Estimation of the Remaining Useful Life by using Wavelet Packet Decomposition and HMMs

This paper deals with an estimation of the Remaining Useful Life of bearings based on the utilization of the Wavelet Packet Decomposition (WPD) and the Mixture of Gaussians Hidden Markov Models (MoG-HMM). The raw data provided by the sensors are first processed to extract features by using the wavelet packet decomposition. This latter provides a more flexible way of time-frequency representation and filtering of a signal, by allowing the use of variable sized windows and different detail levels. The extracted features are then fed as inputs of dedicated learning algorithms in order to estimate the parameters of a mixture of Gaussian Hidden Markov Model. Once this learning phase is achieved, the generated model is exploited during a second phase to continuously assess the current health state of the physical component and to estimate its remaining useful life with the associated confidence value. The proposed method is tested on a benchmark data taken from the “NASA prognostic data repository” related to several bearings´. Bearings are chosen because they are the most used and also the most faulty mechanical element in some industrial systems and process. Furthermore, the method is compared to a traditional time-feature prognostic and some simulation results are given at the end of the paper.