Satellite data processing method, device and equipment based on artificial intelligence

Abstract

The invention provides a satellite data processing method, device and equipment based on artificial intelligence. The problems that an existing satellite integrated electronic system is high in complexity and low in reliability and cannot meet the calculation requirement are effectively solved. The method comprises the following steps: the main processor receives various kinds of collected satellite data through the interface module and identifies the various kinds of satellite data to obtain first satellite data and second satellite data; the main processor processes the first satellite data to obtain a first processing result, and sends the second satellite data to the coprocessor; the coprocessor processes the received second satellite data through an artificial intelligence algorithm to obtain a second processing result; and the coprocessor sends the second processing result to the main processor, so that the main processor performs corresponding control on the satellite based on the first processing result and the second processing result.

Description

Technical Field

[0001] The present application relates to the field of aerospace technology, and more specifically, to a satellite data processing method, device, and equipment based on artificial intelligence. Background Art

[0002] The satellite integrated electronic subsystem mainly completes the functions of satellite platform satellite management, remote control and telemetry processing, energy management, thermal control management, orbit attitude control, time management, communication and signal acquisition. The satellite integrated electronic system is mainly composed of two boards, namely the satellite processing board and the attitude control processing board. Figure 1 As shown in the figure, the satellite service processing board mainly completes the functions of satellite service management, remote control and telemetry processing, energy management, thermal control management, time management, communication and signal acquisition, and command generation; the attitude control processing board mainly completes the functions of communicating with the attitude and orbit control components and adjusting the orbit and attitude of the control satellite. The hardware architecture of the two types of boards is similar, mainly composed of FLASH type FPGA and CPU, of which FPGA is mainly responsible for external interface, and CPU is mainly responsible for control and calculation. FPGA and CPU are connected through address, data, and control buses. The two types of boards are interconnected through cables between boards to realize CAN bus or RS422 bus communication.

[0003] However, existing satellite integrated electronic systems are often composed of multiple independent subsystems. The integration between these subsystems is not high, which makes the overall system more complex, larger in size, and inconvenient to manage and maintain. There are many connecting lines between subsystems, which not only increases the complexity of the system, but may also lead to reduced reliability. In addition, the performance of FPGA and CPU processors in existing satellite integrated electronic systems is poor and cannot meet the needs of high-performance computing and data processing. Summary of the invention

[0004] In view of this, the purpose of this application is to provide a satellite data processing method, device, and equipment based on artificial intelligence, which effectively solves the problems of high complexity, low reliability, and inability to meet computing requirements in existing satellite integrated electronic systems.

[0005] In a first aspect, an embodiment of the present application provides a satellite data processing method based on artificial intelligence, which is applicable to a satellite integrated electronic system, wherein the satellite integrated electronic system includes a main processor, a coprocessor, and an interface module; the main processor is respectively connected to the interface module and the coprocessor, and the method includes:

[0006] The main processor receives the collected multiple satellite data through the interface module, and identifies the multiple satellite data to obtain the first satellite data and the second satellite data;

[0007] The main processor processes the first satellite data to obtain a first processing result, and sends the second satellite data to the coprocessor;

[0008] The coprocessor processes the received second satellite data by using an artificial intelligence algorithm to obtain a second processing result; the artificial intelligence algorithm is preset in the coprocessor, and the type of the artificial intelligence algorithm corresponds to the type of the second satellite data;

[0009] The coprocessor sends the second processing result to the main processor, so that the main processor controls the satellite accordingly based on the first processing result and the second processing result.

[0010] In combination with the first aspect, an embodiment of the present application provides a first possible implementation manner of the first aspect, wherein the coprocessor processes the received second satellite data through an artificial intelligence algorithm to obtain a second processing result, including:

[0011] The coprocessor identifies the data type of the second satellite data to obtain a second identification result;

[0012] The coprocessor calls an artificial intelligence algorithm corresponding to the recognition result based on the recognition result to process the second satellite data to obtain the second processing result.

