Prognostics and Health Management (PHM) is a discipline that focuses on degradation mechanisms of systems in order to estimate their health states, anticipate their failures and optimize their maintenance.

It uses methods, tools and algorithms for condition monitoring, anomaly detection, fault diagnostics, remaining useful life prediction and decision support for maintenance optimization. It allows to continuously monitor the health state of systems and to provide operators and managers with relevant information to decide on actions to be taken to maintain the system in optimal operational conditions.

Scientific developments in the field of PHM can be grouped into three main approaches: data-driven, model-based (or physics-based) and hybrid approaches. This presentation reviews these approaches gives some examples of realizations and makes the link between PHM and maintenance, especially condition-based and predictive maintenance.

Speaker: Kamal Medjaher, Prof. , National School of Engineering in Tarbes, France
Dr. Kamal Medjaher received the M.S. degree in control and industrial computing from Ecole Centrale de Lille, in 2002, and the Ph.D. degree in the same discipline from University of Lille 1, Villeneuve-d’Ascq, France, in 2005. Dr. Medjaher is a Professor at National School of Engineering in Tarbes, France. His research topics include condition monitoring, anomaly detection, fault diagnostics & prognostics. He is co-author of more than 50 journal papers, and a leader of 8 research projects.

свернуть