CN109598815A - A kind of estimation of Fuel On Board system oil consumption and health monitor method - Google Patents
A kind of estimation of Fuel On Board system oil consumption and health monitor method Download PDFInfo
- Publication number
- CN109598815A CN109598815A CN201811472311.2A CN201811472311A CN109598815A CN 109598815 A CN109598815 A CN 109598815A CN 201811472311 A CN201811472311 A CN 201811472311A CN 109598815 A CN109598815 A CN 109598815A
- Authority
- CN
- China
- Prior art keywords
- fuel
- data
- fuel flow
- flight
- failure
- 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
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0808—Diagnosing performance data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/006—Indicating maintenance
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Feedback Control In General (AREA)
Abstract
The present invention relates to a kind of estimation of Fuel On Board system oil consumption and health monitor methods.The present invention is the following steps are included: data sample is handled；Oil consumption estimation model being built and training；Fuel flow predicted value integrates entire segment, can obtain the predicted value of the fuel consumption total amount of flight flight with the flight time to mark；On the basis of the fuel flow model of acquisition, increase output layer the channel of flight failure and anomalous event；The training data sample that will acquire is input in the 4th step in improved fuel flow model as training sample, is trained, and airplane fault and abnormal fuel flow model can be monitored according to airplane data by obtaining；Packet loss, the unmarked failure of additions and deletions processing and abnormal data will only be carried out to be input in the 5th step in improved fuel flow model as test data, unknown failure and abnormal data can be monitored.
Description
Technical field
The invention belongs to Aviation Fuel system regions, it is related to a kind of Fuel On Board system oil consumption estimation and health monitoring side
Method.
Background technique
For company, civil aviaton, aviation fuel cost control and fuel system operational safety are one of its most concerned content, state
Inside and outside airline expands the work and research of fuel system around fuel-economizing, and how to improve aviation fuel cost control ability becomes
The important topic of airline.Basic ideas are to establish aircraft consumption by analyzing and researching to the factor for influencing aviation fuel consumption
Oil estimation model reduces oil consumption cost to improve flight plan course fuel oil estimated accuracy.Meanwhile to fuel system
Failure is completed with abnormal monitoring with aspect, the self-test software and hardware that health monitor method mainly passes through fuel system is isolated.
Existing oil consumption estimation method is to estimate cruise section oil consumption mostly, the oil consumption of unpredictable airline operation overall process, and
Short-term flight a big chunk fuel consumption depends on take-off climb landing phases, therefore these methods are not suitable for work
Journey practical application.These methods also seldom in view of influence of the factors to oil consumption such as meteorology, horizontal plane motion, acceleration, consider
Factor is not comprehensive, does not consider the influence of meteorological (wind, temperature) to fuel oil, the less decaying of consideration engine performance, fuselage light generally
Oil consumption rate caused by clean property is deteriorated is promoted.To failure of fuel system and abnormal monitoring be isolated in terms of, health monitor method
Health and fitness information mainly is provided to onboard maintenance system by the self-testing software of fuel system itself, fails to make full use of aircraft
Flying quality, also have a certain upgrade space.
Summary of the invention
The object of the present invention is to provide a kind of Fuel On Board system oil consumption estimation based on flying quality analysis and health prisons
Survey method is analyzed and researched to the factor for influencing aviation fuel consumption, is built for the aviation fuel consumption that accurate prediction flight navigation needs
Vertical aircraft oil consumption estimates model, to improve flight plan course fuel oil estimated accuracy, reduces oil consumption cost；Meanwhile using fuel oil
The system failure and abnormal data train the model, realize through flying quality to fuel system incipient fault and abnormal monitoring.
