Hierarchical distributed satellite autonomous health management method and system

Abstract

The invention discloses a layered distributed satellite autonomous health management method and system, and the system is used for layering and grading the fault level and health management of each level of an intelligent satellite. The system comprises a subsystem layer used for realizing hardware health management, a satellite service layer used for realizing autonomous safety protection and basic health management, and a whole satellite layer used for realizing autonomous intelligent health management and in-orbit calculation and reconstruction tasks. According to the technology, the dependence of satellite health management on a ground system, communication bandwidth and a communication window can be reduced, fault diagnosis and fault processing which originally must be carried out on the ground system are deployed on a satellite, the autonomy of satellite health management, the real-time performance of exception processing and the intelligence of fault diagnosis are improved, the safety and reliability of satellite operation are remarkably improved, and the safety and reliability of satellite health management are improved. And meanwhile, more technical innovation and application prospects are brought to the field of satellite health management.

Description

Technical Field

[0001] The present invention relates to the field of satellite on-orbit operation and health management, and in particular to a hierarchical distributed satellite autonomous health management method and system for providing scientific, accurate, and comprehensive on-orbit health management services for satellites or satellite clusters. Background Art

[0002] The on-orbit anomaly monitoring, fault diagnosis, and health management of satellites are of great significance for the normal on-orbit operation, mission reliability, and service life of satellites. Through the payloads such as computing power, processing, storage, communication, and sensing on the satellite and the ground system, a satellite health management system can be established to ensure the normal service of the satellite. The prior art closest to the present invention, such as [1]-[4], realizes satellite health management by establishing information collection based on satellite sensors, communication transmission and data anomaly monitoring based on traditional satellite bus systems, establishing the mapping between common satellite faults and signals, and based on the health management program installed in the satellite bus system and data processing and fault diagnosis on the ground system. However, the on-board autonomous health management ability of the prior art inventions is weak, and complex abnormal situations and faults highly rely on the ground system, are restricted by satellite communication bandwidth and windows, and have a large lag. The new type of intelligent satellite integrates a real-time operating system and high-performance computing power, providing an algorithm and computing power basis for intelligent and highly autonomous health management. Installing a swarm intelligence management system and deploying parallel computing on the basis of the real-time operating system can conveniently load machine learning algorithms for intelligent fault diagnosis and autonomous processing.

[0003] Prior Art: [1] On-Orbit Health Comprehensive Management Terminal and Management Method for Small Satellites Based on FPGA The present invention provides an on-orbit health comprehensive management terminal and management method for small satellites based on FPGA. It includes a monitoring information collection system for on-orbit satellites, an FPGA-based satellite data analysis and processing system, an on-orbit satellite health data evaluation and management system, a system fault tolerance control system, a satellite health data output system, a system communication bus, a backup type NOR flash memory, and a PROM module. The FPGA-based satellite data analysis and processing system includes a PROM and an SRAM, can process satellite health information, and has fault tolerance processing ability; the on-orbit satellite health data evaluation and management system contains a satellite health management rule library and on-orbit satellite health evaluation and prediction, and can store the health evaluation criteria and health status of the satellite.

[0004] [2] On-Orbit Spacecraft Health Management Method, Device and Electronic Equipment The present invention provides a method, apparatus, and electronic device for on-orbit spacecraft health management. The method includes: collecting data required for the health management program, where the data includes telemetry data and the logical sequence of the ground control center; storing a script library for fault judgment and disposal required for generating the health management program, where the script library is a database for generating the health management program; based on the operation mode of the health management program and the script library, writing the collected logical sequence and telemetry data into the first health management program to generate the second health management program; using the second health management program to perform fault health diagnosis on the device to be managed and executing corresponding disposal methods according to the diagnosis results. The present invention can continuously expand the fault modes that can be covered by satellite health management through the simple operation of uploading the logical sequence on the ground control center to adapt to the flexible working mode of the spacecraft and the uncertainties caused by the harsh on-orbit environment.

[0005] [3] Satellite Fault Diagnosis System Based on Quality Problem Knowledge Graph The present invention relates to a satellite fault diagnosis system based on a quality problem knowledge graph, which includes two parts: the construction of a satellite quality problem knowledge graph and a satellite fault diagnosis method based on the quality problem knowledge graph. One is to establish multi-dimensional correlation relationships among satellite historical fault case data by constructing a satellite quality problem knowledge graph, and the other is to adopt a multi-dimensional retrieval and interaction paradigm based on the knowledge graph, including input processing for identifying key fault description elements based on a text convolutional neural network, and a similarity calculation method combining keywords, representation learning, and meta-paths to recommend possible fault causes and maintenance measures, assisting engineers in making satellite health management decisions and realizing intelligent fault diagnosis at the satellite system level and single-unit level.

