CN116029570B - Construction method and device of auxiliary decision-making system for tower controller - Google Patents
Construction method and device of auxiliary decision-making system for tower controller Download PDFInfo
- Publication number
- CN116029570B CN116029570B CN202310296126.7A CN202310296126A CN116029570B CN 116029570 B CN116029570 B CN 116029570B CN 202310296126 A CN202310296126 A CN 202310296126A CN 116029570 B CN116029570 B CN 116029570B
- Authority
- CN
- China
- Prior art keywords
- aircraft
- decision
- task information
- flight
- tower controller
- 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.)
- Active
Links
Images
Classifications
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention provides a construction method and a device for a tower controller auxiliary decision-making system, which relate to the technical field of data processing and comprise the steps of acquiring working task information of a tower controller and flight data of aircrafts, carrying out hierarchical analysis on the working task information of the tower controller, determining key decision-making task information of the tower controller, establishing an auxiliary decision-making model based on the flight data of the aircrafts and the key decision-making task information of the tower controller, and constructing an auxiliary decision-making interface and prompting the tower controller to make decisions based on the auxiliary decision-making model.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a device for constructing a tower controller auxiliary decision-making system.
Background
The tower controller is used as an important component in an aviation system to execute dynamic and cognitively complex supervisory control tasks, and is faced with continuously increasing flow and increasingly tense airspace resources, so that the tower controller is required to ensure the safety interval of an aircraft and accelerate the rapid flow of the flow, and the requirements of the two targets of safety and high efficiency on the same direction bring greater pressure and higher requirements to the tower controller. The time for conflict resolution of interval conflict judgment and decision task between aircrafts by the tower controllers is very limited, and huge psychological stress is given to the tower controllers, so that a system capable of assisting the tower controllers in decision making is needed to be constructed, an aircraft intervention decision making scheme is provided, and the efficiency of the tower controllers is improved.
Disclosure of Invention
The invention aims to provide a method and a device for constructing a tower controller auxiliary decision-making system so as to solve the problems. In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
in a first aspect, the present application provides a method for constructing a tower controller auxiliary decision-making system, including:
the method comprises the steps of obtaining tower controller work task information and flight data of an aircraft, wherein the tower controller work task information comprises release seat work task information, ground seat work task information and tower seat work task information;
performing hierarchical analysis on the task information of the tower controller staff to determine key decision task information of the tower controller, wherein the key decision task information is task information with the largest decision difficulty of the tower controller;
and establishing an auxiliary decision-making model based on the flight data of the aircraft and the key decision-making task information of the tower controller, and establishing an auxiliary decision-making interface and prompting the tower controller to make decisions based on the auxiliary decision-making model.
In a second aspect, the present application further provides a device for constructing a tower controller auxiliary decision-making system, which is characterized by comprising:
the system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring tower controller work task information and flight data of an aircraft, and the tower controller work task information comprises release seat work task information, ground seat work task information and tower seat work task information;
the analysis unit is used for carrying out hierarchical analysis on the task information of the tower controller staff to determine the key decision task information of the tower controller, wherein the key decision task information is the task information with the largest decision difficulty of the tower controller;
the decision unit is used for establishing an auxiliary decision model based on the flight data of the aircraft and the key decision task information of the tower controller, establishing an auxiliary decision interface based on the auxiliary decision model and prompting the tower controller to make decisions.
The beneficial effects of the invention are as follows:
the method determines the difficulty score of each decision by an analytic hierarchy process, then determines the task which is most difficult to make the decision aiming at the tower decision task, and further builds an auxiliary decision model, wherein the distance of the flight track of each aircraft can be judged by predicting the flight track of each aircraft, and then the decision is automatically made.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the embodiments of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for constructing a tower controller aid decision making system according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a construction apparatus of a tower controller auxiliary decision-making system according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an interface display of a tower controller aid decision making system according to an embodiment of the present invention.
The marks in the figure: 701. an acquisition unit; 702. an analysis unit; 703. a decision unit; 7021. an analysis subunit; 7022. a first processing subunit; 7023. a first computing subunit; 7024. a second computing subunit; 7031. a first predictor unit; 7032. a first judgment subunit; 7033. a second judgment subunit; 70311. a second processing subunit; 70312. a third processing subunit; 70313. a fourth processing subunit; 70314. a fifth processing subunit; 703131, sixth processing subunit; 703132, a second predictor unit; 703133, seventh processing subunit; 703141, eighth processing subunit; 703142, a third calculation subunit; 703143, ninth processing subunit; 703144, tenth processing subunit.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Example 1
The embodiment provides a method for constructing a tower controller auxiliary decision-making system.