The technical scheme is that a kind of Fuel On Board system oil consumption estimation and health monitor method, including following step
It is rapid:
Step 1: data sample is handled:
1.1) packet loss, additions and deletions processing are carried out to flight initial data, forms complete available flight initial data, further according to
Failure of fuel system and anomalous event record data complete the label to flight initial data；
1.2) extract flight initial data slide, take-off climb, cruise, the flying quality of decline stage, as subsequent
Data sample needed for the training and test of model；
Step 2: oil consumption estimation model being built and training:
2.1) data sample confirmed in the first step is standardized, removes the number in the different channels of data sample
According to the influence of unit difference；
2.2) for standardization after data sample, determine fuel flow model be BP neural network, several input layers and
Output layer neuron, M hidden neuron, hidden layer transfer function select tanh sigmoid functionOutput layer passes
Defeated function selects Log-Sigmoid functionWherein, a is function output, and e is natural constant, and n is function input.BP mind
Through network input layer and the specific data channel of output layer number view, it needs to be determined that, M regards specific input layer channel number and determines, generally
It is 1 to 2 times of input layer port number；The BP neural network includes input layer, output layer, hidden layer；
2.3) it is used using extracted training data sample in 1.2) as training fuel flow model, training is inputted
Levenberg-Marquardt algorithm；
2.4) by extracted test data sample input step 2.3 in 1.2)) in fuel flow model, obtain fuel oil
Traffic prediction value；
Step 3: the fuel flow predicted value that will be obtained in step 2.4), is label with the flight time, to entire segment into
Row integral, can obtain the predicted value of the fuel consumption total amount of flight flight.
Step 4: obtain in the step 2.2) fuel flow model on the basis of, to output layer increase flight failure and
The channel of anomalous event；
Step 5: being input to using the training data sample obtained in step 1.2) as training sample improved in the 4th step
It in fuel flow model, is trained, airplane fault and abnormal fuel flow model can be monitored according to airplane data by obtaining.
Step 6: step 1.1) only to be carried out to packet loss, the unmarked failure of additions and deletions processing and abnormal data as test
Data are input in the 5th step in improved fuel flow model, can be monitored to unknown failure and abnormal data.
The beneficial effects of the present invention are: the aircraft fuel oil discharge model that the present invention establishes can be according to history flying quality, essence
The really aviation fuel consumption that prediction navigation needs, is precisely instructed for aircraft fuel oil carrying amount, to improve flight plan course
Fuel oil service efficiency reduces oil consumption cost；Meanwhile with flight failure and anomalous event data training pattern, realization passes through flight
Data can be greatly decreased aircraft fuel system failure and abnormal maintenance positioning time, mention to incipient fault and abnormal monitoring
High maintenance efficiency reduces maintenance cost, increases in-service time of the aircraft within the period of being on active service, improves the service efficiency of aircraft.With
The development of domestic civil aviaton's industry and transport service, the demand to aircraft oil consumption estimation and health monitoring is increasing, and the present invention has
Very big application prospect.
Detailed description of the invention
Fig. 1 is fuel flow model schematic
Fig. 2 is the calculating of fuel oil total amount
Fig. 3 is reference model oil consumption estimation figure (take-off climb stage)
Fig. 4 is fuel flow model oil consumption of the present invention estimation figure (take-off climb stage)
Fig. 5 is reference model oil consumption estimation figure (cruising phase)
Fig. 6 is fuel flow model oil consumption of the present invention estimation figure (cruising phase)
Fig. 7 is reference model oil consumption estimation figure (decline stage)
Fig. 8 is fuel flow model oil consumption of the present invention estimation figure (decline stage)
Fig. 9 is reference model oil consumption estimation figure (coast period)
Figure 10 is fuel flow model oil consumption of the present invention estimation figure (coast period)
Specific embodiment
The following further describes the specific embodiments of the present invention with reference to the drawings.
The technical scheme is that a kind of Fuel On Board system oil consumption estimation and health monitor method, including following step
It is rapid:
Step 1: data sample is handled:
1.1) packet loss, additions and deletions processing are carried out to flight initial data, forms complete available flight initial data, further according to
Failure of fuel system and anomalous event record data complete the label to flight initial data；
The present invention is using certain flight QAR partial data of BOEING type (737-300) as experimental data base.QAR
About 250 parameters of data record, parameter include the important parameters such as engine parameter, air speed, ground velocity, pressure altitude, there is analog quantity,
Also there are digital signal, switching value etc..These parameters from aircraft state monitoring system (ACMS), record be practical flight when
Parameter value is recorded 1 time, is recorded 1 time within some parameter spaces 4 seconds for some parameters 1 second.