[0013] In combination with the first aspect, an embodiment of the present application provides a second possible implementation of the first aspect, wherein the coprocessor identifies the data type of the second satellite data to obtain a second identification result, including:

[0014] If the coprocessor identifies the data type of the second satellite data, a plurality of identification results are obtained;

[0015] The coprocessor simultaneously calls the artificial intelligence algorithms corresponding to the multiple recognition results, and simultaneously processes the second satellite data containing multiple data types to obtain multiple second processing results.

[0016] In combination with the first aspect, the embodiment of the present application provides a third possible implementation of the first aspect, wherein the artificial intelligence algorithm includes at least one of the following:

[0017] Intelligent modulation and coding algorithm, intelligent antenna beam control algorithm, intelligent navigation algorithm, intelligent orbit adjustment algorithm, intelligent health monitoring algorithm, intelligent resource allocation algorithm and intelligent task planning algorithm.

[0018] In combination with the first aspect, the embodiment of the present application provides a fourth possible implementation of the first aspect, wherein the main processor includes a PL module and a PS module;

[0019] The main processor receives the collected multiple satellite data through the interface module, and identifies the multiple satellite data to obtain the first satellite data and the second satellite data, including:

[0020] The PL module receives the various satellite data collected by the connected interface module; and sends the various satellite data to the PS module;

[0021] The PS module identifies the received multiple satellite data to obtain first satellite data and second satellite data.

[0022] In combination with the first aspect, an embodiment of the present application provides a fifth possible implementation of the first aspect, wherein the main processor processes the first satellite data to obtain a first processing result and sends the second satellite data to the coprocessor, including:

[0023] The main processor identifies the transmission type of the second satellite data to obtain a transmission identification result;

[0024] The main processor selects a corresponding transmission interface according to the transmission identification result to send the second satellite data to the coprocessor.

[0025] In combination with the first aspect, an embodiment of the present application provides a sixth possible implementation of the first aspect, wherein the main processor processes the first satellite data to obtain a first processing result and sends the second satellite data to the coprocessor, further comprising:

[0026] The main processor inputs the data type of the first satellite data into corresponding processing software;

[0027] The processing software processes the first satellite data to obtain a first processing result.

[0028] In a second aspect, an embodiment of the present application provides a satellite data processing device based on artificial intelligence, the device comprising:

[0029] an identification module, used for the main processor to receive the multiple satellite data collected through the interface module, and identify the multiple satellite data to obtain the first satellite data and the second satellite data;

[0030] a sending module, configured for the main processor to send the second satellite data to the coprocessor while processing the first satellite data to obtain a first processing result;

[0031] a receiving module, configured for the coprocessor to process the received second satellite data through an artificial intelligence algorithm to obtain a second processing result; the artificial intelligence algorithm corresponds to the type of the second satellite data;

[0032] A processing module is used for the coprocessor to send the second processing result to the main processor, so that the main processor can control the satellite accordingly based on the first processing result and the second processing result.

[0033] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory through the bus, and when the machine-readable instructions are executed by the processor, any step of the satellite data processing method based on artificial intelligence is performed.

[0034] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the computer program executes any one of the steps of the artificial intelligence-based satellite data processing method.

[0035] An artificial intelligence-based satellite data processing method provided in an embodiment of the present application is applicable to a satellite integrated electronic system, wherein the satellite integrated electronic system comprises a main processor, a coprocessor, and an interface module; the main processor is respectively connected to the interface module and the coprocessor, and the method firstly receives a plurality of satellite data collected by the main processor through the interface module, and identifies the plurality of satellite data to obtain first satellite data and second satellite data; secondly, while the main processor processes the first satellite data to obtain a first processing result, the main processor sends the second satellite data to the coprocessor; then, the coprocessor processes the received second satellite data through an artificial intelligence algorithm to obtain a second processing result; the artificial intelligence algorithm is preset in the coprocessor, and the type of the artificial intelligence algorithm corresponds to the type of the second satellite data ; Finally, the coprocessor sends the second processing result to the main processor, so that the main processor controls the satellite accordingly based on the first processing result and the second processing result, and processes the received multiple satellite data through the main processor and the coprocessor to obtain the processing result, thereby avoiding the existing satellite integrated electronic system which is often composed of multiple independent subsystems, and the integration between these subsystems is not high, resulting in the overall system being more complex, larger in size, and inconvenient to manage and maintain. There are many connecting lines between the subsystems, which not only increases the complexity of the system, but also may lead to the problem of reduced reliability, thereby ensuring the reliability of processing multiple satellite data, and avoiding the problem that the performance of the FPGA and CPU processors of the existing satellite integrated electronic system is poor and cannot meet the needs of high-performance computing and data processing, thereby ensuring the processing for the satellite. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 A schematic diagram of the structure of an existing satellite integrated electronic system is shown.

