47 results about "Pilot training" patented technology

The invention discloses a pilot EBT training target competency identification method and system based on eye movement / flight data fusion driving, and the method comprises the steps: S0, obtaining eye movement data of a pilot in an EBT training process, constructing a GDETC network to achieve the spatial-temporal trajectory clustering of the eye movement data, and extracting the staring spatial-temporal trajectory of the pilot; s1, extracting competency assessment scores and error time-space point data from EBT competency assessment worksheets and flight data; and S2, constructing a VAE-STRF network, fusing the data extracted in the step S0 and the step S1, extracting a pilot key competency evaluation score matrix, establishing a pilot key competency evaluation model, and outputting the target competency of EBT training. According to the method, the target competency of the pilot needing to continue to be improved subsequently is recognized through the eye movement data in the EBT training process of the pilot, an existing manual evaluation system can be replaced, and effective decision support is provided for improving the training pertinence of the pilot.

The invention belongs to the technical field of pilot training evaluation, and discloses a flight simulator multi-modal data-based feature fusion model construction method, which specifically comprises the following steps of 1, selecting a pilot training video, obtaining flight parameter data, and establishing a flight simulator multi-modal data set; 2, data preprocessing; step 3, providing a key point sequence by the ViTPose; step 4, embedding key point sequence features; 5, extracting flight parameter time sequence and pilot operation behavior frequency domain features; step 6, carrying out cross-modal feature fusion; and 7, performing comparative learning. According to the method, signals of different modes in the use process of the flight simulator are fully captured, and operation behavior characteristics in a pilot training video and data time sequence characteristics generated by the flight simulator are fused, so that more accurate and efficient pilot driving training behavior representation and recognition are realized; and meanwhile, the whole learning process is processed in a layered manner, and the information of different signals can be more deeply and effectively combined through the interaction effect of the mode in the main features of different stages of each layer of model, so that more advanced and abstract feature representation can be obtained in the subsequent hierarchical learning.

The invention discloses a flight training quality evaluation method based on DTW and K-means clustering, and belongs to the technical field of pilot training, and the method comprises the following steps: S1, data collection and processing; s2, data preprocessing and standard template generation; s3, DTW similarity measurement and mahalanobis distance weighting are carried out; s4, performing similarity measurement and clustering analysis; s5, generating a personalized training scheme; therefore, the invention provides a scientific, objective and efficient flight trainee quality evaluation method, the landing process of the pilot is subjected to comprehensive quantitative analysis in a data-driven manner, a more accurate and personalized flight training scheme is provided, the flight level of the flight trainee is finally improved, and the risk of flight accidents is reduced.

The invention relates to the technical field of aviation safety data analysis and pilot training optimization, provides an aviation safety data and training data integrated analysis method and system, electronic equipment and a storage medium, and solves the problems of poor pertinence of pilot training and poor foresight of safety guarantee. The method comprises the following steps: automatically extracting threats, errors and unexpected aircraft states in aviation unsafe events from multi-source heterogeneous data, and judging a management state; based on the aviation safety knowledge graph, positive and negative competency and behavior indexes corresponding to the managed and unmanaged states are identified through graph calculation; the statistical frequency is analyzed, and a priority list of the security data side is generated; carrying out weighted fusion to obtain a target training list by combining a training data statistical analysis result of the same period; and in combination with the threat priority, generating a training scene configuration scheme containing threat elements and capability items, and forming a course content, evaluation standard and resource optimization configuration scheme. According to the invention, the pertinence of pilot training is improved.

The embodiment of the invention discloses a training system and method combining a large model and an eVTOL simulation cabin. The system comprises an air traffic control voice recognition module which carries out fine tuning on a general voice model and obtains a pilot instruction based on the fine-tuned model and an intelligent error correction algorithm; the large model intelligent control module is used for finely adjusting the base large model and processing the virtual scene information and the pilot instruction based on the finely-adjusted model to obtain a control instruction; the control voice synthesis module is used for performing fine tuning on the general text-to-voice large model and obtaining voice data based on the fine-tuned model; and the training system management platform is used for realizing man-machine interaction between the training system and the pilot and the controller. According to the invention, a virtual controller system is constructed based on large model fine tuning, the problems of large workload of controllers, lack of controllers during pilot training and the like can be solved, and the efficiency, quality and precision of pilot training can be effectively improved.

