Low-altitude intelligent flight management system and method

Abstract

The invention discloses a low-altitude intelligent flight management system and method, and belongs to the field of low-altitude flight management, and the system comprises a flight plan management module, a data link application module, a flight path prediction module, a flight guide module, a comprehensive navigation management module, a navigation database management module, a performance calculation module and a man-machine interface management module. The artificial intelligence technology is further utilized to realize intelligent track prediction and flight guidance; and by learning historical flight data, specific aircraft performance parameters are implicitly fixed in a neural network, turning, climbing and descending characteristics of the aircraft can be obtained, an artificial intelligence model realizes flight path planning and flight guidance based on the characteristics, and an empirical optimal estimation can be provided for a pilot. The system has the advantages of being high in intelligent degree and high in applicability.

Description

Technical Field

[0001] The present invention relates to the field of low-altitude flight management, and more specifically, to a low-altitude intelligent flight management system and method. Background Art

[0002] With the increasing severity of ground traffic congestion and the gradual maturity of general aircraft, electric Vertical Take-off and Landing (eVTOL), and drone technologies, the world is actively exploring and cultivating the low-altitude economic industry. As a new form of digital economic transformation and development, the low-altitude economy is based on low-altitude airspace and its related ground infrastructure support, and is driven by various low-altitude flight activities of various manned and unmanned aircraft. It plays an important role in promoting many industries such as logistics delivery, logistics transportation, feeder passenger transportation, remote sensing detection, agricultural and forestry plant protection, emergency rescue, sports tourism, etc., and is a comprehensive economic form with strong radiation benefits and a long industrial chain.

[0003] Limited by the development progress of low-altitude airspace control measures, positioning and communication technology, navigation technology, perception technology, computing power and intelligent algorithms, there is currently no complete set of standards to regulate the research and development and application of their products. The flight management of low-altitude aircraft faces problems such as low level of airspace refinement, inaccurate situational awareness, and weak guidance and control capabilities. The research and development and application of related products are in the initial stage.

[0004] Traditional flight management systems are based on aircraft performance data and use dynamic models to predict flight paths and guide flight. However, with the development of artificial intelligence technology, intelligent flight management technology that achieves trajectory prediction and flight guidance by learning historical flight data has also emerged. Therefore, it is necessary to carry out research on intelligent flight management technology for low-altitude economy, make early arrangements in the low-altitude economy, and break through key intelligent flight management technologies such as intelligent flight management system architecture, artificial intelligence trajectory prediction, and low-altitude integrated navigation. It is of great significance to form the ability to design intelligent flight management systems and realize flight management functions that support intelligent decision-making. Summary of the invention

[0005] The purpose of the present invention is to overcome the deficiencies of the prior art and to provide a low-altitude intelligent flight management system and method, which has the advantages of high intelligence and strong applicability.

[0006] The object of the present invention is achieved through the following solutions:

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

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

[0009] Data link application module, used to interconnect with external communication management systems to achieve air-ground track negotiation, capable of transmitting track data, meteorological data and air-ground communication data;

[0010] The track prediction module includes a dual-mode prediction submodule that combines a dynamic model and an intelligent algorithm model, which is used to construct horizontal and vertical tracks and predict speed, altitude, top of climb, top of descent, and remaining fuel information.

[0011] The flight guidance module uses a dual-mode guidance submodule that combines a dynamics model with an intelligent flight guidance algorithm based on reinforcement learning to calculate lateral deviation, vertical deviation, and horizontal guidance instructions and vertical guidance instruction information based on the flight track and current position information. The horizontal and vertical guidance instructions will be sent to the autopilot and autothrottle to enable the aircraft to automatically fly along the desired track.

