CN110796315A - Departure flight delay prediction method based on aging information and deep learning - Google Patents
Departure flight delay prediction method based on aging information and deep learning Download PDFInfo
- Publication number
- CN110796315A CN110796315A CN201911066077.8A CN201911066077A CN110796315A CN 110796315 A CN110796315 A CN 110796315A CN 201911066077 A CN201911066077 A CN 201911066077A CN 110796315 A CN110796315 A CN 110796315A
- Authority
- CN
- China
- Prior art keywords
- flight
- data
- information data
- deep learning
- delay
- 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.)
- Granted
Links
- 238000013135 deep learning Methods 0.000 title claims abstract description 22
- 238000000034 method Methods 0.000 title claims abstract description 22
- 230000032683 aging Effects 0.000 title claims abstract description 17
- 230000006870 function Effects 0.000 claims description 21
- 230000004913 activation Effects 0.000 claims description 8
- 238000013136 deep learning model Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 238000013210 evaluation model Methods 0.000 claims description 2
- 238000011428 standard deviation standardization method Methods 0.000 claims description 2
- 238000012360 testing method Methods 0.000 abstract description 8
- 238000003062 neural network model Methods 0.000 abstract 1
- 230000003111 delayed effect Effects 0.000 description 10
- 238000012549 training Methods 0.000 description 9
- 238000012795 verification Methods 0.000 description 8
- 230000010006 flight Effects 0.000 description 7
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 210000002569 neuron Anatomy 0.000 description 5
- 238000011160 research Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000001934 delay Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000010200 validation analysis 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Operations Research (AREA)
- Evolutionary Computation (AREA)
- Quality & Reliability (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an departure flight delay prediction method based on aging information and deep learning, which relates to the technical field of computer prediction, and is characterized in that a flight delay situation is predicted by using a deep neural network model in combination with aging flight information data and aging meteorological data and adopting a departure flight delay prediction model, a numerical test is carried out by using real data, and the result shows that the constructed delay prediction model can obtain higher flight delay prediction precision in a shorter time and has higher flight delay prediction aging; meanwhile, with the increase of the delay time threshold value, the prediction precision is continuously improved, and the loss value is continuously reduced; particularly, when the threshold value is 60 minutes, the prediction accuracy of the model can reach 91.26%, which illustrates the effectiveness of the method of the invention.
Description
Technical Field
The invention relates to the technical field of computer prediction, in particular to an outbound flight delay prediction method based on aging information and deep learning.
Background
Due to the weather, the flow, passengers and the like, part of flights are delayed or cancelled frequently, and a large number of flight delays are easily formed under the influence of time and space correlation of a flight network. The conflict between passengers and airports and airlines is often caused by a great deal of flight delay, and the conflict becomes a potential problem affecting the safety of the public society. Therefore, early prediction of flight delay can give early warning to airlines, airports and related units, and precious time is gained for making measures for delaying flight delay, so that economic loss caused by flight delay is reduced, and the satisfaction degree of passengers is improved; therefore, flight delay prediction has important practical significance for the civil aviation industry.
A large number of aviation workers have conducted research on flight delay prediction problems from different perspectives. Most of the current researches utilize flight information data, weather data and other data to predict flight delay, and the influence of the time efficiency of input data on the time efficiency of the flight delay prediction is not considered, so that the time efficiency of the prediction result is not high.
Disclosure of Invention
The embodiment of the invention provides an outbound flight delay prediction method based on aging information and deep learning, which can solve the problems in the prior art.
The invention provides an outbound flight delay prediction method based on aging information and deep learning, which comprises the following steps:
acquiring flight information data and meteorological information data;
converting the outbound flight delay prediction problem into a form of g (X, W) according to the flight information data and the meteorological information data, wherein X represents the flight information data, W represents the meteorological information data, when g (X, W) is 1, the flight delay is represented, when g (X, W) is 0, the flight delay is not represented, searching the relationship between the flight information data in the form of g (X, W) and the meteorological information data by using a deep learning model, and further establishing an outbound flight delay prediction model based on deep learning;
and predicting flight delay by adopting an outbound flight delay prediction model based on deep learning.
