PhD in Framework for Novel Hybrid Prognostics System in Cranfield United Kingdom | Cranfield University

This doctoral research will concentrate on creating, assessing, and showcasing an innovative hybrid prognostics framework for specific system applications (such as clogged filters, linear actuators, lithium-ion batteries, rotating equipment, aircraft fuel systems, auxiliary power units, and electrical power generation systems). An extensive experimental setup will facilitate thorough investigations for validation and assessment purposes.
Prognostics serves as a critical component of condition-based maintenance (CBM), defined as forecasting a system's remaining operational lifespan (RUL). It also represents fundamental technology for comprehensive vehicle health management (IVHM) systems, contributing to improved safety, dependability, serviceability, and operational preparedness. Typically, prognostics methodologies can be divided into three main groups: experience-based approaches, data-driven techniques, and physics-based models. In recent developments, combined prognostics strategies have emerged, seeking to capitalize on the strengths of integrating these different model types to better handle uncertainties stemming from system complexity and data limitations, ultimately yielding more precise RUL predictions