Satellite fault evolution analysis method and system based on knowledge graph reasoning

Abstract

This application provides a satellite fault evolution analysis method and system based on knowledge graph reasoning. First, it acquires multi-stage test information of the satellite, including ground-based development information, factory testing information, storage information, and launch site testing information. Then, it performs structured processing on the test information, extracting fault-related entities, entity attributes, and relationships between entities. Next, it constructs a satellite fault knowledge graph stored in triplet form based on the extracted information. This knowledge graph is then used for fault mode reasoning to identify possible fault modes of the satellite. Finally, by combining the relationships between fault-related entities in the satellite fault knowledge graph, it analyzes the fault evolution path and generates satellite fault evolution analysis results. This allows for a systematic and comprehensive analysis of the satellite fault evolution process, improving the reliability of satellite operation.

Description

Technical Field

[0001] This application relates to the field of satellite technology, and more specifically, to a satellite fault evolution analysis method and system based on knowledge graph reasoning. Background Technology

[0002] In the field of satellite technology, satellites, as complex and high-precision spacecraft, directly affect the success or failure of space missions through their operational status. Throughout their lifecycle, from development and launch to on-orbit operation, satellites undergo multiple stages, including the development phase, factory testing phase, storage phase, and launch site testing phase. Each stage generates a wealth of test information, covering various aspects of the satellite and crucial for understanding its performance and potential problems.

[0003] Currently, satellite fault analysis primarily relies on traditional fault diagnosis methods. These methods often focus on the direct detection and location of existing faults, lacking a systematic analysis of the satellite fault evolution process. Traditional methods are typically based on single fault data or simple fault mode matching, failing to comprehensively consider the rich test information generated by the satellite at various stages, as well as the fault-related entities, entity attributes, and interrelationships contained within this information. This results in the inability to accurately predict possible fault modes and evolution paths when facing complex and ever-changing satellite fault situations, hindering the implementation of effective preventative and countermeasure measures in advance, and posing significant risks to the safe operation of satellites and the successful completion of space missions. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a satellite fault evolution analysis method and system based on knowledge graph reasoning.

[0005] In conjunction with the first aspect of this application, a satellite fault evolution analysis method based on knowledge graph reasoning is provided, applied to a satellite fault evolution analysis system based on knowledge graph reasoning, the method comprising:

[0006] Obtain satellite test information on the ground, including satellite development information, factory test information, storage information, and launch site test information;

[0007] The test information is structured to extract fault-related entities, entity attributes, and relationships between entities.

[0008] Based on the extracted fault-related entities, entity attributes, and relationships between entities, a satellite fault knowledge graph is constructed. The satellite fault knowledge graph stores fault-related entities, entity attributes, and relationships between entities in the form of triples.

[0009] The satellite fault knowledge graph is used to perform fault mode reasoning to identify possible fault modes of the satellite.

[0010] Based on the identified fault modes, and combined with the relationships between fault-related entities in the satellite fault knowledge graph, the evolution path of the fault is analyzed, and satellite fault evolution analysis results are generated.

[0011] In conjunction with the second aspect of this application, a satellite fault evolution analysis system based on knowledge graph reasoning is provided. The satellite fault evolution analysis system based on knowledge graph reasoning includes a machine-readable storage medium and a processor. The machine-readable storage medium stores machine-executable instructions. When the processor executes the machine-executable instructions, the satellite fault evolution analysis system based on knowledge graph reasoning implements the aforementioned satellite fault evolution analysis method based on knowledge graph reasoning.

[0012] In conjunction with the third aspect of this application, a computer-readable storage medium is provided, wherein computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed, the aforementioned satellite fault evolution analysis method based on knowledge graph reasoning is implemented.

[0013] Combining any of the above aspects, by comprehensively acquiring multi-stage test information of the satellite on the ground, including development information, factory test information, stored information, and launch site test information, the test information is structured and processed to extract fault-related entities, entity attributes, and relationships between entities. A satellite fault knowledge graph is then constructed and stored in the form of triples. This achieves systematic integration and efficient management of satellite fault-related knowledge. Using this knowledge graph for fault mode reasoning can comprehensively consider multiple factors and accurately identify possible fault modes of the satellite, overcoming the limitations of traditional methods that rely solely on single data or simple pattern matching. Based on the identified fault modes, the evolution path of the fault is analyzed by combining the relationships between fault-related entities in the knowledge graph, generating satellite fault evolution analysis results. This helps to take preventive measures in advance, reduce the probability of satellite faults, improve the reliability and safety of satellite operation, and ensure the smooth progress of space missions. Attached Figure Description

[0014] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained in conjunction with these drawings without creative effort.

[0015] Figure 1A flowchart illustrating the satellite fault evolution analysis method based on knowledge graph reasoning provided in this application embodiment. Detailed Implementation

[0016] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or end that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or ends.

[0018] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0019] Figure 1 This document illustrates a flowchart of a satellite fault evolution analysis method based on knowledge graph reasoning provided in an embodiment of this application. It should be understood that in other embodiments, the order of some steps in the satellite fault evolution analysis method based on knowledge graph reasoning in this embodiment can be shared based on actual needs, or some steps can be omitted or maintained. The detailed components of this satellite fault evolution analysis method based on knowledge graph reasoning include:

[0020] Step S110: Obtain the satellite's test information on the ground, including satellite development information, factory test information, storage information, and launch site test information.

[0021] This embodiment focuses on the fault evolution analysis of a specific satellite model. In order to gain a deeper understanding of the potential faults that may exist in the satellite at each stage on the ground, it is necessary to comprehensively collect the test information generated at different stages.

[0022] Step S111: Obtain the development information generated during the satellite development phase, which includes the design parameters, material properties, and manufacturing process requirements of each satellite component.

[0023] During the satellite development phase, numerous stages generate detailed information related to various satellite components. This information forms the basis of satellite design and manufacturing and is crucial for subsequent fault analysis. Take the satellite's attitude control system as an example. This system primarily adjusts the satellite's attitude in space to ensure its normal operation. Its design parameters cover key indicators such as control accuracy and response speed, which determine whether the attitude control system can accurately and quickly complete attitude adjustment tasks. Regarding material properties, the sensors in the attitude control system may use special semiconductor materials to ensure stable operation in the complex space environment. Manufacturing process requirements involve sensor packaging processes, circuit board soldering processes, etc. The quality of these processes directly affects the performance and reliability of the attitude control system. By obtaining this development information, a deeper understanding of the characteristics of the attitude control system at the design and manufacturing levels can be achieved.

