Search

Abstract: For many years, seawater desalination technique has been operational to deal with water scarcity. In Boujdour region, located near the Atlantic ocean southwest of Morocco, most water drinking is produced by a reverse osmosis seawater desalination plant. The permeate conductivity prediction is used to evaluate the performance of desalination plants. The present paper focuses on the modeling and comparison of the Artificial Neural Network (ANN) and Multiple Linear Regression (MLR) for the prediction of permeate conductivity for a one-year period. Six input variables are considered, including turbidity, temperature, pH, feed conductivity, feed flow, and transmembrane pressure (TMP). Firstly, in this paper, the MLR identifies the most important variables influencing the permeate conductivity with the aim of developing a regression model for the dependent and independent parameters. Secondly, the ANN method is examined to analyze the performance of desalination plant. A study of the effect of the number of neurons and the number of hidden layers on the efficiency of the neural network has been made. Results confirm that the MLR and ANN models forecast the permeate conductivity with a suitable coordination coefficient of the real and predicted values. Finally, ANN model has been successfully tested for reliability with a correlation coefficient R2 of 99.097% and a mean square error (MSE) of 0.002607. method: Artificial Neural Network and Multiple Linear Regression-modeling result: Results confirm that the MLR and ANN models forecast the permeate conductivity with a suitable co-ordination coefficient of the real and predicted values. In terms, ANN model was successfully tested for reliability with a correlation coefficient R2 of 99.097% and a mean square error (MSE) of 0.002607 conclusion: This clearly indicates the success of the ANN model for permeate conductivity prediction. Therefore, it can be concluded that the ANN is superior in modeling and predicting permeate conductivity for reverse osmosis seawater desalination

In this paper, two methods are developed for the prediction of wind speed, namely, the Multiple Linear Regression (MLR) and Artificial Neural Networks (ANNs) in north and south regions of Morocco for three years (i.e., 2011–2012–2013). The first method consists of determining the parameters which most significantly influence the wind speed in order to build a regression model between the predictors and the dependent variable. The second proposed approach is ANNs where the neural network chosen is the multilayer perceptron that uses the back-bropagation (BP) as a supervised learning technique for training. The results show that both MLR and ANNs models predict the wind speed at an acceptable correlation coefficient between the actual and predicted wind speed. However, the ANNs perform better in terms of statistical errors notably in terms of mean absolute error, mean absolute percentage error and mean square error.

International audience; This paper introduces a Web Services based approach that extends resource reservation mechanism for interactive multimedia applications over multimedia satellite systems. It proposes a flexible and extensible scheme for the discovery of services in the network and the configuration of the satellite terminal when resources are requested. It finally presents experimental results of the proposed scheme over a realistic DVB-S2/RCS emulation platform.

In the present work, a mathematical model for an acidification process of water used for the diffusion operation in the beet sugar refineries is developed. This model is based on masses balances taking into account the main chemical reactions occuring. It was validated in dynamic state, experimentally, by carrying out tests on an industrial process. Indeed, it was simulated, in steady state, to determinate of process parameters operation, and in dynamics, to study the behavior in transient state. Dynamic simulation was realized by solving the differential equations of the model using the Runge-Kutta method, and while carrying out on the real processes the various disturbances that have the echelon form. The results obtained are satisfactory and has showed that the model is valid and can be used for the pH control