Machine diagnostics is usually done via conditioned monitoring (CM). This approach analyses certain thresholds or patterns for diagnostic purposes. This approach can be costly and time consuming for industries. A larger downside is the difficulty in generalizing CM to a wider set of machines.There is a new trend of using a Machine learning (ML) approach to diagnose machines states. An ML approach would implement an autonomous system for diagnosing machines. It is highly desirable within industry to replace the manual labor performed when setting up CBM systems. Often the ML algorithms chosen are novelty/anomaly based. It is a popular hypothesis that detecting anomalous measurements from a system is a natural byproduct of a machine in a faulty state.The purpose of this thesis is to help CombiQ with an implementation strategy for a fault detection system. The idea of the fault detection system is to make prediction outcomes for machines within the system. More specifically, the prediction will inform whether a machine is in a faulty state or a normal state. An ML approach will be implemented to predict anomalous measurements that corresponds to a faulty state. The system will have no previous data on the machines. However, data for a machine will be acquired once sensors (designed by CombiQ) have been set up for the machine.The results of the thesis proposes an unsupervised and semi-supervised approach for creating the ML models used for the fault detection system. The unsupervised approach will rely on assumptions when selecting the hyperparameters for the ML. The semi-supervised approach will try to learn the hyperparameters through cross validation and grid search. An experiment was set up check whether three ML algorithms can learn optimal hyperparameter values for predicting rotational unbalance. The algorithm known as OneClassVM showed the best precision results and hence proved more useful for CombiQ’s criterium.

Submitted by Lucienne Costa (lucienneferreira@ufcg.edu.br) on 2018-04-12T17:33:48Z No. of bitstreams: 1 PAULO VICTOR DA SILVA OLINDA – DISSERTAÇÃO (PPGEM) 2018.pdf: 4406932 bytes, checksum: 3015875e87b33898358c6dc22f3c9e3a (MD5) / Made available in DSpace on 2018-04-12T17:33:48Z (GMT). No. of bitstreams: 1 PAULO VICTOR DA SILVA OLINDA – DISSERTAÇÃO (PPGEM) 2018.pdf: 4406932 bytes, checksum: 3015875e87b33898358c6dc22f3c9e3a (MD5) Previous issue date: 2018-02-21 / Capes / O objetivo deste trabalho foi realizar um estudo termográfico visando constatar falha de montagem por desalinhamento em acoplamento flexível do tipo garra, modelo GR 50. A metodologia da pesquisa pode ser caracterizada como do tipo aplicada, quantitativa, explicativa, bibliográfica e experimental. Para tanto, montou-se uma bancada experimental contendo um motor trifásico, eixos, rolamentos e o acoplamento flexível, sem a presença de cargas, destinado a solidarizar dois eixos contendo desalinhamentos entre eles de 0,5; 0,74 e 1,18 mm. Como resultado dos testes efetuados, foi possível perceber que a temperatura do acoplamento aumenta à mesma proporção dos desalinhamentos inseridos, ou seja, quanto maior o desalinhamento, maior a temperatura registrada. Este fato é melhor observado nos primeiros 20 minutos dos testes. Diante destes resultados é possível afirmar que a Termografia pode ser utilizada como técnica de detecção de falhas de montagem por desalinhamento nos primeiros minutos de funcionamento do sistema. / The aim of this work is to perform a thermographic study aiming to verify assembly failure by mounting in flexible claw type coupling, model GR 50. A research methodology can be characterized as applied, quantitative, explanatory, bibliographic and experimental type. For this, an experimental bench was built, containing a three-phase motor, shafts, bearings and the flexible coupling, without a load presence, to join two shafts with misalignments between them; 0.5, 0.74 and 1.18 mm. As a result of the tests performed, it was possible to notice that the temperature of the coupling increases the same proportion of the misalignments inserted, that is, the greater the misalignment, the higher the temperature recorded. This fact is best observed in the first 20 minutes of the tests. In view of these results, it is possible to affirm that the thermography can be used as a technique for detecting mounting faults by misalignment in the first minutes of the system operation.