{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T23:05:42Z","timestamp":1787699142495,"version":"build-2784847793"},"reference-count":66,"publisher":"ASME International","issue":"6","license":[{"start":{"date-parts":[[2020,6,12]],"date-time":"2020-06-12T00:00:00Z","timestamp":1591920000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.asme.org\/publications-submissions\/publishing-information\/legal-policies"}],"funder":[{"DOI":"10.13039\/100007900","name":"University of Central Florida","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007900","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["asmedigitalcollection.asme.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>We present a physics-informed neural network modeling approach for missing physics estimation in cumulative damage models. This hybrid approach is designed to merge physics-informed and data-driven layers within deep neural networks. The result is a cumulative damage model in which physics-informed layers are used to model relatively well understood phenomena and data-driven layers account for hard-to-model physics. A numerical experiment is used to present the main features of the proposed framework. The test problem consists of predicting corrosion-fatigue of an Al 2024-T3 alloy used on panels of aircraft wings. Besides cyclic loading, panels are also subjected to saline corrosion. In this case, physics-informed layers implement the well-known Walker model for crack propagation, while data-driven layers are trained to compensate the bias in damage accumulation due to the corrosion effects. 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 how to compensate the missing physics of corrosion in the original fatigue model. Predictions from the hybrid model can be used in fleet management, for example, to prioritize inspection across the fleet or forecast ahead of time the number of planes with damage above a threshold.<\/jats:p>","DOI":"10.1115\/1.4047173","type":"journal-article","created":{"date-parts":[[2020,5,10]],"date-time":"2020-05-10T09:24:31Z","timestamp":1589102671000},"update-policy":"https:\/\/doi.org\/10.1115\/crossmarkpolicy-asme","source":"Crossref","is-referenced-by-count":113,"title":["Physics-Informed Neural Networks for Missing Physics Estimation in Cumulative Damage Models: A Case Study in Corrosion Fatigue"],"prefix":"10.1115","volume":"20","author":[{"given":"Arinan","family":"Dourado","sequence":"first","affiliation":[{"name":"Department of Mechanical and Aerospace Engineering, University of Central Florida, Orlando, FL 32816"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felipe A. C.","family":"Viana","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Aerospace Engineering, University of Central Florida, Orlando, FL 32816"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"33","published-online":{"date-parts":[[2020,6,12]]},"reference":[{"issue":"1\u20132","key":"2020101211250658000_CIT0001","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1016\/j.ymssp.2013.06.004","article-title":"Prognostics and Health Management Design for Rotary Machinery Systems\u2014Reviews, Methodology and Applications","volume":"42","author":"Lee","year":"2014","journal-title":"Mech. Syst. Signal Process."},{"key":"2020101211250658000_CIT0002","volume-title":"Probabilistic Models of Cumulative Damage","author":"Bogdanoff","year":"1985"},{"key":"2020101211250658000_CIT0003","doi-asserted-by":"crossref","DOI":"10.1520\/STP1450-EB","volume-title":"Probabilistic Aspects of Life Prediction","author":"Johnson","year":"2004"},{"issue":"8","key":"2020101211250658000_CIT0004","doi-asserted-by":"crossref","first-page":"965","DOI":"10.1177\/1045389X14538328","article-title":"Probabilistic Fatigue Damage Prognosis of Lap Joint Using Bayesian Updating","volume":"26","author":"Peng","year":"2015","journal-title":"J. Intell. Mater. Syst. Struct."},{"issue":"3","key":"2020101211250658000_CIT0005","doi-asserted-by":"crossref","first-page":"930","DOI":"10.2514\/1.J055201","article-title":"Dynamic Bayesian Network for Aircraft Wing Health Monitoring Digital Twin","volume":"55","author":"Li","year":"2017","journal-title":"AIAA J."