CN111783286A - Fault trend ratio and feature selection based micro fault diagnosis method and system - Google Patents
Fault trend ratio and feature selection based micro fault diagnosis method and system Download PDFInfo
- Publication number
- CN111783286A CN111783286A CN202010547795.3A CN202010547795A CN111783286A CN 111783286 A CN111783286 A CN 111783286A CN 202010547795 A CN202010547795 A CN 202010547795A CN 111783286 A CN111783286 A CN 111783286A
- Authority
- CN
- China
- Prior art keywords
- data
- fault
- trend
- monitoring data
- feature selection
- 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
Images
Classifications
-
- 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
-
- 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
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Navigation (AREA)
Abstract
The embodiment of the invention provides a tiny fault diagnosis method and a tiny fault diagnosis system based on fault trend ratio and feature selection, wherein the method comprises the steps of obtaining monitoring data of a spacecraft control system through kinematics and dynamics analysis of the control system; removing trend items of normal data in the monitoring data according to prior knowledge; performing feature selection on the monitoring data with normal data trend items removed based on asymmetric importance factors among different faults to obtain corresponding suboptimal visual mapping; and separating fault data in the monitoring data according to the suboptimal visual mapping. According to the technical scheme, through elimination of normal data and suboptimal visual mapping of data selected according to characteristics, the tiny fault diagnosis performance based on the fault trend ratio and the characteristic selection is improved, and the method has important significance for improving the reliability of the in-orbit spacecraft and prolonging the service life of the spacecraft.
Description
Technical Field
The invention relates to the field of spacecraft data processing, in particular to a tiny fault diagnosis method and system based on fault trend ratio and feature selection.
Background
Spacecraft are typically complex systems that integrate many disciplines of mechanics, electronics, materials, control, energy, communications, and computer technology with their latest sophisticated efforts. The spacecraft control system undertakes tasks of attitude control, orbit control, solar sailboard and antenna driving control and the like, and is one of the most important and complex subsystems in the spacecraft [1 ]. In 2018, the success of the moon goddess in the fourth month of Chang E marks great progress of the aerospace industry. However, worldwide, spacecraft control system failures have also resulted in significant losses in space planning, scientific research, economic efficiency, and even political and military [2-4 ]. For example, in 12 months 2005, the attitude of the detector for tench in japan controlled the leakage of fuel from the reaction wheel, and the detector could not maintain the attitude. Loss of contact with the ground control centre for up to 2 months misses a return window, resulting in a "falcon" postponing 3 years to return to earth [5 ]. For another example, in 7 months in 2017, the practice satellite 18 carried by the rocket Changcheng 5 in China crashes into the sea, the task is lost, the technology is returned to zero, and the public opinion shakes. The package for the national academy indicates in the congress report of CAC 2017: if the early-stage micro fault of the spacecraft controller can be detected in time, the controller is intelligent enough, but not single in function, and the 16-billion-element east red 5 satellite platform cannot fall into the sea [6 ]. For another example, in 2018, when a small single-machine fault occurs in a certain type of Chinese spacecraft, the fault is not detected and alarmed in time, the actuator continuously injects air, the attitude angular velocity is rapidly increased, the platform is out of control and rolls, the SADA solar wing is broken, and finally the whole spacecraft fails. Due to the importance of the tasks undertaken by the spacecraft control system and the high occurrence of faults, the improvement of the reliability of the control system becomes the key for ensuring the on-orbit safety and the operation quality of the spacecraft.
Obvious faults are usually evolved from early tiny faults, and if tiny faults are detected in time within a controllable range of system operation and are separated and positioned, failure events are effectively avoided, so that diagnosis of tiny faults plays an important role in achieving high reliability and long service life of the whole satellite.
Disclosure of Invention
The embodiment of the invention provides a tiny fault diagnosis method and system based on fault trend ratio and feature selection, and through elimination of normal data and suboptimal visual mapping of data feature selection, tiny fault diagnosis performance based on fault trend ratio and feature selection is improved, so that the tiny fault diagnosis method and system based on fault trend ratio and feature selection have important significance for improving reliability of an on-orbit spacecraft and prolonging service life of the spacecraft.
