CN108711005A - Flight risk analysis method based on QAR data and Bayesian network - Google Patents
Flight risk analysis method based on QAR data and Bayesian network Download PDFInfo
- Publication number
- CN108711005A CN108711005A CN201810457721.3A CN201810457721A CN108711005A CN 108711005 A CN108711005 A CN 108711005A CN 201810457721 A CN201810457721 A CN 201810457721A CN 108711005 A CN108711005 A CN 108711005A
- Authority
- CN
- China
- Prior art keywords
- bayesian network
- node
- risk
- flight
- qar data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000012502 risk assessment Methods 0.000 title claims abstract description 17
- 238000004458 analytical method Methods 0.000 abstract description 15
- 238000013139 quantization Methods 0.000 abstract description 4
- 235000013350 formula milk Nutrition 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 description 1
- 241000208340 Araliaceae Species 0.000 description 1
- 238000000342 Monte Carlo simulation Methods 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Probability & Statistics with Applications (AREA)
- Life Sciences & Earth Sciences (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention relates to aviation safety technical fields, disclose a kind of flight risk analysis method based on QAR data and Bayesian network, include the following steps:1) flight risk key parameter is extracted;2) it determines Bayesian network node, defines the calculating bore of each node;3) Bayesian network is built;4) conditional probability of the prior probability of root node and intermediate node in Bayesian network is determined;5) one section of QAR data is read, its risk factors generating state is input in Bayesian network, obtains object event probability of happening.Present invention introduces Bayesian networks to establish risk analysis model using the point of key risk of quantization as the node of Bayesian network.The prior probability of network is determined with a large amount of history QAR data, established network structure can be used to carry out positive rational analysis and reversed diagnostic analysis, can more fully be assessed the incidence relation between specific unsafe incidents and risk factors.
Description
Technical field
The present invention relates to aviation safety technical field more particularly to a kind of flight risk analysis methods.
Background technology
In recent years, air-transport industry is quickly grown, and air services total amount is constantly promoted.Aviation safety is that civil aviaton is most important
One of content ensures that aviation safety is that aircraft industry develops eternal theme.Flight risk refers to during the entire process of aircraft flight,
One or more factors trigger under certain conditions, lead to the event that transfinites of flying, cause the consequence of different menace levels.
Aviation flight risk factors have very strong incidence relation with target unsafe incidents, and therefore, aviation flight risk Factor Analysis is
As aircraft industry focus of attention problem.
There are many data acquisition equipments for installation on aircraft, can obtain the various parameters in aircraft flight, such as height,
The indexs such as air speed, rod volume.Wherein quick access recorder (Quick Access Recorder, QAR)
Due to the features such as its own is easy to storage, sample frequency is high, recording parameters are more, be typically used to flight transfinites data
The analysis in the fields such as event detection, flight attributional analysis, maintenance failure detection;But since flight risk factor is difficult to confirm
Relationship is complicated between quantization, risk factors and target unsafe incidents so that carries out flight risk by QAR data at present
Analysis also has larger limitation.Analysis typically for flight risk also rests on qualitative analysis level, such as wind
The result that dangerous source classified, is generated for risk factors is assessed.The existing research to flight risk analysis includes such as
Under:
Traffic information proposes a kind of schedule flight safety risk estimating method with safety (02 phase in 2013).According to flight
Flight characteristic establishes 4 grades of index systems of assessment schedule flight security risk in terms of people, machine, ring, pipe 4.Using level
Analytic approach and the method parameter weight for introducing ambiguity function, establish flight value-at-risk computation model.
From the angle of risk, the correlation for analyzing flight risk emphatically is special for Chinese management informationization (15 phases in 2016)
Sign and Type division.
Nanjing Aero-Space University's journal (04 phase in 2015) proposes a kind of engine wind based on fault statistics data
Dangerous prediction technique, according to engine failure dangerous grade classification, danger coefficient is determining, calculating sides of risks and assumptions and flight risk
Method establishes the engine multiple faults pattern risk assessment flow based on Monte-Carlo Simulation, and a situation arises for prediction engine failure,
Assess the failure risk of engine service stage.
The system engineering theory proposes a kind of high-risk thing of low frequency being based on extreme value theory (EVT) with (02 phase in 2013) is put into practice
Part quantitative evaluating method improves common linear model in extreme value theory using Non-linear Optimal Model.For pole
It is worth the identification of sample distribution Model Parameter, sensor fault risk probability is finally added to the Ma Er for having driver to respond link
Section's husband's process model carries out dynamic quantitative assessment to flight control system risk probability.