[0024] Step S112: Obtain the factory test information generated during the satellite's factory test phase. The factory test information includes test data obtained from functional tests, performance tests, and reliability tests of various satellite systems.

[0025] Before leaving the factory, satellites undergo comprehensive testing to ensure they meet design requirements and quality standards. For the attitude control system, functional testing primarily checks whether the system can accurately adjust the satellite's attitude according to predetermined commands. For example, in tests simulating the space environment, specific attitude adjustment commands are sent, and the attitude control system is observed to respond correctly and achieve the expected attitude. Performance testing focuses on various performance indicators of the attitude control system, such as control accuracy and response speed. Precise measuring equipment is used to obtain actual test data for these indicators, which are then compared with design parameters to evaluate whether the system's performance meets standards. Reliability testing simulates various extreme environments and stress conditions that the satellite may encounter during actual operation, such as high temperature, low temperature, and radiation, to verify the reliability and stability of the attitude control system under these conditions. The test data reflects the actual state of the attitude control system at the time of leaving the factory.

[0026] Step S113: Obtain storage information during the satellite storage phase, which includes storage environment conditions, storage time, and maintenance operation records during storage.

[0027] Before launch, satellites may require a period of storage, and factors such as storage environment and time can affect the performance of various satellite components. For the attitude control system, storage environment conditions include temperature, humidity, and air pressure. If the storage temperature is too high or too low, it may cause changes in sensor performance, affecting the accuracy of the attitude control system. Changes in humidity and air pressure may also cause corrosion or damage to electronic components in the system. The length of storage time is also an important factor; prolonged storage may cause certain materials to age, reducing the reliability of the attitude control system. In addition, maintenance operation records during storage can reflect whether necessary maintenance and inspections of the attitude control system were performed during storage, and whether any potential problems were identified and addressed. For example, maintenance personnel may periodically power on the attitude control system to ensure its proper functioning.

[0028] Step S114: Obtain launch site test information during the satellite launch site testing phase. The launch site test information includes the result data of the overall inspection test, subsystem test, and matching test conducted on the satellite before launch.

[0029] At the launch site, the satellite undergoes a series of final tests to ensure its safety and reliability during launch and operation. For the attitude control system, the overall inspection test is a comprehensive check of the system, including ensuring the hardware connections are secure and the software programs function correctly. Subsystem testing involves individual testing of each subsystem of the attitude control system, such as sensor testing and controller testing, to ensure that each subsystem functions properly. Compatibility testing primarily checks the compatibility and coordination between the attitude control system and other satellite systems. For example, the attitude control system needs to work in conjunction with the satellite's communication and power systems. If signal interference or power mismatch is found during compatibility testing, it may affect the overall performance of the satellite. The test results reflect the final state of the attitude control system before launch.

[0030] Step S115: Integrate the acquired development information, factory test information, storage information, and launch site test information to form a complete set of satellite ground test information.

[0031] After acquiring test information from different stages of the satellite's development, this information needs to be integrated. Since this information comes from different data sources, its format and structure may differ, necessitating appropriate integration methods. A unified data storage platform can be established to classify and store development information, factory test information, stored information, and launch site test information according to certain rules. For example, taking the attitude control system as an example, the system's development information, factory test information, stored information, and launch site test information can be stored in different database tables and linked by a unique system identifier. This forms a complete set of satellite ground test information, facilitating subsequent querying and analysis of fault-related information in the attitude control system.

[0032] Step S120: Perform structured processing on the test information to extract fault-related entities, entity attributes, and relationships between entities.

[0033] Since the acquired satellite ground test information is usually scattered and unstructured, which is not conducive to subsequent analysis and application, it needs to be structured. Specifically, it is necessary to extract the entities related to the fault, entity attributes, and the relationships between entities from this information.

[0034] Step S121: Based on the development information, identify satellite component entities, extract the design parameter attributes, material property attributes, and manufacturing process requirement attributes of the satellite component entities, and determine the association between the satellite component entities and the design parameter entities, material property entities, and manufacturing process requirement entities.

[0035] In the development information, it is necessary to accurately identify satellite component entities. The attitude control system is a crucial satellite component entity. Relevant attributes of this entity are extracted from the development information, including design parameter attributes such as control accuracy and response speed, which determine the basic performance of the attitude control system. Material property attributes include the semiconductor materials used in sensors and the insulating materials of circuit boards; the characteristics of these materials directly affect the stability and reliability of the system. Manufacturing process requirements encompass sensor packaging processes and circuit board soldering processes; the quality of these processes plays a critical role in the system's quality. Simultaneously, the relationships between the attitude control system and the design parameter entity, material property entity, and manufacturing process requirement entity are determined. There is a "possesses" relationship between the attitude control system and the design parameters, meaning the attitude control system possesses specific design parameters such as control accuracy and response speed. There is a "uses" relationship with the material property entity, indicating that the attitude control system uses specific materials. There is a "follows" relationship with the manufacturing process requirement entity, meaning that the manufacturing of the attitude control system must follow specific process requirements.

[0036] Step S122: Based on the factory test information, determine the test item entity, extract the test type attribute, test condition attribute, and test result attribute of the test item entity, and clarify the association between the test item entity and the satellite component entity.

[0037] In the factory test information, identify the test item entities. For the attitude control system, there may be test item entities such as attitude adjustment accuracy test and response speed test. For each test item entity, extract its relevant attributes. Test type attributes can be divided into functional tests, performance tests, etc., such as attitude adjustment accuracy test belonging to performance tests. Test condition attributes include ambient temperature, humidity, simulated space environment, etc., which will affect the accuracy of the test results. Test result attributes are the specific test data, such as the actual accuracy value of attitude adjustment, the measured value of response speed, etc. Clarify the relationship between the test item entities and the satellite component entities. The attitude adjustment accuracy test test item entity has a "targeted" relationship with the attitude control system satellite component entity, that is, this test item is performed specifically for the attitude control system.