In order to achieve the above object, in one aspect, an embodiment of the present invention provides a minor fault diagnosis method based on a fault trend ratio and feature selection, where the method includes:
obtaining monitoring data of a spacecraft control system through kinematic and dynamic analysis of the control system;
removing trend items of normal data in the monitoring data according to prior knowledge;
performing feature selection on the monitoring data with normal data trend items removed based on asymmetric importance factors among different faults to obtain corresponding suboptimal visual mapping;
and separating fault data in the monitoring data according to the suboptimal visual mapping.
On the other hand, the embodiment of the invention provides a tiny fault diagnosis system based on fault trend ratio and feature selection, and the system comprises:
the data acquisition unit is used for acquiring monitoring data of the control system through kinematic and dynamic analysis of the spacecraft control system;
the data removing unit is used for removing the trend item of the normal data in the monitoring data according to the priori knowledge;
the mapping unit is used for carrying out feature selection on the monitoring data with normal data trend items removed based on asymmetric importance factors among different faults so as to obtain corresponding suboptimal visual mapping;
and the fault separation unit is used for separating fault data in the monitoring data according to the suboptimal visual mapping.
The technical scheme has the following beneficial effects:
the technical scheme of the invention utilizes the tiny fault detection method based on normal data elimination and the tiny fault separation method based on the visual mapping technology to break through the difficulty of tiny fault detection, improve the detection rate of tiny faults, provide an optimal fault information view, improve the fault separation rate, enhance the reliability of tiny fault diagnosis results, perfect the tiny fault diagnosis theory, complete the fault library of the on-orbit spacecraft control system, and provide theoretical and technical support for improving the on-orbit fault diagnosis and processing capability of the spacecraft.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a minor fault diagnosis method based on fault trend ratio and feature selection according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating micro fault data in an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a minor fault diagnosis system based on fault trend ratio and feature selection according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the method is a flowchart of a minor fault diagnosis method based on fault trend ratio and feature selection according to an embodiment of the present invention, and the method includes:
s101: obtaining monitoring data of a spacecraft control system through kinematic and dynamic analysis of the control system; preferably, the monitoring data includes an operation mechanism data, a model structure data and a model parameter data of the control system.
And acquiring an information source of a subsequent tiny fault diagnosis method through mechanism analysis and state acquisition. The information source of the on-track typical case mainly comprises two parts, namely a mechanism model and monitoring data. The operation mechanism, the model structure and the model parameters of the control system can be obtained through the kinematics and dynamics analysis of the spacecraft control system, and the information is not only a model information source of a tiny fault diagnosis method, but also a simulation basis of a Simulink control and an S function module of Matlab. The computer can store the actuator monitoring data (momentum wheel/thruster/sailboard driving mechanism, etc.) and the sensor monitoring data (gyroscope/infrared sensor/star sensor/sun sensor, etc.) in real time, and the information is not only the data information source of the tiny fault diagnosis method, but also the entry information of the Qt Widgets window application program.
S102: and eliminating the trend item of the normal data in the monitoring data according to the prior knowledge.
