CN116542651A - On-orbit autonomous health management system and method for payload of spacecraft - Google Patents
On-orbit autonomous health management system and method for payload of spacecraft Download PDFInfo
- Publication number
- CN116542651A CN116542651A CN202310550423.XA CN202310550423A CN116542651A CN 116542651 A CN116542651 A CN 116542651A CN 202310550423 A CN202310550423 A CN 202310550423A CN 116542651 A CN116542651 A CN 116542651A
- Authority
- CN
- China
- Prior art keywords
- fault
- data
- health
- payload
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000036541 health Effects 0.000 title claims abstract description 154
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000003745 diagnosis Methods 0.000 claims abstract description 138
- 238000012544 monitoring process Methods 0.000 claims abstract description 39
- 238000011282 treatment Methods 0.000 claims abstract description 16
- 238000012512 characterization method Methods 0.000 claims abstract description 12
- 238000007726 management method Methods 0.000 claims description 55
- 238000001514 detection method Methods 0.000 claims description 32
- 230000005856 abnormality Effects 0.000 claims description 23
- 230000015556 catabolic process Effects 0.000 claims description 23
- 238000006731 degradation reaction Methods 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 21
- 238000012423 maintenance Methods 0.000 claims description 20
- 230000008859 change Effects 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000005070 sampling Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 8
- 238000002474 experimental method Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 7
- 230000004927 fusion Effects 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 7
- 238000011084 recovery Methods 0.000 claims description 7
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000004519 manufacturing process Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 239000013589 supplement Substances 0.000 claims description 6
- 208000024891 symptom Diseases 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000003066 decision tree Methods 0.000 claims description 4
- 238000013461 design Methods 0.000 claims description 4
- 230000003862 health status Effects 0.000 claims description 4
- 238000005065 mining Methods 0.000 claims description 4
- 238000007476 Maximum Likelihood Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 238000013496 data integrity verification Methods 0.000 claims description 3
- 230000006837 decompression Effects 0.000 claims description 3
- 238000013136 deep learning model Methods 0.000 claims description 3
- 238000013210 evaluation model Methods 0.000 claims description 3
- 230000002068 genetic effect Effects 0.000 claims description 3
- 238000007499 fusion processing Methods 0.000 claims description 2
- 238000011269 treatment regimen Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 abstract description 8
- 230000007246 mechanism Effects 0.000 abstract description 3
- 230000008447 perception Effects 0.000 abstract description 3
- 230000008439 repair process Effects 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 5
- 238000012706 support-vector machine Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 description 1
- 241000208340 Araliaceae Species 0.000 description 1
- 101000606504 Drosophila melanogaster Tyrosine-protein kinase-like otk Proteins 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000002567 autonomic effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000003892 spreading Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Human Resources & Organizations (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Medical Informatics (AREA)
- Tourism & Hospitality (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Economics (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
Abstract
The on-orbit autonomous health management system and method for the payload of the spacecraft comprise a fault characterization unit; a state monitoring unit; a comprehensive fault diagnosis unit; a health state prediction unit; and a health management unit. According to the on-orbit autonomous health management system, the on-orbit autonomous health management system is deployed in the load management unit or the application information system, the health state data of each effective load of the spacecraft are mined, the functions of fault characterization, state monitoring, fault diagnosis, fault treatment, health state prediction, health management and the like are realized, the real-time health state of the effective load subsystem of the spacecraft is comprehensively monitored and managed, and the decision and guarantee capacity based on the rapid perception of the health state is improved; aiming at the characteristics of various functions, structures and working conditions of the payload subsystem and complex failure mode mechanism, the method is deployed on the premise of not influencing the main tasks of a load management unit or an application information system, ensures safe and reliable work of each payload in the whole life cycle of the track, and promotes the maximization of the overall efficiency of the payload task of the spacecraft.
Description
Technical Field
The invention relates to the field of spacecraft payloads, in particular to an on-orbit autonomous health management system and method for spacecraft payloads.
Background
The effective load refers to instruments, equipment, personnel, test organisms, test pieces and the like carried on the spacecraft, aims to complete specific tasks of on-orbit operation of the spacecraft, and is one of the most important subsystems for realizing on-orbit final aerospace mission of the spacecraft.
The effective load of the spacecraft runs on orbit for a long time, has extremely high requirements on the reliability and the safety of the system, and needs to be developed for on-orbit maintenance and system upgrading. Although a series of reliability related measures are adopted in the design and development process, various anomalies or faults still inevitably occur in the in-orbit flight due to complex tasks, variable working conditions and severe space environment, thereby reducing the stable service capability and even causing huge economic loss and disastrous results. And timely and effective health management can overcome the inherent reliability deficiency of effective load from the system level and ensure the safe and reliable operation of the effective load.
At present, the health management in the aerospace field at home and abroad generally adopts a strategy of taking the passive as the main part and taking the active as the auxiliary part, takes the ground operation and control as the main part, selects the machine to download the telemetry data and the working parameters, then analyzes the telemetry data and the working parameters by a ground system, and uses operation and control personnel to carry out data monitoring and cooperate with effective load designers to carry out fault interpretation, analysis and treatment. However, along with the development trend of complicated functional structure, diversified tasks and long-term on-orbit operation of the payload of the spacecraft, the conventional health management method based on the ground system has the problems of long processing time and high labor cost on one hand, is difficult to process a large amount of monitoring data in a short time, cannot quickly solve faults and recover the payload to a normal state, and may even generate misjudgment and misoperation. On the other hand, when the spacecraft is out of the range of the measurement and control arc section, the spacecraft is in an invisible state relative to the ground, so that on-orbit anomalies are difficult to identify and treat in time, and fault spreading can occur. The real-time and accuracy of the current payloads put higher demands on health management, especially failures affecting safety and critical functions, require on-orbit autonomous health management capabilities. The existing on-orbit autonomous health management of the payload of the spacecraft has the following defects:
1) The existing payload fault diagnosis technology is mainly based on the application of single detection and diagnosis methods such as threshold value or knowledge, and cannot comprehensively apply various methods such as expert system, machine learning and the like to improve the diagnosis accuracy and expand the application range.