},{"issue":"1","key":"2020101211250658000_CIT0006","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.compstruct.2017.12.035","article-title":"A Bayesian Framework for Fatigue Life Prediction of Composite Laminates Under Co-Existing Matrix Cracks and Delamination","volume":"187","author":"Corbetta","year":"2018","journal-title":"Compos. Struct."},{"key":"2020101211250658000_CIT0007","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1007\/s42791-019-0016-y","article-title":"A Comprehensive Review of Artificial Intelligence-Based Approaches for Rolling Element Bearing PHM: Shallow and Deep Learning","volume":"1","author":"Hamadache","year":"2019","journal-title":"JMST Adv."},{"issue":"2","key":"2020101211250658000_CIT0008","doi-asserted-by":"crossref","first-page":"021009","DOI":"10.1115\/1.4045663","article-title":"An Integrative Machine Learning Method to Improve Fault Detection and Productivity Performance in a Cyber-Physical System","volume":"20","author":"Chiu","year":"2020","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"2","key":"2020101211250658000_CIT0009","doi-asserted-by":"crossref","first-page":"021004","DOI":"10.1115\/1.4045293","article-title":"Dilated Convolution Neural Network for Remaining Useful Life Prediction","volume":"20","author":"Xu","year":"2020","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"3","key":"2020101211250658000_CIT0010","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1115\/1.2893988","article-title":"Prediction of Machine Deterioration Using Vibration Based Fault Trends and Recurrent Neural Networks","volume":"121","author":"Tse","year":"1999","journal-title":"ASME J. Vib. Acoust."},{"issue":"4","key":"2020101211250658000_CIT0011","doi-asserted-by":"crossref","first-page":"044502","DOI":"10.1115\/1.3249574","article-title":"Prognostics of Machine Condition Using Energy Based Monitoring Index and Computational Intelligence","volume":"9","author":"Samanta","year":"2009","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"key":"2020101211250658000_CIT0012","doi-asserted-by":"crossref","DOI":"10.36001\/phmconf.2010.v2i1.1896","article-title":"An Adaptive Recurrent Neural Network for Remaining Useful Life Prediction of Lithium-Ion Batteries","author":"Liu","year":"2010"},{"issue":"1","key":"2020101211250658000_CIT0013","first-page":"1","article-title":"Predicting Remaining Useful Life Using Time Series Embeddings Based on Recurrent Neural Networks","volume":"9","author":"Gugulothu","year":"2018","journal-title":"Int. J. Prognostics Health Manage."},{"issue":"2","key":"2020101211250658000_CIT0014","doi-asserted-by":"crossref","first-page":"021007","DOI":"10.1115\/1.4045445","article-title":"Failure Prognosis of Complex Equipment With Multistream Deep Recurrent Neural Network","volume":"20","author":"Su","year":"2020","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"2","key":"2020101211250658000_CIT0015","doi-asserted-by":"crossref","first-page":"021012","DOI":"10.1115\/1.4045491","article-title":"NBLSTM: Noisy and Hybrid Convolutional Neural Network and BLSTM-Based Deep Architecture for Remaining Useful Life Estimation","volume":"20","author":"Al-Dulaimi","year":"2020","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"key":"2020101211250658000_CIT0016","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1016\/j.probengmech.2013.01.003","article-title":"Model-Based and Data-Driven Prognostics Under Different Available Information","volume":"32","author":"Baraldi","year":"2013","journal-title":"Probabilistic Eng. Mech."},{"key":"2020101211250658000_CIT0017","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1016\/j.ress.2014.09.014","article-title":"Practical Options for Selecting Data-Driven Or Physics-Based Prognostics Algorithms With Reviews","volume":"133","author":"An","year":"2015","journal-title":"Reliab. Eng. Syst. Saf."},{"issue":"2","key":"2020101211250658000_CIT0018","doi-asserted-by":"crossref","first-page":"1","DOI":"10.36001\/ijphm.2019.v10i2.2727","article-title":"A New Hybrid Prognostic Methodology","volume":"10","author":"Eker","year":"2019","journal-title":"Int. J. Prognostics Health Manage."