The method for making a general survey of above-mentioned flight risk analysis, most methods are with more abstract probability value or qualitative risk
Grade is basic data, focuses on the assessment and quantization to risk probability.But the generation of unsafe incidents often with it is all windy
Dangerous factor is related.For the incidence relation between specific unsafe incidents and risk factors, how to be assessed and studied, really
Determine influence degree of the risk factors to unsafe incidents, improves the attention dynamics to important risk, do not related in existing research
And.
Invention content
In view of this, the purpose of the present invention is to provide a kind of flight risks based on QAR data and Bayesian network point
Analysis method, data source is reliable, method is easily achieved, and analysis result is easily explained.
In order to achieve the above objectives, the present invention provides the following technical solutions:
Flight risk analysis method based on QAR data and Bayesian network, includes the following steps:
1) flight risk key parameter is extracted;
2) it determines Bayesian network node, defines the calculating bore of each node;
3) Bayesian network is built;
4) conditional probability of the prior probability of root node and intermediate node in Bayesian network is determined;
5) one section of QAR data is read, its risk factors generating state is input in Bayesian network, obtains object event
Probability of happening.
Further, the step 1) specifically comprises the following steps:
11) QAR data are pre-processed, unified dimension and frequency acquisition;
12) similarity cluster is carried out to pretreated QAR data;
13) nuisance parameter is rejected to cluster result combination industry experience and flight characteristics, successive ignition finally obtains flight
Risk key parameter.
Further, in the step 2), risk factors are chosen as Bayesian network node.
Further, in the step 3), it is first determined the relationship that influences each other between node, then according between node
The relationship that influences each other builds Bayesian network.
The beneficial effects of the present invention are:Bayesian network is introduced, using the point of key risk of quantization as Bayesian network
Node, establish risk analysis model.The prior probability of network is determined with a large amount of history QAR data, can be used and be established
Network structure carry out positive rational analysis and reversed diagnostic analysis, can more fully assess specific unsafe incidents
Incidence relation between risk factors.
Description of the drawings
In order to keep the purpose of the present invention, technical solution and advantageous effect clearer, the present invention provides following attached drawing:
Fig. 1 is the flow diagram of the flight risk analysis method based on QAR data and Bayesian network;
Fig. 2 is the bayesian network structure schematic diagram of embodiment.
Specific implementation mode
Below in conjunction with attached drawing, the preferred embodiment of the present invention is described in detail, but illustrated embodiment not as
Limitation of the invention.
The flight risk analysis method based on QAR data and Bayesian network of the present embodiment, includes the following steps:
1) flight risk key parameter is extracted;Since different phase risk factors are different in aircraft flight, occur
Unsafe incidents it is different;In the present embodiment, chooses landing period and carry out risk analysis to extract key parameter.Landing period takes
Sections of the 60S and rear 30S as analysis before the vacant lot switching moment.
Ts=Time-60s;
When Air/Gnd SW=On Ground (0);
Te=Time+30s;
Wherein Ts indicates that landing period start time, Te indicate that landing period finish time, Time are to be indicated in QAR data
The parameter of time;Air/Gnd SW are to indicate aircraft air-ground switch parameter.According to this formula, we can cut in QAR data
Take our required parts.Specifically comprise the following steps:
11) in order to improve the validity and accuracy of follow-up clustering algorithm, QAR data are pre-processed, unified dimension
And frequency acquisition.
The transformation for mula of dimension is as follows:
For the mean value of k-th variable,For the standard deviation of k-th variable,For the k-th scalar after standardization
I-th of data.By the transformation, different magnitude indexs are transformed to parameter similar in numerical value by us.Parameter acquisition frequency is unified for
1s is each.
12) similarity cluster is carried out to pretreated QAR data;
Clustering algorithm uses hierarchical clustering algorithm, and clustering distance is chosen for Euclidean distance between parameter.The choosing of clustering distance
It takes, we select Euclidean distance, the formula that Euclidean distance calculates as follows:
In above-mentioned formula, d represents the Euclidean distance between two indexes, xmiIt is represented as m-th of index, i-th of parameter value,
xniIt is represented as n-th of index, i-th of parameter value.The distance between parameter value forms the similarity matrix between variable.