Numbering scheme is used to the label of failure and abnormal data, for example, sharing 10 kinds of failures, is then encoded labeled as 10,
When certain failure occurs, then correspondence markings are " 1 ", are otherwise labeled as " 0 ", then each flight initial data can be labeled.
1.2) extract flight initial data slide, take-off climb, cruise, the flying quality of decline stage, as subsequent
Data sample needed for the training and test of model；
The data item for needing to extract and handle includes but is not limited to (parameter identification is similarly hereinafter) shown in table 1.
1 experimental data parameter list of table
The present invention calculates fuel consumption by mission phase, and aircraft has larger difference in different mission phase flight characteristics,
Oil consumption characteristic is not also identical.Complete plot of route is slided, climbs, cruises, declines 4 ranks by model established by the present invention
Section, is respectively trained it, (slide point take-off run and landing is slided), and different phase applies the different sampling intervals.
ff1、ff2(left and right fuel flow, similarly hereinafter) determines that functional relation exists by parameters such as speed, height, aircraft weights
Each mission phase is different, and the factor that each mission phase influences fuel flow is also different.Thus point mission phase is needed to count
Calculate fuel consumption.
The division of mission phase: with the division such as flying height (practical flight height), pitch angle, air speed.Different flight ranks
Duan Feihang oil consumption feature is different, aircraft fly and take off on air route land when, wind speed and direction influences its oil consumption very big；Fly
Machine horizontal plane motion also can oil consumption to balance turning when increased resistance；Aircraft raising and lowering velocity variations speed also can shadow
Oil consumption is rung, horizontally velocity variations speed also influences oil consumption.Thus fuel flow model increases according to real airplane motion situation
Add and considers wind speed, wind direction, longitudinal acceleration, normal acceleration, these parameters of inclination angle.These parameters with existing technology all
More accurately it can predict or set, may be implemented completely for the prediction of aircraft oil consumption.
Due to different mission phases, aircraft has different aerodynamic configuration and stress condition, so being directed to model not same order
The input parameter selection that section influences fuel flow is also different.
The fuel flow mode input data item of different mission phases:
(1) slide: coast period influence fuel consumption because being known as ground velocity, longitudinal acceleration (percentage speed variation, similarly hereinafter),
Take-off weight, engine behavior, total Air Temperature.Engine behavior be (starting or close, similarly hereinafter) " 1 " or
“0”。
(2) take-off climb: ground velocity, air speed, longitudinal acceleration, normal acceleration (can be learnt from normal acceleration and climb
Rate, similarly hereinafter), height (pressure altitude, similarly hereinafter), total Air Temperature, wind speed, wind direction, inclination angle, aircraft actual weight.
In the take-off climb stage, the climb rate of aircraft, highly all has an impact to aircraft fuel oil flow speed.The reality of aircraft
Border weight refers to the weight reduction along with fuel consumption aircraft, aircraft actual weight at that time.
(3) it cruises: wind speed, wind direction, inclination angle, ground velocity, air speed, height, total Air Temperature, wind speed, aircraft actual weight.
Cruising phase is affected by upper-level winds and flying height, this is because different flying height atmospheric density are different,
Fuel consumption rate is different.
(4) decline: ground velocity, air speed, longitudinal acceleration, normal acceleration, height, total Air Temperature, wind speed, wind direction, inclination
Angle, aircraft actual weight.Decline stage potential energy switchs to kinetic energy, and oil consumption reduces.Furthermore the decline stage be due to will often wait, low latitude
Spiraling, oil consumption section is more, and fuel consumption will increase.
