Research Summary:

In the era of smart manufacturing and industrial internet of things (IoT), there is a high global demand and strategic urgency for development of novel and innovative smart and reliable prognostic health management (PHM) technologies to cope with maintenance development tasks of complex industrial and safety-critical systems.
Prognostic health management is an enabling discipline in industrial engineering that monitors the reliability of complex engineering infrastructure with the objective of improving maintenance effectiveness, safe operability, and enhanced performance. The focus of the PHM is centered on two core dimensions; the first is taking into account the behavior and the evolution over time of a fault once it occurs, while the second one aims at estimating/predicting the remaining useful life (RUL) during which a device can perform its intended function.
My research has spanned several areas with the goal of developing new theories and methodologies for PHM algorithms, strategies, and techniques. Degradation modeling and RUL estimation algorithms along with machine learning form the mainstream of my research. Recent catastrophic incidents, such as the collapse of Morandi bridge and the Gulf of Mexico oil spill disaster, occurred mainly due to a lack of proper PHM considerations resulting in considerable loss of human lives as well as serious/major environmental damages. Such accidents and many others could have been prevented if proper maintenance procedures were implemented. All those events coupled with aging critical infrastructures call for an urgent quest to design advanced and innovative prognostic solutions to efficiently utilize multi-sensor streaming data sources

 Interests:

- Machine Learning and its applications in PHM
- Degradation Modeling
- Prognostics and RUL Estimation Algorithms of an asset.
- Prognostics and Health Management (PHM) and its applications
- Fault Diagnosis and Failure Prognosis of a dynamical system
- Predictive Analytics