Dynamic fault prognosis for multivariate degradation process

Abstract

Abstract Stochastic characteristics of degradation process provides a great challenge for multi-step fault prognosis. Prediction accuracy is a key feature for multivariable time series in the degradation process. In order to achieve good prediction accuracy, it is necessary to take time varying feature of time series into consideration. This paper develops a dynamic multi-step fault prognosis approach for the multivariable time series in degradation process. Firstly, a time varying dynamic model is established via multivariable phase space reconstruction (PSR) method. Then a hybrid algorithm combining iterative dynamic least square-support vector regression (LS-SVR) method and moving window mechanism is proposed for multi-step degradation evolution prediction before fault happening. Finally, a comparative case study on fault prognosis is provided to validate the effectiveness and the feasibility of the proposed algorithms.