2) The existing autonomous health management is mainly based on fault diagnosis and treatment, less considers the health prediction of effective load, and is difficult to meet the requirements of predictive maintenance and spare part planning under the condition of limited maintenance and guarantee resources.
Disclosure of Invention
With the continuous enhancement of the computing power of spaceborne computers of spacecrafts in recent years, the capability of on-orbit data processing and decision making is also greatly improved. By moving the health management system forward from the ground flight control to the space-based edge end, the real-time sensing and response capability of on-orbit autonomous health management can be improved, the problems of insufficient sensing force and control timeliness of the ground health management are overcome, and the weak dependence of a measurement and control link and strong autonomy of state evaluation are realized.
The invention aims to provide an on-orbit autonomous health management system and method for a spacecraft payload, so as to solve the problems of limited effect, incomplete health management function and the like of a single fault diagnosis method in the prior art.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
an on-orbit autonomous health management system for a spacecraft payload, comprising:
the fault characterization unit is used for characterizing the fault knowledge of the payload and forming a fault plan library;
the state monitoring unit is used for accessing real-time health state data of the effective load and monitoring the real-time health state data;
the comprehensive fault diagnosis unit is used for respectively carrying out fault diagnosis aiming at the effective load based on the deployed diagnosis algorithm model, identifying and positioning faults and determining fault reasons and obtaining fault diagnosis results of specific fault types;
a health status prediction unit for predicting the health degree or remaining life of a payload to make a mission plan in advance, the mission plan comprising: the space station machine utilizes the freight airship to replace expendables off track;
and the health management unit is used for carrying out fault classification, fault treatment, guarantee decision and maintenance record on the monitored effective load.
Preferably, the fault characterization unit comprises a fault knowledge representation module and a fault plan module, and is used for analyzing and determining parameter sets related to different payloads and health states thereof according to fault modes and influence analysis hierarchical relations, establishing potential mapping relations between faults and characterization parameters, collecting abnormal detection and fault diagnosis knowledge, and forming a fault plan library, wherein the fault plan library comprises numbers, names, phenomena, grades, influence, monitoring parameters, criteria and treatment programs of different fault modes.
Preferably, the state monitoring unit comprises a data access and processing module and an abnormality detection module; the data access and processing module is used for checking the functional performance of the spacecraft payload subsystem, receiving the health state data of the spacecraft payload subsystem in real time and carrying out data processing work; the data processing work comprises one or more of data frame decomposition, format decomposition, decryption, decompression, data conversion, formula calculation, bit splitting and data integrity verification; the health state data comprise industrial parameter data and telemetry data which characterize the working state of the effective load, and the industrial parameter data and the telemetry data respectively comprise digital quantity and analog quantity types; the industrial parameter data and the remote measurement data are divided into stable data, mutant data and gradual change data; the abnormality detection module is used for carrying out real-time interpretation and abnormality early warning on the stable data according to the access data of each effective load and the fault criteria in the fault plan library, and acquiring an abnormality detection result of whether the fault occurs, so as to find symptoms in advance, timely maintain a system and ensure continuous service.
Preferably, the comprehensive fault diagnosis unit comprises an expert system fault diagnosis module and a data driving integrated fault diagnosis module, and is used for receiving processed industrial parameter data and telemetry data and analyzing abnormal detection results; performing fault diagnosis based on the deployed diagnosis algorithm model, identifying and locating faults, determining fault reasons, and obtaining fault diagnosis results of specific fault types, wherein the fault diagnosis results are aimed at accurately locating faults, taking reasonable measures and assisting in reconstruction decisions;
the comprehensive fault diagnosis result is mainly based on expert system diagnosis results driven by knowledge, is oriented to faults of known criterion rules, and mainly aims at identifying fault characteristics of mutant data; the method is characterized in that the data-driven integrated fault diagnosis model result based on the fusion of various algorithms is used as supplement, faults facing to unknown criterion rules are mainly established by mining health state information contained in gradient data, and a mapping relation between monitoring parameters and fault symptoms is established.
Preferably, the health state prediction unit comprises a health evaluation module and a residual life prediction module; the health evaluation module is used for receiving the processed gradual change type parameter data and the telemetry data for analysis, utilizing the monitoring data to combine with a pre-established health evaluation model to evaluate the future change trend of the health degree, and utilizing the constructed health degree index to quantitatively evaluate the payload fault before the payload fault occurs; the residual life prediction module is also used for receiving the processed gradual change type parameter data and the remote measurement data for analysis, and predicting the residual life of the payload by utilizing the monitoring data and combining a pre-established life prediction model and a fault threshold value.
Preferably, the health management unit comprises a fault grading module, a fault handling module, a guarantee decision module and a maintenance recording module;
the fault grading module and the fault handling module are used for adopting grading treatment strategies for different fault types, carrying out fault grading according to the received comprehensive fault diagnosis results of each payload, executing the treatment programs of corresponding fault grades and fault modes in the fault plan library, and executing on-orbit fault handling and recovery operations;
the guarantee decision module is used for optimizing a corresponding effective load maintenance strategy or spare part strategy based on the output result of the health state prediction and combining with the task planning and resource capacity of the manned spacecraft and the freight spacecraft on the basis of fully balancing the safety and the cost;
the maintenance recording module is used for recording the effective load structure information, fault time, fault mode and fault level, corresponding diagnosis results and treatment measures, and prediction results and guarantee strategy measures;
the fault classification module divides the fault into four classes of I-class faults, II-class faults, III-class faults and IV-class faults according to the output result of the comprehensive fault diagnosis unit and the occurrence hierarchy and influence degree of the faults, wherein:
the first-level fault is an emergency fault affecting the safety of astronauts or aircrafts;
a level ii fault is an emergency fault affecting a key functional performance indicator of the payload;
class iii faults are non-urgent faults affecting key functional performance indicators of the payload;
a non-emergency fault that affects non-critical functional performance indicators of the payload;
the fault handling module determines and executes a corresponding handling program in a fault plan library, including:
autonomous protection measures are adopted for the processing and recovery of the I-level faults, and effective loads enter a safety mode to ensure the safety of astronauts and aircrafts preferentially;
the measures adopted for processing and recovering the II, III and IV level faults comprise resetting, switching backup and reconstruction, so that the safety and the task normality of a payload experiment and devices and samples thereof are ensured as much as possible.
