A portable satellite communication station signal dynamic alignment method and apparatus

Abstract

This invention discloses a method and apparatus for dynamic signal alignment of a portable satellite communication station, designed for the field of satellite-to-ground communication to optimize the real-time performance and stability of communication links. The invention includes: constructing a multi-agent cooperative orbit model describing the three-dimensional dynamic coupling relationship between the portable satellite communication station, a UAV, and the satellite; analyzing the key influencing factors and their degree of influence on communication link performance through causal reasoning based on the multi-agent cooperative orbit model and environmental observation data; performing dynamic channel state prediction on the key influencing factors based on the multi-agent cooperative orbit model and causal reasoning results; and adjusting antenna alignment and compensating for errors based on the dynamic channel state prediction results. This invention addresses the problem of insufficient adaptability of traditional technologies in complex dynamic environments, improving the accuracy, real-time performance, and adaptability of antenna alignment.

Description

Technical Field

[0001] This invention relates to the field of satellite-to-ground communication, and in particular to a method and apparatus for dynamic signal alignment of a portable satellite communication station. Background Technology

[0002] In complex and dynamic environments, portable satellite communication stations have become crucial communication hubs in unmanned aerial vehicle (UAV) scenarios, widely used in disaster relief, military operations, and remote monitoring. However, with the rapid development of UAV technology, their high dynamic characteristics and multi-degree-of-freedom motion pose new challenges to satellite communication, especially in harsh environments, requiring an optimized communication strategy capable of handling dynamic alignment and environmental changes.

[0003] First, the high-speed flight and multi-degree-of-freedom attitude changes (such as pitch, roll, and yaw) of UAVs place stringent requirements on the dynamic alignment of portable satellite communication station antennas. Traditional static alignment or regular adjustment methods can no longer meet their high dynamic and real-time demands. In collaborative communication between low-Earth orbit satellites and UAVs, signal offset caused by alignment errors often leads to communication interruptions, significantly affecting link stability. Furthermore, the rapid changes in the UAV's trajectory further increase the complexity of channel adjustment due to the Doppler shift of the signal.

[0004] Secondly, rainfall (or rain attenuation), as a major environmental factor affecting channel quality, has a particularly significant impact on UAV scenarios, especially in the higher-frequency Ka band. Rainfall causes significant signal attenuation along the propagation path, manifesting as increased path loss, reduced signal-to-noise ratio, and even communication interruption. This phenomenon not only affects communication quality but may also lead to wasted link transmission power. Traditional techniques typically perform static compensation of channel states based on a single rain attenuation parameter, failing to consider the complex coupling relationship between rain attenuation and UAV trajectory changes. In complex dynamic environments, rain attenuation and UAV motion interact, making channel quality prediction, compensation, and optimization a multivariate coupled problem.

[0005] Furthermore, the resource allocation of portable satellite communication stations faces severe conflicts due to the combined effects of rain attenuation and changes in drone trajectories. Traditional communication power and frequency allocation typically rely on preset rules or fixed thresholds, lacking the ability to adjust in real time for complex dynamic environments. The allocation of communication power and dynamic adjustment of frequency need to be completed in real time under the trade-off of multiple factors. Traditional algorithms are insufficient in both efficiency and adaptability when dealing with complex dynamic changes.

[0006] In summary, coordinating rain attenuation compensation, UAV trajectory prediction, and channel resource allocation has become a key technical challenge in improving the robustness and stability of communication links. Summary of the Invention

[0007] The purpose of this invention is to provide a method and apparatus for dynamic alignment of portable satellite communication station signals, addressing all or part of the problems mentioned above, so as to effectively combine the high dynamic motion characteristics of UAVs with the dynamic alignment of portable satellite communication stations in complex environments, thereby optimizing the real-time performance and stability of the communication link.

[0008] The technical solution adopted in this invention is as follows:

[0009] A method for dynamic signal alignment of a portable satellite communication station, comprising:

[0010] S1. Construct a multi-agent collaborative orbit model that describes the three-dimensional dynamic coupling relationship between portable satellite communication stations, UAVs, and satellites;

[0011] S2. Based on the multi-subject collaborative orbit model and environmental observation data, analyze the key influencing factors and their degree of influence on communication link performance through causal reasoning;

[0012] S3. Based on the multi-agent collaborative orbit model and causal inference results, perform dynamic channel state prediction on the key influencing factors;

[0013] S4. Antenna alignment adjustment and error compensation are performed based on dynamic channel state prediction results.

[0014] In addition, this application also provides a portable satellite communication station signal dynamic alignment device, including a processor and a storage medium, wherein the storage medium stores a computer program, and the processor executes the above-described portable satellite communication station signal dynamic alignment method when running the computer program.

[0015] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0016] This application addresses the shortcomings of traditional technologies in complex dynamic environments by constructing a multi-agent collaborative orbit model, analyzing link influencing factors through causal reasoning, predicting dynamic channel states, and employing antenna adjustment and error compensation strategies based on the prediction results. Compared to traditional technologies, this application improves the accuracy, real-time performance, and adaptability of antenna alignment. Attached Figure Description

[0017] The present invention will be described by way of example and with reference to the accompanying drawings, wherein:

[0018] Figure 1 This is a flowchart of a portable satellite communication station signal dynamic alignment method provided in an embodiment of this application. Detailed Implementation

[0019] All features disclosed in this specification, or all steps in all disclosed methods or processes, may be combined in any way, except for mutually exclusive features and / or steps.

[0020] Any feature disclosed in this specification (including any appended claims and abstract) may be replaced by other equivalent or similar features, unless specifically stated otherwise. That is, unless specifically stated otherwise, each feature is merely one example of a series of equivalent or similar features.

