19 results about "Flight model" patented technology

The invention relates to the technical field of unmanned aerial vehicle detection, in particular to a civil small unmanned aerial vehicle cat eye detection and countering system which comprises the steps that a cat eye detection module collects cat eye reflection characteristic signals, environment sensing data and unmanned aerial vehicle flight state associated information in an airspace; the threat level evaluation center identifies the type of the unmanned aerial vehicle and the intrusion risk level through an improved random forest model, and measures the real-time airspace position; the dynamic trajectory modeling module constructs a digital twin flight model of the civil small unmanned aerial vehicle, and simulates a flight trajectory and a potential intrusion path by using an intention pre-judgment algorithm; the grading countering unit generates a non-destructive countering strategy according to the intrusion risk grade, the flight path and the potential intrusion path; the man-machine interaction unit constructs a visual airspace monitoring scene, renders a detection result, an intrusion risk level and a countering effect in real time, and carries out man-machine interaction operation. Therefore, the problems of insufficient perception, poor decision collaboration and the like in the prior art are solved.

The application discloses a multi-unmanned aerial vehicle task unloading and resource scheduling method and device, relates to the technical field of communication, and comprises the following steps: taking maximizing load fairness, minimizing overall energy consumption and minimizing total time delay of a computing task as targets, adopting an unmanned aerial vehicle flight model, a task processing time delay model, an energy consumption model and an unmanned aerial vehicle load balancing model to construct a target optimization function, and combining a decision constraint condition to construct a multi-target joint optimization problem; converting the multi-target joint optimization problem into a Markov decision process and correspondingly constructing a multi-agent deep reinforcement learning model; acquiring task decision state data associated with a to-be-processed computing task, and inputting the multi-agent deep reinforcement learning model for decision analysis, and outputting task decision action data.

The invention relates to the technical field of flight models, in particular to a method and device for building a flight scene physical model, and the device comprises a frame, a lower supporting plate, a sand table plate, an elevator, a flight simulation suite, and an upper supporting plate. The flight simulation suite comprises a suspension device, a driver and an aircraft model; the suspension device and the driver are attracted through magnetic force and installed on the lower supporting plate and the upper supporting plate in a clamped mode, the aircraft model is upwards connected to a winding mechanism of the suspension device through a silk thread, the height of the aircraft model in the Z direction is adjusted by controlling the winding mechanism to wind and unwind the suspension silk thread, and the driver drives the suspension device to move in the plane. Therefore, the plane space positions of the aircraft models in the X direction and the Y direction are changed, the lifter is transferred between the upper supporting plate and the lower supporting plate, and the multiple sets of aircraft models can be stored or added into display activities.

The application discloses an aircraft flight mode recognition method and system based on an air monitoring system, realizes calculation of an aircraft flight route by point flight correlation of fused monitoring data, and realizes estimation of a target state by state estimation of an aircraft track generated by point flight correlation. The heading change rate is obtained by heading calculation of the target state, and the target aircraft flight state is obtained by comprehensively considering the target state and the heading change rate, so that the existing model lacks recognition and processing of aircraft heading and turn rate related modes; meanwhile, the flight mode is recognized by the point flight correlation and state estimation method, so that the method does not need to pre-train sample data or pre-set a flight model, can respond to sudden change of the flight mode of the aircraft in real time, thereby improving real-time performance, and solving the deficiencies of deep learning and neural network algorithms in time complexity and real-time performance.

The application discloses a multi-unmanned aerial vehicle hybrid intelligent path planning method for real city airspace, relates to the technical field of path planning, and is characterized in that the method comprises the following steps: S1, three-dimensional environment modeling, constructing a city low-altitude unmanned aerial vehicle scene; S2, unmanned aerial vehicle flight model modeling, the multi-unmanned aerial vehicle path planning problem involves multi-objective and multi-constraint optimization, a cost function model of comprehensive evaluation is established in combination with the three-dimensional environment model, and a constraint model of unmanned aerial vehicle operation planning is constructed. The technical problem of the application is to provide a multi-unmanned aerial vehicle hybrid intelligent path planning method for real city airspace, which is suitable for the multi-unmanned aerial vehicle hybrid intelligent path planning method under the conditions of real city three-dimensional space and multi-constraints. Through comprehensive optimization of factors such as ground risk, wind field disturbance, flight efficiency and multi-unmanned aerial vehicle cooperative avoidance, the multi-unmanned aerial vehicle can realize safe, stable and efficient task execution in a complex environment.