The method for predicting the departure flight delay based on the aging information and the deep learning can achieve higher prediction accuracy by using flight information data and meteorological data. By setting different flight delay time thresholds, the prediction accuracy of the model is continuously increased along with the increase of the flight delay threshold, and the prediction accuracy of the model can reach 91.26% when the threshold is 60 minutes. Through comparative analysis of the prediction accuracy of the model on the training set, the verification set and the test set, the model has better generalization performance. Through analysis, the model has lower real-time requirement on input data, so that the model theoretically has higher flight delay prediction timeliness, and the practical application value of the method is further improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a graph showing the variation of prediction accuracy with the number of iterations when the delay time threshold is 15 min;
FIG. 3 is a graph of the variation of the loss value with the number of iterations for a delay time threshold of 15 min;
FIG. 4 is a graph showing the variation of prediction accuracy with the number of iterations when the delay time threshold is 30 min;
FIG. 5 is a graph of the variation of loss value with iteration number for a delay time threshold of 30 min;
FIG. 6 is a graph showing the variation of prediction accuracy with the number of iterations when the delay time threshold is 60 min;
fig. 7 shows the variation of the loss value with the number of iterations for a delay time threshold of 60 min.
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.
Before describing the process of the present invention, the definitions of some terms are explained:
definition 1 flight delay, which means the actual flight arrival gear time atLater than the planned arrival time
Over 15 minutes.
Definition 2 flight departure delay (flight departure delay), which means the time d of removing the gear when the flight actually departs from the porttLater than the planned departure time
Over 15 minutes.
Defining 3 flight delay prediction, namely giving out whether the flight will be delayed or the time of the flight delay before the flight delay occurs by certain technology and method.
Flight delay prediction problem classification. According to different stages of flight delay occurrence, flight delay prediction problems can be divided into departure flight delay prediction, route flight delay prediction and inbound flight delay prediction.
Defining 4 flight delay forecast time effectiveness, namely the time of a flight delay forecast result is given by a certain technology and method and the length of the scheduled takeoff time of the flight, namely
Wherein p istPredicting a time to obtain a result for flight delay;
is the scheduled departure time of the flight. Commonly abbreviated as "pt-
Delay false alarm"2 small delay false alarms", "10 small delay false alarms", "24 small delay false alarms" etc. are common.
Defining 5 time efficiency information, namely providing key information of a certain time length compared with the departure advance of the flight by certain technology and method.
The typical weather information is the weather forecast of 40 days, 15 days, 7 days and 24 hours; the actual time for removing the wheel chock is generally not more than 1.5 hours; in order to utilize more accurate information as much as possible and give longer-time flight delay forecast as much as possible, the method adopts 24-hour weather forecast instead of actual wheel shift withdrawal time.
The invention researches the problem of delay prediction of departure flights from the perspective of passengers. From a passenger perspective, flight delays of 15 to 30 minutes are often acceptable, so that different delay periods are selected as the threshold T for determining whether a flight is delayedhTo carry out the study, namely:
here ThRespectively adopting 15min, 30min and 60 min.
Defining 6 flight information data which comprise data such as an airline company, departure date of a flight, planned departure time of the flight, actual departure time of the flight, an originating airport, a destination airport, a flight distance and the like; generally denoted as X.
Defining 7 meteorological information data including data of observation time, temperature, air pressure, visibility, cloud height, cloud amount, wind speed, wind direction, weather phenomenon rain, snow and the like of an airport, and special weather thunderstorm and the like of the airport; generally denoted as W.
Referring to fig. 1, the invention provides an outbound flight delay prediction method based on aging information and deep learning, which comprises the following steps:
step 1, acquiring flight information data and meteorological information data, and preprocessing the data.