[0038] Step S123: For the storage information, extract the storage environment entity, obtain the temperature attribute, humidity attribute, and air pressure attribute of the storage environment entity, and establish the association between the storage environment entity and the satellite component entity.

[0039] Extract the storage environment entity from the stored information. For the attitude control system, the storage environment is a crucial factor affecting its performance. Obtain the relevant attributes of the storage environment entity: temperature reflects the temperature of the storage environment, humidity reflects the water vapor content in the air, and air pressure represents the atmospheric pressure. Establish the association between the storage environment entity and the satellite component entity. There is an "affected by" relationship between the attitude control system and the storage environment, meaning that the performance of the attitude control system may be affected by factors such as temperature, humidity, and air pressure in the storage environment.

[0040] Step S124: For the launch site test information, identify the launch site test equipment entity, extract the equipment model attribute, calibration status attribute, and test function attribute of the launch site test equipment entity, and determine the association between the launch site test equipment entity and the test project entity.

[0041] In the launch site test information, the launch site test equipment entities are identified. For attitude control system testing, launch site test equipment entities such as attitude sensor testers and controller performance testers may be used. The relevant attributes of these equipment entities are extracted. The equipment model attribute clarifies the specific model and specifications of the equipment; the calibration status attribute reflects whether the equipment has been accurately calibrated to ensure the accuracy of the test results; and the test function attribute indicates the types of tests the equipment can perform, such as the attitude sensor tester measuring the accuracy of attitude sensors. The association between the launch site test equipment entities and the test item entities is determined. There is a "used for" association between the attitude sensor tester and the attitude adjustment accuracy test entity, meaning that this test equipment is used to perform attitude adjustment accuracy testing.

[0042] Step S125: Standardize all extracted fault-related entities, entity attributes, and relationships between entities, and unify data format and naming rules.

[0043] Since the extracted fault-related entities, entity attributes, and relationships between entities may originate from different data sources, their data formats and naming conventions may differ, necessitating standardization. For entities and attributes related to the attitude control system, the data format must first be standardized. For example, for temperature attributes, different data sources may use different temperature units; these need to be unified to the same unit. Regarding naming conventions, a unified standard should be established to avoid the same entity or attribute having different names. For example, for the control accuracy attribute of the attitude control system, different data sources may have different expressions; these need to be standardized to a single, consistent name. Standardization improves data consistency and usability.

[0044] Step S130: Based on the extracted fault-related entities, entity attributes, and relationships between entities, construct a satellite fault knowledge graph. The satellite fault knowledge graph stores fault-related entities, entity attributes, and relationships between entities in the form of triples.

[0045] After completing the structured processing of the test information, a satellite fault knowledge graph is constructed based on the extracted fault-related entities, entity attributes, and relationships between entities.

[0046] Step S131: Establish an entity type system and classify fault-related entities into different types such as satellite component entities, test project entities, storage environment entities, and launch site test equipment entities.

[0047] To better organize and manage fault-related entities, an entity type system is established. Extracted fault-related entities are categorized into different types. Satellite component entities, such as the attitude control system, are crucial components of the satellite and directly affect its operation. Test item entities, such as attitude adjustment accuracy testing, are used to evaluate the performance of satellite components. Storage environment entities encompass the environmental conditions during satellite storage, which have a potential impact on the performance of satellite components. Launch site test equipment entities, such as attitude sensor testers, are used to test satellite components at the launch site. This classification effectively demonstrates the roles and functions of different entities in satellite fault analysis.

[0048] Step S132: Define attribute types for each type of entity. For example, the attributes of a satellite component entity include design parameters, material properties, and manufacturing process requirements, while the attributes of a test project entity include test type, test conditions, and test results.

[0049] For different types of entities, corresponding attribute types are defined. For satellite component entity attitude control systems, attributes include design parameters such as control accuracy and response speed, which determine the system's basic performance. Material property attributes, such as the semiconductor materials used in sensors and the insulating materials of circuit boards, affect the system's stability and reliability. Manufacturing process requirements cover sensor packaging processes and circuit board soldering processes, playing a crucial role in system quality. For test item entity attitude adjustment accuracy testing, attributes include test type, such as performance test; test conditions, such as ambient temperature and humidity during testing; and test results, such as the actual accuracy value of attitude adjustment. By defining attribute types for each type of entity, the characteristics and state of the entity can be described more accurately.

[0050] Step S133: Define the relationship type based on the association between entities.

[0051] Based on the extracted relationships between entities, corresponding relationship types are defined. For the "has" relationship between the attitude control system and design parameters, it is clearly stated that the attitude control system possesses specific design parameters. For the "targeted" relationship between attitude adjustment accuracy testing and the attitude control system, it indicates that the test is specifically designed for the attitude control system. For the "affected by" relationship between the attitude control system and the storage environment, it reflects the potential impact of the storage environment on the performance of the attitude control system. By defining relationship types, the interactions and dependencies between entities can be effectively expressed.

[0052] Step S134: Using graph database technology, a satellite fault knowledge graph is constructed by using nodes to represent fault-related entities, edges to represent the relationships between entities, and node attributes to represent entity attributes.

[0053] A graph database technique is employed to construct a satellite fault knowledge graph. In the graph database, nodes represent fault-related entities, such as the attitude control system, attitude adjustment accuracy testing, and storage environment. Each node has corresponding attributes; for example, the attitude control system node has attributes such as design parameters, material properties, and manufacturing process requirements. Edges represent the relationships between entities; for example, the "targeted" relationship between attitude adjustment accuracy testing and the attitude control system is represented by an edge. Through this method, all fault-related entities, entity attributes, and relationships between entities are integrated into a single graph structure, forming the satellite fault knowledge graph. This satellite fault knowledge graph can intuitively display the complex relationships between satellite fault-related information.

[0054] Step S140: Use the satellite fault knowledge graph to perform fault mode reasoning and identify possible fault modes of the satellite.

[0055] After constructing a satellite fault knowledge graph, fault mode reasoning is performed using this knowledge graph to identify potential fault modes of the satellite. By analyzing the entities and relationships in the knowledge graph, potential fault hazards can be discovered.

