Fusion of Gaussian Process Kernel Regressors for Fault Prediction in Intelligent Energy Systems

Integration of energy systems with machine intelligence technologies advances the new generation of intelligent energy systems. One feature of intelligent energy systems is their ability to predict a future fault state (prognosis), and thus support control actions. This paper introduces a prognostic framework based on concepts originating from the machine learning universe and proceeds to assess the performance of the prognostics algorithms with statistical methods aiming to formulate a linear predictor whose coefficients are the solution of a multi-objective optimization problem. Prediction is achieved through independent Gaussian process kernel regressors put together as terms of a linear forecaster. In this novel framework the available data is used to train the regression models whose degradation predictions cover a predetermined time period and have the form of a predictive distribution whose mean and variance values are computed for future moments. Thus, given the observed data points one may search for the most probable values of other quantities of interest, or the values at different points from those measured. The feasibility of the cascading prognostics methodology is demonstrated via a turbine blade degradation example. This implementation is characterized by advantages that include the utilization of an optimization process that simultaneously determines the lowest possible values in a set of different statistical measures and the employment of a set of kernels for modeling various data features and capturing the system dynamics.