Flight arrival time prediction method and system based on data mining analysis
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of data mining and prediction method, which is applied in the field of flight operation management, and can solve problems such as the unsatisfactory accuracy of flight arrival time estimation
Pending Publication Date: 2020-09-11
航科院中宇(北京)新技术发展有限公司
View PDF5 Cites 15 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
At present, the accuracy of flight arrival time estimation is not ideal. The development of data mining technology provides a new method for flight arrival time estimation. The rich flight operation history database also provides sufficient data support for the prediction method based on data mining.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0043] A method for predicting flight arrival time based on data mining analysis, including:
[0044] S1. Matching, fusion and standardization of flight historical operation data: Carry out association matching, multi-dimensional classification, and standardized processing and storage of flight historical data according to feature dimension parameters. The feature dimension parameters include flight number, flight date, three-character code, and machine number , aircraft type, take-off and landing airport, described flight historical data comprises flight dynamics, the running track in the ADS-B system, the running track in the ACARS system, the flight plan route, obtains the historical running data after processing; The flight history of the present embodiment The data mainly comes from flight dynamics, the operating trajectory in the ADS-B system, the operating trajectory in the ACARS system, the flight plan route, and of course other monitoring equipment (such as radar monit...
Embodiment 2
[0069] A method for predicting flight arrival time based on data mining analysis, including:
[0070] S1. Matching, fusion and standardization of flight historical operation data: According to the feature dimension parameters, the historical flight data is correlated and matched to construct a flight operation data set, which includes flight number, aircraft number, aircraft type, departure and landing airport , airlines; perform feature calculation and standardization processing on the data in the flight operation data set, including flight trajectory and flight dynamics. The feature items included in the feature calculation include the following: flight track points, distance D1 from the departure airport, and distance from the destination airport D2, the flight time T1, the remaining flight time T2, and the delay time DT; the flight history data includes flight dynamics, the operation trajectory in the ADS-B system, the operation trajectory in the ACARS system, and the fligh...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
PUM
Login to view more
Abstract
The invention discloses a flight arrival time prediction method and system based on data mining analysis. The flight arrival time prediction method comprises the steps of S1, carrying out flight historical operation data matching fusion and standardization processing; s2, carrying out historical operation data feature screening and correlation analysis; 3, constructing a prediction model; and S4,inputting the characteristic variable data of the predicted flight into the regression prediction model, and performing calculation to obtain a prediction value of the remaining flight time of the flight. According to the invention, flight historical data is collected from an ADS-B system, an ACARS system and other devices; firstly, data is subjected to association and standardization processing;Pearson correlation coefficient calculation is performed according to feature variable screening and feature value calculation, and a regression prediction model based on an XGBoost algorithm is constructed; the parameter optimization model is continuously adjusted to obtain the regression prediction model with the optimal accuracy, the predicted arrival time of the flight can be predicted after the characteristic variable data of the predicted flight is input into the model, and the prediction precision of the arrival time of the flight is improved.
Description
technical field [0001] The invention relates to the field of flight operation management, in particular to a method and system for predicting flight arrival time based on data mining analysis. Background technique [0002] The year-by-year increase in the volume of civil aviation business puts forward higher requirements on the level of flight operations, especially in terms of airline flight punctuality and airport operation efficiency. Accurate estimation of flight arrival time is conducive to improving the operating efficiency and safety level of airports and airlines, and has important and direct significance for improving flight punctuality, improving flight security and operating efficiency, and optimizing resource allocation and task planning. At present, the accuracy of flight arrival time estimation is not ideal. The development of data mining technology provides a new method for flight arrival time estimation. The rich flight operation history database also provide...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more