CN116796874A - Method, device and equipment for predicting off-site flight time of aircraft - Google Patents
Method, device and equipment for predicting off-site flight time of aircraft Download PDFInfo
- Publication number
- CN116796874A CN116796874A CN202210236557.XA CN202210236557A CN116796874A CN 116796874 A CN116796874 A CN 116796874A CN 202210236557 A CN202210236557 A CN 202210236557A CN 116796874 A CN116796874 A CN 116796874A
- Authority
- CN
- China
- Prior art keywords
- data
- aircraft
- learning model
- flight
- predicting
- 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 65
- 238000007781 pre-processing Methods 0.000 claims abstract description 31
- 230000008569 process Effects 0.000 claims abstract description 25
- 238000011156 evaluation Methods 0.000 claims description 36
- 238000012549 training Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 16
- 238000004891 communication Methods 0.000 claims description 10
- 238000012544 monitoring process Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 210000005036 nerve Anatomy 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000012512 characterization method Methods 0.000 claims 1
- 230000029305 taxis Effects 0.000 claims 1
- 238000004458 analytical method Methods 0.000 abstract description 13
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000012795 verification Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 241001178520 Stomatepia mongo Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Biomedical Technology (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Operations Research (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application relates to the field of artificial intelligence, and discloses a method, a device and equipment for predicting off-site flight time of an aircraft. The method for predicting the departure flight time of the aircraft comprises the steps of obtaining data information, storing the data information into a database, and preprocessing the data information to obtain input data; and constructing a learning model, and using the learning model to predict the off-site flight time of the aircraft based on the input data to obtain a prediction result. In this way, in the process of predicting the off-site flight time of the aircraft, the autonomous analysis and prediction of the predicted project are realized by establishing a corresponding learning model and inputting the data characteristics corresponding to the required predicted project, the prediction analysis resource is reduced, and the accuracy of the predicted result is ensured by preprocessing the characteristics of the input data.
Description
Technical Field
The embodiment of the application relates to the field of artificial intelligence, in particular to a method, a device and equipment for predicting off-site flight time of an aircraft.
Background
As an important component in the transportation industry, the aviation industry is accompanied by various data such as flight plan data, flight trajectory data, voice data, weather data, etc. in daily operation and maintenance. If the information is utilized, information such as departure flight time prediction, flow prediction and the like of the airplane can be accurately judged, and the accuracy of prediction is improved.
In the process of actually carrying out data statistics and analysis, the following problems are found, the information acquisition amount in the aviation field is large in the current stage, the processing process takes too long, and because of different types of data, a specific model needs to be built for each independent type of data for analysis, and a large amount of resource investment is also needed.
Disclosure of Invention
The embodiment of the application provides a method, a device and equipment for predicting off-site flight time of an aircraft, which are used for solving the problems that in data analysis in the field of aviation, the processing process is too long due to large data information acquisition quantity and analysis resources are too large due to the variety of the data information.
In a first aspect, an embodiment of the present application provides a method for predicting an off-site time of flight of an aircraft, the method comprising:
acquiring data information, and storing the data information into a database, wherein the data information at least comprises one of the following: flight information, monitoring information, weather information and information corresponding to the aircraft;
preprocessing the data information to obtain input data;
constructing a learning model;
and the learning model is used for predicting the off-site flight time of the aircraft based on the input data to obtain a prediction result.
In some possible embodiments, the database may be selected as a mongo db, so that the database may meet the requirement of a large amount of data.
In some possible embodiments, the data information preprocessing includes at least one of: data cleaning, data integration, data reduction and data conversion, so that the interference of the data on the prediction result can be reduced.
In some possible embodiments, the building a learning model manner includes: the learning model was constructed using the sklearn tool in combination with the keras tool,
the sklearn tool is used for carrying out calculation processing on the input data to obtain characteristic data, and the characteristic data is used for training the learning model;
the keras tool is used to construct a neural network of the learning model to predict the departure time of flight of the aircraft based on the characteristic data,
the off-field flight time of the aircraft includes at least one of: runway taxiing time and adjacent waypoint flight time.
In some possible embodiments, the characteristic data may be obtained from the data information, and the first characteristic data corresponding to the runway sliding time includes at least one of the following: the wheel withdrawal time, the stand and the take-off runway are predicted;
the second characteristic data corresponding to the flight time of the adjacent waypoints comprises at least one of the following: an entry point altitude, an exit point altitude, an entry point, and an exit point.
