Physics-Informed Neural Networks for Corrosion-Fatigue Prognosis

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 (bias in damage accumulation 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 panels of aircraft wing. Besides cyclic loading, the panels are also subjected to saline corrosion. The physics-informed neural network is trained using full observation of inputs (far-field loads, stress ratio and a corrosivity index – defined per airport) and very limited observation of outputs (crack length at inspection for only a small portion of the fleet). Results show that the physics-informed neural network is able to learn the correction in the original fatigue model due to corrosion and predictions are accurate enough for ranking damage in different airplanes in the fleet (which can be used to prioritizing inspection).

[1]  P. R. Underhill,et al.  Fatigue crack growth from corrosion damage in 7075-T6511 aluminium alloy under aircraft loading , 2003 .

[2]  Felipe A. C. Viana,et al.  Fleet Prognosis with Physics-informed Recurrent Neural Networks , 2019, Structural Health Monitoring 2019.

[3]  J. Schijve,et al.  A standardized load sequence for flight simulation tests on transport aircraft wing structures , 1973 .

[4]  Gabriele M. T. D'Eleuterio,et al.  Synthesis of recurrent neural networks for dynamical system simulation , 2015, Neural Networks.

[5]  Gian Antonio Susto,et al.  Machine Learning for Predictive Maintenance: A Multiple Classifier Approach , 2015, IEEE Transactions on Industrial Informatics.

[6]  Mathew J. Palakal,et al.  Comparative Study of Corrosion-Fatigue in Aircraft Materials , 2001 .

[7]  Trevor C. Lindley,et al.  Fatigue-crack initiation at corrosion pits , 1982 .

[8]  Sankaran Mahadevan,et al.  Damage tolerance approach for probabilistic pitting corrosion fatigue life prediction , 2001 .

[9]  Andrew W. Senior,et al.  Long short-term memory recurrent neural network architectures for large scale acoustic modeling , 2014, INTERSPEECH.

[10]  Bin Liang,et al.  Remaining useful life prediction of aircraft engine based on degradation pattern learning , 2017, Reliab. Eng. Syst. Saf..

[11]  M.,et al.  CORROSION AND CORROSION FATIGUE OF AIRFRAME ALUMINUM ALLOYS , 2022 .

[12]  Y. Kondo.  Prediction of Fatigue Crack Initiation Life Based on Pit Growth , 1989 .

[13]  K. M. Golos,et al.  Cumulative fatigue damage , 1988 .

[14]  R. Wei,et al.  Transition from pitting to fatigue crack growth—modeling of corrosion fatigue crack nucleation in a 2024-T3 aluminum alloy , 1996 .

[15]  Xiang Li,et al.  Remaining useful life estimation in prognostics using deep convolution neural networks , 2018, Reliab. Eng. Syst. Saf..

[16]  G. Henaff,et al.  Synergistic action of fatigue and corrosion during crack growth in the 2024 aluminium alloy , 2010 .

[17]  Lovekesh Vig,et al.  Anomaly detection in ECG time signals via deep long short-term memory networks , 2015, 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA).

[18]  Takehisa Yairi,et al.  A review on the application of deep learning in system health management , 2018, Mechanical Systems and Signal Processing.

[19]  Ali Fatemi,et al.  Cumulative fatigue damage and life prediction theories: a survey of the state of the art for homogeneous materials , 1998 .

[20]  Yongming Liu,et al.  Physics-based Learning for Aircraft Dynamics Simulation , 2018, Annual Conference of the PHM Society.

[21]  Dan M. Frangopol,et al.  Probabilistic models for life‐cycle performance of deteriorating structures: review and future directions , 2004 .

[22]  Robert A. Ainsworth,et al.  Corrosion-fatigue: a review of damage tolerance models , 2018 .

[23]  Les E. Atlas,et al.  Recurrent neural networks and robust time series prediction , 1994, IEEE Trans. Neural Networks.

[24]  P. C. Paris,et al.  A Critical Analysis of Crack Propagation Laws , 1963 .