Referring to fig. 1 and 3, the method is shown to include step S1, step S2 and step S3.
Step S1, acquiring tower controller work task information and flight data of an aircraft, wherein the tower controller work task information comprises release seat work task information, ground seat work task information and tower seat work task information;
it will be appreciated that this step provides for later data recall by determining all of the work tasks of the tower controller and the flight data of the aircraft, including the position information of the aircraft, the speed information of the aircraft and the wake length information of the aircraft, and by receiving the data sent by the positioning and speed measuring devices on the aircraft and storing the data, including aircraft, unmanned aircraft, etc.
Step S2, performing hierarchical analysis on the task information of the tower controller staff to determine key decision task information of the tower controller, wherein the key decision task information is task information with the largest decision difficulty of the tower controller;
in the step, the task information which is most difficult to make a decision in the tower controller work task information is quantitatively analyzed through a scientific method by carrying out hierarchical analysis on all the tower controller work task information, and in the step, the step S2 comprises the steps S21, S22, S23 and S24.
S21, performing hierarchical analysis on the task information of the tower controller staff, and establishing a hierarchical structure model, wherein the hierarchical structure model comprises a working area layer, a working task layer and a working target layer;
it can be understood that in this step, classification analysis is performed on task information of all tower control staff, and the task information is divided into a working area layer, a working task layer and a working target layer which are sequentially formed from top to bottom, so that the task information is classified, and the hierarchy and the category to which each working task belongs are determined.
S22, scoring the decision difficulty of each factor in the hierarchical structure model based on a 1-9 scale method, normalizing all scoring results, and converting the processed data into a discrimination matrix;
it can be understood that in the step, decision difficulty scoring is carried out on each factor in the hierarchical structure model through a 1-9 scale method, wherein a method for scoring difficulty can also use a Likert seven-point scoring method, and a discrimination matrix is obtained after normalization processing;
the discrimination matrix is shown in formula (1):
（1）
wherein: f is a discrimination matrix;
the importance ratio of the element i and the element j of the current level to the previous level is scaled; i and j are different kinds of factors, respectively; n is the dimension of the hierarchical model.
Step S23, respectively calculating the eigenvectors and the maximum eigenvalues of the discrimination matrix based on the discrimination matrix, and carrying out consistency test processing on the discrimination matrix to obtain a test result;
it can be understood that the step is also based on the discriminant matrix to perform normalization processing according to column vectors to obtain a normalized matrix; and then adding the normalized matrixes according to rows to obtain feature vectors, calculating the maximum feature values based on the feature vectors, and then carrying out consistency test for ensuring the rationality of the scheme weights, wherein the consistency test is required to be carried out on the judgment matrixes, and indexes for measuring the deviation consistency of the judgment matrixes are obtained based on the maximum feature values and a formula (2), wherein the formula (2) is as follows:
（2）
wherein: r is a consistency index;
the maximum eigenvalue of the matrix is judged; n is the order of the discrimination matrix; e is an average random consistency index;
and step S24, if the test result is that the judging matrix meets the consistency index, carrying out weight calculation based on the feature vector and the maximum feature value, determining a weight value corresponding to each factor, and taking the factor corresponding to the maximum weight value as key decision task information of the tower controller.
It can be understood that in this step, when the discrimination matrix satisfies the consistency index, the solution weight is reasonable. If not, redesigning the discriminant matrix. And finally, calculating index weight by adopting a geometric average method, firstly, calculating a feature vector corresponding to the maximum feature value after passing consistency verification through a judging matrix, normalizing the feature vector, wherein each element corresponding value is the weight of each factor of the layer, and taking the factor with the maximum weight as key decision task information of a tower controller.
And step S3, establishing an auxiliary decision model based on the flight data of the aircraft and key decision task information of the tower controller, establishing an auxiliary decision interface based on the auxiliary decision model, and prompting the tower controller to make a decision.
It will be appreciated that this step assists the tower controller in making decisions by building an assist decision model, wherein step S3 includes step S31, step S32 and step S33.