[0006] [4] A General Satellite Health Management System and Method A general satellite health management system and method relate to the field of satellite management. It solves the problems of poor scalability and portability and the inability to handle complex logical faults in traditional satellite health management methods. The system includes: an on-board service main unit and a health management unit; the on-board service main unit includes a health management node; the health management node contains a standard service configuration module; the health management unit includes a health management module, a standard input / output interface, and a fault processing module; the standard service configuration module obtains the detection data of the health management node and performs service configuration; the health management module reads the configuration information and performs joint diagnosis on the configuration information; the fault processing module obtains the diagnosis result and generates a fault processing description; the standard input / output interface receives the fault processing description and transmits it to the health management unit; the health management node receives the fault processing description and modifies the configuration and working mode according to the ground command. It is applied to the aerospace field. Summary of the Invention

[0007] The object of the present invention is to address the deficiencies of the above-mentioned prior art. The present invention proposes a hierarchical distributed intelligent autonomous health management method and system for intelligent satellites. This technology can reduce the dependence of satellite health management on ground systems, communication bandwidth, and communication windows, deploy fault diagnosis and fault handling that were originally required to be carried out on ground systems to the satellite, and use an intelligent algorithm based on a behavior tree to achieve autonomous health management, which is convenient for code reuse and has high reactivity. This method can improve the autonomy of satellite health management, the real-time performance of exception handling, and the intelligence of fault diagnosis, significantly improve the operational safety and reliability of satellites, optimize energy utilization, and at the same time bring more technological innovations and application prospects to the field of satellite health management.

[0008] To achieve the above object, the present invention provides a hierarchical distributed satellite autonomous health management system. The system is used to hierarchically and classify the fault levels and health management of each level of the intelligent satellite, including a subsystem layer for implementing hardware health management, a satellite bus layer for implementing autonomous safety protection and basic health management, and a satellite layer for implementing autonomous intelligent health management and on-orbit computing and reconstruction tasks; where: The subsystem layer is used to self-check and monitor the status of the hardware of each subsystem, feedback the available, operating, or abnormal status of the subsystem hardware to the satellite bus layer, receive the action commands of the satellite bus layer and execute them. At the same time, it is responsible for collecting the in-system test sensor information of each subsystem and transmitting the data to the control cores of the satellite bus layer and the satellite layer through the satellite bus, providing data input for health management. The satellite bus layer is used to monitor and manage the basic functions of the safe operation of the satellite, and at the same time perform basic health management on the hardware of each subsystem, etc.; the basic functions of the safe operation of the satellite include satellite orbit, attitude, and energy supply; the satellite bus layer can also perform basic monitoring on the subsystem hardware and upload the data to the satellite control core, and can also communicate with the ground system separately. The satellite layer is based on high-performance parallel computing hardware and a real-time operating system, and distributes and deploys an intelligent autonomous health management system, receives data information from the satellite bus layer, and is responsible for the status monitoring of the entire satellite, the confirmation of payload task capabilities, the processing of health management data, data mining and information fusion, fault diagnosis and prediction, intelligent decision-making based on a behavior tree, function reconstruction, and the evaluation of task reliability and software reliability.

[0009] Further, the subsystem hardware includes satellite bus hardware, a control subsystem, an energy subsystem, and a thermal management subsystem.

[0010] Further, in order to save resources, the subsystem layer does not continuously monitor all subsystem hardware, but adopts a work-on-demand method.

[0011] Further, the health management of the satellite bus layer adopts a continuous working method.

[0012] Furthermore, the core of the satellite-wide control consists of multiple parallel computing nodes, and a real-time operating system is distributedly deployed; thereby realizing the transfer of data processing and fault prediction that originally had to be transmitted to the ground through the link during the satellite communication window for processing to the autonomous health management system of the control core.

[0013] Furthermore, the satellite-wide layer can communicate bidirectionally with the ground and the satellite service layer at the same time. The satellite-wide layer adopts an intermittent working mode in each satellite's orbit around the Earth. When the satellite-wide control core is turned off, the satellite service layer takes over the satellite and is responsible for autonomous security protection and basic health management.

[0014] Furthermore, the hardware of each subsystem communicates with the subsystem control node through a bus. The hardware of the subsystem is modularized upward to the control core, and the intelligent autonomous health management application software APP can call and manipulate all the hardware of the subsystem through the interface protocol.