[0012] Integrated navigation management module, which is used to receive signals from inertial reference system, satellite navigation system, atmospheric data computer, radio navigation equipment, mobile base station, low-orbit satellite and landmark, perform integrated navigation calculation to calculate the best position information, and conduct real-time monitoring and alarm of navigation performance such as accuracy and integrity;

[0013] The navigation database management module is used to load and download the navigation database, performance database, and historical flight data using the onboard maintenance system, and provide relevant data information for the flight plan management, track prediction, flight guidance, and integrated navigation management modules;

[0014] Performance calculation module, used to realize performance data calculation and performance calculation, provide data required for dynamic calculation, calculate maximum altitude, optimized altitude, time / fuel to the top of climb / descent, and economic speed based on performance data;

[0015] The human-machine interface management module is used to provide the pilot with human-machine interaction functions such as inputting flight plans into the flight management system, setting flight parameters, monitoring the aircraft navigation status, and viewing flight performance parameters.

[0016] Furthermore, in the track prediction module, the horizontal track and the vertical track are constructed specifically according to the flight plan, aircraft and engine performance, air traffic control requirements, meteorological conditions and historical flight data.

[0017] Furthermore, in the dual-mode prediction submodule, trajectory prediction is performed based on dynamic components, and the integrity of the trajectory prediction performance is monitored in real time. When the performance of the dynamic components drops to an allowable value, the intervention of the artificial intelligence components is achieved through decision switching.

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

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

[0020] Before getting started, train the AI ​​model using historical flight data;

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

[0022] Then, the trajectory is predicted using the dynamic components and artificial intelligence components. The prediction results of the dynamic components are evaluated. If the integrity of the dynamic prediction results is insufficient, the artificial intelligence component prediction results are used, otherwise the dynamic components are continued to be used. The trajectory is recalculated after continuing to fly for a calculation interval until the end of the flight.

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

[0024] A low-altitude intelligent flight management method, based on the low-altitude intelligent flight management system as described above, performs the following steps in a dual-mode prediction submodule combining a dynamic model and an intelligent algorithm model:

[0025] S1, using historical flight data to train AI models;

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

[0027] S3, uses dynamic components and artificial intelligence components to predict flight paths;

[0028] S4, evaluate the prediction results of the dynamic components. If the integrity of the dynamic prediction results is insufficient, use the prediction results of the artificial intelligence components, otherwise continue to use the dynamic components; continue to fly for one calculation interval and recalculate the track until the end of the flight.

[0029] An electronic system includes a computer device, in which 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 as described above is executed.

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

[0031] (1) The invention has the advantage of high intelligence. Specifically, the invention uses artificial intelligence technology to realize intelligent track prediction and flight guidance functions, improves the intelligence level of the aircraft, has the advantages of low computational cost, high real-time performance, high precision, etc., can predict long-term benefits when controlling the flight status, has strong learning and prediction capabilities, can plan in advance for situations that may be encountered in the future, and thus greatly improve flight efficiency and reduce pilot workload.

[0032] (2) The present invention has strong applicability. Specifically, by learning from historical flight data, the performance parameters of a 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 implements track planning and flight guidance based on these characteristics, and can provide the pilot with an empirical best estimate. Because the data comes from actual flight data, the estimate not only takes into account the performance of the aircraft, but also implicitly takes into account the pilot's technical errors and the geographical characteristics of the track. Therefore, it has stronger applicability than the traditional dynamic model. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0034] Figure 1 The intelligent flight management system architecture of an embodiment of the present invention;

[0035] Figure 2 The present invention is a flowchart of the steps of the dual-mode track prediction decision method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0036] All features disclosed in all embodiments in this specification, or steps in all methods or processes implicitly disclosed, except for mutually exclusive features and / or steps, can be combined and / or expanded or replaced in any manner.