The acquired weather information data in the invention is weather forecast data 24 hours before flight take-off, and the pretreatment of the flight information data and the weather information data comprises the following steps:
(1) deleting other data in the acquired original data except the selected flight information data and the weather information data;
(2) deleting the flight cancellation data in the flight information data;
(3) converting the data of the weather phenomenon group in the weather information data into numerical data, wherein the conversion rule is as follows: if the weather phenomenon exists, setting the data to be 1, otherwise, setting the data to be 0;
(4) discrete data such as airports, dates and the like in the flight information data are converted into n-bit binary character strings through one-hot coding;
(5) standardizing the numerical data in the flight information data and the meteorological information data by a standard deviation standardization method:
wherein the content of the first and second substances,
σ is the standard deviation of the raw data, which is the mean of the raw data.
Step 2, according to the preprocessed flight information data and weather information data, converting the problem of delay prediction of the outgoing flight into the following form:
wherein
For flight information data, X1,X2,…,X1414 items of data, namely an originating airport, a destination airport, a scheduled departure time of a flight, an actual arrival time of the flight and the like.
As meteorological data, W1,W2,…,W18The weather conditions of the starting airport respectively comprise 18 items of data such as visibility, humidity, temperature, air pressure, wind speed, wind direction, an airport where the observation station is located, observation time and the like.
And searching the relation between the flight information data and the meteorological information data in the g (X, W) form by using a deep learning model, and further establishing an departure flight delay prediction model based on deep learning.
According to the method, a deep learning model with the depth of 8 is selected to establish an outbound flight delay prediction model, a dropout regularization layer is added behind each full-connection layer according to an overfitting phenomenon existing in deep learning, and meanwhile, a loss function and an activation function are selected as follows.
The flight delay prediction problem is essentially a binary problem, and the cross information entropy function has better performance in processing the binary problem, so that the cross information entropy function is selected as a loss function of an evaluation model:
regarding the selection of the activation function, the hidden layer in the present invention selects the tanh function as the activation function:
and the problem of departure flight delay prediction is a class-two classification problem, so that a sigmod function is selected as an activation function of an output layer:
and 3, predicting flight delay by adopting an outbound flight delay prediction model based on deep learning.
Simulation test and result analysis
The data used are derived from flight data of the U.S. department of transportation 2017, flight delay statistics, and historical data observed by weather stations at airports of the U.S. national weather data center 2017. The experimental training data set, the verification data set and the test data set are 211695 pieces of data in total selected from departure flight data of san Francisco airports, wherein the training data set comprises 1711472 pieces, the verification data set comprises 19053 pieces and the test data set comprises 21170 pieces. The departure flight delay prediction model based on deep learning specifically comprises 8 fully-connected layers, wherein a dropout regularization layer is added behind each fully-connected layer, tanh functions among an input layer, a hidden layer and all hidden layers are selected as activation functions, and a sigmod function is selected as an activation function between the hidden layer and an output layer because the departure flight delay prediction problem is a two-classification problem. The input layer neuron configuration is determined according to the number of fused data items, and the number of neurons in fusing flight information data and meteorological data is 159. The neuron configuration of each hidden layer is shown in Table 1.
TABLE 1 hidden layer neuron configurations
| Hidden layer number | Number of neurons |
| First hidden layer | 120 |
| Second hidden layer | 120 |
| Third hidden layer | 120 |
| The fourth hidden layer | 120 |
| Fifth hideLayer(s) | 120 |
| The sixth hidden layer | 80 |
Flight delay prediction precision also called flight prediction accuracy PaccRefers to the ratio of the number of correctly predicted flights to the total number of flights:
the loss value is an evaluation value of the distance between the target value and the predicted value. The invention selects the cross information entropy as a loss function to be used for calculating the loss value between the target value and the prediction. The accuracy and the loss value are important indexes for evaluating the quality of the model, so the method selects the prediction precision value and the loss value to evaluate and analyze the model.
The following gives a symbolic illustration of the flight delay prediction result confusion matrix. A True Positive (TP) instance in which a flight is actually delayed and the predicted delay is not delayed, a True Negative (TN) instance in which a flight is not delayed and the predicted delay is not delayed, a False Positive (FP) instance in which a flight is not delayed and the predicted delay is not delayed, a False Negative (FN) instance in which a flight is actually delayed and the predicted delay is not delayed, are detailed in table 2.
