CN112949982A - Method for achieving flight near landing stability evaluation based on QAR data - Google Patents
Method for achieving flight near landing stability evaluation based on QAR data Download PDFInfo
- Publication number
- CN112949982A CN112949982A CN202110126329.2A CN202110126329A CN112949982A CN 112949982 A CN112949982 A CN 112949982A CN 202110126329 A CN202110126329 A CN 202110126329A CN 112949982 A CN112949982 A CN 112949982A
- Authority
- CN
- China
- Prior art keywords
- data
- unit
- landing
- qar
- approach
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Abstract
A method for achieving flight approach and approach landing stability assessment based on QAR data adopts a data importing unit, a data cleaning unit, a QAR data parameter selecting unit, an approach landing model calculating unit, an approach landing index visualization unit and an approach landing assessment result exporting unit as assessment application tools, and the assessment method is divided into six steps. Based on QAR data, under the combined action of related application units, the method realizes automatic data acquisition, cleaning and storage, realizes evaluation indexes and data models which accord with industrial standards and are widely accepted, realizes the visualization of the evaluation indexes and evaluation results, realizes the accurate perception of the approach landing evaluation through the QAR data, plays an increasingly important role in the aspect of flight quality monitoring for the QAR data, and provides powerful technical support for the safe operation and flight training of airlines.
Description
Technical Field
The invention relates to the technical field of flight data analysis, in particular to a method for realizing the stability evaluation of flight approach landing based on QAR (quick access recorder) data.
Background
Currently, airlines accumulate a large amount of QAR data (a fast storage device in an airplane onboard recording system can make up for the disadvantage that a flight recorder black box is not convenient to transcribe), which is used as full flight recording data and plays an increasingly important role in the aspect of flight quality monitoring. In the prior art, an airline company invests a large amount of resources to research and explore the quantitative evaluation function of the QAR in the approach landing stage, but the support of a relatively stable and mature mathematical model is always lacked, the evaluation index and the evaluation result depend on the professional ability of a pilot, an automatic, simple and flexible special tool support is always lacked, data needs to be acquired in a plurality of systems, Excel auxiliary calculation is used, the evaluation cost is high, the period is long, the approach landing evaluation cannot be carried out in real time, and effective trend and deviation analysis cannot be formed. In practical situations, an experienced data processing expert needs 10 minutes to clean QAR data of a flight segment, and according to a calculation model determined by a service expert, parameter correction and calculation logic compiling through Excel need 30 minutes, which is long in time consumption, and after an evaluation result is issued, the calculation result cannot be reused due to lack of an effective storage means.
Disclosure of Invention
In order to overcome the defects of the prior QAR data in practical application as background, the invention provides a method for realizing the evaluation of the flying near landing stability based on QAR data, which realizes the automatic data acquisition, cleaning and storage, realizes the evaluation index and the data model which accord with the industrial standard and are widely accepted, realizes the visualization of the evaluation index and the evaluation result, realizes the accurate perception of the evaluation of the near landing through the QAR data, plays an increasingly greater role in the aspect of the monitoring of the flying quality for the QAR data, and provides powerful technical support for the safe operation and the flight training of an airline company.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a method for realizing the stability evaluation of the approach landing of the flight station based on QAR data is characterized in that a data import unit, a data cleaning unit, a QAR data parameter selection unit, an approach landing model calculation unit, an approach landing index visualization unit and an approach landing evaluation result export unit are adopted as application tools for evaluation; the data import unit, the data cleaning unit, the QAR data parameter selection unit, the approach landing model calculation unit, the approach landing index visualization unit and the approach landing evaluation result export unit are application software installed in a PC; the evaluation method comprises six steps, namely: importing OAR data of the airplane into a data cleaning unit in the application of a data importing unit; step two: the data cleaning unit cleans the imported data, the data cleaning is divided into four flows, and abnormal data identification, effective data selection, data deletion operation and data inference are incomplete; step three: the QAR data parameter selection unit extracts corresponding QAR data; step four: the approach landing model calculation unit is used for calculating a landing data evaluation model of the airplane and outputting an evaluation result; step five: the approaching landing index visualization unit finds the deviation and the abnormality of the data; step six: and the approaching landing evaluation result exporting unit classifies and outputs the calculated evaluation data through a time stamp technology and stores the evaluation data in a corresponding relational CSV file.