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

[0038] In the preferred system embodiment, an intelligent flight management system architecture is proposed, which integrates the traditional trajectory prediction and flight guidance algorithm based on dynamics method with the trajectory prediction and flight guidance algorithm based on artificial intelligence. It mainly uses dynamics method and artificial intelligence as auxiliary decision-making. Compared with the traditional flight management system, it has higher flexibility and adaptability, and at the same time has extremely high computing efficiency and long-term benefit prediction and response capabilities, providing pilots with accurate and timely flight information and improving the scientificity and rationality of flight decisions. Intelligent flight management system architecture, such as Figure 1 As shown, it specifically includes the following contents:

[0039] Flight plan management module: The flight plan management function receives the pilot input data according to the human-machine interaction management function, or extracts the required navigation station and waypoint information from the navigation database according to the data received by the data link application management function, and generates a complete flight plan. The flight plan information will be provided to other functions within the FMS for use;

[0040] Data link application module: data link application is interconnected with external communication management system to realize air-ground track negotiation, and can transmit track data, meteorological data, air-ground communication data, etc.

[0041] Track prediction module: Track prediction function includes dual-mode prediction combining dynamic model and intelligent algorithm model. It builds horizontal and vertical tracks based on flight plan, aircraft and engine performance, air traffic control requirements, meteorological conditions and historical flight data, and predicts speed, altitude, top of climb, top of descent, remaining fuel and other information.

[0042] Flight guidance module: Based on the flight guidance module based on the dynamic model, the intelligent flight guidance function uses reinforcement learning technology to design an intelligent flight guidance algorithm based on the flight track and current position information to calculate lateral deviation, vertical deviation, horizontal guidance instructions, vertical guidance instructions and other information; horizontal and vertical guidance instructions will be sent to the autopilot and autothrottle to enable the aircraft to automatically fly according to the desired track;

[0043] Integrated navigation management module: The integrated navigation management function receives signals from inertial reference system, satellite navigation system, atmospheric data computer and radio navigation equipment, mobile base stations, low-orbit satellites, and landmarks, performs integrated navigation calculations to calculate the best position information, and conducts real-time monitoring and alarm of navigation performance such as accuracy and integrity;

[0044] Navigation database management module: The database management function uses the onboard maintenance system to load and download the navigation database, performance database, and historical flight data, and provides relevant data information for modules such as flight plan management, track prediction, flight guidance, and integrated navigation management;

[0045] Performance calculation module: The performance calculation function mainly realizes performance data calculation and performance calculation, provides data required for dynamic calculation, such as aircraft aerodynamic and engine data, thrust, drag, fuel flow and other data, and calculates maximum altitude, optimized altitude, time / fuel to the top of climb / descent, economic speed, etc. based on performance data;

[0046] Human-machine interface management module: Human-machine interface management mainly provides the pilot with human-machine interaction functions such as inputting flight plans into the flight management system, setting flight parameters, monitoring aircraft navigation status, and viewing flight performance parameters.

[0047] In a preferred method embodiment, based on the above system, a dual-mode decision-making method is provided, which performs trajectory prediction based on dynamic components and monitors the integrity of the trajectory prediction performance in real time. When the performance of the dynamic components drops to an allowable value, the intervention of the artificial intelligence components is achieved through decision switching.

[0048] The decision switching process is as follows Figure 2 As shown, it is necessary to use historical flight data to train the artificial intelligence model before starting; after the process starts, first set the initial state of the aircraft, that is, the initial position of the aircraft and the flight plan; then use the dynamic components and artificial intelligence components to predict the trajectory; evaluate the prediction results of the dynamic components, if the integrity of the dynamic prediction results is insufficient, use the artificial intelligence component prediction results, otherwise continue to use the dynamic components; continue to fly for a calculation interval and then recalculate the trajectory until the end of the flight.

[0049] The units involved in the embodiments of the present invention may be implemented by software or hardware, and the units described may also be arranged in a processor. The names of these units do not, in some cases, limit the units themselves.

[0050] According to one aspect of an embodiment of the present invention, a computer program product or a computer program is provided, the computer program product or the computer program includes a computer instruction, and the computer instruction is stored in a computer-readable storage medium. A processor of a computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the method provided in the above various optional implementations.

