Resumen de A Review of Hybrid Prognostics Applicationsfor Power & Energy Systems
Jose Ignacio Aizpurua Unanue, Jokin Alcibar Ibarzabal, Ibai Ramirez García, Ekhi Zugasti Uriguen, Joel Pino Gómez
Prognostics is the ability to acquire knowledge about events before they occur. In industrialsettings, prognostics primarily revolves around predicting the remaining useful life (RUL) ofassets. Data-driven (DD) prognostics models capture complex fault-to-failure dynamics butlack of explicability in predictions. Physics-based models make use of physics-of-failure modelsto predict RUL, albeit at the expense of reduced accuracy compared to DD models. In thiscontext, hybrid prognostics models combine both data-driven and physics-based approachesto enhance accuracy and explicability of results. This paper reviews authors’ experience in thedevelopment of hybrid prognostics solutions applied to power and energy assets.