An on-orbit autonomous health management method for a spacecraft payload, comprising the steps of:
s1, representing the fault knowledge of a payload and forming a fault plan library;
s2, accessing real-time state data of a payload, and monitoring the real-time state data;
s3, carrying out fault diagnosis aiming at the effective load based on the deployed diagnosis algorithm model, identifying and positioning faults and determining fault reasons, and obtaining fault diagnosis results of specific fault types;
s4, predicting the health state of the effective load so as to make a task plan in advance;
s5, performing fault classification, fault handling, guarantee decision-making and maintenance recording on the monitored effective load;
the specific process comprises the following steps:
pre-deploying an anomaly detection model, a comprehensive fault diagnosis model and a health state prediction model of different payloads; obtaining an abnormality detection model according to normalized abnormality detection knowledge, wherein the normalized abnormality detection comprises a threshold-based detection method, wherein faults are detected by defining upper and lower thresholds of parameters, and an abnormality alarm is sent once the upper and lower thresholds are exceeded;
the comprehensive fault diagnosis model is mainly formed by fusing an expert system fault diagnosis module and a data driving integrated fault diagnosis module, wherein the two fault diagnosis modules analyze and process the accessed monitoring data in sequence during diagnosis, and the diagnosis result of the expert system fault diagnosis module is taken as a main part and the diagnosis result of the data driving integrated fault diagnosis module is taken as a supplement; when the expert system fault diagnosis module identifies a fault, the fault is output as a final result of the comprehensive fault diagnosis unit; and when the expert system fault diagnosis module identifies that the fault is normal, executing the data driving integrated fault diagnosis module to output a diagnosis result as a final result output of the comprehensive fault diagnosis unit.
Preferably, the expert system fault diagnosis module adopts a fault diagnosis expert system based on a C language integrated production type system framework aiming at the faults of known criterion rules; the framework mainly comprises a fact library, a rule library, an event list to be negotiated and an inference engine;
the facts store stores facts required for fault diagnosis, and attributes can be represented nestably through the framework data structure; the rule base stores rules required by fault diagnosis, and a generating rule knowledge representation method in the framework can be adopted to realize rule base design; the event list to be negotiated stores the activated rules, and the inference engine uses the rules in the rule base and facts in the fact base to conduct inference through a Rete pattern matching algorithm;
editing expert knowledge in the form of an IF … and THEN … production rule to form a rule knowledge base; and converting the processed monitoring data into a fact format of the framework, comparing the fact format with a rule knowledge base, putting the corresponding rule into an execution list to wait for execution, and outputting a result by the inference engine.
Preferably, the payload monitoring data is closely related to its health and application task execution status; the data-driven fault diagnosis module collects health state data in different fault modes simulated by normal operation and real operation or simulators as tag data according to faults of unknown criterion rules, and trains the tag data through a machine learning or deep learning model to obtain the data-driven fault diagnosis model;
the method utilizes the concept of bagging integrated learning, combines different classifier models to reduce generalization errors and improve the accuracy of fault diagnosis, and mainly comprises the following steps:
3) Sampling N sampling sets containing m training samples in a self-help sampling method aiming at the preprocessed label data;
4) Training a base learner based on each sampling set pair decision tree, SVM, lightGBM, or XGBoost classifier;
3) And combining the classification results of the base learners by a majority voting method, namely voting each sample point by each base learner according to the self-training diagnosis result, and finally obtaining the classification result with the largest number of votes as the final diagnosis result of the sample point.
Preferably, the method further comprises a health state prediction model, wherein the health state prediction model analyzes and mines gradient type parameter data and telemetry data aiming at a degradation type fault mode, evaluates real-time health degree of each payload, and predicts degradation condition of health state and residual life;
the health assessment can adopt a multi-parameter fusion health index construction method, and the health degree index for measuring the health state is synthesized by optimizing and setting the weight coefficient of each key parameter in the data fusion process through Kalman filtering and/or genetic algorithm by optimizing key parameters related to the health state degradation, and then the health degree is quantitatively assessed in real time by adopting a regression or filtering method;
the residual life prediction adopts various degradation modeling methods according to degradation conditions of different health indexes, sets a fault threshold value by combining historical data and expert experience, and adopts a maximum likelihood estimation algorithm to estimate model parameters; the time when the health degree degradation curve changing along with time reaches a preset fault threshold value for the first time is the residual life.
The beneficial effects of the invention are as follows:
in the on-orbit autonomous health management system for the payloads of the spacecraft, provided by the invention, the health state data of each payload of the spacecraft is mined through the on-orbit autonomous health management system deployed in the load management unit or the application information system, so that the functions of fault characterization, state monitoring, fault diagnosis, fault treatment, health state prediction, health management and the like are realized, the real-time health state of the payload subsystem of the spacecraft is comprehensively monitored and managed, the requirements on real-time performance and accuracy of the health management of the payloads are met, and meanwhile, the decision and guarantee capability based on the rapid perception of the health state are improved; according to the invention, by designing the autonomous health management system, aiming at the characteristics of various functions, structures and working conditions of the payload subsystem and complex failure mode mechanism, different monitoring, diagnosing and predicting algorithms are deployed on the premise of not influencing the main tasks of the load management unit or the application information system, the dependence on ground transportation personnel and the space-earth link resources is overcome, the safe and reliable work of each payload in the whole life cycle of the orbit is ensured, the support maintenance guarantee decision is made, and the overall efficiency maximization of the payload task of the spacecraft is promoted.