},{"issue":"Sp11","key":"2020101211250658000_CIT0019","first-page":"1","article-title":"Hybrid Deep Fault Detection and Isolation: Combining Deep Neural Networks and System Performance Models","volume":"10","author":"Chao","year":"2019","journal-title":"Int. J. Prognostics Health Manage."},{"key":"2020101211250658000_CIT0020","doi-asserted-by":"crossref","DOI":"10.12783\/shm2019\/32301","article-title":"Fleet Prognosis With Physics-Informed Recurrent Neural Networks","author":"Nascimento","year":"2019"},{"key":"2020101211250658000_CIT0021","first-page":"1740","article-title":"Fleet Prognosis With Physics-Informed Recurrent Neural Networks","author":"Nascimento","year":"2019"},{"key":"2020101211250658000_CIT0022","volume-title":"Corrosion and Corrosion Fatigue of Airframe Aluminum Alloys","author":"Chen","year":"1994"},{"issue":"2","key":"2020101211250658000_CIT0023","doi-asserted-by":"crossref","first-page":"325","DOI":"10.2514\/2.1308","article-title":"Comparative Study of Corrosion-Fatigue in Aircraft Materials","volume":"39","author":"Wang","year":"2001","journal-title":"AIAA J."},{"issue":"5","key":"2020101211250658000_CIT0024","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1016\/S0142-1123(02)00168-8","article-title":"Fatigue Crack Growth From Corrosion Damage in 7075-T6511 Aluminium Alloy Under Aircraft Loading","volume":"25","author":"DuQuesnay","year":"2003","journal-title":"Int. J. Fatigue"},{"issue":"1","key":"2020101211250658000_CIT0025","first-page":"135","article-title":"Fatigue Crack Initiation at Corrosion Pits","volume":"9","author":"Lindley","year":"1982","journal-title":"Mat. Technol."},{"issue":"1","key":"2020101211250658000_CIT0026","doi-asserted-by":"crossref","first-page":"7","DOI":"10.5006\/1.3577891","article-title":"Prediction of Fatigue Crack Initiation Life Based on Pit Growth","volume":"45","author":"Kondo","year":"1989","journal-title":"Corrosion"},{"issue":"1\u20132","key":"2020101211250658000_CIT0027","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1016\/S0921-5093(96)10414-7","article-title":"Transition From Pitting to Fatigue Crack Growth\u2014Modeling of Corrosion Fatigue Crack Nucleation in a 2024-T3 Aluminum Alloy","volume":"219","author":"Chen","year":"1996","journal-title":"Mater. Sci. Eng."},{"issue":"5","key":"2020101211250658000_CIT0028","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1080\/09506608.2017.1375644","article-title":"Corrosion-Fatigue: A Review of Damage Tolerance Models","volume":"63","author":"Larossa","year":"2018","journal-title":"Int. Mater. Rev."},{"issue":"1","key":"2020101211250658000_CIT0029","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1016\/0021-9991(90)90007-N","article-title":"Neural Algorithm for Solving Differential Equations","volume":"91","author":"Lee","year":"1990","journal-title":"J. Comput. Phys."},{"issue":"9","key":"2020101211250658000_CIT0030","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/0895-7177(94)00160-X","article-title":"Solution of Nonlinear Ordinary Differential Equations by Feedforward Neural Networks","volume":"20","author":"Meade","year":"1994","journal-title":"Math. Comput. Modell."},{"issue":"2","key":"2020101211250658000_CIT0031","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1016\/0893-6080(94)90031-0","article-title":"Neural Network Representation of Finite Element Method","volume":"7","author":"Takeuchi","year":"1994","journal-title":"Neural Netw."},{"issue":"2","key":"2020101211250658000_CIT0032","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1109\/72.661124","article-title":"Runge-Kutta Neural Network for Identification of Dynamical Systems in High Accuracy","volume":"9","author":"Wang","year":"1998","journal-title":"IEEE Trans. Neural Netw."},{"issue":"7","key":"2020101211250658000_CIT0033","doi-asserted-by":"crossref","first-page":"2215","DOI":"10.2514\/1.J055595","article-title":"Machine-Learning-Augmented Predictive Modeling of Turbulent Separated Flows Over Airfoils","volume":"55","author":"Singh","year":"2017","journal-title":"AIAA J."