CN117828517A - Spacecraft on-orbit running state evaluation method based on data mining - Google Patents
Spacecraft on-orbit running state evaluation method based on data mining Download PDFInfo
- Publication number
- CN117828517A CN117828517A CN202410253714.7A CN202410253714A CN117828517A CN 117828517 A CN117828517 A CN 117828517A CN 202410253714 A CN202410253714 A CN 202410253714A CN 117828517 A CN117828517 A CN 117828517A
- Authority
- CN
- China
- Prior art keywords
- data
- time
- real
- spacecraft
- features
- 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
- 238000007418 data mining Methods 0.000 title claims abstract description 30
- 238000011156 evaluation Methods 0.000 title claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 59
- 238000004364 calculation method Methods 0.000 claims abstract description 7
- 238000000034 method Methods 0.000 claims description 35
- 230000002159 abnormal effect Effects 0.000 claims description 25
- 238000000605 extraction Methods 0.000 claims description 18
- 238000007405 data analysis Methods 0.000 claims description 11
- 238000010183 spectrum analysis Methods 0.000 claims description 11
- 238000013136 deep learning model Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 9
- 238000013499 data model Methods 0.000 claims description 8
- 238000005311 autocorrelation function Methods 0.000 claims description 6
- 230000003595 spectral effect Effects 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 125000004122 cyclic group Chemical group 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 4
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 230000005856 abnormality Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000003111 delayed effect Effects 0.000 description 2
- 238000005111 flow chemistry technique Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an on-orbit running state evaluation method of a spacecraft based on data mining, which relates to the technical field of aerospace, and aims to realize real-time data acquisition and analysis by arranging an edge calculation node in the spacecraft, transmitting a real-time data stream form and extracting real-time characteristics, monitoring and analyzing the state of the spacecraft, dividing time series data into short time windows on the edge calculation node, carrying out discrete Fourier transform to convert the time series data into frequency domain signals, detecting anomalies in the frequency domain, simultaneously calculating statistical characteristics and time sequence characteristics to carry out data state comprehensive evaluation, and carrying out real-time data acquisition and analysis by using the edge calculation node and real-time data stream processing.
Description
Technical Field
The invention relates to the technical field of aerospace, in particular to a spacecraft on-orbit running state evaluation method based on data mining.
Background
With the play of more and more important roles of the spacecraft in a plurality of fields such as deep space exploration, national defense application, navigation communication and the like, the requirements of people on the autonomous running of the spacecraft on orbit are also higher and higher.
Autonomous navigation is one of core technologies for realizing autonomous operation of a spacecraft, and is a precondition for realizing autonomous orbit/attitude control, deep space exploration, on-orbit service and other space tasks of the spacecraft. The state estimation is a core means for realizing autonomous navigation of the spacecraft, and the process of acquiring the position, the speed and the gesture of the spacecraft in real time by utilizing self-carrying equipment to acquire measurement data and combining a dynamics/kinematics model of the spacecraft to analyze and process the observation data with errors and performing recursive calculation.
However, the conventional on-orbit operation state evaluation method generally depends on offline data analysis, lacks real-time performance, cannot monitor the state of the spacecraft in real time or near real time, and needs a long time to discover and identify when an abnormality or problem occurs, so that a delayed response is caused, and it is difficult to take timely action in an emergency, so that there is a need for a data mining-based on-orbit operation state evaluation method for performing state identification in real time to solve such problems.
Disclosure of Invention
(one) solving the technical problems
Aiming at the defects of the prior art, the invention provides a spacecraft on-orbit running state evaluation method based on data mining, which solves the problems that in the prior art, when an abnormality or a problem occurs in offline data analysis, a long time is required for finding and identifying, and a response is delayed.