As shown in fig. 2, the monitoring data y of the system can be decomposed into three parts: noise e, trend t, and fault f. The trend term is inherently smoother, affected by noise, and the data perturbs between the upper and lower envelopes. If the trend is non-stationary and the variance ratio of the noise is large, the minor fault is easily masked by the trend and the noise. In fig. 2, the monitoring data between the start of the fault and the end of the fault has a slight fault, but does not significantly break through the upper and lower envelopes, so that it is difficult to visually find the change caused by the fault. Similar phenomena exist in monitoring data of a gyroscope of a spacecraft control system under the condition of micro-drift faults. One of the core problems of minor Fault detection is to weaken the "trend-over-Fault effect", i.e., to increase the Fault-trend ratio FTR (Fault-trend ratio). If r (t) represents the desired sphere radius of the trend space, the failure trend ratio is FTR | | | f | |/r (t). The R (t) of non-stationary systems is very large and requires extraction and elimination of normal trends. If I denotes the identity matrix, Ψ (m, p) denotes the m-th order design operator that characterizes the trend, p is a delay factor, e.g., Φ (2, p) ═ p + p +1, then Φ (2, p) f (k) ═ f (k-2) + f (k-1) + f (k); the signal after eliminating the trend is marked as (I-psi (m, p)) y, and the designed FTR is
FTR(Ψ,m)＝||f||/||(I-Ψ(m,p))y|| (1)
The domain experts have corresponding prior knowledge no matter the data characteristics such as monotonicity, periodicity, inflection points and the like, or the system structure, model parameters and operation mechanism of the monitored system. Therefore, the trend items Ψ (m, p) y of the normal data can be extracted by using the priori knowledge, and when most of the trend items are removed from the monitoring data, the fault trend ratio can be increased, so that the trend inundation fault effect is weakened or even eliminated, the fault detection rate is increased, and the fault detection delay time is reduced. The existing research shows that: if the monitored object meets the linear structure, the conventional multivariate statistical dimension reduction method and the dynamic dimension reduction method, such as principal component analysis and dynamic principal component analysis, can obviously weaken the trend inundation fault effect. However, the spacecraft control system is a typical nonlinear system, and the conventional trend elimination method has no obvious effect, and at the moment, the priori knowledge of the model structure of the control system is particularly important. If it is used
Representing the m-order trend operator family under the constraint of system structure, model parameters, operation mechanism and prior knowledge, the research route can be described as
Preferably, the measurement and control mechanism, the transmission characteristic and the trend characteristic of the spacecraft control system are analyzed; the removing trend items of normal data in the monitoring data according to the priori knowledge comprises the following steps: extracting data of nonlinear non-stationary trend of the monitoring data by using a system modeling means and a parameter estimation means; and rejecting data of the nonlinear non-stationary trend of the monitoring data.
S103: performing feature selection on the monitoring data with normal data trend items removed based on asymmetric importance factors among different faults to obtain corresponding suboptimal visual mapping;
in q faults after dimensionality reduction, the separation information of any two faults is Iso (r)i,rj)＝||Mri-sign(i,j)Mrj||2(i, j equals 1, …, q), wherein if the direction angle is acute, sign (i, j) equals 1, otherwise sign (i, j) equals-1. The symmetric optimal visualization mapping assumes that the importance of different types of faults is the same, so the feature extraction method can be simply converted into a principal component analysis process. In spacecraft control systems, however, the importance of different fault separation information should be treated differently. For example, if the included angle between the two characteristic directions is very small, a slight loss of separation information may cause the two faults to be inseparable; on the contrary, if the included angle between the two characteristic directions is large, the influence of weak separation information loss on the fault separation result is not large.
Finding a suboptimal visualization mapping based on feature selection, the more separation information a certain feature has, the more should be preserved, and the process is refined into three steps: first, a set of features is determined that are optional, such as features that retain large amplitude variations and are prone to failure. And secondly, determining a necessary characteristic set, for example, rejecting a small amount of characteristic which has small amplitude change and is not easy to malfunction. Third, a measure of relevance of the features to the separation information is given, resulting in a preference criterion, and a subset of the features with the most separation information is searched in the candidate feature set.
Preferably, the characteristic selection of the monitoring data with normal data trend items removed based on the asymmetric importance factors between different faults to obtain the corresponding suboptimal visualization mapping is realized by the following formula:
wherein, wij(i, j ═ 1, …, q) is the asymmetric importance factor, q is the number of faults after dimensionality reduction;
Iso(ri,rj) Feature vector r for any two faultsi,rjIs expressed as Iso (r)i,rj)＝||Mri-sign(i,j)Mrj||2(i, j ═ 1, …, q), if two fault feature vectors ri,rjIf the inter-directional angle is an acute angle, sign (i, j) is 1, otherwise sign (i, j) is-1;
m represents a feature selection sparse matrix, and I is an identity matrix.
