CN114662625B - Flight parameter data reconstruction method, device, equipment and medium - Google Patents
Flight parameter data reconstruction method, device, equipment and medium Download PDFInfo
- Publication number
- CN114662625B CN114662625B CN202210581518.3A CN202210581518A CN114662625B CN 114662625 B CN114662625 B CN 114662625B CN 202210581518 A CN202210581518 A CN 202210581518A CN 114662625 B CN114662625 B CN 114662625B
- Authority
- CN
- China
- Prior art keywords
- flight data
- training
- initial
- reconstruction
- flight
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
The application discloses a flight parameter data reconstruction method, a flight parameter data reconstruction device, flight parameter data reconstruction equipment and flight parameter data reconstruction media, and relates to the technical field of artificial intelligence. The flight parameter data reconstruction method comprises the steps of obtaining initial flight data of a target airplane; wherein the initial flight data comprises at least two categories of interrelated flight data; preprocessing the initial flight data to determine abnormal flight data in the initial flight data; performing feature extraction on the initial flight data to obtain an initial feature vector; inputting the initial characteristic vector into a reconstruction model obtained through training, and obtaining reconstructed flight data output by the reconstruction model; and repairing the abnormal flight data based on the reconstructed flight data. The flight parameter data reconstruction method completes the repair of abnormal flight data based on the reconstruction model obtained through training, and improves the repair accuracy of the flight data.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a flight parameter data reconstruction method, device, equipment and medium.
Background
In order to ensure the safety of the flight, the aircraft needs to transmit the flight data generated in the flight process back to the ground. However, errors often occur in the transmission process of flight data of an airplane, and in order to ensure the accuracy of later data display and analysis, the errors need to be repaired.
The existing error code repairing method mainly comprises an interpolation algorithm, which comprises the following steps: linear interpolation, spline interpolation and the like, but the accuracy of error code repair by adopting an interpolation method is lower.
Disclosure of Invention
The present application mainly aims to provide a method, an apparatus, a device and a medium for reconstructing flight parameter data, and aims to solve the technical problem of low error code recovery accuracy in the prior art.
In order to achieve the above purpose, the embodiments of the present application adopt the following technical solutions:
in a first aspect, an embodiment of the present application provides a flight parameter data reconstruction method, including the following steps:
acquiring initial flight data of a target aircraft; wherein the initial flight data comprises at least two categories of interrelated flight data;
preprocessing the initial flight data to determine abnormal flight data in the initial flight data;
extracting the characteristics of the initial flight data to obtain an initial characteristic vector;
inputting the initial characteristic vector into a reconstruction model obtained through training to obtain reconstruction flight data output by the reconstruction model;
and repairing the abnormal flight data based on the reconstructed flight data.
In a possible implementation manner of the first aspect, the performing feature extraction on the initial flight data to obtain an initial feature vector includes: rejecting the abnormal flight data in the initial flight data to obtain first rejected flight data; performing interpolation restoration on the first rejected flight data by adopting an interpolation method to obtain input flight data; and performing feature extraction on the input flight data to obtain the initial feature vector.
In a possible implementation manner of the first aspect, the inputting the initial feature vector into a reconstructed model obtained through training to obtain reconstructed flight data output by the reconstructed model includes: obtaining the classification category of the initial feature vector according to a classification basis; wherein the classification criteria includes a model of the target aircraft; and inputting the initial characteristic vector into a corresponding reconstruction model according to the classification category to obtain the reconstruction flight data output by the reconstruction model.
In one possible implementation manner of the first aspect, before the acquiring initial flight data of the target aircraft, the method further includes: acquiring training flight data of a plurality of airplanes; extracting the features of the training flight data to obtain a first training feature vector; inputting the first training characteristic vector into a reconstruction model to be trained, and obtaining reconstructed flight data to be trained output by the reconstruction model to be trained; and training the reconstruction model to be trained according to the reconstruction flight data to be trained and the training flight data to obtain the reconstruction model.
In one possible implementation form of the first aspect, the training flight data comprises at least two classes of interrelated flight data; wherein the category of the initial flight data is consistent with the category of the training flight data.
In a possible implementation manner of the first aspect, the first training feature vector is input into a reconstructed model to be trained, and reconstructed flight data to be trained output by the reconstructed model to be trained is obtained; training the reconstruction model to be trained according to the reconstruction flight data to be trained and the training flight data to obtain the reconstruction model, including: grouping the first training characteristic vectors according to preset time length to obtain a plurality of groups of second training characteristic vectors; respectively inputting multiple groups of second training characteristic vectors into the reconstruction model to be trained to obtain reconstruction flight data to be trained output by the reconstruction model to be trained; and training the reconstruction model to be trained according to the reconstruction flight data to be trained and the training flight data to obtain the reconstruction model.