13) brief to step (12) cluster result progress parameter, i.e.,:Redundancy ginseng is rejected in conjunction with industry experience and flight characteristics
Number, successive ignition finally obtain flight risk key parameter.Yojan is carried out according to similitude sequence to step (12) result.
These three parameter similarities of vertical speed, normal acceleration and the radio altitude of aircraft are more than 99%;Aircraft vertical speed pair
The derivative of flight time obtains normal acceleration, and vertical speed quadratures to the time and flying height can be obtained.Therefore, this group of phase
Parameter like degree more than 99% only retains vertical speed.
2) it determines Bayesian network node, defines the calculation or bore of each node;Specifically comprise the following steps:
21) according to expertise and historgraphic data recording, risk factors can be divided into fuselage state, personnel's operation, the external world
Environment three classes;Choose node of the important risk factor as Bayesian network.In the present embodiment, it chooses into runway elevation,
Land posture, rate of descent change, pull rod is too quickly, wind direction, light are as Bayesian network node, and target unsafe incidents are attached most importance to
Land.
22) for the node determined in step 21), its classification is defined according to the distribution of each parameter in the historical data one by one
Calculating bore corresponding to state and different classifications state.Such as " into runway elevation " node, classification state for "high" " in "
" low ":
It is indicated when state is "high":Radio altitude when being in runway vertical plane using aircraft position as judge according to
According to, R_alt (radio altitude, the key parameter) > extracted in S1;60ft;
When state be " in " when indicate:40ft<R_alt<60ft;
It is indicated when state is " low ":R_alt<60ft.
" wind direction " node, classification state are " with the wind " " contrary wind ", when state is indicates when " with the wind ", in landing period,
The maximum value S1< of wind direction and the angle in course;60°.It is as shown in table 1 that each node calculates bore simply definition.
1 parameter definition of table
3) context-aware analysis is carried out to landing period, determines the relationship that influences each other between node, build Bayesian network
Network structure.In the present embodiment model, our independent counterweight landing events are analyzed with factor quantity of reducing risks, and are improved and are divided
The precision of analysis.Aircraft state chooses two parameters as node, respectively P1:Into runway elevation, P2:Landing attitude;It is artificial because
Element chooses two parameters as node, and respectively H1, pull rod be too quickly, H2:Rate of descent changes;Environmental factor is chosen two parameters and is made
For node, E1:Wind direction, E2:Light.The main unsafe incidents of landing period are S1:It lands again;Meanwhile unsafe incidents occur
Middle concern to the injury of people, the damage of aircraft.Accordingly establish two nodes:HE1,PE1.
31) it is an important reference factor during aircraft landing into runway elevation, aircraft is from runway head with certain
Angle land according to glide path.If excessively high into runway elevation, unit is to prevent from remaining runway too short or rush to deflect away from runway,
Landing angle need to be increased;If too low into runway elevation, pilot needs quick pull rod control aircraft rate of descent.And light then may be used
It can be the factor for influencing aircraft into runway elevation.When the aircraft landing moment encounter it is more strong with the wind or when contrary wind, it is complicated
Environment can influence the landing attitude and rate of descent of aircraft, and pilot needs to control rate of descent and posture by pull rod operation.
32) by the analysis to landing period and landing interdependent node again in step 31), bayesian network structure is obtained
As shown in Figure 2.
4) conditional probability of the prior probability of root node and intermediate node in Bayesian network is determined;It is gone through mainly in combination with combining
History QAR data are determined with Heuristics.Part of nodes probability tables are as shown in the table:
2 root node probability tables of table
3 intermediate node of table " rate of descent " conditional probability table
5) one section of QAR data is read, its risk factors generating state is input in Bayesian network, obtains object event
Probability of happening.In the present embodiment model, influence the node to land again there are six:Pattra leaves can be obtained in P1, P2, H1, H2, E1, E2
The total probability formula of this network model is:
P (P1, P2, H1, H2, E1, E2, S1)=P (E1) P (E2) P (H2|E1)P(P2|E1)P(P1|E2)P(H1|H2,
P1)P(S1|P2,H1)
With above-mentioned formula, the reasoning of object event probability of happening can be carried out with input node state.
51) forward reasoning is analyzed:In forward reasoning analysis, we set the state of each node successively, are weighed
The probability that land event occurs.Node state can also be combined, reasoning is landed the possibility of generation again, such as from a certain boat
Class QAR data in acquire, the flight land when in contrary wind environment, the time be 11 points of the late into the night, be into runway elevation
45ft;Using factors above as the evidence input in network, it can significantly observe that again landing event occurrence rate is promoted.
