CN112036440A - Satellite attitude control system fault diagnosis and early warning method based on random forest - Google Patents
Satellite attitude control system fault diagnosis and early warning method based on random forest Download PDFInfo
- Publication number
- CN112036440A CN112036440A CN202010754761.1A CN202010754761A CN112036440A CN 112036440 A CN112036440 A CN 112036440A CN 202010754761 A CN202010754761 A CN 202010754761A CN 112036440 A CN112036440 A CN 112036440A
- Authority
- CN
- China
- Prior art keywords
- fault
- attitude control
- control system
- data set
- satellite attitude
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000007637 random forest analysis Methods 0.000 title claims abstract description 37
- 238000004364 calculation method Methods 0.000 claims abstract description 6
- 238000012549 training Methods 0.000 claims description 16
- 238000005259 measurement Methods 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 6
- 238000012952 Resampling Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 abstract description 10
- 238000000926 separation method Methods 0.000 abstract description 3
- 238000003066 decision tree Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000011426 transformation method Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64G—COSMONAUTICS; VEHICLES OR EQUIPMENT THEREFOR
- B64G1/00—Cosmonautic vehicles
- B64G1/22—Parts of, or equipment specially adapted for fitting in or to, cosmonautic vehicles
- B64G1/24—Guiding or controlling apparatus, e.g. for attitude control
- B64G1/244—Spacecraft control systems
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Remote Sensing (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Radar, Positioning & Navigation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Aviation & Aerospace Engineering (AREA)
- Navigation (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a satellite attitude control system fault diagnosis and early warning method based on random forests, which belongs to the technical field of satellite attitude control system fault early warning and comprises the following steps: establishing an original data set; establishing a characteristic data set; establishing a random forest fault diagnosis model; and acquiring a system fault label. The fault separation is difficult to carry out by a fault diagnosis method based on a mechanism model, and in addition, a satellite system is in a space environment and is often under the action of various perturbation forces, and a disturbance signal is difficult to accurately estimate. In order to solve the problem, the method inputs the residual error signal of the mechanism model into a data-driven diagnosis and early warning model, realizes the diagnosis and early warning of the potential fault of the satellite attitude control system, can give timely early warning to the early fault of the satellite attitude control system, has low calculation complexity, high diagnosis accuracy and low missing report rate and false report rate, and provides an effective method for the rapid diagnosis and early warning of the fault of the satellite attitude control system.
Description
Technical Field
The invention belongs to the field of abnormal working condition early warning and early fault diagnosis of a satellite attitude control system, and particularly relates to a fault diagnosis method of the satellite attitude control system based on random forests.
Background
The satellite system is a large-scale complex system, and has special operation environment and a plurality of uncertain factors. The satellite always bears the effect of various perturbation forces in a space environment during in-orbit operation, so that the fault indexes of equipment and components used on the satellite are multiplied compared with those in a ground experimental environment, and in-orbit operation faults are difficult to avoid. The satellite attitude control system is one of important subsystems for guaranteeing that a satellite normally executes a flight task, and the probability of on-orbit fault and fault hazard are relatively high. The operation state of the satellite attitude control system is effectively monitored, and potential faults of the satellite attitude control system are early warned in time, so that the reliability and the safety of the in-orbit operation of the satellite system can be improved.
At present, fault diagnosis of a satellite attitude control system mainly depends on a mechanism model and is carried out by adopting a method based on residual error analysis. The fault diagnosis method based on the mechanism model can obtain an accurate diagnosis result on the premise that the model is accurate and external disturbance is known, but fault separation is difficult to carry out. The satellite system is in a space environment, the working environment is complex, the type and the form of a disturbance signal are difficult to accurately estimate, and a method only relying on a mechanism model is difficult to obtain a satisfactory diagnosis result. And the single adoption of the fault diagnosis method based on data driving is difficult to greatly improve the fault diagnosis accuracy of the satellite attitude control system, and is difficult to cope with the application of missing data and uncertain factors to diagnosis results, so that the false alarm rate is increased in many cases.
