of the satellite to predict future multi-step micro-vibration signals. The predicted signal is then used as a feedforward compensation signal, combined with a feedback compensation signal obtained by using a PID method to suppress satellite micro-vibrations. This approach overcomes the problems of feedforward filter parameter mismatch and adaptive mechanism failure in traditional collaborative control, enabling early prediction of micro-vibration trends and effectively suppressing the phase deviation defect between the compensation signal and the micro-vibration signal caused by time delay.
[0015] As can be seen, this invention utilizes the time-series modeling capability of machine learning prediction models to effectively extract the dynamic features of micro-vibration signals; among them, variational mode decomposition further enhances the decomposition and recognition effect of dynamic features. By combining this time-series prediction signal as feedforward compensation with PID control, joint suppression of satellite micro-vibrations is achieved, thereby significantly reducing micro-vibration fluctuations. Attached Figure Description
[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings:
[0017] Figure 1 A schematic flowchart of a satellite micro-vibration suppression method provided by the present invention; Figure 2 A schematic diagram of a satellite micro-vibration suppression system based on machine learning prediction and PID collaborative control provided by the present invention; Figure 3 This invention provides a comparison diagram of micro-vibrations under different control schemes. Detailed Implementation
[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.
[0019] Based on the technical problems raised in the background section, machine learning, with its excellent nonlinear modeling and temporal feature extraction capabilities, has gradually shown broad application prospects in the field of optical communication. Inspired by this, this invention introduces machine learning into the prediction and feedforward compensation process of satellite micro-vibrations. This can overcome the problems of filter parameter mismatch and adaptive failure in traditional methods, and effectively alleviate the phase deviation caused by signal delay in the feedforward path, thereby improving the micro-vibration suppression performance.
[0020] The technical solutions provided by the various embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
[0021] One embodiment of the present invention relates to a method for suppressing satellite micro-vibrations. The specific process of the satellite micro-vibration suppression method in this embodiment can be as follows: Figure 1 As shown, it includes: Step 101: Obtain the satellite's micro-vibration signal.
[0022] Step 102: The micro-vibration signal is decomposed using the variational mode decomposition method to obtain multiple intrinsic mode components that reflect the vibration characteristics of different frequency bands in the micro-vibration signal. Step 103: Input each intrinsic mode component into the corresponding time-series prediction model trained based on the echo state network. The time-series prediction model uses a sliding window mechanism to divide each intrinsic mode component into multiple signal components. The dynamic characteristics of satellite micro-vibration reflected by the corresponding intrinsic mode component are obtained through multiple signal components to predict the satellite's micro-vibration signal in the future.
[0023] Step 104: The micro-vibration signals of the satellite in the future multi-step prediction corresponding to all the predicted intrinsic mode components are superimposed as the feedforward compensation signal. Combined with the feedback compensation signal obtained by the PID method to suppress the satellite micro-vibration, the satellite micro-vibration is suppressed together.
[0024] The implementation details of the satellite micro-vibration suppression method in this embodiment are described below. The following content is only for the convenience of understanding and is not necessary for implementing this solution.
[0025] In step 101, as Figure 2 As shown, a model of a satellite optical communication micro-vibration suppression system is first established. This system includes key components such as a beam splitter, a position-sensitive device (PSD), an onboard control and processing unit, and an airborne signaling system (FSM). The PSD is used to acquire the pointing error caused by satellite micro-vibrations, i.e., the micro-vibration signal. The onboard processing unit generates control commands to drive the FSM for error compensation. In this embodiment, the system input is set to zero and the feedback channel is in an ideal state in the system modeling, i.e., only the influence of satellite micro-vibrations is considered. This setting helps to simplify the following processing flow and focus on the micro-vibration suppression effect.
[0026] In practical engineering, PSD is used to obtain micro-vibration signals, but the inter-satellite micro-vibration signals of this invention cannot be directly obtained. Therefore, they are generated by simulation based on the power spectrum characteristics of the SILEX system.
[0027] In step 102, the satellite's micro-vibration signal is decomposed using Variational Mode Decomposition (VMD) to obtain multiple intrinsic mode components, thereby improving the accuracy of subsequent micro-vibration signal feature extraction.
[0028] In one example, this embodiment selects the main characteristic modes from multiple intrinsic mode components as inputs to the subsequent time series prediction model. Specifically, based on the vibration characteristics of the corresponding frequency band in the micro-vibration signal reflected by each intrinsic mode component, the influence of each intrinsic mode component on satellite operation performance is determined. Then, based on the influence of each intrinsic mode component on satellite operation performance, the main intrinsic mode components whose influence on satellite operation performance is greater than a preset threshold are extracted from multiple intrinsic mode components. These main intrinsic mode components are then input into the time series prediction model trained based on the echo state network.
[0029] In step 103, this embodiment establishes a time-series prediction model for each intrinsic mode component using an EchoState Network (ESN). Furthermore, a random search algorithm (RS) is introduced to optimize the key parameters of each ESN network and train the ESN network, thereby improving the model's prediction performance. The input data for the time-series prediction model is obtained from historical data through a sliding window mechanism. M The micro-vibration signal of the step is constructed, and the output is for the future. N The predicted value of the micro-vibration signal of the step, where M and N are both integers greater than 1.
[0030] In step 104, the prediction results corresponding to each intrinsic mode component are used to construct a feedforward compensation signal for satellite micro-vibrations. This signal is then combined with the feedback signal of the PID controller to jointly drive the FSM actuator, thereby suppressing satellite micro-vibrations. In specific implementation, all prediction results are used to construct a feedforward compensation channel, forming a control signal for driving the FSM actuator. This achieves early response compensation for impending micro-vibrations. Combining this feedforward control signal with the feedback control signal of the PID controller forms a composite control channel for joint driving of the FSM.
[0031] In one embodiment, this embodiment can acquire the micro-vibration signal of the satellite after micro-vibration suppression, and construct the corresponding probability density function and cumulative distribution function, thereby evaluating the satellite's micro-vibration suppression performance based on the constructed probability density function and cumulative distribution function.
[0032] For example, in a simulation environment, micro-vibration data is generated by power spectrum modeling as system input, and the micro-vibration response of the system output under different control schemes is compared. Then, the micro-vibration suppression performance of the proposed machine learning prediction and PID co-control scheme is evaluated.
[0033] Figure 3This paper presents the changes in system micro-vibration over time under different time delay conditions using Convolutional Neural Network-Long Short-Term Memory Network (CNN-LSTM) feedforward compensation, Gated Recurrent Unit (GRU) feedforward compensation, ESN feedforward compensation, and the feedforward feedback collaborative compensation scheme of this embodiment. The results show that the advantages of the proposed method in micro-vibration suppression become increasingly significant with increasing time delay. Compared with other methods, the collaborative control scheme of this invention effectively decomposes and extracts the main characteristic modes of satellite micro-vibration signals through VMD, thereby improving feature representation capability and signal recognition accuracy. Simultaneously, by combining RS optimization and the efficient time-series modeling capability of ESN, it significantly improves micro-vibration prediction performance. This method can maintain a stable suppression effect under long time delay conditions, providing reliable theoretical support and technical basis for high-precision pointing control in inter-satellite optical communication.
[0034] In this embodiment, a satellite optical communication micro-vibration suppression system model is established, including key components such as a beam splitter, a PSD (Power Segmentation Detector), an onboard control and processing unit, and an FSM (Flying Signal Detector). Micro-vibration signals caused by micro-vibrations collected by the PSD are acquired, a time-series input is constructed, and VMD-RS-ESN (Vibration Dynamics Detection-Resistance-Electronic Signal) is used to predict the micro-vibration signals. The prediction results are then used to generate a feedforward compensation control signal. This feedforward signal is further fused with the feedback control signal output by the PID controller to jointly drive the FSM for micro-vibration suppression control. By statistically analyzing the micro-vibration response output of the system under different control schemes, corresponding error probability density functions and cumulative distribution functions can be constructed, thereby achieving a quantitative evaluation of the performance of the satellite micro-vibration suppression method based on machine learning prediction and PID collaborative control.
[0035] This method is applicable to the suppression of micro-vibrations on satellite platforms in satellite optical communication systems, especially the satellite micro-vibration suppression method based on machine learning prediction and PID collaborative control, which has significant application value. For example, the method of this invention can be effectively applied in fields such as deep space communication and satellite constellation networking. Furthermore, this scheme fully considers the dynamic process caused by micro-vibrations of the satellite platform, combining the time-series modeling capability of machine learning prediction models with the steady-state adjustment capability of PID control, thereby improving the system's suppression effect on multi-frequency composite interference, effectively reducing micro-vibration fluctuations, and realizing the performance evaluation and optimization of micro-vibration control in satellite optical communication application scenarios.
[0036] The steps of the various methods described above are only for clarity. In practice, they can be combined into one step or some steps can be split into multiple steps. As long as they include the same logical relationship, they are all within the protection scope of this invention. Adding insignificant modifications or introducing insignificant designs to the algorithm or process, without changing the core design of the algorithm and process, are also within the protection scope of this invention.
[0037] Another embodiment of the present invention relates to a satellite micro-vibration suppression system. The implementation details of this satellite micro-vibration suppression system are described below. The following details are provided for ease of understanding and are not essential for implementing this solution. The satellite micro-vibration suppression system of this embodiment includes: The data acquisition module is used to acquire the satellite's micro-vibration signals; The data decomposition module is used to decompose the micro-vibration signal using the variational mode decomposition method to obtain multiple intrinsic mode components that reflect the vibration characteristics of different frequency bands in the micro-vibration signal. The data prediction module is used to input each intrinsic mode component into the corresponding time-series prediction model trained based on the echo state network. The time-series prediction model uses a sliding window mechanism to divide each intrinsic mode component into multiple signal components, and obtains the dynamic characteristics of satellite micro-vibration reflected by the corresponding intrinsic mode component through multiple signal components, so as to predict the micro-vibration signal of the satellite in the future. The vibration suppression module is used to superimpose the micro-vibration signals of the satellite in the future multi-step prediction corresponding to all intrinsic mode components as a feedforward compensation signal, and combine it with the feedback compensation signal obtained by the PID method to suppress the satellite micro-vibration, so as to jointly suppress the satellite micro-vibration.
[0038] It is not difficult to see that this embodiment is a system embodiment corresponding to the above method embodiments, and this embodiment can be implemented in conjunction with the above method embodiments. The relevant technical details and technical effects mentioned in the above embodiments are still valid in this embodiment, and will not be repeated here to reduce repetition. Accordingly, the relevant technical details mentioned in this embodiment can also be applied to the above embodiments.
[0039] It is worth mentioning that all modules involved in this embodiment are logical modules. In practical applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. Furthermore, to highlight the innovative aspects of this invention, this embodiment does not introduce units that are not closely related to solving the technical problem proposed by this invention; however, this does not mean that other units are absent from this embodiment.
[0040] Another embodiment of the present invention relates to a computer device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the satellite micro-vibration suppression methods of the above embodiments.
[0041] The memory and processor are connected via a bus, which can include any number of interconnecting buses and bridges, connecting various circuits of one or more processors and memories. The bus can also connect various other circuits, such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and will not be described further herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be a single element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by the processor is transmitted over the wireless medium via an antenna, which further receives data and transmits it to the processor.
[0042] The processor manages the bus and general processing, and also provides various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory is used to store data used by the processor during operation.
[0043] Another embodiment of the present invention relates to a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the method embodiments described above.
[0044] That is, those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. This program is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0045] Those skilled in the art will understand that the above embodiments are specific embodiments for implementing the present invention, and in practical applications, various changes can be made to them in form and detail without departing from the spirit and scope of the present invention.
Claims
1. A method for suppressing satellite micro-vibrations, characterized in that, The method includes: Acquire micro-vibration signals from the satellite; The variational mode decomposition method is used to decompose the micro-vibration signal to obtain multiple intrinsic mode components that reflect the vibration characteristics of different frequency bands in the micro-vibration signal. Each intrinsic mode component is input into the corresponding time-series prediction model trained based on the echo state network. The time-series prediction model uses a sliding window mechanism to divide each intrinsic mode component into multiple signal components. The dynamic characteristics of satellite micro-vibration reflected by the corresponding intrinsic mode component are obtained through multiple signal components, so as to predict the micro-vibration signal of the satellite in the future. The micro-vibration signals of the satellite in the future multi-step prediction corresponding to all intrinsic mode components are superimposed as the feedforward compensation signal. Combined with the feedback compensation signal obtained by the PID method to suppress the satellite micro-vibration, the satellite micro-vibration is suppressed together.
2. The satellite micro-vibration suppression method according to claim 1, characterized in that, The step of inputting each intrinsic mode component into the corresponding time-series prediction model trained based on an echo state network includes: Based on the vibration characteristics of the corresponding frequency band in the micro-vibration signal reflected by each intrinsic mode component, the degree of influence of each intrinsic mode component on the satellite's operational performance is determined. Based on the degree of influence of each intrinsic mode component on satellite operation performance, the main intrinsic mode components whose influence on satellite operation performance is greater than a preset threshold are extracted from multiple intrinsic mode components; The main intrinsic mode components are input into the time series prediction model trained based on the echo state network.
3. The satellite micro-vibration suppression method according to claim 1, characterized in that, The time-series prediction model is obtained by training the echo state network using a random search algorithm.
4. The satellite micro-vibration suppression method according to claim 1, characterized in that, The acquisition of the satellite's micro-vibration signals includes: Micro-vibration signals of satellites were obtained based on the power spectrum characteristics of the SILEX system.
5. The satellite micro-vibration suppression method according to claim 1, characterized in that, The method of using the satellite's micro-vibration signals for the next N steps corresponding to all predicted intrinsic mode components as feedforward compensation signals, combined with feedback compensation signals obtained using the PID method to suppress satellite micro-vibrations, jointly suppresses satellite micro-vibrations, including: By using feedforward compensation signals and feedback compensation signals, the fast steering mirror (FSM) is jointly driven to suppress satellite micro-vibrations.
6. The satellite micro-vibration suppression method according to claim 1, characterized in that, The method further includes: The satellite's micro-vibration signal after micro-vibration suppression was acquired, and the corresponding probability density function and cumulative distribution function were constructed. The suppression performance of satellite micro-vibrations is evaluated based on the constructed probability density function and cumulative distribution function.
7. A satellite micro-vibration suppression system, characterized in that, The system includes: The data acquisition module is used to acquire the satellite's micro-vibration signals; The data decomposition module is used to decompose the micro-vibration signal using the variational mode decomposition method to obtain multiple intrinsic mode components that reflect the vibration characteristics of different frequency bands in the micro-vibration signal. The data prediction module is used to input each intrinsic mode component into the corresponding time-series prediction model trained based on the echo state network. The time-series prediction model uses a sliding window mechanism to divide each intrinsic mode component into multiple signal components, and obtains the dynamic characteristics of satellite micro-vibration reflected by the corresponding intrinsic mode component through multiple signal components, so as to predict the micro-vibration signal of the satellite in the future. The vibration suppression module is used to superimpose the micro-vibration signals of the satellite in the future multi-step prediction corresponding to all intrinsic mode components as a feedforward compensation signal, and combine it with the feedback compensation signal obtained by the PID method to suppress the satellite micro-vibration, so as to jointly suppress the satellite micro-vibration.
8. A computer device, characterized in that, include: At least one processor; And a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the satellite microvibration suppression method as described in any one of claims 1 to 6.
9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the satellite micro-vibration suppression method as described in any one of claims 1 to 6.