Neural Network Based Model Reference Adaptive Control for Ship Steering System
نویسندگان
چکیده
A neural network-based model reference adaptive control approach (MRAC) for ship steering systems is proposed in this paper. For the nonlinearities of ship steering system, performances of traditional adaptive control algorithms are not satisfactory in fact. The presented MRAC system utilizes RBF neural network to approximate the unknown nonlinearities in order to get a high adaptive control performance. Mechanism and stability of the control system are presented in detail. Also, a stable controller parameter adjustment law for RBF neural network, which is determined by using Lyapunov stability theory, is constructed. Simulation also shows the effectiveness and high performance of the proposed algorithm. Keyword: neural network, model reference adaptive control, ship steering.
منابع مشابه
Real-Time Output Feedback Neurolinearization
An adaptive input-output linearization method for general nonlinear systems is developed without using states of the system. Another key feature of this structure is the fact that, it does not need model of the system. In this scheme, neurolinearizer has few weights, so it is practical in adaptive situations. Online training of neuroline...
متن کاملNeural Controller Design for Suspension Systems
The main problem of vehicle vibration comes from road roughness. An active suspension systempossesses the ability to reduce acceleration of sprung mass continuously as well as to minimizesuspension deflection, which results in improvement of tire grip with the road surface. Thus, braketraction control and vehicle maneuverability can be improved consider ably .This study developeda new active su...
متن کاملAdaptive Predictive Controllers Using a Growing and Pruning RBF Neural Network
An adaptive version of growing and pruning RBF neural network has been used to predict the system output and implement Linear Model-Based Predictive Controller (LMPC) and Non-linear Model-based Predictive Controller (NMPC) strategies. A radial-basis neural network with growing and pruning capabilities is introduced to carry out on-line model identification.An Unscented Kal...
متن کاملSpeed Observer Design for Linear Induction Motor Drives
In this paper, a neural network model reference adaptive system speed observer is designed, which can be used in speed control of linear induction motors (LIMs). Dynamical equations of LIM have been considered accurate. In other words, the end effect and the electrical losses of the motor have been included in the motor equivalent circuit. Then equations of the reference model and adaptive mode...
متن کاملReconfigurable Control System for Ship Course-changing/keeping
This paper presents reconfigurable control system for ship coursechanging/keeping. Adaptive neuro-fuzzy inference system (ANFIS) is used to identify a steering gear subsystem (actuator) in order to build an accurate reference model for the fault detection in this non-linear component. The proposed control system uses a compensator for reducing the loss of the control performance produced by fau...
متن کامل