Thomas W. Rauber

Learn More
An essential research objective in artificial vision are shape &sct ip to~ which are invariant for mslation, scale changes and rotations of a bidimensional pattem. k varjety of approaches has proved the capacity to characterize forms, like signatutes, 1-D Fourier descriptors, moment invariants, Complex-log (Log-polar) a m s f o m or Fourier ~lrmsfonn. None(More)
We present a generic procedure for diagnosing faults using features extracted from noninvasive machine signals, based on supervised learning techniques to build the fault classifiers. An important novelty of our research is the use of 2000 examples of vibration signals obtained from operating faulty motor pumps, acquired from 25 oil platforms off the(More)
We extend the visualization technique of highdimensional patterns conceived by Sammon to the case when the patterns have been previously mapped to an implicitly defined Hilbert feature space in which distances can be measured by kernels. The principal benefit of our technique is the possibility to gain insight into the distribution of the patterns, even in(More)
This paper presents vibration analysis techniques for fault detection in rotating machines. Rolling element bearing defects inside a motor pump are the subject of study. Signal processing techniques, like frequency filters, Hilbert transform, and spectral analysis are used to extract features used later as a base to classify the condition of machines. Also,(More)
This paper presents the results achieved by fault classifier ensembles based on supervised learning for diagnosing faults on oil rigs motor pumps. The main goal is to apply two feature-based ensemble construction methods to a real-world problem. Recent studies have shown that the use of ensembles of classifiers that are accurate and at the same time have(More)