Step 2: oil consumption estimation model being built and training:
2.1) data sample confirmed in the first step is standardized, removes the number in the different channels of data sample
According to the influence of unit difference；
Obtain training sample, i.e. fuel flow model outputs and inputs data, copes with it and is standardized, will count
According to data of the processing between section [0,1].Standardization has many methods, it is contemplated that experimental data characteristic, here using as follows
Formula
Wherein, x is the input of certain channel,For corresponding output, xminFor training sample corresponding channel minimum number, xminFor training
Sample corresponding channel maximum number.
2.2) for standardization after data sample, determine fuel flow model be BP neural network, several input layers and
Output layer neuron, M hidden neuron, hidden layer transfer function select tanh sigmoid functionOutput layer passes
Defeated function selects Log-Sigmoid functionWherein, a is function output, and e is natural constant, and n is function input.BP mind
Through network input layer and the specific data channel of output layer number view, it needs to be determined that, M regards specific input layer channel number and determines, generally
It is 1 to 2 times of input layer port number；The BP neural network includes input layer, output layer, hidden layer；Fuel flow after building
Model schematic is as shown in Figure 1, output is engine fuel flow sample data.
2.3) using extracted training data sample in 1.2) as training fuel flow model is inputted, training is general to be used
Levenberg-Marquardt algorithm；
2.4) by extracted test data sample input step 2.3 in 1.2)) in fuel flow model, obtain fuel oil
Traffic prediction value；
Step 3: the fuel flow predicted value that will be obtained in step 2.4), is label with the flight time, to entire segment into
Row integral, can obtain the predicted value of the fuel consumption total amount of flight flight.
Step 2.4) predicts the fuel flow of test sample point on course line, is fitted fuel oil with the fuel flow value of these points
Flow curve is usedOil consumption in expression time Δ t, thenAs approximate fuel oil total amount.Δ t is indicated between sampling
Every tfFor the flight end time, ff is fuel oil total flow, and unit is kg/hr the corresponding fuel oil stream of each engine
Amount, twin fuel flow are ff1, ff2, fuel flow and be ff, fuel oil total amount W calculation formula are as follows:
ff1、ff2It is determined by parameters such as speed, height, aircraft weights.As Fig. 2 fuel oil total amount calculates shown in schematic diagram, by firing
After oil stream amount model obtains every fuel flow, fuel flow is obtained into approximate fuel oil total amount multiplied by time interval and summation.
Step 4: obtain in the step 2.2) fuel flow model on the basis of, to output layer increase flight failure and
The channel of anomalous event；
On the basis of fuel flow model, the data of step 1.2) intermediate fuel oil system marks failure and anomalous event are introduced
Sample is trained, and can be obtained can monitor failure of fuel system and abnormal fuel flow model, the failure of fuel system and
It is abnormal generally to have:
(1) lubricating oil low-voltage；
(2) fuel quantity is low；
(3) lubricating oil overtemperature；
(4) turbine overtemperature；
(5) fuel flow rate exceeds the speed limit；
(6) generator failure；
(7) engine fuel cutting is abnormal；
(8) etc..
The above failure and exception are encoded, can be trained.
Step 5: being input to using the training data sample obtained in step 1.2) as training sample improved in the 4th step
It in fuel flow model, is trained, airplane fault and abnormal fuel flow model can be monitored according to airplane data by obtaining.
It should be noted that the oil consumption estimation of fuel system and health monitor method, are built using BP neural network
Fuel flow model, is trained according to flying quality, and method basic ideas are similar.Health monitor method is in oil consumption estimation side
Further functions expanding on the basis of method, oil consumption estimation method are also the basis of health monitor method, and the two is progressive pass
System, belongs to a kind of method.
In order to verify the validity of specific embodiment, devising confirmatory experiment and analyze experimental result.According to
The characteristics of oil consumption estimation method of the present invention, devise comparative experiments:
(1) aircraft track kinematic parameter is merely entered to reference model, the BP neural network in aircraft each stage inputs parameter phase
Together, parameter is as follows: the ground velocity of aircraft, air speed, pressure altitude, atmospheric temperature, Aircraft Quality.
