Analysis of reliability data plays an important role in the maintenance decision making process. The accurate estimation of residual life in components and systems can be a great asset when planning the preventive replacement of components on machines. Artificial intelligence is a field that has rapidly developed over the last twenty years and practical applications have been found in many diverse areas. The use of such methods in the maintenance field have however not yet been fully explored. With the common availability of condition monitoring data, another dimension has been added to the analysis of reliability data. Neural networks allow for explanatory variables to be incorporated into the analysis process. This is expected to improve the quality of predictions when compared to the results achieved through the use of methods that rely solely on failure time data. Neural networks can therefore be seen as an alternative to the various regression models, such as the proportional hazards model, which also incorporate such covariates into the analysis. For the purpose of investigating their applicability to the problem of predicting the residual life of machines and components, neural networks were trained and tested with the data of two different reliability related datasets. The first dataset represents the renewal case where repair leads to complete restoration of the system. A typical maintenance situation was simulated in the laboratory by subjecting a series of similar test pieces to different loading conditions. Measurements were taken at regular intervals during testing with a number of sensors which provided an indication of the test piece’s condition at the time of measurement. The dataset was split into a training set and a test set and a number of neural network variations were trained using the first set. The networks’ ability to generalize was then tested by presenting the data from the test set to each of these networks. The second dataset contained data collected from a group of pumps working in a coal mining environment. This dataset therefore represented an example of the situation encountered with a repaired system. The performance of different neural network variations was subsequently compared through the use of cross-validation. It was proved that in most cases the use of condition monitoring data as network inputs improved the accuracy of the neural networks’ predictions. The average prediction error of the various neural networks under comparison varied between 431 and 841 seconds on the renewal dataset, where test pieces had a characteristic life of 8971 seconds. When optimized the multi-layer perceptron neural networks trained with the Levenberg-Marquardt algorithm and the general regression neural network produced a sum of squares error within 11.1% of each other for the data of the repaired system. This result emphasizes the importance of adjusting parameters, network architecture and training targets for optimal performance The advantage of using neural networks for predicting residual life was clearly illustrated when comparing their performance to the results achieved through the use of the traditional statistical methods. The potential of using neural networks for residual life prediction was therefore illustrated in both cases. / Dissertation (MEng (Mechanical Engineering))--University of Pretoria, 2007. / Mechanical and Aeronautical Engineering / MEng / unrestricted

La gestion de la continuité des opérations est un cadre complet visant à éviter que les événements perturbateurs n’affectent les opérations commerciales, à rétablir rapidement les activités et à réduire les dommages potentiels correspondants pour les systèmes énergétiques, tels que les centrales nucléaires. Cette thèse propose des discussions sur les aspects suivants: développement de méthodes appropriées d'évaluation des risques afin d'intégrer les données de surveillance de l'état et les données d'inspection pour une mise à jour et des pronostics robustes et en temps réel du profil de risque. Pour tenir compte de l'incertitude des données de surveillance de l'état, un modèle de mélange gaussien de Markov caché est développé pour modéliser les données de surveillance de l'état. Un réseau bayésien est appliqué pour intégrer les deux sources de données. Pour améliorer l'applicabilité de la continuité des opérations dans la pratique, les variables variant dans le temps considèrent l'indice de continuité des opérations, par ex. la dégradation des composants, les revenus en fonction du temps, etc. sont pris en compte dans le processus de modélisation de la continuité des activités. Sur la base de l'indice de continuité d'activité proposé, une méthode d'optimisation conjointe prenant en compte toutes les mesures de sécurité dans le processus d'évolution des événements, y compris les étapes de prévention, d'atténuation, d'urgence et de récupération, est développée pour améliorer la continuité des opérations du système avec des ressources limitées. Les méthodologies proposées sont appliquées aux centrales nucléaires contre les événements perturbateurs. / Business continuity management is a comprehensive framework to prevent the disruptive events from impacting the business operations, quickly recovering business and reducing the corresponding potential damages for energy system, such as nuclear power plants (NPPs). This dissertation provides discussions on the following aspects: developing appropriate risk assessment methods in order to integrate condition monitoring data and inspection data for a robust and real-time risk profile updating and prognostics. To account for the uncertainty of condition monitoring data, a hidden Markov gaussian mixture model is developed to model the condition monitoring data. A Bayesian network is applied to integrate the two data sources. For improving applicability of business continuity in practice, time-variant variables regard business continuity index, e.g. component degradation, time-dependent revenue, etc are taken into consideration in the business continuity modelling process. Based on the proposed business continuity index, a joint optimization method considering all the safety measures in event evolvement process including prevention stage, mitigation stage, emergency stage and recovery stage is developed to enhance system business continuity under limited resources. The proposed methodologies are applied to NPP against disruptive event.