A control method and system for an intelligent networked astronomical telescope with a synchronous base

Abstract

The present invention provides a control method and system for an intelligent networked astronomical telescope with a synchronous base, relating to the field of telescope control technology. The method comprises obtaining historical observation data of the astronomical telescope and initial star map data uploaded in real time; performing star map matching and attitude estimation of the astronomical telescope based on the initial star map data, and performing coordinate conversion on the data obtained from the attitude estimation to obtain initial pointing data of the astronomical telescope; calculating star motion errors based on the initial pointing data, and inputting the star motion errors into a preset control strategy determination model for processing to obtain an initial control strategy for the astronomical telescope; controlling the astronomical telescope to obtain astronomical image data based on the initial control strategy, and optimizing the initial control strategy based on the astronomical image data and historical observation data to obtain a final control strategy for the astronomical telescope. The present invention solves the problems of low astronomical data storage efficiency and insufficient long-term observation strategy optimization capabilities.

Description

Technical Field

[0001] The present invention relates to the field of telescope control technology, and in particular to a control method and system for an intelligent networked astronomical telescope with a synchronous base. Background Art

[0002] In the field of modern astronomical observation, high-precision automated astronomical telescopes have become an important tool for acquiring astronomical data. Traditional astronomical telescope control methods mainly rely on fixed observation plans and manual adjustments, including rough alignment based on star navigation, preset trajectory tracking, and single error compensation techniques. However, these methods have many limitations in practical applications. First, because traditional star map matching methods are mainly based on template matching or simple feature point comparison, they are easily affected by star map distortion, light pollution, and noise interference, resulting in low matching accuracy, which in turn affects the pointing accuracy of the telescope. Second, existing astronomical telescope control systems generally use static error compensation methods, which cannot effectively cope with complex dynamic observation environments and lead to accumulated pointing errors. In addition, traditional control strategy optimization methods mainly rely on preset observation plans and lack the ability to allocate tasks in real time and coordinate control of multiple telescopes. This leads to low observation efficiency and makes it difficult to meet the needs of high-precision, long-term, and multi-target observations.

[0003] Therefore, there is an urgent need for a control method and system for an intelligent networked astronomical telescope with a synchronous base to solve the above problems. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for controlling an intelligent networked astronomical telescope with a synchronized base to improve the above-mentioned problems. To achieve the above-mentioned purpose, the technical solutions adopted by the present invention are as follows:

[0005] In a first aspect, the present application provides a method for controlling an intelligent networked astronomical telescope with a synchronous base, comprising:

[0006] Obtain historical observation data from astronomical telescopes and initial star map data uploaded in real time;

[0007] Performing star map matching and attitude estimation of the astronomical telescope based on the initial star map data, and performing coordinate conversion on the data obtained from the attitude estimation to obtain initial pointing data of the astronomical telescope;

[0008] Calculating a star motion error based on the initial pointing data, and inputting the star motion error into a preset control strategy determination model for processing to obtain an initial control strategy for the astronomical telescope;

[0009] The astronomical telescope is controlled to acquire astronomical image data based on the initial control strategy, and the initial control strategy is optimized based on the astronomical image data and historical observation data to obtain a final control strategy for the astronomical telescope.

[0010] In a second aspect, the present application also provides an intelligent networked astronomical telescope control system with a synchronous base, comprising:

[0011] An acquisition unit is used to obtain historical observation data of the astronomical telescope and initial star map data uploaded in real time;

[0012] a processing unit, configured to perform star map matching and attitude estimation of the astronomical telescope based on the initial star map data, and perform coordinate conversion on the data obtained by the attitude estimation to obtain initial pointing data of the astronomical telescope;

[0013] a calculation unit, configured to calculate a stellar motion error based on the initial pointing data, and input the stellar motion error into a preset control strategy determination model for processing to obtain an initial control strategy for the astronomical telescope;

[0014] The optimization unit is used to control the astronomical telescope to obtain astronomical image data based on the initial control strategy, and optimize the initial control strategy based on the astronomical image data and historical observation data to obtain a final control strategy for the astronomical telescope.

[0015] The beneficial effects of the present invention are:

[0016] This paper first uses a star-chart matching optimization network and adaptive particle filtering to achieve high-precision attitude estimation and coordinate transformation for astronomical telescopes, thereby improving the telescope's pointing accuracy. Secondly, a generalized sparse optical flow estimation algorithm is used to analyze stellar motion errors, and error compensation is combined with a dual adaptive Kalman filter and an adaptive sliding mode observer to optimize the telescope's control strategy and improve pointing stability in dynamic observation environments. Furthermore, the method introduces an entropy-regularized deep reinforcement learning model and a dynamic graph task allocation algorithm to achieve collaborative optimization of multi-telescope tasks and improve observation efficiency.

