A method, device and medium for fast phase calibration of a parabolic antenna

Abstract

This invention provides a rapid phase calibration method, device, and medium for parabolic antennas. The method includes: accumulating prior phase calibration data through system monitoring software and constructing a multi-dimensional phase calibration database; the system monitoring software establishing and training a predictive model of the phase calibration data based on the multi-dimensional phase calibration database; the system monitoring software acquiring phase calibration data from satellite signals in real time and inputting it into the trained predictive model, predicting the phase shift value in real time, and binding it to the tracking receiver; the system monitoring software triggering the antenna control unit to complete rapid phase calibration using the real-time predicted phase shift value as the initial calibration reference, and continuously optimizing the predictive model and phase calibration process through a dynamic feedback mechanism. This invention can solve the problem of long phase calibration time caused by insufficient phase stability in specific frequency bands, significantly improving phase calibration efficiency and success rate.

Description

Technical Field

[0001] This invention relates to the field of aerospace telemetry, tracking, and command (TT&C) data transmission, and particularly to a method, equipment, and medium for rapid phase correction of a parabolic antenna. Background Technology

[0002] In the field of aerospace telemetry, tracking, and command (TT&C) and data transmission, the phase calibration accuracy of ground station equipment directly determines the reliability of satellite-to-ground link signal transmission and mission execution effectiveness. S-band TT&C, X-band data transmission, and Ka-band data transmission are core application bands in aerospace missions, with stringent requirements for phase stability. Currently, there are problems with satellite phase calibration: First, the calibration time is relatively long. For S+Ka dual-band rapid phase calibration, the time is close to 80 seconds, which cannot meet the current demand for rapid data transmission after the target satellite has exited the obscuration angle. If an accurate prediction model could be established, a phase calibration-free approach could be adopted to save calibration time and increase the target data transmission time. Second, the success rate of phase calibration needs improvement, especially in the Ka band. Due to the extremely narrow beam and large target dynamics, antenna deflection during phase calibration can easily cause the electrical axis to exceed the main lobe, leading to signal loss. This is also highly correlated with the initial phase shift value and sensitivity coefficient. Therefore, the demand for establishing a rapid, high-precision initial value training prediction method to improve phase calibration efficiency and success rate is increasingly strong.

[0003] A typical fast phase correction flow for an antenna system includes four processes: First, the satellite encodes and modulates data of different formats and transmits it to the ground station via different frequency bands; Second, after receiving the electromagnetic wave signal, the ground station antenna equipment amplifies and converts the signal before transmitting it to the tracking receiver; Third, when the ground station is performing satellite reception, the system monitoring software stores the initial phase shift value and sensitivity coefficient value in the tracking receiver. When the satellite approaches the station, it sends a fast phase correction command to the ACU (Antenna Control Unit). The ACU then enters the fast phase correction process, and if the phase correction is successful, it stores the phase correction results (phase shift value, sensitivity coefficient) in the tracking receiver; Fourth, the ACU drives the antenna to attempt to close the tracking circuit to complete the satellite self-tracking process.

[0004] The first and second processes involve signal transmission but not rapid phase calibration. The third and fourth processes do involve phase calibration. In some satellite applications, users have extremely high requirements for the timeliness and success rate of rapid phase calibration, and general rapid phase calibration methods cannot meet their requirements for both short time and stability. Summary of the Invention

[0005] This application provides a method, device, and medium for rapid phase correction of a parabolic antenna, which can effectively improve the phase correction efficiency and cover various application scenarios such as S-band, X-band, Ka-band, simultaneous phase correction of multiple bands, and phase correction-free operation.

[0006] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0007] According to a first aspect of the embodiments of this application, a fast phase correction method for a parabolic antenna is provided, comprising: Accumulate prior phase calibration data through system monitoring software and build a multi-dimensional phase calibration database; The system monitoring software establishes and trains a predictive model for the phase alignment data based on a multi-dimensional phase alignment database; The system monitoring software collects phase correction data from satellite signals in real time and inputs it into the trained prediction model to predict the phase shift value in real time and bind it to the tracking receiver. The system monitoring software triggers the antenna control unit to complete rapid phase correction using the real-time predicted phase shift value as the initial calibration reference, and continuously optimizes the prediction model and phase correction process through a dynamic feedback mechanism.

[0008] According to one embodiment of this application, the phase calibration data in the multi-dimensional phase calibration database includes phase calibration time, frequency band, operating frequency, combination number, task code, temperature, humidity, phase shift value, and sensitivity coefficient, and adopts a multi-level tag classification mechanism to highlight the correlation between combination number, frequency band, operating frequency, temperature, phase shift value, and sensitivity coefficient.