52) reverse diagnosis is analyzed:On having built the structure of Bayesian network, different case can be set, with mould
The reason of type diagnostic event occurs.
Finally illustrate, preferred embodiment above is merely illustrative of the technical solution of the present invention and unrestricted, although logical
It crosses above preferred embodiment the present invention is described in detail, however, those skilled in the art should understand that, can be
Various changes are made to it in form and in details, without departing from claims of the present invention limited range.
Claims (4)
1. the flight risk analysis method based on QAR data and Bayesian network, it is characterised in that include the following steps:
1) flight risk key parameter is extracted;
2) it determines Bayesian network node, defines the calculating bore of each node;
3) Bayesian network is built;
4) conditional probability of the prior probability of root node and intermediate node in Bayesian network is determined;
5) one section of QAR data is read, its risk factors generating state is input in Bayesian network, object event is obtained
Probability.
2. the flight risk analysis method according to claim 1 based on QAR data and Bayesian network, feature exist
In the step 1) specifically comprises the following steps:
11) QAR data are pre-processed, unified dimension and frequency acquisition;
12) similarity cluster is carried out to pretreated QAR data;
13) nuisance parameter is rejected to cluster result combination industry experience and flight characteristics, successive ignition finally obtains flight risk
Key parameter.
3. the flight risk analysis method based on QAR data and Bayesian network as described in claim 1, it is characterised in that:
In the step 2), risk factors are chosen as Bayesian network node.
4. the flight risk analysis method based on QAR data and Bayesian network as described in claim 1, it is characterised in that:
In the step 3), it is first determined the relationship that influences each other between node, then according to the relationship structure that influences each other between node
Build Bayesian network.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810457721.3A CN108711005A (en) | 2018-05-14 | 2018-05-14 | Flight risk analysis method based on QAR data and Bayesian network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810457721.3A CN108711005A (en) | 2018-05-14 | 2018-05-14 | Flight risk analysis method based on QAR data and Bayesian network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108711005A true CN108711005A (en) | 2018-10-26 |
Family
ID=63868186
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810457721.3A Pending CN108711005A (en) | 2018-05-14 | 2018-05-14 | Flight risk analysis method based on QAR data and Bayesian network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108711005A (en) |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109978168A (en) * | 2019-03-19 | 2019-07-05 | 北京瑞斯克企业管理咨询有限公司 | The origin cause of formation automated reasoning method and system of landing again based on timing QAR parameter curve cluster |
CN110533095A (en) * | 2019-08-27 | 2019-12-03 | 中国民航大学 | A kind of schedule flight risk behavior recognition methods based on improvement random forest |
CN110807580A (en) * | 2019-10-25 | 2020-02-18 | 上海建科工程咨询有限公司 | Method for analyzing key safety risk of super high-rise construction machinery based on complex network |
CN110991883A (en) * | 2019-12-03 | 2020-04-10 | 中国民用航空总局第二研究所 | Operation control system and method based on flight risk preposition |
CN111008669A (en) * | 2019-12-10 | 2020-04-14 | 北京航空航天大学 | Deep learning-based heavy landing prediction method |
CN111047222A (en) * | 2019-12-30 | 2020-04-21 | 四川函钛科技有限公司 | Grounding time point judgment method based on time sequence QAR parameter |
CN111210668A (en) * | 2019-12-30 | 2020-05-29 | 四川函钛科技有限公司 | Landing stage flight trajectory offset correction method based on time sequence QAR parameter |
CN111477036A (en) * | 2020-04-08 | 2020-07-31 | 中国电子科技集团公司第二十八研究所 | Method for detecting aircraft height abnormity of air traffic control automation system |