(2) other than to the fuel flow mode input aircraft track kinematic parameter, meteorologic parameter, horizontal movement are also inputted
Parameter, acceleration, each stage input parameter of aircraft are different.Increased input parameter has wind speed, wind direction, inclination angle, longitudinal acceleration
Degree, normal acceleration.Height, longitudinal acceleration, wind direction, wind speed are not considered in coast period；Do not consider in the landing and sliding stage
Highly, longitudinal acceleration.Take-off climb stage and decline stage all of above factor require to consider.Cruising phase does not consider to indulge
To acceleration.
The input parameter of this experimental applications and the input parameter of reference model are identical, but reference model needs query performance figure
Table (airline provides reference documents, similarly hereinafter), with training data sample training fuel flow model, then input test data sample
This, is not necessarily to query performance data.
Experimental result is as shown in figs. 3-10, it is seen that fuel flow model accuracy described in the method for the present invention is higher, the combustion of prediction
Oil stream magnitude then illustrates that the influence factor of second group of experiment addition has an impact to fuel oil oil consumption, considers this closer to true consumption
A little meteorology, horizontal movement factors etc. can make model more accurate.
To sum up, the present invention has more accurate oil consumption accuracy of estimation, while can monitor the failure of fuel system and different
Ordinary affair part has more excellent performance.
Claims (4)
1. a kind of Fuel On Board system oil consumption estimation and health monitor method, it is characterized in that the described method comprises the following steps:
Step 1: data sample is handled:
1.1) packet loss is carried out to flight initial data, additions and deletions are handled, the complete available flight initial data of formation, further according to fuel oil
The system failure and anomalous event record data complete the label to flight initial data；
1.2) extract flight initial data slide, take-off climb, cruise, the flying quality of decline stage, as following model
Training and test needed for data sample；
Step 2: oil consumption estimation model being built and training:
2.1) data sample confirmed in the first step is standardized, removes the data sheet in the different channels of data sample
The other influence of potential difference；
2.2) for the data sample after standardization, determine that fuel flow model is BP neural network, several input layers and output
Layer neuron, M hidden neuron, hidden layer transfer function select tanh sigmoid functionOutput layer transmits letter
Number selection Log-Sigmoid functionWherein, a is function output, and e is natural constant, and n is function input.BP nerve net
Network input layer and output layer number regard specific data channel it needs to be determined that, M regards specific input layer channel number and determines, generally defeated
Enter 1 to 2 times of layer port number；The BP neural network includes input layer, output layer, hidden layer；
2.3) it is used using extracted training data sample in 1.2) as training fuel flow model, training is inputted
Levenberg-Marquardt algorithm；
2.4) by extracted test data sample input step 2.3 in 1.2)) in fuel flow model, obtain fuel flow
Predicted value；
Step 3: the fuel flow predicted value that will be obtained in step 2.4), is label with the flight time, accumulates to entire segment
Point, the predicted value of the fuel consumption total amount of flight flight can be obtained.
Step 4: increasing flight failure and exception to output layer in step 2.2) on the basis of the fuel flow model of acquisition
The channel of event；
Step 5: the training data sample obtained in step 1.2) is input to improved fuel oil in the 4th step as training sample
It in discharge model, is trained, airplane fault and abnormal fuel flow model can be monitored according to airplane data by obtaining.
Step 6: step 1.1) only to be carried out to packet loss, the unmarked failure of additions and deletions processing and abnormal data as test data
It is input in the 5th step in improved fuel flow model, unknown failure and abnormal data can be monitored.
2. Fuel On Board system oil consumption estimation according to claim 1 and health monitor method, it is characterized in that: the step
2.1) standardization are as follows: process data into the data between section [0,1]；It is handled using following formula:
Wherein, x is the input of certain channel,For corresponding output, xminFor training sample corresponding channel minimum number, xminFor training sample
Corresponding channel maximum number.