[0009] According to one embodiment of this application, the prediction model is implemented based on a time series prediction algorithm that fuses LSTM and gradient boosting tree.

[0010] According to one embodiment of this application, the training process of the prediction model includes: Obtain a multi-dimensional alignment database and real-time collected alignment data; After preprocessing the phase calibration data, the feature data is decoupled into time-series features and static features, and a sliding window strategy is combined to generate time-series samples with time dependencies. The time series samples are randomly divided into training set, validation set and test set according to a preset ratio; Initiate the parallel training process of the LSTM and gradient boosting tree models; during training, optimize parameters using the training set and monitor loss changes based on the validation set; after training is completed, obtain the LSTM weight parameter file and the gradient boosting tree weight parameter file respectively. A grid search is performed within a preset range, traversing all weight parameter combinations of LSTM and gradient boosting tree. The fusion prediction performance of each combination is evaluated using a validation set. The weight that minimizes the error is selected as the optimal fusion weight, thus obtaining the optimal prediction model. The test set is applied to the optimal prediction model, and RMSE, MAE and confidence index are calculated for each frequency band to generate an evaluation report. If the indexes for each frequency band in the evaluation report meet the requirements, the training is completed; otherwise, preprocessing and feature splitting are re-executed, and the model is retrained.

[0011] According to one embodiment of this application, the rapid phase calibration includes: The antenna control unit selects one or more frequency bands from the S, X, and Ka bands to perform phase correction operations based on the signal tracking status and the preset phase correction strategy. If the phase correction strategy is phase correction, the antenna control unit starts the satellite phase correction process with the real-time predicted phase shift value as the initial calibration reference and immediately sends the completed result back to the system monitoring software. If the phase correction strategy is phase correction-free, the antenna is directly driven to achieve self-tracking based on the pre-calibrated phase shift amount and sensitivity coefficient.

[0012] According to one embodiment of this application, during the rapid phase calibration process, the system monitoring software judges the phase calibration data based on the tracking stability: if the antenna maintains continuous and stable tracking within the current orbit cycle, the phase calibration result is valid and is entered into the multi-dimensional phase calibration database; if self-tracking exit occurs during the period, it is judged as a tracking abnormality, and the phase calibration result of that cycle is not entered into the database and is discarded.

[0013] According to one embodiment of this application, the continuous optimization of the prediction model and the phase correction process through a dynamic feedback mechanism specifically includes: The system monitoring software automatically collects phase calibration data and stores it in a multi-dimensional phase calibration database. The ACU controls the antenna to perform trial tracking of the satellite based on the bound phase shift value. After the satellite is stably tracked, the system monitoring software continuously updates and inserts data into the database based on real-time phase calibration data. When the data is updated, it triggers a dynamic update of the prediction model.

[0014] According to one embodiment of this application, after the satellite is stably tracked, the system monitoring software continuously updates and inserts data into the database based on real-time phase calibration data, specifically including: After the satellite is stably tracked, phase calibration data is collected and cached in real time. Once the antenna self-tracking ends and exits, the collected data is written to the database in batches. If the antenna exits the self-tracking state during the tracking process, the data will not be entered into the database.

[0015] According to a second aspect of the embodiments of this application, an electronic device is provided, comprising: At least one processor; and a memory communicatively connected to said at least one processor; The memory stores instructions executable by the at least one processor, which executes the instructions stored in the memory to perform the method as described in the first aspect.

[0016] According to a third aspect of the embodiments of this application, a computer-readable storage medium is provided for storing instructions that, when executed, cause the method described in the first aspect to be implemented.

[0017] Compared with existing technologies, the beneficial effects of adopting the above technical solution are as follows: This invention proposes a method for rapid phase correction initial value training and prediction based on prior data. The established fusion prediction model can adapt to phase correction initial value training and prediction in various scenarios, including multiple frequency bands (not limited to S / X / Ka), different temperatures and humidity levels, and different frequency ranges. This invention has broad adaptability to phase shift value prediction, meeting the requirements for rapid phase correction initial value prediction in different scenarios. Simultaneously, the prediction results of this invention have small deviations and high accuracy, meeting the requirements for direct tracking without phase correction. It also effectively improves the accuracy of rapid phase correction initial value training and prediction, increasing the success rate of the task. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0019] Figure 1 This is a flowchart of a rapid phase correction method for a parabolic antenna according to an embodiment of this application.