[0015] Furthermore, the satellite service system of the satellite service layer is deployed at the subsystem control node, and all the data and log files of the satellite service system are uploaded and stored in the health data storage unit of the control core.

[0016] Furthermore, both the control core and the subsystem control node communicate with the satellite ground system for two-way backup.

[0017] On the other hand, the present invention provides a hierarchical distributed satellite autonomous health management method, and the method is used to realize satellite autonomous health management.

[0018] Beneficial effects

[0019] 1. The present invention breaks the dependence on the satellite communication link bandwidth and window of traditional satellite health management, and transfers data processing, mining, fusion, fault diagnosis and prediction, and selection of processing measures that originally needed to be carried out in the ground system to be autonomously carried out by the real-time operating system deployed on the satellite control core, improving the autonomy and efficiency of health management.

[0020] 2. Adopting a hierarchical distributed health management architecture, the health status of the satellite is managed in layers and levels. By means of the intermittent working measure of the satellite-wide layer with a large demand for energy, an intelligent health management mode is adopted when the energy is sufficient, and a basic health management mode is adopted when the energy is tense, realizing the maximum utilization of satellite resources while ensuring the basic operation functions of the satellite.

[0021] 3. The satellite autonomous health management architecture proposed by the present invention can achieve on-board storage of all sensor data, subsystem operation log data, etc. during the satellite operation, without occupying valuable link resources, and perform big data mining and model training based on the intelligent algorithms deployed in the control core, making full use of the on-board data and computing power advantages, and thus more scientifically and accurately achieving the early prediction of satellite faults.

[0022] 4. The satellite autonomous health management method and system proposed by the present invention adopt a health management control strategy based on a behavior tree in the control core, and construct a satellite autonomous health management agent, which can achieve autonomous monitoring, switching, prediction, reaction, etc. of the satellite health status. Description of the Drawings

[0023] Figure 1 is a schematic diagram of the hierarchical distributed satellite intelligent autonomous health management architecture of the present invention; Figure 2 is a schematic diagram of the health management strategy and technology of the satellite service layer of the present invention; Figure 3 is a schematic diagram of the health management strategy and technology of the whole satellite layer of the present invention; Figure 4 is a schematic diagram of the data flow of the autonomous health management of the present invention. Detailed Embodiments

[0024] Next, the technical solutions of the present invention will be clearly and completely described in conjunction with the drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0025] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation to the present invention. In addition, the terms "first", "second", and "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0026] In the description of the present invention, it should be noted that, unless otherwise clearly specified and defined, the terms "installation", "connection", and "coupling" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0027] The following will be combined with Figures 1-4 to elaborate in detail on the specific implementation manners of the present invention. It should be understood that the specific implementation manners described herein are only used to illustrate and explain the present invention and are not used to limit the present invention.

[0028] Traditional satellites use the satellite bus system as the core for satellite orbit management, and each subsystem undertakes different payloads and has a separate processing unit. Compared with the architecture of traditional satellite sensors - subsystems - the whole satellite, intelligent satellites adopt modular payload hardware. Instead of setting up a separate control and processing unit and data storage for each subsystem, a separate control core is set up at the whole satellite level. The control core has data storage and high-performance parallel computing power, and deploys a real-time operating system (such as Linux, etc.). All payloads (remote sensing, communication, optics, energy, etc.) are a module for the control core. The swarm intelligence system and application software can be deployed at the real-time operating system level, and each application can call all payload resources. The intelligent satellite architecture provides an operating system software environment, high-performance computing power, and hardware foundation for intelligent autonomous health management. With the help of intelligent algorithms, a large amount of remote sensing data that traditional satellites must transmit to the ground system for processing can be transferred to on-board processing, breaking the dependence on the ground system, reducing the response time of health management, and at the same time, no longer being limited by communication bandwidth and communication windows, which can save a large amount of communication resources for satellite missions. In addition, in order to improve the satellite's survival ability and reliability, the satellite bus management related to satellite orbit safety and basic functions is retained for intelligent satellites. For the architecture of intelligent satellite subsystem layer - satellite bus layer - whole satellite layer, a hierarchical distributed satellite intelligent autonomous health management architecture for intelligent satellites is designed as Figure 1 shown. First, the fault levels and health management of each layer of the intelligent satellite are stratified and graded, so that the hierarchical distributed satellite autonomous health management system includes a subsystem layer for realizing hardware health management, a satellite bus layer for realizing autonomous security protection and basic health management, and a whole satellite layer for realizing autonomous intelligent health management and on-orbit computing and reconstruction tasks. Figure 1The hierarchical distributed satellite intelligent autonomous health management architecture of the intelligent satellite is, in order from the lower level to the higher level, the subsystem layer, the satellite service layer, and the satellite level. Each layer processes the satellite health data at its corresponding level, forming subsystem layer health data, satellite service layer health data, and satellite level health data. Among them, knowledge / rule databases and model databases are respectively built in the satellite service layer and the satellite level. The satellite service layer and the satellite level can communicate directly with the satellite ground system. The satellite level is deployed with a real-time operating system / parallel computing nodes, on which an intelligent autonomous health management APP can be installed, and the health data management of the entire satellite is realized based on the control logic of the behavior tree.

