In this paper, a self-tuning adaptive neural controller strategy for unknown nonlinear system is presented. The system considered is described by an unknown NARMA-L2 model and a feedforward neural network is used to learn the model with two stages. The first stage is learned off-line with two configuration serial-parallel model & parallel model to ensure that model output is equal to actual output of the system & to find the jacobain of the system. Which appears to be of critical importance parameter as it is used for the feedback controller and the second stage is learned on-line to modify the weights of the model in order to control the variable parameters that will occur to the system. A back propagation neural network is appl

Pure SnSe thin film and doped with S at different percentage (0,3,5,7)% were deposited from alloy by thermal evaporation technique on glass substrate at room temperature with 400±20nm thickness .The influences of S dopant ratio on characterization of SnSe thin film Nano crystalline was investigated by using Atomic force microscopy(AFM), X-ray diffraction (XRD), energy dispersive spectroscopy (EDS), Hall Effect measurement, UV-Vis absorption spectroscopy to study morphological, structural, electrical and optical properties respectively .The XRD showed that all the films have polycrystalline in nature with orthorhombic structure, with preferred orientation along (111)plane .These films was manufactured of very fine crystalline size in the ra

The characterization of ZnO and ZnO:In thin films were confirmed by spray pyrolysis technique. The films were deposited onto glass substrate at a temperature of 450°C. Optical absorption measurements were also studied by UV-VIS technique in the wavelength range 300-900 nm which was used to calculate the optical constants. The changes in dispersion and Urbach parameters were investigated as a function of In content. The optical energy gap was decreased and the wide band tails were increased in width from 616 to 844 eV as the In content increased from 0wt.% to 3wt.%. The single–oscillator parameters were determined also the change in dispersion was investigated before and after doping.

Diamond-like carbon, amorphous hydrogenated films forms of carbon, were pretreated from cyclohexane (C6H12) liquid using plasma jet which operates with alternating voltage 7.5kv and frequency 28kHz. The plasma Separates molecules of cyclohexane and Transform it into carbon nanoparticles. The effect of argon flow rate (0.5, 1 and 1.5 L/min) on the optical and chemical bonding properties of the films were investigated. These films were characterized by UV-Visible spectrophotometer, X-ray diffractometer (XRD) Raman spectroscopy and scanning electron microscopy (SEM). The main absorption appears around 296, 299 and 309nm at the three flow rate of argon gas. The value of the optical energy gap is 3.37, 3.55 and 3.68 eV at a different flow rate o

ABSTRACT: Thin film of CdS has been deposited onto clean glass substrate by using Spray pyrolysis technique. Results of Morphological (AFM) studied; electrical properties and optical conductivity studied are analysis. AFM results show a crystalline nature of the films. From the conductivity measurement at different temperatures, the activation energy of the films was calculated and found to be between 0.188 - 0.124 eV for low temperature regions, and between 1.67-1.19eV for high temperature regions. Hall measurements of electrical properties at room temperature show that the resistivity and mobility of CdS polycrystalline films deposited at 400 C0, were 3.878x103 . cm and 1.302x104cm2/ (V.s), respectively. The electrical conductivity of th

This paper proposes a new structure of the hybrid neural controller based on the identification model for nonlinear systems. The goal of this work is to employ the structure of the Modified Elman Neural Network (MENN) model into the NARMA-L2 structure instead of Multi-Layer Perceptron (MLP) model in order to construct a new hybrid neural structure that can be used as an identifier model and a nonlinear controller for the SISO linear or nonlinear systems. Weight parameters of the hybrid neural structure with its serial-parallel configuration are adapted by using the Back propagation learning algorithm. The ability of the proposed hybrid neural structure for nonlinear system has achieved a fast learning with minimum number