Further, in the abnormal data identification of the second step, the abnormal data includes the following data, a: CSV (data) files are incomplete, not the full process data from takeoff to landing of the aircraft; b: the CSV file is flight training data with the same departure place and destination of the airplane; c: decoding the parameter dislocation of the outputted CSV file, wherein the parameter dislocation comprises a certain row in the row of the parameter 1 and displays the data of the parameter 2; d: the parameter value exceeds the theoretical value range; e: and the parameter value has unrealistic jump.
Further, in the selection of the valid data in the second step, the valid data includes the following data, a: the CSV file of the decoded data comprises a file description and a data two-part content, and only a specific part and a data part of the file description are needed; b: data outside of a certain range is not valid data (due to hopping and engineering parameter configuration).
Further, in the data deleting operation of the second step, the deleted data includes the following data, a; for the CSV file format abnormal condition of the abnormal data, discarding the abnormal data as invalid data; and B, regarding the CSV file with correct format, only data with even abnormal parameter values are deleted, and then complement is deduced by combining other parameters.
Further, in the data inference completion of the second step, a: taking a front-back average value of continuous numerical parameters such as airplane speed, longitude and latitude, altitude and the like; b: and taking a front value or a rear value to fill discrete state parameters such as the flap state, the slat state and the like of the airplane.
Furthermore, in the third step, the QAR data processed by the data washing unit has about 200 parameters, and about 40 parameters related to the approach and approach evaluation, and the parameter names of different aircraft models are not consistent, the QAR parameter selection unit adopts a ParaFilter module to select effective parameters, and extracts corresponding QAR data according to the parameter configuration of different aircraft models, and the QAR data mainly includes the parameters AltStd (barometric altitude), Ldgnos (air-to-ground electric door), Cas (airspeed), Gsc (ground speed), HeadMag (heading), windward (wind direction), WinSpd (wind speed), VfeIas (flap speed), Lonpc (longitude), Latpc (dimension), FlightPhase (flight phase), raltrrh (radio altitude), flaplplplevel (flap configuration), logselld (position), sprkppos (position), gletddot (glide slope), dev (devil slope), pitch attitude deviation (pitch attitude), pitch attitude c (pitch attitude deviation), and pitch attitude (pitch attitude c) of aircraft, RollC (roll attitude), ivca (descent rate), GpwsWarStatus (GPWS alert), PitchRate (rate of change in elevation).
Further, in the fourth step, a domestic flight quality monitoring model is mainly referred to, a mature evaluation algorithm model is solved, 18 items of approach landing data evaluation models of all the models are defined in application, configuration supporting small-size number adaptation is adopted, an approach landing model calculation unit adopts an XMLModel factory module to realize analysis and loading of the evaluation models, a WorkHandle module is adopted to realize asynchronous operation of mass data and output of evaluation results, and the approach landing model mainly comprises landing flap in-place late, landing gear releasing late, a low-altitude speed reduction plate, glide slope deviation, course deviation, pitching attitude, rolling attitude, descent rate, approach warning and the like.
Furthermore, in the fifth step, accurate and visual online evaluation results are obtained through data visualization, which is helpful for finding data deviation and abnormality, the approaching landing index visualization unit adopts a Chart component for rendering, the capability change and trend of approaching landing are presented through a scatter diagram, the core index measurement results are displayed through a stacking diagram, and the index early warning distribution is presented through an instrument panel.
Furthermore, in the sixth step, because the format of the corresponding relational CSV file is uniform and the data standard is adopted, the relevant CSV file can be conveniently transferred to an upper layer service system in batches, and data support is provided for application of a higher-level scene, wherein the approaching landing evaluation result export unit adopts a datawriter (data output) module to transfer the evaluation data.
