Browsing by Author "Ratni, Azeddine"

Now showing 1 - 8 of 8

Automatic condition monitoring of electromechanical system based on MCSA, spectral kurtosis and SOM neural network
(JVE International, 2019) Zair, Mohamed; Rahmoune, Chemseddine; Benazzouz, Djamel; Ratni, Azeddine
Condition monitoring and fault diagnosis play the most important role in industrial applications. The gearbox system is an essential component of mechanical system in fault identification and classification domains. In this paper, we propose a new technique which is based on the Fast-Kurtogram method and Self Organizing Map (SOM) neural network to automatically diagnose two localized gear tooth faults: a pitting and a crack. These faults could have very different diagnostics; however, the existing diagnostic techniques only indicate the presence of local tooth faults without being able to differentiate between a pitting and a crack. With the aim to automatically diagnose these two faults, a dynamic model of an electromechanical system which is a simple stage gearbox with and without defect driven by a three phase induction machine is proposed, which makes it possible to simulate the effect of pitting and crack faults on the induction stator current signal. The simulated motor current signal is then analyzed by using a Fast-Kurtogram method. Self-organizing map (SOM) neural network is subsequently used to develop an automatic diagnostic system. This method is suitable for differentiating between a pitting and a crack fault. © 2019 Zair Mohamed, et al
Automatic condition monitoring of electromechanical system based on MCSA, spectral kurtosis and SOM neural network
(2019) Zair, Mohamed; Rahmoune, Chemseddine; Benazzouz, Djamel; Ratni, Azeddine
Condition monitoring and fault diagnosis play the most important role in industrial applications. The gearbox system is an essential component of mechanical system in fault identification and classification domains. In this paper, we propose a new technique which is based on the Fast-Kurtogram method and Self Organizing Map (SOM) neural network to automatically diagnose two localized gear tooth faults: a pitting and a crack. These faults could have very different diagnostics; however, the existing diagnostic techniques only indicate the presence of local tooth faults without being able to differentiate between a pitting and a crack. With the aim to automatically diagnose these two faults, a dynamic model of an electromechanical system which is a simple stage gearbox with and without defect driven by a three phase induction machine is proposed, which makes it possible to simulate the effect of pitting and crack faults on the induction stator current signal. The simulated motor current signal is then analyzed by using a Fast-Kurtogram method. Self-organizing map (SOM) neural network is subsequently used to develop an automatic diagnostic system. This method is suitable for differentiating between a pitting and a crack fault
Detection of bearing fault using Empirical Wavelet Transform and S Transform methods
(IEEE, 2020) Merainani, Boualem; Bouzid, Abir Amar; Ratni, Azeddine; Benazzouz, Djamel
Rolling-element bearing is one of the crucial mechanical components in induction motors. Since, its fault may produce huge damage; the way to efficiently diagnose the bearing faults is a high issue in signal processing, and its fault detection draw an important significance. In this paper, a hybrid method based on Empirical Wavelet Transform and S Transform has been proposed in order to detect the outer race bearing fault in an induction motor using vibration signals. As the collected signals are disturbed by noise, EWT is used to filter the raw signals in conjunction with isolating the region containing fault characteristic frequencies. Then ST is used to represent an Amplitude-Frequency and a Time-Frequency contour of the filtered signals, which allow to detect the bearing fault. Finally, experimental vibration data have been investigated to assess the reliability of the developed method. The results obtained show a good performance
Detection of shaft crack fault in gearbox using hilbert transforms
(IEEE, 2017) Ratni, Azeddine; Rahmoune, Chemseddine; Benazzouz, Djamel; Ould bouamama, Belkacem; Merainani, Boualem
Fault feature extraction and classification based on HEWT and SVD : application to rolling bearings under variable conditions
(IEEE, 2017) Merainani, Boualem; Rahmoune, Chemseddine; Benazzouz, Djamel; Ould-Bouamama, Belkacem; Ratni, Azeddine
Intelligent multi-fault identification and classification of defective bearings in gearbox
(SAGE Publications Inc., 2024) Damou, Ali; Ratni, Azeddine; Benazzouz, Djamel
Bearing faults in gearbox systems pose critical challenges to industrial operations, needing advanced diagnostic techniques for timely and accurate identification. In this paper, we propose a new hybrid method for automated classification and identification of defective bearings in gearbox systems with identical rotating frequencies. The method successfully segmented the signals and captured specific frequency components for deeper analysis employing three distinct signal processing approaches, ensemble empirical mode decomposition EEMD, wavelet packet transform WPT, empirical wavelet transform EWT. By decomposing vibration signals into discrete frequency bands using WPT, relevant features were extracted from each sub-band in the time domain, enabling the capturing of distinct fault characteristics across various frequency ranges. This extensive set of features is then served as inputs for machine learning algorithm in order to identify and classify the defective bearing in the gearbox system. Random forest RF, decision tree DT, ensemble tree ET classifiers showcased a notable accuracy in classifying different fault types and their localizations. The new approach shows the high performance of the diagnostic gearbox with a minimum of accuracy (Min = 99.95 %) and higher stability (standard deviation = 0.1).
Modélisation et surveillance des systèmes industriels : application à un réducteur de vitesse
(2017) Ratni, Azeddine
Toute machine en cours de fonctionnement produit des vibrations. L'analyse de ces effets permet de caractériser la nature des efforts dynamiques et du fonctionnement anormal résultats. Ainsi l'analyse des vibrations est devenue une technique très répandue pour apprécier l'état de santé d'une machine afin d'éviter la défaillance et n'intervenir qu'à bon escient et pendant des arrêts programmés de production. Pour détecter le défaut à un stade précoce, la méthode la plus utilisée est le calcul de l'enveloppe et son spectre, mais pour calculer l'enveloppe nous devons connaitre avec précision les fréquences de résonances qui contiennent les informations nécessaires sur le défaut. Pour déterminer cette bande de fréquence, on utilise le kurtogramme basé principalement sur le calcul du Kurtosis spectral, pour détecter et caractériser des non-stationnarités dans un signal. Cependant, dans le cas d'un réducteur de vitesse, l'analyse d'enveloppe ne permet pas la détection des défauts naissants. Pour pallier l'incapacité du kurtogramme dans le domaine temporel, on a développé dans cette thèse une nouvelle approche du traitement de signal qui permet d'améliorer la détection et le diagnostic des défauts naissants dans le réducteur de vitesse. Cette nouvelle approche est basée sur la déconvolution du Kurtosis Corrélé Maximal et le Kurtosis Spectral. Cette approche permet d'obtenir une meilleure détection dans le système de réducteur de vitesse avec une meilleure sensibilité, comparée au kurtosis spectral. Pour appliquer cette nouvelle approche afin de caractériser et comprendre le bruit rayonné par un réducteur, il est indispensable d'étudier le comportement dynamique des engrenages. Pour établir le modèle mécanique. La méthode proposée permet de détecter et d'identifier au stade précoce la fissuration des dents dans le réducteur de vitesse à la fois dans le domaine temporel et fréquentiel
A new method to enhance of fault detection and diagnosis in gearbox systems
(2017) Ratni, Azeddine; Rahmoune, Chemseddine; Benazzouz, Djamel