[0017] In terms of data processing, this invention extracts stellar spectral features based on a probabilistic tensor decomposition method and combines it with a hybrid greedy search to optimize computational tasks, improving the intelligent level of data processing. Furthermore, to address the issues of low astronomical data storage efficiency and insufficient optimization capabilities for long-term observation strategies, this invention implements data storage optimization and dynamic adjustment of long-term observation strategies, thereby ensuring efficient data storage and the accuracy of long-term observation tasks.

[0018] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or understood by practicing the embodiments of the present invention. The purposes and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 A schematic flow chart of a method for controlling an intelligent networked astronomical telescope of a synchronous base according to an embodiment of the present invention;

[0021] Figure 2 Schematic diagram of the structure of the intelligent networked astronomical telescope control system of the synchronization base described in an embodiment of the present invention.

[0022] In the figure: 701, acquisition unit; 702, processing unit; 703, calculation unit; 704, optimization unit. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0024] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are used only to distinguish the description and should not be understood as indicating or implying relative importance. Example 1:

[0025] This embodiment provides a method for controlling an intelligent networked astronomical telescope with a synchronous base.

[0026] See also Figure 1 , the figure shows that the method includes step S1, step S2, step S3 and step S4.

[0027] Step S1: Obtain historical observation data of the astronomical telescope and the initial star map data uploaded in real time:

[0028] It should be understood that the historical observation data in this step includes the telescope's past observation records, data on identified stars, equipment operating parameters, and environmental conditions (such as atmospheric disturbances, temperature, and humidity). This data not only provides a reference for current observations but also allows for data-driven optimization of the telescope's control strategy. For example, historical data can be used to analyze the pointing deviation of an astronomical telescope under different environments, thereby forming an error compensation model.

[0029] The initial star map data uploaded in real time is primarily acquired by the telescope's onboard star map acquisition system. It includes images of the starry sky in the current observation area, along with corresponding time and coordinate information. After preprocessing, this star map data can be matched against historical star catalogs to correct the telescope's initial pointing error. By building a data cache and edge computing module, rapid retrieval of historical data is achieved, and adaptive data fusion technology is used to improve the accuracy of real-time star map data, laying the foundation for subsequent star map matching and attitude estimation.

[0030] Step S2: performing star map matching and attitude estimation of the astronomical telescope based on the initial star map data, and performing coordinate conversion on the data obtained from the attitude estimation to obtain initial pointing data of the astronomical telescope;

[0031] It can be understood that this step effectively suppresses factors such as light pollution and imaging distortion by regularizing the star map matching network, thereby improving the matching accuracy. Adaptive particle filtering can more accurately handle complex noise environments and improve the accuracy of telescope attitude estimation. The Lie group optimal alignment algorithm is used to reduce cumulative errors, ensure high-precision conversion of telescope pointing data, and provide reliable input data for subsequent error compensation and observation mission execution. In this step, step S2 includes

[0032] Step S21: performing star map matching optimization processing based on the initial star map data and the preset standard star positions, wherein a regularized star map matching network is constructed to extract star map features and perform star map matching to obtain an optimized star map matching result;

[0033] Understandably, in actual observations, the initial star map data is often affected by factors such as light pollution, atmospheric turbulence, and imaging distortion, resulting in blurred star points and positional shifts, which affects matching accuracy. Therefore, this step optimizes the star map matching process by constructing a regularized star map matching network, improving matching accuracy and robustness.

[0034] Among them, weak signal star points are often difficult to be stably detected by traditional methods due to their low brightness and poor contrast. Therefore, a local contrast enhancement method is used to optimize the visibility of star points. Specifically, an adaptive histogram equalization method is used to perform grayscale equalization on the local area of the star map, so that dark star points can still be distinguished under different background brightness. In addition, the Laplace-Poisson equation is introduced to calculate the local gradient field to balance the brightness distribution in the high dynamic range star map and avoid excessive amplification of background noise during the enhancement process. Then, the directional gradient histogram method is used to extract the feature points of the star map. After the feature point extraction is completed, the regularized star map matching network is used for matching optimization. Since weak star points are often easily interfered by noise during the matching process, a multi-scale residual regularization loss function is introduced to enhance the matching weight of weak star points while suppressing background noise to obtain a set of matching points. Among them, the loss function is defined as follows:

[0035] ;

[0036] in, Indicates the degree of matching between two data or images. Indicates the first elements, 、 and is the weight coefficient, which is used to adjust the contribution of each loss function to the total loss function. Indicates the elements in the dataset, Indicates the second data set elements, represents the gradient, Represents the Gaussian filter function.

[0037] By calculating the transformation parameters by randomly sampling matching points and using projection errors to filter out mismatched points, the reliability of the matching data is ultimately improved. The entire process ensures the effective matching of weak signal star points and improves the accuracy and stability of the telescope's attitude estimation.

