CN106649727B - Database construction method for fault detection of unmanned aerial vehicle flight control system - Google Patents
Database construction method for fault detection of unmanned aerial vehicle flight control system Download PDFInfo
- Publication number
- CN106649727B CN106649727B CN201611205514.6A CN201611205514A CN106649727B CN 106649727 B CN106649727 B CN 106649727B CN 201611205514 A CN201611205514 A CN 201611205514A CN 106649727 B CN106649727 B CN 106649727B
- Authority
- CN
- China
- Prior art keywords
- data
- time
- real
- unmanned aerial
- aerial vehicle
- 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.)
- Active
Links
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 title claims abstract description 41
- 238000001514 detection method Methods 0.000 title claims abstract description 40
- 238000010276 construction Methods 0.000 title claims abstract description 16
- 238000000034 method Methods 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 6
- 238000013473 artificial intelligence Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 3
- 238000011160 research Methods 0.000 description 14
- 230000002159 abnormal effect Effects 0.000 description 9
- 230000005856 abnormality Effects 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 240000001987 Pyrus communis Species 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 241001391944 Commicarpus scandens Species 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004378 air conditioning Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 239000007799 cork Substances 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013173 literature analysis Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a database construction method for unmanned aerial vehicle flight control system fault detection, and belongs to the technical field of unmanned aerial vehicle fault detection. The invention fuses the normal real-time flight control data of the unmanned aerial vehicle screened by the judgment rule into the historical data, judges whether the unmanned aerial vehicle with unknown fault at the future moment has fault or not according to the judgment rule trained by the historical data, and dynamically updates the reference database formed by the normal historical data, thereby ensuring the real-time updating of the judgment rule and the real-time characteristic of the reference database formed by the normal historical data.
Description
Technical Field
The invention discloses a database construction method for unmanned aerial vehicle flight control system fault detection, and belongs to the technical field of unmanned aerial vehicle fault detection.
Background
In recent years, with the introduction of a fault Prediction and Health Management (PHM) concept to an integrated management system for an unmanned aerial vehicle, demands for informatization and intellectualization of safety management of the unmanned aerial vehicle have been increasing. The core part of the safety management of the unmanned aerial vehicle, namely safety monitoring and abnormity early warning, can comprehensively monitor the health state of the unmanned aerial vehicle, and has important significance for improving the safety performance of the unmanned aerial vehicle, guaranteeing the maintenance efficiency and reducing the service life. The flight control system of the unmanned aerial vehicle is used as a core component of the unmanned aerial vehicle and comprises subsystems such as various sensors, network links, execution devices and the like, wherein the flight control sensors measure real-time flight state parameters of the aircraft and feed back data to a flight control computer. The flight control computer solves the flight control law so as to complete the flight task of automatic driving of the unmanned aerial vehicle, but the flight control system is very easy to break down due to the complex working environment.
According to research objects, the current research at home and abroad aiming at the special problem of unmanned aerial vehicle safety monitoring and fault early warning mainly focuses on the aspects of generalized unmanned aerial vehicle network communication link safety, unmanned aerial vehicle flight control sensor fault detection, analysis of abnormal behaviors of unmanned aerial vehicles and the like.
Researchers in related colleges and scientific research institutions in China in recent years make extensive researches on detection of abnormal state of output data of a sensor of an unmanned aerial vehicle flight control system and hardware faults. Research teams of northwest industry university research the fault detection of flight control systems based on improved principal component analysis, improved discrete wavelet-optimized extreme learning fault detection and other methods; a series of researches are conducted by teaching teams of Nanjing aerospace university ginger and teaching aiming at algorithms of adaptive fault detection, fault-tolerant navigation and the like of the unmanned aerial vehicle; the Beijing university of aerospace Schmidt and McLeng professor team researches the unmanned aerial vehicle flight control system fault detection method based on extended Kalman filtering and volume Kalman filtering; in addition, research units such as national defense science and technology university also study multiple aspects such as unmanned aerial vehicle fault detection. The series of researches lay a theoretical foundation and a technical foundation for fault detection of the unmanned aerial vehicle flight control system.