The invention discloses a flight control ground closed-loop simulation test system design method, and belongs to the field of aviation aircraft tests. A traditional flight simulation test depends on dispersed racks, equipment systematicness is poor, and dynamic interaction and complex task scenes of multiple airborne equipment are difficult to truly simulate. A flight management computer, a ground station and a communication link closed-loop framework are constructed, real avionics are isolated through a disconnection box, and an industrial personal computer drives a simulation model to simulate dynamic responses of real equipment such as a steering engine, an engine and an undercarriage. The system supports real-time data injection, can simulate the whole-process states of flight, sliding and take-off and landing in the air, synchronously collects system parameters and performs closed-loop feedback, thereby assisting flight line simulation, control law simulation and pilot training simulation.

Provided is a flight simulation system for an unmanned aerial vehicle capable of performing pilot training of the unmanned aerial vehicle in an environment closer to a real environment. The flight simulation system for an unmanned aerial vehicle includes: an operation data acquisition unit configured to acquire operation data of a virtual unmanned aerial vehicle performed by a trainee; a simulator unit configured to calculate, based on geospatial data of a real space and the operation data, a current position of the virtual unmanned aerial vehicle in the real space; and a display unit configured to generate an image of the virtual unmanned aerial vehicle so that the virtual unmanned aerial vehicle is visually recognizable at the current position in the real space, and to output the generated image to the trainee.

The invention relates to the technical field of pilot training effect evaluation, in particular to a pilot training effect evaluation system and method based on multi-source data fusion. A pilot training effect evaluation system based on multi-source data fusion comprises a data acquisition module, a preprocessing module, a data fusion module, an evaluation model module and a feedback optimization module, the data acquisition module comprises a multi-modal sensor, the preprocessing module is in communication connection with the data acquisition module, and the data fusion module is connected with the preprocessing module; the evaluation model module is connected with the data fusion module and outputs a comprehensive evaluation score and a weak link diagnosis result; and the feedback optimization module is connected with the evaluation model module to generate a visual report and an optimization instruction. According to the method, high-precision processing and self-adaptive fusion of multi-source data are realized through multi-modal sensor synchronous acquisition, refined preprocessing, dynamic weight fusion and intelligent model evaluation, a closed loop is formed in combination with visual feedback, and training evaluation accuracy and optimization efficiency are improved.

The invention discloses a flight simulation training auxiliary system and method based on intelligent co-pilot, and the system comprises a data collection module which is used for collecting flight data and carrying out the operation monitoring of a college; the voice interaction interface is used for multi-mode state analysis voice interaction; the student model module is used for skill level evaluation and learning style identification; the emotion perception module is used for flight experience identification and risk prediction analysis; the personalized training module is used for training process monitoring, training result analysis and personalized training adjustment; and the decision engine module is used for deeply reinforcing a learning model and assisting a strategy generator. And intelligent and personalized auxiliary support is provided for pilot training. Through real-time data analysis and an adaptive learning algorithm, functions and behaviors of a real copilot are simulated, and targeted guidance is provided for flight trainees. And a complete training ecosystem is formed. And the flexibility and expandability of the system are ensured, and each functional component can be independently optimized and upgraded.

The present application discloses a simulation method, system, and computer program product for simulating pilots of different skill levels flying along any landing route, belonging to the field of flight simulation technology, including: setting aircraft maneuverability constraints and environmental constraints; constructing a landing route; configuring controller parameters; using Gaussian random numbers to initialize the random perturbation link in the controller and set the initial state of the aircraft; using the controller to obtain a route tracking control signal; based on the route tracking control signal, using a kinematic model to update the aircraft state; judging the flight progress and switching routes to achieve kinematic simulation of pilots of different skill levels flying along any given ideal landing route. The method of the present application can provide a quantifiable method for pilot training in the aviation field, and provide efficient, accurate, and flexible data support close to real scenarios for flight control algorithm verification, and has important practical application value.

A communication system configured to estimate Channel State Information based on a channel estimator transformer model, comprising a transmitting device and a receiving device. The transmitting controller is configured to generate a generic pilot pattern set that includes a plurality of potential pilot patterns, map the generic pilot pattern set into a positional encoding indices set and a positional embedding indices set, generate a positional encoding sequence, PE for a pilot pattern map the positional encoding sequence into the generic pilot pattern thereby generating a Positional Encoding-Embedded Pilot training signal, transmit the generic pilot pattern set to the receiving device, and transmit the PEEP training signals according to the generic pilot pattern set to the receiving device. Moreover, the receiving controller is configured to receive the generic pilot pattern set, receive the transmitted PEEP training signals, and train the channel estimator transformer model based.