S104: and separating fault data in the monitoring data according to the suboptimal visual mapping.
Further preferably, for the separation of the fault noise in the scheme, a test tool box is provided, and the tool box is divided into three layers. An input layer: and simulating the satellite attitude control system by using the Simulink control and the S function module, and using a QFileDialog library of a Qt Widgets designer as a data import port of the satellite attitude control system. And an algorithm layer: and the M file is used for realizing a tiny fault amplification detection algorithm, a tiny fault visual separation algorithm, a data graph export function and the like. An output layer: the toolbox GUI interface is completed with a Qt designer. The availability, the operational efficiency and the diagnosis performance of the data test tool kit and the tiny fault diagnosis method are monitored by utilizing the simulation data and the real satellite control system. The test feedback result can be used as the basis for improving the tiny fault diagnosis method.
Corresponding to the above method, as shown in fig. 3, a schematic structural diagram of a minor fault diagnosis system based on fault trend ratio and feature selection according to an embodiment of the present invention is shown, where the system includes:
a data acquisition unit 21, configured to obtain monitoring data of a spacecraft control system through kinematic and dynamic analysis of the control system;
the data removing unit 22 is used for removing the trend item of the normal data in the monitoring data according to the priori knowledge;
the mapping unit 23 is configured to perform feature selection on the monitoring data from which the normal data trend item is removed based on asymmetric importance factors between different faults to obtain corresponding suboptimal visual mapping;
and the fault separation unit 24 is configured to separate fault data in the monitoring data according to the suboptimal visualization mapping.
Preferably, the monitoring data includes operational mechanism data, model structure data and model parameter data of the control system.
Preferably, the data eliminating unit 23 is specifically configured to:
extracting data of nonlinear non-stationary trend of the monitoring data by using a system modeling means and a parameter estimation means;
and rejecting data of the nonlinear non-stationary trend of the monitoring data.
Preferably, the system modeling means comprises hybrid polynomial approximation, high-dimensional spline fitting, time series modeling and multi-frequency signal decomposition.
Preferably, the mapping unit 23 implements a sub-optimal visual mapping of the monitoring data by the following formula:
wherein, wij(i, j ═ 1, …, p) is the asymmetric importance factor, p is the number of faults after dimensionality reduction;
Iso(ri,rj) Feature vector r for any two faultsi,rjIs expressed as Iso (r)i,rj)＝||Mri-sign(i,j)Mrj||2(i, j ═ 1, …, p), if two fault feature vectors ri,rjIf the inter-directional angle is an acute angle, sign (i, j) is 1, otherwise sign (i, j) is-1;
m represents a feature selection sparse matrix, and I is an identity matrix.
It should be understood that the specific order or hierarchy of steps in the processes disclosed is an example of exemplary approaches. Based upon design preferences, it is understood that the specific order or hierarchy of steps in the processes may be rearranged without departing from the scope of the present disclosure. The accompanying method claims present elements of the various steps in a sample order, and are not intended to be limited to the specific order or hierarchy presented.
In the foregoing detailed description, various features are grouped together in a single embodiment for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the claimed embodiments of the subject matter require more features than are expressly recited in each claim. Rather, as the following claims reflect, invention lies in less than all features of a single disclosed embodiment. Thus, the following claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. To those skilled in the art; various modifications to these embodiments will be readily apparent, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
What has been described above includes examples of one or more embodiments. It is, of course, not possible to describe every conceivable combination of components or methodologies for purposes of describing the aforementioned embodiments, but one of ordinary skill in the art may recognize that many further combinations and permutations of various embodiments are possible. Accordingly, the embodiments described herein are intended to embrace all such alterations, modifications and variations that fall within the scope of the appended claims. Furthermore, to the extent that the term "includes" is used in either the detailed description or the claims, such term is intended to be inclusive in a manner similar to the term "comprising" as "comprising" is interpreted when employed as a transitional word in a claim. Furthermore, any use of the term "or" in the specification of the claims is intended to mean a "non-exclusive or".