[0038] Step S22: performing telescope attitude estimation based on the adaptive particle filter and the optimized star map matching results to obtain telescope attitude estimation data;

[0039] After obtaining the optimized star map matching results, it is necessary to calculate the initial pointing angle of the telescope based on the optical center and celestial coordinate transformation model. Assume that the pixel coordinates of the matching star point are , and its corresponding celestial equatorial coordinates are , then the optical axis direction of the telescope can be solved by the optical imaging model. Assuming that the imaging system of the telescope can be approximated as an ideal pinhole camera model, its projection transformation can be expressed as:

[0040] ;

[0041] in, is the camera intrinsic parameter matrix, is the rotation matrix of the astronomical telescope, is the three-dimensional celestial coordinate of the star point. The pixel coordinates of the matching star point.

[0042] By solving the telescope's rotation matrix through direct linear transformation, the initial pointing angle of the telescope can be obtained, and the telescope's attitude matrix can be further constructed through quaternion rotation transformation:

[0043] ;

[0044] in, represents the rotation matrix, represents the real part of the quaternion, 、 and Represents the imaginary part of a quaternion.

[0045] Then, an initial particle set (i.e., multiple possible attitude states) is set, and the weight of each particle is calculated through importance sampling to obtain the particle distribution of each particle, and then the attitude estimation data of the telescope is obtained.

[0046] Step S23: Based on the attitude estimation data, the telescope coordinate system is aligned with the celestial coordinate system by using a Lie group optimal alignment algorithm to obtain initial pointing data of the astronomical telescope.

[0047] After matching the star map, we obtain the set of star point coordinates observed by the telescope and the set of standard star coordinates in the star catalog. The goal of coordinate transformation is to find the optimal rotation matrix and translation vector so that the star points in the telescope coordinate system can be mapped as accurately as possible to the astronomical coordinate system. To this end, we first perform a rotation transformation using the quaternion rotation matrix, and then set the star point coordinates in the standard star catalog. The goal is to minimize the transformation error between the observed coordinates and the standard star coordinates, and construct an optimization objective function:

[0048] ;

[0049] in, represents the optimization objective function, is the rotation matrix, is the observed star point coordinate, is the corresponding standard coordinate in the star catalog, Indicates the coordinate translation amount.

[0050] During the optimization process, gradient descent is used to adjust the rotation vector to minimize the error, and the new rotation matrix is calculated through exponential mapping. This method ensures that numerical drift is not generated, improving the accuracy and stability of the star map alignment.

[0051] Step S3: calculating the star motion error based on the initial pointing data, and inputting the star motion error into a preset control strategy determination model for processing to obtain an initial control strategy for the astronomical telescope;

[0052] It can be understood that this step calculates the stellar motion error based on the initial pointing data and inputs this error into a preset control strategy determination model for processing to determine the telescope's initial control strategy, enabling it to more accurately track the target celestial object. This step corrects the telescope's target pointing through the error calculation, bringing it closer to the target object's true position. In this step, step S3 includes steps S31, S32, and S33.

[0053] Step S31: performing star motion error analysis based on the initial pointing data, wherein the offset information of star motion is calculated by estimating generalized sparse optical flow to obtain motion error data of the astronomical telescope;

[0054] It will be appreciated that this step first involves obtaining initial pointing information from the telescope's observational data, including the positions of celestial bodies marked in a star map. Each celestial body has a known initial position during observation (given by pre-set catalog data). This data represents the celestial body's initial observed position in the telescope's coordinate system.

[0055] Stars within the field of view can shift in position due to various factors, such as the Earth's rotation, the orbital motion of celestial bodies, and atmospheric influences. This positional shift is time-dependent, meaning that the trajectory of a star within the telescope's field of view is no longer static over time. The goal is to quantify these motions and calculate the amount of star shift and the corresponding error.

[0056] The optical flow constraint equation can be used to derive the movement information of each star point. Assuming that the movement of the star image is smooth and continuous, the optical flow constraint equation can be expressed as:

[0057] ;

[0058] in, is the image intensity About space coordinates The partial derivative of represents the rate of change of image intensity in the horizontal direction, is the image intensity About space coordinates The partial derivative of represents the rate of change of image intensity in the vertical direction, is the image intensity About Time The partial derivative of , which represents the change of image intensity over time. This term reflects the change of image pixels over time. and is the component of optical flow, which indicates the movement speed of pixels in the image.

[0059] After calculating the motion offset of each star, we can use this offset information to determine the motion error of the telescope.

[0060] Step S32: performing error compensation processing on the motion error data according to a dual adaptive Kalman filter algorithm to obtain error-compensated pointing data;

[0061] It's understandable that changes in the telescope's observational errors, system noise, and observational noise are unpredictable in this step, especially in high-precision applications. Therefore, the dual adaptive Kalman filter algorithm dynamically adjusts the noise estimate, allowing the filter to update the noise covariance matrix in real time based on changes in the observed data. By adaptively adjusting the Kalman gain, we can optimize the error compensation process.

