Abstract: A method for prediction of key performance parameters of an aero-engine in transition condition. Bench test data for an aero-engine in transition condition provided by a research institute is used for establishing a training dataset and a testing dataset first; parameter combination is used for predicting and analyzing engine exhaust temperature based on the idea of information fusion; and the method of rolling windows is used for rolling learning in order to predict the parameters such as low pressure rotor speed and exhaust temperature of an engine from the perspective of practical engineering application.

Abstract: An intelligent control method for a dynamic neural network-based variable cycle engine is provided. By adding a grey relation analysis method-based structure adjustment algorithm to the neural network training algorithm, the neural network structure is adjusted, a dynamic neural network controller is constructed, and thus the intelligent control of the variable cycle engine is realized. A dynamic neural network is trained through the grey relation analysis method-based network structure adjustment algorithm designed by the present invention, and an intelligent controller of the dynamic neural network-based variable cycle engine is constructed. Thus, the problem of coupling between nonlinear multiple variables caused by the increase of control variables of the variable cycle engine and the problem that the traditional control method relies too much on model accuracy are effectively solved.

Abstract: A stochastic configuration network based turbofan engine health parameter estimation method is disclosed. The stochastic configuration network based turbofan engine health parameter estimation method designed by the present invention combines the model based Kalman filter algorithm and the data-driven based stochastic configuration network, i.e. using the output of the stochastic configuration network as the compensation of the Kalman filter algorithm, so as to take into account the estimated result of the Kalman filter and the estimated result of the stochastic configuration network and improve the estimation accuracy of the original Kalman filter algorithm when the measurable parameters of the turbofan engine are less than the health parameters to be estimated. In addition, the present invention effectively reduces the accuracy loss caused by the poor structure of the neural network through the stochastic configuration network, and improves the generalization ability of the network.

Abstract: A Simulink modeling method for a mechanical hydraulic device of an aeroengine fuel regulator is proposed. The Simulink modeling method can implement high precision simulation of a mechanical hydraulic device of an engine fuel conditioning system, and greatly increase the simulation speed as compared with the existing modeling simulation in AMESim; solve the problem of a double-layered nested algebraic loop occurring when the mechanical hydraulic device is modeled in Simulink, and improve the simulation precision of the system. In addition, because of having certain universality, the resolving method for a double-layered nested algebraic loop can be generalized to resolve other types of algebraic loops. Meanwhile, the parameters of the simulation model provided by the present invention can be conveniently modified, and can provide a reference for modeling simulation of mechanical and hydraulic devices of engine fuel conditioning systems of other types.

Abstract: A Simulink modeling method for a mechanical hydraulic device of an aeroengine fuel regulator is proposed. The Simulink modeling method can implement high precision simulation of a mechanical hydraulic device of an engine fuel conditioning system, and greatly increase the simulation speed as compared with the existing modeling simulation in AMESim; solve the problem of a double-layered nested algebraic loop occurring when the mechanical hydraulic device is modeled in Simulink, and improve the simulation precision of the system. In addition, because of having certain universality, the resolving method for a double-layered nested algebraic loop can be generalized to resolve other types of algebraic loops. Meanwhile, the parameters of the simulation model provided by the present invention can be conveniently modified, and can provide a reference for modeling simulation of mechanical and hydraulic devices of engine fuel conditioning systems of other types.

Abstract: A stochastic configuration network based turbofan engine health parameter estimation method is disclosed. The stochastic configuration network based turbofan engine health parameter estimation method designed by the present invention combines the model based Kalman filter algorithm and the data-driven based stochastic configuration network, i.e. using the output of the stochastic configuration network as the compensation of the Kalman filter algorithm, so as to take into account the estimated result of the Kalman filter and the estimated result of the stochastic configuration network and improve the estimation accuracy of the original Kalman filter algorithm when the measurable parameters of the turbofan engine are less than the health parameters to be estimated. In addition, the present invention effectively reduces the accuracy loss caused by the poor structure of the neural network through the stochastic configuration network, and improves the generalization ability of the network.

Abstract: A vehicle capable of taking off and landing vertically and operating in water, land, air and submarine environments includes a fuselage, two main wings, ailerons, a vertical tail, a rudder, a horizontal tail, elevators, a propeller, rotor wings, rotor wing supports, etc. The vehicle has the advantages of adaptability to various environments, good concealment and strong survivability. Compared with a traditional unmanned rotorcraft, the vehicle has longer endurance time and larger load. Compared with a fixed wing UAV, the vertical take-off and landing function makes the work more convenient. Compared with unmanned diving equipment, the vehicle is applicable to richer environments, and can complete designated missions in air, land, water and submarine environments. Compared with a tilt rotor UAV in water, land, air and submarine environments, the vehicle is rapider in switching of various modes and is higher in stability.