The utility model discloses an aviation handle clamping device, and relates to the technical field of aviation handles. The handle comprises a handle fixing seat and a handle body, the handle body comprises a straight rod section movably arranged in the middle of the top of the handle body fixing seat and an arc-shaped section connected to the top of the straight rod section, and control buttons are arranged on the two sides and the outer side face of the arc-shaped section. The clamping mechanism is detachably arranged on the edge side of the top face of the handle fixing base, and the clamping mechanism is used for fixing the straight rod section of the handle body. The detachable locking mechanism is introduced, movement of the handle body is limited in a physical mode, the handle can be rapidly and reliably fixed when a pilot trainings, free movement of the handle can be recovered only by detaching the locking mechanism when fixation needs to be removed, normal flight operation is guaranteed not to be affected, and the operation is simple and convenient. The operation is very simple, the practicability is higher, and the method is worthy of general application and popularization.

A method for uplink power control in a cell-free massive MIMO system supporting URLLC is disclosed, comprising: 1: constructing a cell-free massive MIMO system supporting URLLC; 2: establishing a channel model; 3: all users sending pilot signals to all access points for pilot training; 4: performing channel estimation to obtain an estimated channel coefficient vector; 5: all users simultaneously transmitting uplink data to all access points, with each access point preprocessing the data signals of all users; 6: a central processing unit jointly decoding the preprocessed signals to obtain user signals corresponding to the users; 7: calculating the user's signal-to-noise ratio and the user's uplink achievable rate; 8: establishing problem P1; 9: transforming problem P1 into problem P2; 10: transforming problem P2 into problem P3; and 11: solving problem P3 to obtain a local optimal solution to the user weighted sum rate maximization problem. The method reduces the adverse effects of channel aging on the cell-free massive MIMO system supporting URLLC.

The invention discloses a predictive cooperative beam forming and resource allocation method based on multi-station information fusion, which is suitable for a cellular-free large-scale MIMO unmanned aerial vehicle communication system. According to the method, a low-overhead beam tracking frame structure is designed on a ground base station side, and position tracking of a mobile unmanned aerial vehicle user is realized by using an uplink pilot signal and based on an extended Kalman filtering distribution mode; and then, designing beam forming based on position prediction to realize downlink data transmission. Each base station returns user state estimation and covariance information in a low-overhead mode through a forward link, and the central processing unit fuses information of multiple base stations to improve position tracking precision. Furthermore, according to the method, the system effectiveness and the spectrum efficiency are taken as optimization targets, the uplink pilot frequency length, the downlink base station user association and the power distribution are jointly optimized, and a low-complexity iterative algorithm based on compressed sensing and fractional programming is used for solving. According to the invention, the pilot frequency training and backhaul overhead can be obviously reduced.

The present invention is applicable to the field of pilot training technology and provides a ground-based vision training device for pilots that takes environmental and physiological factors into account. The device uses a computer system to rapidly simulate human visual characteristics, including: establishing a light source and brightness detector; obtaining a two-dimensional distributed brightness matrix of the scene; obtaining ambient brightness information of the external scene as perceived by the human eye, which affects optical aberrations by affecting pupil diameter; establishing an optical model of the human eye and obtaining a modulation transfer function; simulating the observation effect of the external scene after passing through the model in the frequency domain, using a GPU for accelerated processing; using an eye tracker to determine the coordinates of the pilot's gaze point, simulating the blur and depth of field characteristics of the peripheral vision; and finally performing image fusion to obtain a simulated image of the external scene after passing through the human eye. The present invention can improve the effectiveness of flight training or the accuracy of new aircraft cockpit evaluations, and provide pilots with a more realistic and intuitive flight visual experience during ground training.

The invention discloses a training monitoring system for a pilot, and the system comprises a flight training collection subsystem which is used for carrying out the collection of flight training related information in the flight training process of the pilot; the daily training acquisition subsystem is used for acquiring daily training related information in the daily training process of the pilot; the data processing module is used for processing the flight training related information and the daily training related information to generate flight training prompt information and daily training prompt information; and the information sending module is used for sending the flight training prompt information and the daily training prompt information to a preset receiving terminal. According to the invention, more comprehensive pilot training can be carried out, and the abnormity of the pilot can be found and prompted in time in the training process.