In a possible implementation manner of the first aspect, the inputting the initial feature vector into a reconstructed model obtained through training to obtain reconstructed flight data output by the reconstructed model includes: grouping the initial characteristic vectors according to the preset duration to obtain a plurality of groups of intermediate characteristic vectors; and respectively inputting the plurality of groups of intermediate characteristic vectors into a reconstruction model obtained by training to obtain the reconstructed flight data output by the reconstruction model.
In a second aspect, an embodiment of the present application provides a flight parameter data reconstruction device, including:
the initial flight data acquisition module is used for acquiring initial flight data of the target aircraft; wherein the initial flight data comprises at least two categories of interrelated flight data;
the first preprocessing module is used for preprocessing the initial flight data to determine abnormal flight data in the initial flight data;
the first feature extraction module is used for extracting features of the initial flight data to obtain an initial feature vector;
the reconstruction module is used for inputting the initial characteristic vector into a reconstruction model obtained through training to obtain reconstructed flight data output by the reconstruction model;
and the repairing module is used for repairing the abnormal flight data based on the reconstructed flight data.
In a third aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program, and when the computer program is loaded and executed by a processor, the flight parameter data reconstruction method provided in any one of the foregoing first aspects is implemented.
In a fourth aspect, an embodiment of the present application provides an electronic device, including a processor and a memory, wherein,
the memory is used for storing a computer program;
the processor is configured to load and execute the computer program to cause the electronic device to perform the flight parameter data reconstruction method as provided in any one of the first aspect.
Compared with the prior art, the beneficial effects of this application are:
the method for reconstructing the flight parameter data comprises the steps of obtaining initial flight data of a target aircraft; wherein the initial flight data comprises at least two categories of interrelated flight data; preprocessing the initial flight data to determine abnormal flight data in the initial flight data; extracting the characteristics of the initial flight data to obtain an initial characteristic vector; inputting the initial characteristic vector into a reconstruction model obtained through training to obtain reconstruction flight data output by the reconstruction model; and repairing the abnormal flight data based on the reconstructed flight data. The flight parameter data reconstruction method completes the repair of abnormal flight data based on the reconstruction model obtained through training, and in the repair process, the incidence relation among the initial flight data is considered, so that the repair accuracy of the abnormal flight data is improved. Specifically, the method comprises the following steps: taking the initial flight data comprising flight attitude data and flight track data as an example, the flight parameter data reconstruction method provided by the application is adopted to carry out error code recovery on abnormal flight data contained in the flight track data, and influence factors of the flight attitude data on the flight track data can be taken into consideration in the recovery process; in the process of repairing the error code by adopting the interpolation algorithm, only a single parameter is considered, for example, the change condition of flight path data per se, and the influence factor of the flight attitude data on the flight path data is ignored. Obviously, the accuracy of error code recovery performed by the flight parameter data reconstruction method provided by the application is higher.
Drawings
Fig. 1 is a schematic structural diagram of an electronic device in a hardware operating environment according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a method for reconstructing flight parameter data according to an embodiment of the present disclosure;
fig. 3 is a schematic flow chart of a feature extraction process provided in an embodiment of the present application;
fig. 4 is a schematic flowchart of a reconstruction model training process provided in an embodiment of the present application;
fig. 5 is a schematic structural diagram of a flight parameter data reconstruction device according to an embodiment of the present application.
The mark in the figure is: 101-processor, 102-communication bus, 103-network interface, 104-user interface, 105-memory.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The main solution of the embodiment of the application is as follows: providing a flight parameter data reconstruction method, which comprises the steps of obtaining initial flight data of a target airplane; wherein the initial flight data comprises at least two categories of interrelated flight data; preprocessing the initial flight data to determine abnormal flight data in the initial flight data; extracting the characteristics of the initial flight data to obtain an initial characteristic vector; inputting the initial characteristic vector into a reconstruction model obtained through training to obtain reconstruction flight data output by the reconstruction model; and repairing the abnormal flight data based on the reconstructed flight data.
The existing error code repairing method mainly comprises an interpolation algorithm, which comprises the following steps: linear interpolation, spline interpolation algorithm, etc. because the interpolation method can only operate on single type of data, the incidence relation between multiple types of data cannot be taken into account in the process of repairing the error code by adopting the interpolation method, therefore, the accuracy of repairing the error code by adopting the interpolation method is lower.