S31, establishing a two-dimensional space coordinate system based on the flight data of all the aircrafts, and sending the flight data of all the aircrafts to a trained aircraft track prediction model to predict and obtain predicted flight tracks of all the aircrafts;
it can be understood that the trained aircraft trajectory prediction model in this step predicts positions of the aircraft in different time periods according to the flight position coordinates of the aircraft, and then performs error compensation and curve simulation according to the position coordinates obtained by prediction to obtain a predicted flight trajectory of the aircraft, where step S31 includes step S311, step S312, step S313 and step S314.
Step S311, processing all aircraft flight data and a preset longitude and latitude coordinate system of the earth, wherein a two-dimensional space coordinate system is obtained by taking a tower as an origin and longitude and latitude as coordinate axes;
it can be appreciated that this step provides for future flight trajectory predictions by establishing a two-dimensional spatial coordinate system, and then determining the position of each aircraft, and rapidly determining the position of each aircraft.
Step S312, transmitting the flight data of the aircraft into the two-dimensional space coordinate system to obtain at least two space coordinate points, wherein the space coordinate points are flight position coordinates of the aircraft;
it will be appreciated that this step rapidly determines the position of each aircraft by transmitting the aircraft's flight data into a two-dimensional spatial coordinate system, rapidly determining the aircraft's flight position coordinates.
Step S313, carrying out flight position coordinate change prediction on the flight position coordinates of the aircrafts and flight data of the aircrafts to obtain predicted flight position coordinates of at least two aircrafts;
it can be understood that in this step, the flight data of all the aircrafts are sent to the two-dimensional space coordinate system to determine the flight positions of all the aircrafts, so as to determine the positions of the adjacent aircrafts, and prevent the occurrence of accidents such as collision of the adjacent aircrafts, and in this step, step S313 includes step S3131, step S3132 and step S3133.
Step S3131, constructing a training set and a test set based on the flight position coordinates of the aircraft and the flight data of the aircraft, wherein the training set and the test set are classified according to the moving time sequence of the aircraft, the flight position coordinates of the aircraft with the previous moving time and the flight data of the aircraft are used as the training set, and the flight position coordinates of the aircraft with the subsequent moving time and the flight data of the aircraft are used as the test set;
it can be understood that the step classifies the historical flight data of the aircraft, takes the aircraft flight data with the previous historical flight time as a training set, takes the historical flight data with the subsequent historical flight time as a test set, and further performs training and testing, wherein the future time flight data can be predicted more accurately and rapidly according to the flight data with the previous movement time, a certain basis is provided, and errors are reduced.
Step S3132, predicting the training set and the testing set in a LSTM neural network model as parameter input values to be optimized to obtain predicted flight position coordinate data of the aircraft;
it can be understood that this step trains the training set through the LSTM neural network model, wherein the data in the training set is initialized, then the data in the training set is predicted based on the neural network, then the predicted data is obtained, and by judging whether the difference value between the predicted flight data and the data in the test set is smaller than a preset threshold value, if so, the historical predicted flight data of the aircraft is obtained, and if so, the predicted parameters are adjusted, and the prediction is performed again until the difference value is smaller than the preset threshold value.
And S3133, optimizing the LSTM neural network model based on a squirrel search optimization algorithm, wherein the data of all the predicted flight position coordinates of the aircraft are initialized by defining the squirrel search optimization algorithm, and then the optimal predicted flight position coordinates are determined based on the squirrel search optimization algorithm.
It can be understood that in the step, historical predicted flight data is optimized through a squirrel search optimization algorithm, so that optimal historical predicted flight data is determined, the prediction accuracy is increased, the optimal data in all predicted data can be selected through the data optimized and predicted through the squirrel search optimization algorithm, the possibility of misjudgment after the optimal data is reduced, judgment time is further provided for manual intervention, and the efficiency is improved while errors are reduced.
And step S314, transmitting all the predicted flight position coordinates of the aircraft to a preset error compensation module for error compensation processing, and processing based on the predicted flight position coordinates after the error compensation processing to obtain the predicted flight trajectory of the aircraft.
It can be understood that the accuracy of the position determination and the prediction accuracy of the present step are improved, error compensation is further performed on the predicted data, and then the flight trajectory fitting is performed based on the flight position coordinates obtained by the error compensation, where step S314 includes step S3141, step S3142, step S3143, and step S3144.