CN111553411A (en) * | 2020-04-27 | 2020-08-18 | 中国民航大学 | Pilot risk portrait method based on multidimensional quantitative data |
CN111626327A (en) * | 2020-04-15 | 2020-09-04 | 中国电子产品可靠性与环境试验研究所((工业和信息化部电子第五研究所)(中国赛宝实验室)) | Airplane heavy landing prediction method and device, computer equipment and storage medium |
CN112488375A (en) * | 2020-11-25 | 2021-03-12 | 东南大学 | Traffic operation risk prediction method and system |
CN113015308A (en) * | 2021-03-17 | 2021-06-22 | 中国科学技术大学 | Plasma current calculation method and device |
CN113284340A (en) * | 2021-05-14 | 2021-08-20 | 交通运输部科学研究院 | Road traffic safety grading system |
CN113379331A (en) * | 2021-07-19 | 2021-09-10 | 中国民航大学 | Flight operation risk network construction and control method based on unsafe events |
CN113807649A (en) * | 2021-07-30 | 2021-12-17 | 浙江工商大学 | Civil aviation flight safety assessment system based on Bayesian network |
CN113850931A (en) * | 2021-11-29 | 2021-12-28 | 武汉大学 | Flight feature extraction method for flight abnormity |
CN114638298A (en) * | 2022-03-15 | 2022-06-17 | 天津大学 | Aircraft attack behavior prediction method and electronic equipment |
CN115293225A (en) * | 2022-06-17 | 2022-11-04 | 重庆大学 | Pilot flat drift ejector rod cause analysis method and device |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070011113A1 (en) * | 2005-03-17 | 2007-01-11 | Ali Mosleh | System and methods for assessing risk using hybrid causal logic |
CN104267415A (en) * | 2014-09-23 | 2015-01-07 | 北京航空航天大学 | Fault identification method and device based on Bayesian decision theory |
-
2018
- 2018-05-14 CN CN201810457721.3A patent/CN108711005A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070011113A1 (en) * | 2005-03-17 | 2007-01-11 | Ali Mosleh | System and methods for assessing risk using hybrid causal logic |
CN104267415A (en) * | 2014-09-23 | 2015-01-07 | 北京航空航天大学 | Fault identification method and device based on Bayesian decision theory |
Non-Patent Citations (3)
Title |
---|
孙瑞山等: "航班起飞阶段QAR关键参数提取研究", 《综合运输》 * |
曹惠玲等: "基于贝叶斯网络的航空发动机燃油泵故障诊断", 《中国民航大学学报》 * |
黄玉洁等: "基于改进贝叶斯模型的信息安全风险评估", 《计算机与现代化》 * |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109978168A (en) * | 2019-03-19 | 2019-07-05 | 北京瑞斯克企业管理咨询有限公司 | The origin cause of formation automated reasoning method and system of landing again based on timing QAR parameter curve cluster |
CN110533095A (en) * | 2019-08-27 | 2019-12-03 | 中国民航大学 | A kind of schedule flight risk behavior recognition methods based on improvement random forest |
CN110533095B (en) * | 2019-08-27 | 2023-01-17 | 中国民航大学 | Flight risk behavior identification method based on improved random forest |
CN110807580B (en) * | 2019-10-25 | 2022-03-04 | 上海建科工程咨询有限公司 | Method for analyzing key safety risk of super high-rise construction machinery based on complex network |
CN110807580A (en) * | 2019-10-25 | 2020-02-18 | 上海建科工程咨询有限公司 | Method for analyzing key safety risk of super high-rise construction machinery based on complex network |
CN110991883A (en) * | 2019-12-03 | 2020-04-10 | 中国民用航空总局第二研究所 | Operation control system and method based on flight risk preposition |
CN110991883B (en) * | 2019-12-03 | 2022-05-20 | 中国民用航空总局第二研究所 | Operation control system and method based on flight risk preposition |
CN111008669A (en) * | 2019-12-10 | 2020-04-14 | 北京航空航天大学 | Deep learning-based heavy landing prediction method |
CN111210668A (en) * | 2019-12-30 | 2020-05-29 | 四川函钛科技有限公司 | Landing stage flight trajectory offset correction method based on time sequence QAR parameter |
CN111047222B (en) * | 2019-12-30 | 2023-04-28 | 四川函钛科技有限公司 | Grounding time point judging method based on timing sequence QAR parameter |
CN111047222A (en) * | 2019-12-30 | 2020-04-21 | 四川函钛科技有限公司 | Grounding time point judgment method based on time sequence QAR parameter |
CN111210668B (en) * | 2019-12-30 | 2022-02-15 | 四川函钛科技有限公司 | Landing stage flight trajectory offset correction method based on time sequence QAR parameter |
CN111477036A (en) * | 2020-04-08 | 2020-07-31 | 中国电子科技集团公司第二十八研究所 | Method for detecting aircraft height abnormity of air traffic control automation system |
CN111477036B (en) * | 2020-04-08 | 2021-01-29 | 中国电子科技集团公司第二十八研究所 | Method for detecting aircraft height abnormity of air traffic control automation system |