[0056] Step S141: Determine the starting entity for fault mode reasoning, wherein the starting entity is a satellite component entity or test item entity that exhibits anomalies in the test information.

[0057] When performing fault mode reasoning, the first step is to identify the starting entity. The starting entity is a satellite component or test item that exhibits abnormalities in the test information. For example, if the attitude adjustment accuracy test results deviate significantly from the design parameters during factory testing, then the attitude adjustment accuracy test entity can be considered the starting entity. Similarly, if an abnormality is found in the output of a sensor in the attitude control system during launch site testing, then the attitude control system itself can be considered the starting entity. Identifying the starting entity is a crucial step in fault mode reasoning.

[0058] Step S142: Starting from the initial entity, traverse along the relationships in the satellite fault knowledge graph to collect all entities associated with the initial entity and their attribute information.

[0059] Starting from a defined initial entity, the process traverses the relationships within the satellite fault knowledge graph. If the initial entity is attitude adjustment accuracy testing, the attitude control system is located through the "target" relationships. Then, the process further collects information about these related entities and their attributes by tracing the relationships between the attitude control system and entities such as design parameters, material properties, and manufacturing process requirements. For example, the design parameters of the attitude control system are collected to check if indicators such as control accuracy and response speed meet requirements. Material property information is collected to check for quality issues with the semiconductor materials used in the sensors. Manufacturing process requirement information is collected to determine if the correct manufacturing process was followed. Through this traversal and information collection, a comprehensive understanding of all factors related to the initial entity can be achieved.

[0060] Step S143: Analyze the collected entity and attribute information to determine whether there are potential factors that could cause satellite malfunction.

[0061] A thorough analysis of the collected entity and attribute information is conducted to determine if any potential factors could lead to satellite malfunctions. For the attitude control system, significant discrepancies between design parameters and actual test results may indicate a problem with the design itself. If material property information shows unstable quality of the semiconductor materials used in the sensors, it could affect the accuracy of the attitude control system. Regarding manufacturing process requirements, failure to strictly adhere to process standards in any step could also cause system failures. By comprehensively analyzing this information, potential factors that could lead to satellite malfunctions can be identified.

[0062] Step S144: Based on the preset fault mode knowledge base, match the identified potential factors with known fault modes to determine the possible fault modes.

[0063] A pre-defined fault mode knowledge base contains various known satellite fault modes and their corresponding characteristics and causes. Identified potential factors are matched against known fault modes in the knowledge base. For example, if a decrease in the control accuracy of the attitude control system is detected, and material properties indicate aging of the sensor's semiconductor material, this matches the fault mode "sensor aging leading to decreased control accuracy" in the knowledge base, thus confirming the possible existence of this fault mode. Through this matching process, potential satellite fault modes can be quickly located.

[0064] Step S145: Evaluate the confidence level of the matched failure modes and determine the confidence level of the failure modes based on the tightness of the association and the degree of conformity of the attribute information.

[0065] The confidence level of the matched fault modes is assessed. The confidence level of a fault mode is determined based on the strength of the association and the degree of consistency of the attribute information. If the association between the starting entity and the fault mode is very strong, and the collected attribute information highly matches the characteristics of the fault mode, then the confidence level of that fault mode is high. For example, if the attitude adjustment accuracy test results are abnormal, and there is conclusive evidence of sensor material aging in the attitude control system, it highly matches the fault mode of "sensor aging leading to decreased control accuracy," then the confidence level of this fault mode can be assessed as high. Through confidence level assessment, the identified fault modes can be filtered and ranked, with higher-confidence fault modes being prioritized.

[0066] Step S150: Based on the identified fault modes and the relationships between fault-related entities in the satellite fault knowledge graph, analyze the evolution path of the fault and generate satellite fault evolution analysis results.

[0067] After identifying the possible failure modes of the satellite, the evolution path of the failure is analyzed by combining the relationships between failure-related entities in the satellite failure knowledge graph, so as to generate satellite failure evolution analysis results.

[0068] Step S151: For each identified failure mode, determine the initial failure entity associated with it and the subsequent entities that may be affected.

[0069] For each identified fault mode, the initial fault entity and potentially affected subsequent entities are determined. If the fault mode is "sensor aging leading to decreased control accuracy," the initial fault entity is the sensor in the attitude control system. Since a decrease in the accuracy of the attitude control system may affect the satellite's attitude adjustment, and consequently affect the normal operation of other systems such as the satellite's communication and energy systems, these affected systems are considered potentially affected subsequent entities. Identifying the initial fault entity and potentially affected subsequent entities helps to clarify the starting point and potential scope of fault propagation.

[0070] Step S152: Starting from the initial fault entity, search for the next layer entities that may be affected along the relationships in the satellite fault knowledge graph, and analyze the possibility and conditions of the fault being transmitted from the initial entity to the next layer entity.

[0071] Starting with the sensors in the attitude control system, the initial faulty entity, we search along the relationships in the satellite fault knowledge graph. These relationships reveal a connection between the attitude control system and the satellite's navigation system, as accurate attitude control is crucial for the navigation system to determine the satellite's position and orbit. Therefore, the navigation system is the next layer entity that may be affected. We analyze the possibility and conditions under which the fault propagates from the initial entity to the next layer entity. When sensor aging in the attitude control system leads to decreased control accuracy, if the satellite is in a mission phase requiring frequent attitude adjustments to maintain accurate navigation, inaccurate attitude control is very likely to be transmitted to the navigation system, leading to increased navigation errors. The conditions for this transmission may be related to factors such as the satellite's mission mode, the frequency and magnitude of attitude adjustments, etc. For example, when the satellite is performing orbital corrections or approaching other celestial bodies, the accuracy requirements for attitude control are higher, increasing the likelihood of fault propagation.

[0072] Step S153: For each potentially affected subsequent entity, further analyze whether it will trigger new failures or cause anomalies in other entities, forming a failure propagation chain.

