No description available.

Machinery failure diagnosis is an important component of the Condition Based Maintenance (CBM) activities for most engineering systems. Rolling element bearings are the most common cause of rotating machinery failure. The existence of the amplitude modulation and noises in the faulty bearing vibration signal present challenges to effective fault detection method. The wavelet transform has been widely used in signal de-noising due to its extraordinary time-frequency representation capability. A new technique for an automated detection and diagnosis of rolling bearing conditions is presented in this thesis. The time-domain vibration signals of rolling bearings with different fault condition are pre-processed using Impulse and Laplace wavelet transforms for rolling bearing fault detection and feature extraction, respectively. The wavelet denoising and the wavelet envelope power spectrums are used for bearing fault detection and diagnosis. Furthermore, the extracted features for the wavelet transform coefficients in time and frequency domain are applied as input vectors to Artificial Neural Networks (ANN) for rolling bearing fault classification. The Impulse and Laplace Wavelets shape and the ANN classifier parameters are optimized using a genetic algorithm (GA). To reduce the computation cost, decrease the size, and enhance the reliability of the ANN, only the predominant wavelet transform scales are selected for feature extraction. The results for both real and simulated bearing vibration data show the effectiveness of the proposed technique for bearing condition identification and classification with very high success rate using minimum input features.

This thesis introduces and develops a novel real-time predictive maintenance system to estimate the machine system parameters using the motion current signature. A crucial concept underpinning this project is that the motion current signature contains infor­mation relating to the machine system parameters and that this information can be extracted using nonlinear mapping techniques, such as neural networks. Towards this end, a proof of con­cept procedure is performed, which substantiates this concept. A simulation model, TuneLearn, is developed to simulate the large amount of training data required by the neural network ap­proach. Statistical validation and verification of the model is performed to ascertain confidence in the simulated motion current signature. Validation experiment concludes that, although, the simulation model generates a good macro-dynamical mapping of the motion current signature, it fails to accurately map the micro-dynamical structure due to the lack of knowledge regarding performance of higher order and nonlinear factors, such as backlash and compliance. Failure of the simulation model to determine the micro-dynamical structure suggests the pres­ence of nonlinearity in the motion current signature. This motivated us to perform surrogate data testing for nonlinearity in the motion current signature. Results confirm the presence of nonlinearity in the motion current signature, thereby, motivating the use of nonlinear tech­niques for further analysis. Outcomes of the experiment show that nonlinear noise reduction combined with the linear reverse algorithm offers precise machine system parameter estimation using the motion current signature for the implementation of the real-time predictive maintenance system. Finally, a linear reverse algorithm, BJEST, is developed and applied to the motion current signature to estimate the machine system parameters.

Dans un contexte économique fortement concurrentiel, la maintenance des équipements de productions constitue un enjeu socio-économique décisif pour les entreprises. De même, les enjeux de maintenance ont connu de fortes évolutions, le secteur est en pleine mutation. Face à cela, les attentes, les besoins en matière de coût, de délai, de qualité et de respect de l’environnement changent. Suite à ce constat, on a souhaité développer dans cette thèse de nouvelles stratégies intégrées de maintenance, de production, de gestion des stocks de pièces de rechange en tenant compte de différentes contraintes opérationnelles. Parmi ces contraintes, on peut citer la variation de la cadence de production des systèmes et son impact sur la dégradation du système de production ainsi que sur le plan de maintenance et de gestion de pièces de rechanges. On s’est intéressé aussi à l’origine et au type des pièces de rechange (neuves ou usagées) utilisées pour assurer les activités de maintenance. En plus de l’influence technico-économique de l’origine des pièces de rechange utilisées sur le système de production, on a également évalué l’impact environnemental de ces derniers en considérant des données de l’ADEME. Formellement, L’objectif de cette thèse est de contribuer par des approches formelles permettant une optimisation des cadences de production couplée à des politiques de maintenance et intégrant des stratégies efficientes dans la gestion des pièces de rechange. Des méthodes analytiques et techniques d’optimisation, appuyées par des modèles de simulations selon la difficulté de résolutions ont été développées afin de réaliser les objectifs de cette thèse. Une étude de cas industrielle ainsi que des exemples numériques sont présentés pour valider les résultats théoriques obtenus / In a highly competitive economic environment, maintenance of production facilities is a crucial socio-economic challenge for companies. Similarly, maintenance issues experienced significant changes, the sector is changing. Faced with this, the expectations, the needs of cost, time, quality and environmental change. Following this, we wanted to develop in this thesis new integrated strategies for maintenance, production, and inventory management of spare parts taking into account different operational constraints. These constraints include the change in the rate of production systems and its impact on the deterioration of the production system and on the maintenance plan and spare parts management. It was also interested in the origin and type of spare parts (new or used) used to ensure maintenance activities. In addition to the technical and economic influence of the origin of spare parts used in the production system, we also evaluated the environmental impact of the latter considering ADEME data. Formally, The aim of this thesis is to contribute by formal approaches to optimization of production rates coupled with maintenance policies and integrating efficient strategies in the management of spare parts. Analytical methods and optimization techniques, supported by simulation models according to resolutions of difficulty have been developed to achieve the objectives of this thesis. An industrial case studies and numerical examples are presented to validate theoretical results