Foreign colleges and universities and research institutions also carry out extensive research on the problem of flight control faults of the unmanned aerial vehicle, and Kim and the like provide an abnormal flight detection framework for the unmanned aerial vehicle under network attack, hardware attack, sensor fraud and wireless attack. An unmanned aerial vehicle abnormal data detection method based on flight control sensor data state analysis estimated by IMM-UKF is designed by Cork and Walker. Lin and Khalatchi and the like establish an abnormal flight judgment model by monitoring and analyzing the states of flight data, pipeline data, engine data and servo data streams of the unmanned aerial vehicle. Mitchell and Chen put forward a self-adaptive unmanned aerial vehicle behavior partitioning standard based on an intrusion detection system in the field of network link data. Birnbaum and the like design flight dynamics based on a real-time recursive least square system and a detection method of flight control parameters to monitor the health state of the unmanned aerial vehicle, and then Birnbaum and the like match flight position, dynamic information, time information and preset unmanned aerial vehicle flight plan related information output by an unmanned aerial vehicle flight control system in real time to realize monitoring of the state of the unmanned aerial vehicle. In addition, there have been some studies directed to generalized aircraft flight control fault detection.
For the research content, from the theory, method and technical route, we can find that the core algorithms of fault detection can be divided into the following three major categories: model based, knowledge-empirical based, and data-driven.
In recent years, with the rapid development of machine learning and data mining, data-driven methods have gradually become a hotspot and direction of fault diagnosis research. The data-driven fault diagnosis method is widely applied to fault detection in various fields, and based on data in the system operation process, information implicit in the data is mined through various data processing and analyzing methods to complete abnormal detection of the system data. Khalatchi et al propose a real-time online data-driven scheme for detecting the abnormality of an onboard sensor of an automatic robot. Beghi et al propose data-driven based fault detection schemes for chiller systems of air conditioning units. Yin et al propose a data-driven based wind turbine system fault diagnosis method. In addition, methods based on data driving are also widely studied in the fields of automation, machinery, and the like. Therefore, the data driving method has great potential and value in the fault detection of the unmanned plane flight control system due to the flexible and changeable characteristics.
Generally, according to domestic and foreign literature analysis, the current model method and knowledge-experience method have the following disadvantages: (1) difficulty in detecting unknown faults; (2) is more suitable for a low-dimensional system. Aiming at the unmanned aerial vehicle flight control complex system, each detail of a complex mechanism model cannot be obtained by a model-based method; on the other hand, the method based on knowledge experience needs long-term experience knowledge accumulation, and has the defect that the method cannot meet the requirement of complex and variable anomaly detection of the unmanned aerial vehicle. Therefore, the problems of large calculation amount, unreasonable fault model assumption, poor flexibility and adaptability and the like generally exist in the current fault detection research based on a model method and a qualitative knowledge-experience method. The data-driven fault detection has a wide application prospect, but key technical problems remain to be solved, wherein effective extraction (fault or normal) of data features and effective construction of a reference database for fault detection are core problems in data-driven fault detection.
Disclosure of Invention
The invention aims to provide a database construction method for unmanned aerial vehicle flight control system fault detection, which aims to overcome the defects of the background technology, realizes the dynamic construction of the unmanned aerial vehicle flight control system fault detection database by extracting normal data features on line in real time, and solves the technical problem that the fault detection of the unmanned aerial vehicle flight control system cannot adapt to the abnormal detection requirement because the extraction of each fault feature is difficult to realize.
The invention adopts the following technical scheme for realizing the aim of the invention:
a database construction method for detecting faults of an unmanned aerial vehicle flight control system includes the steps of collecting real-time observation data of the unmanned aerial vehicle flight control system at the current moment, training off-line duration data at the current moment by adopting an artificial intelligence algorithm to obtain a fault judgment rule at the current moment and screening out a reference database formed by normal historical data at the current moment, judging whether the real-time observation data at the current moment are faulty or not by adopting a fault judgment rule at the current moment, updating the reference database formed by the normal historical data at the current moment when the real-time observation data at the current moment are normal, updating the off-line historical data, repeatedly training the fault judgment rule in real time according to the updated off-line historical data and screening out the reference database formed by the normal historical data in real time, processing the result of the real-time observation data at the current moment according to the real-time trained fault judgment rule, and updating the reference database formed by the normal historical data on line according to the A database.
