This PhD project will focus on developing, evaluating, and demonstrating a framework of novel hybrid prognostics solution for selected system use case (e.g. clogging filter, linear actuator, lithium-ion batteries, rotating machinery, aircraft fuel system, APU, and electrical power generation system). A comprehensive test-bed for in-depth studies will be used for experiments for demonstration and evaluation. Prognostics is an essential part of condition-based maintenance (CBM), described as predicting the remaining useful life (RUL) of a system. It is also a key technology for an integrated vehicle health management (IVHM) system that leads to enhance safety, reliability, maintainability and readiness. Generally, prognostics models can be broadly categorised into experience-based models, data-driven models and physics-based models. More recently, hybrid prognostics approaches have been presented, attempting to leverage the advantages of combining the prognostics models in the aforementioned different categories for a better capability of managing the uncertainty related to system complexity and data availability to achieve more accurate RUL estimations