[0073] For potentially affected navigation systems, further analysis is needed to determine if this will trigger new malfunctions or cause anomalies in other entities. When a navigation system experiences increased navigation errors due to inaccurate attitude control, it may affect the satellite's orbit control. Inaccurate orbit control can cause the satellite to deviate from its intended orbit, thereby impacting its power system. Since a satellite's power system typically relies on the accurate orientation of its solar panels towards the sun, orbital deviations will alter the intensity of sunlight received by the solar panels, potentially leading to insufficient power supply. Insufficient power supply can then affect the normal operation of other systems on the satellite; for example, the communication system may be unable to transmit or receive signals due to insufficient power. This creates a fault propagation chain: aging attitude control system sensors -> decreased attitude control accuracy -> increased navigation system error -> inaccurate orbit control -> insufficient power supply to the energy system -> communication system anomalies.

[0074] Step S154: Combine the interaction and influence between different failure modes to analyze the evolution path of the failure when multiple failure modes coexist.

[0075] In reality, multiple failure modes may coexist. Besides the failure mode of "sensor aging leading to decreased control accuracy," there may also be a failure mode of battery aging in the satellite's energy system causing unstable power supply. These two failure modes may interact and influence each other. A failure in the attitude control system may lead to satellite attitude instability, preventing the solar panels from fully receiving sunlight and further exacerbating the power supply problem in the energy system. Instability in the energy system's power supply may, in turn, affect the normal operation of electronic components in the attitude control system, accelerate sensor aging, and further reduce attitude control accuracy. Analyzing the evolution path of a failure when multiple failure modes coexist requires a comprehensive consideration of the correlations and interactions between each failure mode. Knowledge graphs reveal complex correlations between the attitude control system and the energy system. In-depth analysis of these correlations can reveal the evolution path of a failure when multiple failure modes coexist, such as: attitude control system failure -> exacerbation of energy system failure -> further deterioration of attitude control system failure -> more systems affected.

[0076] Step S155: Record all entities involved in the fault evolution process, the relationships between entities, and the conditions and order of fault propagation to form a complete fault evolution path description.

[0077] After analyzing the failure evolution path, it is necessary to record all entities involved in the failure evolution process, the relationships between entities, and the conditions and sequence of failure propagation. The entities involved in the failure evolution process include sensors in the attitude control system, the attitude control system, the navigation system, the orbit control system, the energy system, and the communication system. The relationships between entities include the relationship between the attitude control system and the navigation system, the relationship between the navigation system and the orbit control system, the relationship between the orbit control system and the energy system, and the relationship between the energy system and the communication system. The conditions for failure propagation include the satellite's mission mode, the frequency and magnitude of attitude adjustments, etc. The sequence of failure propagation starts with the aging of the attitude control system sensors, sequentially affecting the navigation system, the orbit control system, the energy system, and the communication system. This information should be recorded in detail to form a complete description of the failure evolution path, such as: "The attitude control system sensors malfunction due to aging. When the satellite is in a frequent attitude adjustment mission mode, this leads to a decrease in attitude control accuracy, which in turn affects the navigation system, increasing navigation errors. Increased navigation errors affect orbit control, causing orbit deviations, which in turn affect the energy supply of the energy system. Insufficient energy supply ultimately affects the communication system, leading to communication anomalies."

[0078] Step S156: Organize and visualize the fault evolution path obtained from the analysis, and present the entire process from the initial occurrence of the fault to the possible final consequences in a graphical way.

[0079] The complete fault evolution path description is organized, redundant information is removed, and key links and causal relationships are highlighted. Then, visualization tools are used to graphically present the entire process of the fault from its initial occurrence to its potential final consequences. Entities can be represented using nodes, such as using nodes of different colors to represent the attitude control system, navigation system, and energy system, respectively; directed edges are used to represent the relationships between entities and the direction of fault propagation, such as a directed edge from the attitude control system node to the navigation system node indicating that the fault propagates from the attitude control system to the navigation system. The conditions and causes of fault propagation can be labeled on the edges, such as "decreased attitude control accuracy leads to increased navigation error." Through this graphical display, the evolution process of the fault can be intuitively monitored, facilitating relevant personnel to quickly understand and analyze the development trend of the fault.

[0080] Step S157: Extract key nodes and key relationships in the fault evolution process to form a list of key factors in fault evolution.

[0081] Extract key nodes and key relationships from the compiled fault evolution path. Key nodes are entities that play a crucial role in the fault evolution process, such as sensors in the attitude control system, which are the starting point of the fault and have a significant impact on the entire fault evolution process; another example is the energy system, whose energy supply affects the normal operation of multiple other systems. Key relationships are connections that play a crucial role in the fault propagation process, such as the relationship between the attitude control system and the navigation system, which determines whether an attitude control fault will be transmitted to the navigation system. Compile these key nodes and key relationships into a list of key factors in fault evolution, such as "Key Nodes: Attitude Control System Sensors, Energy System; Key Relationships: Attitude Control System - Navigation System, Energy System - Communication System". This list of key factors can help quickly locate the critical links in the fault, providing a focus for subsequent fault prevention and response.

[0082] Step S158: Based on the fault evolution path and the list of key factors, assess the extent of the fault's impact on satellite performance and functionality.

[0083] Based on the fault evolution path and key factor list, the impact of the fault on satellite performance and functionality is assessed. The fault evolution path reveals that attitude control system faults can affect the navigation system, orbit control system, power system, and communication system, thus influencing the overall performance and functionality of the satellite in multiple ways. For example, increased navigation errors may prevent the satellite from accurately reaching its intended orbit, affecting its scientific exploration or communication missions; insufficient power supply may cause some equipment on the satellite to malfunction, reducing the satellite's efficiency and reliability. Combining the key factor list, the impact of critical nodes and key relationships on satellite performance and functionality is emphasized. For instance, aging faults in attitude control system sensors are a critical starting point, and their impact on subsequent systems directly relates to the degree of decline in overall satellite performance. Through comprehensive analysis, a more comprehensive and accurate assessment of the fault's impact on satellite performance and functionality can be achieved, categorized into different levels such as mild, moderate, or severe impact.

[0084] Step S159: Combine satellite design requirements data and usage scenario data to generate preventive measures and response strategies for the failure evolution process.