Therefore, the application provides a flight parameter data reconstruction method, which comprises the steps of obtaining initial flight data of a target aircraft; preprocessing the initial flight data to determine abnormal flight data in the initial flight data; extracting the characteristics of the initial flight data to obtain an initial characteristic vector; inputting the initial characteristic vector into a reconstruction model obtained through training, and obtaining reconstructed flight data output by the reconstruction model; and repairing the abnormal flight data based on the reconstructed flight data. The flight parameter data reconstruction method completes the repair of abnormal flight data based on the reconstruction model obtained through training, and in the repair process, the incidence relation among the initial flight data is considered, so that the repair accuracy of the abnormal flight data is improved.
Referring to fig. 1, fig. 1 is a schematic structural diagram of an electronic device in a hardware operating environment according to an embodiment of the present application, where the electronic device may include: a processor 101, such as a Central Processing Unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. Wherein the communication bus 102 is used to enable connection communication between these components. The user interface 104 may comprise a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 104 may also comprise a standard wired interface, a wireless interface. The network interface 103 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 105 may optionally be a storage device independent of the processor 101, and the Memory 105 may be a Random Access Memory (RAM) Memory, or a Non-Volatile Memory (NVM), such as at least one disk Memory; the processor 101 may be a general-purpose processor including a central processing unit, a network processor, etc., and may also be a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components.
Those skilled in the art will appreciate that the configuration shown in fig. 1 is not intended to be limiting of the electronic device and may include more or fewer components than shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, the memory 105, which is a storage medium, may include therein an operating system, a network communication module, a user interface module, and a flight parameter data reconstruction device.
In the electronic device shown in fig. 1, the network interface 103 is mainly used for data communication with a network server; the user interface 104 is mainly used for data interaction with a user; the processor 101 and the memory 105 in the electronic device of the present invention may be disposed in the electronic device, and the electronic device invokes a flight parameter data reconstruction apparatus stored in the memory 105 through the processor 101, and executes the flight parameter data reconstruction method provided in the embodiment of the present application.
Referring to fig. 2, fig. 2 is a schematic flow chart of a flight parameter data reconstruction method provided in an embodiment of the present application, where the flight parameter data reconstruction method includes the following steps:
s50: acquiring initial flight data of a target aircraft; wherein the initial flight data comprises at least two categories of interrelated flight data;
s60: preprocessing the initial flight data to determine abnormal flight data in the initial flight data;
s70: extracting the characteristics of the initial flight data to obtain an initial characteristic vector;
s80: inputting the initial characteristic vector into a reconstruction model obtained through training, and obtaining reconstructed flight data output by the reconstruction model;
s90: and repairing the abnormal flight data based on the reconstructed flight data.
In step S50, the target aircraft is an aircraft that needs to perform flight data reconstruction, and the initial flight data is flight data of the target aircraft received by the corresponding ground receiving station. The initial flight data includes at least two categories of interrelated flight data, such as: flight attitude data, flight trajectory data, and wind field data of the target aircraft, or: airspeed data, static thrust data, oil consumption data, temperature data and air pressure data of the flight; the flight path data can be influenced by the attitude data of the airplane and the wind field data of the target airplane, so that the correlation among various types of flight data is taken into consideration in the process of reconstructing the flight data, and the accuracy of reconstructing the flight parameter data can be improved. The initial flight data of the target aircraft comprises abnormal flight data, and the initial flight data comprises: the flight attitude data, the flight path data and the wind field data of the target aircraft are taken as examples, the abnormal flight data can be a part of the flight attitude data, can also be a part of the flight path data or the wind field data of the target aircraft, and the abnormal flight data needs to be repaired through flight parameter data reconstruction so as to obtain the repaired flight data.
In step S60, the preprocessing process may be: and determining abnormal flight data according to the frequency, the error, the form and the like of the data contained in the initial flight data. Specifically, the method comprises the following steps: taking the initial flight data comprising flight attitude data, flight trajectory data and wind field data of the target aircraft as an example, determining abnormal flight data in the slowly-changing data such as the flight trajectory data and the wind field data of the target aircraft by adopting a quadratic fitting method; and determining abnormal flight data in the high-frequency change data such as the roll angle and the pitch angle in the flight attitude data by adopting a variance calculation method.
In step S70, the specific process of feature extraction includes: extracting the initial flight data at each preset moment, and then vectorizing the initial flight data at the preset moment to further obtain the initial characteristic vector.