This invention discloses a method and system for identifying pilot EBT training target competencies driven by the fusion of eye-tracking data and flight data. The method includes: S0: acquiring eye-tracking data from the pilot's EBT training process, constructing a GDETC network to achieve spatiotemporal trajectory clustering of the eye-tracking data, and extracting the pilot's gaze spatiotemporal trajectory; S1: extracting competency assessment scores and error spatiotemporal point data from the EBT competency assessment worksheet and flight data; S2: constructing a VAE-STRF network, fusing the data extracted in S0 and S1, extracting the pilot's key competency assessment score matrix, establishing a pilot key competency assessment model, and outputting the target competencies for EBT training. This invention identifies the target competencies that pilots need to further improve through eye-tracking data during EBT training, replacing existing manual evaluation systems and providing effective decision support for improving the targeting of pilot training.

The invention discloses a large-scale MIMO non-orthogonal multiple access bidirectional relay method based on an unmanned aerial vehicle, and belongs to the field of wireless communication, and the method comprises the steps: constructing a hovering rotor unmanned aerial vehicle working in a full duplex mode as an amplification forwarding relay, and constructing a model of M ground user pairs needing bidirectional communication; the ground user pair sends a superposed signal to the unmanned aerial vehicle by adopting a non-orthogonal multiple access protocol; the unmanned aerial vehicle performs pilot frequency training by using a minimum mean square error method to obtain imperfect channel state information, and adopts maximum ratio merging or maximum ratio transmission linear processing as a relay precoder; and the unmanned aerial vehicle broadcasts the processed signals back to all ground user pairs. The large-scale MIMO non-orthogonal multiple access bidirectional relay system based on the unmanned aerial vehicle is reliable in performance, high in communication capacity, strong in coverage capability and good in anti-noise performance.

The invention discloses an AP (Access Point) duplex mode optimization method for a multi-station cooperative communication and inductance integrated system. The method comprises the following steps: initializing two-dimensional position distribution of APs; the method comprises the following steps: dividing time slots in a system based on network-assisted full duplex, wherein each time slot comprises a pilot frequency training stage and a communication sensing stage; constructing an uplink pilot frequency receiving signal model through uplink pilot frequency training, and constructing a downlink pilot frequency receiving signal model through downlink pilot frequency training; in a communication sensing stage, uplink and downlink communication and rate closed expressions are deduced from a communication perspective, and a target position estimation rate expression is deduced from a sensing perspective; a multi-target optimization problem with maximization of communication sum rate and perception position estimation rate as targets is established, and duplex mode optimization is realized by optimizing an AP mode distribution strategy. According to the method, the problem of conflict between communication and sensing performance is solved, and the sensing precision is improved while the communication quality is guaranteed.

A fly-by-wire system that lets a single-engine aircraft mimic multi-engine behavior for real-flight pilot training, especially asymmetric thrust effects that create yaw / roll. A cockpit central thrust control with two independent thrust levers generates an overall power command plus a dissymmetry signal; a calculator applying a dedicated control law converts these into corrected setpoints for the rudder, left / right ailerons, and propeller parameters to reproduce multi-engine handling. Instructors may trigger a simulated engine failure and then reset back to normal single-engine operation. Optional wingtip electric thrusters powered by a battery may increase asymmetric effects while maintaining safety margin, and the system may display / record simulated multi-engine data for debriefing—reducing training cost and CO2 versus operating real twins

The present application relates to the technical field of education training data processing, and more particularly to an intelligent system for pilot psychological assessment and individualized training, the system comprising a psychological data processing module, a psychological assessment module, an individualized matching training scheme module and a team cooperation module, the psychological data processing module performing data fusion on feature extraction results, the psychological assessment module acquiring psychological states, the individualized matching training scheme module acquiring training schemes, and the team cooperation module matching roles for pilots, the present application performing real-time monitoring on training data, real-time matching and adjustment of training schemes for pilots, so as to flexibly match training schemes for individual psychological states of pilots, and reasonably allocate team roles, thereby improving the efficiency of pilot training and team task execution efficiency.

The invention relates to a landing safety event prediction method and system based on QAR data and multi-task learning, and belongs to the technical field of aviation flight safety. The method specifically comprises the following steps: S1, processing multi-parameter QAR data through a multi-scale sharing encoder; s2, performing task specific parameter weight distribution on the shared unified feature representation through a parameter selector; s3, performing time dependence modeling on the task related features through a time sequence decoder; and S4, utilizing a multi-task loss function to jointly optimize the prediction tasks of the plurality of security events. The technical scheme of the invention can be used for simultaneously predicting various safety events in a flight landing stage, such as a tail wiping event and a hard landing event, and a flight safety guarantee tool is provided for an airline company; through deep mining of potential association between flight data and different safety events, pilot training and operation processes are optimized, and flight safety standards are improved.

