This paper presents the design of a neural network based feedback linearization (NNFBL) controller for a two degree-offreedom (DOF), quarter-car, servo-hydraulic vehicle suspension system. The main objective of the direct adaptive NNFBL controller is to improve the system's ride comfort and handling quality. A feedforward, multi-layer perceptron (MLP) neural network (NN) model that is well suited for control by discrete input-output linearization (NNIOL) is developed using input-output data sets obtained from mathematical model simulation. The NN model is trained using the Levenberg-Marquardt optimization algorithm. The proposed controller is compared with a constant-gain PID controller (based on the Ziegler-Nichols tuning method) during suspension travel setpoint tracking in the presence of deterministic road disturbance. Simulation results demonstrate the superior performance of the proposed direct adaptive NNFBL controller over the generic PID controller in rejecting the deterministic road disturbance. This superior performance is achieved at a much lower control cost within the stipulated constraints.
2
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
The paper presents the development of modelling and control strategies for a six-degree-of-freedom, unmanned combat aerial vehicle with the inclusion of the centre of gravity position travel during the straight-leg part of an in-flight refuelling manoeuvre. The centre of gravity position travel is found to have a parabolic variation with an increasing mass of aircraft. A nonlinear dynamic inversion-based neurocontroller is designed for the process under investigation. Three radial basis function neural networks are exploited in order to invert the dynamics of the system, one for each control channel. Modal and time-domain analysis results show that the dynamic properties of the aircraft are strongly influenced during aerial refuelling. The effectiveness of the proposed control law is demonstrated through the use of simulation results for an F-16 aircraft. The longitudinal neurocontroller provided interesting results, and performed better than a baseline nonlinear dynamic inversion controller without neural network. On the other hand, the lateral-directional nonlinear dynamic inversion-based neurocontroller did not perform well as the longitudinal controller. It was concluded that the nonlinear dynamic inversion-based neurocontroller could be applied to control an unmanned combat aerial vehicle during aerial refuelling.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.