CN117057226A - Method and device for determining flight route of aircraft, electronic equipment and storage medium - Google Patents
Method and device for determining flight route of aircraft, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117057226A CN117057226A CN202310960802.6A CN202310960802A CN117057226A CN 117057226 A CN117057226 A CN 117057226A CN 202310960802 A CN202310960802 A CN 202310960802A CN 117057226 A CN117057226 A CN 117057226A
- Authority
- CN
- China
- Prior art keywords
- aircraft
- parameters
- model
- prediction result
- determining
- 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 70
- 230000033001 locomotion Effects 0.000 claims abstract description 28
- 230000006870 function Effects 0.000 claims description 47
- 230000004913 activation Effects 0.000 claims description 22
- 230000008859 change Effects 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 12
- 238000004088 simulation Methods 0.000 abstract description 11
- 230000000875 corresponding effect Effects 0.000 description 20
- 238000012549 training Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 210000002569 neuron Anatomy 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Mathematical Optimization (AREA)
- Strategic Management (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Algebra (AREA)
- Geometry (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Analysis (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Fluid Mechanics (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Navigation (AREA)
Abstract
The application provides a method and a device for determining a flight route of an aircraft, electronic equipment and a storage medium, wherein the method for determining the flight route of the aircraft comprises the following steps: acquiring geometrical parameters and meteorological environment parameters of an aircraft; inputting the geometric parameters and the meteorological environment parameters into a pre-trained agent model to obtain a prediction result of the aircraft on aerodynamic performance data; and inputting the prediction result into a motion model to obtain the flight route of the aircraft. By adopting the technical scheme provided by the application, the obtained geometric parameters and meteorological environment parameters of the aircraft can be used as input variables of the proxy model, and the prediction result of the aerodynamic performance data can be output, so that the flight route is obtained, a complex numerical simulation process is replaced, and the timeliness and applicability of determining the flight route are improved.
Description
Technical Field
The present application relates to the field of aircraft technologies, and in particular, to a method and apparatus for determining a flight path of an aircraft, an electronic device, and a storage medium.
Background
When the aircraft encounters wind shear, rain, snow and other weather in the flight process, the aircraft is easy to cause accidents, in order to avoid the accidents of the aircraft, the flight path of the aircraft is required to be planned, the planned flight path is different due to different aircraft performances, and the aircraft performances under different aviation weather are required to be calculated.
At present, the performance of the aircraft under different aviation weather can be calculated through single dynamic numerical simulation, but the method consumes a long time, so that the aircraft can not warn pilots in real time according to the icing condition and the aerodynamic characteristic change condition of the weather condition, and the timeliness of the subsequent flight path planning is affected; and each time of numerical simulation only can calculate the ice type change and the corresponding aerodynamic force change condition of the wing surface under certain specific aircraft appearance and certain weather change condition, and the method has certain limitation and influences the applicability of the subsequent flight path planning. Therefore, how to determine the flight path of an aircraft becomes a problem to be solved.
Disclosure of Invention
Accordingly, the present application is directed to a method, an apparatus, an electronic device, and a storage medium for determining a flight path of an aircraft, which are capable of obtaining a flight path by using acquired geometric parameters and meteorological environment parameters of the aircraft as input variables of a proxy model and outputting a prediction result of aerodynamic performance data, instead of a complex numerical simulation process, so as to improve timeliness and applicability of determining the flight path by determining the flight path according to performance changes of different aircraft under different meteorological conditions, thereby reducing possibility of flight accidents.
The application mainly comprises the following aspects:
in a first aspect, an embodiment of the present application provides a method for determining a flight path of an aircraft, where the determining method includes:
acquiring geometrical parameters and meteorological environment parameters of an aircraft;
inputting the geometric parameters and the meteorological environment parameters into a pre-trained agent model to obtain a prediction result of the aircraft on aerodynamic performance data;
and inputting the prediction result into a motion model to obtain the flight route of the aircraft.
Further, the step of inputting the geometric parameter and the meteorological environment parameter into a pre-trained proxy model to obtain a prediction result of the aircraft about aerodynamic performance data includes:
inputting the geometric parameters and the meteorological environment parameters as input data into a pre-trained proxy model, and acquiring a plurality of first weights from the input layer to the hidden layer and deviations of the hidden layer through the input layer and the hidden layer of the proxy model;
determining an activation function of the hidden layer based on input data, the plurality of first weights, and a deviation of the hidden layer;
When input data passes through a hidden layer and an output layer of the proxy model, a plurality of second weights from the hidden layer to the output layer and deviations of the output layer are obtained;
and determining an activation function of the output layer based on the activation function of the hidden layer, the plurality of second weights and the deviation of the output layer, and determining a value corresponding to the activation function of the output layer as a prediction result of the aircraft on aerodynamic performance data.
Further, the step of inputting the prediction result into a motion model to obtain a flight path of the aircraft includes:
inputting the prediction result into a motion model to obtain a predicted flight parameter of the aircraft;
determining the change rate of the predicted flight parameters corresponding to each adjacent moment through the predicted flight parameters of the aircraft at each moment in the future flight time;
integrating the change rate of each predicted flight parameter along with the future flight time to obtain the flight route of the aircraft.