In order to realize rapid diagnosis and early warning of faults of a satellite attitude control system, a novel fault early warning method which is strong in generalization capability, small in calculation complexity, small in sensitivity to missing data and low in false alarm rate and missing report rate is urgently needed at present.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a rapid diagnosis and early warning method for the fault of the satellite attitude control system, which integrates a mechanism model and a data driving method, has the advantages of low calculation complexity, high diagnosis accuracy, low missing report rate and false report rate, and provides an effective solution for rapid diagnosis and early warning of the fault of the satellite attitude control system.
In order to achieve the purpose, the invention adopts the following technical scheme:
a satellite attitude control system fault diagnosis and early warning method based on random forests comprises the following steps:
step 1: establishing an original data set;
acquiring measurement output and attitude control instruction signals of a satellite attitude sensor in a normal state and a fault state, performing fusion calculation with output signals of a satellite kinematics and a dynamics model to obtain a residual data set, and then combining fault priori knowledge to construct an original data set;
step 2: establishing a characteristic data set;
extracting time domain features from data in the original data set according to expert knowledge and the characteristics of a satellite attitude control system, and constructing a feature data set;
and step 3: establishing a random forest fault diagnosis model;
repeatedly sampling the data of the training set in the feature data set, constructing a classification regression tree, and establishing a random forest fault diagnosis model;
and 4, step 4: acquiring a system fault label;
and (3) extracting time domain characteristics of the real-time data of the sensor, inputting the fault diagnosis model constructed in the step (3) to obtain a fault label, and thus realizing rapid diagnosis of the potential fault of the satellite attitude control system.
Preferably, in step 1, the method specifically comprises the following steps:
step 1.1: selecting measurement outputs of an infrared earth sensor, a sun sensor, a star sensor and a gyroscope in a satellite attitude control system and an attitude control instruction signal as key variables;
step 1.2: eliminating abnormal points in the data by using a 3 sigma rule to finish data cleaning;
step 1.3: obtaining a model signal by utilizing a satellite kinematics and dynamics model;
step 1.4: calculating residual errors of the two types of data in the step 1.2 and the step 1.3 to obtain a residual error data set;
step 1.5: and fault identification is carried out on the residual error data set by combining fault priori knowledge, and an original data set is constructed.
Preferably, in step 2, the method specifically comprises the following steps:
and extracting time domain characteristics from the data in the original data set according to 7 time domain indexes such as a maximum value, a root mean square, a square root amplitude value, a standard deviation, a peak index, a margin index and an absolute average value, and constructing a characteristic data set.
Preferably, in step 3, the method specifically comprises the following steps:
step 3.1: and (3) repeatedly sampling the characteristic data set constructed in the step (2) by using a bootstrap resampling method to obtain k subsets, generating a random forest model as a training set, and taking the samples which are not sampled as out-of-bag samples (out-of-bag, oob) as a verification set to evaluate the classification accuracy.
Step 3.2: establishing a classification regression tree by using k subsets in the training set, and constructing a base classification group;
step 3.3: and testing the classifier by using the verification data in the verification set, optimizing the classification accuracy of the random forest classifier according to the test result, and obtaining an optimal random forest fault diagnosis model.
Preferably, in step 4, the method specifically comprises the following steps:
step 4.1: extracting time domain characteristics from the real-time data of the sensor according to the methods in the step 1 and the step 2;
step 4.2: and (4) sending the time domain feature data extracted in the step (4.1) into the random forest fault diagnosis model constructed in the step (3.4) to obtain the fault classification label of the sample to be detected.
The invention has the following beneficial technical effects:
the satellite attitude control system is a closed-loop control circuit formed by an attitude sensor, a controller, an actuating mechanism and a star body, and faults in the closed-loop system often cause data abnormity at multiple positions and are difficult to locate. The method integrates the mechanism model and the data-driven algorithm, can fully utilize the accuracy of the mechanism model to improve the detection accuracy of the potential fault of the satellite attitude control system, and enables the diagnosis algorithm to quickly and accurately position the fault point by the integration of the random forest method. The method provided by the invention is used in the satellite system, so that the potential fault early warning accuracy of the satellite attitude control system can be improved, a precious time window is won for expert decision and diagnosis, and the long-term safe and reliable operation of the satellite system is facilitated.