TABLE 2 flight delay prediction confusion matrix
The prediction accuracy and loss value analysis under different thresholds are given below.
The numerical test respectively selects 15 minutes, 30 minutes and 60 minutes as flight delay time thresholds, and the flight delay time thresholds are obtained by performing simulation test on the model, and the model prediction accuracy and the loss value under the corresponding thresholds are shown in the figures 2 to 7 along with the change of iteration times on a training set and a verification set.
From fig. 2, it can be obtained that the prediction accuracy of the model on the training set and the verification set is gradually improved to 80.51% along with the iteration number, and the flight delay prediction aging is 24 hours. Fig. 3 shows that the loss values over the training set and over the validation set steadily decline with the number of iterations, thereby illustrating the effectiveness of the model.
By comparing fig. 2 to fig. 7, it can be seen that the accuracy stability values of the model in the training set and the verification set are continuously improved and the loss stability value is continuously reduced with the increase of the threshold, and in addition, according to the change of the accuracy of the model in the training set and the verification set with the iteration number, the overfitting condition of the model is lighter, so that the model is more stable. Meanwhile, the precision value of the model on the test set (see table 3) and the final precision value which tends to be stable on the training set and the verification set are obtained with little difference, which indicates that the model has better generalization effect.
TABLE 3 prediction accuracy of model under different thresholds
It can be seen from table 3 that the prediction accuracy of the model is continuously increased with the increase of the threshold, because flight delay prediction is a partial classification problem, most of flights which do not have delay are occupied, the proportion of flights which do not have delay is further improved with the increase of the threshold, and the prediction accuracy is further improved, and meanwhile, for passengers, whether flights have delay of 15 to 30 minutes or not usually does not affect the travel experience, but if the delay is as long as 60 minutes or even more, the travel experience of the passengers is greatly affected, and the prediction accuracy of the model can reach 91.26% when the threshold is 60 minutes, so the model has high practical value.
Flight information data in the model of the invention does not contain actual wheel files/wheel starting time and the like, so that the flight information data can be obtained in advance; the 24-hour weather forecast is relatively accurate, so that theoretically, the departure flight delay prediction model based on the aging information and the deep learning can realize 24-hour delay forecast, and the model has higher practical application value.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (4)
1. The method for predicting departure flight delay based on aging information and deep learning is characterized by comprising the following steps:
acquiring flight information data and meteorological information data;
converting the outbound flight delay prediction problem into a form of g (X, W) according to the flight information data and the meteorological information data, wherein X represents the flight information data, W represents the meteorological information data, when g (X, W) is 1, the flight delay is represented, when g (X, W) is 0, the flight delay is not represented, searching the relationship between the flight information data in the form of g (X, W) and the meteorological information data by using a deep learning model, and further establishing an outbound flight delay prediction model based on deep learning;
and predicting flight delay by adopting an outbound flight delay prediction model based on deep learning.
2. The method for predicting departure flight delay based on aging information and deep learning of claim 1, wherein after acquiring the flight information data and weather information data, preprocessing is further performed, and the preprocessing comprises the following steps:
deleting other data in the acquired original data except the selected flight information data and the weather information data;
deleting the flight cancellation data in the flight information data;
converting the data of the weather phenomenon group in the weather information data into numerical data, wherein the conversion rule is as follows: if the weather phenomenon exists, setting the data to be 1, otherwise, setting the data to be 0;
discrete data such as airports, dates and the like in the flight information data are converted into binary character strings through one-hot coding;
and standardizing the numerical data in the flight information data and the meteorological information data by a standard deviation standardization method.
3. The method for predicting departure flight delay based on aging information and deep learning of claim 1, wherein the acquired weather information data is weather forecast data 24 hours before flight departure.