Taking the initial flight data including flight attitude data, flight track data and wind field data of a target aircraft as an example, converting the initial flight data at a preset moment i into a vector form of (Ai, bi, ci, di, ei, fi, gi, hi, ii) to further obtain an initial feature vector; ai, bi, ci are used for representing flight path data at a preset moment i, di, ei, fi are used for representing flight attitude data at the preset moment i, and Gi, hi, ii are used for representing wind field data of a target aircraft at the preset moment i. Specifically, the method comprises the following steps: ai may be used for representing longitude of a preset moment i, bi may be used for representing latitude of the preset moment i, ci may be used for representing altitude of the preset moment i, di may be used for representing heading of the preset moment i, ei may be used for representing pitch angle of the preset moment i, fi may be used for representing roll angle of the preset moment i, gi may be used for representing a wind field component in the longitude direction of the preset moment i, hi may be used for representing a wind field component in the latitude direction of the preset moment i, and Ii may be used for representing a wind field component in the altitude direction of the preset moment i.
Wherein, in step S80, the reconstruction model may include an RNN network model.
In step S90, the reconstructed flight data corresponding to the abnormal flight data may be used to replace the original abnormal flight data, so as to complete the repair of the abnormal flight data.
As in the above embodiment, the flight parameter data reconstruction method is implemented by obtaining initial flight data of a target aircraft; wherein the initial flight data comprises at least two categories of interrelated flight data; preprocessing the initial flight data to determine abnormal flight data in the initial flight data; performing feature extraction on the initial flight data to obtain an initial feature vector; inputting the initial characteristic vector into a reconstruction model obtained through training, and obtaining reconstructed flight data output by the reconstruction model; and repairing the abnormal flight data based on the reconstructed flight data. According to the flight parameter data reconstruction method, in the process of repairing error codes, namely abnormal flight data, incidence relation among initial flight data is considered, and the repairing accuracy of the abnormal flight data is improved.
Referring to fig. 3, fig. 3 is a schematic flow chart of a feature extraction process provided in an embodiment of the present application.
In one embodiment, S70: performing feature extraction on the initial flight data to obtain an initial feature vector, including: s701: rejecting the abnormal flight data in the initial flight data to obtain first rejected flight data; s702: performing interpolation restoration on the first rejected flight data by adopting an interpolation method to obtain input flight data; s703: and performing feature extraction on the input flight data to obtain the initial feature vector.
After the abnormal flight data in the initial flight data are removed, the removing positions of the abnormal flight data need to be marked, so that the positions needing data repairing can be determined more quickly in the repairing process, the initial flight data of other positions are reserved, and the efficiency and accuracy of repairing the abnormal flight data based on the reconstructed flight data are improved. Interpolation restoration is carried out on the first rejected flight data through an interpolation method, and input flight data which are more accurate than the initial flight data can be obtained. By carrying out feature extraction on more accurate input flight data, more accurate initial feature vectors can be obtained, and the more accurate initial feature vectors are input into the reconstruction model, so that the accuracy of the obtained reconstructed flight data can be improved while the operation complexity of the reconstruction model is reduced, and the repairing accuracy of abnormal flight data is further improved.
In one embodiment, S80: inputting the initial characteristic vector into a reconstruction model obtained by training, and obtaining reconstructed flight data output by the reconstruction model, wherein the method comprises the following steps: obtaining the classification category of the initial feature vector according to a classification basis; wherein the classification criteria includes a model of the target aircraft; and inputting the initial characteristic vector into a corresponding reconstruction model according to the classification category to obtain the reconstruction flight data output by the reconstruction model.
The initial characteristic vector is input into the reconstruction model corresponding to the model according to the model of the target airplane, so that the accuracy of the obtained reconstructed flight data can be improved, and the repair accuracy of abnormal flight data is improved. The classification criteria may also include the number of take-offs and landings of the target aircraft or the duration of flight, among other factors that may affect the aircraft flight data.
Referring to fig. 4, fig. 4 is a schematic flowchart of training a reconstructed model according to an embodiment of the present application.
In one embodiment, at S50: before the initial flight data of the target aircraft are obtained, the flight parameter data reconstruction method further comprises the following steps: s10: acquiring training flight data of a plurality of airplanes; s20: extracting the features of the training flight data to obtain a first training feature vector; s30: inputting the first training characteristic vector into a reconstruction model to be trained to obtain reconstruction flight data to be trained output by the reconstruction model to be trained; s40: and training the reconstruction model to be trained according to the reconstruction flight data to be trained and the training flight data to obtain the reconstruction model.
The training flight data may be flight data recorded in onboard recorders on multiple airplanes. Because the flight data recorded in the recording recorder on the airplane is relatively accurate, the flight data recorded in the airborne recorder is used as training flight data, and the accuracy of the reconstructed model obtained by training can be ensured.
In one embodiment, the training flight data includes at least two categories of interrelated flight data; wherein the category of the initial flight data is consistent with the category of the training flight data.
