A Proportional-Integral (PI) controller and a non-linear Fuzzy and Neuro controller is designed and its application to the regulation of 54V, 2.916kW Quasi-Resonant Buck Converter is comparatively investigated. PI controller involves Proportional gain (Kp) and Integral time (Ki) parameters whose manual tuning provides an appropriate action. Fuzzy logic is on the notion of graded membership and ...

Neuro-fuzzy modeling has been intensively studied since the early nineties. Recently a method has been disclosed, that uses a classical feedforward neural network with just one hidden layer. Nodes of the hidden layer use the logistic function as activation function meanwhile the output node has a linear activation function. This paper introduces a generalization of the logistic function and eva...

This paper presents a nonlinear adaptive observer based on multilayer perceptron (MLP) neural networks, which is indeed a nonlinear-in-parameters neural network (NLPNN), for a class of nonlinear systems including chaotic systems in which all MLP weights are tuned on-line. These systems can be decomposed into linear and nonlinear parts. It is assumed that the linear part is known while the nonli...

Abstract: This paper presents a neuro-adaptive output-feedback stabilization method for nonlinear non-minimum phase systems with partially known Lipschitz continuous functions in their arguments. The proposed controller is comprised of a linear, a neuro-adaptive, and an adaptive robustifying control term. The adaptation laws for the neural network weights are obtained using the Lyapunov’s direc...

In this work, a Neuro-Sliding mode controller (NSMC) for piezo-positioning mechanism (PEA) was designed. This controller takes into account parameter uncertainties and unknown external disturbances. The LuGre model is used to establish the mathematical model of the system including the mechanical motion dynamics, the hysteresis friction, the load disturbance and parameter uncertainties. Using t...

This paper describes the application of adaptive neuro-fuzzy inference system (ANFIS) methodology for the backcalculation of airport flexible pavement layer moduli. The proposed ANFIS-based backcalculation approach employs a hybrid learning procedure to construct a non-linear input-output mapping based on qualitative aspects of human knowledge and pavement engineering experience incorporated in...

We apply our on-line learning neural network approach to control of non-linear systems; first to joint level trajectory control of an industrial welding robot, and then to one front leg of a hexapod walking robot. The first application demonstrates the ability of neuro-control to model complex non-linear components of a plant, thereby yielding impressive improvements in accuracy compared to the...