[0062] After each observation, the Kalman gain of the dual adaptive Kalman filter algorithm is adjusted according to the actual observation error to ensure that the gain of the filter adapts to the current noise environment. The update formula of the Kalman gain in the dual adaptive Kalman filter algorithm is:

[0063] ;

[0064] in, represents the Kalman gain, Indicates that the system is at time The error covariance matrix of represents the observation matrix, represents the measurement noise covariance matrix, Represents the observation matrix The transpose of .

[0065] Leveraging the dual processing capabilities of the dual adaptive Kalman filter, we achieve more accurate compensation for motion errors. The first step is to correct the predicted motion errors, and the second step is to gradually optimize them based on dynamic observation data to obtain compensated pointing data. This correction process eliminates errors caused by external interference (such as wind speed and temperature changes). Furthermore, the Kalman filter's update process provides a more accurate estimate of the system state, effectively compensating for errors. The adaptive mechanism enables the filter to dynamically adjust to various environmental noise levels and system errors. As a result of the gradual optimization of the filtering algorithm, the pointing data becomes more stable, reducing errors caused by short-term fluctuations or external factors.

[0066] Step S33: performing synchronous base control according to the pointing data after error compensation, and optimizing the control strategy through an adaptive sliding mode observer to obtain a control strategy for the astronomical telescope.

[0067] It can be understood that this step ensures that the base of the astronomical telescope can quickly and accurately respond to the pointing data after error compensation, so that the telescope lens remains on the target star and avoids offset or deviation of the observation data due to inconsistent movement.

[0068] In this step, the required adjustment angle of the telescope base is first calculated based on the error-compensated pointing data. The goal is to ensure that the telescope's movement is completely synchronized with the movement of the celestial body. The PID control algorithm is then used to precisely adjust the telescope base. Specifically, the PID control algorithm adjusts the base's angular velocity and acceleration to ensure that the base can respond to changes in the pointing data in the shortest possible time and achieve the desired angle. The target angle is calculated as follows:

[0069] ;

[0070] in, Indicates the reference signal or control signal output by the controller, that is, the target angle, Represents the proportional gain, which is the proportional part of the controller; Indicates the error between the target angle and the current angle, represents the differential gain, which is the differential part of the controller, represents the rate of change of the error (i.e., the derivative of the error), Represents the integral gain, which is the integral part of the controller, represents the integral of the error.

[0071] In this step, after performing synchronous base control, a sliding surface is set. When the system state is on the sliding surface, the control system can eliminate the error and force the system to slide along the surface, ensuring that the system can resist external interference and quickly stabilize. The sliding surface can be defined as a weighted combination of the error and the error change rate, as shown below:

[0072] ;

[0073] in, represents the control signal or state error function, is the weight coefficient, which indicates the contribution of the angle error to the control signal. Indicates the current angle of the synchronization base. Indicates the target angle of the synchronization base, is another weight coefficient, which indicates the contribution of the speed error to the control signal. To synchronize the current angular velocity of the base, Indicates the target angular velocity of the synchronous base.

[0074] To overcome the problems of traditional sliding mode control, this step introduces an adaptive adjustment mechanism. Based on the system's real-time feedback information, the gain parameters of the sliding mode controller are dynamically adjusted to obtain the control strategy of the astronomical telescope, thereby enabling the system to cope with various external disturbances and uncertainties. The adaptive control law of the adaptive sliding mode observer is as follows:

[0075] ;

[0076] in, Represents the control signal. It is the output signal of the control system, used to adjust the state of the controlled object. represents the adaptive gain matrix, It represents the difference between the current state of the system and the target state, and consists of position error and velocity error.

[0077] In this step, by combining sliding mode control with an adaptive mechanism, the system can automatically adapt to environmental changes and internal errors, provide strong robustness, and ensure stable control performance even in environments with large noise or interference.

[0078] Step S4: controlling the astronomical telescope to acquire astronomical image data based on the initial control strategy, and optimizing the initial control strategy based on the astronomical image data and historical observation data to obtain a final control strategy for the astronomical telescope.

[0079] It can be understood that this step optimizes the initial control strategy using acquired astronomical image data and historical observation data. This data-based optimization process makes the control strategy more adaptable, enabling real-time adjustments to varying environmental conditions, target celestial bodies, and observation tasks. This allows the telescope to dynamically adapt to different observation scenarios, improving the robustness and stability of the system. In this step, step S4 includes steps S41, S42, and S43.