CN111626327A (en) * | 2020-04-15 | 2020-09-04 | 中国电子产品可靠性与环境试验研究所((工业和信息化部电子第五研究所)(中国赛宝实验室)) | Airplane heavy landing prediction method and device, computer equipment and storage medium |
CN111553411A (en) * | 2020-04-27 | 2020-08-18 | 中国民航大学 | Pilot risk portrait method based on multidimensional quantitative data |
CN112488375A (en) * | 2020-11-25 | 2021-03-12 | 东南大学 | Traffic operation risk prediction method and system |
CN113015308A (en) * | 2021-03-17 | 2021-06-22 | 中国科学技术大学 | Plasma current calculation method and device |
CN113015308B (en) * | 2021-03-17 | 2022-07-15 | 中国科学技术大学 | Plasma current calculation method and device |
CN113284340A (en) * | 2021-05-14 | 2021-08-20 | 交通运输部科学研究院 | Road traffic safety grading system |
CN113284340B (en) * | 2021-05-14 | 2022-11-01 | 交通运输部科学研究院 | Road traffic safety grading system |
CN113379331B (en) * | 2021-07-19 | 2022-03-25 | 中国民航大学 | Flight operation risk network construction and control method based on unsafe events |
CN113379331A (en) * | 2021-07-19 | 2021-09-10 | 中国民航大学 | Flight operation risk network construction and control method based on unsafe events |
CN113807649A (en) * | 2021-07-30 | 2021-12-17 | 浙江工商大学 | Civil aviation flight safety assessment system based on Bayesian network |
CN113850931A (en) * | 2021-11-29 | 2021-12-28 | 武汉大学 | Flight feature extraction method for flight abnormity |
CN114638298A (en) * | 2022-03-15 | 2022-06-17 | 天津大学 | Aircraft attack behavior prediction method and electronic equipment |
CN115293225A (en) * | 2022-06-17 | 2022-11-04 | 重庆大学 | Pilot flat drift ejector rod cause analysis method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108711005A (en) | Flight risk analysis method based on QAR data and Bayesian network | |
US11501039B2 (en) | Optimizing aircraft flows at airports using data driven predicted capabilities | |
Olive et al. | Detection and identification of significant events in historical aircraft trajectory data | |
US9196165B2 (en) | Assessing feasibility of an aircraft trajectory | |
US11922817B2 (en) | 4-dimensional trajectory regulatory decision-making method for air traffic | |
Li et al. | Civil aircraft big data platform | |
EP4024370A1 (en) | Decision-support system for aircraft requiring emergency landings | |
Deshmukh et al. | Incremental-learning-based unsupervised anomaly detection algorithm for terminal airspace operations | |
Murça et al. | A data-driven probabilistic trajectory model for predicting and simulating terminal airspace operations | |
Singh et al. | Real-time unstable approach detection using sparse variational gaussian process | |
Deshmukh et al. | Temporal logic learning-based anomaly detection in metroplex terminal airspace operations | |
Deshmukh et al. | Data-driven precursor detection algorithm for terminal airspace operations | |
Gillet et al. | Enhancement in realism of ATC simulations by improving aircraft behaviour models | |
Silagyi II et al. | Prediction of severity of aviation landing accidents using support vector machine models | |
Diallo | A predictive aircraft landing speed model using neural network | |
Gluck et al. | Too fast, too low, and too close: Improved real time safety assurance of the national airspace using long short term memory | |
Janakiraman et al. | Using ADOPT algorithm and operational data to discover precursors to aviation adverse events | |
Deshmukh | Data-Driven Anomaly and Precursor Detection in Metroplex Airspace Operations | |
Zeng et al. | [Retracted] Analysis of Abnormal Flight and Controllers Data Based on DBSCAN Method | |
Chen et al. | A deep learning method for landing pitch prediction based on flight data | |
Luo et al. | An Aircraft Fuel Flow Model of Cruise Phase Based on LSTM and QAR Data | |
Zhang et al. | Runway visual range prediction based on ensemble learning | |
Saintis et al. | Computing in-service aircraft reliability | |
Jiang et al. | A method for the outlier flights detection of the final approach based on FOQA data | |
Rohani et al. | Machine Learning Approach for Aircraft Performance Model Parameter Estimation for Trajectory Prediction Applications |
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 |