In some possible embodiments, before constructing the learning model, the method further includes preprocessing the feature data to improve accuracy of the learning model, where the feature data preprocessing includes: and denoising and feature coding are carried out on the feature data.
In some possible implementations, preprocessing the feature data further includes:
acquiring a first evaluation result corresponding to the characteristic data denoising process, and if the first evaluation result is smaller than or equal to a first preset threshold value, setting the learning model related parameters corresponding to the characteristic data;
if the first evaluation result is larger than the first preset threshold value, continuing denoising processing on the characteristic data,
the first evaluation result mode comprises the following steps: and (5) evaluating average absolute errors.
In some possible embodiments, setting the learning model-related parameter includes:
acquiring a second evaluation result of each learning model related parameter, and if the second evaluation result is smaller than or equal to a second preset threshold value, selecting the learning model related parameter corresponding to the second evaluation result as the learning model use parameter;
if the second evaluation result is larger than the second preset threshold value, the related parameter value of the learning model is adjusted,
the model-related parameters include: for the number of samples grabbed in a single training, the number of nerve layers, the dropout parameters and the number of dense nodes,
the second evaluation result mode comprises: and (5) evaluating the average absolute error and the mean square error.
In a second aspect, an embodiment of the present application further provides an apparatus for predicting an off-site flight time of an aircraft, where the apparatus includes: the acquisition module is used for storing the data information into a database, and the data information at least comprises one of the following: flight information, monitoring information, weather information and information corresponding to the aircraft;
the preprocessing module is used for preprocessing the data information to obtain input data;
the building module is used for building a learning model;
and the learning module is used for predicting the off-site flight time of the aircraft based on the input data by using the learning model to obtain a prediction result.
In a third aspect, an embodiment of the present application further provides an electronic device for predicting an off-site flight time of an aircraft, including: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is for storing executable instructions that when executed cause the processor to perform a method of predicting an off-field time of flight of an aircraft in any one of the possible implementations of the first or second aspects.
In a fourth aspect, embodiments of the present application also provide a computer-readable storage medium having stored therein executable instructions that, when executed, cause a computing device to perform a method of predicting an off-field time of flight of an aircraft in any of the possible implementations of the first or second aspects.
The embodiment of the application provides a method for predicting off-site flight time of an aircraft, which comprises the steps of acquiring relevant data information of the aircraft, storing the data information into a database, and preprocessing the data information to obtain input data; and constructing a learning model, and using the learning model to predict the off-site flight time of the aircraft based on the input data to obtain a prediction result. In the process of predicting the off-site flight time of the aircraft, autonomous analysis and prediction of the predicted project are realized by establishing a corresponding learning model and inputting data features corresponding to the required predicted project, prediction analysis resources are reduced, and the accuracy of a predicted result is ensured by preprocessing the features of the input data.
Drawings
FIG. 1 is a flow chart of a method for predicting off-site flight time of an aircraft according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a data information preprocessing result provided by an embodiment of the present application;
FIG. 3a is a schematic diagram showing a comparison of training results of different feature choices of a learning model according to an embodiment of the present application;
FIG. 3b is an iterative view of a neural network of a learning model provided by an embodiment of the present application;
FIG. 3c is a graph showing the number of training data before and after denoising, which is required by the learning model according to the embodiment of the present application;
FIG. 4 is a schematic diagram of an apparatus for predicting off-field flight of an aircraft provided by an embodiment of the present application;
fig. 5 is a schematic diagram of an apparatus for predicting departure time of an aircraft according to an embodiment of the present application.
Detailed Description
The terminology used in the following examples of the application is for the purpose of describing alternative embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms as well. It should also be understood that, although the terms first, second, etc. may be used in the following embodiments to describe some type of object, the object is not limited to these terms. These terms are used to distinguish between specific objects of that class of objects. For example, other classes of objects that may be described in the following embodiments using the terms first, second, etc. are not described in detail herein.
