A direct adaptive state-feedback controller is proposed for highly nonlinear systems. We consider uncertain or ill-defined nonaffine nonlinear systems and employ a neural network (NN) with flexible structure, i.e., an online variation of the number of neurons. The NN approximates and adaptively cancels an unknown plant nonlinearity. A control law and adaptive laws for the weights in the hidden layer and output layer of the NN are established so that the whole closed-loop system is stable in the sense of Lyapunov. Moreover, the tracking error is guaranteed to be uniformly asymptotically stable (UAS) rather than uniformly ultimately bounded (UUB) with the aid of an additional robustifying control term. The proposed control algorithm is relatively simple and requires no restrictive conditions on the design constants for the stability. The efficiency of the proposed scheme is shown through the simulation of a simple nonaffine nonlinear system.

A stable sensorless controller for DTC of induction motor fed by three-level inverter using the Radial Basis Function Network (RBFN) is presented in this paper. The torque ripple can be drastically reduced and low speed performance can be obtained in the DTC system for high performance induction motor drives. However, speed control performance is still influenced by the lumped uncertainties of the system such as parameter variations, external load disturbances, and unmodeled dynamics which make it difficult to obtain an exact mathematical model. In this paper, the lumped uncertainties are estimated on-line by the RBFN. Simulations as well as experimental results are shown to illustrate the performance of the proposed system.

No abstract

Abstract. This paper is concerned with the modeling and identification of time series data corrupted by noise using nonsingleton fuzzy logic system (NFLS). Main characteristic of the NFLS is a fuzzy system whose inputs are modeled as fuzzy number. So the NFLS is especially useful in cases where the available training data, or the input data to the fuzzy logic system, are corrupted by noise Simulation results of the Box-Jenkin's gas furnace data will be demonstrated to show the performance. We also compare the results of the NFLS approach with the results of using only a traditional fuzzy logic system. Thus it can be considered NFLS does a much better job of modeling noisy time series data than does a traditional fuzzy logic system.

No abstract