The present invention discloses a pilot control ability evaluation method and system based on multimodal data and online learning, including: determining an input parameter set, establishing a flight visual temporal fusion network, and extracting each feature of the parameter set. Feature fusion of multimodal data is completed through attention mechanism and global aggregation. A pilot control ability evaluation architecture is constructed, and an offline pilot control ability evaluation model is generated by designing a loss function based on comprehensive scoring error and sub-scoring consistency constraints. A sliding window mechanism is used to segment and preprocess the flight data and eye movement data streams generated in real time. A lightweight model based on pruning and parameter quantization technology is designed for real-time scoring requirements, and the feature expression capability in the offline pilot control ability evaluation model is migrated to a lightweight online evaluation model. The present invention can be used to improve pilot training programs, optimize the human-machine interface design of the cockpit, and improve the efficiency and safety of flight operations.

There is provided a system of monitoring an airborne training aircraft, the system comprising a processing circuitry configured to: a) receive, from one or more ground- based aircraft simulators, data indicative of, at least, respective three-dimensional (3D) positions and bearings of one or more virtual aircraft associated with the respective simulators; b) receive, from the training aircraft, data indicative of, at least, the training aircraft's 3D position and bearing; c) construct, utilizing, at least, the training aircraft's 3D position and bearing, and the respective three-dimensional (3D) positions and bearings of respective virtual aircraft, at least one of: i) imaging depicting a view, from an external point of reference, of the training aircraft and relative positions of virtual aircraft, and ii) imaging depicting at least one instrument of the training aircraft, wherein the depicted at least one instrument depicts positions of the one or more virtual aircraft relative to training aircraft.

The present invention relates to the field of flight training simulators, specifically to a pilot training simulator based on big data and machine learning. This simulator collects pilot head movement data in real time, combines it with machine algorithms to dynamically correct the field of view, and reduces simulator viewing angle delay and distortion issues. Furthermore, by combining high-frequency and low-frequency motions of motion simulation components and simulated seats, it achieves a simulation effect closer to that of a real flight attitude. Supported by long-term flight simulation data, it generates simulation change curves using big data, which intuitively display training progress trends. This allows for the training effects of different pilots to be determined, helping to formulate personalized training plans and reducing the cost of pilot simulation training.

The invention discloses a simulation method and system for simulating flight of pilots at different levels along any landing route and a computer program product, and belongs to the technical field of flight simulation. Constructing a landing route; controller parameters are configured; initializing a random disturbance link in a controller by using a Gaussian random number, and setting an initial state of the aircraft; acquiring a route tracking control signal by using a controller; updating an airplane state by using a kinematic model based on the airline tracking control signal; and judging the flight progress, switching the flight route, and realizing kinematics simulation of pilots at different levels flying along any given ideal landing flight route. According to the method, a quantifiable method can be provided for pilot training in the aviation field, efficient, accurate and flexible data support close to a real scene is provided for flight control algorithm verification, and the method has important practical application value.

The invention relates to a helicopter simulation system based on a six-degree-of-freedom turntable. According to the system, various attitudes and motion states of the helicopter in flight are simulated through the 6-degree-of-freedom turntable, and real-time simulation of the flight process of the helicopter is realized by combining a high-precision sensor and simulation software. Experiments show that the system can efficiently and accurately simulate the flight characteristics of the helicopter, and is suitable for pilot training and flight performance testing. The invention relates to a three-degree-of-freedom semi-physical simulation platform and an experiment method for a single-rotor unmanned aerial vehicle in the prior art. In the prior art, only algorithm simulation of a controller can be carried out, and the functions of educational training and flight training of a simulation system are not achieved. An existing simulation system is difficult to comprehensively simulate complex flight attitudes and motion states of helicopters. The invention provides a helicopter simulation system based on a six-degree-of-freedom turntable, which can effectively solve the problem.

The invention provides a pilot training demand determination method and a storage medium, relates to the technical field of aviation, and is used for accurately identifying the training demand of a driver. The method comprises the steps that multiple pieces of pilot driving data corresponding to a target pilot are acquired, the multiple pieces of pilot driving data comprise safe operation data, driving habit data or operation risk data, and the safe operation data are used for reflecting the preset safe operation state of an aircraft driven by the target pilot; the driving habit data is used for reflecting the driving habit of the target pilot facing the risk event, and the operation risk data is used for reflecting the safety risk degree of the driving behavior of the target pilot. And determining a driving style of the target pilot based on the plurality of pilot driving data. And based on the driving style of the target pilot, determining at least one training demand point to be improved by the target pilot, and obtaining a training demand corresponding to the target pilot.