3. Fuel On Board system oil consumption estimation according to claim 1 and health monitor method, it is characterized in that: the step
2.4) fuel flow for predicting test sample point on course line is fitted fuel flow curve with the fuel flow value of these points, usesOil consumption in expression time Δ t, thenAs approximate fuel oil total amount；Δ t indicates sampling interval, tfFor flight knot
Beam time, ff are fuel oil total flow, and unit is kg/hr the corresponding fuel flow of each engine, twin fuel oil
Flow is ff1, ff2, fuel flow and be ff, fuel oil total amount W calculation formula are as follows:
ff1、ff2It is determined by speed, height, aircraft weight parameter；After obtaining every fuel flow by fuel flow model, it will fire
Oil stream amount obtains approximate fuel oil total amount multiplied by time interval and summation.
4. Fuel On Board system oil consumption estimation according to claim 1 and health monitor method, it is characterized in that: in fuel oil stream
On the basis of measuring model, the data sample of step 1.2) intermediate fuel oil system marks failure and anomalous event is introduced, is trained, i.e.,
Can get can monitor failure of fuel system and abnormal fuel flow model, and the failure of fuel system includes that lubricating oil is low with exception
It presses, fuel quantity is low, the cutting of lubricating oil overtemperature, turbine overtemperature, fuel flow rate hypervelocity, generator failure, engine fuel is abnormal；It is right
The failure and exception of fuel system are encoded, and can be trained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811472311.2A CN109598815A (en) | 2018-12-04 | 2018-12-04 | A kind of estimation of Fuel On Board system oil consumption and health monitor method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811472311.2A CN109598815A (en) | 2018-12-04 | 2018-12-04 | A kind of estimation of Fuel On Board system oil consumption and health monitor method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109598815A true CN109598815A (en) | 2019-04-09 |
Family
ID=65960821
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811472311.2A Pending CN109598815A (en) | 2018-12-04 | 2018-12-04 | A kind of estimation of Fuel On Board system oil consumption and health monitor method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109598815A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110060374A (en) * | 2019-04-19 | 2019-07-26 | 中国航空无线电电子研究所 | A kind of aircraft fuel system method for detecting abnormality and device |
| CN110147820A (en) * | 2019-04-11 | 2019-08-20 | 北京远航通信息技术有限公司 | Recommended method, device, equipment and the storage medium of the additional oil mass of flight |
| CN110276479A (en) * | 2019-05-31 | 2019-09-24 | 南京航空航天大学 | The cruising phase fuel consumption prediction technique of Aircraft Quality variation |
| CN110781457A (en) * | 2019-10-24 | 2020-02-11 | 深圳市瑞达飞行科技有限公司 | Off-site oil consumption data processing method and device, electronic equipment and storage medium |
| CN111696389A (en) * | 2020-05-29 | 2020-09-22 | 航科院中宇（北京）新技术发展有限公司 | Aircraft fuel estimation method and system based on flight plan |
| CN112378468A (en) * | 2020-11-13 | 2021-02-19 | 四川泛华航空仪表电器有限公司 | Method for measuring fuel consumption of airplane cruising under condition of small sample training data |
| CN113673815A (en) * | 2021-07-08 | 2021-11-19 | 三一智矿科技有限公司 | Mine car scheduling method and device based on vehicle data processing |
| CN114117967A (en) * | 2021-12-28 | 2022-03-01 | 北京航空航天大学 | Dynamic rapid prediction method for fuel temperature in aircraft fuel tank under flight envelope |
| CN114117967B (en) * | 2021-12-28 | 2024-06-28 | 北京航空航天大学 | Dynamic rapid prediction method for internal combustion oil temperature of aircraft oil tank under flight envelope |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001044939A2 (en) * | 1999-12-16 | 2001-06-21 | Simmonds Precision Products, Inc. | Method of verifying pretrained neural net mapping for use in safety-critical software |