[0020] Figure 2 This is a flowchart of the prediction model training process proposed in this invention.

[0021] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0022] The embodiments of this application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar modules or modules having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application. Rather, the embodiments of this application include all variations, modifications, and equivalents falling within the spirit and scope of the appended claims.

[0023] To overcome the shortcomings of conventional fast phase correction methods in achieving both short time and high efficiency, this application proposes a fast phase correction method for parabolic antennas. By predicting the initial value for fast phase correction in real time, the efficiency and success rate of fast phase correction are improved.

[0024] Please refer to Figure 1 The rapid phase correction method for this parabolic antenna includes the following steps: S101. Accumulate prior phase calibration data through system monitoring software and build a multi-dimensional phase calibration database.

[0025] In this embodiment, prior data is accumulated through the system monitoring software of the ground system, mainly including phase calibration data such as calibration time, frequency band, operating frequency, combination number, mission code, temperature, humidity, phase shift value, and sensitivity coefficient.

[0026] After data collection, a multi-dimensional phase calibration database needs to be established. In this embodiment, the multi-dimensional phase calibration database adopts a multi-level tag classification mechanism, highlighting the association between specific characteristics such as combination number, frequency band, operating frequency, and temperature and dynamic parameters such as phase shift value and sensitivity coefficient, ensuring data retrieval efficiency. Simultaneously, the database supports parallel data retrieval and updating, providing high-quality data support for dynamic parameters of the S / X / Ka band-specific prediction models.

[0027] S102. The system monitoring software establishes and trains a prediction model for the calibration data based on a multi-dimensional calibration database.

[0028] In this embodiment, based on the constructed multi-dimensional phase calibration database, the system monitoring software adopts a time-series prediction algorithm that fuses LSTM (Long Short-Term Memory) network and gradient boosting tree. Their core advantages complement each other: LSTM effectively uncovers the patterns of prior data changes over time, while gradient boosting tree excels at handling the coupling relationship between nonlinear environmental factors (temperature, humidity, operating frequency) and high-dimensional dynamic parameters (phase shift value, sensitivity coefficient, etc.), improving the model's robustness under complex conditions. In the LSTM model, the number of hidden layers, the number of neurons per layer, the activation function, the number of iterations, and the batch size are selected to construct the model; parameters for different frequency bands can be configured. For the gradient boosting tree, parameters such as learning rate, number of iterations, and decision tree depth are selected for model construction. Finally, in the fusion strategy, the weighting coefficients of LSTM and gradient boosting tree are adjusted.

[0029] Please refer to Figure 2 This embodiment also provides the specific training process of the prediction model: Data preparation phase: Integrate prior phase databases for S, X, and Ka bands with real-time operational data, covering multi-dimensional information such as temperature, humidity, operating frequency, frequency band, combination number, measured phase shift value, and sensitivity coefficient. Through unified timestamp alignment and field mapping, construct a complete and consistent original feature dataset.

[0030] Feature preprocessing and splitting stage: The original dataset undergoes systematic cleaning and structuring, including outlier removal (based on statistical methods and physical plausibility criteria), linear interpolation imputation of missing temporal values, and normalization and standardization of numerical features. Based on this, the features are decoupled into temporal features and static features, and a sliding window strategy is used to generate time-dependent temporal samples.

[0031] Dataset partitioning stage: Based on the preprocessed feature set, it is randomly partitioned in a 7:2:1 ratio to construct training, validation, and test sets. The partitioning process strictly follows chronological order or stratified sampling strategies to ensure that the three types of data are representative in terms of frequency band distribution, temperature / humidity range, combination number coverage, and phase response characteristics. Finally, independent training, validation, and test sets are output.

[0032] The dual-model parallel training phase involves initiating parallel training of the LSTM (Long Short-Term Memory) network and the gradient boosting tree model. Each model is configured with independent hyperparameter sets (e.g., number of hidden units, number of layers, and learning rate for the LSTM; number of trees, learning rate, and maximum depth for the gradient boosting tree model) and early stopping strategies. During training, parameters are optimized using the training set, and loss changes are monitored based on the validation set to achieve dynamic early stopping, effectively preventing overfitting. The final output is the optimal weight parameters for both the fully trained LSTM and gradient boosting tree models. Finally, LSTM weight files and gradient boosting tree weight files are obtained separately.