[0080] Step S41: Input the control strategy and preset observation requirements of the astronomical telescope into the entropy regularized deep reinforcement learning model to optimize the task allocation strategy and obtain a preliminary optimized task allocation strategy;

[0081] It should be understood that the telescope's control strategy in this step includes attitude adjustment and base control. These strategies are based on the telescope's motion error compensation and control strategy optimization. They define the telescope's movements and behaviors under different observation conditions. Preset observation requirements include parameters such as the observation target for a specific celestial body, the observation time window, image resolution, and exposure time.

[0082] It can be understood that this step first combines the telescope's control strategy, such as its attitude and motion control, with pre-set observation requirements—such as observation of specific celestial bodies, exposure duration, and image clarity—and inputs them into a deep reinforcement learning model. Through interaction with the environment, the model learns how to dynamically adjust task allocation under the given control strategy and task requirements to ensure optimal utilization of telescope resources (such as field of view and exposure time). The entropy regularization mechanism plays a key role here, penalizing policy uncertainty to promote more stable and predictable task allocation. Through this optimization process, the resulting preliminary optimized task allocation strategy can more accurately guide the telescope's resource allocation and task execution under varying observation requirements, ensuring that resource conflicts are reduced and observation efficiency is improved when multiple tasks are performed simultaneously. The technical effect of this step is to adaptively optimize the telescope's task scheduling through deep reinforcement learning, avoiding the shortcomings of traditional static strategies and improving system responsiveness and task execution accuracy. The optimization objective of task allocation not only includes maximizing rewards but also factors such as task priority, resource allocation, and control strategy execution efficiency. Therefore, the reward function for task allocation needs to comprehensively consider the actual task requirements and control strategies of the astronomical telescope. The specific task allocation reward function is as follows:

[0083] ;

[0084] in, represents the task assignment reward function, Indicates action The efficiency of task execution in a given state, Indicates the priority of the current task. Indicates the clarity of astronomical images and the accuracy of star observations. 、 and Respectively 、 and The indicator weight.

[0085] Step S42: performing multi-telescope task collaborative optimization on the initially optimized task allocation strategy using a dynamic graph task allocation algorithm to obtain a collaboratively optimized task allocation strategy;

[0086] Understandably, multi-telescope task coordination optimization requires considering constraints such as the telescopes' resources, observation requirements, and operational space. Dynamic graph task allocation algorithms optimize tasks by updating each telescope's task status and observation data in real time. This algorithm first models the task requirements, status information, and execution strategies of the multiple telescopes. Each telescope's task allocation strategy must consider not only its own status (such as location, available resources, and observation targets) but also the collaborative task requirements of other telescopes. This task coordination optimization problem can be modeled using a dynamic flow algorithm from graph theory. During the task allocation process, the dynamic graph algorithm dynamically adjusts the allocation of tasks based on real-time observation data and task priorities. For example, if a task's execution time is delayed or a telescope fails to complete its task due to a malfunction, the dynamic flow algorithm adjusts the execution order of the corresponding task or assigns it to another telescope. After determining the priority of each task, a scheduling algorithm is used to dynamically schedule and allocate tasks. In multi-telescope task coordination optimization, task allocation not only considers the execution capabilities of each telescope but also ensures that multiple telescopes collaborate on the observation target, avoiding conflicts and wasted resources during task execution. Through collaborative optimization, the comprehensive mission benefits of all telescopes are maximized and the overall system efficiency is optimized.

[0087] Step S43: predicting the optimal observation time window based on the collaboratively optimized task allocation strategy and historical observation data, wherein a control strategy prediction model is established through a hierarchical memory network, and control strategy prediction is performed to obtain the final control strategy of the astronomical telescope.

[0088] It can be understood that in this step, the hierarchical memory network includes multiple processing levels, and each level stores and processes information through different memory units. The network can capture both short-term and long-term dependencies, thereby extracting the most representative features for task prediction under multi-dimensional data input. For the control strategy prediction of astronomical telescopes, the input data includes: historical observation data: such as the targets observed by the astronomical telescope in the past, task execution status, timestamps, etc. Task allocation strategy: The collaboratively optimized task allocation plan describes the tasks performed by each telescope at different time points and their priorities. Telescope status data: includes information such as the operating status of each telescope and resource availability. Through the multiple levels of the hierarchical memory network, the model can dynamically learn the correlation of this information and combine past experience to predict future observation time windows.

[0089] During the control strategy prediction process, the model not only focuses on the priority and resource allocation of the current task, but also needs to predict the optimal switching time between different observation tasks. This process requires deep learning of past task execution to identify which observation tasks can be efficiently executed in which time period. Specifically, the prediction model analyzes historical data to predict which tasks have higher execution benefits at the current moment and calculates the most appropriate observation time window. The control strategy prediction formula can be expressed as:

[0090] ;

[0091] in, Indicates time The optimal observation time window is Indicates the task execution efficiency, Indicates the priority of the task, Indicates selecting the task that maximizes the product of efficiency and priority. Represents a task or action.

