Design of a feature extraction and a fault classifier system using data mining techniques. T4Liikkudia. Version 1.0.1

Mikko Hiirsalmi

Research output: Book/ReportReport

Abstract

We have addressed the issue of how to create better classifiers to detect different failure types of a hydraulic cylinder drive based on a set of temporal measurements of key aspects of the system. We have shown that one should try to discover a compact set of feature extractors to identify key differences between the time series prevailing during the different fault conditions. In a case study we have created feature extractors and classifiers for a test case by using visual data mining to learn about the measurements and to discover the differences between the measurement signals. The results show a clear improvement on the classification results previously achieved by using a different set of feature extractors called statistical windows.
Original languageEnglish
PublisherVTT Technical Research Centre of Finland
Number of pages16
Publication statusPublished - 2005
MoE publication typeD4 Published development or research report or study

Publication series

SeriesVTT Information Technology. Research Report
NumberTTE1-2005-29

Fingerprint Dive into the research topics of 'Design of a feature extraction and a fault classifier system using data mining techniques. T4Liikkudia. Version 1.0.1'. Together they form a unique fingerprint.

Cite this