[0033] The training and error feedback phase of the fusion module: First, a grid search is performed within a preset range (w1[0.5, 0.7], w2[0.3, 0.5], step size 0.05) to traverse all possible weighted combinations. The fusion prediction performance under each combination is evaluated using the validation set, and the weight that minimizes the error is selected as the optimal fusion weight. Then, the error correction factor is calculated based on the deviation between the optimal fusion result and the true value. Finally, the optimal fusion weight, the error correction factor, and the prediction error after fusion are output.

[0034] Model evaluation and deployment phase: The optimal fusion model is applied to the test set, and RMSE, MAE, and confidence indices are calculated for each frequency band, generating an evaluation report. Then, the decision node is reached, where the evaluation report is used to determine if the indices for each frequency band meet the accuracy requirements. If they do, the model training is complete, and the trained model is used for phase value prediction; otherwise, the process returns to the feature preprocessing and splitting phase for retraining. After model deployment, online iterative training based on newly acquired samples is supported to continuously improve model accuracy and reliability.

[0035] S103 The system monitoring software collects phase correction data from satellite signals in real time and inputs it into the trained prediction model to predict the phase shift value in real time and bind it to the tracking receiver.

[0036] When a satellite enters orbit, the ground station receives the satellite signal, which is then transmitted to the tracking receiver via a parabolic antenna and a front-end channel. The ground station's monitoring software automatically collects phase calibration data, including the current mission's operating frequency, frequency band, combination number, current temperature, humidity, and phase calibration time. This collected phase calibration data is then input in real-time into a deployed prediction model to predict phase shift values ​​and sensitivity coefficients, yielding the predicted phase shift value. Finally, the predicted phase shift value is transmitted to the tracking receiver via a network interface.

[0037] S104. The system monitoring software triggers the antenna control unit to complete rapid phase correction using the real-time predicted phase shift value as the initial calibration reference, and continuously optimizes the prediction model and phase correction process through a dynamic feedback mechanism.

[0038] In this embodiment, the ground station system monitoring software triggers the ACU to execute a rapid phase calibration process. In this embodiment, the rapid phase calibration process, based on the signal tracking status and a preset phase calibration strategy, can select one or more frequency bands from the S, X, and Ka bands to perform phase calibration operations, and also supports a phase calibration-free mode. Specifically, if the phase calibration strategy is phase calibration, the antenna control unit starts the satellite phase calibration process using the real-time predicted phase shift value as the initial calibration reference, and immediately transmits the completed result back to the system monitoring software; if the phase calibration strategy is phase calibration-free, the antenna is directly driven to achieve self-tracking based on the pre-calibrated phase shift amount and sensitivity coefficient, without the need for an actual phase calibration process.

[0039] During antenna stabilization tracking, system environmental parameters (such as temperature and humidity) exhibit time-varying characteristics. To ensure the integrity and effectiveness of phase calibration data accumulation, the system monitoring software employs a tracking stability assessment mechanism based on the current cycle. Specifically, if the system remains in self-tracking mode, it collects and caches key parameters in real time, including operating frequency, frequency band, combination number, ambient temperature and humidity, and the phase shift value and sensitivity coefficient of the tracking receiver. After the antenna exits the self-tracking cycle, the collected data is written to the database in batches, achieving complete data archiving and traceable management, significantly improving system calibration accuracy and operational reliability. If the antenna exits self-tracking mode during tracking, it is considered a tracking anomaly, and the phase calibration results for that cycle are discarded, ensuring the reliability and consistency of the database data. This re-entry mechanism effectively accumulates high-precision environmental influence factors, enhances the redundancy of multi-source data, provides solid data support for establishing a highly robust environmental compensation model, optimizes the training effect of the prediction model, and lays the foundation for high-precision prediction of subsequent phase calibration initial values.

[0040] It should be noted that in this embodiment, the prediction model is dynamically updated after the database is updated, in order to ensure the accuracy of the prediction model.

[0041] The fast phase correction method of this invention establishes a dynamic closed-loop link of phase correction results data entry, model building, data prediction, and re-entry into the database. It continuously optimizes the phase correction prediction model by accumulating input samples of the LSTM (Long Short-Term Memory) network and gradient boosting tree fusion algorithm.

[0042] The model integrates core parameters such as phase shift value, sensitivity coefficient, operating frequency, frequency band, combination number, and time from the data used for prediction. Combined with environmental factors such as temperature and humidity, a time-series prediction algorithm fusing LSTM (Long Short-Term Memory) and gradient boosting tree is employed for initial value training and prediction. This approach considers both the linear change of phase value over time and the influence of nonlinear factors such as temperature and humidity on the predicted values. The prediction results exhibit small deviations and high accuracy, meeting the requirements for direct tracking without phase calibration. This effectively improves the accuracy of initial value training and prediction for rapid phase calibration, increasing the success rate of the task.

