Online Reliability Estimation of Physical Systems Using Neural Networks and Wavelets

Abstract

Individual component reliability can often be estimated from degradation signals. In this paper, we examine the utility of the wavelet transform in preprocessing degradation signals for online reliability estimation. Wavelet preprocessing facilitates examination of degradation signals in both the time- and frequency-domains, simultaneously. Neural networks are used for forecasting the degradation signals (or a transformation thereof) and estimating the likelihood that these signals would exceed a predetermined critical plane representative of unit failure in the immediate future. This leads to an online estimate for individual unit reliability. The proposed method is applied for analyzing degradation signals collected from avertical CNC drilling machine using drill bits. The degradation signals, force and torque, were collected as the drill bits were destructively tested.