CN112801421A - Method for predicting airplane flight punctuality rate based on probability theory - Google Patents
Method for predicting airplane flight punctuality rate based on probability theory Download PDFInfo
- Publication number
- CN112801421A CN112801421A CN202110289449.4A CN202110289449A CN112801421A CN 112801421 A CN112801421 A CN 112801421A CN 202110289449 A CN202110289449 A CN 202110289449A CN 112801421 A CN112801421 A CN 112801421A
- Authority
- CN
- China
- Prior art keywords
- flight
- data
- error
- rate
- holiday
- 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 43
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 25
- 238000012896 Statistical algorithm Methods 0.000 claims abstract description 13
- 238000013179 statistical model Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000013461 design Methods 0.000 claims abstract description 7
- 238000012216 screening Methods 0.000 claims description 21
- 230000010006 flight Effects 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000013479 data entry Methods 0.000 claims description 5
- 230000008676 import Effects 0.000 claims description 5
- 238000012417 linear regression Methods 0.000 claims description 5
- 238000007476 Maximum Likelihood Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000011282 treatment Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 4
- 238000011161 development Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013499 data model Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/10—Office automation; Time management
- G06Q10/109—Time management, e.g. calendars, reminders, meetings or time accounting
- G06Q10/1091—Recording time for administrative or management purposes
-
- G06Q50/40—
Abstract
The invention discloses a method for predicting airplane flight punctuality rate based on probability theory, which comprises the following steps of designing a data mode, inputting/importing original data, establishing a dimension statistical model, performing a statistical algorithm process and predicting an algorithm 1: the method comprises a data fitting method based on historical records and a prediction algorithm processing flow, wherein the data mode design comprises a flight time record table, a legal holiday definition, a daily time period definition, a full-scale statistic of the error point rate of a flight number, a full-scale statistic of the error point rate of an airplane model, a classification statistic of inbound data (working day, holiday, double-holiday), a classification statistic of outbound data (working day, holiday, double-holiday), a classification data weight and inbound/outbound prediction, the establishing of a dimension statistic model and the statistic algorithm flow comprise establishing a dimension statistic model and establishing a statistic algorithm flow, and the method can predict the quasi-takeoff rate or the error point rate of an appointed flight for a plurality of days in the future through the analysis result of historical flight data.
Description
Technical Field
The invention relates to the technical field of civil data probability theory, in particular to a method for predicting airplane flight quasi-point rate based on the probability theory.
Background
Civil aviation means that various aircrafts are used for all aviation activities except military, the service range of civil aviation is continuously expanded, and the civil aviation becomes an important economic department of the country. The development of commercial aviation is mainly reflected in the rapid increase of passenger and cargo traffic volume, and regular airlines are densely distributed in all continents of the world. Due to a series of advantages of rapidness, safety, comfort, no terrain limitation and the like, commercial aviation occupies a unique position in a transportation structure, promotes the development of domestic and international trade, tourism and various communication activities, and makes the development of remote areas possible in a short time;
at present, factors such as weather, airport capacity, legal holidays, time periods of each day, double holidays, airplane failure rate and flight service level influence the flight punctuality rate, and in order to improve the flight punctuality rate and improve the service quality of passengers, a probability theory-based airplane flight punctuality rate prediction method is provided.
Disclosure of Invention
The invention aims to improve the punctuality rate of flights and improve the service quality of passengers.
The invention adopts the following technical scheme to solve the technical problems: the method for predicting the airplane flight punctuality rate based on the probability theory comprises the following steps of designing a data mode, inputting/importing original data, establishing a dimension statistical model, performing a statistical algorithm process and predicting an algorithm 1: and processing flow of a data fitting method and a prediction algorithm based on historical records.
Preferably, the data pattern design comprises a flight schedule, a legal holiday definition, a daily time period definition, a full-scale statistics of the error point rate of a flight number, a full-scale statistics of the error point rate of an airplane model, a classification statistics of inbound data (working day, holiday, double holiday), a classification statistics of outbound data (working day, holiday, double holiday), a classification data weight and inbound/outbound prediction.
Preferably, the raw data entry/import includes entering of flight time, departure place, arrival place, model, planned departure time, actual departure time, planned arrival time, actual arrival time, and port entry and exit type.