According to the method, the measurement signal and the instruction signal of the satellite attitude control system are acquired, the acquired data are compared with the mechanism model data to obtain a residual error data set, then time domain characteristics are extracted, a complete training data set is constructed by fusing priori fault knowledge, and the rate of missing report of the system fault is effectively reduced. A plurality of classification regression trees are constructed by utilizing resampling, and a fault classifier based on random forests is established, so that the generalization capability of faults is greatly improved, meanwhile, the effective separation of various faults can be realized, and the sensitivity and the accuracy of fault diagnosis are further improved.
Drawings
FIG. 1 is a flow chart of a fault diagnosis method of a satellite attitude control system based on a random forest according to the invention;
FIG. 2 is a final error rate versus decision tree number curve for the method of the present invention;
Detailed Description
The invention is described in further detail below with reference to the following figures and detailed description:
as shown in fig. 1, a method for diagnosing and pre-warning a fault of a satellite attitude control system based on a random forest includes:
step 1: acquiring measurement output and control instruction signals of the satellite attitude sensor in a normal state and a fault state, performing fusion calculation with output signals of a satellite kinematics and a dynamic model to obtain residual data, and then combining fault priori knowledge to construct an original data set;
step 1 comprises the following substeps:
step 1.1: the measurement output of an attitude sensor in 2000 groups of satellite attitude control systems and an attitude control instruction signal are selected as key variables, and the attitude sensor is specifically selected from an infrared earth sensor, a sun sensor, a star sensor and a gyroscope.
And 1.2, removing coarse data outside the range of (mu +3 sigma, mu-3 sigma) in the data by using a 3 sigma rule to finish data cleaning, wherein mu is a mean value, and sigma is a standard deviation.
Step 1.3: utilizing satellite kinematics and kinematics model to obtain 2000 groups of above-mentioned variable model output signals;
step 1.4: calculating residual errors of the two types of data in the step 1.2 and the step 1.3 to obtain a residual error data set;
step 1.5: fusing expert knowledge to carry out fault identification and obtaining an original data set D ═ qe qg Mc yi"to be specific; wherein the measurement output of the infrared earth sensor is And thetaeRespectively representing a pitch angle and a roll angle output by the infrared earth sensor; the measurement output of the gyroscope is Andrepresenting angular velocity of gyroscope outputDegree; the control command signal is Mc=[ux uy uz」,ux、uyAnd uzRepresenting the control moment of the momentum wheel. y isiFor the type of failure, see table 1.
TABLE 1 failure types
Step 2: according to expert knowledge and the characteristics of a satellite attitude control system, time domain characteristics are extracted from data in an original data set according to 7 time domain indexes such as a maximum value, a root mean square, a square root amplitude, a standard deviation, a peak index, a margin index and an absolute average value, and a characteristic data set T is constructed.
Further, the time domain feature of the original data is extracted from each group of 4 continuous data according to the formula in table 2: finally forming a feature data setWherein T isqe,Tqg,TMcTime domain characteristics of the infrared earth sensor measurement output, the gyroscope measurement output and the momentum wheel control instruction, yiA fault category label; the number of features in the feature subset is M, each time selectedAnd the number is used as a splitting attribute in the growth of the decision tree.
TABLE 2 time domain feature transformation method
X in Table 2iThe ith variable in the original data set is represented, and n is the number of samples in the original data set.
In particular, T is described by way of example in Table 3qe,Tqg,TMcEach column is a variable, and each row is a rowA sample is obtained; the measurement output of the infrared earth sensor, the measurement output of the gyroscope and the momentum wheel control instruction are respectively obtained by calculating 1 sensor signal through the time domain characteristic transformation method shown in the table 2.
Table 3: characteristic data example
And step 3: and repeatedly sampling the data of the training set in the characteristic data set to obtain k bootstrap subsets, constructing a classification regression tree as a base classifier group of the random forest by using each subset, and testing by using the data in the test set, thereby completing the construction of the random forest model.
The step 3 comprises the following substeps:
step 3.1: and (3) repeatedly sampling the characteristic data set T constructed in the step (2) by utilizing a bootstrap resampling method to obtain k subsets, generating a random forest model as a training set, and taking the samples which are not sampled as out-of-bag samples (oob) as a verification set to evaluate the classification accuracy.
Specifically, the data in the feature data set T is resampled by the bootstrap method to obtain k subsets, where k is 350 in this embodiment.