The invention has the following effects: the invention is based on QAR data, mainly solves the complexity and non-uniformity of approach landing evaluation, realizes the quantification and visualization of approach quality evaluation through nine core indexes according to the actual flight experience of pilots and the algorithm basis provided by aircraft manufacturers in combination with the local flight quality monitoring standard, and defines approach short boards, and in application, under the combined action of a data import unit, a data cleaning unit, a QAR data parameter selection unit, an approach landing model calculation unit, an approach landing index visualization unit and an approach landing evaluation result derivation unit, by analyzing QAR (data, abstracting fields and data required by a calculation model, realizing the flexible configuration of fields, data sets and data fields, realizing the automatic data acquisition, cleaning and storage, realizing the evaluation indexes and data models which accord with the industry standard and are widely accepted, the method realizes the visualization of the evaluation index and the evaluation result, realizes the accurate perception from the QAR data to the approach landing evaluation, plays an increasingly important role in the aspect of flight quality monitoring for the QAR data, and provides powerful technical support for the safe operation and flight training of the airline company. Based on the above, the invention has good application prospect.
Drawings
The invention is further illustrated below with reference to the figures and examples.
Fig. 1 is a diagram showing an example of a scale model configuration.
Fig. 2 is a diagram showing an example of a configuration of the departure warning model.
FIG. 3 is an exemplary graph of a stacked graph presenting an index distribution.
FIG. 4 is an exemplary graph of a scatter plot presenting near-earth energy trends.
FIG. 5 is an illustration of a cockpit presenting an overrun pre-warning.
Fig. 6 is an exemplary diagram of a relational computation result.
FIG. 7 is a block diagram illustration of the software architecture of the present invention.
Detailed Description
Fig. 7 shows a method for implementing the evaluation of the stability of the approach landing of the flight based on the QAR data, in which a data importing unit, a data cleaning unit, a QAR data parameter selecting unit, an approach landing model calculating unit, an approach landing index visualizing unit, and an approach landing evaluation result deriving unit are used as evaluation application tools; the data import unit, the data cleaning unit, the QAR data parameter selection unit, the approach landing model calculation unit, the approach landing index visualization unit and the approach landing evaluation result export unit are application software installed in a PC.
FIG. 7 illustrates that, in the present invention, the QAR data in CSV format requires related cleaning, interception and modification of the data due to the frequency of acquisition and the jump to use the QAR data for near landing evaluation. And in the application of the data import unit, the OAR data of the airplane is imported into the data cleaning unit, and then the data cleaning unit cleans and subsequently processes the data, wherein the specific evaluation method comprises the following steps. S1, the data cleaning unit cleans the data, in practical condition, each CSV file contains a plurality of lines, each line corresponds to a data acquisition time (unit: second), namely the ith line represents the flight parameter of the ith second in the QAR recording process; each line corresponds to a plurality of QAR acquisition parameters, the acquisition frequency of most parameters is 1HZ (sampling 1 time per second), the acquisition frequency of part of parameters is higher than 1HZ (maximum 8HZ), the parameters appear in the same line for many times, the acquisition frequency of part of parameters is 1 time (minimum 0.5HZ) of sampling in several seconds, the parameters appear 1 time every other lines, and the acquisition frequency of the parameters is related to an engineering value parameter acquisition mode and comprises a frame connection mode, a frame skipping mode, a super frame mode, a double-character slot mode and a dense sampling mode; the data cleaning is mainly completed by two problems of day-crossing time and parameter jumping. The cleaning comprises the following operations, wherein data correction is combined with the QAR data acquisition characteristics to identify, delete and infer and complement abnormal data. (ii) a The following method is adopted for correction, and the abnormal data is identified as follows: the CSV files are incomplete, and the whole process from take-off to landing is omitted; the CSV file is flight training data with the same departure place and destination; decoding the parameter dislocation of the outputted CSV file, namely displaying the data of the parameter 2 in a certain row in the parameter 1 column; the parameter value exceeds the theoretical value range; and the parameter value has unrealistic jump and the like. In the deletion operation: for the CSV file format abnormal condition of the abnormal data, discarding the abnormal data as invalid data; and for the CSV file, the format is correct, only the data with even abnormal parameter values are used, only the abnormal data in the CSV file are deleted, and then the completion is deduced by combining other parameters. And (3) in deduction and completion: taking the average value of the continuous numerical parameters such as speed, longitude and latitude, height and the like; and for discrete state parameters such as a flap state, a slat state and the like, filling the discrete state parameters by taking a front value or a rear value.