Further, the proxy model is trained by:
acquiring sample geometric parameters of a plurality of sample aircrafts, a plurality of sample meteorological environment parameters and target aerodynamic performance data corresponding to each sample aircrafts under each sample meteorological environment parameter;
Inputting the sample geometric parameters and each sample meteorological environment parameter of each sample aircraft into a proxy model for each sample aircraft to obtain a sample prediction result of the sample aircraft on aerodynamic performance data under each sample meteorological environment parameter;
determining whether a loss function in the proxy model converges or not by using the sample prediction result and the corresponding target aerodynamic performance data;
if not, updating model parameters in the proxy model to train the proxy model; the model parameters comprise a plurality of first weights from an input layer to a hidden layer in the proxy model, a deviation of the hidden layer, a plurality of second weights from the hidden layer to an output layer in the proxy model and a deviation of the output layer;
and if the model is converged, obtaining a trained proxy model.
Further, after the flight path of the aircraft is obtained, the determining method further includes:
acquiring actual data of the aircraft regarding aerodynamic performance data over a time period of flight;
the actual data and the prediction result are subjected to difference to obtain a difference value of each piece of pneumatic performance data;
if the difference value of each pneumatic performance data is within the preset difference range, continuing to fly according to the flight route;
And if any difference value of the aerodynamic performance data is not in the preset difference range, updating the flight route of the aircraft in a future time period.
Further, the flight path of the aircraft over a future time period is updated by:
updating the proxy model by using the prediction result and the actual data;
re-acquiring current geometrical parameters and meteorological environment parameters of the aircraft through a plurality of sensors on the aircraft;
inputting the re-acquired geometric parameters and meteorological environment parameters into the updated proxy model, and updating the prediction result of the aircraft on aerodynamic performance data;
and inputting the updated prediction result into a motion model, and updating the flight route of the aircraft in a future time period.
Further, the step of updating the proxy model using the prediction result and the actual data includes:
updating a loss function in the proxy model by using the prediction result and the actual data;
model parameters in the proxy model are updated based on the updated loss function to obtain an updated proxy model.
In a second aspect, an embodiment of the present application further provides a device for determining a flight path of an aircraft, where the determining device includes:
the acquisition module is used for acquiring the geometric parameters and the meteorological environment parameters of the aircraft;
the input module is used for inputting the geometric parameters and the meteorological environment parameters into a pre-trained agent model to obtain a prediction result of the aircraft on aerodynamic performance data;
and the determining module is used for inputting the prediction result into the motion model to obtain the flight route of the aircraft.
In a third aspect, an embodiment of the present application further provides an electronic device, including: the system comprises a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, the processor and the memory are communicated through the bus when the electronic device is running, and the machine-readable instructions are executed by the processor to perform the steps of the method for determining the flight path of the aircraft.
In a fourth aspect, embodiments of the present application also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of a method of determining a flight path of an aircraft as described above.
The embodiment of the application provides a method and a device for determining a flight path of an aircraft, electronic equipment and a storage medium, wherein the method for determining the flight path of the aircraft comprises the following steps: acquiring geometrical parameters and meteorological environment parameters of an aircraft; inputting the geometric parameters and the meteorological environment parameters into a pre-trained agent model to obtain a prediction result of the aircraft on aerodynamic performance data; and inputting the prediction result into a motion model to obtain the flight route of the aircraft.
In this way, the technical scheme provided by the application outputs the prediction result of the aerodynamic performance data by taking the acquired geometric parameters and weather environment parameters of the aircraft as the input variables of the proxy model, thereby obtaining the flight route, replacing the complex numerical simulation process, and improving the timeliness and applicability of determining the flight route by determining the flight route through the performance changes of different aircrafts under different weather conditions, thereby reducing the possibility of flight accidents.
In order to make the above objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart illustrating a method for determining a flight path of an aircraft according to an embodiment of the present application;
FIG. 2 illustrates a flow chart of another method of determining a flight path of an aircraft provided by an embodiment of the application;
FIG. 3 shows one of the structural schematic diagrams of an apparatus for determining a flight path of an aircraft according to an embodiment of the present application;
FIG. 4 is a schematic diagram showing a second configuration of an apparatus for determining a flight path of an aircraft according to an embodiment of the present application;
fig. 5 shows a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for the purpose of illustration and description only and are not intended to limit the scope of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. A flowchart, as used in this disclosure, illustrates operations implemented according to some embodiments of the present application. It should be appreciated that the operations of the flow diagrams may be implemented out of order and that steps without logical context may be performed in reverse order or concurrently. Moreover, one or more other operations may be added to or removed from the flow diagrams by those skilled in the art under the direction of the present disclosure.
In addition, the described embodiments are only some, but not all, embodiments of the application. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by a person skilled in the art based on embodiments of the application without making any inventive effort, fall within the scope of the application.
In order to enable one skilled in the art to make use of the present disclosure, the following embodiments are provided in connection with a particular application scenario "determination of flight path of an aircraft", it being possible for one skilled in the art to apply the general principles defined herein to other embodiments and application scenarios without departing from the spirit and scope of the present disclosure.
The method, the device, the electronic equipment or the computer readable storage medium can be applied to any scene needing to determine the flight path of the aircraft, the embodiment of the application is not limited to specific application scenes, and any scheme using the method, the device, the electronic equipment and the storage medium for determining the flight path of the aircraft provided by the embodiment of the application is within the protection scope of the application.
It is worth noting that when the aircraft encounters wind shear, rain, snow and other weather in the flight process, the aircraft is easy to cause accidents, in order to avoid the accidents of the aircraft, the flight path of the aircraft is required to be planned, the planned flight path is different due to different aircraft performances, and the aircraft performances under different aviation weather are required to be calculated.
At present, the performance of the aircraft under different aviation weather can be calculated through single dynamic numerical simulation, but the method consumes a long time, so that the aircraft can not warn pilots in real time according to the icing condition and the aerodynamic characteristic change condition of the weather condition, and the timeliness of the subsequent flight path planning is affected; and each time of numerical simulation only can calculate the ice type change and the corresponding aerodynamic force change condition of the wing surface under certain specific aircraft appearance and certain weather change condition, and the method has certain limitation and influences the applicability of the subsequent flight path planning. Therefore, how to determine the flight path of an aircraft becomes a problem to be solved.
Based on the above, the application provides a method, a device and an electronic device for determining a flight path of an aircraft, wherein the method comprises the following steps: acquiring geometrical parameters and meteorological environment parameters of an aircraft; inputting the geometric parameters and the meteorological environment parameters into a pre-trained agent model to obtain a prediction result of the aircraft on aerodynamic performance data; and inputting the prediction result into a motion model to obtain the flight route of the aircraft.
In this way, the technical scheme provided by the application outputs the prediction result of the aerodynamic performance data by taking the acquired geometric parameters and weather environment parameters of the aircraft as the input variables of the proxy model, thereby obtaining the flight route, replacing the complex numerical simulation process, and improving the timeliness and applicability of determining the flight route by determining the flight route through the performance changes of different aircrafts under different weather conditions, thereby reducing the possibility of flight accidents.
For the convenience of understanding the embodiments of the present application, a method for determining a flight path of an aircraft disclosed in the embodiments of the present application will be described in detail.
Referring to fig. 1, fig. 1 is a flowchart of a method for determining a flight path of an aircraft according to an embodiment of the present application, where, as shown in fig. 1, the method includes:
s101, acquiring geometric parameters and meteorological environment parameters of an aircraft;
in this step, the geometric parameter may be a geometric feature of the wing of the aircraft, such as span, chord length, leading edge sweep, etc.; meteorological parameters may be obtained by weather forecast, such as air density, temperature, wind speed, etc. The geometrical parameters at the current time and the meteorological environment parameters in the future time period can be obtained.
S102, inputting the geometric parameters and the meteorological environment parameters into a pre-trained agent model to obtain a prediction result of the aircraft on aerodynamic performance data;
in the step, the aerodynamic force change of the aircraft under different meteorological conditions is predicted according to the geometrical characteristics of the aircraft and real-time meteorological environment parameters by using a trained proxy model. The predicted outcome may be predicted aerodynamic performance data of the aircraft at the next time or over a future time period, lift, drag, moment, etc.
It should be noted that, referring to fig. 2, fig. 2 is a flowchart of another method for determining a flight path of an aircraft according to an embodiment of the present application, and as shown in fig. 2, the steps of inputting geometric parameters and meteorological environment parameters into a pre-trained proxy model to obtain a prediction result of the aircraft about aerodynamic performance data include:
s201, inputting the geometric parameters and the meteorological environment parameters as input data into a pre-trained proxy model, and acquiring a plurality of first weights from the input layer to the hidden layer and deviations of the hidden layer through the input layer and the hidden layer of the proxy model;
S202, determining an activation function of the hidden layer based on input data, the first weights and deviations of the hidden layer;
s203, when input data passes through a hidden layer and an output layer of the proxy model, a plurality of second weights from the hidden layer to the output layer and deviations of the output layer are obtained;
s204, determining an activation function of the output layer based on the activation function of the hidden layer, the second weights and the deviation of the output layer, and determining a value corresponding to the activation function of the output layer as a prediction result of the aircraft on aerodynamic performance data.
In the above steps S201 to S204, the proxy model may include an input layer, a hidden layer, and an output layer, the weight between the input layer and the hidden layer is determined as a first weight, the weight between the hidden layer and the output layer is determined as a second weight, and the formula for determining the activation function of the hidden layer is as follows:
a j ＝f(∑(w ij ×x i )+b j )；
wherein a is j Is the output of the activation function of the hidden layer, f is the activation function, x i Is input data, w ij Is a first weight, b j Is the bias of the hidden layer. The predicted outcome is determined by the following formula:
y i ＝f(∑(w jk ×a j )+b k )；
wherein y is i Is the prediction result, w jk Is a second weight, b k Is the deviation of the output layer.
S103, inputting the prediction result into a motion model to obtain the flight route of the aircraft.
The step of inputting the prediction result into the motion model to obtain the flight path of the aircraft includes:
s1031, inputting the prediction result into a motion model to obtain a predicted flight parameter of the aircraft;
in this step, the motion model can be expressed by the following formula:
l, D, M is a prediction result and can respectively represent the lift force, the resistance and the pitching moment of the aircraft; alpha, beta,θ is the angle of attack, sideslip angle, yaw angle, pitch angle, respectively; p, q and r are components (rolling angle speed, pitch angle speed and yaw angle speed) of the angular speed in a machine body coordinate system respectively; v, m and g are respectively aircraft speed, mass and gravitational acceleration; i xx 、I yy 、I zz For the moment of inertia of the aircraft about the axis of the fuselage, I xy 、I zx 、I yz The product of inertia of the aircraft around the axis of the aircraft body. V, alpha, theta, q, p and r are predicted flight parameters, and a preset initial value can be adopted to participate in calculation in the first calculation, and the predicted flight parameters can be updated in a subsequent iteration mode by using corresponding real flight parameters; / > Derivatives for the corresponding predicted flight parameters; t (T) x Is the component of the thrust in the x-direction; t (T) z Is the component of thrust in the z-direction; here, the body coordinate system is selected. Wherein its datum point O coincides with the centre of mass of the aircraft, wherein the X-axis is positive with the nose directed from the centre of mass to the aircraft, the Y-axis is directed to the right wing of the aircraft, and the Z-axis is directed downwards.
S1032, determining the change rate of the predicted flight parameters corresponding to each adjacent moment through the predicted flight parameters of the aircraft at each moment in the future flight time;
s1033, integrating the change rate of each predicted flight parameter along with the future flight time to obtain the flight route of the aircraft.
In the above steps S1032 to S1033, the nonlinear mathematical model (motion model) equation in step S1031 may be used to solve the motion route of the aircraft by a computer digital integration method, that is, calculate the rate of change of each predicted flight parameter and then integrate over time to obtain the flight route.
Before proceeding to step S102, it is also necessary to train the proxy model by:
1. acquiring sample geometric parameters of a plurality of sample aircrafts, a plurality of sample meteorological environment parameters and target aerodynamic performance data corresponding to each sample aircrafts under each sample meteorological environment parameter;
2. Inputting the sample geometric parameters and each sample meteorological environment parameter of each sample aircraft into a proxy model for each sample aircraft to obtain a sample prediction result of the sample aircraft on aerodynamic performance data under each sample meteorological environment parameter;
3. determining whether a loss function in the proxy model converges or not by using the sample prediction result and the corresponding target aerodynamic performance data;
4. if not, updating model parameters in the proxy model to train the proxy model; the model parameters comprise a plurality of first weights from an input layer to a hidden layer in the proxy model, a deviation of the hidden layer, a plurality of second weights from the hidden layer to an output layer in the proxy model and a deviation of the output layer;
5. and if the model is converged, obtaining a trained proxy model.
In the first to fifth steps, the initial training process of the proxy model is that the proxy model is trained through simulation data, so that the initially trained proxy model can be obtained, and in the subsequent application process, the proxy model can be updated again through actual data, and further training is performed, so that the proxy model with better prediction effect can be obtained. Here, a surrogate model of aerodynamic changes may be constructed based on machine learning algorithms (e.g., neural networks, support vector machines, etc.), with geometric parameters and meteorological environment parameters as inputs, aerodynamic performance changes as outputs, training the surrogate model to learn complex relationships between inputs and outputs, training the surrogate model with a large amount of sample data, optimizing model parameters to improve prediction accuracy and generalization ability.
By way of example, by means of a computational fluid dynamics tool, the aerodynamic changes of the wing under different weather conditions (aerodynamic performance data) and the ice growth of the wing surface (geometrical parameters) are calculated assuming possible changes of the weather over a period of time (weather environment parameters), the aerodynamic performance data under different aircraft geometries and weather environment conditions are collected, and pre-processed and standardized. Key geometric characteristic parameters such as span, chord length, leading edge sweep angle and the like are extracted and correlated with meteorological environment parameters (such as air density, temperature, wind speed and the like). Input data set: x= [ X ] 1 ,x 2 ,…,x n ]Wherein x is i Is the input information, here the geometric parameters and the meteorological environment parameters. Target data set: y= [ Y ] 1 ,y 2 ,…,y n ]Wherein y is i The output is the corresponding target output, which is the aerodynamic performance data of the lifting force, the resistance, the moment and the like of the aircraft. Taking a neural network as an example, the proxy model includes an input layer, a hidden layer, and an output layer, where the input layer is connected to the hidden layer: calculating the weighted sum (z) of each neuron of the hidden layer j ) And an activation function (a) j ) Is provided. z j ＝∑(w ij ×x i )+b j Wherein w is ij Is the weight of the input layer to the hidden layer, b j Is the bias of the hidden layer. a, a j ＝f(z j ) Where f () is an activation function. Hidden layer to output layer: calculating a weighted sum (z) of the output layers k ) And an activation function (a) k ) Is provided. z k ＝∑(w jk ×a j )+b k Wherein w is jk Is the hidden layer to output layer weight, b k Is the deviation of the output layer. a, a k ＝f(z k ). A Loss function is defined to measure the difference between the predicted outcome of the network and the target output, such as mean square error (Mean Squared Error) and Cross-Entropy Loss (Cross-Entropy Loss). Determining the minimum value of the loss function by a gradient descent method, so as to determine whether the loss function is converged, and if not, back-propagating weights and deviations for updating the network to reduce the value of the loss function. The gradient of the output layer to the hidden layer is calculated by the following formula:
wherein L is 1 Is input data of the input layer, z k Represents the weight of the kth neuron and, therefore, delta k Is the gradient of the output layer to the hidden layer; the gradient of the hidden layer to the input layer is calculated by the following formula:
wherein,is a partial guide symbol L 2 Is the input data of the hidden layer, z j Representing the weight, delta, of the jth neuron j Is the gradient from the hidden layer to the input layer, where the gradient is the direction in which the minimum of the loss function is determined, and a new round of L is determined by the gradient 2 、z j And original L 2 、z j Updating the original model parameters; judging whether the loss function value is converged or not by judging whether the loss function value gradually falls or reaches a certain threshold value, comparing the loss function value with a preset threshold value in real time, if the iteration times are completed but still not smaller than the preset threshold value, and the value subsequently increases with the iteration times at the moment to have an ascending trend, indicating that the loss function is not converged, wherein the specific updating of the weight and deviation from the hidden layer to the output layer is as follows:
Wherein eta 1 And eta 2 Is the learning rate, w jk Is the weight momentThe jth layer of kth neurons in the array, b k Is the kth dimension data in the bias matrix. The training network is iterated by repeating the forward propagation and the backward propagation until a predetermined stopping condition is reached, i.e. the loss function converges, resulting in a trained proxy model.
After step S103, i.e. after obtaining the flight path of the aircraft, the determining method further includes:
1) Acquiring actual data of the aircraft regarding aerodynamic performance data over a period of time of flight;
in this step, because there is a deviation between the external weather environment and the ideal gas, there may be a complex weather such as frost, rain, and snow affecting the external atmospheric flow field, and there may be a change in a certain range between the predicted result and the actual value of these proxy models such as L (lift force) and M (moment), so the predicted L, D, M and the actual data are different, and the flight path of the aircraft may change. Here, the time period may be the last time or the last time, and the actual data is aerodynamic data obtained by calculating the actual flight data of the aircraft according to the equation of motion, for example, the actual lift L, the drag D, the pitching moment M, and the like.
2) The actual data and the prediction result are subjected to difference to obtain a difference value of each piece of pneumatic performance data;
as an example, the actual data and the predicted result at the same time are subjected to difference, for example, the lift force L in the actual data and the lift force L in the predicted result are subtracted to obtain a difference value of the lift force L, the resistance D in the actual data and the resistance D in the predicted result are subtracted to obtain a difference value of the resistance D, and the moment M in the actual data and the moment M in the predicted result are subtracted to obtain a difference value of the moment M.
3) If the difference value of each piece of aerodynamic performance data is within a preset difference range, continuing to fly according to the flight route;
in this step, each aerodynamic performance data has a corresponding preset difference range, for example, the lift force L corresponds to a first preset difference range, the resistance D corresponds to a second preset difference range, the moment M corresponds to a third preset difference range, if the predicted result is only three aerodynamic performance data, the flight can be continued according to the current flight route only if the difference value of the lift force L is in the first preset difference range, the difference value of the resistance D is in the second preset difference range, and the difference value of the moment M is in the third preset difference range, otherwise, step 4 is entered.
4) And if any difference value of the aerodynamic performance data is not in the preset difference range, updating the flight route of the aircraft in a future time period.
In the step, if any difference value of the aerodynamic performance data is not in the corresponding preset difference range, the movement track is changed, and the subsequent flight route of the aircraft needs to be updated to ensure that the aircraft arrives at the destination safely.
It should be noted that, the flight route of the aircraft in the future time period is updated by the following steps:
(1) Updating the proxy model by using the prediction result and the actual data;
in the step, when the actual data of the flight of the aircraft is obtained in the actual flight process, the agent model can be updated by utilizing the actual data and the data predicted before, so that the prediction result of the agent model is further optimized.
The step of updating the proxy model by using the prediction result and the actual data includes:
(1) updating a loss function in the proxy model by using the prediction result and the actual data;
(2) and updating model parameters in the proxy model based on the updated loss function to obtain an updated proxy model.
In the above steps (1) to (2), the method of updating the proxy model is identical to the above method of training the proxy model, except that the loss function is determined by the actual data and the predicted result at the same time, instead of the target aerodynamic performance data simulated in the above step one.
(2) Re-acquiring current geometrical parameters and meteorological environment parameters of the aircraft through a plurality of sensors on the aircraft;
in the step, an airspeed tube, a signal receiver, a navigation control system and the like are arranged on the aircraft and are used for collecting aerodynamic performance data, meteorological environment parameters and geometric parameters of the aircraft in real time, and periodically updating a training data set to reflect new meteorological environment conditions and aerodynamic performance changes, so that the performance of the proxy model is further optimized and improved.
(3) Inputting the re-acquired geometric parameters and meteorological environment parameters into the updated proxy model, and updating the prediction result of the aircraft on aerodynamic performance data;
in the step, feedback adjustment and parameter optimization (updating weight and deviation or repeating the training process) are carried out on the prediction error of the proxy model, so that the updated proxy model is obtained, and the accuracy and stability of the proxy model can be improved. And inputting the re-acquired geometric parameters and meteorological environment parameters into the updated proxy model, and updating the prediction result.
(4) And inputting the updated prediction result into a motion model, and updating the flight route of the aircraft in a future time period.
In the step, the flight route is updated according to the updated prediction result, and the path on-line planning is carried out according to the re-predicted aerodynamic force change condition. The navigation control system is combined with the path planning system to realize linkage among the systems, so that the aircraft can be adaptively adjusted and path optimized according to real-time meteorological conditions. Through the embodiment, the method for the path on-line planning system under aviation weather variation can be realized. The system can utilize the cyclic neural network agent model to predict aerodynamic changes and combine the aerodynamic changes with numerical weather forecast to realize the accuracy and reliability of path planning. Meanwhile, through the linkage of the airspeed tube, the signal receiver and the navigation control system, the timely response of the aircraft to the weather change and the dynamic adjustment of the flight path can be realized, so that potential disastrous results are avoided.
The embodiment of the application provides a method for determining a flight path of an aircraft, which comprises the following steps: acquiring geometrical parameters and meteorological environment parameters of an aircraft; inputting the geometric parameters and the meteorological environment parameters into a pre-trained agent model to obtain a prediction result of the aircraft on aerodynamic performance data; and inputting the prediction result into a motion model to obtain the flight route of the aircraft.
In this way, the technical scheme provided by the application outputs the prediction result of the aerodynamic performance data by taking the acquired geometric parameters and weather environment parameters of the aircraft as the input variables of the proxy model, thereby obtaining the flight route, replacing the complex numerical simulation process, and improving the timeliness and applicability of determining the flight route by determining the flight route through the performance changes of different aircrafts under different weather conditions, thereby reducing the possibility of flight accidents.
Based on the same inventive concept, the embodiment of the application also provides a device for determining the flight route of the aircraft, which corresponds to the method for determining the flight route of the aircraft, and because the principle of solving the problem by the device in the embodiment of the application is similar to that of the method in the embodiment of the application, the implementation of the device can refer to the implementation of the method, and the repetition is omitted.
Referring to fig. 3 and 4, fig. 3 is a schematic structural diagram of a determining device for an aircraft flight path according to an embodiment of the present application, and fig. 4 is a schematic structural diagram of a second determining device for an aircraft flight path according to an embodiment of the present application, as shown in fig. 3, the determining device 310 includes:
The acquisition module 311 is configured to acquire geometric parameters and meteorological environment parameters of the aircraft;
the input module 312 is configured to input the geometric parameter and the meteorological environment parameter into a pre-trained proxy model, so as to obtain a prediction result of the aircraft about aerodynamic performance data;
and the determining module 313 is used for inputting the prediction result into the motion model to obtain the flight route of the aircraft.
Optionally, when the input module 312 is configured to input the geometric parameter and the meteorological environment parameter into a pre-trained proxy model, to obtain a prediction result of the aircraft about aerodynamic performance data, the input module 312 is specifically configured to:
inputting the geometric parameters and the meteorological environment parameters as input data into a pre-trained proxy model, and acquiring a plurality of first weights from the input layer to the hidden layer and deviations of the hidden layer through the input layer and the hidden layer of the proxy model;
determining an activation function of the hidden layer based on input data, the plurality of first weights, and a deviation of the hidden layer;
when input data passes through a hidden layer and an output layer of the proxy model, a plurality of second weights from the hidden layer to the output layer and deviations of the output layer are obtained;
And determining an activation function of the output layer based on the activation function of the hidden layer, the plurality of second weights and the deviation of the output layer, and determining a value corresponding to the activation function of the output layer as a prediction result of the aircraft on aerodynamic performance data.
Optionally, when the determining module 313 is configured to input the prediction result into a motion model to obtain a flight path of the aircraft, the determining module 313 is specifically configured to:
inputting the prediction result into a motion model to obtain a predicted flight parameter of the aircraft;
determining the change rate of the predicted flight parameters corresponding to each adjacent moment through the predicted flight parameters of the aircraft at each moment in the future flight time;
integrating the change rate of each predicted flight parameter along with the future flight time to obtain the flight route of the aircraft.
Optionally, as shown in fig. 4, the determining apparatus 310 further includes a training module 314, where the training module 314 is configured to:
acquiring sample geometric parameters of a plurality of sample aircrafts, a plurality of sample meteorological environment parameters and target aerodynamic performance data corresponding to each sample aircrafts under each sample meteorological environment parameter;
Inputting the sample geometric parameters and each sample meteorological environment parameter of each sample aircraft into a proxy model for each sample aircraft to obtain a sample prediction result of the sample aircraft on aerodynamic performance data under each sample meteorological environment parameter;
determining whether a loss function in the proxy model converges or not by using the sample prediction result and the corresponding target aerodynamic performance data;
if not, updating model parameters in the proxy model to train the proxy model; the model parameters comprise a plurality of first weights from an input layer to a hidden layer in the proxy model, a deviation of the hidden layer, a plurality of second weights from the hidden layer to an output layer in the proxy model and a deviation of the output layer;
and if the model is converged, obtaining a trained proxy model.
Optionally, as shown in fig. 4, the determining apparatus 310 further includes an update module 315, where the update module 315 is configured to:
acquiring actual data of the aircraft regarding aerodynamic performance data over a time period of flight;
the actual data and the prediction result are subjected to difference to obtain a difference value of each piece of pneumatic performance data;
If the difference value of each pneumatic performance data is within the preset difference range, continuing to fly according to the flight route;
and if any difference value of the aerodynamic performance data is not in the preset difference range, updating the flight route of the aircraft in a future time period.
Optionally, when the updating module 315 is configured to update the flight path of the aircraft in the future time period, the updating module 315 is specifically configured to:
updating the proxy model by using the prediction result and the actual data;
re-acquiring current geometrical parameters and meteorological environment parameters of the aircraft through a plurality of sensors on the aircraft;
inputting the re-acquired geometric parameters and meteorological environment parameters into the updated proxy model, and updating the prediction result of the aircraft on aerodynamic performance data;
and inputting the updated prediction result into a motion model, and updating the flight route of the aircraft in a future time period.
Optionally, when the updating module 315 is configured to update the proxy model using the prediction result and the actual data, the updating module 315 is specifically configured to:
Updating a loss function in the proxy model by using the prediction result and the actual data;
model parameters in the proxy model are updated based on the updated loss function to obtain an updated proxy model.
The embodiment of the application provides a device for determining a flight path of an aircraft, which comprises the following components: the acquisition module is used for acquiring the geometric parameters and the meteorological environment parameters of the aircraft; the input module is used for inputting the geometric parameters and the meteorological environment parameters into a pre-trained agent model to obtain a prediction result of the aircraft on aerodynamic performance data; and the determining module is used for inputting the prediction result into the motion model to obtain the flight route of the aircraft.
In this way, the technical scheme provided by the application outputs the prediction result of the aerodynamic performance data by taking the acquired geometric parameters and weather environment parameters of the aircraft as the input variables of the proxy model, thereby obtaining the flight route, replacing the complex numerical simulation process, and improving the timeliness and applicability of determining the flight route by determining the flight route through the performance changes of different aircrafts under different weather conditions, thereby reducing the possibility of flight accidents.
Referring to fig. 5, fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the application. As shown in fig. 5, the electronic device 500 includes a processor 510, a memory 520, and a bus 530.
The memory 520 stores machine-readable instructions executable by the processor 510, and when the electronic device 500 is running, the processor 510 communicates with the memory 520 through the bus 530, and when the machine-readable instructions are executed by the processor 510, the steps of the method for determining a flight path of an aircraft in the method embodiments shown in fig. 1-2 can be executed, and detailed implementation can be referred to the method embodiments and will not be repeated herein.
The embodiment of the present application further provides a computer readable storage medium, where a computer program is stored on the computer readable storage medium, and the computer program when executed by a processor may perform the steps of the method for determining a flight path of an aircraft in the method embodiment shown in the foregoing fig. 1 to fig. 2, and a specific implementation manner may refer to the method embodiment and will not be described herein.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be other manners of division in actual implementation, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Finally, it should be noted that: the above examples are only specific embodiments of the present application, and are not intended to limit the scope of the present application, but it should be understood by those skilled in the art that the present application is not limited thereto, and that the present application is described in detail with reference to the foregoing examples: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (10)
1. A method of determining a flight path of an aircraft, the method comprising:
acquiring geometrical parameters and meteorological environment parameters of an aircraft;
inputting the geometric parameters and the meteorological environment parameters into a pre-trained agent model to obtain a prediction result of the aircraft on aerodynamic performance data;
and inputting the prediction result into a motion model to obtain the flight route of the aircraft.
2. The method of determining according to claim 1, wherein the step of inputting the geometric parameters and the meteorological environment parameters into a pre-trained proxy model to obtain a prediction of aerodynamic performance data of the aircraft comprises:
inputting the geometric parameters and the meteorological environment parameters as input data into a pre-trained proxy model, and acquiring a plurality of first weights from the input layer to the hidden layer and deviations of the hidden layer through the input layer and the hidden layer of the proxy model;
determining an activation function of the hidden layer based on input data, the plurality of first weights, and a deviation of the hidden layer;
when input data passes through a hidden layer and an output layer of the proxy model, a plurality of second weights from the hidden layer to the output layer and deviations of the output layer are obtained;
And determining an activation function of the output layer based on the activation function of the hidden layer, the plurality of second weights and the deviation of the output layer, and determining a value corresponding to the activation function of the output layer as a prediction result of the aircraft on aerodynamic performance data.
3. The method according to claim 1, wherein the step of inputting the prediction result into a motion model to obtain a flight path of the aircraft comprises:
inputting the prediction result into a motion model to obtain a predicted flight parameter of the aircraft;
determining the change rate of the predicted flight parameters corresponding to each adjacent moment through the predicted flight parameters of the aircraft at each moment in the future flight time;
integrating the change rate of each predicted flight parameter along with the future flight time to obtain the flight route of the aircraft.
4. The method of determining of claim 1, wherein the proxy model is trained by:
acquiring sample geometric parameters of a plurality of sample aircrafts, a plurality of sample meteorological environment parameters and target aerodynamic performance data corresponding to each sample aircrafts under each sample meteorological environment parameter;
Inputting the sample geometric parameters and each sample meteorological environment parameter of each sample aircraft into a proxy model for each sample aircraft to obtain a sample prediction result of the sample aircraft on aerodynamic performance data under each sample meteorological environment parameter;
determining whether a loss function in the proxy model converges or not by using the sample prediction result and the corresponding target aerodynamic performance data;
if not, updating model parameters in the proxy model to train the proxy model; the model parameters comprise a plurality of first weights from an input layer to a hidden layer in the proxy model, a deviation of the hidden layer, a plurality of second weights from the hidden layer to an output layer in the proxy model and a deviation of the output layer;
and if the model is converged, obtaining a trained proxy model.
5. The method of determining according to claim 1, wherein after the obtaining the flight path of the aircraft, the method further comprises:
acquiring actual data of the aircraft regarding aerodynamic performance data over a time period of flight;
the actual data and the prediction result are subjected to difference to obtain a difference value of each piece of pneumatic performance data;
If the difference value of each pneumatic performance data is within the preset difference range, continuing to fly according to the flight route;
and if any difference value of the aerodynamic performance data is not in the preset difference range, updating the flight route of the aircraft in a future time period.
6. The method of determining of claim 5, wherein the flight path of the aircraft over a future time period is updated by:
updating the proxy model by using the prediction result and the actual data;
re-acquiring current geometrical parameters and meteorological environment parameters of the aircraft through a plurality of sensors on the aircraft;
inputting the re-acquired geometric parameters and meteorological environment parameters into the updated proxy model, and updating the prediction result of the aircraft on aerodynamic performance data;
and inputting the updated prediction result into a motion model, and updating the flight route of the aircraft in a future time period.
7. The method of determining according to claim 6, wherein the step of updating the proxy model using the prediction result and the actual data includes:
Updating a loss function in the proxy model by using the prediction result and the actual data;
model parameters in the proxy model are updated based on the updated loss function to obtain an updated proxy model.
8. A determination device for a flight path of an aircraft, the determination device comprising:
the acquisition module is used for acquiring the geometric parameters and the meteorological environment parameters of the aircraft;
the input module is used for inputting the geometric parameters and the meteorological environment parameters into a pre-trained agent model to obtain a prediction result of the aircraft on aerodynamic performance data;
and the determining module is used for inputting the prediction result into the motion model to obtain the flight route of the aircraft.
9. An electronic device, comprising: a processor, a memory and a bus, said memory storing machine readable instructions executable by said processor, said processor and said memory communicating via said bus when the electronic device is operating, said machine readable instructions when executed by said processor performing the steps of the method of determining a flight path of an aircraft as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that it has stored thereon a computer program which, when being executed by a processor, performs the steps of the method of determining a flight path of an aircraft according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310960802.6A CN117057226A (en) | 2023-08-01 | 2023-08-01 | Method and device for determining flight route of aircraft, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310960802.6A CN117057226A (en) | 2023-08-01 | 2023-08-01 | Method and device for determining flight route of aircraft, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117057226A true CN117057226A (en) | 2023-11-14 |
Family
ID=88652782
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310960802.6A Pending CN117057226A (en) | 2023-08-01 | 2023-08-01 | Method and device for determining flight route of aircraft, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117057226A (en) |
-
2023
- 2023-08-01 CN CN202310960802.6A patent/CN117057226A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104773304B (en) | Load estimation system for aerodynamic structures | |
| CN111351488B (en) | Intelligent trajectory reconstruction reentry guidance method for aircraft | |
| US10520389B2 (en) | Aerodynamic modeling using flight data | |
| CN110209195B (en) | Remote control system and control method for offshore unmanned aerial vehicle | |
| CN110806759B (en) | Aircraft route tracking method based on deep reinforcement learning | |
| CN114048889A (en) | Aircraft trajectory prediction method based on long-term and short-term memory network | |
| CN107021237A (en) | Synthesis of air data output is generated | |
| CN111310965A (en) | Aircraft track prediction method based on LSTM network | |
| CN111176263B (en) | Online identification method for thrust fault of aircraft based on BP neural network | |
| CN113268074B (en) | Unmanned aerial vehicle flight path planning method based on joint optimization | |
| ES2953038T3 (en) | Optimization of a parametric model of aircraft performance | |
| CN113190036A (en) | Unmanned aerial vehicle flight trajectory prediction method based on LSTM neural network | |
| CN114329766A (en) | Flight dynamics model reliability evaluation method for deep reinforcement learning | |
| Mersha et al. | Angle of attack prediction using recurrent neural networks in flight conditions with faulty sensors in the case of F-16 fighter jet | |
| CN113485443A (en) | Unmanned aerial vehicle control method based on deep learning, storage medium and equipment | |
| CN110779526B (en) | Path planning method, device and storage medium | |
| CN117113870A (en) | Aerodynamic modeling method of fixed wing aircraft considering wind interference | |
| CN117057226A (en) | Method and device for determining flight route of aircraft, electronic equipment and storage medium | |
| CN115993077A (en) | Optimal decision method and optimal decision system for inertial navigation system under complex road condition transportation condition | |
| Millidere et al. | Kalman based neural network model analysis with resampling methods for longitudinal aerodynamic coefficient estimation | |
| Sharma et al. | Gradient descent feed forward neural networks for forecasting the trajectories | |
| Gao et al. | Adaptive air-data estimation in wind disturbance based on flight data | |
| Hussain et al. | Aircraft sensor estimation for fault tolerant flight control system using fully connected cascade neural network | |
| Garcia et al. | Adaptive and resilient flight control system for a small unmanned aerial system | |
| Donofrio | All weather, gps free and data-driven synthetic sensor for angle of attack and sideslip estimation |
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 |