The bootstrap resampling comprises the following specific steps:
(1) extracting training sets from the original sample set, extracting n training samples from the original sample set in each round, and performing k rounds of extraction to obtain k training sets which are independent from each other;
(2) training a model by using a training set and adopting a decision tree algorithm each time;
(3) and obtaining k classification subsets by voting the k models obtained in the last step.
Step 3.2: establishing a classification regression tree by using k subsets in the training set, and constructing a base classification group;
specifically, the "Gini index" is first used to select the partition attribute,
wherein p isiIs the probability of the ith class.
Then, selecting the characteristic with the minimum Gini index as ti and the optimal splitting value alpha for node splitting, wherein the optimal splitting value alpha is selected as follows:
whereinThe optimal splitting feature obtained for enumeration is tiThe time is two sub-sample sets, N1 and N2 are the number of samples of the two sub-sample sets, and N is the number of samples of the bootstrap sub-sample set.
When a classification regression tree is constructed, starting from a root node, recursively calculating the kini indexes of all existing features to a training data set for each node, selecting the minimum kini index as a splitting attribute, and splitting the nodes until a stopping condition is met.
The stopping conditions of the method are selected as follows:
(1) the number of samples of the sample subset is less than the minimum number of leaf nodes.
(2) The classes of the sample subset all belong to the same class.
(3) The decision tree height reaches a threshold.
Step 3.3: and testing the classifier by using the verification data in the verification set, optimizing the classification accuracy of the random forest classifier according to the test result, and obtaining an optimal random forest fault diagnosis model.
And 4, step 4: and (3) extracting time domain characteristics of real-time data of the sensor, and inputting the random forest model constructed in the step (3) to obtain a system fault label so as to realize rapid diagnosis of the potential fault of the satellite attitude control system.
The step 4 comprises the following substeps:
step 4.1: and (3) extracting time domain characteristics of the real-time sensor data according to the method in the step 2.
Step 4.2: and (3) sending the extracted time domain feature data into the random forest model constructed in the step (3), integrating classification results of k decision trees, voting by using a minority-compliant principle to obtain a classification result of the random forest, and thus realizing rapid diagnosis of signature faults of the sample to be detected.
And obtaining a fault classification label of the sample to be tested, wherein the fault diagnosis result in the test data is shown in table 4.
TABLE 4 confusion matrix of classification results
As can be seen from table 4, when the random forest algorithm is used for classification, there is no classification error between the y1 and the y4 types, 1 sample of y2 is classified incorrectly into y1,5 samples are classified incorrectly into y4, 1 sample of y3 is classified incorrectly into y4, 4 samples of y5 are classified incorrectly into y2, and the classification accuracy can reach 98.54%. Where the final error rate is related to the number of decision trees as shown in figure 2.
The above is a complete implementation process of the present embodiment.
It is to be understood that the above description is not intended to limit the present invention, and the present invention is not limited to the above examples, and those skilled in the art may make modifications, alterations, additions or substitutions within the spirit and scope of the present invention.
Claims (5)
1. A satellite attitude control system fault diagnosis and early warning method based on random forests is characterized by comprising the following steps:
step 1: establishing an original data set;
acquiring measurement output and attitude control instruction signals of a satellite attitude sensor in a normal state and a fault state, performing fusion calculation with output signals of a satellite kinematics and a dynamics model to obtain a residual data set, and then combining fault priori knowledge to construct an original data set;
step 2: establishing a characteristic data set;
extracting time domain features from data in the original data set according to expert knowledge and the characteristics of a satellite attitude control system, and constructing a feature data set;
and step 3: establishing a random forest fault diagnosis model;
repeatedly sampling the data of the training set in the feature data set, constructing a classification regression tree, and establishing a random forest fault diagnosis model;
and 4, step 4: acquiring a system fault label;
and (3) extracting time domain characteristics of real-time data of the sensor, inputting the random forest fault diagnosis model constructed in the step (3) to obtain a fault label, and thus, quickly diagnosing potential faults of the satellite attitude control system.