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

Claims

1. A low-altitude intelligent flight management system, characterized in that: include: The flight plan management module is used to receive the pilot input data according to the human-machine interaction management function, or extract the required navigation station and waypoint information from the navigation database according to the data received by the data link application management function, and generate a complete flight plan. The flight plan information will be provided to other functions within the FMS for use; Data link application module, used to interconnect with external communication management systems to achieve air-ground track negotiation, capable of transmitting track data, meteorological data and air-ground communication data; The track prediction module includes a dual-mode prediction submodule that combines a dynamic model and an intelligent algorithm model, which is used to construct horizontal and vertical tracks and predict speed, altitude, top of climb, top of descent, and remaining fuel information. The flight guidance module uses a dual-mode guidance submodule that combines a dynamics model with an intelligent flight guidance algorithm based on reinforcement learning to calculate lateral deviation, vertical deviation, and horizontal guidance instructions and vertical guidance instruction information based on the flight track and current position information. The horizontal and vertical guidance instructions will be sent to the autopilot and autothrottle to enable the aircraft to automatically fly along the desired track. Integrated navigation management module, which is used to receive signals from inertial reference system, satellite navigation system, atmospheric data computer, radio navigation equipment, mobile base station, low-orbit satellite and landmark, perform integrated navigation calculation to calculate the best position information, and conduct real-time monitoring and alarm of navigation performance such as accuracy and integrity; The navigation database management module is used in the airborne maintenance system to load and download the navigation database, performance database, and historical flight data, and to provide relevant data information for the flight plan management, track prediction, flight guidance, and integrated navigation management modules; Performance calculation module, used to realize performance data calculation and performance calculation, provide data required for dynamic calculation, calculate maximum altitude, optimized altitude, time / fuel to the top of climb / descent, and economic speed based on performance data; The human-machine interface management module is used to provide the pilot with human-machine interaction functions such as inputting flight plans into the flight management system, setting flight parameters, monitoring the aircraft navigation status, and viewing flight performance parameters.

2. The low-altitude intelligent flight management system according to claim 1, characterized in that: In the track prediction module, the horizontal track and the vertical track are constructed specifically according to the flight plan, aircraft and engine performance, air traffic control requirements, meteorological conditions and historical flight data.

3. The low-altitude intelligent flight management system according to claim 1, characterized in that: In the dual-mode prediction submodule, trajectory prediction is performed based on dynamic components, and the performance of trajectory prediction is monitored in real time for integrity. When the performance of the dynamic components drops to an allowable value, the intervention of artificial intelligence components is achieved through decision switching.

4. The low-altitude intelligent flight management system according to claim 1, characterized in that: In the performance calculation module, the data required for the dynamics calculation specifically include aircraft aerodynamic and engine data, thrust, drag and fuel flow data.

5. The low-altitude intelligent flight management system according to claim 3, characterized in that: The intervention of the artificial intelligence component by decision switching specifically includes: Before getting started, train the AI ​​model using historical flight data; After starting, set the initial state of the aircraft; Then, the trajectory is predicted using the dynamic components and artificial intelligence components. The prediction results of the dynamic components are evaluated. If the integrity of the dynamic prediction results is insufficient, the artificial intelligence component prediction results are used, otherwise the dynamic components are continued to be used. The trajectory is recalculated after continuing to fly for a calculation interval until the end of the flight.

6. The low-altitude intelligent flight management system according to claim 5, characterized in that: The initial state of the aircraft is the initial position and flight plan of the aircraft.

7. A low-altitude intelligent flight management method, characterized in that: Based on the low-altitude intelligent flight management system described in claim 1, in the dual-mode prediction submodule combining the dynamic model and the intelligent algorithm model, the following steps are performed: S1, using historical flight data to train AI models; S2, first set the initial state of the aircraft; S3, uses dynamic components and artificial intelligence components to predict flight paths; S4, evaluate the prediction results of the dynamic components. If the integrity of the dynamic prediction results is insufficient, use the prediction results of the artificial intelligence components, otherwise continue to use the dynamic components; continue to fly for one calculation interval and recalculate the track until the end of the flight.

8. An electronic system, characterized in that: It comprises a computer device, in which 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 described in claim 7 is executed.

Images