Preferably, the step (3) of establishing the dimension statistical model and the statistical algorithm includes a step of establishing the dimension statistical model and a step of establishing the statistical algorithm, where the dimension statistics includes: flight dimension, model dimension, weather dimension, double-holiday dimension, workday dimension, and period dimension;
the algorithm flow comprises the following steps: the method comprises the following steps of screening and counting working day flight data, screening and counting double-holiday flight data, screening and counting holiday flight data, wherein the steps of screening and counting the working day flight data are as follows:
step 1: importing the defined holidays, time period definition and project data into a database;
step 2: and reading the database to take out a flight record and judging whether the record is a working day flight record, a double holiday flight record or a holiday flight record.
And step 3: judging whether the flight records are punctual, if so, accumulating punctual numbers, otherwise, accumulating error punctual numbers, if so, judging whether claim error punctuation is required to be settled, and if so, accumulating claim error punctual numbers;
and 4, step 4: judging whether the judged statistical records exist or not, if so, updating (related quantity), and if not, adding the records;
and 5: and reading the next flight record in the database, entering the step 2 if the flight record exists, and ending the screening if the flight record does not exist.
The specific steps of screening and counting the double-holiday flight data and the holiday flight data are the same as the specific steps of screening and counting the working day flight data.
Preferably, the prediction algorithm 1: the data fitting method (4) based on the historical records adopts a multiple linear regression function for fitting, and the calculation method comprises the following steps:
setting Y as the comprehensive error point rate; x0The weather error point rate is obtained; x1The flight point error rate is; x2The machine type error point rate is obtained; x3The error point rate is 0 (early morning) in a time period; x4The error point rate is time period 1 (morning); x5Is the time period 2 (morning) error point rate; x6Is the time period 3 (noon) error point rate; x7Is the error point rate of time period 4 (afternoon); x8The time period 5 (evening) error point rate; x9When isInterval 6 (evening) false point rate; x10The time period 7 (late night) error point rate;
the concrete formula is as follows:
the mathematical expression of the probability of error points in the time period Ti (i ═ 0,1, …,7) of the arrival or departure of all flights is:
Y(X1，X2，Ti)＝W1*X1+W2*X2+WTi*XTi(formula 1);
wherein W1，W2，WiIs a probability weight, and W1+W2+WTi1, (Ti ═ 0,1, …,7, corresponding to time periods 0-7), to obtain the weight value W1，W2，WTi(Ti ═ 0,1, …,7, corresponding to period 0-7), the following treatments were performed:
step 1: estimating W using maximum likelihood estimationiI.e. by
This is minimized by finding Ti (Ti 0,1, …,7, corresponding to time period 0-7) and Wi；
Step 2: m to (equation 2) is respectively to W1,W2,WTi(Ti 0,1, …,7 for time periods 0-7) and making the value equal to 0
3 normal equations can be obtained, and W can be obtained by solving the normal equations1，W2，WTi(Ti ═ 0,1, …,7, corresponding to periods 0-7);
according to the sample data (X)i,Yi) Acquiring the error point rate of each time period of each month through monthly statistical query (average value in monthly time period) of the database;
solving method according to multiple linear regression W ═ (X' X)-1Time period T that X' can ask0OfA class number error point rate weight value W1 and a model number error point rate weight value W2;
the method for solving other time periods (T1, T2, … and T7) is the same, and only data corresponding to the error point rate of each time period in each month need to be filled in and calculated;
obtaining a weight table of error point rate by matrix operation and normalization, wherein W1Is the flight number point error rate weight, W2Is the model error Point Rate weight, W3-W10Is the weight of the error point rate of each time segment.