(II) technical scheme
In order to achieve the above object, the present invention provides a method for evaluating the on-orbit operation state of a spacecraft based on data mining, comprising the following steps:
step 1, edge node feature extraction, namely collecting data collected by a sensor on a spacecraft and communication data of a satellite as basic data, transmitting the basic data in a real-time data stream form, and arranging edge computing nodes in the spacecraft, wherein the edge computing nodes are used for feature extraction of the data;
step 2, real-time processing of the data stream, namely carrying out real-time data stream processing on the edge computing node by adopting a stream processing engine based on the real-time data characteristics extracted by the edge node, and distinguishing abnormal data;
step 3, feature transmission, namely deploying a central processing unit, performing real-time feature selection again by the deployed edge computing nodes in the step 1, generating new features, and transmitting the relevant features to the central processing unit, wherein the central processing unit in the step 3 is deployed at a ground station and used for data mining and model evaluation;
step 4, continuously updating the model in real time, wherein the central processing unit is based on the deep learning model, and the model is trained according to historical data and continuously updated;
and 5. Outputting the decision, wherein the central processing unit executes real-time decision support and provides targeted suggestions, including state adjustment and task re-planning.
The invention is further arranged to: in the step 1, the edge node feature extraction method includes:
collecting data collected by a sensor on a spacecraft, including temperature, pressure, speed, position and communication link data;
transmitting the collected data in the form of a real-time data stream;
disposing edge computing nodes in the spacecraft, wherein the disposing positions of the computing nodes are close to the data sources;
performing data preprocessing on the edge computing nodes, and performing real-time feature extraction on the edge computing nodes based on the acquired data, wherein the real-time feature extraction comprises spectrum analysis, statistical features and time sequence features;
the invention is further arranged to: in the step 1, the deployed edge node adopts a real-time data stream processing engine, and the step of executing abnormal data detection includes:
dividing the time series data into short time windows, each window containing N data points;
performing discrete fourier transform, DFT, conversion to a frequency domain signal for each time window:
，
wherein the method comprises the steps ofRepresents a frequency domain signal, x (N) is a time domain signal, f is a frequency, N represents the number of data points in a window,for negative exponential terms, j represents an imaginary unit;
calculating spectral features, i.e. principal frequenciesAnd spectral energy E:
，
；
the invention is further arranged to: in the step 1, the statistical features include:
the mean value and variance of the data window are calculated, and the method specifically comprises the following steps:
，
，
wherein the method comprises the steps ofMean value->As variance, N represents the number of data points in the window, and x (N) is the nth data point in the window;
the invention is further arranged to: in the step 1, the time sequence features include:
calculating an autocorrelation function for analyzing periodicity within the time series data:
，
wherein,for representing the periodicity of the data, N represents the number of data points in the window, x (N) is the nth data point in the window, k represents the time interval, here +.>Indicating a lag of the time series data;
the invention is further arranged to: in the step 2, the real-time data stream processing step includes:
setting a data stream receiver on the edge computing node, wherein the data stream receiver is used for receiving the real-time characteristic data extracted in the step 1;
dividing the received data into time windows, each window containing a number of data points;
performing data stream processing operations on the edge computing nodes using a stream processing engine ApacheSparkStreaming:
a. performing real-time spectral analysis using a stream processing engine to detect anomalies in the frequency domain features;
b. calculating the mean, variance, skewness and kurtosis to detect anomalies in the statistical features;
c. calculating an autocorrelation function to detect anomalies in the time sequence;
marking abnormal data points detected in the data stream based on the results of the stream processing engine;
separating the abnormal data from the normal data, and generating a real-time alarm according to the detected abnormal data;
the invention is further arranged to: in the step 3, the step of transmitting the real-time features extracted from the edge computing nodes to the central processing unit for data mining and model evaluation includes:
calculating real-time features by using the spectrum analysis, the statistical features and the time sequence features in the step 1 on the edge calculation nodes;
combining, converting or generating new features based on the real-time features selected on the edge compute nodes;
transmitting the selected real-time features and the generated new features to a central processing unit;
the invention is further arranged to: in the step 4, the real-time continuous updating method comprises the following steps:
training an initial model by using historical data by adopting a cyclic neural network (RNN);
adopting an online learning method to continuously receive real-time characteristic data of edge computing nodes
Analyzing the real-time characteristic data by using the updated model, and identifying abnormal data points;
comparing the difference between the actual data and the model prediction to determine whether an abnormal condition exists;
adopting an incremental learning method to adapt to new conditions and modes;
the invention is further arranged to: in the step 5, the real-time decision support method for the running state of the spacecraft is as follows:
the updated deep learning model is used for analyzing the real-time characteristic data;
decision rules and policies are formulated to make decisions based on the results of the data analysis,
and according to the data analysis and the decision rule, the central processing unit generates a decision suggestion in real time and outputs the decision suggestion to related personnel.