Drawings
FIG. 1 is a schematic diagram of a spacecraft payload autonomous health management system provided by the present invention;
FIG. 2 is a schematic diagram of an autonomic health management process provided by the present invention;
FIG. 3 is a flow chart of integrated fault diagnosis data provided by the present invention;
fig. 4 is a data flow diagram for health status prediction provided by the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the detailed description is presented by way of example only and is not intended to limit the invention.
The payload equipment of the space station space application system comprises shared supporting equipment such as information management, power supply and distribution, heat control, nitrogen supply and the like, space science experiment and technology experiment cabinets, independent loads outside and inside the cabin and the like.
As shown in fig. 1, the on-orbit autonomous health management system for a spacecraft payload of the invention comprises:
the fault characterization unit comprises a fault knowledge representation module and a fault planning module, and is used for analyzing and determining parameter sets related to different payloads and health states thereof according to fault modes and influence analysis hierarchical relations, establishing potential mapping relations between faults and characterization parameters, collecting abnormal detection and fault diagnosis knowledge, and forming a fault planning library comprising numbers, names, phenomena, grades, influences, monitoring parameters, criteria, treatment programs and the like of different fault modes.
The state monitoring unit comprises a data access and processing module and an abnormality detection module. The data access and processing module is used for checking the functional performance of the spacecraft payload subsystem, receiving the health state data in real time, and carrying out data processing work such as data frame decomposition, format decomposition, decryption, decompression, data conversion, formula calculation, bit splitting, data integrity verification and the like.
The health status data includes parametric data and telemetry data characterizing the working status of the payload, including digital quantity, analog quantity types, respectively.
The ginseng and telemetry data are divided into stable data, abrupt data and gradual data.
The stable data basically keeps unchanged or changes in a certain range, such as the fluctuation of the analog voltage value of the load management unit is small, the abrupt data changes greatly along with time, such as the charging module of the power supply controller is interfered by single particles to cause the charging multiplying power and the charging current jump, and the gradual data gradually increases or decreases along with time, such as the refrigeration duration of the Stirling refrigerator is prolonged, the positioning speed residual error of the GNSS receiver is increased, and the like.
The abnormality detection module is used for carrying out real-time interpretation and abnormality early warning on stable data according to the access data of each payload and the fault criteria in the fault plan library, and acquiring an abnormality detection result of whether faults occur or not, and aims to discover symptoms in advance, timely maintain a system and ensure continuous service.
The comprehensive fault diagnosis unit comprises an expert system fault diagnosis module and a data driving integrated fault diagnosis module, and is used for receiving the processed industrial parameters and telemetry data and analyzing the abnormal detection result. The fault diagnosis is respectively carried out based on the deployed diagnosis algorithm model, the fault is identified and positioned, the fault cause is determined, the fault diagnosis result of the specific fault type is obtained, and the purposes of accurately positioning the fault, taking reasonable measures and assisting in reconstruction decisions are achieved.
In the embodiment, the comprehensive fault diagnosis result is mainly based on the expert system diagnosis result driven based on knowledge, and is oriented to faults of known criterion rules, and fault characteristics are mainly identified aiming at mutant data; the method is characterized in that the data-driven integrated fault diagnosis model results based on the fusion of various algorithms such as machine learning, deep learning and the like are used as supplements, faults oriented to unknown criterion rules are mainly established by mining health state information contained in gradual change data, and the mapping relation between monitoring parameters and fault symptoms is established.
The health state prediction unit comprises a health evaluation module and a residual life prediction module, and aims at predicting health state, making a plan in advance and selecting off-track replacement. The health evaluation module is used for receiving the processed gradual change type parameter and the telemetry data for analysis. And (3) evaluating future change trend of the health degree by utilizing the monitoring data in combination with a pre-established health evaluation model, and quantitatively evaluating the health degree by utilizing the constructed health degree index before the fault occurs. The residual life prediction module is also used for receiving the processed gradual change type parameter and the remote measurement data for analysis. And predicting the residual life of the payload by using the monitoring data in combination with a pre-established life prediction model and a fault threshold.
The health management unit comprises a fault grading module, a fault handling module, a guarantee decision module and a maintenance recording module.
The fault classification and fault handling module is to take a policy of classification handling for different fault types. And carrying out fault classification according to the received comprehensive fault diagnosis results (including faults identified by the abnormality detection module of the previous link) of each payload, executing a treatment program of corresponding fault level and fault mode in a fault plan library, and executing on-orbit fault processing and recovery operation.
The fault grading module is divided into four grades of I grade (catastrophic) fault, II grade (serious) fault, III grade (general) fault and IV grade (slight) fault according to the output result of the comprehensive fault diagnosis module and the fault occurrence level and influence degree, wherein:
the first-level fault is an emergency fault affecting the safety of astronauts or aircrafts;
a level ii fault is an emergency fault affecting a key functional performance indicator of the payload;
class iii faults are non-urgent faults affecting key functional performance indicators of the payload;
a non-emergency fault that affects non-critical functional performance indicators of the payload;
the fault handling module determines and executes a corresponding handler in the fault plan library, comprising:
the method comprises the steps of taking autonomous protection measures for the processing and recovery of the I-level faults, wherein a payload enters a safety mode, and the safety of astronauts and aircrafts is ensured preferentially;
measures such as reset, switching backup and reconstruction are adopted for the treatment and recovery of II, III and IV level faults, so that the safety and the normal tasks of effective load experiments and devices and samples thereof are ensured as much as possible;
the guarantee decision-making module is used for optimizing corresponding effective load maintenance strategies or spare part strategies based on the output result of the health state prediction and combining with the task planning and resource capacity of the manned airship and the freight airship on the basis of fully balancing the safety and the cost.
