A hybrid model of a subminiature helicopter in horizontal turn is presented. This model is based on a mechanism model and its compensated neural network （NN）. First, the nonlinear dynamics of a sub-miniature helicop...A hybrid model of a subminiature helicopter in horizontal turn is presented. This model is based on a mechanism model and its compensated neural network （NN）. First, the nonlinear dynamics of a sub-miniature helicopter is established. Through the linearization of the nonlinear dynamics on a trim point, the linear time-invariant mechanism model in horizontal turn is obtained. Then a diagonal recursive neural network is used to compensate the model error between the mechanism model and the nonlinear model, thus the hybrid model of a subminiature helicopter in horizontal turn is achieved. Simulation results show that the hybrid model has higher accuracy than the mechanism model and the obtained compensated-NN has good generalization capability.展开更多
The parametric model of stratospheric airships is established in the body axes coordinate system. In this paper we study the turning mechanism of stratospheric airships including the generated forces and the key param...The parametric model of stratospheric airships is established in the body axes coordinate system. In this paper we study the turning mechanism of stratospheric airships including the generated forces and the key parameters for steady turning. We compare and analyze the different driven-characteristics between aerodynamic control surfaces and vectored thrust in turning. We design a composite control combining aerodynamic control surfaces and vectored thrust according to different dynamic pressure conditions, to achieve coordinated turning under high or low airspeed situations.展开更多
文摘A hybrid model of a subminiature helicopter in horizontal turn is presented. This model is based on a mechanism model and its compensated neural network （NN）. First, the nonlinear dynamics of a sub-miniature helicopter is established. Through the linearization of the nonlinear dynamics on a trim point, the linear time-invariant mechanism model in horizontal turn is obtained. Then a diagonal recursive neural network is used to compensate the model error between the mechanism model and the nonlinear model, thus the hybrid model of a subminiature helicopter in horizontal turn is achieved. Simulation results show that the hybrid model has higher accuracy than the mechanism model and the obtained compensated-NN has good generalization capability.
基金Project (No.61175074) supported by the National Natural Science Foundation of China
文摘The parametric model of stratospheric airships is established in the body axes coordinate system. In this paper we study the turning mechanism of stratospheric airships including the generated forces and the key parameters for steady turning. We compare and analyze the different driven-characteristics between aerodynamic control surfaces and vectored thrust in turning. We design a composite control combining aerodynamic control surfaces and vectored thrust according to different dynamic pressure conditions, to achieve coordinated turning under high or low airspeed situations.
