A Probabilistic Similarity Based Modeling Approach for Turbomachine Fault Prediction

Abstract

Faults in the critical components of a turbomachine usually result in unplanned outage, leading to huge loss of properties and life. Condition monitoring becomes a promising tool to provide automatic early alerting of potential damage in critical components thus ensuring the system safety and reliability while lowering its maintenance cost. This is still a challenging hot topic due to the data imperfection and multivariate correlation, as well as the variation of faults and components in different turbomachines. This paper presents an enhanced generic probabilistic similarity-based method to address these challenges in fault prediction of large turbomachines. Bayesian wavelet multi-scale decomposition is proposed to address the potential noise in the sensed multivariate time historical data. The advanced signal processing balances the over-denoising and under-denoising of raw multivariate signals. An optimized auto-associative kernel regression (OAKR) approach is developed to represent the healthy status of the turbomachine system and further predict its responses under unknown status. The band width of the kernel function in the method is optimized through Nelder-Mead simplex algorithm. The alerting threshold based on the squared mean errors of the predicted and measured time series is adjusted automatically through a rolling window strategy. A comparison study is conducted to demonstrate the effectiveness and feasibility of the proposed methodology by using the real-world data and events collected from a centrifugal compressor.