| CN1471627A (en) * | 2000-10-26 | 2004-01-28 | �Ʒ� | A fault tolerant liquid measurement system using multiple-model state estimators |
| US20070288409A1 (en) * | 2005-05-31 | 2007-12-13 | Honeywell International, Inc. | Nonlinear neural network fault detection system and method |
| CN102980771A (en) * | 2012-12-04 | 2013-03-20 | 南京航空航天大学 | Portable failure detection system and method for aero-engine gas path component |
| CN103645891A (en) * | 2013-11-28 | 2014-03-19 | 陕西千山航空电子有限责任公司 | Rapid diagnosis method based on flight data |
| CN103970990A (en) * | 2014-04-22 | 2014-08-06 | 中国民航大学 | Aircraft route segment fuel consumption range estimation method based on QAR data |
| CN106372323A (en) * | 2016-08-31 | 2017-02-01 | 陕西千山航空电子有限责任公司 | Airborne equipment failure rate detection method based on flight data |
| CN106547967A (en) * | 2016-11-01 | 2017-03-29 | 哈尔滨工程大学 | A kind of costing analysis combine the diesel fuel system repair determining method of Bayesian network model |
| CN107622251A (en) * | 2017-09-29 | 2018-01-23 | 西安科技大学 | A kind of aircraft fuel pump signal degradation feature extracting method and device |
-
2018
- 2018-12-04 CN CN201811472311.2A patent/CN109598815A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001044939A2 (en) * | 1999-12-16 | 2001-06-21 | Simmonds Precision Products, Inc. | Method of verifying pretrained neural net mapping for use in safety-critical software |
| CN1471627A (en) * | 2000-10-26 | 2004-01-28 | �Ʒ� | A fault tolerant liquid measurement system using multiple-model state estimators |
| US20070288409A1 (en) * | 2005-05-31 | 2007-12-13 | Honeywell International, Inc. | Nonlinear neural network fault detection system and method |
| CN102980771A (en) * | 2012-12-04 | 2013-03-20 | 南京航空航天大学 | Portable failure detection system and method for aero-engine gas path component |
| CN103645891A (en) * | 2013-11-28 | 2014-03-19 | 陕西千山航空电子有限责任公司 | Rapid diagnosis method based on flight data |
| CN103970990A (en) * | 2014-04-22 | 2014-08-06 | 中国民航大学 | Aircraft route segment fuel consumption range estimation method based on QAR data |
| CN106372323A (en) * | 2016-08-31 | 2017-02-01 | 陕西千山航空电子有限责任公司 | Airborne equipment failure rate detection method based on flight data |
| CN106547967A (en) * | 2016-11-01 | 2017-03-29 | 哈尔滨工程大学 | A kind of costing analysis combine the diesel fuel system repair determining method of Bayesian network model |
| CN107622251A (en) * | 2017-09-29 | 2018-01-23 | 西安科技大学 | A kind of aircraft fuel pump signal degradation feature extracting method and device |
Non-Patent Citations (2)
| Title |
|---|
| 刘婧: "基于飞行数据分析的飞机燃油估计模型", 《中国优秀硕士学位论文全文数据库》 * |
| 龙浩；王新民: "基于BP网络的飞机燃油***故障诊断方法研究", 《北京联合大学学报》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110147820A (en) * | 2019-04-11 | 2019-08-20 | 北京远航通信息技术有限公司 | Recommended method, device, equipment and the storage medium of the additional oil mass of flight |
| CN110147820B (en) * | 2019-04-11 | 2021-06-15 | 北京远航通信息技术有限公司 | Method, device, equipment and storage medium for recommending extra oil quantity of flight |
| CN110060374B (en) * | 2019-04-19 | 2021-06-01 | 中国航空无线电电子研究所 | Method and device for detecting abnormality of aircraft fuel system |
| CN110060374A (en) * | 2019-04-19 | 2019-07-26 | 中国航空无线电电子研究所 | A kind of aircraft fuel system method for detecting abnormality and device |
| CN110276479A (en) * | 2019-05-31 | 2019-09-24 | 南京航空航天大学 | The cruising phase fuel consumption prediction technique of Aircraft Quality variation |
| CN110276479B (en) * | 2019-05-31 | 2023-01-03 | 南京航空航天大学 | Cruise phase fuel consumption prediction method for aircraft mass change |