The embodiment of the application provides a method for predicting off-site flight time of an aircraft, which comprises the steps of acquiring relevant data information of the aircraft, storing the data information into a database, and preprocessing the data information to obtain input data; and constructing a learning model, and using the learning model to predict the off-site flight time of the aircraft based on the input data to obtain a prediction result. In the process of predicting the off-site flight time of the aircraft, autonomous analysis and prediction of the predicted project are realized by establishing a corresponding learning model and inputting data features corresponding to the required predicted project, prediction analysis resources are reduced, and the accuracy of a predicted result is ensured by preprocessing the features of the input data.
The strategy model training method provided by the embodiment of the application can be executed by one electronic device or by a computer cluster. The computer cluster comprises at least two electronic devices supporting the strategy model training method of the embodiment of the application, and any electronic device can realize the strategy model training function described by the embodiment of the application through the strategy model training method.
Any of the electronic devices contemplated by the embodiments of the present application may be an electronic device such as a cell phone, tablet computer, wearable device (e.g., smart watch, wristband only, etc.), notebook computer, desktop computer, and vehicle-mounted device. The electronic device is pre-installed with a policy model training application. It will be appreciated that embodiments of the present application are not limited in any way by the particular type of electronic device.
In general, the aviation industry, as an important component in the transportation industry, generates various data such as flight plan data, flight trajectory data, voice data, weather data, etc. in daily operation and maintenance. If the information is utilized, information such as departure flight time prediction, flow prediction and the like of the airplane can be accurately judged, and the accuracy of prediction is improved.
In the process of actually carrying out data statistics and analysis, the following problems are found, the information acquisition amount in the aviation field is large in the current stage, the processing process takes too long, and because of different types of data, a specific model needs to be built for each independent type of data for analysis, and a large amount of resource investment is also needed.
The following is a description of several exemplary embodiments, and describes technical solutions of the embodiments of the present application and technical effects produced by the technical solutions of the present application.
Referring to fig. 1, fig. 1 is a flowchart of a method for predicting off-site flight time of an aircraft according to an embodiment of the present application, including the following steps:
acquiring data information, and storing the data information into a database, wherein the data information at least comprises one of the following: flight information, monitoring information, weather information and information corresponding to the aircraft;
preprocessing the data information to obtain input data;
constructing a learning model;
and the learning model is used for predicting the off-site flight time of the aircraft based on the input data to obtain a prediction result.
Typically, the off-site flight time of the aircraft includes: runway taxiing time, which is the time taken by the aircraft to start taxiing on a runway to take off the runway, and adjacent waypoint flight time, is generally calculated as: subtracting the actual push-out time of the aircraft from the actual take-off time;
the adjacent waypoint flight time refers to the time that the aircraft is flying between two waypoints (e.g., a takeoff airport and a landing airport), and is typically calculated as: the time of the last arrival at the waypoint minus the time of the previous arrival at the waypoint.
By way of example, the acquisition of the data information is usually issued by the corresponding information system,
the flight information at least comprises one of the following: flight number, flight departure time and flight departure place;
the monitoring information includes at least: various index performance parameters monitored in the flight process of the aircraft, and the vertical height and the speed of the position of the aircraft;
the weather information includes at least: weather information of the environment in which the aircraft is located;
the information corresponding to the aircraft at least comprises: runway switch status of the target point or origin.
Optionally, the preprocessing of the data information at least includes: data cleaning, data integration, data reduction and data conversion;
the data cleaning at least comprises: the method comprises the steps of inconsistent detection of data, recognition of noise data, data filtering and data correction, so that consistency and accuracy of data information can be improved, interference of the data on a prediction result is reduced, and training quality of a training model is improved.
In a possible implementation manner, in the process of performing the off-site flight time prediction of the aircraft, a database needs to be selected, and the database can be selected as an open source non-relational database which is commonly used as MongoDB, mongoDB, and can store xml, json, bson and other types of data. And, the MongoDB database has a slicing storage mechanism, and can meet the requirement of rapid increase of data quantity. Therefore, the MongoDB database is selected to adapt to various and large number of data environments in the process of acquiring the data information, so that the interference on the prediction process caused by the overlarge data quantity in the prediction process is reduced.
In a possible implementation manner, the method for constructing the learning model includes: the learning model was constructed using the sklearn tool in combination with the keras tool,
the sklearn tool is used for carrying out calculation processing on the input data so as to obtain characteristic data for training the learning model;
the keras tool is used to construct a neural network of the learning model to predict the departure time of flight of the aircraft based on the characteristic data,
the off-field flight time of the aircraft includes at least one of: runway taxiing time and adjacent waypoint flight time.
In a possible implementation manner, the characteristic data may be obtained from the data information, and the first characteristic data corresponding to the runway sliding time includes at least one of the following: the method comprises the steps of predicting wheel withdrawal time, a stand and a take-off runway, wherein the predicted wheel withdrawal time, the stand and the take-off runway can be obtained from monitoring information corresponding to the aircraft;
the second characteristic data corresponding to the flight time of the adjacent waypoints comprises at least one of the following: the system comprises an entry point height, an exit point height, an entry point and an exit point, wherein the entry point height, the exit point height, the entry point and the exit point can be obtained from monitoring information corresponding to the aircraft.
In a possible implementation manner, after the feature data is acquired before the learning model is constructed, the method further comprises preprocessing the feature data, and specifically comprises denoising and feature encoding the feature data.
Illustratively, taking the runway slip behavior prediction target as an example, the characteristic selection is to predict the withdrawal time, the stand and the take-off runway,
the three data are subjected to denoising (namely, the characteristic data are subjected to denoising processing), a specific operation denoising diagram is shown in fig. 2, threshold limiting is carried out on each data, corresponding data in a preset threshold are obtained, the total data before denoising of the three data is 26576 after actual denoising verification, the total data after denoising is 22026, which is equivalent to 18% denoising, and similarly, denoising processing can be carried out on other shown data information, and a specific denoising diagram is shown in fig. 3c, so that fluctuation of a final result can be reduced when the characteristic number after denoising is taken by the learning model.
Taking the predicted runway sliding time of the aircraft as an example, obtaining denoised data, carrying out data coding and modeling by using a neural network to obtain a predicted result,
for example, the actual runway sliding time corresponding to the aircraft is 19 minutes 45 seconds, the aircraft adopts all the features (i.e. the predicted wheel withdrawal time, the stand and the take-off runway) to predict 20 minutes 23 seconds, adopts part of the features (taking the stand and the take-off runway as examples here) to predict 21 minutes 34 seconds, adopts the average absolute error evaluation (mae, mean absolute error) as the evaluation standard, and adopts the specific evaluation data as shown in fig. 3a (the feature selection in fig. 3 is the feature data selection), and as can be seen from fig. 3a, the full features are adopted, the full features are more approximate to the correct value of about 70 seconds, so that the full features are selected.
After the feature data is selected, setting relevant parameters of the learning model, wherein the relevant parameters of the learning model comprise: the number of iterations, the number of samples grabbed for a single training (batch-size), the number of neural layers, the dropout parameters and the number of dense nodes,
taking the determination of the iteration number and the batch-size as an example, in a reasonable range, the larger the batch-size is, the more accurate the corresponding diagram is, the smaller the oscillation is, when the batch-size is too large, the local optimum condition can occur, through experimental verification, the iteration number is selected to be 120, the batch-size 800, the dropout parameter is set to be 0.2, and the dense node number is set to be 100, and the specific diagram is shown in fig. 3 b.
Optionally, after the feature data and the related parameters are determined, the learning model is constructed and trained to obtain the prediction result.
In some possible implementations, preprocessing the feature data further includes:
acquiring a first evaluation result corresponding to the characteristic data denoising process, and if the first evaluation result is smaller than or equal to a first preset threshold value, setting the learning model related parameters corresponding to the characteristic data;
if the first evaluation result is larger than the first preset threshold value, continuing denoising processing on the characteristic data,
the first evaluation result mode comprises the following steps: and (5) evaluating average absolute errors.
Optionally, for the process of selecting the feature data, a corresponding evaluation criterion may be introduced to perform auxiliary screening (that is, the first preset threshold is introduced, for example, the mae numerical requirement on the verification result needs to satisfy an actual application range, where the application range is the first preset threshold), and the result under the learning model parameter (that is, the first evaluation result) is compared with the first preset threshold by performing evaluation, so as to select the learning model parameter corresponding to the result meeting the threshold requirement.
In some possible embodiments, setting the learning model-related parameter includes:
acquiring a second evaluation result of each learning model related parameter, and if the second evaluation result is smaller than or equal to a second preset threshold value, selecting the learning model related parameter corresponding to the second evaluation result as the learning model use parameter;
if the second evaluation result is larger than the second preset threshold value, the related parameter value of the learning model is adjusted,
the model-related parameters include: for the number of samples grabbed in a single training, the number of nerve layers, the dropout parameters and the number of dense nodes,
the second evaluation result mode comprises: and (5) evaluating the average absolute error and the mean square error.
Optionally, for the process of selecting the learning model parameters, a corresponding evaluation criterion may be introduced to perform auxiliary screening (i.e. the second preset threshold is introduced, for example, the mae numerical requirement on the verification result needs to satisfy an actual application range, where the application range is the first preset threshold), and the learning model parameters corresponding to the result meeting the threshold requirement are selected by performing evaluation comparison between the result under the learning model parameters (i.e. the second evaluation result) and the second preset threshold.
Optionally, the adjacent waypoint time is taken as a prediction target, and the above process is also adopted, wherein the difference is that the feature data includes: the entry point height, the exit point height, the entry point and the exit point are not described in detail herein.
The embodiment of the application provides a method for predicting off-site flight time of an aircraft, which comprises the steps of acquiring relevant data information of the aircraft, storing the data information into a database, and preprocessing the data information to obtain input data; and constructing a learning model, and using the learning model to predict the off-site flight time of the aircraft based on the input data to obtain a prediction result. In the process of predicting the off-site flight time of the aircraft, autonomous analysis and prediction of the predicted project are realized by establishing a corresponding learning model and inputting data features corresponding to the required predicted project, prediction analysis resources are reduced, and the accuracy of a predicted result is ensured by preprocessing the features of the input data.
The above embodiment describes each implementation of the method for predicting the off-site flight time of the aircraft provided by the embodiment of the application from the angles of action logic and learning algorithm processing executed by the electronic device, such as obtaining data information, preprocessing the data information to obtain input data, constructing a learning model to obtain a prediction result, and the like. It should be understood that, corresponding to obtaining data information, preprocessing the data information to obtain input data, and constructing a learning model to obtain a prediction result, the embodiment of the application may implement the above functions in a form of hardware or a combination of hardware and computer software. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
For example, if the implementation step implements the corresponding function by using a software module, as shown in fig. 4, an apparatus for predicting an off-site flight time of an aircraft, the apparatus includes: the acquisition module is used for storing the data information into a database, and the data information at least comprises one of the following: flight information, monitoring information, weather information and information corresponding to the aircraft;
the preprocessing module is used for preprocessing the data information to obtain input data;
the building module is used for building a learning model;
and the learning module is used for predicting the off-site flight time of the aircraft based on the input data by using the learning model to obtain a prediction result.
It should be understood that the above division of each module/unit is merely a division of logic functions, and in actual implementation, the functions of each module may be integrated into a hardware entity to implement, for example, the deployment module, the execution network training module, the interaction training module, and the comparison module may be integrated into a processor to implement, and a program and an instruction for implementing the functions of each module may be maintained in a memory. For example, fig. 5 provides an electronic device that includes a processor, a transceiver, and a memory. Wherein the transceiver obtains the data information. The memory may be used to store corresponding trajectory data generated by the learning model during operation, code for execution by the processor, and the like. The processor, when executing the code stored in the memory, causes the electronic device to perform some or all of the operations described above for predicting the off-field time of flight of an aircraft.
The specific implementation process is described in detail in the embodiments illustrated by the above method, and will not be described in detail here.
In a specific implementation, corresponding to the foregoing electronic device, the embodiment of the present application further provides a computer storage medium, where the computer storage medium provided in the electronic device may store a program, and when the program is executed, part or all of the steps in each embodiment including the multi-agent learning method may be implemented. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), a random-access memory (random access memory, RAM), or the like.
One or more of the above modules or units may be implemented in software, hardware, or a combination of both. When any of the above modules or units are implemented in software, the software exists in the form of computer program instructions and is stored in a memory, a processor can be used to execute the program instructions and implement the above method flows. The processor may include, but is not limited to, at least one of: a central processing unit (central processing unit, CPU), microprocessor, digital Signal Processor (DSP), microcontroller (microcontroller unit, MCU), or artificial intelligence processor, each of which may include one or more cores for executing software instructions to perform operations or processes. The processor may be built into a SoC (system on a chip) or an application specific integrated circuit (application specific integrated circuit, ASIC) or may be a separate semiconductor chip. The processor may further include necessary hardware accelerators, such as field programmable gate arrays (field programmable gate array, FPGAs), PLDs (programmable logic devices), or logic circuits implementing dedicated logic operations, in addition to the cores for executing software instructions for operation or processing.
When the above modules or units are implemented in hardware, the hardware may be any one or any combination of a CPU, microprocessor, DSP, MCU, artificial intelligence processor, ASIC, soC, FPGA, PLD, dedicated digital circuitry, hardware accelerator, or non-integrated discrete device that may run the necessary software or that is independent of the software to perform the above method flows.
Further, a bus interface may be included in FIG. 5, which may include any number of interconnected buses and bridges, with various circuits of the memory, in particular, represented by one or more of the processors and the memory. The bus interface may also link together various other circuits such as peripheral devices, voltage regulators, power management circuits, etc., which are well known in the art and, therefore, will not be described further herein. The bus interface provides an interface. The transceiver provides a means for communicating with various other apparatus over a transmission medium. The processor is responsible for managing the bus architecture and general processing, and the memory may store data used by the processor in performing operations.
When the above modules or units are implemented in software, they may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.
It should be understood that, in various embodiments of the present application, the size of the sequence number of each process does not mean that the execution sequence of each process should be determined by its functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments.
All parts of the specification are described in a progressive manner, and all parts of the embodiments which are the same and similar to each other are referred to each other, and each embodiment is mainly described as being different from other embodiments. In particular, for apparatus and system embodiments, the description is relatively simple, as it is substantially similar to method embodiments, with reference to the description of the method embodiments section.
While alternative embodiments of the present application 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. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.
The foregoing embodiments have been provided for the purpose of illustrating the general principles of the present application in further detail, and are not to be construed as limiting the scope of the application, but are merely intended to cover any modifications, equivalents, improvements, etc. based on the teachings of the application.
Claims (10)
1. A method of predicting off-site flight time of an aircraft, the method comprising:
acquiring data information, and storing the data information into a database, wherein the data information at least comprises one of the following: flight information, monitoring information, weather information and information corresponding to the aircraft;
preprocessing the data information to obtain input data;
constructing a learning model;
and the learning model is used for predicting the off-site flight time of the aircraft based on the input data to obtain a prediction result.
2. The method of predicting an aircraft departure time of flight of claim 1, wherein the data information preprocessing comprises at least one of: data cleaning, data integration, data reduction and data conversion.
3. The method of predicting an aircraft departure time of flight of claim 1, wherein the constructing a learning model means comprises: the learning model was constructed using the sklearn tool in combination with the keras tool,
the sklearn tool is used for carrying out calculation processing on the input data to obtain characteristic data, and the characteristic data is used for training the learning model;
the keras tool is used to construct a neural network of the learning model to predict the departure time of flight of the aircraft based on the characteristic data,
the off-field flight time of the aircraft includes at least one of: runway taxiing time and adjacent waypoint flight time.
4. A method of predicting an aircraft departure time of flight as claimed in claim 1 or claim 3, wherein the characteristic data is derived from the data information, and the first characteristic data corresponding to runway taxis time comprises at least one of: the wheel withdrawal time, the stand and the take-off runway are predicted;
the second characteristic data corresponding to the flight time of the adjacent waypoints comprises at least one of the following: an entry point altitude, an exit point altitude, an entry point, and an exit point.
5. A method of predicting an aircraft departure time of flight as claimed in claim 3, further comprising, prior to constructing the learning model, pre-processing the feature data to improve the learning model accuracy,
the feature data preprocessing comprises the following steps: and denoising and feature coding are carried out on the feature data.
6. The method of predicting an aircraft departure time of flight of claim 1 or 5, wherein preprocessing the characterization data further comprises:
acquiring a first evaluation result corresponding to the characteristic data denoising process, and if the first evaluation result is smaller than or equal to a first preset threshold value, setting the learning model related parameters corresponding to the characteristic data;
if the first evaluation result is larger than the first preset threshold value, continuing denoising processing on the characteristic data,
the first evaluation result mode comprises the following steps: and (5) evaluating average absolute errors.