},{"issue":"15","key":"2020101211250658000_CIT0034","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1016\/j.jcp.2017.11.039","article-title":"Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations","volume":"357","author":"Raissi","year":"2018","journal-title":"J. Comput. Phys."},{"key":"2020101211250658000_CIT0035","first-page":"6572","volume-title":"Neural Ordinary Differential Equations","author":"Chen","year":"2018"},{"issue":"1","key":"2020101211250658000_CIT0036","doi-asserted-by":"crossref","first-page":"A172","DOI":"10.1137\/17M1120762","article-title":"Numerical Gaussian Processes for Time-Dependent and Nonlinear Partial Differential Equations","volume":"40","author":"Raissi","year":"2018","journal-title":"SIAM J. Sci. Comput."},{"issue":"3","key":"2020101211250658000_CIT0037","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1007\/s11242-018-1170-7","article-title":"Reduced-Order Modeling of Subsurface Multi-Phase Flow Models Using Deep Residual Recurrent Neural Networks","volume":"126","author":"Kani","year":"2018","journal-title":"Transp. Porous Media"},{"issue":"25","key":"2020101211250658000_CIT0038","first-page":"1","article-title":"Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations","volume":"19","author":"Raissi","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"2020101211250658000_CIT0039","doi-asserted-by":"crossref","DOI":"10.36001\/phmconf.2018.v10i1.513","article-title":"Physics-Based Learning for Aircraft Dynamics Simulation","author":"Yu","year":"2018"},{"issue":"1","key":"2020101211250658000_CIT0040","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/S0142-1123(97)00081-9","article-title":"Cumulative Fatigue Damage and Life Prediction Theories: a Survey of the State of the Art for Homogeneous Materials","volume":"20","author":"Fatemi","year":"1998","journal-title":"Int. J. Fatigue"},{"issue":"4","key":"2020101211250658000_CIT0041","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1002\/pse.180","article-title":"Probabilistic Models for Life-Cycle Performance of Deteriorating Structures: Review and Future Directions","volume":"6","author":"Frangopol","year":"2004","journal-title":"Prog. Struct. Eng. Mater."},{"issue":"5","key":"2020101211250658000_CIT0042","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1109\/24.46485","article-title":"Replacement Policies for a Cumulative Damage Model With Minimal Repair at Failure","volume":"38","author":"Nakagawa","year":"1989","journal-title":"IEEE Trans. Reliab."},{"issue":"4","key":"2020101211250658000_CIT0043","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1115\/1.3656900","article-title":"A Critical Analysis of Crack Propagation Laws","volume":"85","author":"Paris","year":"1963","journal-title":"ASME J. Basic Eng."},{"key":"2020101211250658000_CIT0044","article-title":"MMPDS - 12: Metallic Materials Properties Development and Stadardization","author":"MMPDS Collaborators","year":"2017"},{"key":"2020101211250658000_CIT0045","volume-title":"Mechanical Behavior of Materials: Engineering Methods for Deformation, Fracture, and Fatigue","author":"Dowling","year":"2012"},{"key":"2020101211250658000_CIT0046","first-page":"47","article-title":"Pitting Corrosion Fatigue of Structural Materials","author":"Goswami","year":"1995"},{"issue":"13","key":"2020101211250658000_CIT0047","doi-asserted-by":"crossref","first-page":"1493","DOI":"10.1016\/S0013-7944(01)00041-8","article-title":"Damage Tolerance Approach for Probabilistic Pitting Corrosion Fatigue Life Prediction","volume":"68","author":"Shi","year":"2001","journal-title":"Eng. Fract. Mech."},{"issue":"1","key":"2020101211250658000_CIT0048","doi-asserted-by":"crossref","first-page":"1441","DOI":"10.1016\/j.proeng.2010.03.156","article-title":"Synergistic Action of Fatigue and Corrosion During Crack Growth in the 2024 Aluminum Alloy","volume":"2","author":"Menan","year":"2010","journal-title":"Procedia Eng."