Ladjal M.,ila University |
Bouamar M.,ila University |
Djerioui M.,ila University
Mediterranean Journal of Measurement and Control | Year: 2016
The control, measurement and monitoring of water quality is becoming more and more interesting because of its effects on human life. Many approaches were developed in order to ameliorate the water quality monitoring process. This paper presents the application of Artificial Neural Network (ANN) and Support Vector Machines (SVM) multiclass classification techniques in control and monitoring of water quality. This study involved the interpretation of surface water quality data of Tilesdit dam (Algeria). A multi-class problem is a typical example for solving the mentioned problem. The MLP networks and the algorithm of SVM, one-against-all, are the most popular strategies for multi-class problems. In this work, the training phase is carried out using these approaches to supervise water quality from four several physicochemical parameters such as temperature, pH, Conductivity and Turbidity. These parameters of water quality indicators were collected at Tilesdit production station during three years (2009- 2011). In order to evaluate their performances, a simulation using real dataset measured from study area station, corresponding to the recognition rates (training and test), training time and robustness, is carried out. The results are compared to get the best performance evaluation of the intelligent proposed approach for of monitoring and measurement of water quality. Copyright © 2016 SoftMotor Ltd.
Mezahi F.Z.,University of Mentouri Constantine |
Mezahi F.Z.,ila University |
Oudadesse H.,University of Rennes 1 |
Harabi A.,University of Mentouri Constantine |
Le Gal Y.,University of Rennes 1
International Journal of Applied Ceramic Technology | Year: 2012
In this study, the ability to form bone-like apatite on surface of both pure natural hydroxapatite (N-HA) and natural hydroxyapatite containing 5 wt% of ZrO 2 or TiO 2 or Al 2O 3, sintered at 1300°C for 2 h and soaked in the simulated body fluid for different times, was studied. It has been found that the presence of β-tricalcium phosphate in N-HA + 5 wt% ZrO 2 or TiO 2 has promoted the precipitation of bone-like apatite in the Zr or Ti poorest regions. By contrast, the presence of 5 wt% of Al 2O 3 did not induce any apatite precipitation on N-HA sample surfaces. © 2012 American Ceramic Society.
Chemachema M.,ila University |
Belarbi K.,University of Mentouri Constantine
International Journal of Modelling, Identification and Control | Year: 2010
In this paper, a neural network (NN) direct adaptive control algorithm is presented for a class of uncertain SISO non-linear systems. In the proposed approach there is no sign constraint on the system control gain and/or on its derivative as done in the literature. The NN approximates an ideal controller in feedback linearisation form based on an estimate of the control error signal used in the adaptive laws derivation. An estimated value of the control error is provided by a fuzzy inference system composed of a set of rules determined heuristically from information related to the history of the output tracking error. Lyapunov direct method is then used to prove the global exponential boundedness of all the signals involved in the closed loop and hence the stability of the system. Simulation results demonstrate the effectiveness of the proposed approach. Copyright © 2010 Inderscience Enterprises Ltd.
Mezahi F.-Z.,University of Mentouri Constantine |
Mezahi F.-Z.,ila University |
Girot A.L.-.,CNRS Chemistry Institute of Rennes |
Oudadesse H.,CNRS Chemistry Institute of Rennes |
Harabi A.,University of Mentouri Constantine
Journal of Non-Crystalline Solids | Year: 2013
A new composition of bioactive glass, in the quaternary system SiO 2-CaO-Na2O-P2O5, was synthesized using melting and sol-gel routes. The prepared glass, 52S4: (wt.%) 52% SiO 2-30% CaO-14% Na2O-4% P2O5, was soaked in Simulated Body Fluid (SBF) in order to evaluate the kinetic reactivity of this glass versus the synthesis mode. The obtained results have shown that 52S4 is a bioactive glass if it is prepared either by melting or sol-gel methods. The bone-like apatite was formed at the glass surface prepared by sol-gel route after 2 h. However, the formation of this apatite was delayed to 1 day when the glass was prepared by melting method. In addition, this apatite was crystallized, after 30 days soaking in SBF, only if the glass is prepared by melting route. The glass prepared by sol-gel method was more resorbable and leads to silica gel formation up on amorphous apatite layers at any time. So, this silica gel inhibited the crystallization of amorphous apatite. © 2012 Elsevier B.V.
Ladaci S.,Polytechnic School of Algiers |
Chettah S.,Skikda University |
Khettab K.,ila University
16th International Conference on Sciences and Techniques of Automatic Control and Computer Engineering, STA 2015 | Year: 2015
This paper deals with direct adaptive pole placement control bases on polynomial control solution. The considered problem concerns many potential industrial applications. We propose a direct adaptive control algorithm by mean of fractional order pole assignment. A simulation example illustrates the enhancement obtained in system's dynamics comparatively to existing algorithms. © 2015 IEEE.
Meddah A.,University of Bordj Bou Arréridj |
Meddah A.,ila University |
Beddar M.,ila University |
Bali A.,Polytechnic School of Algiers
Journal of Cleaner Production | Year: 2014
Recycling of waste rubber tires in pavements is considered as ecological and economical solutions due to their advantages. It may help preserving natural resources and producing an eco-friendly material. Roller compacted concrete used in pavements (RCCP) has the same basic ingredients as in ordinary concrete. But unlike the conventional concrete, it is an enough drier mix-stiff to be compacted by vibratory rollers. This study aims to experimentally investigate the possibility of using shredded rubber tire in RCCP. The rubber particles are added to mixes as a partial replacement by volume of some parts of natural crushed aggregates. Unit weight, mechanical properties, modulus of elasticity and porosity are evaluated and compared according to the rubber content in the concrete mix. The effects of compaction energy and roughness of rubber surfaces are also studied. The results obtained showed that the inclusion of rubber particles in RCCP mixes will change their characteristics in fresh state as well as hardened state. Even though the mechanical properties decrease when rubber content in the mix is increasing, it should be noted that it is possible to use rubber particles in low traffic pavements project. In the other hand, rubber particles may improve some desired technical characteristics such as; porosity, ductility and cracking resistance performance. In addition to that, it may be more environmentally efficient to use rubber aggregates in RCCP, because this helps to remove some parts of these wastes and protect the environment. The performance of RCCP with shredded rubber additions can be improved by modifying the roughness of rubber particle surfaces, when the optimal rubber content depends on technical requirements and the destination of project. © 2014 Elsevier Ltd. All rights reserved.
Amroune A.,ila University |
Davvaz B.,University of Yazd
Iranian Journal of Fuzzy Systems | Year: 2011
The starting point of this paper is given by Priestley's papers, where a theory of representation of distributive lattices is presented. The purpose of this paper is to develop a representation theory of fuzzy distributive lattices in the finite case. In this way, some results of Priestley's papers are extended. In the main theorem, we show that the category of finite fuzzy Priestley spaces is equivalent to the dual of the category of finite fuzzy distributive lattices. Several examples are also presented.
Razika I.,ila University |
Nabila I.,ila University |
Madani B.,ila University |
Zohra H.F.,ila University
Energy Conversion and Management | Year: 2014
A solar collector is a device that converts solar energy into heat. This paper presents an experimental study on the influences of volumetric flow rate and inclination angle on the performance of a solar collector. The tests were conducted on a solar energy demonstration system (ET200), which consists of a solar collector, a storage tank, a control and command cabinet and a high power lamp simulating solar energy. For radiation intensity of 1.033 kW/m2 and inclination angle of 0, the results showed that the efficiency of the collector followed a linear relationship versus the flow rate; η = 0.68 × Qv + 49.79 and presented a coefficient of correlation (R 2) of 0.9898. Similarly, the increase of the inclination angle from 0 to 60 increased the effectiveness of the collector. A linear relationship; η = 0.43 × α + 53.07 with a high coefficient of determination (R2 = 0.967) relates the collector efficiency to the inclination angle. It is important to operate at higher mass flow rates and take the collector angle at 0 in order to reach its meaning full efficiency (heating water). © 2013 Elsevier Ltd. All rights reserved.
Bouamar M.,ila University |
Ladjal M.,ila University
International Journal of Computational Intelligence and Applications | Year: 2012
Water quality is one of the major concerns of countries around the world. Monitoring of water quality is becoming more and more interesting because of its effects on human life. The control of risks in the factories that produce and distribute water ensures the quality of this vital resource. Many techniques were developed in order to improve this process attending to rigorous follow-ups of the water quality. In this paper, we present a comparative study of the performance of three techniques resulting from the field of the artificial intelligence namely: Artificial Neural Networks (ANN), RBF Neural Networks (RBF-NN), and Support Vector Machines (SVM). Developed from the statistical learning theory, these methods display optimal training performances and generalization in many fields of application, among others the field of pattern recognition. In order to evaluate their performances regarding the recognition rate, training time, and robustness, a simulation using generated and real data is carried out. To validate their functionalities, an application performed on real data is presented. Applied as a classification tool, the technique selected should ensure, within a multisensor monitoring system, a direct and quasi permanent control of water quality. © 2012 Imperial College Press.
Ihaddadene N.,ila University |
Ihaddadene R.,ila University |
Mahdi A.,ila University
Applied Mechanics and Materials | Year: 2014
In this research document, an attempt has been made to come across the effect of double glazing on the efficiency of a solar thermal collector. Experiments were performed on an active solar energy demonstration system (ET 200). Commercial glass pane of 3 mm thick having the same dimensions as that of the apparatus was placed above the collector at a distance of 2 cm. Tests were done with and without the added glass. Experiments were performed for double glazing with two positions of the light meter. In one position, it was placed in the middle of the collector surface. While, in the other, the light meter was placed in the middle of the added glass. To study the effect of double glazing on the performance of the solar collector ET200, the correct position of the light meter was to place it exactly in the middle of the additional pane under the lamp. Double glazing decreased the efficiency of the collector of 15%. © (2014) Trans Tech Publications, Switzerland.