(III) beneficial effects
The invention provides a spacecraft on-orbit running state evaluation method based on data mining. The beneficial effects are as follows:
according to the spacecraft on-orbit running state evaluation method based on data mining, on the basis of sensor data and satellite communication data on a spacecraft, edge computing nodes are deployed in the spacecraft to conduct transmission in a real-time data stream form and real-time feature extraction, and the features comprise spectrum analysis, statistical features and time sequence features and are used for monitoring and analyzing the state of the spacecraft.
On the edge computing node, a real-time data stream processing engine is adopted to divide time series data into short time windows, discrete Fourier transform is carried out to convert the time series data into frequency domain signals, anomalies are detected in the frequency domain, meanwhile, statistical characteristics and time sequence characteristics are calculated to carry out data state comprehensive evaluation, real-time data acquisition and analysis are realized by using the edge computing node and the real-time data stream processing, the state of a spacecraft can be monitored timely, a reaction can be carried out quickly, once abnormal data points are detected, the abnormal data points can be recorded by the stream processing engine and separated from normal data, and an alarm is generated to inform related personnel or a system under the real-time condition.
The real-time features extracted in step 3 are transmitted to a central processing unit, deployed at a ground station, for data mining and model evaluation.
And 4, training according to historical data by adopting a deep learning model, adapting to the continuously changing situation, and carrying out data analysis and anomaly detection under the real-time situation, thereby improving the adaptability to the new situation.
And finally, providing real-time decision support for the running state of the spacecraft, and generating decision suggestions by the central processing unit based on the deep learning model and the decision rules.
The method solves the problems that in the prior art, when abnormality or problem occurs in offline data analysis, long time is required for finding and identifying, and response delay is caused.
Drawings
FIG. 1 is a flow chart of a method for evaluating the on-orbit running state of a spacecraft based on data mining;
fig. 2 is a flowchart of edge node feature extraction in the data mining-based spacecraft on-orbit running state evaluation method of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Examples
Referring to fig. 1-2, the invention provides a spacecraft on-orbit running state evaluation method based on data mining, which comprises the following steps:
s1, edge node feature extraction, namely collecting data collected by a sensor on a spacecraft and communication data of a satellite as basic data, transmitting the basic data in a real-time data stream form, and deploying edge computing nodes in the spacecraft, wherein the edge computing nodes are used for feature extraction of the data;
in step 1, the edge node feature extraction method includes:
collecting data collected by a sensor on a spacecraft, including temperature, pressure, speed, position and communication link data;
transmitting the collected data in the form of a real-time data stream;
disposing edge computing nodes in the spacecraft, wherein the disposing positions of the computing nodes are close to the data sources;
performing data preprocessing on the edge computing nodes, and performing real-time feature extraction on the edge computing nodes based on the acquired data, wherein the real-time feature extraction comprises spectrum analysis, statistical features and time sequence features;
in step 1, the deployed edge node adopts a real-time data stream processing engine, and the step of executing abnormal data detection comprises the following steps:
dividing the time series data into short time windows, each window containing N data points;
performing discrete fourier transform, DFT, conversion to a frequency domain signal for each time window:
，
wherein the method comprises the steps ofRepresents a frequency domain signal, x (N) is a time domain signal, f is a frequency, N represents the number of data points in a window,for negative exponential terms, j represents an imaginary unit;
calculating spectral features, i.e. principal frequenciesAnd spectral energy E:
，
；
in step 1, the statistical features include:
the mean value and variance of the data window are calculated, and the method specifically comprises the following steps:
，
，
wherein the method comprises the steps ofMean value->As variance, N represents the number of data points in the window, and x (N) is the nth data point in the window;
in step 1, the timing characteristics include:
calculating an autocorrelation function for analyzing periodicity within the time series data:
，
wherein,for representing the periodicity of the data, N represents the number of data points in the window, x (N) is the nth data point in the window, k represents the time interval, here +.>Indicating a lag of the time series data;