2. The random forest based satellite attitude control system fault diagnosis and early warning method according to claim 1, wherein in step 1, the method specifically comprises the following steps:
step 1.1: selecting measurement outputs of an infrared earth sensor, a sun sensor, a star sensor and a gyroscope in a satellite attitude control system and an attitude control instruction signal as key variables;
step 1.2: eliminating abnormal points in the data by using a 3 sigma rule to finish data cleaning;
step 1.3: obtaining a model signal by utilizing a satellite kinematics and dynamics model;
step 1.4: calculating residual errors of the two types of data in the step 1.2 and the step 1.3 to obtain a residual error data set;
step 1.5: and fault identification is carried out on the residual error data set by combining fault priori knowledge, and an original data set is constructed.
3. The random forest based satellite attitude control system fault diagnosis and early warning method according to claim 1, wherein in step 2, the method specifically comprises the following steps:
and extracting time domain characteristics from the data in the original data set according to 7 time domain indexes such as a maximum value, a root mean square, a square root amplitude value, a standard deviation, a peak index, a margin index and an absolute average value, and constructing a characteristic data set.
4. The random forest based satellite attitude control system fault diagnosis and early warning method as claimed in claim 1, wherein in step 3, the method specifically comprises the following steps:
step 3.1: repeatedly sampling the characteristic data set constructed in the step 2 by using a bootstrap resampling method to obtain k subsets, generating a random forest model as a training set, wherein samples which are not sampled are called out-of-bag samples (out-of-bag, oob), and are used as a verification set to evaluate the classification accuracy;
step 3.2: establishing a classification regression tree by using k subsets in the training set, and constructing a base classification group;
step 3.3: and testing the classifier by using the verification data in the verification set, optimizing the classification accuracy of the random forest classifier according to the test result, and obtaining an optimal random forest fault diagnosis model.
5. The random forest based satellite attitude control system fault diagnosis and early warning method according to claim 1, wherein in step 4, the method specifically comprises the following steps:
step 4.1: extracting time domain characteristics from the real-time data of the sensor according to the methods in the step 1 and the step 2;
step 4.2: and (4) sending the time domain feature data extracted in the step (4.1) into the random forest fault diagnosis model constructed in the step (3.4) to obtain the fault classification label of the sample to be detected.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010754761.1A CN112036440A (en) | 2020-07-31 | 2020-07-31 | Satellite attitude control system fault diagnosis and early warning method based on random forest |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010754761.1A CN112036440A (en) | 2020-07-31 | 2020-07-31 | Satellite attitude control system fault diagnosis and early warning method based on random forest |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112036440A true CN112036440A (en) | 2020-12-04 |
Family
ID=73583629
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010754761.1A Pending CN112036440A (en) | 2020-07-31 | 2020-07-31 | Satellite attitude control system fault diagnosis and early warning method based on random forest |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112036440A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112668806A (en) * | 2021-01-17 | 2021-04-16 | 中国南方电网有限责任公司 | Photovoltaic power ultra-short-term prediction method based on improved random forest |
CN113391622A (en) * | 2021-06-22 | 2021-09-14 | 中国人民解放军国防科技大学 | Spacecraft attitude system anomaly detection method using multivariate multistep prediction technology |
CN113469281A (en) * | 2021-07-22 | 2021-10-01 | 西北工业大学 | Industrial gear box multi-source information fusion fault diagnosis method |
CN113505445A (en) * | 2021-09-10 | 2021-10-15 | 北京航空航天大学 | Real-time fault diagnosis method and system based on sequential random forest |