As shown in fig. 7, the evaluation method S2: corresponding QAR data are extracted through a QAR data parameter selecting unit, the QAR data processed by the data cleaning unit have about 200 parameters and about 40 parameters related to the approach ground evaluation, the parameter names of different airplane types are not consistent, the QAR parameter selecting unit adopts a ParaFilter module to realize effective parameter selection, and corresponding QAR data are extracted according to the parameter configuration of different airplane types and mainly comprise the parameters of AltStd (barometric altitude), Ldgnos (air-to-ground electric door), Cas (airspeed), Gsc (ground speed), HeadMag (heading), Windir (wind direction), WinSpd (wind speed), VfaAs (flap speed), Lonpc (longitude), Latpc (dimension), Flightphase (flight phase), Raltrh (radio altitude), FlapLevel (flap configuration), LogSeldw (position), SprkPos (position), GleDot (glide slope), DevRatlv (flight slope), Piftc (pitch attitude deviation), Pitch attitude C attitude (attitude deviation), and LodBtC (attitude), and the corresponding QAR (attitude) data are extracted through the corresponding QAR data are extracted according to the parameter configuration of different airplane types, And in the selection, QAR parameters required in an approach landing mathematical model are extracted, wherein the QAR parameters comprise flap configuration, undercarriage position, speed reducer plate position, gliding, course, pitch attitude, elevation angle change rate, roll attitude angle, descent rate, ground proximity warning and the like.
As shown in fig. 7, the evaluation method S3: index measurement configuration is realized through XML, and the approach landing model calculation unit is used for calculating the landing data evaluation model of the airplane and outputting the evaluation result. In practical situations, nine core indexes for evaluation of approach and approach landing are combed out by researching an airline flight unit and referring to ICAO (international civil aviation organization), CAAC (national civil aviation administration) and aircraft manufacturer standards, wherein the nine core indexes comprise: landing flaps in place, landing gear, low altitude use of speed pads, glide slope deviation, course deviation, pitch attitude, roll attitude, descent rate, and ground proximity warning. Scores of nine major indexes are calculated through two major dimensions of overrun early warning and deviation measurement, configuration items are reserved for each model through an overrun early warning model and a deviation measurement model, on one hand, the algorithm standard of the model is stable, and on the other hand, the method is suitable for slight differences of different models (series). Related examples of implementing index metric configuration through XML are shown in fig. 1 and fig. 2 (fig. 1 refers to a scale metric model configuration example, and fig. 2 is a departure warning model configuration example).
As shown in fig. 7, the evaluation method S4: the deviation and the abnormality of the data are found through an approaching landing index visualization unit; and the measurement and early warning of the approaching landing indexes are visually presented by adopting visualization means including a stacking chart, a scatter diagram, a cockpit and the like. The stacked graph realizes the overall evaluation of the branch flight sections and realizes the distribution of different indexes of a unified flight section; the scatter diagram presents the capability distribution from approach to landing sites and can identify deviation legs; the cockpit realizes the early warning distribution of nine indexes including early warning times. FIG. 3 illustrates a stacked graph presentation index distribution; FIG. 4 illustrates a scatter plot presenting an approaching energy trend; FIG. 5 illustrates the cockpit presenting an overrun warning.
In the evaluation method S5 shown in fig. 7, the approach landing evaluation result derivation unit classifies the calculated evaluation data by the time stamp technique, outputs the classification, and stores the classification in the corresponding relational CSV file for the convenience of reusing the subsequent data, and the example of the relational calculation result is shown in fig. 6.