[0085] By combining satellite design requirements data and usage scenario data, preventative measures and response strategies are generated to address the failure evolution process. The satellite design requirements data specifies the performance indicators and operating conditions of each satellite system, while the usage scenario data describes the satellite's operation under different mission phases and environments. For attitude control system sensor aging failures, redundant sensor design can be added during the design phase, i.e., installing multiple sensors with the same function. When one sensor fails, the others can continue to operate, ensuring the accuracy of attitude control. Regarding usage scenarios, if the satellite is in an environment prone to sensor aging, such as a high-radiation orbital region, additional sensor protection measures can be implemented, such as using radiation-resistant shielding materials. For situations where failures have already occurred, response strategies can include timely adjustment of the satellite's mission mode, reducing tasks requiring high attitude control accuracy, and prioritizing the satellite's basic functions and safety. Simultaneously, backup systems, such as backup navigation or power systems, can be activated to maintain normal satellite operation.

[0086] Step S160: Integrate the fault evolution path, key factor list, impact assessment, preventive measures and response strategies to generate a complete satellite fault evolution analysis report.

[0087] This report integrates the fault evolution path, a list of key factors, impact assessment, preventative measures, and response strategies to generate a complete satellite fault evolution analysis report. The report begins with a brief introduction to the background of the satellite fault and the purpose of the analysis. It then details the fault evolution path, including the entire process from the initial fault entity to the potential consequences, presented graphically for easy understanding. Next, it lists the key factors in the fault evolution, clearly identifying critical nodes and key relationships. The report assesses the impact of the fault on satellite performance and functionality, providing specific assessment levels and justifications. Finally, the report details preventative measures and response strategies for the fault evolution process, including design-phase improvement suggestions, protective measures during operation, and emergency response methods after a fault occurs. This comprehensive satellite fault evolution analysis report helps improve satellite reliability and safety.

[0088] Before performing structured processing on the test information and extracting fault-related entities, entity attributes, and relationships between entities, the method further includes:

[0089] Step S210: Clean the acquired test information to obtain the cleaned test information.

[0090] Before structuring the acquired satellite ground-based test information, the data quality varies greatly due to the potential sources of this information, including duplicate records, erroneous data, and irrelevant data. Therefore, data cleaning is necessary to improve data quality.

[0091] Step S211: Check whether there are duplicate records in the test information, and perform deduplication processing on the duplicate records.

[0092] A comprehensive review of the acquired test information is conducted to determine if duplicate records exist. This can be done by comparing key information such as satellite component identification, test item names, and test times. For example, if the same satellite component undergoes the same test at the same time, and the test results are identical, these records are likely duplicates. For identified duplicate records, select one representative record to retain and delete the others. This avoids data redundancy and reduces subsequent processing workload.

[0093] Step S212: Verify whether the data in the test information conforms to the preset data format and value range, and correct or delete any erroneous data that does not meet the requirements.

[0094] The data in the test information is verified according to the preset data format and value range. The preset data format can include requirements such as data type (e.g., numerical, text), length, and precision; the value range specifies the reasonable range of values ​​for the data. For example, for temperature test data of satellite components, the preset data format is numerical, and the value range is the temperature range during normal satellite operation. If a temperature test data point is found to be non-numerical or exceeds the preset value range, then this data is considered erroneous. Erroneous data can be corrected or deleted depending on the specific circumstances. If it can be inferred and corrected using other relevant data, such as estimating and correcting based on temperature data of other similar satellite components within the same time period, then the erroneous data is corrected; if it cannot be corrected, the erroneous data is deleted to ensure data accuracy.

[0095] Step S213: Based on the goals and requirements of fault evolution analysis, filter out the valid data related to the fault and remove the data that is irrelevant to the fault.

[0096] Based on the goals and requirements of fault evolution analysis, the data in the test information is filtered. It is determined which data is relevant to satellite fault analysis and which is irrelevant. For example, in the satellite's development information, some details about the satellite's external design may be irrelevant to fault analysis, while the design parameters and material properties of various satellite components are closely related. Removing data irrelevant to the fault and retaining only the relevant and valid data reduces the amount of data, improves data processing efficiency, and highlights key information, facilitating subsequent analysis and data mining.

[0097] Step S214: Record the operations and processing results performed during the data cleaning process.

[0098] During the data cleaning process, detailed records are kept of the operations performed and the results. These records include the number of duplicate records removed, the number of erroneous data corrected or deleted, the number of valid data selected, and the number of irrelevant data removed. The time of each operation and the personnel involved are also recorded. These records provide a basis for subsequent data quality assessment and problem tracing, and also help ensure the traceability and standardization of the data processing process.

[0099] Step S220: Perform data standardization processing on the cleaned test information to obtain standardized test information.

[0100] After data cleaning is completed, since the test information may come from different data sources and there may be differences in data format, naming and semantics, it is necessary to perform data standardization processing on the cleaned test information to improve data consistency and usability.

[0101] Step S221: Establish a unified data dictionary, defining the names, data types, value ranges, and semantic interpretations of each field in the data.

[0102] Establish a unified data dictionary to standardize and define each field in the test information. Clearly define the name of each field to avoid using different names for the same field in different data sources; determine the data type, such as numeric, text, date, etc., to ensure data consistency; specify the value range to limit the reasonable range of data values ​​and avoid unreasonable data entry; and provide detailed explanations of the semantics of the fields to ensure consistent understanding of the data among different personnel. For example, for the "temperature" field of a satellite component, define its name in the data dictionary as "satellite component temperature," its data type as numeric, its value range as the temperature range during normal satellite operation, and its semantic explanation as "the temperature value of the satellite component at a specific moment, reflecting the thermal state of the component."

[0103] Step S222: For data of the same type from different sources, perform unified naming and format conversion according to the definition of the data dictionary.

[0104] For data of the same type from different sources, standardized naming and format conversion are performed according to the definitions in the established data dictionary. For example, the "power" of satellite components may be named differently in different data sources, such as "component power" or "equipment power," but it is uniformly named "satellite component power" according to the data dictionary definition. Regarding data format, different data sources may use different representations, such as date formats like "year / month / day" or "month-day-year," which are converted to the unified date format specified in the data dictionary. Through the above standardized naming and format conversion, differences in data names and formats can be eliminated, improving data consistency and comparability.