The application discloses a flight model allocation method, device and equipment, the method comprises the following steps: collecting flight information, model information, airport information and economic data of a target airline; extracting a first flight set within a first preset time range from the flight information; setting a same model change penalty threshold for each flight in the first flight set; establishing a target function of the model change penalty threshold; constructing a model allocation model with multiple optimization targets; iteratively searching the target function, and obtaining a candidate model allocation scheme and a candidate model change number corresponding to the output of the model allocation model according to each candidate model change penalty threshold; and outputting a target model change penalty threshold and a target flight model allocation scheme within the first preset time range after iterative solution. The embodiment of the application can automatically adjust the model change penalty threshold, optimize the flight model allocation scheme, and improve the efficiency of flight model allocation.

The invention discloses a multi-unmanned aerial vehicle hybrid intelligent path planning method for a real urban airspace, and relates to the technical field of path planning, and the method is characterized in that the method comprises the following steps: S1, carrying out the three-dimensional environment modeling, and constructing an urban low-altitude unmanned aerial vehicle scene; s2, modeling an unmanned aerial vehicle flight model, establishing a cost function model for comprehensive evaluation by combining a three-dimensional environment model according to multi-target and multi-constraint optimization of a multi-unmanned aerial vehicle path planning problem, and constructing an unmanned aerial vehicle operation planning constraint model; the technical problem of the invention is to provide a multi-unmanned-aerial-vehicle hybrid intelligent path planning method for a real city airspace, and the multi-unmanned-aerial-vehicle hybrid intelligent path planning method is suitable for a real city three-dimensional space and under a multi-constraint condition. Through comprehensive optimization of factors such as ground risk, wind field disturbance, flight efficiency and multi-unmanned aerial vehicle cooperative avoidance, the multi-unmanned aerial vehicle can realize safe, stable and efficient task execution in a complex environment.

The invention discloses an unmanned aerial vehicle cluster collaborative target hunting elastic control method for coping with network attacks, and relates to the field of unmanned aerial vehicles, and the method comprises the steps: constructing a flight model of an unmanned aerial vehicle and a control law of the unmanned aerial vehicle; constructing a potential field function based on the body radius of the unmanned aerial vehicle at the current moment and the communication distance of the unmanned aerial vehicle at the current moment; adopting a distributed Kalman consensus filtering algorithm to obtain motion information of the target at the next moment; based on the motion information of each unmanned aerial vehicle in the unmanned aerial vehicle cluster at the current moment, the upper and lower bounds of the network attack at the current moment and the motion information of the target at the next moment, obtaining the motion information of each unmanned aerial vehicle at the next moment by taking a potential field function as a constraint and adopting a flight model of the unmanned aerial vehicle and a control law of the unmanned aerial vehicle; and controlling the unmanned aerial vehicles to surround the target according to the motion information of each unmanned aerial vehicle at the next moment until the surrounding of the target is completed. According to the invention, the accuracy, flexibility and anti-interference performance of unmanned aerial vehicle cluster cooperative target encircling elastic control can be improved.

The application provides a kind of unmanned aerial vehicle three-dimensional path planning method based on improved snake optimization algorithm, and relates to the field of unmanned aerial vehicle three-dimensional path planning.The flight model containing city terrain and cost function is constructed, the temperature index is dynamically adjusted by using non-monotonic factor, and the solution of the shortest path under the constraint condition in the three-dimensional path planning of unmanned aerial vehicle is realized;The golden sine strategy is introduced to replace the mating mode in the standard snake optimization algorithm, the search step is dynamically adjusted, and the population diversity is ensured by means of random variable, which reduces the path redundancy of the three-dimensional path of unmanned aerial vehicle, introduces non-monotonic factor, dynamically adjusts food index to make the algorithm flexibly switch between exploration stage and development stage, and strengthens the ability of the algorithm to pass through dense obstacle group.The short board existing in the path planning of the existing snake optimization algorithm is solved, and a reliable path planning scheme is provided for the autonomous operation of unmanned aerial vehicle.