s2, carrying out real-time data flow processing on the edge computing nodes by adopting a flow processing engine based on the real-time data characteristics extracted by the edge nodes, and distinguishing abnormal data;
in step 2, the real-time data stream processing step includes:
setting a data stream receiver on the edge computing node, wherein the data stream receiver is used for receiving the real-time characteristic data extracted in the step 1;
dividing the received data into time windows, each window containing a number of data points;
performing data stream processing operations on the edge computing nodes using a stream processing engine ApacheSparkStreaming:
a. performing real-time spectral analysis using a stream processing engine to detect anomalies in the frequency domain features;
b. calculating the mean, variance, skewness and kurtosis to detect anomalies in the statistical features;
c. calculating an autocorrelation function to detect anomalies in the time sequence;
marking abnormal data points detected in the data stream based on the results of the stream processing engine;
separating the abnormal data from the normal data, and generating a real-time alarm according to the detected abnormal data;
s3, feature transmission and deployment of a central processing unit, wherein the edge computing nodes deployed in the step 1 perform real-time feature selection again and generate new features, the related features are transmitted to the central processing unit, and the central processing unit in the step 3 is deployed at a ground station and used for data mining and model evaluation;
in step 3, the step of transmitting the real-time features extracted from the edge computing nodes to the central processing unit for data mining and model evaluation includes:
calculating real-time features by using the spectrum analysis, the statistical features and the time sequence features in the step 1 on the edge calculation nodes;
combining, converting or generating new features based on the real-time features selected on the edge compute nodes;
transmitting the selected real-time features and the generated new features to a central processing unit;
s4, continuously updating the model in real time, wherein the central processing unit is based on the deep learning model, and the model is trained according to historical data and continuously updated;
in step 4, the real-time continuous updating method comprises the following steps:
training an initial model by using historical data by adopting a cyclic neural network (RNN);
adopting an online learning method to continuously receive real-time characteristic data of edge computing nodes
Analyzing the real-time characteristic data by using the updated model, and identifying abnormal data points;
comparing the difference between the actual data and the model prediction to determine whether an abnormal condition exists;
adopting an incremental learning method to adapt to new conditions and modes;
s5, outputting the decisions, and executing real-time decision support by the central processing unit to provide targeted suggestions, wherein the suggestions comprise state adjustment and task re-planning;
in step 5, the real-time decision support method for the running state of the spacecraft comprises the following steps:
the updated deep learning model is used for analyzing the real-time characteristic data;
decision rules and policies are formulated to make decisions based on the results of the data analysis.
And according to the data analysis and the decision rule, the central processing unit generates a decision suggestion in real time and outputs the decision suggestion to related personnel.
In combination with the above, in the present application:
according to the spacecraft on-orbit running state evaluation method based on data mining, on the basis of sensor data and satellite communication data on a spacecraft, edge computing nodes are deployed in the spacecraft to conduct transmission in a real-time data stream form and real-time feature extraction, and the features comprise spectrum analysis, statistical features and time sequence features and are used for monitoring and analyzing the state of the spacecraft.
On the edge computing node, a real-time data stream processing engine is adopted to divide time series data into short time windows, discrete Fourier transform is carried out to convert the time series data into frequency domain signals, anomalies are detected in the frequency domain, meanwhile, statistical characteristics and time sequence characteristics are calculated to carry out data state comprehensive evaluation, real-time data acquisition and analysis are realized by using the edge computing node and the real-time data stream processing, the state of a spacecraft can be monitored timely, a reaction can be carried out quickly, once abnormal data points are detected, the abnormal data points can be recorded by the stream processing engine and separated from normal data, and an alarm is generated to inform related personnel or a system under the real-time condition.
The real-time features extracted in step 3 are transmitted to a central processing unit, deployed at a ground station, for data mining and model evaluation.
