Fleet Prognosis with Physics-informed Recurrent Neural Networks

Predictive models for component distress are important for companies working with services and warranties of large fleets of engineering assets (e.g., airplanes, jet engines, wind turbines, etc.). Unfortunately, factors such as duty cycle variation, harsh environments, inadequate maintenance, and manufacturing problems can lead to large discrepancies between designed and observed component lives. This paper introduces a novel physics-informed neural network approach to prognosis by extending recurrent neural networks to cumulative damage models. We propose a new recurrent neural network cell designed to merge physics-informed and data-driven layers. With that, engineers and scientists can use physics-informed layers to model parts that are well understood (e.g., fatigue crack growth) and use data-driven layers to model parts that are poorly characterized (e.g., internal loads). A fatigue crack growth test problem is used to present the main features of the proposed recurrent neural network. The results demonstrate that our physics-informed neural network is able to accurately model fatigue crack growth.