Automatique

Nombre total de résultats : 81
Pertinence Titre A-Z Plus récents Plus anciens
10 25 50
Année de publication
et

Modélisation et diagnostic de défaillance d’une électrovanne pneumatique

Khouloud BEDOUD (2010)
Mémoire de magister

Ce sujet de recherche porte sur le diagnostic de défauts, on s'intéresse particulièrement à développer des algorithmes de décision basés sur la logique floue pour la surveillance des défauts latents qui abrègent la durée de vie de l'installation, voir l'endommager à court terme. L'installation qui fait l'objet de notre étude est une électrovanne de régulation de flux (jus de betterave) dans les installations de production de sucre. C'est un benchmark (projet DAMADICS) développé par un Consortium de Laboratoires Européen (France, Pologne, Allemagne, etc.), qui a fait l'objet d'intenses recherches notamment en ce qui concerne le diagnostic des défauts brusques par différentes techniques. Dans une première étape nous exploitons le modèle Simulink de l'actionnaire (électrovanne) proposé par le benchmark, pour générer les résidus obtenus de la comparaison des mesures réelles des variables du processus et les sorties du modèle Simulink, qui seront ensuite analysés par un algorithme de décision basé sur le raisonnement flou. L'objectif d'une telle démarche étant la validation de l'algorithme de décision. Dans une seconde étape nous construisons un modèle basé sur des mesures réelles produites sur l'installation en cours de production. La technique utilisée est l'optimisation d'un modèle TS. Contrairement à la première étape ou le modèle Simulink n'accepte qu'un seul type de défauts à la fois, cette fois-ci on peut injecter plusieurs défauts simultanément. Voir les détails

Mots clés : diagnostic de défaillance, détection de défauts, isolation de défauts.

Support Vector Machine Based on Firefly Algorithm For Bearing Fault Diagnosis

Tawfik THELAIDJIA, Abdelkrim Moussaoui, Salah CHENIKHER  (2014)
Article de conférence

The fault diagnostics and identification of rolling element bearings have been the subject of extensive research. It consists of two major parts: vibration signal feature extraction and condition classification for the extracted features. In this paper, feature extraction from faulty bearing vibration signals is performed by signal’s time-varying statistical parameters. In this way, a 7-dimensional vector of the vibration signal feature is obtained. After feature extraction from vibration signal, the support vector machine (SVM) was applied to automate the fault diagnosis procedure. To improve the classification accuracy for bearing fault prediction, Firefly Algorithm (FFA) is employed to simultaneously optimize the SVM kernel function parameter and the penalty parameter. The results have shown feasibility and effectiveness of the proposed approach. Voir les détails

Mots clés : Condition monitoring, Firefly Algorithm, Roller Bearing, Statistical parameters, Support Vector Machine.

Autoregressive Modeling and PCA Preprocessing to Support Vector Machines Based on PSO for Bearing Fault Diagnosis

Tawfik THELAIDJIA, Abdelkrim Moussaoui, Salah CHENIKHER, Amar BOUTAGHANE  (2014)
Article de conférence

In this paper a method for fault diagnosis of rolling bearings is presented. It consists of two major parts: vibration signal feature extraction and condition classification for the extracted features. In this paper Autoregressive Modeling followed by Principal Components Analysis (PCA) was introduced for feature extraction from faulty bearing vibration signals. After extracting feature vectors by AR-PCA, the support vector machine (SVM) was applied to automate the fault diagnosis procedure. To improve the classification accuracy for bearing fault prediction, particle swarm optimization (PSO) is employed to simultaneously optimize the SVM kernel function parameter and the penalty parameter. The results have shown feasibility and effectiveness of the proposed approach. Voir les détails

Mots clés : Autoregressive Modeling, Principal Components Analysis, Support vector machine, Particle Swarm Optimization, Wavelet Packet, Fault Diagnosis, Roller Bearing.

Feature Extraction and SOM for Bearing Fault Diagnosis

Tawfik THELAIDJIA, Abdelkrim Moussaoui, Salah CHENIKHER, Amar BOUTAGHANE, Sami KAHLA  (2014)
Article de conférence

In this paper a method for fault diagnosis of rolling bearings is presented. It consists of two parts: vibration signal feature extraction and condition classification. The aim of the first step is the extraction of the relevant parameters; the proposed technique consists of preprocessing the bearing fault vibration signal using a combination of the signal’s Kurtosis and discrete wavelet transform (DWT). The Self-organization Map (SOM) is used to accomplish the classification step and automate the fault diagnosis procedure. The results have shown feasibility and effectiveness of the proposed approach. Voir les détails

Mots clés : Condition monitoring, Discrete wavelet transform, Fault Diagnosis, Kurtosis, Roller Bearing, Rotating machines, Self-organization Map, Vibration measurement.

Direct adaptive backstepping control with tuning functions for a single-link flexible-joint robot

Y. Soukkou, A. Boutaghane, H. Khebbache  (2014)
Article de conférence

In this paper, direct adaptive backstepping control with tuning functions approach for a single-link flexible-joint robot model is proposed. The proposed approach of adaptation is based on the tracking error based parameter adaptation law. First, the direct adaptive backstepping control with tuning functions is applied for a class of nonlinear systems in parametric strict-feedback form to avoid overparametrization. Next, the main steps of the controller design for a single-link flexible-joint robot manipulator model are described. The stability of the proposed controller is studied by using the Lyapunov functions. Finally, the simulation results are given to demonstrate the performance of the proposed approach. Voir les détails

Mots clés : Single-link flexible-joint robot, Backstepping control, direct adaptive control, tuning functions, direct adaptation

Indirect adaptive backstepping control by using the virtual controls filtering

Y. Soukkou, S. Labiod, A. Boutaghane  (2014)
Article de conférence

In this paper, by using the dynamic surface control technique, an indirect adaptive backstepping controller based x-swapping identifier with a gradient-type update law is proposed for a class of parametric strict-feedback nonlinear systems. The main steps of the controller design for a class of nonlinear systems in parametric strict-feedback form are described. Then, the closed-loop error dynamics is shown to be globally stable by using the Lyapunov stability approach. Simulation results for a single-link flexible-joint robot manipulator are given to illustrate the performance of the proposed controller. Voir les détails

Mots clés : Backstepping control, adaptive control, dynamic surface control, Lyapunov stability, Single-link flexible-joint robot

Adaptive backstepping control using combined direct and indirect σ–modification adaptation

Y. Soukkou, S. Labiod  (2014)
Article de conférence

In this paper, by using the dynamic surface control technique, an adaptive backstepping controller using combined direct and indirect σ-modification adaptation is proposed for a class of parametric strict-feedback systems. In this approach, a σ-modification parameter adaptation law that combines direct and indirect update laws is proposed. At first, the x-swapping identifier with a gradient-type update law is presented for a class of parametric strict-feedback nonlinear systems. Next, the main steps of the controller design for a class of nonlinear systems in parametric strict-feedback form are described. The closed-loop error dynamics is shown to be globally stable by using the Lyapunov stability approach. Finally, simulation results for a single-link flexible-joint robot manipulator are given to illustrate the tracking performance of the proposed adaptive control scheme. Voir les détails

Mots clés : Backstepping control, direct and indirect adaptive control, adaptive dynamic surface control, Lyapunov stability, flexible joint manipulators

Modélisation et Commande Vectorielle d’une Machine Asynchrone à Sept phase

BOUSSIALA Boubakr, NEZLI Lazhari, MAHMOUDI M.Oulhadj  (2013)
Article de conférence

In this work, we present the modeling and vector control of seven-phase induction machine, regularly shifted them in space. The modeling is based on the method of diagonalization of matrices inductors to magnetically decouple phases. Secondly, the vector control used is intended to obtain the excellent performance of the DC machine Voir les détails

Mots clés : Seven-phase Asynchronous machine, diagonalization, vector control

Condition monitoring of rotating machinery by vibration signal processing methods

H. Bendjama, K. Gherfi, D. Idiou, M.S. Boucherit  (2014)
Article de conférence

La détection et le diagnostic de défauts jouent un rôle important dans la sécurité, la productivité et la qualité des pro-duits. Durant la dernière décennie, des recherches actives et considérables se sont effectuées en vue de développer des mé-thodes de détection et de diagnostic de défauts des machines tournantes. Dans ce travail, des techniques d’analyse dans les domaines : temporel, fréquentiel et temps-fréquence, sont étu-diées. Des résultats en utilisant des mesures réelles, sont pré-sentés et discutés. Voir les détails

Mots clés : diagnostic de défauts, machines tournantes, domaine temporel, domaine fréquentiel, domaine temps-fréquence.

NEURAL MODEL IDENTIFICATION OF METALLURGICAL PROCESS IN OXYGEN CONVERTER

Kaddour Gherfi, Houssine Bendjama, Salah Bouhouche, Hezem Meradi  (2012)
Article de conférence

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.