And 4, training according to historical data by adopting a deep learning model, adapting to the continuously changing situation, and carrying out data analysis and anomaly detection under the real-time situation, thereby improving the adaptability to the new situation.
And finally, providing real-time decision support for the running state of the spacecraft, and generating decision suggestions by the central processing unit based on the deep learning model and the decision rules.
It is to be understood that the above examples of the present invention are provided by way of illustration only and not by way of limitation of the embodiments of the present invention. Other variations or modifications of the above teachings will be apparent to those of ordinary skill in the art. It is not necessary here nor is it exhaustive of all embodiments. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the invention are desired to be protected by the following claims.
Claims (9)
1. The method for evaluating the on-orbit running state of the spacecraft based on data mining is characterized by comprising the following steps of:
step 1, edge node feature extraction, namely collecting data collected by a sensor on a spacecraft and communication data of a satellite as basic data, transmitting the basic data in a real-time data stream form, and arranging edge computing nodes in the spacecraft, wherein the edge computing nodes are used for feature extraction of the data;
step 2, real-time processing of the data stream, namely carrying out real-time data stream processing on the edge computing node by adopting a stream processing engine based on the real-time data characteristics extracted by the edge node, and distinguishing abnormal data;
step 3, feature transmission, namely deploying a central processing unit, performing real-time feature selection again by the deployed edge computing nodes in the step 1, generating new features, and transmitting the relevant features to the central processing unit, wherein the central processing unit in the step 3 is deployed at a ground station and used for data mining and model evaluation;
step 4, continuously updating the model in real time, wherein the central processing unit is based on the deep learning model, and the model is trained according to historical data and continuously updated;
and 5. Outputting the decision, wherein the central processing unit executes real-time decision support and provides targeted suggestions, including state adjustment and task re-planning.
2. The method for evaluating the on-orbit running state of a spacecraft based on data mining according to claim 1, wherein in the step 1, the edge node feature extraction method comprises:
collecting data collected by a sensor on a spacecraft, including temperature, pressure, speed, position and communication link data;
transmitting the collected data in the form of a real-time data stream;
disposing edge computing nodes in the spacecraft, wherein the disposing positions of the computing nodes are close to the data sources;
and carrying out data preprocessing on the edge computing nodes, and carrying out real-time feature extraction on the edge computing nodes based on the acquired data, wherein the real-time feature extraction comprises spectrum analysis, statistical features and time sequence features.
3. The method for evaluating the on-orbit running state of a spacecraft based on data mining according to claim 1, wherein in the step 1, the deployed edge node adopts a real-time data stream processing engine, and the performing the abnormal data detection step includes:
dividing the time series data into short time windows, each window containing N data points;
performing discrete fourier transform, DFT, conversion to a frequency domain signal for each time window:
，
wherein the method comprises the steps ofRepresents the frequency domain signal, x (N) is the time domain signal, f is the frequency, N represents the number of data points in the window, < >>For negative exponential terms, j represents an imaginary unit;
calculating spectral features, i.e. principal frequenciesAnd spectral energyQuantity E:
，
。
4. the method for evaluating the on-orbit running state of a spacecraft based on data mining according to claim 1, wherein in the step 1, the statistical features include:
the mean value and variance of the data window are calculated, and the method specifically comprises the following steps:
，
，
wherein the method comprises the steps ofMean value->For variance, N represents the number of data points within the window, and x (N) is the nth data point within the window.
5. The method for evaluating the on-orbit operation state of a spacecraft based on data mining according to claim 1, wherein in the step 1, the timing characteristics include:
calculating an autocorrelation function for analyzing periodicity within the time series data:
，
wherein,for representing the periodicity of the data, N represents the number of data points in the window, x (N) is the nth data point in the window, k represents the time interval, here +.>Indicating the lag of the time series data.