[0029] Among them, the subsystem layer is responsible for self-checking and monitoring the states of the hardware of each subsystem (such as sensing, communication, etc.), feeding back the available, operating, and abnormal states of the subsystem to the upper level, receiving action commands (such as restart, reset, etc.) from the upper level and executing them. At the same time, it is responsible for collecting the information of built-in test (BIT) sensors of each subsystem and transmitting the data to the control cores of the satellite service layer and the satellite level (application software) through the satellite bus, providing data input for higher-level health management. To save resources, the subsystem layer does not need to continuously monitor all subsystems, so it can work on demand. The on-demand working logic is divided into: power-on self-check, regular reporting, and on-demand acquisition. First, when the satellite starts up and runs, the subsystem layer conducts a state self-check on all its affiliated hardware to obtain self-check information, which includes the power supply information, working state information, working mode, communication state, data storage state, and whether it can be called of the sensing and communication payloads, and transmits the self-check information upward to the satellite service layer and the satellite level. When a certain piece of hardware in the subsystem layer is in a silent state (not working), it reports its state upward at regular intervals. When the satellite needs to call a certain piece of hardware in the subsystem layer to execute a task, a state acquisition instruction is issued to obtain the health state data of all subsystems required for the task as needed. In addition, the subsystem layer sets basic health management strategies based on threshold values to ensure the robustness and reliability of health management. When the above monitoring parameters exceed / fall below the set thresholds, monitoring is started, and when there is no abnormality, monitoring is carried out at the set intervals.

[0030] The satellite bus layer is responsible for monitoring and managing the basic functions related to the safe operation of the satellite, such as satellite orbit, attitude, and energy supply. At the same time, it conducts basic health management on the satellite bus hardware, control subsystem, energy subsystem, thermal management subsystem, etc. A fault knowledge / rule database is established in the satellite bus system, covering common faults of the satellite bus, subsystems, and basic function hardware of the satellite. Program-controlled codes are established for each fault, enabling the perception, diagnosis, and handling of faults related to satellite safety. Meanwhile, the satellite bus layer can also conduct basic monitoring on the subsystem hardware and upload the data to the satellite control core, and can also communicate with the ground system independently. Since the health management of the satellite bus layer is related to the basic safety of the satellite, it needs to work continuously. The strategies and technologies for the basic health management of the satellite bus layer of the intelligent satellite are as Figure 2 shown. In terms of technology, based on relevant aerospace test standards and basic methods such as fault detection, diagnosis, and abnormal threshold values, a rule-based database is established. In terms of strategy, it realizes the monitoring of subsystem and satellite bus status, ensures the safety of payload tasks and energy supply, and can control the satellite to enter the satellite safety mode when necessary, and implement system recovery and system reconstruction.

[0031] The whole satellite layer is based on high-performance parallel computing hardware and a real-time operating system, and distributes and deploys an intelligent autonomous health management system (application software). It receives data information from the satellite bus layer and subsystem layer, and is responsible for the status monitoring of the whole satellite, the confirmation of payload task capabilities, the processing of health management data, data mining and information fusion, fault diagnosis and prediction, intelligent decision-making based on behavior trees, function reconstruction, and the evaluation of task reliability and software reliability, etc. The satellite control core consists of multiple parallel computing nodes and can distribute and deploy a real-time operating system. Due to the high-performance computing, data storage advantages of the control core and the environment provided by the real-time operating system, data processing, fault prediction, etc. that originally had to be transmitted to the ground for processing through the link during the satellite communication window can be transferred to the autonomous health management system of the control core for direct intelligent analysis and prediction, autonomous decision-making, and rapid processing, without being restricted by the link window, bandwidth, and task occupation, and more resources can be provided to critical tasks.