4. The method for predicting the departure flight delay based on the aging information and the deep learning of claim 1, wherein the model for predicting the departure flight delay based on the deep learning is built by adopting a deep learning model with the depth of 8, a dropout regularization layer is arranged behind each full-connection layer in the deep learning model, a cross information entropy function is adopted as a loss function of an evaluation model, a tanh function is selected as an activation function of a hidden layer, and a sigmod function is selected as an activation function of an output layer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911066077.8A CN110796315B (en) | 2019-11-04 | 2019-11-04 | Departure flight delay prediction method based on aging information and deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911066077.8A CN110796315B (en) | 2019-11-04 | 2019-11-04 | Departure flight delay prediction method based on aging information and deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110796315A true CN110796315A (en) | 2020-02-14 |
| CN110796315B CN110796315B (en) | 2023-11-28 |
Family
ID=69442527
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911066077.8A Active CN110796315B (en) | 2019-11-04 | 2019-11-04 | Departure flight delay prediction method based on aging information and deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110796315B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112365037A (en) * | 2020-10-29 | 2021-02-12 | 杭州富阳富创大数据产业创新研究院有限公司 | Airport airspace flow prediction method based on long-term and short-term data prediction model |
| CN112686309A (en) * | 2020-12-29 | 2021-04-20 | 北京维艾思气象信息科技有限公司 | Aircraft test flight condition prediction method and device based on actual observation |
| CN113128769A (en) * | 2021-04-22 | 2021-07-16 | 上海工程技术大学 | Intelligent flight delay prediction method based on deep learning |
| CN116362430A (en) * | 2023-06-02 | 2023-06-30 | 中国民航大学 | Flight delay prediction method and system based on online increment MHHA-SRU |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201814781D0 (en) * | 2018-09-11 | 2018-10-24 | Satavia Ltd | System and method for aircraft flight planning |
| CN109448445A (en) * | 2018-09-05 | 2019-03-08 | 南京航空航天大学 | Flight based on shot and long term Memory Neural Networks is delayed grading forewarning system method |
| CN109492334A (en) * | 2018-12-11 | 2019-03-19 | 青岛心中有数科技有限公司 | Delayed method for establishing model, prediction technique and device |
| CN109948716A (en) * | 2019-03-25 | 2019-06-28 | 中国民航大学 | A kind of airport delay prediction technique based on region residual sum LSTM network |
-
2019
- 2019-11-04 CN CN201911066077.8A patent/CN110796315B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109448445A (en) * | 2018-09-05 | 2019-03-08 | 南京航空航天大学 | Flight based on shot and long term Memory Neural Networks is delayed grading forewarning system method |
| GB201814781D0 (en) * | 2018-09-11 | 2018-10-24 | Satavia Ltd | System and method for aircraft flight planning |
| CN109492334A (en) * | 2018-12-11 | 2019-03-19 | 青岛心中有数科技有限公司 | Delayed method for establishing model, prediction technique and device |
| CN109948716A (en) * | 2019-03-25 | 2019-06-28 | 中国民航大学 | A kind of airport delay prediction technique based on region residual sum LSTM network |
Non-Patent Citations (15)
| Title |
|---|
| 吴仁彪等: "基于双通道卷积神经网络的航班延误预测模型", 《计算机应用》 * |
| 吴仁彪等: "基于双通道卷积神经网络的航班延误预测模型", 《计算机应用》, no. 07, 3 April 2018 (2018-04-03) * |
| 吴仁彪等: "基于深度SE-DenseNet的航班延误预测模型", 《电子与信息学报》 * |
| 吴仁彪等: "基于深度SE-DenseNet的航班延误预测模型", 《电子与信息学报》, no. 06, 5 December 2018 (2018-12-05) * |
| 吴仁彪等: "融合气象数据的并行化航班延误预测模型", 《信号处理》 * |
| 吴仁彪等: "融合气象数据的并行化航班延误预测模型", 《信号处理》, 31 May 2018 (2018-05-31), pages 505 - 509 * |
| 屈景怡等: "基于区域残差和LSTM网络的机场延误预测模型", 《通信学报》 * |
| 屈景怡等: "基于区域残差和LSTM网络的机场延误预测模型", 《通信学报》, no. 04, 25 April 2019 (2019-04-25) * |