Step S3141, initializing all the predicted flight position coordinates of the aircraft, wherein the predicted flight position coordinates comprise the dimension number of the flight position coordinate parameters, the number of the flight position coordinates, the maximum iteration number and the preset range of the predicted flight position coordinates;
step S3142, taking an average absolute error between a preset historical predicted flight position coordinate of the aircraft and a preset historical actual flight position coordinate of the aircraft as a loss function;
step S3143, inputting the loss function to a trained prediction model for prediction parameter adjustment, and obtaining a predicted flight position coordinate after error compensation processing;
it can be understood that in this step, error calculation is performed on the predicted positions of all the aircrafts, so as to determine error values of the predicted positions and the actual positions of the aircrafts, and then, by calculating an average absolute error of the predicted positions and the actual positions as a loss function, error compensation is further performed, wherein the difference between the error values and the loss function is an improved precision range, so that the original precision is improved, and the possibility of misjudgment is reduced.
And step S3144, processing all the error-compensated predicted flight position coordinates based on the Bezier curve method to obtain a predicted flight trajectory corresponding to each aircraft.
It can be understood that in this step, the predicted flight position coordinates are fitted by means of a bezier curve in a line, so as to determine the flight trajectory of each aircraft, and then determine the minimum distance between two adjacent aircraft, so as to make a decision that an intervention needs to be performed.
Step S32, an auxiliary decision model is constructed based on the predicted flight trajectory of the aircraft and key decision task information of a tower controller, wherein the auxiliary decision model is a model for judging whether the predicted flight trajectory of the aircraft needs to perform an intervention decision or not based on a preset wake interval standard;
it can be understood that in this step, whether the distance between the front machine and the rear machine violates the preset safety interval standard is judged by the predicted flight trajectory of the aircraft, wherein the judging method is that six points of the Likert are scored, which are "certain meeting, high possibility, possible, impossible, and certain not possible respectively". And determining the minimum interval prediction distance of the adjacent front aircraft and the adjacent rear aircraft based on six-point scores, calculating the minimum interval difference according to the minimum interval prediction distance, defining that the minimum interval difference is equal to the predicted distance of the controller minus the actual minimum interval distance, and further judging whether the predicted flight track of the aircraft needs to be subjected to intervention decision, wherein different aircraft are divided into different types according to the maximum takeoff weight and the wingspan size, and the front-rear interval distance between each aircraft pair is not smaller than the specified minimum wake flow interval.
And step S33, if the auxiliary decision model judges that the predicted flight trajectory of the aircraft needs to be subjected to intervention decision, generating an auxiliary decision interface based on the predicted flight trajectory of the aircraft, and sending the auxiliary decision interface and a prompt instruction to a display interface of a tower staff for display.
It will be appreciated that, in this step, after determining the minimum possible separation distance between two future devices, the tower controller does not directly compare the minimum separation distance with the wake separation criteria and then makes a decision, but uses the safety margin as a buffer zone, and the actual comparison is the sum of the wake separation criteria and the safety margin. And generating an auxiliary decision-making interface shown in fig. 3, wherein A and B in fig. 3 represent height information of two aircrafts, C and D represent distance information of the two aircrafts, and the lower left corner in fig. 3 represents distance information of the two aircrafts, so that decision-making staff is prompted to make decisions or not through the auxiliary decision-making interface. And the time pressure evaluation of the tested task scene can be inquired after the intervention selection is made by the controller, and the scoring mode is Likert six-point scoring.
Example 2
As shown in fig. 2, the present embodiment provides a device for constructing a tower controller auxiliary decision-making system, which includes an acquisition unit 701, an analysis unit 702, and a decision-making unit 703.
An obtaining unit 701, configured to obtain tower controller task information and flight data of an aircraft, where the tower controller task information includes release seat task information, ground seat task information, and tower seat task information;
the analysis unit 702 is configured to perform hierarchical analysis on the task information of the tower controller staff, and determine critical decision task information of the tower controller, where the critical decision task information is task information with the greatest decision difficulty of the tower controller;
the decision unit 703 is configured to establish an auxiliary decision model based on the flight data of the aircraft and the critical decision task information of the tower controller, and construct an auxiliary decision interface based on the auxiliary decision model and prompt the tower controller to make a decision.
In one embodiment of the present disclosure, the analysis unit 702 includes an analysis subunit 7021, a first processing subunit 7022, a first computing subunit 7023, and a second computing subunit 7024.
