In this paper, novel methods for performing condition monitoring for power station turbine shafts are presented. The objective of this work is to investigate methods for producing accurate turbine vibration fault alarms during turbine shaft rundowns. Wavelet packet analysis is employed to extract spectral features from healthy vibration signals and the probability density functions of these features are estimated. Both Gaussian models, using Bayesian inferencing, and mixture models are employed. Preliminary results show that the more computationally expensive mixture models produce more accurate density estimates and hence more reliable fault alarms.