Edwin Lughofer, Erich Klement, Luigi del Re, Hajrudin Efendic,
"Filtering of Dynamic Measurements in Intelligent Sensors for Fault Detection based on Data-Driven Models"
: Proceedings IEEE CDC --- IEEE CDC Conference, Maui, Hawaii, Seite(n) 463-468, 12-2003
Original Titel:
Filtering of Dynamic Measurements in Intelligent Sensors for Fault Detection based on Data-Driven Models
Sprache des Titels:
Englisch
Original Buchtitel:
Proceedings IEEE CDC --- IEEE CDC Conference, Maui, Hawaii
Original Kurzfassung:
Increasing complexity of test benches and the widespread use of automatic calibration and optimization tools leads to tighter requirements on the data quality. For many applications, like engine test benches, there are too few
physical information a priori to allow the use of classical fault detection methods. In this paper, we propose a structure which has been developed and tested for engine test benches, in which data-driven models are built
dynamically from measurements and fault detection is carried out by using data-driven models as reference situation. To improve the performance of
fault detection statements, i.e. increasing the detection rate while decreasing or at least not worsening the overdetection rate, and hence to improve the efficiency of the overall system, signal analysis algorithms in
intelligent sensors are applied to detect or even eliminate, i.e. filter disturbances such as peaks or drifts in the dynamic signals. The verification of the impact of filtering on fault detection statements due to
real-life engine test bench measurements is presented at the end of the paper.
Sprache der Kurzfassung:
Deutsch
Seitenreferenz:
463-468
Erscheinungsmonat:
12
Erscheinungsjahr:
2003
Anzahl der Seiten:
6
Notiz zur Publikation:
Authors: Edwin Lughofer, Hajrudin Efendic, Luigi Del Re, Erich Peter Klement, Johannes Kepler University Linz