As shown in fig. 7, the present invention mainly solves the complexity and non-uniformity of approach landing evaluation based on QAR data, and implements quantification and visualization of approach quality evaluation through nine core indexes according to the actual flight experience of pilots and the algorithm basis provided by aircraft manufacturers, in combination with the local flight quality monitoring standard, to clarify approach short boards, and in application, under the combined action of the data importing unit, the data cleaning unit, the QAR data parameter selecting unit, the approach landing model calculating unit, the approach landing index visualization unit, and the approach landing evaluation result exporting unit, by analyzing multi-model QAR data, abstracting fields and data required by the calculation model, implementing flexible configuration of fields, data sets, and data fields, implementing automated data acquisition, cleaning, and storage, implementing evaluation indexes and data models that meet the industry standards and are widely accepted, the method realizes the visualization of the evaluation index and the evaluation result and realizes the accurate perception of the approach landing evaluation through the QAR data. The method effectively improves the approaching evaluation efficiency, the evaluation result can be presented 5 minutes after the airplane lands on the ground, real-time approaching evaluation of flight is realized, operation trend analysis and large operation deviation can be assisted through mass data batch calculation, and labor required to be invested in data statistics, calculation and reporting is greatly saved; single flight assessment performance: and obtaining an approaching landing evaluation result and mass flight evaluation efficiency within 3 seconds: and obtaining an evaluation result of 20 flight segments within 10 seconds, wherein the efficiency is linearly related to the number of the flight segments. The term f (x) is 0.5 x, and a leg is processed every 0.5 seconds. The method plays an increasingly large role in monitoring the flight quality for the QAR data, and provides powerful technical support for safe operation and flight training of the airline company.
While there have been shown and described what are at present considered the fundamental principles and essential features of the invention and its advantages, it will be apparent to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, but is capable of other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Furthermore, it should be understood that although the present description refers to embodiments, the embodiments do not include only one independent technical solution, and such description is only for clarity, and those skilled in the art should take the description as a whole, and the technical solutions in the embodiments may be appropriately combined to form other embodiments that can be understood by those skilled in the art.
Claims (9)
1. A method for realizing the stability evaluation of the approach landing of the flight station based on QAR data is characterized in that a data import unit, a data cleaning unit, a QAR data parameter selection unit, an approach landing model calculation unit, an approach landing index visualization unit and an approach landing evaluation result export unit are adopted as application tools for evaluation; the data import unit, the data cleaning unit, the QAR data parameter selection unit, the approach landing model calculation unit, the approach landing index visualization unit and the approach landing evaluation result export unit are application software installed in a PC; the evaluation method comprises six steps, namely: importing OAR data of the airplane into a data cleaning unit in the application of a data importing unit; step two: the data cleaning unit cleans the imported data, the data cleaning is divided into four flows, and abnormal data identification, effective data selection, data deletion operation and data inference are incomplete; step three: the QAR data parameter selection unit extracts corresponding QAR data; step four: the approach landing model calculation unit is used for calculating a landing data evaluation model of the airplane and outputting an evaluation result; step five: the approaching landing index visualization unit finds the deviation and the abnormality of the data; step six: and the approaching landing evaluation result exporting unit classifies and outputs the calculated evaluation data through a time stamp technology and stores the evaluation data in a corresponding relational CSV file.
2. The method for achieving stability assessment of flight approach landing based on QAR data as claimed in claim 1, wherein in the identification of abnormal data in step two, the abnormal data comprises the following, A: the CSV file is incomplete, not the overall process data from takeoff to landing of the aircraft; b: the CSV file is flight training data with the same departure place and destination of the airplane; c: decoding the parameter dislocation of the outputted CSV file, wherein the parameter dislocation comprises a certain row in the row of the parameter 1 and displays the data of the parameter 2; d: the parameter value exceeds the theoretical value range; e: and the parameter value has unrealistic jump.
3. The method of claim 1, wherein in the selecting of the valid data in the second step, the valid data includes the following data, a: the CSV file of the decoded data comprises a file description and a data two-part content, and only a specific part and a data part of the file description are needed; b: data outside of a certain range is not valid data (due to hopping and engineering parameter configuration).
4. The method of claim 1, wherein in the data deleting operation of step two, the deleted data includes the following, a; for the CSV file format abnormal condition of the abnormal data, discarding the abnormal data as invalid data; and B, regarding the CSV file with correct format, only data with even abnormal parameter values are deleted, and then complement is deduced by combining other parameters.
5. The method of claim 1 for performing an evaluation of stability against a flying near landing based on QAR data, wherein in the step two data inference completion, A: taking a front-back average value of continuous numerical parameters such as airplane speed, longitude and latitude, altitude and the like; b: and taking a front value or a rear value to fill discrete state parameters such as the flap state, the slat state and the like of the airplane.
6. The method for achieving flight approach landing stability assessment based on QAR data according to claim 1, characterized in that, in step three, the QAR data processed by the data cleaning unit has about 200 parameters, and about 40 parameters related to approach ground assessment, and the parameter names of different models are not consistent, the QAR data parameter selection unit employs a paramfiltte module to achieve effective parameter selection, and extracts corresponding QAR data according to parameter configuration of different aircraft models, which mainly includes parameters AltStd, Ldgnos, Cas, Gsc, HeadMag, winddltr, WinSpd, VfeIas, loc, Latpc, FlightPhase, ralrh, flappevel, seldchw, spdckpos, glidedot, locdot, pitchdot, PitchC, rollvcca, gvractatus, and pitchrank.
7. The method for achieving assessment of stability of flying approach landing based on QAR data as claimed in claim 1, wherein in the fourth step, referring mainly to a domestic flight quality monitoring model, a mature assessment algorithm model is solved, 18 approach landing data assessment models of each model are defined in application, configuration support mini-size adaptation is adopted, an approach landing model calculation unit adopts an XMLModelFactory module to achieve analysis and loading of the assessment models, a WorkHandle module is adopted to achieve asynchronous operation of mass data and output of assessment results, and the approach landing model mainly includes landing flap late in place, landing gear late, low altitude use speed reduction plates, glide slope deviation, course deviation, pitching attitude, roll attitude, descent rate, approach warning and the like.
8. The method for realizing the assessment of the stability of the approach landing during the flying process based on the QAR data as claimed in claim 1, wherein in the fifth step, the accurate and visual online assessment result is obtained through data visualization, which is helpful for finding out data deviation and abnormality, the approach landing index visualization unit adopts Chart component to render, presents the capability change and trend of the approach landing through a scatter diagram, displays the core index measurement result through a stacking diagram, and presents the index early warning distribution through a dashboard.
9. The method according to claim 1, wherein in step six, the format of the corresponding relational CSV file is uniform and the data standard is standardized, so that the relational CSV file can be conveniently transferred to an upper layer service system in batch, and data support is provided for application of a higher-level scene, and the approach landing evaluation result derivation unit employs a DateWriter module to transfer the evaluation data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110126329.2A CN112949982A (en) | 2021-01-29 | 2021-01-29 | Method for achieving flight near landing stability evaluation based on QAR data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110126329.2A CN112949982A (en) | 2021-01-29 | 2021-01-29 | Method for achieving flight near landing stability evaluation based on QAR data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112949982A true CN112949982A (en) | 2021-06-11 |
Family
ID=76239736
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110126329.2A Pending CN112949982A (en) | 2021-01-29 | 2021-01-29 | Method for achieving flight near landing stability evaluation based on QAR data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112949982A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114241852A (en) * | 2021-12-30 | 2022-03-25 | 中国民航科学技术研究院 | Multi-source data fusion-based flight simulation training evaluation system and method for in-process aircraft |
| CN115952694A (en) * | 2023-03-13 | 2023-04-11 | 中国民用航空飞行学院 | QAR data-based wind shear operation manipulation quality evaluation method in approach stage |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8204637B1 (en) * | 2007-12-20 | 2012-06-19 | The United States Of America As Represented By The Secretary Of The Navy | Aircraft approach to landing analysis method |
| CN106599230A (en) * | 2016-12-19 | 2017-04-26 | 北京天元创新科技有限公司 | Method and system for evaluating distributed data mining model |
| CN109979037A (en) * | 2019-03-19 | 2019-07-05 | 四川函钛科技有限公司 | QAR parametric synthesis visual analysis method and system |
| CN110705716A (en) * | 2019-09-30 | 2020-01-17 | 大连民族大学 | Multi-model parallel training method |
| CN111199343A (en) * | 2019-12-24 | 2020-05-26 | 上海大学 | Multi-model fusion tobacco market supervision abnormal data mining method |
-
2021
- 2021-01-29 CN CN202110126329.2A patent/CN112949982A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8204637B1 (en) * | 2007-12-20 | 2012-06-19 | The United States Of America As Represented By The Secretary Of The Navy | Aircraft approach to landing analysis method |
| CN106599230A (en) * | 2016-12-19 | 2017-04-26 | 北京天元创新科技有限公司 | Method and system for evaluating distributed data mining model |
| CN109979037A (en) * | 2019-03-19 | 2019-07-05 | 四川函钛科技有限公司 | QAR parametric synthesis visual analysis method and system |
| CN110705716A (en) * | 2019-09-30 | 2020-01-17 | 大连民族大学 | Multi-model parallel training method |
| CN111199343A (en) * | 2019-12-24 | 2020-05-26 | 上海大学 | Multi-model fusion tobacco market supervision abnormal data mining method |
Non-Patent Citations (1)
| Title |
|---|
| 洪小沯: "浅谈QAR大数据分析与应用", pages 11 - 16, Retrieved from the Internet <URL:http://news.carnoc.com/list/506/506417.html> * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114241852A (en) * | 2021-12-30 | 2022-03-25 | 中国民航科学技术研究院 | Multi-source data fusion-based flight simulation training evaluation system and method for in-process aircraft |
| CN114241852B (en) * | 2021-12-30 | 2022-06-21 | 中国民航科学技术研究院 | Multi-source data fusion-based flight simulation training evaluation system and method for in-process aircraft |
| CN115952694A (en) * | 2023-03-13 | 2023-04-11 | 中国民用航空飞行学院 | QAR data-based wind shear operation manipulation quality evaluation method in approach stage |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112949982A (en) | Method for achieving flight near landing stability evaluation based on QAR data | |
| CN109829468B (en) | Bayesian network-based civil aircraft complex system fault diagnosis method | |
| CN111639467B (en) | Aero-engine service life prediction method based on long-term and short-term memory network | |
| CN108199795A (en) | The monitoring method and device of a kind of equipment state | |
| CN110376003B (en) | Intelligent train service life prediction method and system based on BIM | |
| CN110457829B (en) | Source item release inversion and diffusion prediction method based on integrated atmospheric diffusion model | |
| CN112131782A (en) | Multi-loop intelligent factory edge side digital twin scene coupling device | |
| CN112732687A (en) | Aviation flight data visualization processing system and analysis method based on data cleaning | |
| CN116610747A (en) | Visual intelligent management system based on three-dimensional numbers | |
| CN113748066A (en) | System and method for monitoring an aircraft engine | |
| Li et al. | A functional architecture of prognostics and health management using a systems engineering approach | |
| CN111062949B (en) | Power line point cloud extraction method based on airborne laser radar | |
| CN111881623A (en) | Task-oriented aircraft pilot human error risk assessment method | |
| Figuet et al. | Data-driven mid-air collision risk modelling using extreme-value theory | |
| EP3292540B1 (en) | Method for operating a network with a plurality of node devices and corresponding network | |
| CN107562538A (en) | Data pick-up multitask management process and system in railway traffic statistics | |
| CN116914917A (en) | Big data-based monitoring and management system for operation state of power distribution cabinet | |
| CN105868402A (en) | Aircraft maintenance quality analysis oriented QAR (quick access recorder) data preprocessing method and device | |
| CN113361730B (en) | Risk early warning method, device, equipment and medium for maintenance plan | |
| Jeyan et al. | Flight manoeuvring and safe flight visualization with the aid of wide-ranging scrutiny and automation software | |
| CN114200962A (en) | Unmanned aerial vehicle flight task execution condition analysis method | |
| Zhang et al. | Construction and Research of Safety Management System for Machine Patrol Operation | |
| CN116258381A (en) | Quantitative evaluation method and device for operation command work | |
| CN117909326A (en) | Outfield flight data processing method and device for avionics ground test | |
| CN116956047B (en) | Wind turbine generator system performance evaluation system based on wind power generation data |
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 |