The initial flight data may include flight attitude data, flight track data, wind field data of the target aircraft, airspeed data, static thrust data, oil consumption data, temperature data of the flight, air pressure data, and the like. Taking the example that the initial flight data includes flight attitude data, flight track data and wind field data where the target aircraft is located, the training flight data includes training attitude data, training track data of multiple aircraft and training wind field data where the multiple aircraft are located.
Because the training flight data comprises the at least two types of flight data which are correlated with each other, the correlation between the at least two types of flight data which are correlated with each other can be also considered in the process of calculating the reconstructed flight data of the obtained reconstructed model, the accuracy of the reconstructed flight data obtained by adopting the reconstruction method is better, and the repair accuracy of the abnormal flight data can be further improved.
In an embodiment, the first training feature vector is input into a reconstructed model to be trained, and reconstructed flight data to be trained output by the reconstructed model to be trained is obtained; training the reconstruction model to be trained according to the reconstruction flight data to be trained and the training flight data to obtain the reconstruction model, including: grouping the first training characteristic vectors according to preset time length to obtain a plurality of groups of second training characteristic vectors; respectively inputting a plurality of groups of second training characteristic vectors into the reconstruction model to be trained to obtain reconstruction flight data to be trained output by the reconstruction model to be trained; and training the reconstruction model to be trained according to the reconstruction flight data to be trained and the training flight data to obtain the reconstruction model.
The preset time period may be one minute, or three minutes or five minutes, which is not specifically limited in the present application. Because the time of each flight of the airplane is long, the first training characteristic vectors corresponding to the training flight data of a plurality of airplanes are directly input into the reconstruction model to be trained for training, so that the reconstruction model to be trained cannot complete data processing in a short time, and the training time and the training difficulty of the reconstruction model to be trained are greatly increased. In the training method provided by this embodiment, the first training feature vectors are grouped according to the preset duration, and the grouped second training feature vectors are input into the reconstructed model to be trained for training, so that the single data processing amount of the reconstructed model to be trained is reduced, the training difficulty of the reconstructed model to be trained is reduced, and the training efficiency of the reconstructed model is further improved. Wherein there may be data overlap between the sets of second training feature vectors.
In one embodiment, S80: inputting the initial characteristic vector into a reconstruction model obtained by training, and obtaining reconstructed flight data output by the reconstruction model, wherein the method comprises the following steps: grouping the initial characteristic vectors according to the preset duration to obtain a plurality of groups of intermediate characteristic vectors; and respectively inputting the plurality of groups of intermediate characteristic vectors into a reconstruction model obtained by training to obtain the reconstructed flight data output by the reconstruction model.
The initial characteristic vectors are the same as the first training characteristic vectors and are grouped according to the same preset time length, and in the process of calculating the reconstructed flight data by using the reconstructed model obtained through training, the accuracy of the obtained reconstructed flight data can be further improved by ensuring the consistency with the model training process as much as possible, so that the repairing accuracy of the abnormal flight data is improved.
Referring to fig. 5, fig. 5 is a schematic structural diagram of a flight parameter data reconstruction device according to an embodiment of the present application. Based on the same inventive concept as the foregoing embodiment, the present application further provides a flight parameter data reconstruction apparatus, including:
the initial flight data acquisition module is used for acquiring initial flight data of the target aircraft; wherein the initial flight data comprises at least two categories of interrelated flight data;
the first preprocessing module is used for preprocessing the initial flight data to determine abnormal flight data in the initial flight data;
the first feature extraction module is used for extracting features of the initial flight data to obtain an initial feature vector;
the reconstruction module is used for inputting the initial characteristic vector into a reconstruction model obtained through training to obtain reconstructed flight data output by the reconstruction model;
and the repairing module is used for repairing the abnormal flight data based on the reconstructed flight data.
According to the embodiment, the flight parameter data reconstruction device acquires initial flight data of a target aircraft; wherein the initial flight data comprises at least two categories of interrelated flight data; preprocessing the initial flight data to determine abnormal flight data in the initial flight data; extracting the characteristics of the initial flight data to obtain an initial characteristic vector; inputting the initial characteristic vector into a reconstruction model obtained through training, and obtaining reconstructed flight data output by the reconstruction model; and repairing the abnormal flight data based on the reconstructed flight data. The flight parameter data reconstruction device considers the incidence relation between the initial flight data in the process of repairing error codes, namely abnormal flight data, and improves the repairing accuracy of the abnormal flight data.
In one embodiment, a first feature extraction module comprises: the abnormal flight data removing module is used for removing the abnormal flight data in the initial flight data to obtain first removed flight data; the interpolation restoration module is used for carrying out interpolation restoration on the first rejected flight data by adopting an interpolation method to obtain input flight data; and the second feature extraction module is used for performing feature extraction on the input flight data to obtain the initial feature vector.
In an embodiment, the reconstruction module is specifically configured to: obtaining the classification category of the initial feature vector according to a classification basis; wherein the classification criteria includes a model of the target aircraft; and inputting the initial characteristic vector into a corresponding reconstruction model according to the classification category to obtain the reconstruction flight data output by the reconstruction model.
In one embodiment, the flight parameter data reconstruction device further includes: the training flight data acquisition module is used for acquiring training flight data of a plurality of airplanes; the first training feature vector extraction module is used for extracting features of the training flight data to obtain a first training feature vector; the reconstruction model obtaining module is used for inputting the first training characteristic vector into a reconstruction model to be trained to obtain reconstruction flight data to be trained output by the reconstruction model to be trained; and training the reconstruction model to be trained according to the reconstruction flight data to be trained and the training flight data to obtain the reconstruction model.
In one embodiment, the training flight data includes at least two categories of interrelated flight data; wherein the category of the initial flight data is consistent with the category of the training flight data.
In an embodiment, the reconstruction model obtaining module is specifically configured to: grouping the first training characteristic vectors according to preset time length to obtain a plurality of groups of second training characteristic vectors; respectively inputting a plurality of groups of second training characteristic vectors into the reconstruction model to be trained to obtain reconstruction flight data to be trained output by the reconstruction model to be trained; and training the reconstruction model to be trained according to the reconstruction flight data to be trained and the training flight data to obtain the reconstruction model.
In an embodiment, the reconfiguration module is specifically configured to: grouping the initial characteristic vectors according to the preset duration to obtain a plurality of groups of intermediate characteristic vectors; and respectively inputting the plurality of groups of intermediate characteristic vectors into a reconstruction model obtained by training to obtain the reconstructed flight data output by the reconstruction model.
It should be understood by those skilled in the art that the division of each module in the embodiment is only a division of a logic function, and all or part of the modules may be integrated onto one or more actual carriers in actual application, and all of the modules may be implemented in a form called by a processing unit through software, or implemented in a form of hardware, or implemented in a form of combination of software and hardware.
Based on the same inventive concept as that in the foregoing embodiments, embodiments of the present application further provide a computer-readable storage medium, which stores a computer program, and when the computer program is loaded and executed by a processor, the flight parameter data reconstruction method provided by the embodiments of the present application is implemented.
Based on the same inventive concept as the foregoing embodiments, embodiments of the present application further provide an electronic device, including a processor and a memory, wherein,
the memory is used for storing a computer program;
the processor is used for loading and executing a computer program to enable the electronic device to execute the flight parameter data reconstruction method provided by the embodiment of the application.
Furthermore, based on the same inventive concept as in the previous embodiments, embodiments of the present application also provide a computer program product comprising a computer program for performing the flight parameter data reconstruction method as provided by embodiments of the present application when the computer program is executed.
In some embodiments, the computer-readable storage medium may be memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash, magnetic surface memory, optical disk, or CD-ROM; or may be various devices including one or any combination of the above memories. The computer may be a variety of computing devices including intelligent terminals and servers.
In some embodiments, executable instructions may be written in any form of programming language (including compiled or interpreted languages), in the form of programs, software modules, scripts or code, and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.
By way of example, executable instructions may correspond, but do not necessarily have to correspond, to files in a file system, and may be stored in a portion of a file that holds other programs or data, such as in one or more scripts in a hypertext Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code).
By way of example, executable instructions may be deployed to be executed on one computing device or on multiple computing devices at one site or distributed across multiple sites and interconnected by a communication network.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of other like elements in a process, method, article, or system comprising the element.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
Through the description of the foregoing embodiments, it is clear to those skilled in the art that the method of the foregoing embodiments may be implemented by software plus a necessary general hardware platform, and certainly may also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (e.g., a rom/ram, a magnetic disk, an optical disk) and includes instructions for enabling a multimedia terminal (e.g., a mobile phone, a computer, a television receiver, or a network device) to perform the method according to the embodiments of the present application.
In summary, according to the flight parameter data reconstruction method provided by the application, the initial flight data of the target aircraft is obtained; wherein the initial flight data comprises at least two categories of interrelated flight data; preprocessing the initial flight data to determine abnormal flight data in the initial flight data; extracting the characteristics of the initial flight data to obtain an initial characteristic vector; inputting the initial characteristic vector into a reconstruction model obtained through training, and obtaining reconstructed flight data output by the reconstruction model; and repairing the abnormal flight data based on the reconstructed flight data. The flight parameter data reconstruction method completes the repair of abnormal flight data based on the reconstruction model obtained through training, and in the repair process, the incidence relation among the initial flight data is considered, so that the repair accuracy of the abnormal flight data is improved.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (8)
1. A method of flight parameter data reconstruction, the method comprising:
acquiring initial flight data of a target aircraft; wherein the initial flight data comprises at least two categories of interrelated flight data;
preprocessing the initial flight data to determine abnormal flight data in the initial flight data;
performing feature extraction on the initial flight data to obtain an initial feature vector;
inputting the initial characteristic vector into a reconstruction model obtained through training, and obtaining reconstructed flight data output by the reconstruction model;
repairing the abnormal flight data based on the reconstructed flight data;
prior to the acquiring initial flight data for the target aircraft, the method further comprises:
acquiring training flight data of a plurality of airplanes;
extracting the features of the training flight data to obtain a first training feature vector;
inputting the first training characteristic vector into a reconstruction model to be trained, and obtaining reconstructed flight data to be trained output by the reconstruction model to be trained;
training the reconstruction model to be trained according to the reconstruction flight data to be trained and the training flight data to obtain the reconstruction model;
inputting the first training characteristic vector into a reconstruction model to be trained, and obtaining reconstructed flight data to be trained output by the reconstruction model to be trained; training the reconstruction model to be trained according to the reconstruction flight data to be trained and the training flight data to obtain the reconstruction model, including:
grouping the first training characteristic vectors according to preset time length to obtain a plurality of groups of second training characteristic vectors;
respectively inputting a plurality of groups of second training characteristic vectors into the reconstruction model to be trained to obtain reconstruction flight data to be trained output by the reconstruction model to be trained;
and training the reconstruction model to be trained according to the reconstruction flight data to be trained and the training flight data to obtain the reconstruction model.
2. The method of claim 1, wherein the performing feature extraction on the initial flight data to obtain an initial feature vector comprises:
rejecting the abnormal flight data in the initial flight data to obtain first rejected flight data;
performing interpolation restoration on the first rejected flight data by adopting an interpolation method to obtain input flight data;
and performing feature extraction on the input flight data to obtain the initial feature vector.
3. The method of claim 1, wherein the inputting the initial feature vector into a reconstructed model obtained by training, and obtaining reconstructed flight data output by the reconstructed model comprises:
obtaining the classification category of the initial feature vector according to a classification basis; wherein the classification criteria includes a model number of the target aircraft;
and inputting the initial characteristic vector into a corresponding reconstruction model according to the classification category to obtain the reconstruction flight data output by the reconstruction model.
4. The method of claim 1, wherein the training flight data includes at least two categories of interrelated flight data; wherein the category of the initial flight data is consistent with the category of the training flight data.
5. The method according to claim 1, wherein the inputting the initial feature vector into a reconstructed model obtained by training to obtain reconstructed flight data output by the reconstructed model comprises:
grouping the initial characteristic vectors according to the preset duration to obtain a plurality of groups of intermediate characteristic vectors;
and respectively inputting the multiple groups of intermediate characteristic vectors into a reconstruction model obtained through training to obtain reconstructed flight data output by the reconstruction model.
6. An apparatus for reconstructing flight parameter data, the apparatus comprising:
the initial flight data acquisition module is used for acquiring initial flight data of the target aircraft; wherein the initial flight data comprises at least two categories of interrelated flight data;
the first preprocessing module is used for preprocessing the initial flight data to determine abnormal flight data in the initial flight data;
the first feature extraction module is used for extracting features of the initial flight data to obtain an initial feature vector;
the reconstruction module is used for inputting the initial characteristic vector into a reconstruction model obtained through training to obtain reconstructed flight data output by the reconstruction model;
the repairing module is used for repairing the abnormal flight data based on the reconstructed flight data;
the device further comprises: the training flight data acquisition module is used for acquiring training flight data of a plurality of airplanes; the first training feature vector extraction module is used for extracting features of the training flight data to obtain a first training feature vector; the reconstruction model obtaining module is used for inputting the first training characteristic vector into a reconstruction model to be trained to obtain reconstruction flight data to be trained output by the reconstruction model to be trained; training the reconstruction model to be trained according to the reconstruction flight data to be trained and the training flight data to obtain the reconstruction model;
the reconstruction model obtaining module is used for grouping the first training characteristic vectors according to preset time to obtain a plurality of groups of second training characteristic vectors; respectively inputting a plurality of groups of second training characteristic vectors into the reconstruction model to be trained to obtain reconstruction flight data to be trained output by the reconstruction model to be trained; and training the reconstruction model to be trained according to the reconstruction flight data to be trained and the training flight data to obtain the reconstruction model.