Preferably, the prediction algorithm processing flow comprises the steps of 1: summarizing all records of flights, and calculating the average error point rate of all flights;
step 2: summarizing all records of flights, and calculating the average error point rate of all airplane models;
and step 3: calculating the weight value of each dimension through data fitting;
and 4, step 4: classifying and summarizing (working days, double holidays, holidays) to obtain historical error points and error point rate of flights, airplane models and time periods;
and 5: scanning each classification summary table (working day, double holidays, holidays), predicting the error point rate of flights + airplane models + time periods within 7 days in the future, wherein the calculation formula is as follows:
P＝W1error rate of flight number + W2Type error dot rate + W1Dot error rate of ith time segment
If the data dimension (flight number, model number, time period) has no historical data, the corresponding error point rate is 0 to measure and calculate,
if the current day is both holiday and double-holiday, the final error point rate is the holiday error point rate and the double-holiday error point rate;
step 6: if total or partial error point rates are required, the categories (weekday, double holiday, holiday) and data dimensions (flight number, model, time period) are combined and averaged.
Compared with the prior art, the invention provides a method for predicting the airplane flight punctuality rate based on the probability theory, which has the following beneficial effects:
1. a prediction method of airplane flight punctuality rate based on probability theory is characterized in that a data model can be established and completed firstly through data mode design, then a database table is established according to the designed data model to facilitate data processing, then basic data including flight time, departure place, arrival place, airplane type, planned departure time, actual departure time, planned arrival time, incoming and outgoing port type and other information are recorded into a database to facilitate data analysis, then data are analyzed through establishing a dimension statistical model and a statistical algorithm flow, the punctuality number, the error number and the claim settlement error number of each data are counted, and a prediction algorithm 1 is adopted: the data fitting method based on the historical records can calculate the weight of the point error rate of the flight number, the weight of the point error rate of the model number and the weight of the point error rate of each time period, and stores the data into a database, thereby facilitating the statistics of big data, facilitating the prediction of the point error rate of the flight in a plurality of days in the future and providing technical support for improving the service quality of passengers;
2. a prediction method of airplane flight punctuality rate based on probability theory scans all classification summary tables (working days, double holidays and holidays) through a prediction algorithm processing flow, and predicts the error punctuality rate of flights + airplane models + time periods in 7 days in the future.
Drawings
FIG. 1 is a schematic flow chart of the system of the present invention;
FIG. 2 is a schematic flow chart of the algorithm;
FIG. 3 is a flight time record representation intent;
FIG. 4 is a statutory holiday representation intent;
FIG. 5 is a time period definition representation intention;
FIG. 6 shows the intent of the statistics of flight number miss points;
FIG. 7 is a diagram of a model error point statistic table;
FIG. 8 is a statistical representation of the node error in entering the port on holidays;
FIG. 9 is a schematic diagram of a claims point of error table;
FIG. 10 is a statistical representation of the arrival error points on weekdays;
FIG. 11 is a statistical representation of error points for double-holiday departure from port;
FIG. 12 is a statistical representation of the departure error points on holidays;
FIG. 13 is a statistical representation of departure error points on a working day;
FIG. 14 is a dimension weight representation intent;
FIG. 15 is a schematic diagram of a departure point error rate prediction table;
FIG. 16 is a schematic view of a working schedule.
In the figure: 1. designing a data mode; 2. inputting/importing original data; 3. establishing a dimension statistical model and a statistical algorithm process; 4. prediction algorithm 1: data fitting method based on history record; 5. and (5) processing flow of a prediction algorithm.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-2, a method for predicting an airplane flight punctuality rate based on a probability theory includes data pattern design 1, raw data entry/import 2, building a dimension statistical model, a statistical algorithm flow 3, and a prediction algorithm 1: a data fitting method based on historical records 4 and a prediction algorithm processing flow 5.
The data pattern design 1 comprises a flight time record table, legal holiday definition, daily time period definition, full-scale statistics on the error point rate of a flight number, full-scale statistics on the error point rate of an airplane model, classification statistics of port entry data (working days, holidays and double-holidays), classification statistics of port exit data (working days, holidays and double-holidays), classification data weight and port entry/exit prediction.
The raw data entry/import 2 comprises the entry of flight time, departure place, arrival place, model, planned departure time, actual departure time, planned arrival time, actual arrival time, and type of port entry and exit.
The step (3) of establishing the dimension statistical model and the statistical algorithm comprises the steps of establishing the dimension statistical model and establishing the statistical algorithm, wherein the dimension statistics comprises the following steps: flight dimension, model dimension, weather dimension, double-holiday dimension, workday dimension, and period dimension;
the algorithm flow comprises the following steps: the method comprises the following steps of screening and counting working day flight data, screening and counting double-holiday flight data, screening and counting holiday flight data, wherein the steps of screening and counting the working day flight data are as follows:
step 1: importing the defined holidays, time period definition and project data into a database;
step 2: and reading the database to take out a flight record and judging whether the record is a working day flight record, a double holiday flight record or a holiday flight record.