As a further optimization scheme of the database construction method, real-time observation data of the unmanned aerial vehicle flight control system at the current moment comprises the following steps: and measuring data of a three-axis gyroscope, a GPS, an accelerometer and a barometer.
As a further optimization scheme of the database construction method, a reference database formed by normal historical data at the current time is updated when real-time observation data at the current time are normal, and the specific method is as follows: and representing a reference database formed by normal historical data at the current moment by using a time sequence with a window length, eliminating tail data in the time sequence with the window length by using a sliding window model with the window length, and adding real-time observation data at the tail of the time sequence with the window length at the current moment.
As a further optimization scheme of the database construction method, before judging whether the real-time observation data at the current time has a fault by adopting a fault judgment rule at the current time, the noise in the real-time observation data at the current time is removed by adopting a Kalman filtering algorithm.
As a further optimization scheme of the database construction method, an artificial intelligence algorithm including but not limited to an artificial neural network and a decision tree is adopted to train offline duration data at the current time to obtain a fault judgment rule at the current time, and a reference database formed by normal historical data at the current time is screened out.
By adopting the technical scheme, the invention has the following beneficial effects: the invention provides a database construction method for data driving aiming at the fault detection of an unmanned aerial vehicle flight control system, which trains a historical database at each moment in real time to obtain a fault judgment rule at each moment and screens out a reference database formed by normal historical data at each moment, adopts the fault judgment rule at each moment to process real-time observation data at corresponding moment, fuses normal data in the real-time flight control data of the unmanned aerial vehicle into the reference database to further update the historical database, ensures the real-time characteristic of the reference database formed by the normal historical data by dynamically updating the reference database formed by the normal history and the fault judgment rule, and can effectively detect various abnormal forms such as isolated point abnormality, context abnormality, accumulation abnormality and the like in the flight control data of the unmanned aerial vehicle by utilizing the reference database formed by the dynamically updated normal historical data, therefore, the recall ratio and the accuracy of fault detection are effectively improved, and the false alarm rate is reduced.
Drawings
Fig. 1 is a flow chart of dynamic construction of a fault detection database of an unmanned aerial vehicle flight control system.
Detailed Description
The technical solution of the invention is explained in detail with reference to fig. 1. The invention provides a data-driven database construction method for solving the technical problem that fault detection of an unmanned aerial vehicle flight control system cannot adapt to abnormal detection requirements due to the fact that extraction of each fault feature is difficult to achieve, a historical database at each moment is trained in real time to obtain a fault judgment rule at each moment and a reference database formed by normal historical data at each moment is screened out, real-time observation data at corresponding moments are processed by adopting the fault judgment rule at each moment, normal data in the real-time flight control data of the unmanned aerial vehicle are merged into the reference database to further update the historical database, and real-time characteristics of the reference database formed by the normal historical data are guaranteed by dynamically updating the reference database and the fault judgment rule formed by the normal history.
Updating a reference database and a fault judgment rule at the current time t + 1:
(1) gather the data that unmanned aerial vehicle flight control system exported under current moment t +1, include: measurement data of three-axis gyroscope, GPS, accelerometer, barometer, etc., marked as matrix xt+1,xt+1Mixed data including normal data, known fault data and unknown fault data, and Kalman filtering algorithm is adopted to obtain real-time observation data x at current momentt+1Preprocessing is carried out to remove noise, false alarm caused by noise data interference abnormal detection is avoided, and preprocessed real-time observation data at the current moment are marked as
(2) Training offline data at the current time by adopting an artificial intelligence algorithm including but not limited to an artificial neural network and a decision tree for the offline duration data at the current time t +1 to obtain a fault judgment rule at the current time t +1, screening out a reference database consisting of normal historical data at the current time t +1, and marking a reference number consisting of the normal historical data at the current time t +1The database is a time series with a window length: { xt'-q+1,...,xt'+1T represents time, q represents the length of the window, and since no online data is input at time t0, that is, at the first time, the reference database formed by the normal data is the reference database formed by the real-time online normal data;
(3) judging the preprocessed real-time observation data at the current moment by adopting a fault judgment rule at the current moment t +1Whether it is faulty or not is judgedIn normal condition, a time sequence { x 'of window length is rejected by adopting a sliding window model with the window length of q't-q+1,...,x't+1Tail data x 'in }'t+1Will beThe addition at the end of the window length time series yields:that is, the reference database composed of the normal history data at the current time t +1 is updated toAnd then updating the offline data at the current moment for training at the next moment.