[0032] such as Figure 3As shown in the figure, with the help of machine learning, parallel computing, data mining, information fusion, and historical data, all the data of the entire satellite can be monitored, diagnosed, and predicted in real time. Machine learning is carried out based on the model-based database to realize on-board model training, making full use of the advantages of on-board big data and computing power. Intelligent decision-making is carried out based on the behavior tree, and the satellite health management function can be reconstructed as needed. The entire satellite layer can communicate bidirectionally with the ground and the satellite service layer at the same time, providing status information and payload task ability confirmation for the ground center and other tasks. First, when the entire satellite layer is powered on, the satellite service layer communicates bidirectionally with the entire satellite layer through the intelligent satellite high-speed communication bus, saves all the data of the subsystems and the health management of this layer obtained to the entire satellite layer. At the same time, the entire satellite layer refines the health management operation instructions of fault diagnosis, isolation, and function reconstruction into the execution instructions of the satellite service layer and sends them to the satellite service layer for execution; when the satellite reaches the communication window with the satellite ground system, the entire satellite layer communicates with the satellite ground system through the satellite-ground communication link. The entire satellite layer combs, streamlines, and packages the entire satellite health management data, and sends the key data and information to the satellite ground system so that ground personnel can obtain the satellite health status. At the same time, the entire satellite layer can receive the manual instructions sent by the satellite ground system through the communication link, so that manual intervention in the intelligent satellite health management can be carried out when necessary. The above bidirectional communication mechanism realizes the access, acquisition, and instruction distribution of the entire satellite layer for satellite health management data, while retaining the status acquisition and manual intervention of the satellite ground system for the entire satellite, solving the problems of less health management data and operation delay caused by the communication link bandwidth limitation and communication window limitation of traditional satellites, and enabling real-time, fast, and intelligent autonomous health management of the satellite based on on-board computing power and big data. Since the parallel computing nodes and the real-time operating system have a large demand for energy, the entire satellite layer used to implement autonomous intelligent health management works intermittently in the middle of each satellite's orbit around the earth. When the entire satellite control core is turned off, the satellite service layer takes over the satellite and is responsible for autonomous safety protection and basic health management. During the satellite's orbit around the earth, there is a period of time when the satellite enters the shadow area. At this time, the satellite's solar panels cannot charge the satellite. When the battery power of the satellite is lower than the set threshold, the satellite needs to enter the low-power mode. Since the high-performance parallel computing nodes of the entire satellite layer have a high power consumption, the power of the intelligent satellite during the orbit around the earth cannot support the continuous operation of the computing nodes without shutting down. During the operation of the satellite, the health management of the entire satellite layer and the health management of the satellite service layer monitor the satellite's energy state in real time. When the satellite enters the area where it cannot be charged and the remaining power of the entire satellite is less than the set threshold, the parallel computing nodes of the entire satellite layer are turned off, and only the satellite service layer is retained to maintain the key operation of the satellite. After the battery is charged to the set threshold when the satellite enters the rechargeable area, the parallel computing nodes are turned on.

[0033] During each satellite's orbital period around the Earth, the satellite-level switches between the working state and the off state; when the satellite-level is in the working state, it manages the satellite using an autonomous intelligent health management mode, while the on-board management layer is responsible for autonomous security protection; when it is detected that the satellite enters the shadow area and the battery power is lower than the set power threshold, the satellite-level switches to the off state. At this time, the parallel computing nodes of the satellite-level are turned off, the satellite enters the low-power mode, and the on-board management layer takes over the satellite, responsible for autonomous security protection and managing the satellite using the basic health management mode. When it is detected that the satellite leaves the shadow area, the output current of the solar panels is greater than the set current threshold, and the battery power exceeds the set power threshold, the satellite-level switches to the working state, turns on the parallel computing nodes of the satellite-level, realizes the autonomous intelligent health management mode of the satellite, and at the same time the on-board management layer turns off the basic health management mode and is only responsible for autonomous security protection.

[0034] The autonomous intelligent health management mode adopted by the satellite-level means that based on the data information provided by the subsystem layer and the on-board management layer, with the help of machine learning, parallel computing, data mining, information fusion, and historical data, all data of the satellite are monitored, diagnosed, and predicted in real time. Machine learning is carried out based on the model-based database to realize on-board model training, intelligent decision-making is carried out based on the behavior tree, and the satellite health management function is reconstructed as needed.

[0035] The basic health management mode adopted by the on-board management layer means that based on the data information provided by the subsystem layer, combined with the fault knowledge and rule database, program control codes for each fault are established to realize the perception, diagnosis, and handling of faults related to satellite safety. The fault knowledge and rule database cover common faults in on-board management, subsystems, and satellite basic function hardware.