6. The method for evaluating the on-orbit running state of a spacecraft based on data mining according to claim 1, wherein in the step 2, the real-time data stream processing step comprises:
setting a data stream receiver on the edge computing node, wherein the data stream receiver is used for receiving the real-time characteristic data extracted in the step 1;
dividing the received data into time windows, each window containing a number of data points;
performing data stream processing operations on the edge computing nodes using a stream processing engine ApacheSparkStreaming:
a. performing real-time spectral analysis using a stream processing engine to detect anomalies in the frequency domain features;
b. calculating the mean, variance, skewness and kurtosis to detect anomalies in the statistical features;
c. calculating an autocorrelation function to detect anomalies in the time sequence;
marking abnormal data points detected in the data stream based on the results of the stream processing engine;
the abnormal data is separated from the normal data, and a real-time alarm is generated according to the detected abnormal data.
7. The method for estimating the on-orbit running state of a spacecraft based on data mining according to claim 1, wherein in the step 3, the step of transmitting the real-time features extracted in the edge computing nodes to the central processing unit for data mining and model estimation includes:
calculating real-time features by using the spectrum analysis, the statistical features and the time sequence features in the step 1 on the edge calculation nodes;
combining, converting or generating new features based on the real-time features selected on the edge compute nodes;
the selected real-time features and the generated new features are transmitted to a central processing unit.
8. The method for evaluating the on-orbit running state of a spacecraft based on data mining according to claim 1, wherein in the step 4, the real-time continuous updating method is as follows:
training an initial model by using historical data by adopting a cyclic neural network (RNN);
adopting an online learning method to continuously receive real-time characteristic data of edge computing nodes
Analyzing the real-time characteristic data by using the updated model, and identifying abnormal data points;
comparing the difference between the actual data and the model prediction to determine whether an abnormal condition exists;
and adopting an incremental learning method to adapt to new situations and modes.
9. The method for evaluating the on-orbit operation state of a spacecraft based on data mining according to claim 1, wherein in the step 5, the method for supporting real-time decision support of the operation state of the spacecraft is as follows:
the updated deep learning model is used for analyzing the real-time characteristic data;
decision rules and policies are formulated to make decisions based on the results of the data analysis,
and according to the data analysis and the decision rule, the central processing unit generates a decision suggestion in real time and outputs the decision suggestion to related personnel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410253714.7A CN117828517A (en) | 2024-03-06 | 2024-03-06 | Spacecraft on-orbit running state evaluation method based on data mining |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410253714.7A CN117828517A (en) | 2024-03-06 | 2024-03-06 | Spacecraft on-orbit running state evaluation method based on data mining |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117828517A true CN117828517A (en) | 2024-04-05 |
Family
ID=90524507
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410253714.7A Pending CN117828517A (en) | 2024-03-06 | 2024-03-06 | Spacecraft on-orbit running state evaluation method based on data mining |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117828517A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110073301A (en) * | 2017-08-02 | 2019-07-30 | 强力物联网投资组合2016有限公司 | The detection method and system under data collection environment in industrial Internet of Things with large data sets |
| CN111736566A (en) * | 2019-03-25 | 2020-10-02 | 南京智能制造研究院有限公司 | Remote equipment health prediction method based on machine learning and edge calculation |
| CN115828611A (en) * | 2022-12-15 | 2023-03-21 | 北京控制工程研究所 | Method and device for evaluating health state of electromechanical component of spacecraft |
| CN116011109A (en) * | 2023-01-13 | 2023-04-25 | 北京控制工程研究所 | Spacecraft service life prediction method and device, electronic equipment and storage medium |
