Condition monitoring of a steam turbine generator using wavelet spectrum based control chart

Abstract

Condition-based maintenance (CBM) is designed to take maintenance actions only when there is an imminent evidence of failure for a monitoring system. The parameters indicating health status of the system are continuously monitored in CBM. This article proposes a condition monitoring scheme based on energy profiles generated from wavelet spectrum analysis. The energy of time series is represented by a wavelet spectrum in scale representations of signals. After deriving wavelet spectrums using a discrete wavelet transform at pre-specified windows, we aim to monitor the system based on multivariate T2 chart for the parameters in the linear energy profiles. The monitoring scheme is applied to temperature signals measured from a steam turbine generator. The proposed T2 chart based on the energy profiles shows a potential in early detecting the abnormality of a monitoring system which is not clearly detectable in original time scales.