[0038] Figure 2 A schematic diagram of a flow chart of a first satellite data processing method based on artificial intelligence provided in an embodiment of the present application is shown;

[0039] Figure 3 A schematic diagram of a process for obtaining first satellite data and second satellite data provided by an embodiment of the present application is shown;

[0040] Figure 4A schematic diagram of a process of sending the second satellite data to the coprocessor provided in an embodiment of the present application is shown;

[0041] Figure 5 A schematic diagram of the structure of a satellite integrated electronic system provided in an embodiment of the present application is shown.

[0042] Figure 6 A data interaction diagram of a satellite integrated electronic system provided in an embodiment of the present application is shown.

[0043] Figure 7 A schematic structural diagram of a first artificial intelligence-based satellite data processing device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0044] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0045] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0046] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0047] Currently, existing satellite integrated electronic systems are often composed of multiple independent subsystems. The integration between these subsystems is not high, which makes the overall system more complex, larger in size, and inconvenient to manage and maintain. There are many connecting lines between subsystems, which not only increases the complexity of the system, but may also lead to reduced reliability. In addition, the performance of FPGA and CPU processors in existing satellite integrated electronic systems is poor and cannot meet the needs of high-performance computing and data processing.

[0048] Based on this, the embodiments of the present application provide a satellite data processing method, device, and equipment based on artificial intelligence, which are described below through embodiments.

[0049] Example 1

[0050] To facilitate understanding of this embodiment, a satellite data processing method based on artificial intelligence disclosed in the embodiment of this application is first introduced in detail. Figure 2 The flowchart of a satellite data processing method based on artificial intelligence is shown in the figure. The satellite data processing method based on artificial intelligence provided by the present application is applicable to a satellite integrated electronic system. The satellite integrated electronic system includes a main processor, a coprocessor, and an interface module; the main processor is respectively connected to the interface module and the coprocessor, and the method includes:

[0051] S101, the main processor receives a plurality of satellite data collected through the interface module, and identifies the plurality of satellite data to obtain first satellite data and second satellite data;

[0052] S102, the main processor processes the first satellite data to obtain a first processing result, and sends the second satellite data to the coprocessor;

[0053] S103, the coprocessor processes the received second satellite data through an artificial intelligence algorithm to obtain a second processing result; the artificial intelligence algorithm is preset in the coprocessor, and the type of the artificial intelligence algorithm corresponds to the type of the second satellite data;

[0054] S104. The coprocessor sends the second processing result to the main processor, so that the main processor controls the satellite accordingly based on the first processing result and the second processing result.

[0055] The satellite integrated electronic system is provided with a power supply module, which supplies power to the satellite integrated electronic system, that is, the power supply modules are respectively for the main processor, the coprocessor and the interface module; the main processor adopts the chip of XILINX Zynq UltraScale+MPSoC, and the coprocessor adopts the NVIDIA GPU chip, wherein the Xilinx Zynq UltraScale+MPSoC adopted by the main processor is a series of highly integrated multi-processor system chips, which integrates 64-bit quad-core or dual-core ARM Cortex-A53 processors and dual-core ARM Cortex-R5F processors, providing powerful computing power and real-time processing capabilities. In addition to the processor core, the chip also includes programmable logic, allowing users to customize hardware accelerators to optimize the performance of specific applications. Zynq UltraScale+MPSoC adopts FinFET process nodes, provides ASIC-level single-chip functions, and achieves high performance and low power consumption. These chips support a variety of memory interfaces and high-speed I / O interfaces, such as PCIe, 10 / 40G Ethernet, USB 3.0, etc., which facilitates high-speed data exchange with external devices and systems. It supports multiple operating systems such as Linux and FreeRTOS, as well as open source frameworks such as OpenCV and OpenCL. The main processor can also be used with other chips similar to XILINX Zynq UltraScale+MPSoC. The coprocessor uses the NVIDIA GPU chip, a GPU module designed for edge computing. It is a member of the NVIDIA Jetson series, providing powerful AI computing capabilities and efficient energy efficiency. Jetson Xavier NX provides up to 21TOPS (trillion operations per second) of AI computing power, supports multiple precision calculations, is equipped with an 8-core ARMv8.2 64-bit CPU and a 512-core Volta architecture GPU, as well as 64 Tensor Cores, equipped with 16GB of LPDDR4x memory and 32GB of eMMC storage, providing sufficient resources to store and process data, compact size and low power design, Jetson Xavier NX is suitable for integration into various embedded systems, supports multiple power consumption modes, including 10W, 15W and 30W, and can be configured according to the needs of specific applications. It provides a variety of interfaces and expansion options, including PCIe, USB, CSI camera interface, etc., to facilitate the connection of various peripheral devices.

[0056] In step S101, the main processor receives the collected multiple satellite data through the interface module. The main processor is connected to multiple peripheral devices through the interface module. The peripheral devices are used to collect multiple satellite data, including radar, high-spectrum camera, etc. The multiple satellite data include optical image data, radar image data, high-spectrum image data, and voltage, current, temperature and other data of multiple single machines on the satellite, as well as satellite attitude data, etc., and the multiple satellite data are identified. The identification method is preset in the main processor to obtain first satellite data and second satellite data; the main processor processes the first satellite data and the second satellite data according to the set processing method.

[0057] In the specific implementation process of step S101, there is an implementation method as follows: Figure 3 As shown, the main processor includes a PL module and a PS module;

[0058] The main processor receives the collected multiple satellite data through the interface module, and identifies the multiple satellite data to obtain the first satellite data and the second satellite data, including:

[0059] S1011, the PL module receives the multiple satellite data collected by the connected interface module; and sends the multiple satellite data to the PS module;

[0060] S1012: The PS module identifies the received multiple satellite data to obtain first satellite data and second satellite data.

[0061] The main processor uses the XILINX Zynq UltraScale+MPSoC chip, including a PL module and a PS module, such as Figure 5As shown, the PL module and the PS module are connected in a fixed manner for communication, such as through an AXI-4 bus, so the PL module outputs the various satellite data received by the interface module to the PS module. The PL module is a programmable logic control part, which is used to flexibly configure interfaces applicable to various types, so the interface module is connected to the PL module in the main processor module. The PL module has built-in interface communication software to achieve connection and communication with various peripheral devices. The interface modules that the PL module can connect to include analog quantity acquisition interface, thermal control interface, attitude control component interface, CAN bus interface, RS422 interface, OC command interface, and other interfaces, which can be set according to actual conditions. The analog quantity acquisition interface is used to receive analog quantities such as voltage and current on various single machines on the satellite, and the thermal control interface is used to connect to the thermal control interface for the satellite. Thermal component, the attitude control component interface is used to receive satellite attitude data and output control signals for the satellite, the CAN bus interface and RS422 interface are both communication interfaces for communicating with multiple single machines on the satellite, the OC command interface is used for the satellite integrated electronic system to output pulse signals for controlling multiple single machines on the satellite, the PS module is used to provide a running platform for the main control program, the main control program includes satellite service software and attitude control software, the PS module uses the satellite service software and attitude control software in the satellite data to identify multiple satellite data, when there are satellite service data and satellite attitude data that can be processed by the satellite service software and attitude control software, the satellite service data and satellite attitude data are used as the first satellite data, and the data other than the satellite service data and satellite attitude data in the multiple satellite data are the second satellite data, the PS module is connected to QSPI FLASH, QSPI FLASH is mainly used to store and load the program of the main processor MPSOC, and the PS module is mounted with DDR4, which is used as a cache when the program is running.

[0062] The satellite service data may describe the position and motion status of the satellite in orbit, such as longitude, latitude, altitude, speed, etc. It may also monitor the temperature changes of various components of the satellite to ensure that the satellite operates within an appropriate temperature range. It may also reflect the power supply status of the satellite power supply, including battery power, voltage, current, etc.

[0063] In step S102, after the main processor identifies the first satellite data and the second satellite data from the received multiple satellite data, the main processor processes the first satellite data to obtain a first processing result, where the first processing result includes a control instruction for controlling the satellite attitude, etc. While the main processor processes the first satellite data to obtain the first processing result, the main processor sends the second satellite data to the coprocessor. A transmission interface is provided between the main processor and the coprocessor, so that the second satellite data to be sent by the main processor can be sent to the coprocessor, and the coprocessor receives the second satellite data based on the transmission interface.

[0064] In the specific implementation process of step S102, there is an implementation mode in which the main processor processes the first satellite data to obtain the first processing result and sends the second satellite data to the coprocessor, and further includes:

[0065] S10211, the main processor inputs the data type of the first satellite data into corresponding processing software;

[0066] S10212: The processing software processes the first satellite data to obtain a first processing result.

[0067] In steps S10211-S10212, the main processor, upon identifying the first satellite data, divides the first satellite data into three data types according to the types of software existing in the processor, that is, the main processor divides the first satellite data into satellite service data and satellite attitude data according to the existing satellite service software, attitude control software and interface communication software, sends the satellite service data in the first satellite data to the satellite service software, sends the satellite attitude data in the first satellite data to the attitude control software, processes the satellite service data and satellite attitude data based on the satellite service software and the attitude control software, respectively, to obtain satellite service processing results and satellite attitude processing results, and uses the satellite service processing results and satellite attitude processing results as the first processing results, and stores the first satellite data and the first processing results at the same time for easy recording and backtracking.

[0068] In the specific implementation process of step S102, there is another implementation method: Figure 4 As shown, the main processor processes the first satellite data to obtain a first processing result and sends the second satellite data to the coprocessor, including:

[0069] S10221. The main processor identifies the transmission type of the second satellite data to obtain a transmission identification result;

[0070] S10222: The main processor selects a corresponding transmission interface according to the transmission identification result to send the second satellite data to the coprocessor.

[0071] In steps S10221-S10222, the main processor identifies the transmission type of the second satellite data, and divides the types of the second satellite data into control data and business data. The control data is data related to the coprocessor, such as setting the working module data of the coprocessor, and the business data is satellite-related data, such as satellite navigation positioning information data. The control data is set as low-speed data, and the business data is set as high-speed data. The low-speed data and the high-speed data are transmitted using different transmission interfaces. The high-speed data uses a PCIe interface for communication, and the low-speed data uses a UART for communication. A GPIO interface is also set between the main processor and the coprocessor for function expansion.

[0072] In step S103, the coprocessor works in cooperation with the main processor to share the computing task of the main processor. The coprocessor receives the second satellite data transmitted by the main processor through the interface between the coprocessor and the main processor. Figure 6 As shown, the working mode of the coprocessor is set based on the control data in the second satellite data, so that the coprocessor can process the satellite service data quickly and efficiently, and the received second satellite data is processed by the artificial intelligence algorithm preset in the coprocessor to obtain a second processing result, and the satellite is controlled accordingly based on the second processing result; the type of the artificial intelligence algorithm corresponds to the type of the second satellite data, that is, the coprocessor has an artificial intelligence algorithm corresponding to the type of the second satellite data, which can fully realize efficient and accurate processing of the second satellite data.

[0073] In the specific implementation process of step S103, there is an implementation mode in which the coprocessor processes the received second satellite data through an artificial intelligence algorithm to obtain a second processing result, including:

[0074] S1031, the coprocessor identifies the data type of the second satellite data to obtain a second identification result;

[0075] S1032: The coprocessor calls an artificial intelligence algorithm corresponding to the recognition result based on the recognition result to process the second satellite data to obtain the second processing result.

[0076] In steps S1031-S1032, the coprocessor receives the second satellite data transmitted by the main processor, and identifies the data type of the second satellite data based on a preset identification rule to obtain an identification result, wherein the identification rule is the type of the artificial intelligence algorithm existing in the coprocessor, that is, if the coprocessor has the artificial intelligence algorithm corresponding to the second satellite data, the identification result is passed, otherwise it is failed, then the coprocessor calls the artificial intelligence algorithm preset in the coprocessor to process the second satellite data according to the second satellite data with the identification result of passed to obtain a second processing result, and the second processing result includes multiple types. For example, if the coprocessor obtains that the real-time position of the satellite is not at the predetermined target position according to the artificial intelligence algorithm, then the coprocessor calculates the path information required for the satellite to reach the predetermined target position according to the second satellite data.

[0077] In the specific implementation process of step S1031, there is an implementation mode in which the coprocessor identifies the data type of the second satellite data to obtain a second identification result, including:

[0078] S10311: If the coprocessor identifies the data type of the second satellite data, a plurality of identification results are obtained;

[0079] S10312: The coprocessor simultaneously calls the artificial intelligence algorithms corresponding to the multiple recognition results, and simultaneously processes the second satellite data containing multiple data types to obtain multiple second processing results.

[0080] In steps S10311-S10312, if the second satellite data received by the coprocessor has multiple types and requires multiple artificial intelligence algorithms to process, the coprocessor identifies the data types of the second satellite data, thereby outputting multiple identification results, and the coprocessor simultaneously calls the artificial intelligence algorithms corresponding to the multiple identification results, and simultaneously processes the second satellite data containing multiple data types to obtain multiple second processing results. The NVIDIA GPU chip used by the coprocessor has powerful parallel processing capabilities, has thousands of cores, and can process a large number of computing tasks at the same time, which is very effective for matrix operations and large-scale data processing in deep learning; the NVIDIA GPU chip can provide high throughput, that is, it processes more satellite data per unit time, which is crucial for large neural networks that require fast iteration and training; compared with the main processor, the coprocessor usually has a higher energy efficiency ratio when performing parallel computing tasks, that is, it can complete more computing work while consuming the same amount of power; it has a mature ecosystem, and also provides optimized software libraries and frameworks for deep learning and machine learning, which simplifies the programming and application development process of the coprocessor.

[0081] In the specific implementation process of step S103, there is another implementation method: the artificial intelligence algorithm includes at least one of the following:

[0082] Intelligent modulation and coding algorithm, intelligent antenna beam control algorithm, intelligent navigation algorithm, intelligent orbit adjustment algorithm, intelligent health monitoring algorithm, intelligent resource allocation algorithm and intelligent task planning algorithm.

[0083] As satellite functions become more complex and their scale becomes larger, and the resources of ground control stations are limited, the satellite integrated electronic systems will develop towards intelligence and autonomy in the future, and artificial intelligence algorithms will be more and more widely used in satellite integrated electronic systems. Therefore, the artificial intelligence algorithms include but are not limited to intelligent modulation and coding algorithms, intelligent antenna beam control algorithms, intelligent navigation algorithms, intelligent orbit adjustment algorithms, intelligent health monitoring algorithms, intelligent resource allocation algorithms, and intelligent mission planning algorithms. Among them, the intelligent modulation and coding algorithm can dynamically adjust the modulation and coding scheme of satellite communications to adapt to different channel conditions and data requirements; the intelligent antenna beam control algorithm can be used to optimize the beamforming technology of satellite communications to improve signal quality and coverage; the intelligent navigation algorithm can help satellites to navigate autonomously, avoid space debris and other satellites, and reduce the intervention of ground control centers; the intelligent orbit adjustment algorithm can predict and adjust the orbit of the satellite to maximize its mission efficiency and lifespan; the intelligent health monitoring algorithm is used to monitor the health of the satellite in real time, predict potential failures, and make maintenance recommendations; the intelligent resource allocation algorithm can help optimize the allocation of satellite resources, such as power supply, bandwidth and computing power, to support different tasks; the intelligent task planning algorithm can automatically adjust the priority of tasks according to the urgency and importance of the tasks.

[0084] In step S104, the coprocessor sends the second processing result to the main processor, so that the main processor controls the satellite accordingly based on the first processing result and the second processing result.

[0085] After processing the second satellite data to obtain a second processing result, the coprocessor transmits the second processing result to the main processor through the communication interface between the main processor and the coprocessor. The main processor makes decisions based on the second processing result and the first processing result to generate control instructions. The decision-making can be performed by logical judgment, rule matching, optimization algorithm or machine learning model in the main processor, and the satellite is controlled accordingly according to the control instruction. The execution result of the satellite after executing the control instruction will be fed back to the main processor through the satellite's sensor or other monitoring equipment. The main processor will evaluate the feedback information to understand whether the control effect meets expectations. If there is a deviation or deficiency, the main processor will re-evaluate the processing result, make a new decision and generate a new control instruction to make necessary adjustments and optimizations.

[0086] Example 2

[0087] The present application also provides a satellite data processing device based on artificial intelligence, such as Figure 7The block diagram of a satellite data processing device based on artificial intelligence is shown. The functions implemented by the satellite data processing device based on artificial intelligence correspond to the steps of executing a satellite data processing method based on artificial intelligence on a terminal device. The device can be understood as a component of a server including a processor, and the device includes:

[0088] An identification module 701 is used for the main processor to receive the multiple satellite data collected through the interface module, and identify the multiple satellite data to obtain the first satellite data and the second satellite data;

[0089] A sending module 702, configured for the main processor to send the second satellite data to the coprocessor while processing the first satellite data to obtain a first processing result;

[0090] The receiving module 703 is used for the coprocessor to process the received second satellite data through an artificial intelligence algorithm to obtain a second processing result; the artificial intelligence algorithm corresponds to the type of the second satellite data;

[0091] The processing module 704 is used for the coprocessor to send the second processing result to the main processor, so that the main processor controls the satellite accordingly based on the first processing result and the second processing result.

[0092] In a feasible implementation manner, the receiving module includes:

[0093] A first identification module, configured for the coprocessor to identify the data type of the second satellite data to obtain a second identification result;

[0094] A calling module is used for the coprocessor to call the artificial intelligence algorithm corresponding to the recognition result based on the recognition result to process the second satellite data to obtain the second processing result.

[0095] In a feasible implementation manner, the receiving module further includes:

[0096] A second identification module, configured to obtain a plurality of identification results if the coprocessor identifies the data type of the second satellite data;

[0097] The first processing module is used for the coprocessor to simultaneously call the artificial intelligence algorithms corresponding to the multiple recognition results, and simultaneously process the second satellite data containing multiple data types to obtain multiple second processing results.

[0098] In a feasible implementation manner, the receiving module further includes:

[0099] Intelligent modulation and coding algorithm, intelligent antenna beam control algorithm, intelligent navigation algorithm, intelligent orbit adjustment algorithm, intelligent health monitoring algorithm, intelligent resource allocation algorithm and intelligent task planning algorithm.

[0100] In a feasible implementation, the identification module includes:

[0101] The PL module receives the various satellite data collected by the connected interface module; and sends the various satellite data to the PS module;

[0102] The PS module identifies the received multiple satellite data to obtain first satellite data and second satellite data.

[0103] In a feasible implementation manner, the sending module includes:

[0104] The main processor identifies the transmission type of the second satellite data to obtain a transmission identification result;

[0105] The main processor selects a corresponding transmission interface according to the transmission identification result to send the second satellite data to the coprocessor.

[0106] In a feasible implementation manner, the sending module further includes:

[0107] The main processor inputs the data type of the first satellite data into corresponding processing software;

[0108] The processing software processes the first satellite data to obtain a first processing result.

[0109] Example 3

[0110] The present application also provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory through the bus, and when the machine-readable instructions are executed by the processor, any one of the steps of the satellite data processing method based on artificial intelligence is performed.

[0111] Example 4

[0112] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the computer program executes the steps of any one of the satellite data processing methods based on artificial intelligence.

[0113] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the method embodiment, and will not be repeated in this application. In the several embodiments provided in this application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0114] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0115] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0116] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a platform server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks, or optical disks.

[0117] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A satellite data processing method based on artificial intelligence, characterized in that: Applicable to a satellite integrated electronic system, the satellite integrated electronic system comprising a main processor, a coprocessor, and an interface module; The main processor is connected to the interface module and the coprocessor respectively, and the method includes: The main processor receives the collected multiple satellite data through the interface module, and identifies the multiple satellite data to obtain the first satellite data and the second satellite data; The main processor processes the first satellite data to obtain a first processing result, and sends the second satellite data to the coprocessor; The coprocessor processes the received second satellite data by using an artificial intelligence algorithm to obtain a second processing result; the artificial intelligence algorithm is preset in the coprocessor; the type of the artificial intelligence algorithm corresponds to the type of the second satellite data; The coprocessor sends the second processing result to the main processor, so that the main processor controls the satellite accordingly based on the first processing result and the second processing result.

2. The method according to claim 1, characterized in that The coprocessor processes the received second satellite data by using an artificial intelligence algorithm to obtain a second processing result, including: The coprocessor identifies the data type of the second satellite data to obtain a second identification result; The coprocessor calls an artificial intelligence algorithm corresponding to the recognition result based on the recognition result to process the second satellite data to obtain the second processing result.

3. The method according to claim 2, characterized in that The coprocessor identifies the data type of the second satellite data to obtain a second identification result, including: If the coprocessor identifies the data type of the second satellite data, a plurality of identification results are obtained; The coprocessor simultaneously calls the artificial intelligence algorithms corresponding to the multiple recognition results, and simultaneously processes the second satellite data containing multiple data types to obtain multiple second processing results.

4. The method according to claim 1, characterized in that: The artificial intelligence algorithm includes at least one of the following: Intelligent modulation and coding algorithm, intelligent antenna beam control algorithm, intelligent navigation algorithm, intelligent orbit adjustment algorithm, intelligent health monitoring algorithm, intelligent resource allocation algorithm and intelligent task planning algorithm.

5. The method according to claim 1, characterized in that The main processor includes a PL module and a PS module; The main processor receives the collected multiple satellite data through the interface module, and identifies the multiple satellite data to obtain the first satellite data and the second satellite data, including: The PL module receives the various satellite data collected by the connected interface module; and sends the various satellite data to the PS module; The PS module identifies the received multiple satellite data to obtain first satellite data and second satellite data.

6. The method according to claim 1, characterized in that The main processor processes the first satellite data to obtain a first processing result and sends the second satellite data to the coprocessor, including: The main processor identifies the transmission type of the second satellite data to obtain a transmission identification result; The main processor selects a corresponding transmission interface according to the transmission identification result to send the second satellite data to the coprocessor.

7. The method according to claim 1, characterized in that The main processor processes the first satellite data to obtain a first processing result and sends the second satellite data to the coprocessor, further comprising: The main processor inputs the data type of the first satellite data into corresponding processing software; The processing software processes the first satellite data to obtain a first processing result.

8. A satellite data processing device based on artificial intelligence, characterized in that: The device comprises: an identification module, used for the main processor to receive the multiple satellite data collected through the interface module, and identify the multiple satellite data to obtain the first satellite data and the second satellite data; a sending module, configured for the main processor to send the second satellite data to the coprocessor while processing the first satellite data to obtain a first processing result; a receiving module, configured for the coprocessor to process the received second satellite data through an artificial intelligence algorithm to obtain a second processing result; the artificial intelligence algorithm corresponds to the type of the second satellite data; A processing module is used for the coprocessor to send the second processing result to the main processor, so that the main processor can control the satellite accordingly based on the first processing result and the second processing result.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the satellite data processing method based on artificial intelligence as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the satellite data processing method based on artificial intelligence as described in any one of claims 1 to 7 are executed.

Images