Automatique
NEURAL MODEL IDENTIFICATION OF METALLURGICAL PROCESS IN OXYGEN CONVERTER
In the iron and steel industry domain, the adjustment of the percentage of the chemical composition of the cast iron in the oxygen converter is essential to produce steel; this operation is to carry out by an oxygen lance in the liquid cast iron without expenditure of energy (fuel). The oxygen injected makes chemical reactions with the cast iron elements, and according to the quantity of oxygen injected we can fix the percentage of each chemical element in steel. It is sometimes extremely difficult to modeling the variations of the chemical compositions with the dynamic nonlinear. In this work, the identification of the nonlinear relations are studied by using the neural networks, the real cases were adapted using data banks of the process, the results obtained are presented and discussed. Voir les détails
Mots clés : modeling, neural networks, oxygen converter.
FAULT DIAGNOSIS OF ROTATING MACHINERY USING WAVELET TRANSFORM AND PRINCIPAL COMPONENT ANALYSIS
Fault diagnosis is playing today a crucial role in industrial systems. To improve the reliability, safety and efficiency advanced methods of fault diagnosis become increasingly important for many systems. In this paper, fault diagnosis of rotating machinery is performed using a combination between Wavelet Transform (WT) and Principal Component Analysis (PCA) methods. The WT is employed to decompose the vibration signal of measurements data in different frequency bands. The obtained decomposition levels are used as input to the PCA method for fault detection and diagnosis. The objective of this method is to obtain the information contained in the frequency bands of the measured data. The proposed method is evaluated using experimental measurements data with mass unbalance and gear fault. Voir les détails
Mots clés : Vibration measurement, Fault Diagnosis, Wavelet Analysis, principal component analysis, Mass Unbalance, Gear Fault
Identification d'un modèle neuronale du processusmétallurgique dans le convertisseur à oxygène
Dans le domaine de la sidérurgie, l'ajustement dupourcentage de la composition chimique de la fonte dansle convertisseur à oxygène est indispensable pour produirede l'acier, cette opération est effectuer par une lanced'oxygène dans la fonte liquide sans dépense d'énergie(combustible). L'oxygène injecté faire des réactionschimique avec les éléments de la fonte, et suivant laquantité d'oxygène injecté on peut fixer le pourcentage dechaque élément chimique dans l'acier. Il est parfoisextrêmement difficile de modéliser les variations descompositions chimiques avec des dynamiques nonlinéaires. Dans ce travail, l’identification des relations nonlinéaire à été étudiée en utilisant les réseaux de neurones,des cas réels ont été adaptés utilisant des banques dedonnées du processus, les résultats obtenus sont présentéset discutés. Voir les détails
Mots clés : modélisation, réseau de neurone, convertisseur à oxygène.
Simulation of the variation in temperaturein a material without and with default
In this article our principal study is the simulation ofthe variation in temperature in a solid material in absence and inpresence the default, in particular a fracture on the level of surfaceof material, and to see how the default influences on heat transferin a solid. The simulation is made by FLUENT software whichpermits us to solve the energy equation by finite volumes method. Voir les détails
Mots clés : heat transfer; simulation; material; default
Application of the neural networks for modeling the molten steel level variation in the continuous casting process
In this paper our principal study is the development of a model of synthesis presents the variation of the molten steellevel in the ingot mould of continuous casting by using the extraction speed in the input of the model. The approach usedis based on the neural networks technique which allows modeled the process of level variation, and also makes it possibleto know the reliability of the neural networks the modeling the industrial processes. Voir les détails
Mots clés : modeling, continuous casting, neural networks
Détection et Classification de Defaults dans les Machines Tournantes par l’Analyse en Composante Principale Multi-Echelle
L’analyse en composantes principales à multi-échelles (MSPCA) et le classificateur Neuro logique floue sont considérés parmi les méthodes modernes, et qui est utilisée dans nombreux applications de classifications. D’entre eux une nouvelle application dans les machines tournantes, le diagnostic des defaults est proposé. Le modèle ACP à multi-échelle est construit par la variance des cinq niveaux de décomposition en ondelette. Comme un vecteur de caractéristiques, ces caractéristiques sont entrainées par le classificateur neuro flou pour diagnostiquer le défaut. La performance de la méthode sera discutée, et les résultants montrent l’efficacité de l’approche proposée. Voir les détails
Mots clés : ACP multi échelle, Classifieur Neuro flou, diagnostique de défaut
Task Performance Evaluation for Industrial Robots
Integrated multi-modal Supervisory Control Systems(ISCS) are a new generation of complex and synergistic Human-Machine Interaction Systems (HMIS). This paper deals withmulti-modal interaction and control applied to HRS. A taskperformance evaluation technique dedicated for multi-modalinteraction and control is proposed. It enables comparison oftask performance carried out by using different selection ofcontrol modes or by different operators. Objective andsubjective performance measures are defined. Based on theanalytical hierarchy process method (AHP) which takes intoaccount qualitative and quantitative attributes and criteria.Experimental results have been carried out and somepreliminary results will be presented concerning industrialmanipulators. Voir les détails
Mots clés : Task performance evaluation, Robotics, human factors, Analytical Hierarchy Process, Adaptive supervisory control, Multi-modal interaction, Graphical-user interface.
Vibration signal-based bearing fault diagnosis usingoptimized multi-scale entropy and ANFIS network
This paper presents an application of a multi-scaleclassification method to detect bearing-related faults in anexperimental benchmark. Multi-scale analysis of the vibrationsignal allows the representation of nonlinear dynamics andcoupling effects between different mechanical components ofindustrial equipment. An improved multi-scale entropy analysisis used as features extraction tool for the diagnosis procedure.The classification of the state of health of the bearings is achievedusing adaptive neuro-fuzzy inference system and neural networksfor different faults scenarios with variable fault severity.Experimental results show the importance of the choice of thefeatures extraction method for the classification of faults and thedetermination of their severity. Voir les détails
Mots clés : Fault Diagnosis, Vibration analysis, multi-scale entropy (MSE), bearing faults
Profile of heat transfer between two different materials
In this article we made a study on the transfer of heatin two different materials such as steel and copper. Initially wepresent the profile of heat transfer in each material alone, after wepresent the profile of the same phenomena in the two materials incontacts, and to see how the temperature is propagated when we havea variation of thermal conductivity. The simulation is made byANSYS software which permits us to solve the energy equation byfinite element method. Voir les détails
Mots clés : Simulation; material; heat transfer.
Conception of fractional PIλ controllerthrough classical PI controller
Fractional order PIλDμ controllers are gaining more interests from the control community. They have been introduced in the control loops in a continuous effort to ameliorate the system control performances. In this work, the design of the fractional order PIλ controller derived through the regular PI controller used for the first order lag plus time delay control system is proposed. The main idea of this article is the tuning of the parameter λ of the fractional order PIλ controller to ameliorate the overshoot, the integral squared error and the settling time performances of the step response of the feedback control system compared to the ones of the feedback control system with the corresponding classical PI controller. The control quality enhancement of the proposed PIλ controller scheme compared to the corresponding classical PI controller has been presented through the simulation results of illustrative examples. Voir les détails
Mots clés : component; fractional order controllers; fractional order PI controllers; PI tuning, time delay.