Abstract: A vehicle running status field model-based information transmission frequency optimization method in the Internet of Vehicles belongs to the technical field of network communications. The method establishes a running status field model according to the real-time running status of a road vehicle to describe the degree of risk of the vehicle, the degree of risk can be used to dynamically adjust the transmission frequency of safety-critical information, and the transmission frequency of non-safety-critical information is adjusted through the real-time transmission frequency of safety-critical information to achieve the purpose of improving the utilization ratio of link. The method establishes the running status field model of a moving vehicle, uses the risk intensity of the vehicle in the running status field to describe the current running risk of the vehicle, and takes account of different application scenarios, thereby having generality.

Abstract: A design method for optimization of a transient control law of the aero-engine is disclosed, and performs the transient schedule optimization for the aero-engine by adopting an SQP algorithm, to realize the design of the transient control law along a constrained boundary condition. The fuel flow rate value is adjusted, other constraints remain unchanged, and the transient control law is designed under different limits. The transient time under each transient control law is calculated by constructing the transient time evaluation function. A lookuptable interpolation table is established by using the calculated transient time and corresponding fuel flow, to realize the fuel flow scheduling under different transient time. The fuel flow obtained by scheduling in the expected time is taken as an acceleration and deceleration control schedule of the closed-loop control of the aero-engine, and the output thereof is taken as the reference instruction of an acceleration process.

Abstract: The present invention belongs to the technical field of modeling and simulation of an aeroengine, and provides a method of modeling, simulation and fault injection for a combined high pressure gear pump for an aeroengine, which comprises: extracting the flow regions of a centrifugal pump and a gear pump in the aeroengine and merging into a combined flow region; dividing the combined flow region into different units according to a working principle; meshing each unit by a finite element analysis method, and setting boundary conditions and media parameters; simulating in Pumplinx to obtain the operation performance of the pumps, and adjusting the lateral clearance of the gear to debug the simulation model till a simulation error is within 5%; and then setting faults based on the debugged model to obtain the change of the operation performance of the pumps under the faults.

Abstract: A design method for optimization of a transient control law of the aero-engine is disclosed, and performs the transient schedule optimization for the aero-engine by adopting an SQP algorithm, to realize the design of the transient control law along a constrained boundary condition. The fuel flow rate value is adjusted, other constraints remain unchanged, and the transient control law is designed under different limits. The transient time under each transient control law is calculated by constructing the transient time evaluation function. A lookuptable interpolation table is established by using the calculated transient time and corresponding fuel flow, to realize the fuel flow scheduling under different transient time. The fuel flow obtained by scheduling in the expected time is taken as an acceleration and deceleration control schedule of the closed-loop control of the aero-engine, and the output thereof is taken as the reference instruction of an acceleration process.

Abstract: The present invention discloses a method for fault diagnosis of the sensors and actuators of an aero-engine based on LFT, and belongs to the field of fault diagnosis of aero-engines. The method comprises: establishing an aero-engine state space model using a combination of a small perturbation method and a linear fitting method; establishing an affine parameter-dependent linear-parameter-varying (LPV) model of the aero-engine based on the model; converting the LPV model of the aero-engine having perturbation signals and sensor and actuator fault signals into a linear fractional transformation (LFT) structure to obtain an synthesis framework of an LPV fault estimator; solving a set of linear matrix inequalities (LMIs) to obtain the solution conditions of the fault estimator; and designing the fault estimator in combination with the LFT structure to realize fault diagnosis of the sensors and actuators of an aero-engine.

Abstract: The present invention provides an interval error observer-based aircraft engine active fault tolerant control method, and belongs to the technical field of aircraft control. The method comprises: tracking the state and the output of a reference model of an aircraft engine through an error feedback controller; compensating a control system of the aircraft engine having a disturbance signal and actuator and sensor faults through a virtual sensor and a virtual actuator; observing an error between a system with fault of the aircraft engine and the reference model through an interval error observer, and feeding back the error to the error feedback controller; and finally, using a difference between the output of the reference model of the system with fault and the output of the virtual actuator as a control signal to realize active fault tolerant control of the aircraft engine.