And step 3: judging whether the flight records are punctual, if so, accumulating punctual numbers, otherwise, accumulating error punctual numbers, if so, judging whether claim error punctuation is required to be settled, and if so, accumulating claim error punctual numbers;
and 4, step 4: judging whether the judged statistical records exist or not, if so, updating (related quantity), and if not, adding the records;
and 5: and reading the next flight record in the database, entering the step 2 if the flight record exists, and ending the screening if the flight record does not exist.
The specific steps of screening and counting the double-holiday flight data and the holiday flight data are the same as the specific steps of screening and counting the working day flight data.
Prediction algorithm 1: the data fitting method (4) based on the historical records adopts a multiple linear regression function for fitting, and the calculation method comprises the following steps:
setting Y as the comprehensive error point rate; x0The weather error point rate is obtained; x1The flight point error rate is; x2The machine type error point rate is obtained; x3The error point rate is 0 (early morning) in a time period; x4The error point rate is time period 1 (morning); x5Is the time period 2 (morning) error point rate; x6Is the time period 3 (noon) error point rate; x7Is time period 4 (afternoon) errorThe dot rate; x8The time period 5 (evening) error point rate; x9The error point rate is time period 6 (evening); x10The time period 7 (late night) error point rate;
the concrete formula is as follows:
the mathematical expression of the probability of error points in the time period Ti (i ═ 0,1, …,7) of the arrival or departure of all flights is:
Y(X1，X2，Ti)＝W1*X1+W2*X2+WTi*XTi(formula 1);
wherein W1，W2，WiIs a probability weight, and W1+W2+WTi1, (Ti ═ 0,1, …,7, corresponding to time periods 0-7), to obtain the weight value W1，W2，WTi(Ti ═ 0,1, …,7, corresponding to period 0-7), the following treatments were performed:
step 1: estimating W using maximum likelihood estimationiI.e. by
This is minimized by finding Ti (Ti 0,1, …,7, corresponding to time period 0-7) and Wi；
Step 2: m to (equation 2) is respectively to W1,W2,WTi(Ti 0,1, …,7 for time periods 0-7) and making the value equal to 0
3 normal equations can be obtained, and W can be obtained by solving the normal equations1，W2，WTi(Ti ═ 0,1, …,7, corresponding to periods 0-7);
according to the sample data (X)i,Yi) Acquiring the error point rate of each time period of each month through monthly statistical query (average value in monthly time period) of the database;
from multiple linear regressionSolution method W ═ X' X)-1Time period T that X' can ask0The flight number point error rate weight value W1 and the model point error rate weight value W2;
the method for solving other time periods (T1, T2, … and T7) is the same, and only data corresponding to the error point rate of each time period in each month need to be filled in and calculated;
obtaining a weight table of error point rate by matrix operation and normalization, wherein W1Is the flight number point error rate weight, W2Is the model error Point Rate weight, W3-W10Is the weight of the error point rate of each time segment.
The prediction algorithm processing flow 5 includes step 1: summarizing all records of flights, and calculating the average error point rate of all flights;
step 2: summarizing all records of flights, and calculating the average error point rate of all airplane models;
and step 3: calculating the weight value of each dimension through data fitting;
and 4, step 4: classifying and summarizing (working days, double holidays, holidays) to obtain historical error points and error point rate of flights, airplane models and time periods;
and 5: scanning each classification summary table (working day, double holidays, holidays), predicting the error point rate of flights + airplane models + time periods within 7 days in the future, wherein the calculation formula is as follows:
P＝W1error rate of flight number + W2Type error dot rate + W1Dot error rate of ith time segment
If the data dimension (flight number, model number, time period) has no historical data, the corresponding error point rate is 0 to measure and calculate,
if the current day is both holiday and double-holiday, the final error point rate is the holiday error point rate and the double-holiday error point rate;
step 6: if total or partial error point rates are required, the categories (weekday, double holiday, holiday) and data dimensions (flight number, model, time period) are combined and averaged.
During working, in order to establish convenience of dimension statistical model and statistical algorithm process, original flight takeoff data is recordedClassifying (working day, holiday and double holiday) and preliminarily summarizing, firstly, designing and establishing a data table, wherein the specific data table is as follows: the method comprises the following steps of (1) carrying out full-disk statistics on a flight time record table, legal holiday definition, daily time period definition, full-disk statistics on the error point rate of a flight number, full-disk statistics on the error point rate of an airplane model, classification statistics on port entry data (working days, holidays and double holidays), classification statistics on port exit data (working days, holidays and double holidays), classification data weight and port entry/exit prediction, and then importing the data into a data table, wherein the imported data comprises the following steps: the method comprises the following steps of inputting flight time, departure place, arrival place, model, planned departure time, actual departure time, planned arrival time, actual arrival time and entry and exit port types, analyzing imported data, counting error points, error point claim numbers and quasi points, introducing data through a prediction algorithm 1 according to a formula, calculating flight number error point rate weight, model error point rate weight and error point rate weight of each time period, and then according to the formula: p ═ W1Error rate of flight number + W2Type error dot rate + W1And predicting the dot error rate of the flight + airplane model + time period within 7 days in the future by the dot error rate of the ith time period.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (6)
1. A method for predicting airplane flight punctuality rate based on probability theory is characterized by comprising the following steps: the method comprises the steps of data pattern design (1), original data entry/import (2), dimension statistical model establishment, statistical algorithm flow (3) and prediction algorithm 1: a data fitting method (4) based on historical records and a prediction algorithm processing flow (5).
2. The method for predicting the airplane flight punctuality rate based on the probability theory as claimed in claim 1, wherein: the data mode design (1) comprises a flight time record table, legal holiday definition, daily time period definition, full-disk statistics on the error point rate of a flight number, full-disk statistics on the error point rate of an airplane model, classification statistics of port entry data (working days, holidays and double holidays), classification statistics of port exit data (working days, holidays and double holidays), classification data weight and port entry/exit prediction.
3. The method for predicting the airplane flight punctuality rate based on the probability theory as claimed in claim 1, wherein: the original data entry/import (2) comprises the steps of entering flight time, departure place, arrival place, model, planned departure time, actual departure time, planned arrival time, actual arrival time and port entering and exiting types.
4. The method for predicting the airplane flight punctuality rate based on the probability theory as claimed in claim 1, wherein: the step (3) of establishing the dimension statistical model and the statistical algorithm comprises the steps of establishing the dimension statistical model and establishing the statistical algorithm, wherein the dimension statistics comprises the following steps: flight dimension, model dimension, weather dimension, double-holiday dimension, workday dimension, and period dimension;
the algorithm flow comprises the following steps: the method comprises the following steps of screening and counting working day flight data, screening and counting double-holiday flight data, screening and counting holiday flight data, wherein the steps of screening and counting the working day flight data are as follows:
step 1: importing the defined holidays, time period definition and project data into a database;
step 2: and reading the database to take out a flight record and judging whether the record is a working day flight record, a double holiday flight record or a holiday flight record.
And step 3: judging whether the flight records are punctual, if so, accumulating punctual numbers, otherwise, accumulating error punctual numbers, if so, judging whether claim error punctuation is required to be settled, and if so, accumulating claim error punctual numbers;
and 4, step 4: judging whether the judged statistical records exist or not, if so, updating (related quantity), and if not, adding the records;
and 5: and reading the next flight record in the database, entering the step 2 if the flight record exists, and ending the screening if the flight record does not exist.
The specific steps of screening and counting the double-holiday flight data and the holiday flight data are the same as the specific steps of screening and counting the working day flight data.