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. The tiny fault diagnosis method based on the fault trend ratio and the feature selection is characterized by comprising the following steps of:
obtaining monitoring data of a spacecraft control system through kinematic and dynamic analysis of the control system;
removing trend items of normal data in the monitoring data according to prior knowledge;
performing feature selection on the monitoring data with normal data trend items removed based on asymmetric importance factors among different faults to obtain corresponding suboptimal visual mapping;
and separating fault data in the monitoring data according to the suboptimal visual mapping.
2. The method of fault trend ratio and feature selection based minor fault diagnosis according to claim 1, wherein the monitoring data includes operational mechanism data, model structure data and model parameter data of the control system.
3. The minor fault diagnosis method based on fault tendency ratio and feature selection as claimed in claim 2, wherein the removing trend items of normal data in the monitoring data according to prior knowledge comprises:
extracting data of nonlinear non-stationary trend of the monitoring data by using a system modeling means and a parameter estimation means;
and rejecting data of the nonlinear non-stationary trend of the monitoring data.
4. The method of fault trend ratio and feature selection based minor fault diagnosis according to claim 3, wherein the system modeling means includes hybrid polynomial approximation, high-dimensional spline fitting, time sequence modeling and multi-frequency signal decomposition.
5. The method as claimed in claim 4, wherein the characteristic selection of the monitoring data with normal data trend items removed based on the asymmetric importance factors between different faults to obtain the corresponding sub-optimal visual mapping is implemented by the following formula:
wherein, wij(i, j ═ 1, …, q) is the asymmetric importance factor, q is the number of faults after dimensionality reduction;
Iso(ri,rj) Feature vector r for any two faultsi,rjIs expressed as Iso (r)i,rj)＝||Mri-sign(i,j)Mrj||2(i, j ═ 1, …, q), if two fault feature vectors ri,rjIf the inter-directional angle is an acute angle, sign (i, j) is 1, otherwise sign (i, j) is-1;
m represents a feature selection sparse matrix, and I is an identity matrix.
6. A tiny fault diagnosis system based on fault trend ratio and feature selection is characterized by comprising:
the data acquisition unit is used for acquiring monitoring data of the control system through kinematic and dynamic analysis of the spacecraft control system;
the data removing unit is used for removing the trend item of the normal data in the monitoring data according to the priori knowledge;
the mapping unit is used for carrying out feature selection on the monitoring data with normal data trend items removed based on asymmetric importance factors among different faults so as to obtain corresponding suboptimal visual mapping;
and the fault separation unit is used for separating fault data in the monitoring data according to the suboptimal visual mapping.
7. The minor fault diagnosis system based on fault trend ratio and feature selection according to claim 6, wherein the monitoring data includes operational mechanism data, model structure data and model parameter data of the control system.
8. The minor fault diagnosis system based on fault trend ratio and feature selection as claimed in claim 7, wherein the data culling unit is specifically configured to:
extracting data of nonlinear non-stationary trend of the monitoring data by using a system modeling means and a parameter estimation means;
and rejecting data of the nonlinear non-stationary trend of the monitoring data.
9. The fault trend ratio and feature selection based minor fault diagnosis system of claim 8, wherein the system modeling means comprises hybrid polynomial approximation, high-dimensional spline fitting, timing modeling and multi-frequency signal decomposition.