Abstract: The present invention belongs to the technical field of fault diagnosis of aero-engines, and provides a method for fault diagnosis of an aero-engine rolling bearing based on random forest of power spectrum entropy. Aiming at the above-mentioned defects existing in the prior art, a method for fault diagnosis of an aero-engine rolling bearing based on random forest is provided, wherein test measured data for an aero-engine rolling bearing provided by a research institute are used for establishing a training dataset and a test dataset first; and based on an idea of fault feature extraction, time domain statistical analysis and frequency domain analysis are conducted on original collection data by adopting wavelet analysis; thereby realizing effective fault diagnosis from the perspective of engineering application.

Abstract: A method for prediction of key performance parameters of an aero-engine transition state acceleration process based on space reconstruction. Aero-engine transition state acceleration process test data provided by a research institute is used for establishing a training dataset and a testing dataset; dimension increase is conducted on the datasets based on the data space reconstruction of an auto-encoder; model parameters optimization is conducted by population optimization algorithms which is represented by particle swarm algorithm; and random forest regression algorithm performing well on high-dimensional data is used for carrying out regression on transition state performance parameters, which realizes effective real-time prediction from the perspective of engineering application.

Abstract: A steady state and transition state multi-variable control method of a turbofan engine based on an active disturbance rejection control theory (ADRC) belongs to the technical field of aero-engine control. Firstly, multiple groups of manipulated variables and controlled variables of a turbofan engine are preliminarily selected, and then the manipulated variables and controlled variables with high correlation are further determined by a correlation analysis method. Each group of control instructions is planned as a tracking trajectory by using a tracking differentiator, and is used as the input of a nonlinear proportional-differential controller together with the current state estimated by the extended state observer to calculate the manipulated variables.

Abstract: A method for prediction of key performance parameters of an aero-engine in transition condition. Bench test data for an aero-engine in transition condition provided by a research institute is used for establishing a training dataset and a testing dataset first; parameter combination is used for predicting and analyzing engine exhaust temperature based on the idea of information fusion; and the method of rolling windows is used for rolling learning in order to predict the parameters such as low pressure rotor speed and exhaust temperature of an engine from the perspective of practical engineering application.

Abstract: An air, sea, land and underwater tilt tri-rotor UAV capable of performing vertical take-off and landing. By the method for controlling a submerged floating device and a tilt tri-rotor device, the UAV is switched among the vertical take-off and landing mode, fixed wing mode, water surface sailing mode and underwater submerging mode, thereby making same have the advantages of four kinds of UAVs, and enhancing the applicability, maneuverability and efficiency of UAV. This has high efficiency in power system, has obviously improved endurance time and flight distance as compared with the traditional multi rotor UAV because of having the fixed wing mode, is applicable to more scenarios, and may operate on flat land, mountain land, water surface and underwater, thereby completing designated missions such as aerial, ground, water surface and underwater investigation, survey and concealment.

Abstract: An underwater launching apparatus for a small unmanned aerial vehicle capable of floating on water, having an airbag, inflating module, airbag arm, cylindrical body, upper baffle plate, spring, airbag arm connecting rod, lower baffle plate, upper buckle and lower buckle. This apparatus has compact and reliable structure. Relative to a traditional underwater catapult, the apparatus has smaller body and completes deployment and ejection of the launching apparatus by means of elasticity of the spring. The underwater launching apparatus for the small unmanned aerial vehicle has high stability and diversified applications. After the airbag arm of the catapult is deployed on the water and the inflating module inflates the airbag, developed area is larger and resistance to wind and waves is stronger. In a deployed state, a sensor on the unmanned aerial vehicle can be matched and steadily deployed on the water for investigation.

Abstract: An aero-engine full flight envelope model adaptive modification method based on a deep learning algorithm. A dynamic parallel compensator based on a recursive neural network is adopted to compensate the error of the original nonlinear model within the full flight envelope under the condition without aero-engine performance deterioration. A modifier based on a genetic algorithm is also adopted to conduct adaptive adjustment on correction coefficients of health parameters to be modified in the original nonlinear component-level model. The health parameters to be modified are determined by a multi-attribute decision algorithm based on integrated evaluation. The sum of the modified nonlinear component-level model output and the compensator output is consistent with the aero-engine operation test output data. This provides powerful support for the design of aero-engine control systems and fault diagnosis systems.