[0036] The autonomous health management system of the intelligent satellite manages the health status of the satellite based on the Behavior Tree (BT). The behavior tree is a method for switching between different tasks in an autonomous agent and is an effective way to create a modular and reactive complex system, commonly used in agents in robots or games. The present invention proposes an autonomous management and control of the satellite health status based on the behavior tree, which has the advantages of modularity, hierarchical organization, reusable code, high reactivity and expressive ability, strong readability, and applicability to analysis and autonomous planning. Compared with control strategies such as finite state machines, decision trees, subsumption architectures, and remote reaction programs, it has significant advantages.

[0037] The data flow of the autonomous health management of the intelligent satellite is as Figure 4 shown. Figure 4The intelligent autonomous health management APP and the health data storage unit are deployed in the real-time operating system of the whole satellite layer, and the real-time operating system is installed on the parallel computing nodes. There are multiple computing nodes deployed in the whole satellite layer, which can achieve parallel computing and back up each other. The subsystem control nodes are deployed in the satellite bus layer, which can realize data sharing and storage for the subsystem layer and the whole satellite layer, and directly communicate with the satellite ground system in the low-power mode (when the parallel computing nodes in the whole satellite layer are in the off state). Each subsystem and its components are deployed in the subsystem layer, and data sharing and storage are carried out with the subsystem control nodes through the data bus. The subsystem layer is all designed in a modular way, and upward modularization is achieved for the whole satellite layer in terms of hardware resources. The intelligent autonomous health management application software (APP) can call and manipulate all subsystem hardware through the interface protocol. The satellite bus system is deployed in the subsystem control nodes, and all data and log files of the satellite bus system are uploaded and stored in the health data storage unit of the control core. Both the control core and the subsystem control nodes can communicate with the satellite ground system for two-way backup.

[0038] On the other hand, the present invention provides a hierarchical distributed satellite autonomous health management method, which is used to realize satellite autonomous health management. Specifically, the method includes the following steps: S1. Power on the whole satellite, power on the satellite bus layer and the subsystem layer, and each subsystem enters the self-check state. Each subsystem layer uploads the data of each sensor to the satellite bus layer; S2. Judge whether the whole satellite layer can enter the working state according to the working state of the solar panels and the battery power. If the whole satellite layer is in the off state, the satellite bus layer manages the satellite in the basic health management mode; if the whole satellite layer enters the working state, the autonomous health management system is initialized and step S3 is entered; S3. The whole satellite layer receives the data from the satellite bus layer, where the data includes the sensor data of each subsystem layer, and stores the received data in the health management database of the whole satellite layer; S4. The intelligent autonomous health management APP of the entire satellite level runs; (The intelligent autonomous health management APP is the software of the autonomous health management system) The intelligent autonomous health management APP reads the data in the health management database, including the key sensor data of each subsystem (such as temperature, pressure, battery voltage, momentum wheel speed, etc.), the available status data of the software and hardware of each level (such as the status of parallel computing nodes, energy status, attitude and orbit control status, communication status, etc.), etc.; Execute the entire satellite health management behavior tree to achieve real-time monitoring and management of the entire satellite's operating status; During the operation of the health management behavior tree, based on the massive data in the entire satellite health management database, adopt artificial intelligence methods such as big data mining and reinforcement learning to achieve the processing of the entire satellite's health management data, status monitoring, payload task ability confirmation, data mining and information fusion, fault diagnosis and prediction, and task reliability assessment, and give intelligent decisions such as fault location, isolation, maintenance, emergency recovery, and autonomous optimization according to the fault situation, as well as the reconstruction plan of the satellite mission, hardware, software, and system. In terms of intelligent decision-making, monitor the real-time status of the satellite's key components, systems, and the entire satellite, collect parameters such as temperature, voltage, and current, and use data processing and analysis techniques to evaluate the health status of the satellite in combination with the set thresholds or established models, such as determining whether the components are working properly and whether the system performance has declined, etc.; When an abnormal condition is detected, rely on methods such as fault tree analysis, expert system, and machine learning to accurately locate and analyze the cause of the fault, determine which component and which system have failed, as well as the type and severity of the fault, such as whether it is a sensor fault, a power system fault, or a communication system fault, etc.; Use machine learning and data mining techniques to learn and analyze the satellite's historical operation data, fault data, etc., continuously optimize the decision-making model and algorithm, improve the accuracy and reliability of intelligent decision-making, and enable the satellite to better adapt to the complex on-orbit operation environment and mission requirements; When the satellite encounters a sudden fault or emergency, such as component failure, being affected by space radiation, etc., it can quickly make an emergency response decision and take measures such as switching to backup equipment, entering the safe mode, and reconfiguring system parameters to make the satellite resume normal operation as soon as possible or minimize the impact of the fault on the satellite.In terms of function reconstruction, the satellite's tasks are re-planned and optimized by combining the satellite's health status and mission requirements, and the satellite's resources are reasonably allocated, such as adjusting the satellite's attitude, controlling the power-on and power-off time of payloads, and allocating energy, etc., to ensure that while meeting the mission objectives, the satellite's health and lifespan are not affected by excessive resource consumption or unreasonable allocation; according to the changes in the satellite's health status and mission objectives, the satellite's tasks are redefined and adjusted so that it can better complete the established tasks or undertake new tasks. For example, when some payloads of the satellite fail, through task reconstruction, the priority and objectives of the task are adjusted, and the remaining payload functions are used to complete more valuable scientific exploration or data acquisition tasks, etc.; the satellite's hardware components are replaced, repaired or reconfigured in orbit to restore or enhance its functions. For example, faulty electronic components are replaced in orbit, the optical lens is cleaned or repaired, and the antenna pattern is reconfigured, etc.; the satellite's software system is upgraded, updated or rewritten to implement new functions or repair existing vulnerabilities and defects. For example, the algorithm of the flight software is optimized to improve control accuracy, new mission modes and function modules are added, and software failures caused by the space environment are repaired, etc.; function reconstruction is carried out at the satellite system level, including adjusting and optimizing the collaborative working mode between multiple subsystems to meet new mission requirements or solve existing system problems. For example, the data transmission method and collaborative control strategy between the communication system and the attitude control system are changed to improve the stability of communication and the accuracy of attitude control, etc.