Updating the reference database and the failure judgment rule at the next moment and at each moment after the next moment:
training a fault judgment rule in real time according to the updated offline historical data, screening a reference database formed by normal historical data in real time, and processing the result of real-time observation data at the current moment according to the fault judgment rule trained in real time to update the reference database formed by the normal historical data on line.
Claims (4)
1. A database construction method for unmanned aerial vehicle flight control system fault detection is characterized in that,
collecting real-time observation data of an unmanned aerial vehicle flight control system at the current moment, training off-line duration data at the current moment by adopting an artificial intelligence algorithm to obtain a fault judgment rule at the current moment and screening out a reference database consisting of normal historical data at the current moment, judging whether the real-time observation data at the current moment is faulty or not by adopting the fault judgment rule at the current moment, expressing the reference database consisting of the normal historical data at the current moment by using a time sequence with a window length, eliminating tail data in the time sequence with the window length by adopting a sliding window model with the window length, adding the real-time observation data at the current moment to the tail of the time sequence with the window length, updating the off-line historical data, and repeatedly training out the fault judgment rule in real time according to the updated off-line historical data and screening out the reference database consisting of the normal historical data in real time, and processing the result of real-time observation data at the current moment according to a real-time trained fault judgment rule, and updating a reference database formed by normal historical data on line.
2. The method for constructing the database for detecting the faults of the flight control system of the unmanned aerial vehicle according to claim 1, wherein the real-time observation data of the flight control system of the unmanned aerial vehicle at the current moment comprises: and measuring data of a three-axis gyroscope, a GPS, an accelerometer and a barometer.
3. The method as claimed in claim 1, wherein before determining whether the real-time observation data at the current time has a fault according to the fault determination rule at the current time, noise in the real-time observation data at the current time is removed by using a kalman filter algorithm.
4. The method for constructing the database for detecting the faults of the flight control system of the unmanned aerial vehicle according to claim 1, wherein an artificial intelligence algorithm including but not limited to an artificial neural network and a decision tree is adopted to train offline duration data at the current time to obtain a fault judgment rule at the current time, and a reference database consisting of normal historical data at the current time is screened out.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611205514.6A CN106649727B (en) | 2016-12-23 | 2016-12-23 | Database construction method for fault detection of unmanned aerial vehicle flight control system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611205514.6A CN106649727B (en) | 2016-12-23 | 2016-12-23 | Database construction method for fault detection of unmanned aerial vehicle flight control system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106649727A CN106649727A (en) | 2017-05-10 |
CN106649727B true CN106649727B (en) | 2019-12-24 |
Family
ID=58826891
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611205514.6A Active CN106649727B (en) | 2016-12-23 | 2016-12-23 | Database construction method for fault detection of unmanned aerial vehicle flight control system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106649727B (en) |