The invention provides an unmanned aerial vehicle edge network control method, an unmanned aerial vehicle and a computer program product, and relates to the technical field of wireless communication, and the method comprises the steps: loading an unmanned aerial vehicle edge network scene model; loading a user terminal mobile model and a task generation model; loading a flight model and a coverage model of the unmanned aerial vehicle; loading a communication model of the unmanned aerial vehicle and the user equipment; loading a predefined energy consumption model and a target function; a seven-tuple of the POMDP model is loaded; obtaining observation information of an observation space under the current time slot; determining target decision action information based on observation information of an observation space under the current time slot, a seven-tuple, a Dyna environment model and an RSAC algorithm by taking minimization of calculation energy consumption of user equipment and maximization of an uplink rate of the user equipment as targets; and controlling the unmanned aerial vehicle edge network under the current time slot based on the target decision action information. The method is used for providing an unmanned aerial vehicle edge network control scheme.

The invention provides an unmanned aerial vehicle three-dimensional flight path planning method based on an improved snake optimization algorithm, and relates to the field of unmanned aerial vehicle three-dimensional flight path planning. According to the method, a flight model containing urban terrain and a cost function is constructed, a temperature index is dynamically adjusted by using a non-monotonic factor, and the solution of a shortest path under a constraint condition in three-dimensional flight path planning of the unmanned aerial vehicle is realized; a golden sine strategy is introduced to replace a mating mode in a standard snake optimization algorithm, the search step length is dynamically adjusted, population diversity is ensured by means of random variables, the path redundancy of the three-dimensional track of the unmanned aerial vehicle is reduced, a non-monotonic factor is introduced, and the algorithm is flexibly switched between an exploration stage and a development stage by dynamically adjusting food indexes, so that the development efficiency of the unmanned aerial vehicle is improved. And the ability of the algorithm to pass through dense obstacle groups is enhanced. According to the method, the defects of an existing snake optimization algorithm in flight path planning are overcome, and a reliable flight path planning scheme is provided for autonomous operation of the unmanned aerial vehicle.

The invention discloses an unmanned aerial vehicle detection path planning method for low-altitude security and protection, and relates to an unmanned aerial vehicle. The method comprises the steps that geographic space data and flight mission parameters of a target area are acquired; constructing a three-dimensional grid map model according to the geographic space data; based on the three-dimensional grid map model, establishing a multi-constraint flight model comprising a height safety constraint, an airspace limitation constraint and a sensor coverage constraint; carrying out two-stage decomposition on the flight space by adopting a hierarchical set division method to obtain a hierarchical space decomposition graph; constructing an optimization problem of unmanned aerial vehicle detection path planning based on the spatial decomposition graph; solving the optimization problem by adopting a hybrid heuristic algorithm to obtain an unmanned aerial vehicle detection path covering the target area; according to the method, a large-scale complex three-dimensional urban space path planning problem is converted into a hierarchical small-scale sub-problem through hierarchical spatial decomposition, efficient solving is performed in combination with a hybrid heuristic algorithm, and the solving efficiency is improved.

The invention provides a flight and hotel joint recommendation method and system, a medium and equipment, and belongs to the technical field of information reckoning, and the method comprises the steps: collecting the original data of passengers, candidate flights and hotels, and carrying out the feature vectorization processing, and obtaining corresponding feature vectors; an initial recommendation model is constructed, and a flight and hotel recommendation model is obtained through candidate data pre-training; calculating a first matching degree between the passenger and the candidate flight through the flight model, and generating a passenger intention weighted flight vector; fusing the vector with a passenger feature vector to obtain a context-aware passenger vector, and calculating a second matching degree by using a hotel model; and based on the two types of matching degrees, forming a joint recommendation model by means of a joint loss function training model, and finally outputting a flight-hotel recommendation combination. According to the invention, an end-to-end unified model is adopted, deep collaboration of flight and hotel recommendation is realized, flight recommendation loss in training can be reversely propagated to the hotel recommendation module, deep association between model learning tasks is realized, and recommendation accuracy is improved.

The invention discloses a high-integration-level flight control system, relates to the field of wind tunnel dynamic flight tests, and solves the problems that an existing flight control system is limited in interface adaptation type, single in control mode and insufficient in attitude and power cooperative control precision under closed-loop control. Comprising a data receiving interface, a control signal output interface and a control processing module. The data receiving interface is adapted to various communication types such as 485, 232 and the like and is used for acquiring sensing data of multiple components such as inertial navigation, a GPS (Global Positioning System), a remote controller and the like; and the control signal output interface outputs corresponding signals to the control surface control unit, the electronic speed control and electric culvert unit and the like. The control processing module comprises a system self-checking module, a data analysis module and an instruction resolving module, sensing data are analyzed after self-checking is passed, the instruction resolving module can select an open loop mode or a closed loop mode to resolve an instruction and transmit the instruction, and multi-source data collection and multi-execution-unit cooperative control are achieved. The method can be used for flight control of virtual flight, free flight and outfield flight of a dynamic flight model.