[0039] S5. The intelligent autonomous health management APP sends decision instructions to the satellite service layer and the subsystem layer, and bets data to the ground system.

[0040] Further, in step S1, the specific work content of the subsystem layer includes: S1-1. The sensors of the subsystem layer detect the status of the hardware of each subsystem, collect the data of the built-in test (BIT) sensors of each subsystem, and upload the sensor data and the status data such as available, running, and abnormal of each subsystem to the satellite service layer for storage; S1-2. The subsystem layer receives the initialization action commands (such as restart, reset, etc.) and status acquisition instructions from the upper level and executes them; S1-3. The subsystem layer enters the on-demand work control logic, and the on-demand work control logic includes regular reporting, on-demand acquisition, and abnormal alarm; the subsystem layer sets the basic health management strategy based on threshold values to ensure the robustness and reliability of health management. When the above monitoring parameters exceed or are lower than the set threshold values, monitoring is started, and when there is no abnormality, monitoring is carried out according to the set cycle; Further, in S2, the satellite service layer manages the satellite in the basic health management mode; including: S2-1. The satellite service layer receives the data from various sensors of the subsystem layer, preliminarily processes the data of each sensor, and realizes the perception, diagnosis and processing of faults related to satellite safety based on the diagnostic rules; when the satellite service layer detects common faults in the basic function hardware, it runs the programmed codes for each fault. S2-2. When the satellite service layer detects a fault threatening satellite safety, it controls the satellite to enter the satellite safety mode. The satellite service layer directly communicates with the ground system and implements system recovery and system reconstruction.

[0041] Technical effects: 1. The present invention aims at the hierarchical distributed autonomous health management architecture of the subsystem - satellite service - satellite level of an intelligent satellite. An intelligent autonomous health management system is deployed in the on - satellite real - time operating system. Based on high - performance computing power and intelligent algorithms, on - satellite fault intelligent diagnosis, intelligent prediction and intelligent reconstruction are realized. The health status of the satellite is managed in a hierarchical and graded manner. Different health management strategies, methods and hardware are adopted at the subsystem, satellite service and satellite levels, realizing the maximum utilization of satellite resources.

[0042] 2. The present invention realizes the on - satellite storage of all sensor data, subsystem operation log data, etc. during the satellite operation process, no longer relying on precious satellite link resources, greatly improving the health management efficiency and reducing the response time. And based on the intelligent algorithms deployed in the control core, big data mining and model training are carried out, making full use of the advantages of on - satellite data and computing power, and then more scientifically and accurately realizing the early prediction of satellite faults.