[0092] It can be understood that after step S4, step S5, step S6 and step S7 are also included.

[0093] Step S5: controlling the astronomical telescope to perform observation based on the final control strategy, and performing image noise reduction processing on the astronomical image data obtained by observation to obtain noise-reduced astronomical image data;

[0094] It's understandable that after an astronomical telescope completes an observation, the image data it acquires will contain optical images of celestial objects. However, due to the complexity of the observation environment (e.g., atmospheric disturbances, telescope motion, and other factors), the acquired images are often accompanied by noise. This noise can come from a variety of sources, such as noise in the optical equipment, atmospheric interference, and errors in signal transmission. This noise not only affects image clarity but can also interfere with subsequent astronomical analysis and research. For astronomical telescope systems, noise reduction can ensure that the acquired data is more accurate and reliable, especially under long exposures or in high-noise environments. It can effectively improve the signal-to-noise ratio of the image and enhance the effectiveness of astronomical observations. Furthermore, the introduction of deep learning methods makes the noise reduction process not only highly adaptable but also capable of continuous optimization as data volume increases in practical applications, further improving the accuracy and efficiency of image processing.

[0095] Step S6: performing probability tensor decomposition on the astronomical image data after noise reduction, extracting star spectral features and classifying them to obtain star identification data;

[0096] It's understandable that tensors in this step are an extension of high-dimensional arrays and can naturally represent multidimensional data. In the context of astronomical images, we can represent multi-dimensional features such as the image's spatial position (e.g., rows and columns of pixels) and spectral information (e.g., image data in different wavelengths) as tensors.

[0097] In this step, the goal of probabilistic tensor decomposition is to extract underlying low-dimensional structures from the tensor, thereby revealing hidden patterns in the image. During this process, the tensor is decomposed using a probabilistic model to generate a set of latent factors (factor matrices) that capture the key information in the image. The factor matrices obtained through probabilistic tensor decomposition contain spatial and spectral information from the image. Further analysis of these factor matrices allows the extraction of the spectral signatures of each star. K-means clustering is then used to classify celestial bodies into multiple categories based on the similarity of their spectral signatures. This yields star identification data, including each star's position (i.e., spatial coordinates), its spectral signature (such as spectral type, temperature, and redshift), and its classification label (e.g., star, planet, or nebula).

[0098] Step S7: Optimize the allocation of computing tasks according to the hybrid greedy search optimization algorithm and the star recognition data to obtain optimized astronomical computing tasks.

[0099] In this step, a hybrid greedy search optimization algorithm initializes the task list and computing resource pool based on the input star identification data and computing task information. Each computing task is assigned a different priority based on the star identification data. High-priority tasks may involve important star feature extraction or complex spectral analysis. The computing task pool is sorted by task complexity, categorizing tasks into "simple" and "complex."

[0100] The tasks are then ranked based on factors such as the planet's priority and task complexity. For example, high-priority, computationally complex tasks are assigned to high-performance computing resources. Resource allocation: Appropriate resources are selected from the computing resource pool to handle the ranked tasks. At this point, the greedy algorithm selects the optimal resource to handle the current task, without considering future task allocations. For example, if the first task requires more computing resources (such as time and memory) while the second task is simpler, the greedy algorithm will prioritize allocating more computing resources to the first task and fewer resources to the second task.

[0101] While the greedy algorithm can quickly arrive at a preliminary solution, it may reach a local optimum. Therefore, local search is used for further optimization, including adjusting task order and reallocating resources. Adjusting task order involves local search, which adjusts the order in which tasks are assigned, trying different task scheduling methods to find a more optimal solution. For example, some compute-intensive tasks may require more computing resources, but they may also be assigned to inefficient resources due to their lower priority. Local search can avoid this resource waste by adjusting the matching of priorities and resources. Resource reallocation, including local search, also adjusts resource allocation based on the actual execution status of tasks (such as execution time and resource consumption) to optimize the utilization of computing resources.

[0102] It can be understood that after step S7, step S8 and step S9 are also included.

[0103] Step S8: Optimizing local cache and cloud storage based on the denoised astronomical image data and star recognition data, wherein the data is structured and stored using a hierarchical storage management model to obtain optimized storage data;

[0104] It can be understood that in this step, first, the astronomical image data after noise reduction is classified according to the priority of the celestial bodies or the needs of scientific research. For example, the image data of key celestial bodies may be marked as "high priority", while the image data of ordinary background celestial bodies may be marked as "low priority". Classification of celestial body identification data: Structured classification of identification data based on the characteristics or classification labels of celestial bodies. Certain celestial bodies with special scientific value (such as supernovae or black holes) may be marked as high-priority data, while ordinary celestial bodies may be marked as low-priority data. Then, based on the data classification, the high-priority astronomical image data and celestial body identification data are allocated to the local cache. Since local storage has a faster access speed, it can ensure a rapid response to high-priority tasks and ensure the real-time processing and analysis of high-priority tasks by the astronomical telescope.