5. The method for predicting the airplane flight punctuality rate based on the probability theory as claimed in claim 1, wherein: the prediction algorithm 1: the data fitting method (4) based on the historical records adopts a multiple linear regression function for fitting, and the calculation method comprises the following steps:
setting Y as the comprehensive error point rate; x1The flight point error rate is; x2The machine type error point rate is obtained; x3The error point rate is 0 (early morning) in a time period; x4The error point rate is time period 1 (morning); x5Is the time period 2 (morning) error point rate; x6Is the time period 3 (noon) error point rate; x7Is the error point rate of time period 4 (afternoon); x8The time period 5 (evening) error point rate; x9The error point rate is time period 6 (evening); x10The time period 7 (late night) error point rate;
the concrete formula is as follows:
the mathematical expression of the probability of error points in the time period Ti (i ═ 0,1, …,7) of the arrival or departure of all flights is:
Y(X1，X2，Ti)＝W1*X1+W2*X2+WTi*XTi(formula 1);
wherein W1，W2，WiIs a probability weight, and W1+W2+WTi1, (Ti ═ 0,1, …,7, corresponding to time periods 0-7), to obtain the weight value W1，W2，WTi(Ti ═ 0,1, …,7, corresponding to period 0-7), the following treatments were performed:
step 1: estimating W using maximum likelihood estimationiI.e. by
This is minimized by finding Ti (Ti 0,1, …,7, corresponding to time period 0-7) and Wi；
Step 2: m to (equation 2) is respectively to W1,W2,WTi(Ti 0,1, …,7 for time periods 0-7) and making the value equal to 0
3 normal equations can be obtained, and W can be obtained by solving the normal equations1，W2，WTi(Ti ═ 0,1, …,7, corresponding to periods 0-7);
according to the sample data (X)i,Yi) Acquiring the error point rate of each time period of each month through monthly statistical query (average value in monthly time period) of the database;
solving method according to multiple linear regression W ═ (X' X)-1Time period T that X' can ask0The flight number point error rate weight value W1 and the model point error rate weight value W2;
the method for solving other time periods (T1, T2, … and T7) is the same, and only data corresponding to the error point rate of each time period in each month need to be filled in and calculated;
obtaining a weight table of error point rate by matrix operation and normalization, wherein W1Is the flight number point error rate weight, W2Is the model error Point Rate weight, W3-W10Is the weight of the error point rate of each time segment.
6. The method for predicting the airplane flight punctuality rate based on the probability theory as claimed in claim 1, wherein: the prediction algorithm processing flow (5) comprises the following steps of 1: summarizing all records of flights, and calculating the average error point rate of all flights;
step 2: summarizing all records of flights, and calculating the average error point rate of all airplane models;
and step 3: calculating the weight value of each dimension through data fitting;
and 4, step 4: classifying and summarizing (working days, double holidays, holidays) to obtain historical error points and error point rate of flights, airplane models and time periods;
and 5: scanning each classification summary table (working day, double holidays, holidays), predicting the error point rate of flights + airplane models + time periods within 7 days in the future, wherein the calculation formula is as follows:
P＝W1error rate of flight number + W2Type error dot rate + W1Dot error rate of ith time segment
If the data dimension (flight number, model number, time period) has no historical data, the corresponding error point rate is 0 to measure and calculate,
if the current day is both holiday and double-holiday, the final error point rate is the holiday error point rate and the double-holiday error point rate;
step 6: if total or partial error point rates are required, the categories (weekday, double holiday, holiday) and data dimensions (flight number, model, time period) are combined and averaged.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110289449.4A CN112801421A (en) | 2021-03-18 | 2021-03-18 | Method for predicting airplane flight punctuality rate based on probability theory |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110289449.4A CN112801421A (en) | 2021-03-18 | 2021-03-18 | Method for predicting airplane flight punctuality rate based on probability theory |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112801421A true CN112801421A (en) | 2021-05-14 |
Family
ID=75817157
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110289449.4A Pending CN112801421A (en) | 2021-03-18 | 2021-03-18 | Method for predicting airplane flight punctuality rate based on probability theory |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112801421A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105184729A (en) * | 2015-09-18 | 2015-12-23 | 黑龙江大学 | Airplane scheduling module and method based on probability theory |
