Physics-informed neural networks for corrosion-fatigue prognosis

Abstract

In this paper, we present a novel physics-informed neural network modeling approach for corrosion-fatigue. The hybrid approach is designed to merge physics-informed and data-driven layers within deep neural networks. The result is a cumulative damage model where the physics-informed layers are used to model the relatively well-understood physics (crack growth through Paris law) and the data-driven layers account for the hard to model effects (damage bias due to corrosion). A numerical experiment is used to present the main features of the proposed physics-informed recurrent neural network for damage accumulation. The test problem consists of predicting corrosion-fatigue of an Al 2024-T3 alloy used on fuselage panels of aircraft wings. Besides cyclic loading, the panels are also subjected to saline corrosion (3.5% solution of sodium chloride, emulating coastal exposure). The physics-informed neural network is trained using full observation of inputs (far-field loads, stress ratio and a corrosion index for environment corrosivity defined by airport) and very limited observation of outputs (crack length at inspection for only a small portion of the fleet). We then address the following question: Is the physics-informed neural network able to properly compensate corrosion effects on fatigue damage accumulation? Results demonstrate that our proposed framework is able to accurately compensate for damage bias due to the lack of corrosion modeling in the mechanical fatigue model. Additionally, results indicate that corrosion plays a drastic role in crack propagation significantly reducing useful life.