7. The method of predicting an aircraft departure time of flight of claim 5, wherein setting the learning model related parameters comprises:
acquiring a second evaluation result of each learning model related parameter, and if the second evaluation result is smaller than or equal to a second preset threshold value, selecting the learning model related parameter corresponding to the second evaluation result as the learning model use parameter;
if the second evaluation result is larger than the second preset threshold value, the related parameter value of the learning model is adjusted,
the model-related parameters include: for the number of samples grabbed in a single training, the number of nerve layers, the dropout parameters and the number of dense nodes,
the second evaluation result mode comprises: and (5) evaluating the average absolute error and the mean square error.
8. An apparatus for predicting off-site flight time of an aircraft, the apparatus comprising: the acquisition module is used for storing the data information into a database, and the data information at least comprises one of the following: flight information, monitoring information, weather information and information corresponding to the aircraft;
the preprocessing module is used for preprocessing the data information to obtain input data;
the building module is used for building a learning model;
and the learning module is used for predicting the off-site flight time of the aircraft based on the input data by using the learning model to obtain a prediction result.
9. An electronic device for predicting off-site flight time of an aircraft, comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is configured to store executable instructions that, when executed, cause the processor to perform the method of predicting an aircraft departure time of flight of any one of claims 1-7.
10. A computer storage medium having stored therein executable instructions that when executed cause a computing device to perform the method of predicting an aircraft departure time of flight of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210236557.XA CN116796874A (en) | 2022-03-11 | 2022-03-11 | Method, device and equipment for predicting off-site flight time of aircraft |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210236557.XA CN116796874A (en) | 2022-03-11 | 2022-03-11 | Method, device and equipment for predicting off-site flight time of aircraft |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116796874A true CN116796874A (en) | 2023-09-22 |
Family
ID=88037763
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210236557.XA Pending CN116796874A (en) | 2022-03-11 | 2022-03-11 | Method, device and equipment for predicting off-site flight time of aircraft |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116796874A (en) |
-
2022
- 2022-03-11 CN CN202210236557.XA patent/CN116796874A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11017677B2 (en) | Decision-making aid for revising a flight plan | |
| US9911339B2 (en) | Experimental real-time performance enhancement for aircraft | |
| CN102208028A (en) | Fault predicting and diagnosing method suitable for dynamic complex system | |
| CN110826788A (en) | Airport scene variable slide-out time prediction method based on big data deep learning | |
| CN113657814B (en) | Aviation network risk prediction method and risk grade evaluation method | |
| CN115225516B (en) | LSSVM network flow prediction method based on improved ABC-VMD | |
| CN111290422B (en) | Method and device for flight control based on bump index and aircraft | |
| CN110610226A (en) | Generator fault prediction method and device | |
| CN114819054A (en) | Power electronic system state monitoring method based on physical information neural network | |
| CN116485031A (en) | Method, device, equipment and storage medium for predicting short-term power load | |
| CN115752708A (en) | Airport single-point noise prediction method based on deep time convolution network | |
| CN109814101B (en) | Method and device for predicting position of aircraft | |
| CN105303051A (en) | Air pollutant concentration prediction method | |
| CN114781704A (en) | Flight delay prediction method based on station-passing flight guarantee process | |
| CN114648060A (en) | Fault signal standardization processing and classification method based on machine learning | |
| CN117034090A (en) | Model parameter adjustment and model application methods, devices, equipment and media | |
| CN116796874A (en) | Method, device and equipment for predicting off-site flight time of aircraft | |
| CN115310732B (en) | Flight delay prediction method and system | |
| CN116380438A (en) | Fault diagnosis method and device, electronic equipment and storage medium | |
| CN113961765B (en) | Searching method, searching device, searching equipment and searching medium based on neural network model | |
| CN114595525A (en) | Rolling bearing degradation trend prediction method based on linear regression and TCN | |
| CN111724053A (en) | Aviation network risk propagation identification method | |
| AU2020408906A1 (en) | Method and device for supervising a traffic control system | |
| CN110084511B (en) | Unmanned aerial vehicle configuration method, device, equipment and readable storage medium | |
| CN111091254A (en) | Operation risk quantification method, operation risk evaluation method and device |
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 |