| 徐海文;韩松臣;刘晓东;: "基于旅客角度的航班延误影响因素分析", 中国市场, no. 52 * |
| 王红等: "民航突发事件领域本体关系提取方法的研究", 《计算机科学与探索》 * |
| 王红等: "民航突发事件领域本体关系提取方法的研究", 《计算机科学与探索》, no. 02, 17 May 2019 (2019-05-17) * |
| 罗凤娥;张成伟;刘安;: "基于数据挖掘的航班延误预警管理分析", 计算机科学, no. 1 * |
| 谢华等: "基于BP神经网络的机场离港延误等级预测", 《航空计算技术》 * |
| 谢华等: "基于BP神经网络的机场离港延误等级预测", 《航空计算技术》, no. 03, 25 May 2019 (2019-05-25), pages 71 - 74 * |
| 陈佳炀;: "航班延误的现状、原因及治理", 智富时代, no. 02 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112365037A (en) * | 2020-10-29 | 2021-02-12 | 杭州富阳富创大数据产业创新研究院有限公司 | Airport airspace flow prediction method based on long-term and short-term data prediction model |
| CN112686309A (en) * | 2020-12-29 | 2021-04-20 | 北京维艾思气象信息科技有限公司 | Aircraft test flight condition prediction method and device based on actual observation |
| CN113128769A (en) * | 2021-04-22 | 2021-07-16 | 上海工程技术大学 | Intelligent flight delay prediction method based on deep learning |
| CN116362430A (en) * | 2023-06-02 | 2023-06-30 | 中国民航大学 | Flight delay prediction method and system based on online increment MHHA-SRU |
| CN116362430B (en) * | 2023-06-02 | 2023-08-01 | 中国民航大学 | Flight delay prediction method and system based on online increment MHHA-SRU |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110796315B (en) | 2023-11-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yazdi et al. | Flight delay prediction based on deep learning and Levenberg-Marquart algorithm | |
| Fabbian et al. | Application of artificial neural network forecasts to predict fog at Canberra International Airport | |
| CN110796315B (en) | Departure flight delay prediction method based on aging information and deep learning | |
| CN107818382B (en) | Flight arrival time prediction method | |
| Kern et al. | Data-driven aircraft estimated time of arrival prediction | |
| Choi et al. | Hybrid machine learning and estimation-based flight trajectory prediction in terminal airspace | |
| Achenbach et al. | Prescriptive analytics in airline operations: Arrival time prediction and cost index optimization for short-haul flights | |
| CN106779222B (en) | Airport ground waiting time prediction method and device | |
| Yang et al. | Airport arrival flow prediction considering meteorological factors based on deep‐learning methods | |
| Zhang et al. | Data‐driven flight time prediction for arrival aircraft within the terminal area | |
| Subramanian et al. | Deep-learning based time series forecasting of go-around incidents in the national airspace system | |
| CN115953186A (en) | Network appointment demand pattern recognition and short-time demand prediction method | |
| CN115358491A (en) | Subway passenger flow prediction method and system based on CEEMDAN-LSTM | |
| Lui et al. | Weather impact quantification on airport arrival on-time performance through a Bayesian statistics modeling approach | |
| CN112132366A (en) | Prediction system for flight clearance rate | |
| CN113221472B (en) | Passenger flow prediction method based on LSTM | |
| Behere | A Reduced Order Modeling Methodology for the Parametric Estimation and Optimization of Aviation Noise | |
| Lu et al. | Flight delay prediction using gradient boosting machine learning classifiers | |
| CN113284369A (en) | Prediction method for actual measurement airway data based on ADS-B | |
| CN111175852B (en) | Airport fog forecast early warning method based on long-time memory algorithm | |
| Chandramouleeswaran et al. | Machine learning prediction of airport delays in the US air transportation network | |
| Widiyaningtyas et al. | Use of ARIMA method to predict the number of train passenger in Malang City | |
| Jiang et al. | A multi-index prediction method for flight delay based on long short-term memory network model | |
| LU501642B1 (en) | Prediction method of departure flight delay based on timely information and deep learning | |
| Cheng et al. | Risk management using big real time 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |