Neural network model for prognostic as a service in private cloud computing

International audiencePrognostic and health management (PHM) systems are designed to predict impending faults and to determine remaining useful life of machinery. An efficient prognostic system can speed up fault diagnosis by providing an indication of what parts of the machinery are most likely to fail and will need maintenance in the near future. PHM systems for manufacturing industry have not been widely implemented despite the extensive research on PHM in academia, which is mostly due to high costs in both development and implementation of PHM solutions in industrial applications. In this paper, we are defined the predictive maintenance, prognostic and health management (PHM) architecture and present the state of the art of prognostic approaches and display the related works in this domain. After that, we are proposed a new approach that is adapting cloud computing paradigm with PHM systems that is Prognostic as a Service to provide high readiness, easy-to-configure, low cost and ondemand PHM services. We had presented our obtained results and its simulatio