10. The minor fault diagnosis system based on fault trend ratio and feature selection according to claim 9, wherein the mapping unit implements a suboptimal visual mapping of the monitoring data by:
wherein, wij(i, j ═ 1, …, q) is asymmetricThe importance factor q is the number of faults after dimensionality reduction;
Iso(ri,rj) Feature vector r for any two faultsi,rjIs expressed as Iso (r)i,rj)＝||Mri-sign(i,j)Mrj||2(i, j ═ 1, …, q), if two fault feature vectors ri,rjIf the inter-directional angle is an acute angle, sign (i, j) is 1, otherwise sign (i, j) is-1;
m represents a feature selection sparse matrix, and I is an identity matrix.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010547795.3A CN111783286A (en) | 2020-06-16 | 2020-06-16 | Fault trend ratio and feature selection based micro fault diagnosis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010547795.3A CN111783286A (en) | 2020-06-16 | 2020-06-16 | Fault trend ratio and feature selection based micro fault diagnosis method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111783286A true CN111783286A (en) | 2020-10-16 |
Family
ID=72756014
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010547795.3A Pending CN111783286A (en) | 2020-06-16 | 2020-06-16 | Fault trend ratio and feature selection based micro fault diagnosis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111783286A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113051092A (en) * | 2021-02-04 | 2021-06-29 | 中国人民解放军国防科技大学 | Fault diagnosis method based on optimized kernel density estimation and JS divergence |
-
2020
- 2020-06-16 CN CN202010547795.3A patent/CN111783286A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113051092A (en) * | 2021-02-04 | 2021-06-29 | 中国人民解放军国防科技大学 | Fault diagnosis method based on optimized kernel density estimation and JS divergence |
| CN113051092B (en) * | 2021-02-04 | 2022-05-17 | 中国人民解放军国防科技大学 | Fault diagnosis method based on optimized kernel density estimation and JS divergence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jiang et al. | Adaptive neural observer‐based backstepping fault tolerant control for near space vehicle under control effector damage | |
| Alcorta-Garcia et al. | A nonlinear observer-based strategy for aircraft oscillatory failure detection: A380 case study | |
| Falcoz et al. | Robust fault diagnosis for atmospheric reentry vehicles: a case study | |
| Rahimi et al. | Fault isolation of reaction wheels for satellite attitude control | |
| CN107392226A (en) | The modeling method of pilot's working condition identification model | |
| CN111783286A (en) | Fault trend ratio and feature selection based micro fault diagnosis method and system | |
| Chu et al. | Least square based ensemble deep learning for inertia tensor identification of combined spacecraft | |
| Baram | Realization and reduction of Markovian models from nonstationary data | |
| Chen et al. | A random forest and model-based hybrid method of fault diagnosis for satellite attitude control systems | |
| Wang et al. | Fault detection of flywheel system based on clustering and principal component analysis | |
| Grauer | Real-time data-compatibility analysis using output-error parameter estimation | |
| Huang et al. | A modified fusion model-based/data-driven model for sensor fault diagnosis and performance degradation estimation of aero-engine | |
| Akbari et al. | A new feature selection-aided observer for sensor fault diagnosis of an industrial gas turbine | |
| Wang et al. | A machine learning method for the orbit state classification of large LEO constellation satellites | |
| CN111813074B (en) | Fault noise ratio and feature extraction based tiny fault diagnosis method and system | |
| Zixuan et al. | Predictive reentry guidance with aerodynamic parameter online correction | |
| Matthews et al. | Space shuttle main propulsion system anomaly detection: A case study | |
| Nassar et al. | Supervised learning algorithms for spacecraft attitude determination and control system health monitoring | |
| Abedini et al. | Design of a robust fault-tolerant control algorithm based on failure mode effects criticality analysis for a three-axis satellite | |
| Wei et al. | Fault diagnosis method of spacecraft control systems based on PCA-ResNet | |
| Rahimi et al. | Fault isolation of reaction wheels onboard 3-axis controlled in-orbit satellite using ensemble machine learning techniques | |
| Zhang et al. | Convergence analysis of Zhang neural networks solving time-varying linear equations but without using time-derivative information | |
| Peters et al. | A Data-Driven Reduced Order Model of an Isolated Rotor | |
| Ashari et al. | Auxiliary input design for stochastic subspace-based structural damage detection | |
| Balachandran et al. | Classification of Resident Space Objects by shape and spin motion using neural networks and photometric light curves |
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 |