The repair maintenance strategies typically include, among other things, the environment in which the on-orbit repair is performed, the repair steps, repair operating tools, repair secondary hazards, maximum allowable repair time, etc. The spare part strategy generally comprises an on-orbit spare part storage list, spare part supply projects and quantity, emission ascending time and other guarantee support requirements, and a ground spare part storage form, so that the service life of a product is matched, the production of spare parts is planned, the matching check of the ground spare part and the on-orbit spare part planning is performed, the spare parts can be obtained within the allowable time of safe operation of the system, the maintenance is implemented, and the normal operation is restored.
The maintenance recording module is used for recording the effective load structure information, fault time, fault mode, fault level, corresponding diagnosis results and treatment measures, and prediction results and guarantee strategy measures.
An anomaly detection model, a comprehensive fault diagnosis model, a health prediction model, and a health management policy support on-orbit updating.
The invention discloses an on-orbit autonomous health management method for a spacecraft payload, which comprises the following steps:
an anomaly detection model, a comprehensive fault diagnosis model and a health state prediction model of different payloads deployed in advance;
and obtaining an abnormality detection model according to normalized abnormality detection knowledge, such as a threshold-based detection method, detecting faults by defining upper and lower threshold limits of parameters, and sending out an abnormality alarm once the upper and lower threshold limits of parameters exceed the range.
And (3) adopting an integrated fault diagnosis model fused by an expert system and a data driving algorithm, and analyzing and processing the accessed monitoring data by the two fault diagnosis modules in sequence during diagnosis, wherein the diagnosis result of the expert system is taken as the main part, and the diagnosis result based on the data driving integrated model is taken as the supplement. When the expert system fault diagnosis module identifies a fault, the fault is output as a final result of the comprehensive fault diagnosis unit; and when the expert system identifies that the fault is normal, executing the data driving integrated fault diagnosis module, and outputting a diagnosis result as a final result.
In this embodiment, the expert system fault diagnosis module may overcome the defect of low diagnosis efficiency existing in the current stage of spacecraft payload fault diagnosis that mainly relies on manual interpretation and fixed threshold, and for the fault of the known criterion rule, a fault diagnosis expert system based on a C language integrated generation system (clanage integrated ProductionSystem, CLIPS) framework may be adopted. The CLIPS consist of a fact library, a rule library, a practice table to be proposed, and an inference engine.
Facts stock the facts required for fault diagnosis may represent attributes nestably through a framework data structure. The CLIPS custom framework includes a frame name and a slot name, the frame containing a plurality of slots, each slot representing an attribute. If the voltage output of the 28V power panel of the scientific experiment cabinet controller of a certain space station is 27V with the lowest threshold value and the highest threshold value is 29V, the initial facts can be inserted into the expert system:
(initial-fact)
(device-normal (name "experiment cabinet controller 28V Power Panel Voltage output"); structural Unit (slotindex); sequence number index)
(slotlow-line 27); minimum threshold value
(slothigh-line 29)); maximum threshold value
Rules required for fault diagnosis are stored in the rule base, and the rule base design can be realized by adopting a generating rule knowledge representation method in the CLIPS framework.
The fault diagnosis rule of the payload can be generally extracted by a fault tree analysis method according to the typical fault mode and characteristic parameters of the payload. For example, in the power system fault tree, the power system fault is a top event, the output performance of the solar cell array is reduced to one of the middle events, and the power system fault tree further corresponds to the change of characteristic parameters such as charging time, bus voltage, output current, discharging depth, charging current and the like. Therefore, two diagnostic rules can be combed out (1) if "charge time unchanged" and "bus voltage unchanged" and "battery array output current reduced", then "power supply system solar array performance degradation failure", and (2) if "charge time extended" and "depth of discharge reduced" and "output current reduced" and "charge current reduced" then "power supply system solar array performance degradation failure".
The event table to be negotiated stores the rules that have been activated, and the inference engine uses rules in the rule base and facts in the fact base to infer through the Rete pattern matching algorithm.
Expert knowledge is compiled in the form of "IF …, THEN …" production rules to form a rule knowledge base. And converting the processed monitoring data into a fact format of CLIPS, comparing the fact format with a rule knowledge base, putting the corresponding rule into an execution list to wait for execution, and outputting a result by an inference engine.
In this embodiment, the payload monitoring data is closely related to its health and application task execution status. The data-driven fault diagnosis module collects health state data in different fault modes simulated by normal operation and real operation or simulators as tag data according to faults of unknown criterion rules, and trains through machine learning or deep learning models. In consideration of limited on-orbit computing resources, a lightweight classification model such as a decision tree, a Support Vector Machine (SVM), a LightGBM or XGBoost and the like can be adopted to obtain a data-driven fault diagnosis model. In addition, each classification model is adopted independently, so that certain limitation exists in practical application, and the concept of bagging integrated learning is utilized, and generalization errors are reduced by combining different classifier models, so that the accuracy of fault diagnosis is improved. Mainly comprises the following three steps:
(1) And sampling N sampling sets containing m training samples in a self-help sampling method aiming at the preprocessed label data.
(2) The base learner is trained for decision tree, SVM, lightGBM, XGBoost, etc. classifiers based on each sample set.
(3) And combining the classification results of the base learners by a majority voting method, namely voting each sample point by each base learner according to the self-training diagnosis result, and finally obtaining the classification result with the largest number of votes as the final diagnosis result of the sample point.