| KR20160036310A (en) * | 2014-09-25 | 2016-04-04 | 한국항공대학교산학협력단 | Apparatus and method for aircraft arrival time prediction using trajectory pattern |
| CN105844346A (en) * | 2016-03-17 | 2016-08-10 | 福州大学 | Flight delay prediction method based on ARIMA model |
| CN107103753A (en) * | 2016-02-22 | 2017-08-29 | 财团法人资讯工业策进会 | Traffic time prediction system, traffic time prediction method, and traffic model establishment method |
| CN108197081A (en) * | 2017-11-03 | 2018-06-22 | 上海敬之网络科技有限公司 | A kind of data actuarial model method for building up of flight delay danger |
| CN111144631A (en) * | 2019-12-19 | 2020-05-12 | 南京航空航天大学 | Flight delay real-time probability prediction method based on Bayesian network algorithm |
-
2021
- 2021-03-18 CN CN202110289449.4A patent/CN112801421A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160036310A (en) * | 2014-09-25 | 2016-04-04 | 한국항공대학교산학협력단 | Apparatus and method for aircraft arrival time prediction using trajectory pattern |
| CN105184729A (en) * | 2015-09-18 | 2015-12-23 | 黑龙江大学 | Airplane scheduling module and method based on probability theory |
| CN107103753A (en) * | 2016-02-22 | 2017-08-29 | 财团法人资讯工业策进会 | Traffic time prediction system, traffic time prediction method, and traffic model establishment method |
| CN105844346A (en) * | 2016-03-17 | 2016-08-10 | 福州大学 | Flight delay prediction method based on ARIMA model |
| CN108197081A (en) * | 2017-11-03 | 2018-06-22 | 上海敬之网络科技有限公司 | A kind of data actuarial model method for building up of flight delay danger |
| CN111144631A (en) * | 2019-12-19 | 2020-05-12 | 南京航空航天大学 | Flight delay real-time probability prediction method based on Bayesian network algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 杨新湦，王倩，刘俊，张宝成: "大数据时代下的航班延误组合预测", 中国科技论文, vol. 11, no. 19, pages 1 - 5 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103632212B (en) | System and method for predicating time-varying user dynamic equilibrium network-evolved passenger flow | |
| CN110390349A (en) | Bus passenger flow volume based on XGBoost model predicts modeling method | |
| CN108564391B (en) | Shared electric vehicle demand prediction method and system considering subjective and objective information | |
| CN109242170B (en) | Urban road management system and method based on data mining technology | |
| CN110555990A (en) | effective parking space-time resource prediction method based on LSTM neural network | |
| CN110348614A (en) | It is a kind of obtain passenger OD method and bus passenger flow prediction technique | |
| CN111179592B (en) | Urban traffic prediction method and system based on spatio-temporal data flow fusion analysis | |
| CN115953186A (en) | Network appointment demand pattern recognition and short-time demand prediction method | |
| CN109949005A (en) | A kind of airdrome scene flight ensures method, system and the terminal of operating analysis | |
| CN111507762A (en) | Urban taxi demand prediction method based on multi-task co-prediction neural network | |
| CN110889092A (en) | Short-time large-scale activity peripheral track station passenger flow volume prediction method based on track transaction data | |
| CN113672846A (en) | Network appointment scheduling method and device, electronic equipment and storage medium | |
| CN114331234A (en) | Rail transit passenger flow prediction method and system based on passenger travel information | |
| CN113821547B (en) | Rapid and efficient short-time prediction method, system and storage medium for occupancy of parking lot | |
| CN111222703A (en) | Method and device for predicting passenger travel mode | |
| CN109409563B (en) | Method, system and storage medium for analyzing real-time number of people in public transport operation vehicle | |
| CN110796315A (en) | Departure flight delay prediction method based on aging information and deep learning | |
| CN113987944A (en) | Subway station-entering passenger flow prediction method and device based on Prophet model | |
| Monmousseau et al. | Predicting passenger flow at Charles de Gaulle airport security checkpoints | |
| Wang | An intelligent passenger flow prediction method for pricing strategy and hotel operations | |
| CN111275305B (en) | Fair assessment method for traditional taxi and network appointment service in peak time | |
| Li et al. | Characteristics analysis of bus stop failure using automatic vehicle location data | |
| CN112801421A (en) | Method for predicting airplane flight punctuality rate based on probability theory | |
| CN117436653A (en) | Prediction model construction method and prediction method for travel demands of network about vehicles | |
| CN115359659B (en) | Lane opening and closing configuration method and system |
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 |