CN113671363A (en) * | 2021-08-13 | 2021-11-19 | 华北电力大学(保定) | High-voltage circuit breaker state identification system and method |
CN113803647A (en) * | 2021-08-25 | 2021-12-17 | 浙江工业大学 | Pipeline leakage detection method based on fusion of knowledge characteristics and mixed model |
CN114169398A (en) * | 2022-01-28 | 2022-03-11 | 国网天津市电力公司 | Photovoltaic direct-current arc fault identification method and device based on random forest algorithm |
CN115048976A (en) * | 2022-04-20 | 2022-09-13 | 中国科学院微小卫星创新研究院 | Satellite attitude fault detection method combining XGboost with FocalLoss under data imbalance |
CN116127398A (en) * | 2023-04-10 | 2023-05-16 | 中国航空油料集团有限公司 | Hydraulic pump fault diagnosis method based on mechanism model and multi-source data fusion |
CN117113165A (en) * | 2023-07-07 | 2023-11-24 | 上海蓝箭鸿擎科技有限公司 | Satellite alarm data processing method and computer storage medium |
CN118419285A (en) * | 2024-07-03 | 2024-08-02 | 上海卫星互联网研究院有限公司 | Satellite fault early warning method and ground station |
CN118520789A (en) * | 2024-07-25 | 2024-08-20 | 山东科技大学 | High-speed train traction inverter fault diagnosis method based on weighted random forest |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080313488A1 (en) * | 2005-09-29 | 2008-12-18 | Seong-Kyun Jeong | Apparatus and Method for Diagnosing Fault and Managing Data in Satellite Ground System |
CN106742068A (en) * | 2016-12-07 | 2017-05-31 | 中国人民解放军国防科学技术大学 | A kind of method for diagnosing satellite attitude control system unknown failure |
CN110489254A (en) * | 2019-07-13 | 2019-11-22 | 西北工业大学 | Large aircraft aviation big data fault detection and causal reasoning system and method based on depth random forests algorithm |
CN110531737A (en) * | 2019-08-28 | 2019-12-03 | 北京空间飞行器总体设计部 | Satellite executing mechanism method for diagnosing faults, system and medium based on mixed model |
CN111290366A (en) * | 2020-02-12 | 2020-06-16 | 北京科技大学顺德研究生院 | Multi-fault diagnosis method for spacecraft attitude control system |
-
2020
- 2020-07-31 CN CN202010754761.1A patent/CN112036440A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080313488A1 (en) * | 2005-09-29 | 2008-12-18 | Seong-Kyun Jeong | Apparatus and Method for Diagnosing Fault and Managing Data in Satellite Ground System |
CN106742068A (en) * | 2016-12-07 | 2017-05-31 | 中国人民解放军国防科学技术大学 | A kind of method for diagnosing satellite attitude control system unknown failure |
CN110489254A (en) * | 2019-07-13 | 2019-11-22 | 西北工业大学 | Large aircraft aviation big data fault detection and causal reasoning system and method based on depth random forests algorithm |
CN110531737A (en) * | 2019-08-28 | 2019-12-03 | 北京空间飞行器总体设计部 | Satellite executing mechanism method for diagnosing faults, system and medium based on mixed model |
CN111290366A (en) * | 2020-02-12 | 2020-06-16 | 北京科技大学顺德研究生院 | Multi-fault diagnosis method for spacecraft attitude control system |
Non-Patent Citations (2)
Title |
---|
王子兰 等: "基于随机森林算法的旋转机械齿轮组故障诊断计", 《山东科技大学学报(自然科学版)》 * |
赵文 等: "卫星在轨故障地面诊断系统设计", 《航天器工程》 * |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112668806A (en) * | 2021-01-17 | 2021-04-16 | 中国南方电网有限责任公司 | Photovoltaic power ultra-short-term prediction method based on improved random forest |
CN112668806B (en) * | 2021-01-17 | 2022-09-06 | 中国南方电网有限责任公司 | Photovoltaic power ultra-short-term prediction method based on improved random forest |
CN113391622B (en) * | 2021-06-22 | 2022-09-02 | 中国人民解放军国防科技大学 | Spacecraft attitude system anomaly detection method using multivariate multistep prediction technology |
CN113391622A (en) * | 2021-06-22 | 2021-09-14 | 中国人民解放军国防科技大学 | Spacecraft attitude system anomaly detection method using multivariate multistep prediction technology |
CN113469281B (en) * | 2021-07-22 | 2023-11-24 | 西北工业大学 | Industrial gearbox multisource information fusion fault diagnosis method |
CN113469281A (en) * | 2021-07-22 | 2021-10-01 | 西北工业大学 | Industrial gear box multi-source information fusion fault diagnosis method |
CN113671363A (en) * | 2021-08-13 | 2021-11-19 | 华北电力大学(保定) | High-voltage circuit breaker state identification system and method |
CN113803647B (en) * | 2021-08-25 | 2023-07-04 | 浙江工业大学 | Pipeline leakage detection method based on fusion of knowledge features and hybrid model |
CN113803647A (en) * | 2021-08-25 | 2021-12-17 | 浙江工业大学 | Pipeline leakage detection method based on fusion of knowledge characteristics and mixed model |