Most payloads, except for abrupt electronic failure modes, undergo a gradual degradation of functional performance until the use requirements, such as pump sets, filters, batteries, etc., are not met. Accordingly, some of the critical monitoring parameters associated with the health state also undergo a process of continuing degradation from normal to abnormal states. The health state prediction model is used for analyzing and mining gradient type parameter data and telemetry data aiming at a degradation type fault mode, evaluating real-time health degree of each payload and predicting health state degradation condition and residual life.
In this embodiment, the health assessment may adopt a multi-parameter fusion health index construction method, and the weight coefficient of each key parameter during data fusion is optimally set by optimizing key parameters related to health state degradation through methods such as kalman filtering and genetic algorithm, so as to synthesize a health index for measuring health state, and then a regression or filtering method is adopted to quantitatively assess health in real time.
In this embodiment, the residual life prediction should select degradation modeling methods such as degradation track modeling, random process modeling, etc. according to degradation conditions of different health indexes, set a fault threshold by combining historical data and expert experience, and select different estimation algorithms such as maximum likelihood estimation, extended kalman filtering, etc. to estimate model parameters. The time when the health degree degradation curve changing along with time reaches a preset fault threshold value for the first time is the residual life.
It is noted that, the uncertainty of time domain fluctuation, degradation rate change, random fault threshold and the like may be caused by quality fluctuation and random influence caused by environmental and working condition change, and finally the accuracy of the health state prediction may be directly affected.
By adopting the technical scheme disclosed by the invention, the following beneficial effects are obtained:
in the on-orbit autonomous health management system for the payloads of the spacecraft, provided by the invention, the health state data of each payload of the spacecraft is mined through the on-orbit autonomous health management system deployed in the load management unit or the application information system, so that the functions of fault characterization, state monitoring, fault diagnosis, fault treatment, health state prediction, health management and the like are realized, the real-time health state of the payload subsystem of the spacecraft is comprehensively monitored and managed, the requirements on real-time performance and accuracy of the health management of the payloads are met, and meanwhile, the decision and guarantee capability based on the rapid perception of the health state are improved; according to the invention, by designing the autonomous health management system, aiming at the characteristics of various functions, structures and working conditions of the payload subsystem and complex failure mode mechanism, different monitoring, diagnosing and predicting algorithms are deployed on the premise of not influencing the main tasks of the load management unit or the application information system, the dependence on ground transportation personnel and the space-earth link resources is overcome, the safe and reliable work of each payload in the whole life cycle of the orbit is ensured, the support maintenance guarantee decision is made, and the overall efficiency maximization of the payload task of the spacecraft is promoted. The load management unit or the application information system is a neural center for operation control management and information processing of the effective load subsystem, provides unified on-orbit scheduling and collaborative management for loads with various types, complex control and massive information, and supports on-orbit high-bandwidth data transmission, acquisition, storage and processing.
The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which is also intended to be covered by the present invention.
Claims (10)
1. An on-orbit autonomous health management system for a spacecraft payload, comprising:
the fault characterization unit is used for characterizing the fault knowledge of the payload and forming a fault plan library;
the state monitoring unit is used for accessing real-time health state data of the effective load and monitoring the real-time health state data;
the comprehensive fault diagnosis unit is used for respectively carrying out fault diagnosis aiming at the effective load based on the deployed diagnosis algorithm model, identifying and positioning faults and determining fault reasons and obtaining fault diagnosis results of specific fault types;
a health status prediction unit for predicting the health degree or remaining life of a payload to make a mission plan in advance, the mission plan comprising: the space station machine utilizes the freight airship to replace expendables off track;
and the health management unit is used for carrying out fault classification, fault treatment, guarantee decision and maintenance record on the monitored effective load.
2. The on-orbit autonomous health management system for a spacecraft payload according to claim 1, wherein the fault characterization unit comprises a fault knowledge representation module and a fault plan module, and is configured to analyze and determine parameter sets related to different payloads and their health states according to a fault mode and an influence analysis hierarchical relationship, establish a potential mapping relationship between faults and characterization parameters, collect anomaly detection and fault diagnosis knowledge, and form a fault plan library, where the fault plan library contains numbers, names, phenomena, grades, influence, monitoring parameters, criteria, and treatment procedures of different fault modes.
3. The spacecraft payload on-orbit autonomous health management system of claim 1, wherein the state monitoring unit comprises a data access and processing module and an anomaly detection module; the data access and processing module is used for checking the functional performance of the spacecraft payload subsystem, receiving the health state data of the spacecraft payload subsystem in real time and carrying out data processing work; the data processing work comprises one or more of data frame decomposition, format decomposition, decryption, decompression, data conversion, formula calculation, bit splitting and data integrity verification; the health state data comprise industrial parameter data and telemetry data which characterize the working state of the effective load, and the industrial parameter data and the telemetry data respectively comprise digital quantity and analog quantity types; the industrial parameter data and the remote measurement data are divided into stable data, mutant data and gradual change data; the abnormality detection module is used for carrying out real-time interpretation and abnormality early warning on the stable data according to the access data of each effective load and the fault criteria in the fault plan library, and acquiring an abnormality detection result of whether the fault occurs, so as to find symptoms in advance, timely maintain a system and ensure continuous service.
4. The on-orbit autonomous health management system for a spacecraft payload according to claim 1, wherein the comprehensive fault diagnosis unit comprises an expert system fault diagnosis module and a data driven integrated fault diagnosis module for receiving processed industrial parameter data and telemetry data and analyzing anomaly detection results; performing fault diagnosis based on the deployed diagnosis algorithm model, identifying and locating faults, determining fault reasons, and obtaining fault diagnosis results of specific fault types, wherein the fault diagnosis results are aimed at accurately locating faults, taking reasonable measures and assisting in reconstruction decisions;
the comprehensive fault diagnosis result is mainly based on expert system diagnosis results driven by knowledge, is oriented to faults of known criterion rules, and mainly aims at identifying fault characteristics of mutant data; the method is characterized in that the data-driven integrated fault diagnosis model result based on the fusion of various algorithms is used as supplement, faults facing to unknown criterion rules are mainly established by mining health state information contained in gradient data, and a mapping relation between monitoring parameters and fault symptoms is established.