An analysis subunit 7021, configured to perform hierarchical analysis on task information of the tower tubular staff, and establish an obtained hierarchical structure model, where the hierarchical structure model includes a working area layer, a working task layer, and a working target layer;
a first processing subunit 7022, configured to score the decision difficulty of each factor in the hierarchical structure model based on a 1-9 scale method, normalize all the scoring results, and convert the processed data into a discrimination matrix;
a first calculating subunit 7023, configured to calculate, based on the discrimination matrix, a feature vector and a maximum feature value of the discrimination matrix, and perform consistency test processing on the discrimination matrix to obtain a test result;
and a second calculating subunit 7024, configured to perform weight calculation based on the feature vector and the maximum feature value if the test result is that the discrimination matrix meets the consistency index, determine a weight value corresponding to each factor, and use the factor corresponding to the maximum weight value as key decision task information of the tower controller.
In one embodiment of the disclosure, the decision unit 703 includes a first prediction subunit 7031, a first determination subunit 7032, and a second determination subunit 7033.
The first prediction subunit 7031 is configured to establish a two-dimensional space coordinate system based on the flight data of all the aircrafts, send the flight data of all the aircrafts to a trained aircraft track prediction model, and predict to obtain predicted flight tracks of all the aircrafts;
in one embodiment of the present disclosure, the first prediction subunit 7031 includes a second processing subunit 70311, a third processing subunit 70312, a fourth processing subunit 70313, and a fifth processing subunit 70314.
The second processing subunit 70311 is configured to process all the aircraft flight data and a preset longitude and latitude coordinate system of the earth, where a tower is used as an origin, and the longitude and latitude are used as coordinate axes, so as to obtain a two-dimensional space coordinate system;
a third processing subunit 70312, configured to send flight data of the aircraft to the two-dimensional spatial coordinate system to obtain at least two spatial coordinate points, where the spatial coordinate points are flight position coordinates of the aircraft;
a fourth processing subunit 70313, configured to predict a flight position coordinate of the aircraft and flight data of the aircraft, to obtain predicted flight position coordinates of at least two aircraft;
in one embodiment of the present disclosure, the fourth processing subunit 70313 includes a sixth processing subunit 703131, a second prediction subunit 703132, and a seventh processing subunit 703133.
A sixth processing subunit 703131, configured to construct a training set and a test set based on the flight position coordinates of the aircraft and the flight data of the aircraft, where the training set is classified according to the moving time sequence of the aircraft, the flight position coordinates of the aircraft with the preceding moving time and the flight data of the aircraft are used as the training set, and the flight position coordinates of the aircraft with the following moving time and the flight data of the aircraft are used as the test set;
the second prediction subunit 703132 is configured to predict the training set and the test set in the LSTM neural network model as parameter input values to be optimized to obtain predicted flight position coordinate data of the aircraft;
and a seventh processing subunit 703133, configured to optimize the LSTM neural network model based on a squirrel search optimization algorithm, where all the predicted flight position coordinate data of the aircraft are initialized by defining the squirrel search optimization algorithm, and then determine an optimal predicted flight position coordinate based on the squirrel search optimization algorithm.
And the fifth processing subunit 70314 is configured to send the predicted flight position coordinates of all the aircraft to a preset error compensation module for performing error compensation processing, and perform processing based on the predicted flight position coordinates after the error compensation processing, so as to obtain a predicted flight trajectory of the aircraft.
In one embodiment of the present disclosure, the fifth processing subunit 70314 includes an eighth processing subunit 703141, a third computing subunit 703142, a ninth processing subunit 703143, and a tenth processing subunit 703144.
An eighth processing subunit 703141, configured to initialize all the predicted flight position coordinates of the aircraft, where the initialization processing includes a dimension of a parameter of the flight position coordinates, the number of flight position coordinates, a maximum iteration number, and a preset range of the predicted flight position coordinates;
a third calculation subunit 703142, configured to take, as a loss function, an average absolute error between a preset historical predicted flight position coordinate of the aircraft and a preset historical actual flight position coordinate of the aircraft;
a ninth processing subunit 703143, configured to perform prediction parameter adjustment based on the loss function input to the trained prediction model, and obtain a predicted flight position coordinate after error compensation processing;
and a tenth processing subunit 703144, configured to process all the error-compensated predicted flight position coordinates based on the bezier curve method, so as to obtain a predicted flight trajectory corresponding to each aircraft.
A first judging subunit 7032, configured to construct an auxiliary decision-making model based on the predicted flight trajectory of the aircraft and the critical decision-making task information of the tower controller, where the auxiliary decision-making model is a model for judging whether the predicted flight trajectory of the aircraft needs to make an intervention decision based on a preset wake interval criterion;
and the second judging subunit 7033 is configured to generate an auxiliary decision-making interface based on the predicted flight trajectory of the aircraft if the auxiliary decision-making model judges that the predicted flight trajectory of the aircraft needs to make an intervention decision, and send the auxiliary decision-making interface and a prompt instruction to a display interface of a turret staff for display.
It should be noted that, regarding the apparatus in the above embodiments, the specific manner in which the respective modules perform the operations has been described in detail in the embodiments regarding the method, and will not be described in detail herein.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (6)
1. A method of constructing a tower controller aid decision making system, comprising:
the method comprises the steps of obtaining tower controller work task information and flight data of an aircraft, wherein the tower controller work task information comprises release seat work task information, ground seat work task information and tower seat work task information;
performing hierarchical analysis on the task information of the tower controller staff to determine key decision task information of the tower controller, wherein the key decision task information is task information with the largest decision difficulty of the tower controller;
establishing an auxiliary decision-making model based on flight data of the aircraft and key decision task information of a tower controller, and establishing an auxiliary decision-making interface and prompting the tower controller to make decisions based on the auxiliary decision-making model;
the step of performing hierarchical analysis on the task information of the tower controller staff to determine key decision task information of the tower controller includes:
performing hierarchical analysis on the task information of the staff of the tower controller, and establishing a hierarchical structure model, wherein the hierarchical structure model comprises a working area layer, a working task layer and a working target layer;
scoring the decision difficulty of each factor in the hierarchical structure model based on a 1-9 scale method, normalizing all scoring results, and converting the processed data into a discrimination matrix;
respectively calculating the feature vector and the maximum feature value of the discrimination matrix based on the discrimination matrix, and carrying out consistency test on the discrimination matrix to obtain a test result;
if the test result is that the judging matrix meets the consistency index, carrying out weight calculation based on the feature vector and the maximum feature value, determining a weight value corresponding to each factor, and taking the factor corresponding to the maximum weight value as key decision task information of a tower controller;
the method for establishing the auxiliary decision-making model based on the flight data of the aircraft and the critical decision-making task information of the tower controller, establishing an auxiliary decision-making interface based on the auxiliary decision-making model and prompting the tower controller to make decisions comprises the following steps:
establishing a two-dimensional space coordinate system based on the flight data of all the aircrafts, and sending the flight data of all the aircrafts to a trained aircraft track prediction model to predict and obtain predicted flight tracks of all the aircrafts;
constructing an auxiliary decision model based on the predicted flight trajectory of the aircraft and key decision task information of a tower controller, wherein the auxiliary decision model is a model for judging whether the predicted flight trajectory of the aircraft needs to be subjected to intervention decision or not based on a preset wake interval standard;
if the auxiliary decision model judges that the predicted flight trajectory of the aircraft needs to be subjected to intervention decision, an auxiliary decision interface is generated based on the predicted flight trajectory of the aircraft, and the auxiliary decision interface and a prompt instruction are sent to a display interface of a tower staff for display.
2. The method for constructing a tower controller decision-making support system according to claim 1, wherein the establishing a two-dimensional space coordinate system based on the flight data of all the aircrafts, and sending the flight data of all the aircrafts to a trained aircraft trajectory prediction model, predicting to obtain predicted flight trajectories of all the aircrafts, comprises:
processing all aircraft flight data and a preset longitude and latitude coordinate system of the earth, wherein a two-dimensional space coordinate system is obtained by taking a tower as an origin and longitude and latitude as coordinate axes;
transmitting the flight data of the aircraft into the two-dimensional space coordinate system to obtain at least two space coordinate points, wherein the space coordinate points are flight position coordinates of the aircraft;
carrying out flight position coordinate change prediction on the flight position coordinates of the aircrafts and flight data of the aircrafts to obtain predicted flight position coordinates of at least two aircrafts;
and sending all the predicted flight position coordinates of the aircraft to a preset error compensation module for error compensation processing, and processing based on the predicted flight position coordinates after the error compensation processing to obtain the predicted flight trajectory of the aircraft.
3. The method of constructing a tower controller aid decision making system according to claim 2, wherein predicting the flight position coordinates of the aircraft and the flight data of the aircraft to obtain predicted flight position coordinates of at least two aircraft comprises:
constructing a training set and a testing set based on the flight position coordinates of the aircraft and the flight data of the aircraft, wherein the training set and the testing set are classified according to the moving time sequence of the aircraft, the flight position coordinates of the aircraft with the previous moving time and the flight data of the aircraft are used as the training set, and the flight position coordinates of the aircraft with the subsequent moving time and the flight data of the aircraft are used as the testing set;
predicting the training set and the testing set in a LSTM neural network model as parameter input values to be optimized to obtain predicted flight position coordinate data of the aircraft;
and optimizing the LSTM neural network model based on a squirrel search optimization algorithm, wherein the data of all the predicted flight position coordinates of the aircraft are initialized by defining the squirrel search optimization algorithm, and then the optimal predicted flight position coordinates are determined based on the squirrel search optimization algorithm.
4. A tower controller aid decision making system construction apparatus, comprising:
the system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring tower controller work task information and flight data of an aircraft, and the tower controller work task information comprises release seat work task information, ground seat work task information and tower seat work task information;
the analysis unit is used for carrying out hierarchical analysis on the task information of the tower controller staff to determine the key decision task information of the tower controller, wherein the key decision task information is the task information with the largest decision difficulty of the tower controller;
the decision unit is used for establishing an auxiliary decision model based on the flight data of the aircraft and key decision task information of the tower controller, establishing an auxiliary decision interface based on the auxiliary decision model and prompting the tower controller to make a decision;
wherein the analysis unit includes:
the analysis subunit is used for carrying out hierarchical analysis on the task information of the tower controller staff and establishing a hierarchical structure model, wherein the hierarchical structure model comprises a working area layer, a working task layer and a working target layer;
the first processing subunit is used for scoring the decision difficulty of each factor in the hierarchical structure model based on a 1-9 scale method, normalizing all scoring results, and converting the processed data into a discrimination matrix;
the first calculating subunit is used for respectively calculating the eigenvectors and the maximum eigenvalues of the discrimination matrix based on the discrimination matrix, and carrying out consistency test processing on the discrimination matrix to obtain a test result;
the second calculation subunit is used for carrying out weight calculation based on the feature vector and the maximum feature value if the test result is that the discrimination matrix meets the consistency index, determining a weight value corresponding to each factor, and taking the factor corresponding to the maximum weight value as key decision task information of a tower controller;
wherein the decision unit comprises:
the first prediction subunit is used for establishing a two-dimensional space coordinate system based on the flight data of all the aircrafts, sending the flight data of all the aircrafts to a trained aircraft track prediction model, and predicting to obtain predicted flight tracks of all the aircrafts;
the first judging subunit is used for constructing an auxiliary decision-making model based on the predicted flight trajectory of the aircraft and key decision-making task information of a tower controller, wherein the auxiliary decision-making model is a model for judging whether the predicted flight trajectory of the aircraft needs to be subjected to intervention decision-making or not based on a preset wake interval standard;
and the second judging subunit is used for generating an auxiliary decision interface based on the predicted flight trajectory of the aircraft if the auxiliary decision model judges that the predicted flight trajectory of the aircraft needs to be subjected to intervention decision, and sending the auxiliary decision interface and the prompting instruction to a display interface of a tower staff for display.
5. The tower controller aid decision making system construction apparatus in accordance with claim 4, wherein the apparatus comprises:
the second processing subunit is used for processing all aircraft flight data and a preset longitude and latitude coordinate system of the earth, wherein a tower is taken as an origin, and the longitude and latitude are taken as coordinate axes to obtain a two-dimensional space coordinate system;
the third processing subunit is used for sending the flight data of the aircraft into the two-dimensional space coordinate system to obtain at least two space coordinate points, wherein the space coordinate points are flight position coordinates of the aircraft;
a fourth processing subunit, configured to predict a flight position coordinate of the aircraft and flight data of the aircraft, to obtain predicted flight position coordinates of at least two aircraft;
and the fifth processing subunit is used for sending the predicted flight position coordinates of all the aircrafts to a preset error compensation module for error compensation processing, and processing the predicted flight position coordinates based on the error compensation processing to obtain the predicted flight trajectories of the aircrafts.
