Degradation data-driven approach for remaining useful life estimation

Abstract

Remaining useful life (RUL) estimation is termed as one of the key issues in prognostics and health management (PHM). To achieve RUL estimation for individual equipment, we present a degradation data-driven RUL estimation approach under the collaboration between Bayesian updating and expectation maximization (EM) algorithm. Firstly, we utilize an exponential-like degradation model to describe equipment degradation process and update stochastic parameters in the model via Bayesian approach. Based on the Bayesian updating results, both probability distribution of the RUL and its point estimation can be derived. Secondly, based on the monitored degradation data to date, we give a parameter estimation approach for non-stochastic parameters in the degradation model and prove that the obtained estimation is unique and optimal in each iteration. Finally, a numerical example and a practical case study for global positioning system (GPS) receiver are provided to show that the presented approach can model degradation process and achieve RUL estimation effectively and generate better results than a previously reported approach in literature.