5. The spacecraft payload on-orbit autonomous health management system of claim 1, wherein the health prediction unit comprises a health assessment module and a remaining life prediction module; the health evaluation module is used for receiving the processed gradual change type parameter data and the telemetry data for analysis, utilizing the monitoring data to combine with a pre-established health evaluation model to evaluate the future change trend of the health degree, and utilizing the constructed health degree index to quantitatively evaluate the payload fault before the payload fault occurs; the residual life prediction module is also used for receiving the processed gradual change type parameter data and the remote measurement data for analysis, and predicting the residual life of the payload by utilizing the monitoring data and combining a pre-established life prediction model and a fault threshold value.
6. The spacecraft payload on-orbit autonomous health management system of claim 1, wherein the health management unit comprises a fault classification module, a fault handling module, a warranty decision module, and a maintenance record module;
the fault grading module and the fault handling module are used for adopting grading treatment strategies for different fault types, carrying out fault grading according to the received comprehensive fault diagnosis results of each payload, executing the treatment programs of corresponding fault grades and fault modes in the fault plan library, and executing on-orbit fault handling and recovery operations;
the guarantee decision module is used for optimizing a corresponding effective load maintenance strategy or spare part strategy based on the output result of the health state prediction and combining with the task planning and resource capacity of the manned spacecraft and the freight spacecraft on the basis of fully balancing the safety and the cost;
the maintenance recording module is used for recording the effective load structure information, fault time, fault mode and fault level, corresponding diagnosis results and treatment measures, and prediction results and guarantee strategy measures;
the fault classification module divides the fault into four classes of I-class faults, II-class faults, III-class faults and IV-class faults according to the output result of the comprehensive fault diagnosis unit and the occurrence hierarchy and influence degree of the faults, wherein:
the first-level fault is an emergency fault affecting the safety of astronauts or aircrafts;
a level ii fault is an emergency fault affecting a key functional performance indicator of the payload;
class iii faults are non-urgent faults affecting key functional performance indicators of the payload;
a non-emergency fault that affects non-critical functional performance indicators of the payload;
the fault handling module determines and executes a corresponding handling program in a fault plan library, including:
autonomous protection measures are adopted for the processing and recovery of the I-level faults, and effective loads enter a safety mode to ensure the safety of astronauts and aircrafts preferentially;
the measures adopted for processing and recovering the II, III and IV level faults comprise resetting, switching backup and reconstruction, so that the safety and the task normality of a payload experiment and devices and samples thereof are ensured as much as possible.
7. An on-orbit autonomous health management method for a spacecraft payload, comprising the steps of:
s1, representing the fault knowledge of a payload and forming a fault plan library;
s2, accessing real-time state data of a payload, and monitoring the real-time state data;
s3, carrying out fault diagnosis aiming at the effective load based on the deployed diagnosis algorithm model, identifying and positioning faults and determining fault reasons, and obtaining fault diagnosis results of specific fault types;
s4, predicting the health state of the effective load so as to make a task plan in advance;
s5, performing fault classification, fault handling, guarantee decision-making and maintenance recording on the monitored effective load;
the specific process comprises the following steps:
pre-deploying an anomaly detection model, a comprehensive fault diagnosis model and a health state prediction model of different payloads; obtaining an abnormality detection model according to normalized abnormality detection knowledge, wherein the normalized abnormality detection comprises a threshold-based detection method, wherein faults are detected by defining upper and lower thresholds of parameters, and an abnormality alarm is sent once the upper and lower thresholds are exceeded;
the comprehensive fault diagnosis model is mainly formed by fusing an expert system fault diagnosis module and a data driving integrated fault diagnosis module, wherein the two fault diagnosis modules analyze and process the accessed monitoring data in sequence during diagnosis, and the diagnosis result of the expert system fault diagnosis module is taken as a main part and the diagnosis result of the data driving integrated fault diagnosis module is taken as a supplement; when the expert system fault diagnosis module identifies a fault, the fault is output as a final result of the comprehensive fault diagnosis unit; and when the expert system fault diagnosis module identifies that the fault is normal, executing the data driving integrated fault diagnosis module to output a diagnosis result as a final result output of the comprehensive fault diagnosis unit.
8. The method for on-orbit autonomous health management of a spacecraft payload according to claim 7, wherein the expert system fault diagnosis module employs a C-language integrated production type system framework based fault diagnosis expert system for faults of known criteria rules; the framework mainly comprises a fact library, a rule library, an event list to be negotiated and an inference engine;
the facts store stores facts required for fault diagnosis, and attributes can be represented nestably through the framework data structure; the rule base stores rules required by fault diagnosis, and a generating rule knowledge representation method in the framework can be adopted to realize rule base design; the event list to be negotiated stores the activated rules, and the inference engine uses the rules in the rule base and facts in the fact base to conduct inference through a Rete pattern matching algorithm;
editing expert knowledge in the form of an IF … and THEN … production rule to form a rule knowledge base; and converting the processed monitoring data into a fact format of the framework, comparing the fact format with a rule knowledge base, putting the corresponding rule into an execution list to wait for execution, and outputting a result by the inference engine.
9. The method of on-orbit autonomous health management of a spacecraft payload according to claim 7, wherein the payload monitoring data is closely related to its health and application task execution status; the data-driven fault diagnosis module collects health state data in different fault modes simulated by normal operation and real operation or simulators as tag data according to faults of unknown criterion rules, and trains the tag data through a machine learning or deep learning model to obtain the data-driven fault diagnosis model;
the method utilizes the concept of bagging integrated learning, combines different classifier models to reduce generalization errors and improve the accuracy of fault diagnosis, and mainly comprises the following steps:
1) Sampling N sampling sets containing m training samples in a self-help sampling method aiming at the preprocessed label data;
2) Training a base learner based on each sampling set pair decision tree, SVM, lightGBM, or XGBoost classifier;
3) And combining the classification results of the base learners by a majority voting method, namely voting each sample point by each base learner according to the self-training diagnosis result, and finally obtaining the classification result with the largest number of votes as the final diagnosis result of the sample point.
