In this article, we design an optimal neural network based on new LM training algorithm. The traditional algorithm of LM required high memory, storage and computational overhead because of it required the updated of Hessian approximations in each iteration. The suggested design implemented to converts the original problem into a minimization problem using feed forward type to solve non-linear 3D - PDEs. Also, optimal design is obtained by computing the parameters of learning with highly precise. Examples are provided to portray the efficiency and applicability of this technique. Comparisons with other designs are also conducted to demonstrate the accuracy of the proposed design.

This deals with estimation of Reliability function and one shape parameter (?) of two- parameters Burr – XII , when ?(shape parameter is known) (?=0.5,1,1.5) and also the initial values of (?=1), while different sample shze n= 10, 20, 30, 50) bare used. The results depend on empirical study through simulation experiments are applied to compare the four methods of estimation, as well as computing the reliability function . The results of Mean square error indicates that Jacknif estimator is better than other three estimators , for all sample size and parameter values

This paper presents a modified training method for Recurrent Neural Networks. This method depends on the Non linear Auto Regressive (NARX) model with Modified Wavelet Function as activation function (MSLOG) in the hidden layer. The modified model is known as Modified Recurrent Neural (MRN). It is used for identification Forward dynamics of four Degrees of Freedom (4-DOF) Selective Compliance Assembly Robot Arm (SCARA) manipulator robot. This model is also used in the design of Direct Inverse Control (DIC). This method is compared with Recurrent Neural Networks that used Sigmoid activation function (RS) in the hidden layer and Recurrent Neural Networks with Wavelet activation function (RW). Simulation results shows that the MRN model is bett

In this research Artificial Neural Network (ANN) technique was applied to study the filtration process in water treatment. Eight models have been developed and tested using data from a pilot filtration plant, working under different process design criteria; influent turbidity, bed depth, grain size, filtration rate and running time (length of the filtration run), recording effluent turbidity and head losses. The ANN models were constructed for the prediction of different performance criteria in the filtration process: effluent turbidity, head losses and running time. The results indicate that it is quite possible to use artificial neural networks in predicting effluent turbidity, head losses and running time in the filtration process, wi

In this paper a new structure for the AVR of the power system exciter is proposed and designed using digital-based LQR. With two weighting matrices R and Q,  this method produces an optimal regulator that is used to generate the feedback control law. These matrices are called state and control weighting matrices and are used to balance between the relative importance of the input and the states in the cost function that is being optimized. A sample power system composed of single machine connected to an infinite- bus bar (SMIB) with both a conventional and a proposed Digital AVR (DAVR) is simulated. Evaluation results show that the DAVR damps well the oscillations of the terminal voltage and presents a faster respo

The objective of this study was tointroduce a recursive least squares (RLS) parameter estimatorenhanced by using a neural network (NN) to facilitate the computing of a bit error rate (BER) (error reduction) during channels estimation of a multiple input-multiple output orthogonal frequency division multiplexing (MIMO-OFDM) system over a Rayleigh multipath fading channel.Recursive least square is an efficient approach to neural network training:first, the neural network estimator learns to adapt to the channel variations then it estimates the channel frequency response. Simulation results show that the proposed method has better performance compared to the conventional methods least square (LS) and the original RLS and it is more robust a

In this research estimated the parameters of Gumbel distribution Type 1 for Maximum values through the use of two estimation methods:- Moments (MoM) and Modification Moments(MM) Method. the Simulation used for comparison between each of the estimation methods to reach the best method to estimate the parameters where the simulation was to generate random data follow Gumbel distributiondepending on three models of the real values of the parameters for different sample sizes with samples of replicate (R=500).The results of the assessment were put in tables prepared for the purpose of comparison, which made depending on the mean squares error (MSE).