[0043] This invention relates to a rapid phase correction initial value training and prediction method based on prior data. The established fusion prediction model can adapt to phase correction initial value training and prediction in various scenarios, including multiple frequency bands (not limited to S / X / Ka), different temperatures and humidity levels, and different frequency ranges. This invention has broad adaptability to phase value prediction and meets the needs of rapid phase correction initial value prediction in different scenarios.

[0044] Based on the same technical concept, this application also provides an electronic device that can implement the rapid phase correction method for parabolic antennas provided in the above embodiments of the present invention. In one embodiment, the electronic device can be a server, a terminal device, or other electronic equipment. Figure 3 As shown, the electronic device may include: At least one processor and a memory connected to the at least one processor. In this embodiment of the invention, the specific connection medium between the processor and the memory is not limited. Figure 3 The example used is the connection between the processor and memory via a bus. The bus... Figure 3 The connections between other components are indicated by thick lines and are for illustrative purposes only, not as limiting information. Buses can be divided into address buses, data buses, control buses, etc., but for ease of representation, [the specific bus type is not shown here]. Figure 3 The processor is represented by a single thick line, but this does not imply that there is only one bus or one type of bus. Alternatively, a processor can also be called a controller; there are no restrictions on the name.

[0045] In this embodiment of the invention, the memory stores instructions executable by at least one processor. By executing the instructions stored in the memory, the at least one processor can perform the rapid phase correction method for a parabolic antenna described above. The processor can implement... Figure 3 The functions of each module in the device shown.

[0046] The processor is the control center of the device. It can connect to various parts of the control device through various interfaces and lines. By running or executing instructions stored in memory and calling data stored in memory, it can monitor the device's various functions and process data, thereby enabling overall monitoring of the device.

[0047] In an alternative design, the processor may include one or more processing units. The processor may integrate an application processor and a modem processor, wherein the application processor primarily handles the operating system, user interface, and applications, while the modem processor primarily handles wireless communication. It is understood that the modem processor may also not be integrated into the processor. In some embodiments, the processor and memory may be implemented on the same chip; in some embodiments, they may also be implemented separately on separate chips.

[0048] The processor can be a general-purpose processor, such as a CPU, digital signal processor, application-specific integrated circuit, field-programmable array, or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the rapid phase correction method for a parabolic antenna disclosed in the embodiments of this invention can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0049] Memory, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. Memory can include at least one type of storage medium, such as flash memory, hard disk, multimedia card, card-type memory, random access memory (RAM), static random access memory (SRAM), programmable read-only memory (PROM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic memory, magnetic disk, optical disk, etc. Memory is any other medium capable of carrying or storing desired program code in the form of instructions or data structures, and accessible by a computer, but is not limited thereto. In embodiments of the present invention, memory can also be a circuit or any other device capable of implementing storage functions, used to store program instructions and / or data.

[0050] By designing and programming the processor, the code corresponding to the rapid phase correction method for parabolic antennas described in the foregoing embodiments can be embedded into the chip, enabling the chip to execute the steps of the method described in the foregoing embodiments during runtime. How to design and program the processor is a technique well-known to those skilled in the art and will not be elaborated upon here.

[0051] Based on the same inventive concept, embodiments of the present invention also provide a storage medium storing computer instructions that, when executed on a computer, cause the computer to perform a rapid phase correction method for a parabolic antenna as described above.

[0052] In some alternative embodiments, the present invention also provides a method for rapid phase correction of a parabolic antenna that can also be implemented as a program product including program code that, when the program product is run on a device, causes the control device to perform the steps in a method for rapid phase correction of a parabolic antenna according to various exemplary embodiments of the present invention as described in this specification.

[0053] It should be noted that although several units or sub-units of the apparatus have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of the invention, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided and embodied by multiple units. Furthermore, although the operation of the method of the invention is described in a specific order in the drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0054] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0055] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a server, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0056] Program code for performing the operations of this invention can be written using any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0057] In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0058] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0059] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0060] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for fast phasing of a parabolic antenna, characterized in that, include: Accumulate prior phase calibration data through system monitoring software and build a multi-dimensional phase calibration database; The system monitoring software establishes and trains a predictive model for the phase alignment data based on a multi-dimensional phase alignment database; The system monitoring software collects phase correction data from satellite signals in real time and inputs it into the trained prediction model to predict the phase shift value in real time and bind it to the tracking receiver. The system monitoring software triggers the antenna control unit to complete rapid phase correction using the real-time predicted phase shift value as the initial calibration reference, and continuously optimizes the prediction model and phase correction process through a dynamic feedback mechanism.

2. The rapid phase correction method for a parabolic antenna according to claim 1, characterized in that, The phase calibration data in the multi-dimensional phase calibration database includes phase calibration time, frequency band, operating frequency, combination number, task code, temperature, humidity, phase shift value, and sensitivity coefficient. It adopts a multi-level tag classification mechanism to highlight the correlation between combination number, frequency band, operating frequency, temperature, phase shift value, and sensitivity coefficient.

3. The rapid phase correction method for a parabolic antenna according to claim 1, characterized in that, The prediction model is based on a time-series prediction algorithm that combines LSTM and gradient boosting trees.

4. The rapid phase correction method for a parabolic antenna according to claim 3, characterized in that, The training process of the prediction model includes: Obtain a multi-dimensional alignment database and real-time collected alignment data; After preprocessing the phase calibration data, the feature data is decoupled into time-series features and static features, and a sliding window strategy is combined to generate time-series samples with time dependencies. The time series samples are randomly divided into training set, validation set and test set according to a preset ratio; Initiate the parallel training process of the LSTM and gradient boosting tree models; during training, optimize parameters using the training set and monitor loss changes based on the validation set; after training is completed, obtain the LSTM weight parameter file and the gradient boosting tree weight parameter file respectively. A grid search is performed within a preset range, traversing all weight parameter combinations of LSTM and gradient boosting tree. The fusion prediction performance of each combination is evaluated using a validation set. The weight that minimizes the error is selected as the optimal fusion weight, thus obtaining the optimal prediction model. The test set is applied to the optimal prediction model, and RMSE, MAE and confidence index are calculated for each frequency band to generate an evaluation report. If the indexes for each frequency band in the evaluation report meet the requirements, the training is completed; otherwise, preprocessing and feature splitting are re-executed, and the model is retrained.

5. The rapid phase correction method for a parabolic antenna according to claim 1, characterized in that, The rapid phase calibration includes: The antenna control unit selects one or more frequency bands from the S, X, and Ka bands to perform phase correction operations based on the signal tracking status and the preset phase correction strategy. If the phase correction strategy is phase correction, the antenna control unit starts the satellite phase correction process with the real-time predicted phase shift value as the initial calibration reference and immediately sends the completed result back to the system monitoring software. If the phase correction strategy is phase correction-free, the antenna is directly driven to achieve self-tracking based on the pre-calibrated phase shift amount and sensitivity coefficient.

6. The rapid phase correction method for a parabolic antenna according to claim 5, characterized in that, During the rapid phase calibration process, the system monitoring software judges the phase calibration data based on tracking stability: if the antenna maintains continuous and stable tracking within the current orbital period, the phase calibration result is valid and is entered into the multi-dimensional phase calibration database; If self-tracking exits during the process, it is determined to be a tracking anomaly, and the phase correction result for that cycle will not be entered into the database and will be discarded.

7. The rapid phase correction method for a parabolic antenna according to claim 5, characterized in that, The continuous optimization of the prediction model and the phase correction process through a dynamic feedback mechanism specifically includes: The system monitoring software automatically collects phase calibration data and stores it in a multi-dimensional phase calibration database. The antenna control unit controls the antenna to perform trial tracking of the satellite based on the pre-set phase shift value. After the satellite is stably tracked, the system monitoring software continuously updates and inserts data into the database based on real-time phase calibration data. When the data is updated, it triggers a dynamic update of the prediction model.

8. The rapid phase correction method for a parabolic antenna according to claim 7, characterized in that, After the satellite is stably tracked, the system monitoring software continuously updates and inserts data into the database based on real-time phase calibration data, specifically including: After the satellite is stably tracked, phase calibration data is collected and cached in real time. Once the antenna self-tracking ends and exits, the collected data is written to the database in batches. If the antenna exits the self-tracking state during the tracking process, the data will not be entered into the database.

9. An electronic device, characterized in that, include: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores instructions executable by the at least one processor, which executes the instructions stored in the memory to perform the method as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store instructions that, when executed, cause the method as described in any one of claims 1 to 8 to be implemented.

Images