Families Citing this family (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109085748A (en) * | 2017-06-13 | 2018-12-25 | 袁兵 | Unmanned aerial vehicle control system based on fault self-adapting study |
CN107272654B (en) * | 2017-07-21 | 2019-06-14 | 南京航空航天大学 | A kind of data clusters dimension reduction method for system for flight control computer fault detection |
CN109905286B (en) * | 2017-12-11 | 2021-10-12 | 北京京东乾石科技有限公司 | Method and system for monitoring running state of equipment |
US10931687B2 (en) | 2018-02-20 | 2021-02-23 | General Electric Company | Cyber-attack detection, localization, and neutralization for unmanned aerial vehicles |
CN108521571B (en) * | 2018-04-11 | 2021-01-01 | 上海小蚁科技有限公司 | SDI chip automatic detection method and device, storage medium and terminal |
CN109062183B (en) * | 2018-07-31 | 2021-05-11 | 杭州休伦科技有限公司 | New energy automobile remote monitoring analysis method and system |
CN109302444A (en) * | 2018-08-06 | 2019-02-01 | 佛山科学技术学院 | A kind of unmanned plane information collecting method and system based on block chain |
CN109800858B (en) * | 2018-12-21 | 2021-03-05 | 东软集团股份有限公司 | Application system abnormality detection method and device, readable storage medium and electronic equipment |
CN110429709B (en) * | 2019-07-19 | 2021-04-23 | 淮阴工学院 | Petrochemical enterprise power failure monitoring device and method based on OneNET cloud platform |
CN112945592B (en) * | 2019-12-10 | 2023-11-21 | 广州极飞科技股份有限公司 | Fault cause determining method and device |
CN111930094A (en) * | 2020-07-13 | 2020-11-13 | 北京航空航天大学 | Unmanned aerial vehicle actuator fault diagnosis method based on extended Kalman filtering |
CN112925344B (en) * | 2021-01-25 | 2022-01-04 | 南京航空航天大学 | Unmanned aerial vehicle flight condition prediction method based on data driving and machine learning |
CN113312809B (en) * | 2021-04-06 | 2022-12-13 | 北京航空航天大学 | Spacecraft telemetry data multi-parameter anomaly detection method based on related cluster division |
CN113537838A (en) * | 2021-08-16 | 2021-10-22 | 上海志茗航空科技有限公司 | Product full-data intelligent management system for large-load mooring unmanned aerial vehicle |
CN113514109A (en) * | 2021-08-18 | 2021-10-19 | 广东新创华科环保股份有限公司 | Unmanned aerial vehicle flight fault detection method and system |
CN113850138B (en) * | 2021-08-25 | 2024-03-22 | 哈尔滨工业大学 | Unmanned aerial vehicle sensor fault detection method, system and device based on data driving |
CN116882751B (en) * | 2023-07-19 | 2024-02-06 | 江苏锐天智能科技股份有限公司 | Equipment analysis system and method based on multi-source heterogeneous data fusion |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101963937A (en) * | 2010-09-29 | 2011-02-02 | 南京航空航天大学 | Method for predicting residual service life of flight control computer system |
CN102419593A (en) * | 2011-10-08 | 2012-04-18 | 济中节能技术(苏州)有限公司 | Sensor fault diagnosis method based on data mining |
CN102495949A (en) * | 2011-11-23 | 2012-06-13 | 西北工业大学 | Fault prediction method based on air data |
CN103279679A (en) * | 2013-06-09 | 2013-09-04 | 浪潮电子信息产业股份有限公司 | Data stream online prediction method based on chained rewritable window |
CN104091070A (en) * | 2014-07-07 | 2014-10-08 | 北京泰乐德信息技术有限公司 | Rail transit fault diagnosis method and system based on time series analysis |
CN104102773A (en) * | 2014-07-05 | 2014-10-15 | 山东鲁能软件技术有限公司 | Equipment fault warning and state monitoring method |
CN105183937A (en) * | 2015-07-17 | 2015-12-23 | 中国运载火箭技术研究院 | Fault diagnosis method suitable for electrical system of unmanned aerial vehicle |
CN106200629A (en) * | 2016-09-30 | 2016-12-07 | 山东科技大学 | The fault of a kind of UAV Flight Control System degree of detection can analyze method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060200278A1 (en) * | 2005-03-02 | 2006-09-07 | Honeywell International Inc. | Generic software fault mitigation |
-
2016
- 2016-12-23 CN CN201611205514.6A patent/CN106649727B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101963937A (en) * | 2010-09-29 | 2011-02-02 | 南京航空航天大学 | Method for predicting residual service life of flight control computer system |
