This EPSRC funded PhD is aligned with a major EPSRC funded research on early wear detection being conducted at the national centre for advanced tribology at Southampton (nCATS). The project would be in collaboration with the Engineering Department at City, University of London. Heavy machines use numerous tribology based systems and the onset of wear within these systems is the main reason why they are made unavailable for use. This decay/damage is typically a result of multiple mechanisms occurring simultaneously and the evolution is poorly understood. This project will develop compound degradation modelling within heavy machines in partnership with Shell, GE Aviation, Schaeffler and Senseye. It will aim to provide predictive capabilities of remaining useful life (RUL) of systems. The research will start with existing physics and materials based models of multiple degradation modes and develop a framework to model the interaction between the different modes of degradations. This compound degradation model will also incorporate uncertainties involved to support the RUL prediction. Such modelling would be validated by experiments on tribometers and real engineering systems using wear sensor arrays with embedded electronics that will allow far better spatial and temporal resolution of tribological contact decay mechanisms (surface, subsurface and lubricant). Data and model outputs would be fed into machine learning algorithms for robust trend recognition and life prediction. This dual site PhD would allow research to be conducted at both Southampton and City Universities.