[0105] Step S223: For numerical data, unify the units and precision of the data; for text data, perform word segmentation, part-of-speech tagging and normalization to eliminate synonyms, near-synonyms and ambiguity, so that each data item in the standardized test information has a unique identifier and semantics.

[0106] For numerical data, the units and precision of the data are standardized. For example, for voltage test data of satellite components, different data sources may use different voltage units (such as volts, millivolts, etc.). These should be standardized to the same unit (such as volts), and the precision of the data should be specified according to actual needs, such as retaining two decimal places. For text data, word segmentation, part-of-speech tagging, and normalization are performed. Word segmentation divides text data into words according to certain rules; part-of-speech tagging assigns the part of speech to each word, such as noun, verb, adjective, etc.; normalization eliminates synonyms, near-synonyms, and ambiguity, unifying the representation of words with the same or similar semantics. For example, for text data describing the status of satellite components, expressions such as "normal operation" and "operating normally" are standardized to "normal operation." Through these processes, each data item in the standardized test information has a unique identifier and semantic meaning, facilitating subsequent data analysis and mining.

[0107] In the above embodiments, the satellite fault evolution analysis system based on knowledge graph reasoning for performing the above method embodiments has at least one processor, a control module (chipset) coupled to at least one of the processors, a memory coupled to the control module, a non-volatile memory (NVM) / storage device coupled to the control module, at least one load to / output device coupled to the control module, and a network interface coupled to the control module.

[0108] The processor may include at least one single-core or multi-core processor, and may include any combination of general-purpose processors or special-purpose processors (e.g., graphics processors, application processors, baseband processors, etc.). For some alternative implementations, a satellite fault evolution analysis system based on knowledge graph reasoning can serve as an electronic device such as the gateway described in the embodiments of this application.

[0109] In some alternative implementations, a satellite fault evolution analysis system based on knowledge graph reasoning may include at least one computer-readable medium (e.g., a memory or NVM / storage device) having instructions and at least one processor fused with the at least one computer-readable medium and configured to execute the instructions to implement the module thereby performing the actions described in this disclosure.

[0110] In one embodiment, the control module may include any suitable interface controller to provide any suitable interface to at least one of the processors and / or any suitable device or component communicating with the control module.

[0111] The control module may include a memory controller module to provide an interface to the memory. The memory controller module may be a hardware module, a software module, and / or a firmware module.

[0112] The memory can be used, for example, to load and store data and / or instructions for a satellite fault evolution analysis system based on knowledge graph reasoning. In one embodiment, the memory may include any suitable volatile memory, such as suitable DRAM.

[0113] In one embodiment, the control module may include at least one load-to-output controller to provide an interface to the NVM / storage device and (at least one) load-to-output device.

[0114] For example, an NVM / storage device can be used to store data and / or instructions. An NVM / storage device may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable (at least one) non-volatile storage device (e.g., at least one hard disk drive (HDD), at least one optical disc (CD) drive, and / or at least one digital universal optical disc (DVD) drive).

[0115] NVM / storage devices may include storage resources that are physically part of a device mounted on which a knowledge graph-based reasoning satellite fault evolution analysis system is installed, or that can be accessed by that device without needing to be part of that device. For example, NVM / storage devices may be accessed over a network via (at least one) load-to-output device.

[0116] At least one loading / output device may provide an interface for the knowledge graph-based reasoning satellite fault evolution analysis system to communicate with any other suitable device. The loading / output device may include communication components, pinyin components, sensor components, etc. A network interface may provide an interface for the knowledge graph-based reasoning satellite fault evolution analysis system to communicate via at least one network. The knowledge graph-based reasoning satellite fault evolution analysis system may wirelessly communicate with at least one component of a wireless network based on at least one wireless network prior and / or protocol, such as accessing a wireless network based on communication priors.

[0117] In one embodiment, at least one of the processors may be integrated with the logic of at least one controller of the control module (e.g., a memory controller module). In one embodiment, at least one of the processors may be integrated with the logic of at least one controller of the control module to form a system-level integration. In one embodiment, at least one of the processors may be fused with the logic of at least one controller of the control module on the same die. In one embodiment, at least one of the processors may be fused with the logic of at least one controller of the control module on the same die to form a system-on-a-chip (SoC).

[0118] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

[0119] This invention discloses a computer read storage medium that stores a computer program for electronic data interchange, wherein the computer program causes a computer to execute the steps in the satellite fault evolution analysis method based on knowledge graph reasoning described in the foregoing embodiments.

[0120] This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps in the satellite fault evolution analysis method based on knowledge graph reasoning described in the foregoing embodiments.

[0121] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any inventive effort.

[0122] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electronically erasable rewritable read-only memory (EEPROM), compact optical disc (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium that can be used to have or store data.

[0123] Finally, it should be noted that the above-disclosed embodiments are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A satellite fault evolution analysis method based on knowledge graph reasoning, characterized in that, The method includes: Obtain satellite test information on the ground, including satellite development information, factory test information, storage information, and launch site test information; The test information is structured to extract fault-related entities, entity attributes, and relationships between entities. Based on the extracted fault-related entities, entity attributes, and relationships between entities, a satellite fault knowledge graph is constructed. The satellite fault knowledge graph stores fault-related entities, entity attributes, and relationships between entities in the form of triples. The satellite fault knowledge graph is used to perform fault mode reasoning to identify possible fault modes of the satellite. Based on the identified fault modes, and combined with the relationships between fault-related entities in the satellite fault knowledge graph, the evolution path of the fault is analyzed, and satellite fault evolution analysis results are generated. The step of structuring the test information and extracting fault-related entities, entity attributes, and relationships between entities includes: Based on the aforementioned development information, satellite component entities are identified, and the design parameter attributes, material property attributes, and manufacturing process requirement attributes of the satellite component entities are extracted. The association between the satellite component entities and the design parameter entities, material property entities, and manufacturing process requirement entities is determined. Based on the factory test information, identify the test item entities, extract the test type attributes, test condition attributes, and test result attributes of the test item entities, and clarify the association between the test item entities and the satellite component entities; Based on the storage information, the storage environment entity is extracted, and its temperature, humidity, and air pressure attributes are obtained. The association between the storage environment entity and the satellite component entity is established. Based on the launch site test information, the launch site test equipment entity is identified, and the equipment model attribute, calibration status attribute, and test function attribute of the launch site test equipment entity are extracted to determine the association between the launch site test equipment entity and the test item entity. All extracted fault-related entities, entity attributes, and relationships between entities are standardized to unify data format and naming rules.