CN113505445A (en) * | 2021-09-10 | 2021-10-15 | 北京航空航天大学 | Real-time fault diagnosis method and system based on sequential random forest |
CN114169398A (en) * | 2022-01-28 | 2022-03-11 | 国网天津市电力公司 | Photovoltaic direct-current arc fault identification method and device based on random forest algorithm |
CN115048976A (en) * | 2022-04-20 | 2022-09-13 | 中国科学院微小卫星创新研究院 | Satellite attitude fault detection method combining XGboost with FocalLoss under data imbalance |
CN116127398A (en) * | 2023-04-10 | 2023-05-16 | 中国航空油料集团有限公司 | Hydraulic pump fault diagnosis method based on mechanism model and multi-source data fusion |
CN117113165A (en) * | 2023-07-07 | 2023-11-24 | 上海蓝箭鸿擎科技有限公司 | Satellite alarm data processing method and computer storage medium |
CN118419285A (en) * | 2024-07-03 | 2024-08-02 | 上海卫星互联网研究院有限公司 | Satellite fault early warning method and ground station |
CN118419285B (en) * | 2024-07-03 | 2024-11-05 | 上海卫星互联网研究院有限公司 | Satellite fault early warning method and ground station |
CN118520789A (en) * | 2024-07-25 | 2024-08-20 | 山东科技大学 | High-speed train traction inverter fault diagnosis method based on weighted random forest |
CN118520789B (en) * | 2024-07-25 | 2024-10-01 | 山东科技大学 | High-speed train traction inverter fault diagnosis method based on weighted random forest |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112036440A (en) | Satellite attitude control system fault diagnosis and early warning method based on random forest | |
WO2023044978A1 (en) | Adversarial-flow-model-based unsupervised fault diagnosis method for mechanical device | |
CN108594788B (en) | Airplane actuator fault detection and diagnosis method based on deep random forest algorithm | |
CN110207997B (en) | Liquid rocket engine fault detection method based on convolution self-encoder | |
CN111985546B (en) | Single-classification extreme learning algorithm-based multi-working-condition detection method for aircraft engine | |
EP2478423A1 (en) | Supervised fault learning using rule-generated samples for machine condition monitoring | |
CN102722722A (en) | Mixed failure detection diagnosis method based on logical deduction and failure identification | |
CN108921230A (en) | Method for diagnosing faults based on class mean value core pivot element analysis and BP neural network | |
CN111639678A (en) | INS/GPS integrated navigation fault detection and diagnosis method based on integrated neural network | |
Yong et al. | Unmanned aerial vehicle sensor data anomaly detection using kernel principle component analysis | |
Han et al. | Quadratic-Kalman-filter-based sensor fault detection approach for unmanned aerial vehicles | |
CN111006860A (en) | Airplane actuator fault diagnosis method based on AdaBoost-ASVM algorithm | |
CN108427400A (en) | A kind of aircraft airspeed pipe method for diagnosing faults based on neural network Analysis design | |
WO2021114320A1 (en) | Wastewater treatment process fault monitoring method using oica-rnn fusion model | |
CN114997296A (en) | Unsupervised track anomaly detection method and unsupervised track anomaly detection system based on GRU-VAE model | |
CN107655690A (en) | Motor bearings method for diagnosing faults based on artificial neural network | |
CN101149819A (en) | Meteorological element real time data singular value elimination method | |
CN110119579B (en) | OICA-based complex industrial process fault monitoring method | |
CN110297475A (en) | A kind of batch process fault monitoring method based on Fourth-order moment singular value decomposition | |
CN103514458B (en) | The sensor fault discrimination method combined with support vector machine based on Error Correction of Coding | |
CN114417729A (en) | Mining area environment safety early warning method based on BP neural network | |
CN113885371B (en) | Mixed variable process monitoring method based on health state data | |
CN115964676A (en) | Unsupervised automatic driving automobile fault detection method and system | |
CN111506994B (en) | Motor rotor fault diagnosis method based on intelligent set | |
Wu et al. | Research on safety analysis method of functional integrated avionics 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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201204 |
|
RJ01 | Rejection of invention patent application after publication |