[0105] Step S9: optimizing the observation strategy for the preset time period based on the optimized stored data, wherein the observation strategy for the preset time period is dynamically adjusted by a cyclic Bayesian update algorithm to obtain the observation strategy for the preset time period;

[0106] It should be understood that this step uses the optimized stored data and the preset time period observation strategy as input data. The optimized stored data includes astronomical image data, star identification data, and other optimized data, which may reflect the observation characteristics of different time periods. The preset time period observation strategy is the initial observation time period and strategic plan, including the observation activities and goals to be carried out during the specific time period.

[0107] Then, for each time period, set a preliminary estimate (prior distribution) of the observation strategy. For example, the preliminary observation time period may be set based on the average of historical data or empirical rules.

[0108] Next, the likelihood function is updated. As observation data accumulates, each round of new observation data will be used to update the likelihood function. This new data reflects the observation results of the current time period, which may include the specific performance of the celestial body, the clarity of the image, the use of observation resources, etc.

[0109] Then, we calculate the posterior distribution by combining the likelihood function with the prior distribution according to the Bayesian formula. This posterior distribution represents the best estimate of the future observation strategy under the current observation data.

[0110] Preferably, policy adjustment is performed, where the optimal policy parameters (e.g., optimal observation period, target selection, etc.) are extracted from the posterior distribution and future observation policies are adjusted based on these parameters. Example 2:

[0111] like Figure 2 As shown, this embodiment provides an intelligent networked astronomical telescope control system with a synchronous base, see Figure 2 The system includes an acquisition unit 701 , a processing unit 702 , a calculation unit 703 and an optimization unit 704 .

[0112] An acquisition unit 701 is used to acquire historical observation data of an astronomical telescope and initial star map data uploaded in real time;

[0113] The processing unit 702 is configured to perform star map matching and attitude estimation of the astronomical telescope based on the initial star map data, and perform coordinate conversion on the data obtained by the attitude estimation to obtain initial pointing data of the astronomical telescope;

[0114] A calculation unit 703 is configured to calculate a stellar motion error based on the initial pointing data, and input the stellar motion error into a preset control strategy determination model for processing to obtain an initial control strategy for the astronomical telescope;

[0115] The optimization unit 704 is configured to control the astronomical telescope to acquire astronomical image data based on the initial control strategy, and optimize the initial control strategy based on the astronomical image data and historical observation data to obtain a final control strategy for the astronomical telescope.

[0116] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated on here.

[0117] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

[0118] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for controlling an intelligent networked astronomical telescope with a synchronous base, characterized in that: include: Obtain historical observation data from astronomical telescopes and initial star map data uploaded in real time; Performing star map matching and attitude estimation of the astronomical telescope based on the initial star map data, and performing coordinate conversion on the data obtained from the attitude estimation to obtain initial pointing data of the astronomical telescope; Calculating a star motion error based on the initial pointing data, and inputting the star motion error into a preset control strategy determination model for processing to obtain an initial control strategy for the astronomical telescope; controlling the astronomical telescope to acquire astronomical image data based on the initial control strategy, and optimizing the initial control strategy based on the astronomical image data and historical observation data to obtain a final control strategy for the astronomical telescope; Calculating the star motion error based on the initial pointing data and inputting the star motion error into a preset control strategy determination model for processing includes: Performing star motion error analysis based on the initial pointing data, wherein offset information of star motion is calculated by generalized sparse optical flow estimation to obtain motion error data of the astronomical telescope; performing error compensation processing on the motion error data according to a dual adaptive Kalman filter algorithm to obtain error-compensated pointing data; The synchronous base control is performed according to the pointing data after error compensation, and the control strategy is optimized through an adaptive sliding mode observer to obtain the initial control strategy of the astronomical telescope.

2. The method for controlling an intelligent networked astronomical telescope with a synchronous base according to claim 1, wherein: Performing star map matching and telescope attitude estimation based on the initial star map data, and performing coordinate conversion on the data obtained from the attitude estimation, including: According to the initial star map data and the preset standard star positions, the star map matching optimization process is performed, wherein the star map features and star map matching are extracted by constructing a regularized star map matching network to obtain the optimized star map matching result; Based on the adaptive particle filter and optimized star map matching results, the attitude of the astronomical telescope is estimated to obtain the attitude estimation data of the telescope; According to the attitude estimation data, the telescope coordinate system is aligned with the celestial coordinate system through a Lie group optimal alignment algorithm to obtain initial pointing data of the astronomical telescope.