2. The satellite fault evolution analysis method based on knowledge graph reasoning according to claim 1, characterized in that, The acquisition of satellite test information on the ground includes: Acquire development information generated during the satellite development phase, including design parameters, material properties, and manufacturing process requirements for each satellite component; Obtain the factory test information generated during the satellite's factory test phase. The factory test information includes test data obtained from functional tests, performance tests, and reliability tests of various satellite systems. Acquire storage information during the satellite storage phase, including storage environment conditions, storage time, and maintenance operation records during storage; Acquire launch site test information during the satellite launch site testing phase. The launch site test information includes the results data of the overall inspection test, subsystem test, and matching test conducted on the satellite before launch. The acquired research and development information, factory test information, storage information, and launch site test information are integrated to form a complete set of satellite ground test information.

3. The satellite fault evolution analysis method based on knowledge graph reasoning according to claim 1, characterized in that, The satellite fault knowledge graph is constructed based on the extracted fault-related entities, entity attributes, and relationships between entities, including: Establish an entity type system to classify fault-related entities into different types, such as satellite component entities, test project entities, storage environment entities, and launch site test equipment entities; Define attribute types for each type of entity. For example, the attributes of a satellite component entity include design parameters, material properties, and manufacturing process requirements, while the attributes of a test project entity include test type, test conditions, and test results. Define the relationship type based on the associations between entities; Using graph database technology, a satellite fault knowledge graph is constructed by using nodes to represent fault-related entities, edges to represent the relationships between entities, and node attributes to represent entity attributes.

4. The satellite fault evolution analysis method based on knowledge graph reasoning according to claim 3, characterized in that, The step of using the satellite fault knowledge graph to perform fault mode reasoning and identify possible fault modes of the satellite includes: The starting entity for fault mode reasoning is determined, wherein the starting entity is a satellite component entity or a test item entity that exhibits anomalies in the test information; Starting from the initial entity, the system traverses along the relationships in the satellite fault knowledge graph to collect all entities and their attribute information associated with the initial entity. Analyze the collected entity and attribute information to determine whether there are any potential factors that could cause satellite malfunctions; Based on a pre-set fault mode knowledge base, the identified potential factors are matched with known fault modes to determine the possible fault modes. The confidence level of the matched failure modes is evaluated, and the confidence level of the failure modes is determined based on the tightness of the association and the degree of consistency of the attribute information.

5. The satellite fault evolution analysis method based on knowledge graph reasoning according to claim 4, characterized in that, The process of analyzing the evolution path of a fault based on the identified fault modes and the relationships between fault-related entities in the satellite fault knowledge graph includes: For each identified failure mode, determine the initial failure entity associated with it and the subsequent entities that may be affected; Starting from the initial fault entity, we search for the next layer entities that may be affected by the relationships in the satellite fault knowledge graph, and analyze the possibility and conditions of the fault being transmitted from the initial entity to the next layer entity. For each potentially affected subsequent entity, further analysis is conducted to determine whether it will trigger new failures or cause anomalies in other entities, thus forming a chain of failure propagation. By combining the interactions and influences between different failure modes, the evolution path of failure when multiple failure modes coexist is analyzed. Record all entities involved in the fault evolution process, the relationships between entities, and the conditions and order of fault propagation to form a complete fault evolution path description.

6. The satellite fault evolution analysis method based on knowledge graph reasoning according to claim 5, characterized in that, The generated satellite fault evolution analysis results include: The fault evolution paths obtained from the analysis are organized and visualized, presenting the entire process from the initial occurrence of the fault to the possible final consequences in a graphical way; Extract key nodes and key relationships in the fault evolution process to form a list of key factors in fault evolution; Based on the failure evolution path and list of key factors, assess the extent to which the failure affects satellite performance and functionality; By combining satellite design requirements data and usage scenario data, preventive measures and response strategies are generated to address the failure evolution process. The fault evolution path, key factor list, impact assessment, preventive measures, and response strategies are integrated to generate a complete satellite fault evolution analysis report.

7. The satellite fault evolution analysis method based on knowledge graph reasoning according to claim 1, characterized in that, Before performing structured processing on the test information and extracting fault-related entities, entity attributes, and relationships between entities, the method further includes: The acquired test information is cleaned to obtain the cleaned test information; The cleaned test information is subjected to data standardization processing to obtain the standardized test information. The standardized test information is classified into different categories according to its type and purpose.

8. The satellite fault evolution analysis method based on knowledge graph reasoning according to claim 7, characterized in that, The step of cleaning the acquired test information to obtain cleaned test information includes: Check if there are duplicate records in the test information, and remove duplicate records if necessary; Verify whether the data in the test information conforms to the preset data format and value range, and correct or delete any erroneous data that does not meet the requirements. Based on the goals and requirements of fault evolution analysis, select effective data related to the fault and remove data that is irrelevant to the fault. Record the operations and processing results performed during the data cleaning process; And, the step of standardizing the cleaned test information to obtain standardized test information includes: Establish a unified data dictionary to define the names, data types, value ranges, and semantic interpretations of each field in the data. For data of the same type from different sources, uniform naming and format conversion are performed according to the definition of the data dictionary; For numerical data, the units and precision of the data are standardized. For textual data, word segmentation, part-of-speech tagging, and normalization are performed to eliminate synonyms, near-synonyms, and ambiguity, so that each data item in the standardized test information has a unique identifier and semantics.

9. A satellite fault evolution analysis system based on knowledge graph reasoning, characterized in that, The method includes a processor and a computer-readable storage medium storing machine-executable instructions, which, when executed by a computer, implement the satellite fault evolution analysis method based on knowledge graph reasoning as described in any one of claims 1-8.

Images