10. The method of on-orbit autonomous health management of spacecraft payloads according to claim 7, further comprising a health state prediction model that analyzes mined graded type parameter data and telemetry data for a degenerate failure mode, evaluates real-time health of each payload, predicts health state degradation and remaining life;
the health assessment can adopt a multi-parameter fusion health index construction method, and the health degree index for measuring the health state is synthesized by optimizing and setting the weight coefficient of each key parameter in the data fusion process through Kalman filtering and/or genetic algorithm by optimizing key parameters related to the health state degradation, and then the health degree is quantitatively assessed in real time by adopting a regression or filtering method;
the residual life prediction adopts various degradation modeling methods according to degradation conditions of different health indexes, sets a fault threshold value by combining historical data and expert experience, and adopts a maximum likelihood estimation algorithm to estimate model parameters; the time when the health degree degradation curve changing along with time reaches a preset fault threshold value for the first time is the residual life.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310550423.XA CN116542651A (en) | 2023-05-16 | 2023-05-16 | On-orbit autonomous health management system and method for payload of spacecraft |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310550423.XA CN116542651A (en) | 2023-05-16 | 2023-05-16 | On-orbit autonomous health management system and method for payload of spacecraft |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116542651A true CN116542651A (en) | 2023-08-04 |
Family
ID=87457484
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310550423.XA Pending CN116542651A (en) | 2023-05-16 | 2023-05-16 | On-orbit autonomous health management system and method for payload of spacecraft |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116542651A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117131785A (en) * | 2023-10-23 | 2023-11-28 | 北京航空航天大学杭州创新研究院 | Health management system and method for electric aeroengine |
| CN117454232A (en) * | 2023-12-22 | 2024-01-26 | 山东未来集团有限公司 | Production network construction fault diagnosis, prediction and health management system and method |
| CN117828517A (en) * | 2024-03-06 | 2024-04-05 | 北京开运联合信息技术集团股份有限公司 | Spacecraft on-orbit running state evaluation method based on data mining |
| CN117894476A (en) * | 2024-03-12 | 2024-04-16 | 西南医科大学附属医院 | Reproductive health management system based on cloud data |
-
2023
- 2023-05-16 CN CN202310550423.XA patent/CN116542651A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117131785A (en) * | 2023-10-23 | 2023-11-28 | 北京航空航天大学杭州创新研究院 | Health management system and method for electric aeroengine |
| CN117131785B (en) * | 2023-10-23 | 2024-01-05 | 北京航空航天大学杭州创新研究院 | Health management system and method for electric aeroengine |
| CN117454232A (en) * | 2023-12-22 | 2024-01-26 | 山东未来集团有限公司 | Production network construction fault diagnosis, prediction and health management system and method |
| CN117828517A (en) * | 2024-03-06 | 2024-04-05 | 北京开运联合信息技术集团股份有限公司 | Spacecraft on-orbit running state evaluation method based on data mining |
| CN117894476A (en) * | 2024-03-12 | 2024-04-16 | 西南医科大学附属医院 | Reproductive health management system based on cloud data |
| CN117894476B (en) * | 2024-03-12 | 2024-05-14 | 西南医科大学附属医院 | Reproductive health management system based on cloud data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116542651A (en) | On-orbit autonomous health management system and method for payload of spacecraft | |
| Ibrahim et al. | Machine learning techniques for satellite fault diagnosis | |
| CN109885907B (en) | Cloud model-based satellite attitude control system health state assessment and prediction method | |
| Iverson et al. | General purpose data-driven monitoring for space operations | |
| CN111874268B (en) | Satellite centralized type autonomous health management system | |
| CN112836833A (en) | Health state evaluation method for aerospace measurement and control data transmission integrated equipment | |
| CN111581782A (en) | Satellite health level assessment method based on health state laminar flow logic model | |
| CN111553059B (en) | Satellite health degree assessment method with task health and risk health coupled | |
| CN111894946B (en) | Equipment hydraulic system fault prediction method based on combat intensity and environment | |
| CN116451016A (en) | Diagnostic evaluation method for satellite intelligent fault system | |
| Barlas et al. | Self-evolution in knowledge bases | |
| CN116136926A (en) | Underwater robot health management system based on Bayesian network | |
| Knight et al. | Intelligent management of helicopter health and usage management systems data | |
| Gao | Research on architecture design of UAV PHM system | |
| Yi et al. | A survey on prognostic and health management for special vehicles | |
| Xiong et al. | Research on health condition assessment method for spacecraft power control system based on SVM and cloud model | |
| Alandihallaj et al. | MBSE-Enhanced LSTM Framework for Satellite System Reliability and Failure Prediction. | |
| Cheng et al. | Research on Spacecraft Fault Diagnosis and Recovery Architecture | |
| Salvador et al. | Using big data and machine learning to improve aircraft reliability and safety | |
| Pirani et al. | A pattern recognition approach for enhancing lifecycle maintainability of battery systems | |
| Chen et al. | Architecture analysis for avionics prognostics and health management system | |
| CN113554177B (en) | Satellite power supply system autonomous fault diagnosis method based on soft decision | |
| Jain et al. | Prediction of telemetry data using machine learning techniques | |
| Gao et al. | Study on the Influence of PHM Technology on Aircraft Maintenance Support Mode | |
| Simon et al. | Enhancing the diagnostic performance of condition based maintenance through the fusion of sensor with maintenance data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |