Low altitude intelligent flight management system and method

Abstract

The application discloses a low-altitude intelligent flight management system and method, belonging to the field of low-altitude flight management, comprising a flight plan management module, a data link application module, a flight path prediction module, a flight guidance module, a comprehensive navigation management module, a navigation database management module, a performance calculation module and a man-machine interface management module, further utilizing artificial intelligence technology to realize intelligent flight path prediction and flight guidance; and through learning of historical flight data, specific aircraft performance parameters are implicitly fixed in a neural network, the turning, climbing and descending characteristics of the aircraft can be obtained, the artificial intelligence model realizes flight path planning and flight guidance based on the characteristics, and can provide a best estimation in experience for pilots. The application has the advantages of high intelligence degree and strong applicability.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of low-altitude flight management, and more particularly to a low-altitude intelligent flight management system and method. BACKGROUND

[0002] With the increasingly serious problem of ground traffic congestion and the gradual maturity of general aviation, electric vertical take-off and landing (eVTOL), and unmanned aerial vehicle technology, the world is actively exploring and cultivating low-altitude economic industries. As a new form of digital economic transformation and development, low-altitude economy is based on low-altitude airspace and its associated ground infrastructure, driven by various manned and unmanned aerial vehicles, and plays an important role in promoting logistics delivery, logistics transportation, feeder passenger transportation, remote sensing detection, agricultural and forestry plant protection, emergency rescue, sports tourism, and other industries. It has strong radiation benefits and a long industrial chain, and is a comprehensive economic form.

[0003] Due to the development process of low-altitude airspace control measures, positioning communication technology, navigation technology, sensing technology, computing power, and intelligent algorithms, a complete set of standards has not yet been formed to regulate product research and development and application. The flight management of low-altitude aircraft is facing problems such as low airspace refinement level, inaccurate situation awareness, and weak guidance and control capabilities. The research and development and application of related products are still in the early stages.

[0004] Traditional flight management systems are based on aircraft performance data and use dynamic models for trajectory prediction and flight guidance. However, with the development of artificial intelligence technology, intelligent flight management systems that learn from historical flight data to predict trajectories and guide flights have also emerged. Therefore, it is important to conduct research on intelligent flight management technology for low-altitude economy, to break through the architecture of intelligent flight management systems, artificial intelligence trajectory prediction, and low-altitude integrated navigation, and to form design capabilities for intelligent flight management systems that support intelligent decision-making flight management functions. SUMMARY

[0005] The present application aims to overcome the shortcomings of the prior art and provide a low-altitude intelligent flight management system and method with high intelligence and strong applicability.

[0006] The purpose of the present application is achieved by the following scheme:

[0007] A low-altitude intelligent flight management system, comprising:

[0008] The flight plan management module is configured to receive pilot input data according to a human-machine interaction management function, or receive data according to a data link application management function, extract required navigation station and waypoint information from a navigation database, and generate a complete flight plan, wherein flight plan information is provided to other functions inside the FMS for use;

[0009] The data link application module is configured to be connected with an external communication management system, realize air-ground track negotiation, and be capable of transmitting track data, weather data and air-ground communication data.

[0010] The track prediction module specifically comprises a dual-mode prediction submodule combined by a dynamic model and an intelligent algorithm model, and is configured to construct horizontal and vertical tracks, and perform prediction of speed, height, climb vertex, descent vertex and remaining fuel information.

[0011] The flight guidance module is configured to calculate lateral deviation, vertical deviation, horizontal guidance instruction and vertical guidance instruction information according to flight tracks and current position information by using a dual-mode guidance submodule combined by a dynamic model and an intelligent flight guidance algorithm based on reinforcement learning, and send the horizontal and vertical guidance instructions to an autopilot and an automatic throttle, so that the aircraft automatically flies according to the expected track.

[0012] The integrated navigation management module is configured to receive signals of an inertial reference system, a satellite navigation system, an air data computer, a radio navigation device, a mobile base station, a low-orbit satellite and a landmark, perform integrated navigation calculation, calculate optimal position information, and perform real-time monitoring and alarming on navigation performance such as precision and integrity.

[0013] The navigation database management module is configured to load and download a navigation database, a performance database and historical flight data by using an onboard maintenance system, and provide related data information for the flight plan management, track prediction, flight guidance and integrated navigation management modules.

[0014] The performance calculation module is configured to perform performance data calculation and performance calculation, provide data required for dynamic calculation, and calculate maximum height, optimized height, time / fuel to climb / descent vertex and economic speed based on performance data.

[0015] The human-machine interface management module is configured to provide human-machine interaction functions for pilots to input flight plans, set flight parameters, monitor aircraft navigation states and view flight performance parameters to the flight management system.

[0016] Further, in the track prediction module, the construction of the horizontal and vertical tracks is specifically based on flight plans, aircraft and engine performance, air traffic control requirements, weather conditions and historical flight data.

[0017] Further, in the dual-mode predictor module, the track prediction is based on the dynamic component, and the performance of the track prediction is monitored in real time, and when the performance of the dynamic component drops to the allowable value, the intervention of the artificial intelligence component is realized through decision switching.

[0018] Further, in the performance calculation module, the data required for the dynamic calculation specifically includes aircraft aerodynamic and engine data, thrust, drag and fuel flow data.

[0019] Further, the intervention of the artificial intelligence component through decision switching specifically includes:

[0020] Before starting, the artificial intelligence model is trained using historical flight data;

[0021] After starting, the initial state of the aircraft is set;

[0022] Then, the track prediction is performed using the dynamic component and the artificial intelligence component; the prediction result of the dynamic component is evaluated, and if the integrity of the dynamic prediction result is insufficient, the prediction result of the artificial intelligence component is used, otherwise the dynamic component is continuously used; after continuing to fly for a calculation interval, the track is recalculated until the flight ends.

[0023] Further, the initial state of the aircraft is the initial position of the aircraft and the flight plan.

[0024] A low-altitude intelligent flight management method, based on the low-altitude intelligent flight management system as described above, in the dual-mode predictor module combining the dynamic model and the intelligent algorithm model, the following steps are performed:

[0025] S1, training an artificial intelligence model using historical flight data;

[0026] S2, first setting the initial state of the aircraft;

[0027] S3, track prediction is performed using the dynamic component and the artificial intelligence component;

[0028] S4, the prediction result of the dynamic component is evaluated, and if the integrity of the dynamic prediction result is insufficient, the prediction result of the artificial intelligence component is used, otherwise the dynamic component is continuously used; after continuing to fly for a calculation interval, the track is recalculated until the flight ends.

[0029] An electronic system, comprising a computer device, and a program is stored in the memory of the computer device, and when the program is loaded by the processor, the low-altitude intelligent flight management method as described above is executed.

[0030] The beneficial effects of the present application include:

[0031] (1) The application has the advantages of high intelligence. Specifically, the application utilizes artificial intelligence technology to realize intelligent flight path prediction and flight guidance function, thereby improving the intelligence level of the aircraft, and has the advantages of low calculation cost, high real-time performance and high precision. When controlling the flight state, the long-term benefits can be predicted, and the learning ability and prediction ability are very strong. The future situation that may be encountered can be planned in advance, thereby greatly improving the flight benefit and reducing the workload of the pilot.

[0032] (2) The application has strong applicability. Specifically, by learning the historical flight data, the performance parameters of the specific aircraft are implicitly fixed in the neural network, and the turning, climbing and descending characteristics of the aircraft can be obtained. The artificial intelligence model realizes flight path planning and flight guidance based on these characteristics, and can provide the best estimate in experience for the pilot. Since the data comes from actual flight data, the estimate not only considers the performance of the aircraft, but also implicitly considers the technical error of the pilot and the geographical features of the flight path. Therefore, the application has stronger applicability than the traditional dynamic model. BRIEF DESCRIPTION OF DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only some embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0034] Figure 1 The intelligent flight management system architecture of the embodiment of the application;

[0035] Figure 2 The step flow chart of the dual-mode flight path prediction decision method of the embodiment of the application. DETAILED DESCRIPTION

[0036] All features disclosed in all embodiments of the present specification, or all steps in the implicitly disclosed methods, can be combined and / or extended, replaced, unless mutually exclusive features and / or steps are mutually exclusive.

[0037] The specific implementation process of the application is as follows:

[0038] In a preferred system embodiment, an intelligent flight management system architecture is proposed, which integrates the traditional trajectory prediction and flight guidance algorithm based on the dynamics method and the trajectory prediction and flight guidance algorithm based on artificial intelligence, with the dynamics method as the main method and the artificial intelligence as the auxiliary decision-making. Compared with the traditional flight management system, the intelligent flight management system has higher flexibility and adaptability, and has high computing efficiency and long-term benefit prediction and response ability, and provides accurate and timely flight information for the pilot, and improves the scientificity and rationality of flight decision-making. The intelligent flight management system architecture, as shown in Figure 1 includes the following contents:

[0039] A flight plan management module, the flight plan management function receives the pilot input data according to the human-computer interaction management function, or receives the data from the data link application management function, extracts the required navigation station and waypoint information from the navigation database, generates a complete flight plan, and the flight plan information will be provided to other functions inside the FMS for use;

[0040] A data link application module, the data link application is cross-linked with the external communication management system, realizes air-ground trajectory negotiation, and can transmit trajectory data, weather data, air-ground communication and other data;

[0041] A trajectory prediction module, the trajectory prediction function includes a dual-mode prediction combining a dynamics model and an intelligent algorithm model, constructs horizontal and vertical trajectories according to the flight plan, aircraft and engine performance, air traffic control requirements, weather conditions and historical flight data, and predicts speed, altitude, climb top, descent top, remaining fuel and other information;

[0042] A flight guidance module, the flight guidance function is based on the flight guidance module based on the dynamics model, and the intelligent flight guidance function calculates the lateral deviation, vertical deviation, horizontal guidance instruction and vertical guidance instruction according to the flight trajectory and the current position information by using the reinforcement learning technology; The horizontal and vertical guidance instructions are sent to the autopilot and the automatic throttle, so that the aircraft automatically flies according to the expected trajectory;

[0043] A comprehensive navigation management module, the comprehensive navigation management function receives the signals of the inertial reference system, the satellite navigation system, the air data computer, the radio navigation equipment, the mobile base station, the low-orbit satellite and the landmark, performs comprehensive navigation calculation to calculate the best position information, and performs real-time monitoring and alarm on the navigation performance such as accuracy and integrity;

[0044] A navigation database management module, the database management function realizes the loading and downloading of the navigation database, the performance database and the historical flight data by using the onboard maintenance system, and provides related data information for the flight plan management, trajectory prediction, flight guidance, comprehensive navigation management and other modules;

[0045] The performance calculation module mainly realizes performance data calculation and performance calculation, and provides data required by dynamic calculation, such as aircraft aerodynamic and engine data, thrust, resistance, fuel flow and the like, and calculates maximum height, optimized height, time / fuel to climb / descent top point, economic speed and the like based on the performance data.

[0046] The human-computer interface management module mainly provides human-computer interaction functions for the pilot to input a flight plan, set flight parameters, monitor aircraft navigation states and view flight performance parameters to the flight management system.

[0047] In a preferred method embodiment, based on the above system, a dual-mode decision method is provided to perform trajectory prediction based on the dynamic component, and to perform real-time integrity monitoring on the performance of the trajectory prediction, and when the performance of the dynamic component decreases to a permitted value, the intervention of the artificial intelligence component is realized through decision switching.

[0048] The decision switching process is as shown in Figure 2 Before starting, the artificial intelligence model needs to be trained using historical flight data; after starting, the initial state of the aircraft, i.e., the initial position of the aircraft and the flight plan, is first set; then the dynamic component and the artificial intelligence component are used to perform trajectory prediction; the prediction result of the dynamic component is evaluated, and if the integrity of the dynamic prediction result is insufficient, the prediction result of the artificial intelligence component is used, otherwise the dynamic component is continuously used; after continuing to fly for a calculation interval, the trajectory is recalculated until the flight ends.

[0049] The units described in the embodiments of the present application can be implemented in the form of software, or can be implemented in the form of hardware, and the described units can also be arranged in a processor. In some cases, the names of these units do not constitute a limitation on the units themselves.

[0050] According to an aspect of an embodiment of the present application, a computer program product or computer program is provided, which includes computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method provided in the various optional implementation manners described above.

[0051] As another aspect, the embodiment of the present application further provides a computer readable medium, which can be included in the electronic device described in the above embodiments, or can exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device implements the method described in the above embodiments.

Claims

1. A low altitude intelligent flight management system, characterized by, The application relates to a flight management system (FMS) for a large aircraft, which comprises the following modules: a flight plan management module for receiving pilot input data according to a human-machine interaction management function or data received according to a data link application management function, extracting required navigation station and waypoint information from a navigation database, and generating a complete flight plan, wherein the flight plan information is provided for other functions inside the FMS; a data link application module for cross-linking with an external communication management system, realizing air-ground track negotiation, and being capable of transmitting track data, weather data and air-ground communication data; a track prediction module, which specifically comprises a double-mode prediction sub-module combining a dynamic model and an intelligent algorithm model, and is used for constructing horizontal and vertical tracks and predicting speed, height, climbing top point, descending top point and residual fuel information; a flight guidance module, which adopts a double-mode guidance sub-module combining a dynamic model and an intelligent flight guidance algorithm based on reinforcement learning to calculate lateral deviation, vertical deviation and horizontal and vertical guidance instruction information according to flight tracks and current position information, and sends the horizontal and vertical guidance instructions to an autopilot and an automatic throttle, so that the aircraft automatically flies according to the expected tracks; a comprehensive navigation management module for receiving signals of an inertial reference system, a satellite navigation system, an air data computer, a radio navigation device, a mobile base station, a low-orbit satellite and a landmark, performing comprehensive navigation calculation to calculate optimal position information, and performing real-time monitoring and alarming on the precision and integrity of navigation performance; a navigation database management module for realizing loading and downloading of a navigation database, a performance database and historical flight data by an onboard maintenance system, and providing related data information for the flight plan management, track prediction, flight guidance and comprehensive navigation management modules; a performance calculation module for realizing performance data calculation and performance calculation, providing data required for dynamic calculation, calculating maximum height, optimized height, time / fuel to a climbing / descending top point and economic speed based on performance data; a human-machine interface management module for providing human-machine interaction functions for a pilot to input a flight plan, set flight parameters, monitor aircraft navigation states and view flight performance parameters to the flight management system; in the double-mode prediction sub-module, track prediction is performed based on a dynamic component, and the performance of track prediction is monitored in real time, when the performance of the dynamic component drops to an allowable value, an artificial intelligent component is intervened through decision switching; the intervention of the artificial intelligent component through decision switching specifically comprises the following steps: before starting, training the artificial intelligent model by using historical flight data; after starting, setting an initial state of the aircraft; then, performing track prediction by using the dynamic component and the artificial intelligent component; evaluating the prediction result of the dynamic component, using the prediction result of the artificial intelligent component when the integrity of the dynamic prediction result is insufficient, otherwise, continuing to use the dynamic component; recalculating the track after continuing to fly for a calculation interval until the flight is finished.

2. The low altitude intelligent flight management system of claim 1, wherein, In the flight path prediction module, the horizontal flight path and the vertical flight path are constructed according to a flight plan, aircraft and engine performance, air traffic control requirements, weather conditions and historical flight data.

3. The low altitude intelligent flight management system of claim 1, wherein, In the performance calculation module, the data required for the dynamic calculation specifically includes aircraft aerodynamic and engine data, thrust, drag and fuel flow data.

4. The low altitude intelligent flight management system of claim 1, wherein, The initial state of the aircraft is an initial position of the aircraft and a flight plan.

5. A low altitude intelligent flight management method, characterized by, The low-altitude intelligent flight management system according to claim 1.

6. An electronic system, characterized by The low-altitude intelligent flight management system comprises a computer device, and a program is stored in a memory of the computer device, and when the program is loaded by a processor, the low-altitude intelligent flight management method according to claim 5 is executed.

Images