| CN116225762A (en) * | 2023-03-01 | 2023-06-06 | 北京航空航天大学 | Data-driven model management method for long-term time sequence abnormality detection task |
| CN116542651A (en) * | 2023-05-16 | 2023-08-04 | 中国科学院空间应用工程与技术中心 | On-orbit autonomous health management system and method for payload of spacecraft |
| CN117390507A (en) * | 2023-09-22 | 2024-01-12 | 北京航空航天大学 | Spacecraft telemetry data detection system based on deep learning |
| CN117556310A (en) * | 2024-01-10 | 2024-02-13 | 北京中科航天人才服务有限公司 | Spacecraft residual life prediction method |
-
2024
- 2024-03-06 CN CN202410253714.7A patent/CN117828517A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110073301A (en) * | 2017-08-02 | 2019-07-30 | 强力物联网投资组合2016有限公司 | The detection method and system under data collection environment in industrial Internet of Things with large data sets |
| CN111736566A (en) * | 2019-03-25 | 2020-10-02 | 南京智能制造研究院有限公司 | Remote equipment health prediction method based on machine learning and edge calculation |
| CN115828611A (en) * | 2022-12-15 | 2023-03-21 | 北京控制工程研究所 | Method and device for evaluating health state of electromechanical component of spacecraft |
| CN116011109A (en) * | 2023-01-13 | 2023-04-25 | 北京控制工程研究所 | Spacecraft service life prediction method and device, electronic equipment and storage medium |
| CN116225762A (en) * | 2023-03-01 | 2023-06-06 | 北京航空航天大学 | Data-driven model management method for long-term time sequence abnormality detection task |
| CN116542651A (en) * | 2023-05-16 | 2023-08-04 | 中国科学院空间应用工程与技术中心 | On-orbit autonomous health management system and method for payload of spacecraft |
| CN117390507A (en) * | 2023-09-22 | 2024-01-12 | 北京航空航天大学 | Spacecraft telemetry data detection system based on deep learning |
| CN117556310A (en) * | 2024-01-10 | 2024-02-13 | 北京中科航天人才服务有限公司 | Spacecraft residual life prediction method |
Non-Patent Citations (2)
| Title |
|---|
| 崔吉俊;: "载人航天发射技术", 载人航天, no. 03, 5 June 2004 (2004-06-05) * |
| 彭喜元;庞景月;彭宇;刘大同;: "航天器遥测数据异常检测综述", 仪器仪表学报, no. 09, 15 September 2016 (2016-09-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106649727B (en) | Database construction method for fault detection of unmanned aerial vehicle flight control system | |
| US10992697B2 (en) | On-board networked anomaly detection (ONAD) modules | |
| US7403869B2 (en) | System state monitoring using recurrent local learning machine | |
| US7769507B2 (en) | System for gas turbine health monitoring data fusion | |
| US9122273B2 (en) | Failure cause diagnosis system and method | |
| CN113469060A (en) | Multi-sensor fusion convolution neural network aeroengine bearing fault diagnosis method | |
| CN109211548A (en) | A kind of mechanical failure diagnostic method | |
| US20030065409A1 (en) | Adaptively detecting an event of interest | |
| CN112949683B (en) | Intelligent fault diagnosis and early warning method and system for low-earth-orbit satellite | |
| EP3087445A1 (en) | Systems and methods for event detection and diagnosis | |
| CN113776794B (en) | Fault diagnosis method, device and system for embedded edge calculation | |
| CN108427400B (en) | Aircraft airspeed head fault diagnosis method based on neural network analytic redundancy | |
| CN108475445A (en) | The method and system of the automation fusion and analysis of multi-source aircraft data | |
| Pang et al. | Anomaly detection based on data stream monitoring and prediction with improved Gaussian process regression algorithm | |
| CN109630449B (en) | Three-proofing ventilation equipment fault prediction system based on RBF algorithm | |
| CN111103137A (en) | Wind turbine gearbox fault diagnosis method based on deep neural network | |
| Clifton et al. | Bayesian extreme value statistics for novelty detection in gas-turbine engines | |
| CN116609440A (en) | Intelligent acceptance management method and system for building engineering quality based on cloud edge cooperation | |
| Siegel | Prognostics and health assessment of a multi-regime system using a residual clustering health monitoring approach | |
| CN117828517A (en) | Spacecraft on-orbit running state evaluation method based on data mining | |
| WO2020230422A1 (en) | Abnormality diagnosis device and method | |
| Tabella et al. | Time-aware distributed sequential detection of gas dispersion via wireless sensor networks | |
| CN112733446A (en) | Data-driven self-adaptive anomaly detection method | |
| CN114299693B (en) | GNSS-based slope monitoring and early warning method | |
| Aftabi et al. | A Variational Autoencoder Framework for Robust, Physics-Informed Cyberattack Recognition in Industrial Cyber-Physical Systems |
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 |