[0021] To address the shortcomings of traditional portable satellite communication station signal alignment methods in adaptability and real-time performance in highly dynamic environments, this application proposes a portable satellite communication station signal dynamic alignment method and apparatus. This method effectively combines the high-dynamic motion characteristics of UAVs with the dynamic alignment of portable satellite communication stations in rain-attenuated environments, thereby optimizing the real-time performance and stability of the communication link.

[0022] The portable satellite communication station signal dynamic alignment method provided in this application includes the following steps:

[0023] S1. Construct a multi-agent collaborative orbit model that describes the three-dimensional dynamic coupling relationship between portable satellite communication stations, drones, and satellites.

[0024] As an optional implementation, step S1 above includes the following sub-steps S11-S14, which are used to establish an orbital model that can characterize multi-subject collaborative (communication) operation by combining the high dynamic motion characteristics of the UAV, the on-orbit operation law of the satellite, and the location of the ground station.

[0025] S11. Acquire the trajectory data of the portable satellite communication station, the UAV and the satellite respectively, and unify the coordinate reference.

[0026] In some feasible implementations, sub-step S11 includes:

[0027] S11.1: Obtain the satellite's on-orbit operational parameters (i.e., trajectory data), including the satellite's orbital radius R. s Satellite angular velocity ω s and initial phase φ s And record the geographical location information (X) of the ground portable satellite communication station. g ,Y g Z g This refers to the trajectory data of portable satellite communication stations.

[0028] S11.2: Collect the flight trajectory data of the UAV, including the UAV's initial position (X). u (0),Y u (0),Z u (0)), velocity vu (t) and heading angle α u (t), and the pitch angle, roll angle and yaw angle corresponding to the change in attitude of the UAV.

[0029] S11.3: The spatial positions of the aforementioned multiple entities are described using a unified geocentric coordinate system. A coordinate transformation matrix is ​​used to align the local coordinates of the UAV with the global coordinates of the ground portable satellite communication station and the satellite, resulting in a three-dimensional position vector of the satellite, UAV, and ground portable satellite communication station under the same coordinate reference, denoted as:

[0030] p s (t)=[X s (t),Y s (t),Z s (t)] T ,p u (t)=[X u (t),Y u (t),Z u (t)] T ,p g =[X g ,Y g Z g ] T

[0031] Where, p s (t) represents the satellite's trajectory position over time, p u (t) represents the drone's flight position over time, p g This indicates the fixed location of a ground-based portable satellite communication station.

[0032] S12. Establish a satellite orbit model describing the satellite's on-orbit position based on satellite trajectory data.

[0033] In some feasible implementations, sub-step S12 includes:

[0034] S12.1: Based on the acquired satellite in-orbit operating parameters, a circular orbit model is used to parameterize the satellite's position:

[0035]

[0036] Among them, R s Let ω be the orbital radius. s φ is the satellite's angular velocity. s For the initial phase, h s The height is approximately constant.

[0037] S12.2: The satellite position vector p obtained in step S12.1 is... s(t) is aligned with the coordinate reference obtained in S11.3 to obtain satellite on-orbit motion data consistent with the geocentric-ground-fixed coordinate system, providing basic input for subsequent multi-subject collaborative orbit model.

[0038] S13. Based on the trajectory data of the UAV, establish a motion model describing the flight trajectory of the UAV, and couple the attitude change information of the UAV to obtain the UAV orbit model.

[0039] In some feasible implementations, sub-step S13 includes:

[0040] S13.1: Based on the speed and heading angle information of the UAV, a discretized time-varying equation is used to describe the flight trajectory of the UAV, which can be specifically expressed as:

[0041]

[0042] Where Δt is the discrete sampling time step, v u (t) represents the speed of the UAV in the horizontal plane, α u (t) represents the real-time heading angle of the horizontal motion, Δh u (t) represents the height increment of the UAV along the vertical direction.

[0043] S13.2: Based on step S13.1, in order to accurately characterize the attitude changes of the UAV, the pitch angle β is... u (t), roll angle γ u (t) and yaw angle δ u (t) Synchronous recording is performed, and these attitude parameters are mapped to the three-dimensional coordinate transformation matrix R. u (t), update the precise attitude vector A of the UAV in the coordinate system. u (t). This attitude vector plays a role in correcting the line-of-sight vector during subsequent channel assessment and antenna alignment.

[0044] S14. Couple the satellite orbit model, the UAV orbit model, and the trajectory data of the portable satellite communication station to obtain a multi-entity collaborative orbit model.

[0045] In some feasible implementations, sub-step S14 includes:

[0046] S14.1: Based on the orbital model obtained in sub-steps S12 and S13, determine the satellite's on-orbit position p. s (t), UAV position p u (t) and its attitude A u (t), Location of ground portable satellite communication station p g A multi-entity cooperative orbit model for channel assessment and antenna alignment is established through overall coupling.

[0047] S14.2: Store the multi-agent cooperative orbit model obtained in step S14.1 and call it in subsequent steps to form a complete spatiotemporal coordinate sequence {p s (t),p u (t),A u (t),p g This spatiotemporal coordinate sequence can provide a high-precision input for subsequent processes such as rain attenuation compensation, Doppler frequency shift estimation, and antenna error correction.

[0048] S14.3: In the multi-agent cooperative orbit model, to further evaluate the dynamic channel, this embodiment defines a Doppler frequency shift f. d (t) is used to characterize the offset of the signal transmission frequency caused by the relative motion between the satellite and the UAV:

[0049]

[0050] Where f0 is the carrier center frequency, v s (t) and v u (t) represent the instantaneous velocity vectors of the satellite and the UAV, respectively. Let be the unit vector pointing from the transmitter to the receiver, and c be the propagation speed of the electromagnetic wave in free space. The Doppler frequency shift obtained in this step can be used in subsequent steps to correct the signal receiving frequency and alignment errors of the portable satellite communication station.

[0051] S2. Based on a multi-agent collaborative orbital model and environmental observation data, the key influencing factors and their degree of influence on communication link performance are analyzed through causal reasoning.

[0052] As an optional implementation, step S2 includes sub-steps S21-S24, which use the output of the multi-agent cooperative orbit model constructed in step S1 as input to perform causal relationship modeling, identify the interaction mechanism between environmental and link influencing factors, and provide data support and logical basis for subsequent dynamic channel prediction and antenna error compensation.

[0053] S21. Obtain the multi-entity collaborative orbit model and load environmental observation data.

[0054] In some feasible implementations, sub-step S21 includes:

[0055] S21.1: Call the multi-agent cooperative orbit model output from step S1 {p s (t),p u (t),A u (t),p g}, where p s (t) represents the satellite's position in orbit, p u(t) represents the drone's position, A u (t) represents the UAV attitude vector, p g Indicates the location of a ground-based portable satellite communication station.

[0056] S21.2: Based on S21.1, load the observation dataset related to the external environment, including rainfall intensity r(t) and its spatiotemporal distribution, meteorological radar data, and Geographic Information System (GIS) data. Align these environmental observation data with the orbital model in the time dimension to obtain the environmental observation data sequence {E(t)}, where E(t) can be expressed as E(t)=[r(t),θ rain (t),…],θ rain (t) can be regarded as a marker of rainfall direction or region, used for spatial positioning in subsequent rainfall attenuation calculations.

[0057] S22. Based on the multi-subject collaborative orbit model and environmental observation data, construct a causal relationship diagram describing the causal path between environmental influencing factors and communication link performance, and identify key influencing factors and causal paths from the causal relationship diagram.

[0058] In some feasible implementations, sub-step S22 includes:

[0059] S22.1: Based on the multi-agent collaborative orbit model and environmental observation data obtained in sub-step S21, clarify the causal paths between different variables by constructing a causal relationship diagram. Potential factors that may lead to communication interruption or link quality degradation are categorized as dependent or independent variables. These potential factors include, but are not limited to, rainfall intensity r(t), Doppler shift f... d (t), antenna pointing deviation δ ant (t) and UAV attitude change parameters A u (t).

[0060] S22.2: Define the meaning of information flow for each node and directed edge in the causal relationship graph, as follows:

[0061] Node r(t): represents the rainfall intensity at the current moment;

[0062] node f d (t): represents the Doppler frequency shift derived from the multi-subject cooperative orbit model constructed in step S1;

[0063] node δ ant (t): represents the instantaneous pointing error of the antenna;

[0064] Node A u (t): represents the attitude change of the UAV;

[0065] Node Q link(t): Represents link performance metrics (such as signal-to-noise ratio or signal received power).

[0066] In this embodiment of the application, if r(t)→Q exists in the causal relationship graph... link If there is a directed edge (t), it indicates that the rainfall intensity has a direct causal impact on the link performance index; if there exists A u (t)→δ ant (t)→Q link (t) indicates that changes in the UAV's attitude indirectly affect the link performance indicators through antenna pointing deviation. The other nodes in the causal relationship diagram are similar. Based on this, key influencing factors can be identified through the causal relationship diagram.

[0067] S22.3: Screening the main causal paths affecting satellite communication quality in the application scenarios of this application embodiment, for example, by screening according to empirical rules. The screened causal paths are recorded in the form of a directed acyclic graph (DAG) to lay a structural foundation for subsequent parameter learning and interference source localization.

[0068] S23. Based on the causal relationship diagram, the influence relationship of key influencing factors on the performance of communication links is parameterized.

[0069] In some feasible implementations, sub-step S23 includes:

[0070] S23.1: The impact of rainfall intensity r(t) on link channel loss is selected as a typical causal path. The modified rain attenuation loss model is used to parameterize this impact. Let the additional path loss caused by rainfall be L. rain (t), defined as:

[0071] L rain (t)=α·r(t) β ·d,

[0072] Where α and β are attenuation coefficients calibrated from experience or test data, and d is the path length of the signal propagation within the rainfall area. This formula is used in the embodiments of this application to measure the degree of channel attenuation caused by rainfall intensity.

[0073] S23.2: Based on the relative velocity and position vectors obtained from the multi-agent cooperative orbit model, the representation of the Doppler frequency shift is corrected. Let the Doppler frequency shift f be... d (t) for link performance metrics Q link The effect of (t) is described by a logarithmic decay relationship, which is expressed as:

[0074] Q link (t)=Q0-10log(1+k·|f d (t)|),

[0075] Where Q0 is the baseline link quality index, k is the ratio constant used to quantify the Doppler effect, and |f d (t)| represents the absolute value of the Doppler frequency shift.

[0076] The above equations demonstrate how the increased communication carrier offset due to Doppler shift leads to a decrease in system demodulation performance.

[0077] S23.3: Regarding antenna pointing deviation δ ant (t), in this embodiment of the application, based on the cumulative effect of attitude change and alignment error, it is assumed that the impact of antenna deviation on link performance has a multiplicative amplification characteristic, and can therefore be expressed as:

[0078] Q link (t)←Q link (t)exp(-λδ ant (t)),

[0079] Wherein, λ is a parameter characterizing the sensitivity of the antenna alignment error.

[0080] By combining the above formula with the rain attenuation model in S23.1 and the Doppler model in S23.2, we can construct the main causal equation system of key influencing factors in the causal relationship diagram, thereby achieving parameterized characterization of the influence relationship of key influencing factors on communication link performance.

[0081] S24. Based on the causal relationship diagram and the parameterized characterization results of key influencing factors, assess the degree of influence of key influencing factors in the causal path and obtain the causal inference results.

[0082] As an optional implementation, the degree of impact assessed in sub-step S24 includes the causal path contribution value of the key influencing factors to the communication link performance, and the importance of the key influencing factors to the communication link performance. In some feasible implementations, sub-step S24 includes:

[0083] S24.1: Based on the causal relationship graph constructed in sub-step S22 and the parameterized characterization results in sub-step S23, the rainfall intensity r(t) and Doppler frequency shift f are analyzed. d (t), antenna pointing deviation δ ant (t) and the drone attitude A u (t) and other key nodes were quantitatively evaluated for causal effects to obtain a description of the impact of these key influencing factors on the link performance index Q. link (t) The contribution value of the causal path that has a direct or indirect impact.

[0084] S24.2: Rank the relative importance of key influencing factors in the causal path to identify the most significant link interference sources under different flight periods or rainfall conditions. If a factor (e.g., sudden rainfall) is found to cause significant degradation to the communication link in a short period of time, it is marked as a high-priority warning factor. Subsequent steps will be based on the priority marking results of each key influencing factor to design dynamic channel prediction and antenna compensation strategies.

[0085] S24.3: Output the causal reasoning results of S24.1 and S24.2, and interface with the dynamic channel prediction and resource scheduling module in subsequent steps to achieve forward-looking identification and comprehensive consideration of environmental and link changes.

[0086] S3. Based on the multi-agent collaborative orbit model and causal inference results, dynamic channel state prediction is performed on key influencing factors.

[0087] Step S3 takes the causal inference result output from step S2 and the multi-agent cooperative orbit model output from step S1 as its main inputs. It performs dynamic channel state prediction for complex rain attenuation environments, Doppler frequency shift, and antenna pointing deviation, aiming to provide timely and accurate prior information for subsequent antenna alignment compensation, power control, and resource scheduling. As an optional implementation, step S3 includes the following sub-steps:

[0088] S31. Extract key influencing factors from the causal reasoning results and synchronize them over time.

[0089] In some feasible implementations, sub-step S31 includes:

[0090] S31.1: Data Integration and Time Synchronization

[0091] Extract key influencing factors (i.e., the set of key variables) from the causal inference results output in step S2, including rainfall intensity r(t) and Doppler shift f. d (t), antenna pointing deviation δ ant (t) and the drone attitude A u (t). Obtain the collaborative orbit data of the portable satellite communication station, the UAV, and the satellite from the multi-agent collaborative orbit model constructed in step S1, denoted as p respectively. s (t), p u (t), p g To ensure alignment of multi-source data in the same time coordinate system, a unified multivariate time series dataset is constructed based on the minimum time difference criterion or interpolation method.

[0092]

[0093] Q link(t) represents the link performance metrics at the current moment (e.g., signal-to-noise ratio or received power).

[0094] S31.2: Outlier detection and cleaning.

[0095] In multivariate time series datasets The dataset detects missing values ​​that may be caused by measurement anomalies or communication packet loss. If missing values ​​are found, piecewise linear interpolation is used to repair them. If extreme outliers are detected, they are removed based on three times the standard deviation, resulting in a more complete and consistent dataset.

[0096] S31.3: Data initialization and segmentation.

[0097] Dataset The model is divided into a training set and a validation set along the time dimension. The training set is used for learning model parameters, while the validation set is used for evaluating subsequent prediction performance and tuning hyperparameters. Let the training set be... The validation set is During initialization, the periods of most severe rain attenuation and high-speed UAV maneuvers are labeled based on prior knowledge, providing a reference for model fitting in subsequent steps.

[0098] S32. Construct a multi-dimensional state-space model to describe the state of influence of the communication link, and impose collaborative constraints on states that have mutual influence.

[0099] In some feasible implementations, sub-step S32 includes:

[0100] S32.1: Definition of multidimensional state vector.

[0101] In this embodiment, dynamic channel prediction is considered as a joint inference process of estimating internal system state variables and changes in external environmental factors. The state vector S(t) is defined to include the internal state of the communication link (such as channel attenuation coefficient and frequency offset) and the environmental influence state (such as rain attenuation level and Doppler component), specifically expressed as:

[0102] S(t)=[α ch (t),Δf(t),δ ant (t),r(t),…] T

[0103] Where α ch (t) can be regarded as the instantaneous channel attenuation factor, and Δf(t) represents the dynamic quantization of Doppler frequency offset.

[0104] S32.2: Definition of state transition equation and observation equation.

[0105] In a multidimensional state-space model, the state transition equation is defined as follows:

[0106] S(t+1)=F(S(t),U(t))+w(t)

[0107] Where F is the state transition function, U(t) is the system input or disturbance (such as UAV acceleration, abrupt change in rain attenuation distribution), w(t) is the process noise, and the observation equation is defined as follows:

[0108] Y(t)=H(S(t))+v(t)

[0109] Where Y(t) represents the observable link performance (Q) link The function mapping of v(t) to the orbital data, where v(t) is the measurement noise.

[0110] Based on the above equations, we ensure that the evolution of S(t) is physically interpretable, and combine the causal graph information from step S2 to embed the coupling relationship between key variables in F and the observation function H.

[0111] S32.3: Cooperative constraints on causal priors.

[0112] Based on the causal relationship diagram generated in step S2, and based on the Doppler frequency shift f d (t) for α ch The characteristic of α having a significant nonlinear effect is addressed by explicitly including this effect term in the definition of F(S(t),U(t)), i.e., for α. ch The update of (t) introduces the sigmoid function:

[0113] α ch (t+1)=α ch (t)sigmoid(κf d (t)),

[0114] Where κ is the scaling factor, used to control the magnitude of the effect of Doppler frequency shift on the channel attenuation factor.

[0115] S33. Construct a time-series prediction network that takes the current state vector and observation vector of the multidimensional state-space model as input and the state vector and communication link performance of the next time step as output.

[0116] In some alternative implementations, sub-step S33 includes:

[0117] S33.1: High-order timing model structure design.

[0118] In this embodiment, to capture complex temporal correlations, a multidimensional state vector S(t) and its observation vector Y(t) are used as inputs based on LSTM to learn short-term and long-term dependencies. The network core mapping is denoted as Φ(S(t)), which is used to predict the next time step S(t+1) and the link performance Q. link(t+τ).

[0119] S33.2: Multi-step prediction and output mapping.

[0120] To obtain multi-step prediction results (t+1, t+2, ..., t+τ), this embodiment of the application connects a decoupled output header to the last layer of the LSTM, and establishes mappings for the outputs at different prediction times:

[0121]

[0122] Where h LSTM (t) is the hidden state vector of the LSTM network at time t, W o and b o For learnable parameter matrix and bias.

[0123] Based on this strategy, multiple prediction results can be obtained simultaneously in a single forward propagation, improving real-time performance.

[0124] S33.3: Attention mechanism that combines orbital characteristics with attitude coupling.

[0125] This application also takes into account the attitude changes of the UAV. u (t) and the satellite's relative position p s (t) Correlation with link metrics, an attention mechanism is added to the LSTM hidden layer. Let z t For the hidden layer output, a context vector c is introduced at that time step. t To measure the importance of drone attitude and satellite orientation to current forecasts:

[0126]

[0127] in,

[0128] e t,τ′ =ATTN(z τ′ A u (t),p s (t))

[0129] ATTN(·) is the attention scoring function, which comprehensively considers the influence of attitude and satellite position on z. τ′ Weighted average.

[0130] This mechanism is used to characterize important moments in highly dynamic scenarios, thereby improving the sensitivity and accuracy of predictions.

[0131] S34. Construct the loss function for the time series prediction network.

[0132] In some feasible implementations, sub-step S34 includes:

[0133] S34.1: Construct a multi-objective loss function.

[0134] To take into account different prediction objectives ( and To improve the accuracy of multi-target loss during network training, this application defines the following in its embodiments:

[0135]

[0136] Where S true (t) is the true state vector that may be measurable at some time or estimated from priors, and α1 and α2 are weighting coefficients used to balance the link index prediction error and the internal state estimation error.

[0137] S34.2: Incorporation of regularization terms and causal constraints.

[0138] exist Further regularization constraints on model complexity, denoted as Ω(Θ), are added to prevent overfitting. Furthermore, based on the causal analysis results from step S2, it is shown that a certain key influencing factor has monotonicity or sparsity requirements on link performance. Therefore, a non-negativity constraint is added in this embodiment, specifically the attenuation influence coefficient α on rainfall intensity r(t). rain Apply α rain The constraint ≥0 ensures the physical rationality of the model.

[0139] S35. Use the data obtained in sub-step S31 to train the time series prediction network.

[0140] In some optional implementations, sub-step S35 includes:

[0141] S35.1: Initialization and Batch Training.

[0142] Initialize the network's learnable parameters to small random values. Set the dataset... The data is divided into mini-batches, and the loss function is calculated using forward propagation. Then, the parameters are updated using the Adam optimization algorithm.

[0143] S35.2: Gradient Calculation and Update Formula

[0144] The update of Adam's general parameter Θ can be expressed as:

[0145]

[0146] Where m Θ With v Θ These represent first-order and second-order momentum estimates, respectively, where β1 and β2 are hyperparameters, η is the learning rate, and ∈ is the numerical stability term. This update process is performed after each training batch until the loss function converges or a specified number of rounds is reached.

[0147] S35.3: Dynamic learning rate and early stopping strategy.

[0148] During training, if it is found that the loss function no longer decreases significantly after several rounds, the learning rate η is dynamically adjusted, and an early stopping strategy is used to prevent overfitting and excessive consumption of training time.

[0149] S36. Using the trained temporal prediction network, predict the communication link performance and the multidimensional state space model in the target scenario based on the current multidimensional state space model.

[0150] In some feasible implementations, sub-step S36 performs short-term and medium-to-long-term trend predictions of the communication link performance, and perturbs the input data to improve the prediction's anti-interference capability. Specifically, sub-step S36 includes:

[0151] S36.1: Short-time prediction and adaptive output.

[0152] In practical satellite communications, to guide antenna alignment and power allocation in a timely manner, embodiments of this application propose that the link performance index Q from t+1 to t+τ can be monitored in online mode. link Perform short-term forecasting and output the predicted values. And its reliable measurement. If the drone attitude A is detected u (t) will undergo significant changes, triggering the internal network (AttentionLayer, which is the previous attention layer) to further strengthen the weights on pose-related components.

[0153] S36.2: Medium- and Long-Term Trend Forecast.

[0154] Furthermore, due to the relatively slow spatial propagation characteristics of rainfall, this application also proposes an environmental prediction method for longer time scales (t+τ′, τ′>>τ). Within the existing model framework, an exponential regression form is established for rainfall intensity r(t) and other slowly varying parameters, thereby providing medium- to long-term channel quality trend estimates at the minute to hour level for collaborative scheduling and backup resource planning.

[0155] S36.3: Uncertainty Analysis and Diversity Prediction.

[0156] Furthermore, to more accurately respond to sudden environmental changes, this application proposes to further employ Monte Carlo simulation to perturb w(t) and v(t) and generate predicted distributions under different scenarios. For extreme conditions that may result in significant rain attenuation or high-speed flight, assess their probability of impact on the distribution tail to enable the system to make early intervention decisions during the warning phase.

[0157] In addition, in an optional implementation, step S3 further includes sub-step S37: outputting the dynamic channel prediction result of sub-step S36.

[0158] In some feasible implementations, sub-step S37 includes:

[0159] S37.1: Generate a comprehensive forecast report.

[0160] Based on the short-term and medium-to-long-term forecast results obtained in sub-step S36, and combined with the causal weights of key influencing factors such as attitude, rain attenuation, and Doppler frequency shift, the forecast values ​​and uncertainty ranges are output in a structured format to form a comprehensive forecast report R, either visualized or numerical. pred The report includes real-time... Estimated values ​​and link risk assessment values ​​(such as the probability of interruption).

[0161] S37.2: Feedback and Collaborative Applications.

[0162] Comprehensive forecast report R pred Together with state vector estimation The data is submitted to the satellite communication station control module or the UAV navigation system. If rain attenuation is detected to increase significantly in the short term, an antenna power boost command is issued in advance or the system switches to a backup frequency band. If a drastic change in the UAV's attitude is detected, the antenna pointing adjustment subsystem is triggered to perform pre-calibration, thereby reducing the risk of link interruption.

[0163] S4. Antenna alignment adjustment and error compensation are performed based on dynamic channel state prediction results.

[0164] After completing the dynamic channel state prediction for rain attenuation, Doppler shift, and attitude disturbance factors, this step, based on the prediction results and state estimation output in step S3, performs multi-stage optimization and execution of the antenna alignment strategy and error compensation scheme for portable satellite communication stations to ensure effective avoidance of link interruption and continuous guarantee of communication quality in high-speed maneuvering and complex environments.

[0165] In one optional implementation, step S4 includes the following sub-steps:

[0166] S41. Obtain the dynamic channel state prediction results and extract key information related to antenna alignment error.

[0167] In some feasible implementations, sub-step S41 includes:

[0168] S41.1: Analyze the prediction results and uncertainty indicators.

[0169] Call the comprehensive forecast report R output in step S3 pred Extract short-term data from it. and medium to long term The predicted value of the communication link quality is combined with the corresponding confidence interval or uncertainty quantification index.

[0170] S41.2: Extract antenna error sensitivity parameters.

[0171] Analysis and antenna alignment error δ ant (t) Relevant sensitivity information, including causal inference or prediction models for δ ant The importance assessment value, denoted as λ sens This is used to determine the priority of subsequent antenna adjustment schemes.

[0172] S41.3: Multi-channel information fusion.

[0173] If the system has other monitoring channels (such as satellite backup links or surrounding weather radar information), their observations are integrated into the antenna adjustment process of this application embodiment to further improve the completeness of the adjustment decision.

[0174] S42. Construct a mapping model between the antenna attitude and the line-of-sight vector, and characterize the antenna pointing error based on this mapping model.

[0175] In some feasible implementations, sub-step S42 includes:

[0176] S42.1: Define the antenna attitude vector.

[0177] In this embodiment of the application, the elevation angle θ of the antenna body is... EL (t), azimuth angle θ AZ (t) and polarization angle θ POL (t) are combined into the antenna attitude vector Θ ant (t).

[0178] S42.2: Coupling of line-of-sight vector and position coordinates.

[0179] To facilitate subsequent alignment adjustments, a line-of-sight vector is defined. The direction pointing towards the target, and its relationship with the antenna attitude vector, can be expressed as:

[0180]

[0181] Where R(·) is the rotation matrix constructed from the attitude angles, u z This is the reference orientation in the antenna coordinate system (e.g., vertically upward by default).

[0182] Based on this It can be compared with the target position p in step S1 s (t) or p u(t) is compared to measure the pointing error of the antenna.

[0183] S42.3: Angle measurement of antenna pointing error.

[0184] Let the target direction vector (starting from the relative position of the antenna) be . Based on inner product operations, the pointing error δ can be defined. ant (t) is:

[0185]

[0186] like and For perfect alignment, the inner product is 1, δ ant (t) = 0.

[0187] S43. Generate an antenna alignment strategy based on the dynamic channel state prediction results.

[0188] In some feasible implementations, sub-step S43 includes:

[0189] S43.1: Generate a segmented alignment strategy.

[0190] Combined with the short-term forecast given in step S3 Considering factors such as rainfall intensity r(t+1), the embodiments of this application dynamically adjust the antenna attitude within each sampling period. If it is predicted that rain attenuation or Doppler shift will increase, priority is given to ensuring the antenna angle alignment accuracy, and if necessary, the upper limit of the tracking rate of the elevation and azimuth axes is increased.

[0191] S43.2: Definition of objective function.

[0192] During the segmented alignment process, the antenna attitude target at one moment is recorded as follows. It is obtained through the following optimization objectives:

[0193]

[0194] Where δ ant (t+1) is calculated based on the definition in (S42.3), Q link (t+1) is the expected value of the link quality predicted in step S3, and w1 and w2 are weighting factors used to make a trade-off between alignment error and link performance.

[0195] S43.3: Priority Inheritance and Multi-Objective Balancing.

[0196] If the prediction indicates that the attitude change is extremely drastic (e.g., the drone turns at high speed), the degree of drasticness can be determined according to the corresponding threshold or rules. Then, w1 is appropriately increased according to the pre-defined rules to prioritize reducing antenna deviation. If rain attenuation is predicted to occur suddenly, w2 is increased according to the pre-defined rules to highlight the need to ensure link performance.

[0197] S44. Match the transmit power compensation to the antenna alignment strategy.

[0198] In some feasible implementations, sub-step S44 includes:

[0199] S44.1: Define the error compensation gain factor

[0200] In this embodiment of the application, in order to further offset the effective received power attenuation caused by pointing error, a transmit power compensation factor Γ(t) is configured simultaneously with alignment, that is, Γ(t) and δ ant (t) has a negative logarithmic correlation:

[0201] Γ(t)=exp(-η0δ ant (t))

[0202] Where η0 is an adjustable parameter.

[0203] If δ ant If Γ(t) is large, then Γ(t) tends to a smaller value, and the transmission power P is increased. tx (t) or increase the RF gain G rx (t) to compensate for the losses caused by alignment deviations.

[0204] S44.2: Cooperative power allocation.

[0205] Considering the combined effects of rain attenuation, antenna misalignment, and Doppler frequency shift on the link, this application proposes the following cooperative equation for power allocation:

[0206] P out (t)=P base +κ r r(t) β +κ δ δ ant (t)+κ f |f d (t)|

[0207] Where P out (t) represents the actual transmission power, P base As the reference power, (κ) r ,β),κ δ ,κ fThese are the compensation coefficients for rain attenuation, pointing deviation, and Doppler frequency shift, respectively. Based on the matching relationship between the output of this formula and Γ(t), joint optimization of alignment and power is achieved.

[0208] In addition, as an optional implementation, step S4 may also include the following sub-steps:

[0209] S45. Define the constraints on antenna maneuvers in the antenna alignment strategy.

[0210] This sub-step S45 imposes corresponding constraints on the antenna alignment strategy based on the physical conditions of the antenna maneuvering platform. In some feasible implementations, this sub-step S45 includes:

[0211] S45.1: Physical limitations of the mobile platform

[0212] On a real antenna maneuvering platform, there are upper limits to the maneuvering speed of the elevation and azimuth axes. and the upper limit of acceleration When it is predicted that the drone will perform high-speed maneuvers at time t+1, it should be determined whether the required antenna rotation exceeds the limit. If it exceeds the platform's physical capabilities, adjustments should be made in advance, such as adjusting to align at the maximum maneuver speed or the maximum acceleration limit.

[0213] S45.2: Speed ​​Limit Planning.

[0214] To ensure the mobile platform does not exceed its physical limits, the pitch angle is adjusted by Δθ. EL (t+1) and azimuth adjustment Δθ AZ Speed ​​limiting planning is performed at (t+1):

[0215]

[0216] The same principle applies to the azimuth speed limit planning. Based on this plan, it can be ensured that the rotation amount within each sampling period Δt does not exceed the limit, and acceleration constraints can be further considered to prevent mechanical overload or speed oscillation.

[0217] S46. Execute the antenna alignment strategy and monitor the execution results.

[0218] In some feasible implementations, sub-step S46 includes:

[0219] S46.1: Execute antenna alignment strategy online (including compensation for transmit power).

[0220] After completing the Power compensation P out After multiple calculations of (t) and antenna maneuver constraints, a comprehensive command is sent to the antenna execution module of the portable satellite communication station to realize the synchronous execution of operations such as antenna attitude adjustment and transmit power gain.

[0221] S46.2: Real-time error and link quality detection.

[0222] During system execution, the current antenna pointing error δ is calculated. ant (t) and link metric Q link (t) Monitor the data and compare it with the prediction results from step S3. If the actual error or link attenuation is significantly higher than the model prediction, immediately trigger a security strategy or a secondary adjustment process to prevent further degradation of communication quality.

[0223] S47. Perform dynamic iteration and feedback optimization based on monitoring results.

[0224] In some feasible implementations, sub-step S47 includes:

[0225] S47.1: Error accumulation correction.

[0226] If the antenna alignment deviation accumulates excessively over a period of time (which can be determined by a preset threshold) or the deviation between the predicted and measured link quality increases (which can be determined by the deviation over a greater number of adjacent moments), then an iterative correction process is initiated. This is achieved by comparing the actual δ... ant The difference between (t) and the predicted value in step S3 is used to correct λ. sens κ δ These key parameters enable subsequent alignment and compensation strategies to better fit the real-time environment.

[0227] S47.2: Long-term feedback and cause-effect graph update.

[0228] Over a longer timescale (e.g., after several large-angle adjustments), the error compensation records and alignment logs are fed back to the causal reasoning module (step S2) and the dynamic prediction model (step S3) to enhance their adaptability to special cases (heavy rain attenuation, extreme Doppler shift, etc.) and continuously improve the closed-loop self-learning capability of the alignment method of this application.

[0229] S47.3: Output the execution result.

[0230] Finally, the antenna alignment and error compensation results of the final iteration are encapsulated into a detailed execution log or data packet for output, including the final antenna attitude Θ. ant (t), transmission power P out (t) and the observed δ ant (t) and Q link (t).

[0231] This application also provides a portable satellite communication station signal dynamic alignment device, which includes a processor and a storage medium. The storage medium stores a computer program, and when the processor runs the computer program, it executes the portable satellite communication station signal dynamic alignment method described above.

[0232] Through the above design, firstly, this application constructs a multi-entity cooperative orbit model to establish a three-dimensional cooperative motion trajectory of a low-Earth orbit satellite, a UAV, and a ground-based portable satellite communication station. It then employs an attitude transformation matrix and trajectory coupling method to establish the fundamental model required for dynamic channel optimization. This surpasses traditional static pointing models or simple rule-based adjustment strategies, which cannot effectively handle the impact of high-speed UAV flight and multi-degree-of-freedom attitude changes on antenna pointing. In contrast, this application explicitly introduces dynamic parameterization of Doppler frequency shift and antenna error in trajectory modeling, which not only improves the model's dynamic adaptability but also provides higher-precision input for subsequent dynamic alignment.

[0233] Secondly, regarding environmental factor modeling and causal reasoning, this application quantifies the causal relationships between key link factors such as rain attenuation, Doppler frequency shift, and antenna pointing deviation by constructing a causal relationship graph, and describes the coupling relationships between these key influencing factors using parameterized formulas. Traditional techniques typically perform static compensation based on a single environmental parameter, failing to effectively capture the dynamic coupling between rain attenuation and UAV movement. The causal reasoning in this application enhances the ability to identify and logically interpret factors affecting link performance. Through this method, this application provides a clear causal path and data support for dynamic channel prediction and compensation strategy design.

[0234] Furthermore, in dynamic channel state prediction, this application employs a Long Short-Term Memory (LSTM) network combined with an attention mechanism to learn complex temporal correlations and utilizes causal priors to collaboratively constrain the prediction model. This method addresses the insufficient adaptability and accuracy issues caused by traditional techniques using heuristic algorithms or static optimization models. In particular, this application explicitly identifies the nonlinear effects of Doppler shift, rain attenuation intensity, and link performance, and further enhances the ability to capture temporal correlations through multi-step prediction and an attention mechanism, resulting in more accurate and reliable prediction results.

[0235] Finally, regarding antenna alignment and error compensation, this application proposes a segmented alignment strategy and a power allocation coordination mechanism by combining dynamic channel prediction results. Unlike traditional technologies where antenna alignment relies on fixed thresholds or simple rule adjustments, this application optimizes the attitude angle based on a dynamic comparison of the line-of-sight vector and target position, and utilizes the collaborative modeling of power compensation factors and link influencing factors to achieve joint optimization of alignment and power control. This closed-loop adjustment strategy effectively reduces the risk of link interruption.

[0236] In summary, traditional technologies, limited by static and rule-based constraints, cannot cope with highly dynamic changes in complex environments. This application improves the system's responsiveness and stability to complex dynamic environments by combining multi-dimensional modeling with dynamic adaptability and optimizing the entire process.

[0237] This invention is not limited to the specific embodiments described above. The invention extends to any new feature or combination disclosed in this specification, as well as any new method or process step or combination disclosed herein.

Claims

1. A method for dynamic signal alignment of a portable satellite communication station, characterized in that, include: S1. Construct a multi-agent cooperative orbit model describing the three-dimensional dynamic coupling relationship between the portable satellite communication station, the UAV, and the satellite, including the following sub-steps: S11. Acquire trajectory data from portable satellite communication stations, drones, and satellites respectively, and unify the coordinate references; S12. Establish a satellite orbit model describing the satellite's on-orbit position based on satellite trajectory data; S13. Based on the trajectory data of the UAV, establish a motion model describing the flight trajectory of the UAV, and couple the attitude change information of the UAV to obtain the UAV orbit model; S14. Couple the satellite orbit model, the UAV orbit model, and the portable satellite communication station trajectory data to obtain the multi-entity collaborative orbit model; S2. Based on the multi-subject collaborative orbit model and environmental observation data, analyze the key influencing factors and their degree of influence on communication link performance through causal reasoning; S3. Based on the multi-agent cooperative orbit model and causal inference results, perform dynamic channel state prediction on the key influencing factors, including the following sub-steps: S31. Obtain the key influencing factors from the causal reasoning results and synchronize them over time; S32. Construct a multi-dimensional state-space model to describe the state of influence of the communication link, and impose collaborative constraints on states that have mutual influence. S33. Construct a time-series prediction network that takes the current state vector and observation vector of the multidimensional state space model as input and the state vector and communication link performance of the next time step as output; S34. Construct the loss function of the time series prediction network; S35. Train the time series prediction network using the data obtained in sub-step S31; S36. Using the trained temporal prediction network, predict the communication link performance and the multidimensional state space model in the target scene based on the current multidimensional state space model. S4. Antenna alignment adjustment and error compensation are performed based on dynamic channel state prediction results.

2. The portable satellite communication station signal dynamic alignment method as described in claim 1, characterized in that, Step S2 includes: S21. Obtain the multi-entity collaborative orbit model and load environmental observation data; S22. Based on the multi-subject collaborative orbit model and environmental observation data, construct a causal relationship diagram describing the causal path between environmental influencing factors and communication link performance, and identify key influencing factors and causal paths from the causal relationship diagram; S23. Based on the causal relationship diagram, the influence relationship of the key influencing factors on the communication link performance is parameterized and characterized. S24. Based on the causal relationship diagram and the parameterized characterization results of the key influencing factors, assess the degree of influence of the key influencing factors in the causal path and obtain the causal inference results.

3. The portable satellite communication station signal dynamic alignment method as described in claim 2, characterized in that, The assessment of the influence of the key influencing factors in the causal path includes: The causal path contribution values ​​of the aforementioned key influencing factors to the communication link performance were assessed; and, The importance of the key influencing factors on the performance of the communication link was assessed.

4. The portable satellite communication station signal dynamic alignment method as described in claim 1, characterized in that, The time-series prediction network is a multi-step prediction model; in sub-step S36, short-term and medium-to-long-term trend predictions are performed on the communication link performance, and the input data is perturbed.

5. The portable satellite communication station signal dynamic alignment method as described in claim 1, characterized in that, Step S4 includes: S41. Obtain the dynamic channel state prediction results and obtain key information related to antenna alignment error; S42. Construct a mapping model between antenna attitude and line-of-sight vector, and characterize the antenna pointing error based on this mapping model; S43. Generate antenna alignment strategy based on dynamic channel state prediction results; S44. Perform transmit power compensation in accordance with the antenna alignment strategy.

6. The portable satellite communication station signal dynamic alignment method as described in claim 5, characterized in that, Step S4 further includes: S45. Define the constraints on antenna maneuvers in the antenna alignment strategy.

7. The portable satellite communication station signal dynamic alignment method as described in claim 5 or 6, characterized in that, Step S4 further includes: S46. Execute the antenna alignment strategy and monitor the execution results; S47. Perform dynamic iteration and feedback optimization based on monitoring results.

8. A portable satellite communication station signal dynamic alignment device, comprising a processor and a storage medium, wherein the storage medium stores a computer program, characterized in that, When the processor runs the computer program, it executes the portable satellite communication station signal dynamic alignment method as described in any one of claims 1-7.

Images