6. The tower controller aid decision making system construction apparatus in accordance with claim 5, wherein the apparatus comprises:
a sixth processing subunit, configured to construct a training set and a test set based on the flight position coordinates of the aircraft and the flight data of the aircraft, where the training set and the test set are classified according to a movement time sequence of the aircraft, the flight position coordinates of the aircraft and the flight data of the aircraft with the preceding movement time are used as the training set, and the flight position coordinates of the aircraft and the flight data of the aircraft with the following movement time are used as the test set;
the second prediction subunit is used for predicting the training set and the testing set in the LSTM neural network model as parameter input values needing to be optimized to obtain predicted flight position coordinate data of the aircraft;
and the seventh processing subunit is used for optimizing the LSTM neural network model based on a squirrel search optimization algorithm, wherein the initialization processing is carried out on all the predicted flight position coordinate data of the aircraft by defining the squirrel search optimization algorithm, and then the optimal predicted flight position coordinate is determined based on the squirrel search optimization algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310296126.7A CN116029570B (en) | 2023-03-24 | 2023-03-24 | Construction method and device of auxiliary decision-making system for tower controller |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310296126.7A CN116029570B (en) | 2023-03-24 | 2023-03-24 | Construction method and device of auxiliary decision-making system for tower controller |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116029570A CN116029570A (en) | 2023-04-28 |
| CN116029570B true CN116029570B (en) | 2023-06-09 |
Family
ID=86074265
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310296126.7A Active CN116029570B (en) | 2023-03-24 | 2023-03-24 | Construction method and device of auxiliary decision-making system for tower controller |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116029570B (en) |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10037704B1 (en) * | 2017-02-01 | 2018-07-31 | David Myr | Automatic real-time air traffic control system and method for maximizing landings / takeoffs capacity of the airport and minimizing aircrafts landing times |
| CN107085978B (en) * | 2017-06-21 | 2020-02-18 | 南京航空航天大学 | Control aid decision instruction generation method based on required arrival time |
| CN112258898B (en) * | 2020-10-16 | 2021-08-24 | 中国民用航空华东地区空中交通管理局 | Air traffic control method, system, electronic device and storage medium based on digital twin technology |
| CN114333428A (en) * | 2021-12-17 | 2022-04-12 | 广州市中南民航空管通信网络科技有限公司 | Airport landing aircraft interval management method, device and storage medium |
-
2023
- 2023-03-24 CN CN202310296126.7A patent/CN116029570B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN116029570A (en) | 2023-04-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114048889B (en) | Aircraft trajectory prediction method based on long-term and short-term memory network | |
| Perez-Carabaza et al. | A real world multi-UAV evolutionary planner for minimum time target detection | |
| CN108759839A (en) | A kind of unmanned vehicle paths planning method based on situation space | |
| CN108320051B (en) | Mobile robot dynamic collision avoidance planning method based on GRU network model | |
| US11790767B2 (en) | Method, apparatus, device and storage medium for pre-warning of aircraft flight threat evolution | |
| US11928813B2 (en) | Method and system for detecting change to structure by using drone | |
| CN106200662A (en) | A kind of UAV Flight Control System | |
| Koutras et al. | Autonomous and cooperative design of the monitor positions for a team of uavs to maximize the quantity and quality of detected objects | |
| CN106127407B (en) | Airplane travel scoring method and system based on multi-sensor information fusion | |
| CN112578673B (en) | Perception decision and tracking control method for multi-sensor fusion of formula-free racing car | |
| CN116029570B (en) | Construction method and device of auxiliary decision-making system for tower controller | |
| CN116954264B (en) | Distributed high subsonic unmanned aerial vehicle cluster control system and method thereof | |
| Zhang et al. | UAV Trajectory Prediction Based on Flight State Recognition | |
| Wang et al. | Air combat effectiveness assessment of military aircraft using a fuzzy AHP and TOPSIS methodology | |
| Zhang et al. | Human control model in teleoperation rendezvous | |
| CN114897193A (en) | Airplane structure maintenance decision method and decision system based on man-in-the-loop | |
| Kim et al. | Control of an UAV for Fire Monitoring | |
| CN114035536A (en) | Flight control system robustness assessment method based on Monte Carlo method | |
| CN115729269B (en) | Unmanned aerial vehicle intelligent recognition system based on machine vision | |
| CN112488146A (en) | Airplane danger identification and trend prediction method based on deep learning | |
| Xia et al. | Data association-based fault diagnosis of IMUs: Optimized DBN design and wheeled robot evaluation | |
| Deese et al. | Recursive Gaussian Process-based Adaptive Control: Theoretical Framework and Application to an Airborne Wind Energy System | |
| EP4068033A1 (en) | Method and device for simulating a robotic system | |
| Horii | Vehicle occupant restraint system design under uncertainty by using multi-objective robust design optimization | |
| Santos et al. | Model-based and machine learning-based high-level controller for autonomous vehicle navigation: lane centering and obstacles avoidance |
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 |