[0043] 3. The control core of the present invention adopts a health management control strategy based on a behavior tree, constructs an intelligent agent for satellite autonomous health management, realizes autonomous health management, and is convenient for code reuse and reuse, with the characteristics of modularity and high reactivity.

[0044] 4. Adopting a hierarchical distributed health management architecture, the health status of the satellite is managed in a hierarchical and graded manner. By means of the measure that the satellite level with large energy demand works intermittently, when the energy is sufficient, the satellite level adopts an autonomous intelligent health management mode, and when the energy is tense, the satellite service layer adopts a basic health management mode, realizing the maximum utilization of satellite resources while ensuring the basic operation functions of the satellite.

[0045] Any process or method described in the flowchart of the present invention or in other ways herein can be understood as representing a module, segment or part of code including one or more executable instructions for implementing a specific logical function or process, which can be implemented in any computer - readable medium for an instruction execution system, apparatus or device. The computer - readable medium can be any medium including storage, communication, propagation or transmission programs for use by an instruction execution system, apparatus or device, including read - only memory, magnetic disk or optical disc, etc.

[0046] In the description of this specification, the descriptions referring to terms such as "embodiment", "example", etc. mean that the specific features, structures, materials or characteristics described in connection with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. In addition, those skilled in the art can combine or combine the different embodiments or examples described in this specification and the features therein without contradiction.

[0047] Although the above has shown and described embodiments of the present invention, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can perform update operations such as changes, modifications, substitutions, and variations on the above embodiments within the scope of the present invention.

Claims

1. A hierarchical distributed satellite autonomous health management system, characterized in that: The system includes a subsystem layer, an on-board management layer, and a satellite-level layer; the on-board management layer is used to implement autonomous security protection and basic health management of the satellite, and the satellite-level layer is used to implement autonomous intelligent health management of the satellite and on-orbit computing and reconstruction tasks; where: The subsystem layer is used to self-check and monitor the status of each subsystem hardware, feedback the self-check and monitoring data to the on-board management layer, provide data input for health management, and receive and execute the action commands of the on-board management layer; The on-board management layer is used to perform autonomous security protection on the basic functions of the satellite's safe operation, and at the same time perform basic health management on each subsystem hardware; the basic functions of the satellite's safe operation include satellite orbit, attitude, and power supply; the on-board management layer uploads the received data information to the satellite-level layer and can also communicate with the ground system independently; The satellite-level layer is based on parallel computing hardware and a real-time operating system, and distributes and deploys an intelligent autonomous health management system, receives data information from the on-board management layer, and realizes autonomous intelligent health management of the satellite based on a behavior tree.

2. The hierarchical distributed satellite autonomous health management system according to claim 1, characterized in that, The subsystem hardware includes on-board management hardware, a control subsystem, a power subsystem, and a thermal management subsystem.

3. The hierarchical distributed satellite autonomous health management system according to claim 1, characterized in that In order to save resources, the subsystem layer does not continuously monitor all subsystem hardware, but adopts a work-on-demand mode.

4. The hierarchical distributed satellite autonomous health management system according to claim 1, characterized in that: The on-board management layer's basic health management adopts a continuous working mode.

5. The hierarchical distributed satellite autonomous health management system according to claim 1, characterized in that: The control core of the satellite-level layer consists of multiple parallel computing nodes, and a real-time operating system is distributed and deployed; thus, data processing and fault prediction that originally had to be transmitted to the ground through a link for processing during the satellite communication window are transferred to the autonomous health management system of the control core.

6. The hierarchical distributed satellite autonomous health management system according to claim 5, wherein The satellite-level layer communicates bidirectionally with the ground and the on-board management layer at the same time, and the satellite-level layer adopts an intermittent working mode in each satellite's orbit around the earth.

7. The hierarchical distributed satellite autonomous health management system according to claim 5, wherein Each subsystem hardware communicates with the subsystem control node through a bus, and the subsystem hardware is modularized upward to the control core. The intelligent autonomous health management application software APP calls and manipulates all subsystem hardware through an interface protocol.

8. The hierarchical distributed satellite autonomous health management system according to claim 7, wherein, The on-board management system of the on-board management layer is deployed on the subsystem control node, and all data and log files of the on-board management system are uploaded and stored in the health data storage unit of the control core.

9. The hierarchical distributed satellite autonomous health management system according to claim 7, wherein The control core and the subsystem control node both communicate with the satellite ground system for two-way backup.

10. A hierarchical distributed satellite autonomous health management method, characterized in that, The method is applied to the hierarchical distributed satellite autonomous health management system according to any one of claims 1-9, and is used to realize satellite autonomous health management.

Images