7. A computer-readable storage medium, storing a computer program, wherein the computer program, when loaded and executed by a processor, implements a method for reconstructing flight parameter data according to any one of claims 1 to 5.
8. An electronic device comprising a processor and a memory, wherein,
the memory is used for storing a computer program;
the processor is configured to load and execute the computer program to cause the electronic device to perform the flight parameter data reconstruction method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210581518.3A CN114662625B (en) | 2022-05-26 | 2022-05-26 | Flight parameter data reconstruction method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210581518.3A CN114662625B (en) | 2022-05-26 | 2022-05-26 | Flight parameter data reconstruction method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114662625A CN114662625A (en) | 2022-06-24 |
| CN114662625B true CN114662625B (en) | 2022-10-25 |
Family
ID=82038374
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210581518.3A Active CN114662625B (en) | 2022-05-26 | 2022-05-26 | Flight parameter data reconstruction method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114662625B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2988835B1 (en) * | 2012-03-28 | 2015-01-30 | Dassault Aviat | METHOD FOR DETERMINING A CREDIBILITY STATE OF SENSOR MEASUREMENTS OF AN AIRCRAFT AND CORRESPONDING SYSTEM |
| CN107133635B (en) * | 2017-03-30 | 2020-04-21 | 南京航空航天大学 | A Multi-source Heterogeneous Flight Accident Track Data Fusion Method |
| CN109445972B (en) * | 2018-09-21 | 2022-11-04 | 深圳供电局有限公司 | Data recovery method, device, equipment and storage medium |
| CN111144375B (en) * | 2019-12-31 | 2022-07-05 | 中国民用航空总局第二研究所 | Abnormal behavior detection method, device and electronic device based on feature coding |
| CN113869379B (en) * | 2021-09-15 | 2024-11-12 | 南京航空航天大学 | A data-driven method for identifying aircraft energy anomalies |
-
2022
- 2022-05-26 CN CN202210581518.3A patent/CN114662625B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| 基于平稳小波变换的飞行数据去噪方法;李正欣等;《计算机应用》;20111031(第10期);第2790-2792+2810页 * |
| 飞行轨迹重构研究;李乃宏等;《哈尔滨工业大学学报》;19921230(第06期);第49-56页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114662625A (en) | 2022-06-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112052151B (en) | Fault root cause analysis method, device, equipment and storage medium | |
| US8311697B2 (en) | Impact assessment system and method for determining emergent criticality | |
| CN109448100B (en) | Three-dimensional model format conversion method, system, computer device and storage medium | |
| CN107066382A (en) | A kind of Space Vehicle System automated testing method based on model | |
| CN106446412B (en) | Model-based test method for avionics system | |
| CN112464105B (en) | Internet platform information pushing method based on big data positioning and cloud computing center | |
| CN113221362B (en) | Satellite launching field performance test subject purpose selection method and device and electronic equipment | |
| CN114124567A (en) | Cloud service processing method based on big data vulnerability mining and artificial intelligence system | |
| WO2022039675A1 (en) | Method and apparatus for forecasting weather, electronic device and storage medium thereof | |
| CN113901647B (en) | Part technical specification compiling method and device, storage medium and electronic equipment | |
| CN113032257A (en) | Automatic test method, device, computer system and readable storage medium | |
| CN114157507A (en) | Cloud service vulnerability analysis method and artificial intelligence system adopting big data analysis | |
| CN113762454A (en) | Track abnormity detection method and device | |
| CN114692889A (en) | Meta-feature training model for machine learning algorithm | |
| CN117875288A (en) | Form page generation method and device and electronic equipment | |
| CN114911788B (en) | Data interpolation method and device and storage medium | |
| CN114662625B (en) | Flight parameter data reconstruction method, device, equipment and medium | |
| CN112465141A (en) | Model compression method, model compression device, electronic device and medium | |
| CN113780996A (en) | Post data detection method, model training method and device and electronic equipment | |
| CN113312485A (en) | Log automatic classification method and device and computer readable storage medium | |
| CN118334310A (en) | Object detection method, device, edge device and computer readable storage medium | |
| CN115759885B (en) | Material sampling inspection method and device based on distributed material supply | |
| CN117994494A (en) | Target detection method and device | |
| CN116204648A (en) | Sample determination method, sample determination device, computer equipment and computer readable storage medium | |
| CN114416596A (en) | Application testing method and device, computer equipment and storage medium |
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 |