3. The method for controlling an intelligent networked astronomical telescope with a synchronous base according to claim 1, wherein: and optimizing an initial control strategy based on the astronomical image data and historical observation data, including: The initial control strategy and preset observation requirements of the astronomical telescope are input into the entropy regularized deep reinforcement learning model to optimize the task allocation strategy and obtain a preliminary optimized task allocation strategy; The dynamic graph task allocation algorithm is used to perform collaborative optimization of multi-telescope tasks on the initially optimized task allocation strategy to obtain the collaboratively optimized task allocation strategy. The optimal observation time window is predicted based on the collaboratively optimized task allocation strategy and historical observation data. A control strategy prediction model is established through a hierarchical memory network, and control strategy prediction is performed to obtain the final control strategy of the astronomical telescope.

4. The method for controlling an intelligent networked astronomical telescope with a synchronous base according to claim 1, wherein: After obtaining the final control strategy of the astronomical telescope, it also includes: Controlling the astronomical telescope to perform observation based on the final control strategy, and performing image noise reduction processing on the astronomical image data obtained by the observation to obtain noise-reduced astronomical image data; Performing probability tensor decomposition on the astronomical image data after noise reduction, and extracting star spectral features and classification to obtain star identification data; The computing tasks are optimally allocated according to the hybrid greedy search optimization algorithm and the star identification data to obtain optimized astronomical computing tasks.

5. An intelligent networked astronomical telescope control system with a synchronous base, characterized in that: include: An acquisition unit is used to obtain historical observation data of the astronomical telescope and initial star map data uploaded in real time; a processing unit, configured to perform star map matching and attitude estimation of the astronomical telescope based on the initial star map data, and perform coordinate conversion on the data obtained by the attitude estimation to obtain initial pointing data of the astronomical telescope; a calculation unit, configured to calculate a stellar motion error based on the initial pointing data, and input the stellar motion error into a preset control strategy determination model for processing to obtain an initial control strategy for the astronomical telescope; an optimization unit, configured to control the astronomical telescope to acquire astronomical image data based on the initial control strategy, and optimize the initial control strategy based on the astronomical image data and historical observation data to obtain a final control strategy for the astronomical telescope; Wherein, the computing unit includes: A first calculation subunit is configured to perform star motion error analysis based on the initial pointing data, wherein offset information of star motion is calculated by generalized sparse optical flow estimation to obtain motion error data of the astronomical telescope; a second calculation subunit, configured to perform error compensation processing on the motion error data according to a dual adaptive Kalman filter algorithm to obtain error-compensated pointing data; The third calculation subunit is used to perform synchronous base control according to the pointing data after error compensation, and optimize the control strategy through an adaptive sliding mode observer to obtain an initial control strategy for the astronomical telescope.

6. The intelligent networked astronomical telescope control system of the synchronous base according to claim 5, characterized in that: The processing unit includes: The first processing subunit is used to perform star map matching optimization processing based on the initial star map data and the preset standard star positions, wherein the star map features are extracted and the star map matching is performed by constructing a regularized star map matching network to obtain an optimized star map matching result; The second processing subunit is used to perform attitude estimation of the astronomical telescope based on the adaptive particle filter and the optimized star map matching results to obtain attitude estimation data of the telescope; The third processing subunit is configured to align the telescope coordinate system with the celestial coordinate system using a Lie group optimal alignment algorithm according to the attitude estimation data, so as to obtain initial pointing data of the astronomical telescope.

7. The intelligent networked astronomical telescope control system of the synchronous base according to claim 5, characterized in that: The optimization unit comprises: The first optimization subunit is used to input the initial control strategy and preset observation requirements of the astronomical telescope into the entropy regularized deep reinforcement learning model to optimize the task allocation strategy and obtain a preliminary optimized task allocation strategy; The second optimization subunit is used to perform multi-telescope task collaborative optimization on the initially optimized task allocation strategy through a dynamic graph task allocation algorithm to obtain a collaboratively optimized task allocation strategy; The third optimization subunit is used to predict the optimal observation time window based on the collaboratively optimized task allocation strategy and historical observation data. A control strategy prediction model is established through a hierarchical memory network, and control strategy prediction is performed to obtain the final control strategy of the astronomical telescope.

8. The intelligent networked astronomical telescope control system of the synchronous base according to claim 5, characterized in that: After the optimization unit, it also includes: a fourth processing subunit, configured to control the astronomical telescope to perform observation based on the final control strategy, and perform image noise reduction processing based on the astronomical image data obtained by observation to obtain noise-reduced astronomical image data; a fifth processing subunit, configured to perform probability tensor decomposition on the noise-reduced astronomical image data, extract spectral features of stars, and classify them to obtain star identification data; The fourth computing subunit is used to optimize the allocation of computing tasks according to the hybrid greedy search optimization algorithm and the star identification data to obtain optimized astronomical computing tasks.

Images