The invention discloses a near-earth threat avoidance method for aircraft flight safety. According to the near-earth threat avoidance method, a real-time reference flight strategy or execution strategy meeting the low-altitude flight requirement of an aircraft is planned mainly by building a near-earth threat avoidance model, a motion model, a near-earth flight model and a dynamic evaluation model; therefore, the problem that when a low-performance aircraft executes automatic pull-up, controllable ground collision is likely to occur due to large and long-lasting topographic relief is effectively solved, and meanwhile the safety and flexibility of the aircraft in executing a near-ground flight task are effectively improved.

The invention discloses a flight parameter anomaly detection method based on an LNN and a correlation coefficient, and the method comprises the steps: collecting flight parameter data for preprocessing, and obtaining a fault-free sample set; calculating correlation coefficients between the data of the to-be-predicted features in the fault-free sample set and the data of the other features, and screening out the features of which the absolute values of the correlation coefficients are greater than a threshold value to form a feature data set; performing data screening by using a sliding window method to form a training set; inputting the training set into an LNN neural network for training, and inputting the fault-free sample set as a verification set into the trained LNN neural network for parameter updating to obtain a flight parameter data prediction model; determining to-be-predicted features, inputting the flight parameter data into the flight model for prediction to obtain prediction data, and determining whether the flight parameter data is abnormal or not according to the prediction data; advanced early warning of faults can be realized, and the prediction precision is remarkably improved.

This application provides a UAV edge network control method, a UAV, and a computer program product, relating to the field of wireless communication technology. The method includes: loading a UAV edge network scenario model; loading a user terminal mobility model and a task generation model; loading a UAV flight model and a coverage model; loading a communication model between the UAV and the user equipment; loading a predefined energy consumption model and objective function; loading the seven-tuple of the POMDP model; acquiring observation information of the observation space in the current time slot; determining target decision action information based on the observation information of the observation space in the current time slot, the seven-tuple, the Dyna environment model, and the RSAC algorithm, with the goal of minimizing the computational energy consumption of the user equipment and maximizing the uplink rate of the user equipment; and controlling the UAV edge network in the current time slot based on the target decision action information. This method is used to provide a UAV edge network control scheme.

The utility model relates to the technical field of undercarriages of flight models, and discloses a retractable double-damping undercarriage for a small-sized flight model airplane, which comprises a retractable frame, a support frame elastically mounted at one end close to the ground, and bearing blocks symmetrically and elastically mounted on two sides of the support frame, rollers and mounting cylinders for moving the model airplane along the ground are rotatably mounted between the two bearing blocks through rotating shafts, the mounting cylinders are symmetrically mounted on the two sides of the supporting frame, the two mounting cylinders are located over the two bearing blocks, delay pipes are rotatably mounted in inner cavities of the two mounting cylinders, sliding rods are slidably mounted in inner cavities of the delay pipes, and the sliding rods are slidably mounted in the inner cavities of the delay pipes. The top of the delay pipe is fixedly provided with a spring connected with the inner wall of the mounting cylinder, and the end, away from the spring, of the sliding rod is fixedly connected with the outer wall of the bearing block. According to the flying model airplane, the parts are matched with one another, so that vibration generated when the idler wheels collide with the ground can be absorbed, the vibration strength of the flying model airplane and an undercarriage is reduced, and the stability of the flying model airplane is improved.

The utility model discloses an adjusting device of a flight wing structure, which relates to the technical field of flight models and comprises a first wing panel, a second wing panel and a butt joint seat, the first wing panel and the second wing panel are respectively arranged on two sides of the butt joint seat, one side of the first wing panel is provided with an adjusting assembly, and the other side of the first wing panel is provided with a second wing panel. The inclination angle of the first wing panel is adjusted through an adjusting assembly, a detection assembly used for monitoring the adjusting angle is arranged on one side of the first wing panel and one side of the second wing panel, and the adjusting assembly comprises a rotating seat fixedly connected to the outer wall of the circumference of the butt joint seat. The inner walls of the two sides of the rotating base are rotationally connected with rotating shafts, and the ends, away from the rotating base, of the rotating shafts are fixedly connected to the outer wall of one side of the first wing piece. According to the flight model or toy, the flight model or toy can achieve more diversified flight actions through the adjusting assembly, and then the flexibility and operability of the flight model or toy in the flight process are improved.