CN102419593A (en) * | 2011-10-08 | 2012-04-18 | 济中节能技术(苏州)有限公司 | Sensor fault diagnosis method based on data mining |
CN102495949A (en) * | 2011-11-23 | 2012-06-13 | 西北工业大学 | Fault prediction method based on air data |
CN103279679A (en) * | 2013-06-09 | 2013-09-04 | 浪潮电子信息产业股份有限公司 | Data stream online prediction method based on chained rewritable window |
CN104102773A (en) * | 2014-07-05 | 2014-10-15 | 山东鲁能软件技术有限公司 | Equipment fault warning and state monitoring method |
CN104091070A (en) * | 2014-07-07 | 2014-10-08 | 北京泰乐德信息技术有限公司 | Rail transit fault diagnosis method and system based on time series analysis |
CN105183937A (en) * | 2015-07-17 | 2015-12-23 | 中国运载火箭技术研究院 | Fault diagnosis method suitable for electrical system of unmanned aerial vehicle |
CN106200629A (en) * | 2016-09-30 | 2016-12-07 | 山东科技大学 | The fault of a kind of UAV Flight Control System degree of detection can analyze method |
Non-Patent Citations (1)
Title |
---|
"基于MDARM和VxWorks的小型无人机执行器故障检测方法";鞠凤娟;《计算机测量与控制》;20150625;第23卷(第6期);第1912-1914,1918页 * |
Also Published As
Publication number | Publication date |
---|---|
CN106649727A (en) | 2017-05-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106649727B (en) | Database construction method for fault detection of unmanned aerial vehicle flight control system | |
CN107941537B (en) | A kind of mechanical equipment health state evaluation method | |
CN111274737A (en) | Method and system for predicting remaining service life of mechanical equipment | |
CN113469060A (en) | Multi-sensor fusion convolution neural network aeroengine bearing fault diagnosis method | |
CN104102773B (en) | A kind of equipment fault early-warning and state monitoring method | |
CN107272654B (en) | A kind of data clusters dimension reduction method for system for flight control computer fault detection | |
CN107622308B (en) | Power generation equipment parameter early warning method based on DBN (database-based network) | |
CN114738205B (en) | Method, device, equipment and medium for monitoring state of floating fan foundation | |
CN114118673A (en) | Workshop intelligent fault diagnosis early warning method based on digital twin technology | |
CN108427400A (en) | A kind of aircraft airspeed pipe method for diagnosing faults based on neural network Analysis design | |
CN116228186A (en) | Ship cabin intelligent operation and maintenance system based on human engineering | |
CN110851422A (en) | Data anomaly monitoring model construction method based on machine learning | |
CN109359662A (en) | A kind of multilayer Bayesian network method for diagnosing faults based on causality analysis towards gigawatt extra-supercritical unit non-stationary property | |
CN113496061A (en) | SOM network clustering electromechanical device bearing fault analysis method based on transfer learning and manifold distance | |
CN115577860A (en) | Intelligent maintenance method and system for rail transit based on adaptive control | |
Xu et al. | New RUL prediction method for rotating machinery via data feature distribution and spatial attention residual network | |
CN107860420A (en) | A kind of large and complex structure health monitoring systems based on multi-main body cooperation | |
Xiao et al. | A review of fault diagnosis methods based on machine learning patterns | |
CN113593605B (en) | Industrial audio fault monitoring system and method based on deep neural network | |
CN117217097B (en) | Method and system for constructing digital twin body of ship industry in platformization mode | |
CN111894946B (en) | Equipment hydraulic system fault prediction method based on combat intensity and environment | |
CN108830291A (en) | A kind of wheeled crane Fault Diagnosis Methods for Hydraulic System and system | |
Yuan et al. | The application analysis of fault diagnosis with artificial Intelligent for industrial equipment | |
CN113850138B (en) | Unmanned aerial vehicle sensor fault detection method, system and device based on data driving | |
CN114330413A (en) | Fault type identification and positioning method for traction motor bearing |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |