Machine vision systems combined with classification algorithms are being increasingly used for different applications in the age of automation. One such application would be the quality control of the painted automobile parts. The fundamental elements of the machine vision system include camera, illumination, image acquisition software and computer vision algorithms. Traditional way of thinking puts too much importance on camera systems and ignores other elements while designing a machine vision system. In this thesis work, it is shown that selecting an appropriate illumination for illuminating the surface being examined is equally important in case of machine vision system for examining specular surface. Knowledge about the nature of the surface, type and properties of the defect to be detected and classified are important factors while choosing the illumination system for the machine vision system. The main illumination system tested were bright field, dark field and structured illumination and out of the three, dark field and structured illumination gave best results. This thesis work proposes a dark field illumination based machine vision system for fault detection on specular painted surface. A single layer Artificial Neural Network model is employed for the classification of defects in intensity images of painted surface acquired with this machine vision system. The results of this research work proved that the quality of the images and size of data set used for training the Neural Network model play a vital role in the performance of the classifier algorithm.

The majority of condition monitoring techniques employed today consider the acquisitioning and analysis of structural responses as a means of profiling machine condition and performing fault detection. Modern research and newer technologies are driving towards non-contact and non-invasive methods for better machine characterisation. In particular, unshrouded rotors which are exposed to a full field of fluid interaction such as helicopter rotors and wind turbines, amongst others, benefit from such an approach. Current literature lacks investigations into the monitoring and detection of anomalous conditions using fluid dynamic behaviour. This is interesting when one considers that rotors of this nature are typically slender, implying that their structural behaviour is likely to be dependent on their aerodynamic behaviour and vice versa. This study sets out to investigate whether a seeded rotor fault can be inferred from the flow field. Studies of this nature have the potential to further a branch of condition monitoring techniques. It is envisaged that successful detection of rotor anomalies from the flow field will aid in better distinction between mass and aerodynamic imbalances experienced by rotor systems. Furthermore, the eventual goal is to better describe the adjustments made to helicopter rotor systems when performing rotor track and balance procedures. Time-dependent fluid dynamic data is numerically simulated around a helicopter tail rotor blade using URANS CFD with the OpenFOAM software package. Pressures are probed at locations in the field of the rotor and compared to results attained in an experimental investigation where good correlation is seen between the results. A blade is modelled with a seeded fault in the form of a single blade out of plane by 4°. Comparisons are drawn between the blade in its ‘healthy’ and ‘faulty’ configuration. It is observed that the fault can be detected by deviations in the amplitudes of the pressure signals for a single revolution at the probed locations in the field. These deviations manifest as increases in the frequency spectrum at frequencies equivalent to the rotational rate (1 per revolution frequencies). The results described are assessed for their fidelity when the pressure is probed at different locations in the domain of the rotor. Deviations in the pressure profiles over the surface of the blades are also seen for the asymmetric rotor configuration but may prove too sensitive for practical application. / Dissertation (MEng)--University of Pretoria, 2019. / Mechanical and Aeronautical Engineering / MEng / Unrestricted

Les machines à commutation de flux cinq-phases présentent une tolérance aux pannes et une robustesse qui les rendent très intéressantes dans un point de vue de la fiabilité, comme montré dans le premier chapitre.Dans ces travaux de thèse nous avons explorés la possibilité de détecter les défauts qui affectent cette machine par la signature des vibrations générées dans la machine.En utilisant les outils physiques et mathématiques présentés dans le deuxième chapitre, nous avons construit deux modèles multiphysiques, un modèle aux les éléments finis développé dans le troisième chapitre et un modèle analytique, appelé aux réseaux de perméances, dans le quatrième chapitre.Le comportement vibratoire de la machine a été étudié à l'aide de ces deux modèles, en régimesain et en défaut afin de connaitre comment ce comportement est influencé par les grandeurs électriques et magnétiques de la machine.Par ailleurs nous avons étudié la possibilité de détecter et discriminer les différents types de défauts.Le modèle analytique se présente comme un bon estimateur du comportement en défaut de la machine, malgré ses écarts avec la simulation.Dans le cinquième chapitre, les deux modèles multiphysiques ont été validés par des essais expérimentaux et nous avons pu expliquer le comportement en défaut d’un point de vue mécanique plutôt que magnétique.Enfin, dans le sixième chapitre, nous avons utilisé les deux modèles pour étudier le comportement en défaut de la machine, à des vitesses au-dessus de la limite expérimentale (3100 tr/min). / Five-phase flux switching machines have a fault tolerance and robustness that makes them very interesting from the point of view of reliability, as shown in chapter one of this work. In our studies we have explored the possibility of detecting faults that affect this type of machine using the signature of stator vibrations.Using the physical and mathematical tools presented in chapter two, we improved two multyphisics models, one based on finite elements method that it's presented in chapter three and the seconde one analitycal model, called permeance networks, in chapter four. The vibratory behavior of the machine was studied using these two models, under healthy and faulty conditions, in order to know how this behavior is influenced by the electrical and magnetic magnitudes of the machine. In addition, we have studied the possibility of detecting and discriminating different types of faults. Analytical model is a good estimator of fault behavior of the machine, despite its differences with the simulation.In chapter five, the two multiphysical models have been validated by experimental tests and we have been able to explain fault behavior by mechanical origin rather than magnetic origin.Finally, in chapter six, we used both models to study the fault behavior of the machine, at speeds above the experimental limit (3100 rpm).

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

One of the crucial challenges for Data Center (DC) operation is inefficient thermal management which leads to excessive energy waste. The information technology (IT) equipment and cooling systems of a DC are major contributors to power consumption. Additionally, failure of a DC cooling system leads to higher operating temperatures, causing critical electronic devices, such as servers, to fail which leads to significant economic loss. Improvements can be made in two ways, through (1) better design of a DC architecture and (2) optimization of the system for better heat transfer from hot servers. Row-based cooling is a suitable DC configuration that reduces energy costs by improving airflow distribution. Here, the IT equipment is contained within an enclosure that includes a cooling unit which separates cold and back chambers to eliminate hot air recirculation and cold air bypass, both of which produce undesirable airflow distributions. Besides, due to scalability, ease of implementation, and operational cost, row-based systems have gained in popularity for DC computing applications. However, a general thermal model is required to predict spatiotemporal temperature changes inside the DC and properly apply appropriate strategies. As yet, only primitive tools have been developed that are time-consuming and provide unacceptable errors during extrapolative predictions. We address these deficiencies by developing a rapid, adaptive, and accurate hybrid model by combining a DDM and the thermofluid transport relations to predict temperatures in a DC. Our hybrid model has low interpolative prediction errors below 0.7 oC and extrapolative errors less than one half of black-box models. Additionally, by changing the studied DC configuration such as cooling unit fans and severs locations, there are a few zones with prediction error more than 2 oC. Existing methods for cooling unit fault detection and diagnosis (FDD) are designed to successfully overcome individually occurring faults but have difficulty handling simultaneous faults. We apply a gray-box model involves a case study to detect and diagnose cooling unit fan and pump failure in a row-based DC cooling system. Fast detection of anomalous behavior saves energy and reduces operational costs by initiating remedial actions. Cooling unit fans and pumps are relatively low-reliability components, where the failure of one or more components can cause the entire system to overheat. Therefore, appropriate energy-saving strategies depend largely on the accuracy and timeliness of temperature prediction models. We used our gray-box model to produce thermal maps of the DC airspace for single as well as simultaneous failure conditions, which are fed as inputs for two different data-driven classifiers, CNN and RNN, to rapidly predict multiple simultaneous failures. Our FDD strategy can detect and diagnose multiple faults with accuracy as high as 100% while requiring relatively few simultaneous fault training data samples. / Thesis / Candidate in Philosophy