| CN110781457A (en) * | 2019-10-24 | 2020-02-11 | 深圳市瑞达飞行科技有限公司 | Off-site oil consumption data processing method and device, electronic equipment and storage medium |
| CN110781457B (en) * | 2019-10-24 | 2024-03-08 | 深圳市瑞达飞行科技有限公司 | Method and device for processing oil consumption data in departure stage, electronic equipment and storage medium |
| CN111696389A (en) * | 2020-05-29 | 2020-09-22 | 航科院中宇（北京）新技术发展有限公司 | Aircraft fuel estimation method and system based on flight plan |
| CN112378468A (en) * | 2020-11-13 | 2021-02-19 | 四川泛华航空仪表电器有限公司 | Method for measuring fuel consumption of airplane cruising under condition of small sample training data |
| CN113673815A (en) * | 2021-07-08 | 2021-11-19 | 三一智矿科技有限公司 | Mine car scheduling method and device based on vehicle data processing |
| CN114117967A (en) * | 2021-12-28 | 2022-03-01 | 北京航空航天大学 | Dynamic rapid prediction method for fuel temperature in aircraft fuel tank under flight envelope |
| CN114117967B (en) * | 2021-12-28 | 2024-06-28 | 北京航空航天大学 | Dynamic rapid prediction method for internal combustion oil temperature of aircraft oil tank under flight envelope |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109598815A (en) | A kind of estimation of Fuel On Board system oil consumption and health monitor method | |
| CN106777554B (en) | State baseline-based health state evaluation method for air circuit unit body of aero-engine | |
| CN109408552A (en) | The monitoring of the civil aircraft system failure and recognition methods based on LSTM-AE deep learning frame | |
| CN111177851B (en) | Assessment method for ground risk in unmanned aerial vehicle operation safety risk assessment | |
| CN110930770A (en) | Four-dimensional track prediction method based on control intention and airplane performance model | |
| Zhu et al. | Analyzing commercial aircraft fuel consumption during descent: A case study using an improved K-means clustering algorithm | |
| Zeppetelli et al. | In-flight icing risk management through computational fluid dynamics-icing analysis | |
| CN104108474A (en) | Method For Predicting A Bleed Air System Fault | |
| CN109738035A (en) | Aircraft fuel consumption calculation method based on ADS-B track data | |
| CN108256285A (en) | Flight path exception detecting method and system based on density peaks fast search | |
| CN105956790A (en) | Low-altitude flight situation safety evaluation indexes and evaluation method thereof | |
| CN108609202A (en) | Flight is jolted prediction model method for building up, prediction technique and system | |
| CN112215416B (en) | Intelligent planning inspection route system and method | |
| Uzun et al. | Design of a hybrid digital-twin flight performance model through machine learning | |
| Lv et al. | A novel method of overrun risk measurement and assessment using large scale QAR data | |
| CN103149929B (en) | Fault diagnosing and tolerance control method for aircraft longitudinal movement | |
| Shmelova et al. | Collective Models of the Aviation Human-Operators in Emergency for IntelligentDecisionSupportSystem. | |
| CN106127407B (en) | Airplane travel scoring method and system based on multi-sensor information fusion | |
| CN106651014A (en) | Optimization method for flight path of transport aircraft | |
| Hu et al. | Research on Flight Delay Prediction Based on Random Forest | |
| Lee | Modeling aviation's global emissions, uncertainty analysis, and applications to policy | |
| Chen et al. | A deep learning method for landing pitch prediction based on flight data | |
| Janakiraman et al. | Using ADOPT algorithm and operational data to discover precursors to aviation adverse events | |
| Reed | Indirect aircraft structural monitoring using artificial neural networks | |
| CN114118802A (en) | Helicopter flight risk assessment method based on analytic hierarchy process |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190409 |