},{"key":"2020101211250658000_CIT0049","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"issue":"8","key":"2020101211250658000_CIT0050","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"2020101211250658000_CIT0051","first-page":"2067","article-title":"Gated Feedback Recurrent Neural Networks","author":"Chung","year":"2015"},{"issue":"2","key":"2020101211250658000_CIT0052","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1109\/72.279188","article-title":"Recurrent Neural Networks and Robust Time Series Prediction","volume":"5","author":"Connor","year":"1994","journal-title":"IEEE Trans. Neural Netw."},{"key":"2020101211250658000_CIT0053","article-title":"Generating Text With Recurrent Neural Networks","author":"Sutskever","year":"2011"},{"key":"2020101211250658000_CIT0054","first-page":"6645","article-title":"Speech Recognition With Deep Recurrent Neural Networks","author":"Graves","year":"2013"},{"key":"2020101211250658000_CIT0055","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2014-80","article-title":"Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling","author":"Sak","year":"2014"},{"key":"2020101211250658000_CIT0056","first-page":"1","article-title":"Anomaly Detection in ECG Time Signals Via Deep Long Short-Term Memory Networks","author":"Chauhan","year":"2015"},{"key":"2020101211250658000_CIT0057","first-page":"1784","article-title":"Model-Assisted Probability of Detection Evaluation for Eddy Current Inspection of Fastener Sites","author":"Aldrin","year":"2009"},{"issue":"7","key":"2020101211250658000_CIT0058","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1016\/j.ndteint.2006.03.006","article-title":"Ultrasonic Arrays for Non-Destructive Evaluation: A Review","volume":"39","author":"Drinkwater","year":"2006","journal-title":"NDT & E Int."},{"key":"2020101211250658000_CIT0059","unstructured":"Hoye, M. V. , 1986, \u201cFluorescent Penetrant Crack Detection,\u201d U.S. Patent No. US4621193A, Nov."},{"issue":"4","key":"2020101211250658000_CIT0060","doi-asserted-by":"crossref","first-page":"317","DOI":"10.12989\/sss.2009.5.4.317","article-title":"Real Time Crack Detection Using Mountable Comparative Vacuum Monitoring Sensors","volume":"5","author":"Roach","year":"2009","journal-title":"Smart Struct. Syst."},{"issue":"8","key":"2020101211250658000_CIT0061","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/50.618320","article-title":"Fiber Bragg Grating Technology Fundamentals and Overview","volume":"15","author":"Hill","year":"1997","journal-title":"J. Lightwave Technol."},{"key":"2020101211250658000_CIT0062","unstructured":"Jonge, J. B. D., Schutz, D., Lowak, H., and Schijve, J., 1973, \u201cA Standardized Load Sequence for Flight Simulation Tests on Transport Aircraft Wing Structures,\u201d NLR TR 73029U, Report from National Aerospace Laboratory."},{"issue":"4","key":"2020101211250658000_CIT0063","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1016\/S0169-2070(99)00007-2","article-title":"On the Asymmetry of the Symmetric MAPE","volume":"15","author":"Goodwin","year":"1999","journal-title":"Int. J. Forecast."},{"key":"2020101211250658000_CIT0064","unstructured":"Viana, F. A. C., Nascimento, R. G., Yucesan, Y., and Dourado, A., 2019, Physics-Informed Neural Networks Package, https:\/\/github.com\/PML-UCF\/pinn\u02d9wind\u02d9bearing, August."},{"key":"2020101211250658000_CIT0065","doi-asserted-by":"crossref","unstructured":"Dourado, A., and Viana, F. A. C., 2019, Python Scripts for Physics-Informed Neural Networks for Corrosion-Fatigue Prognosis, v0.0.1, https:\/\/github.com\/PML-UCF\/pinn\u02d9corrosion\u02d9fatigue, August.","DOI":"10.36001\/phmconf.2019.v11i1.814"},{"key":"2020101211250658000_CIT0066","first-page":"1137","article-title":"A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection","author":"Kohavi","year":"1995"}],"container-title":["Journal of Computing and Information Science in Engineering"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/doi\/10.1115\/1.4047173\/6576078\/jcise_20_6_061007.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/doi\/10.1115\/1.4047173\/6576078\/jcise_20_6_061007.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T16:19:50Z","timestamp":1722874790000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article\/doi\/10.1115\/1.4047173\/1083614\/PhysicsInformed-Neural-Networks-for-Missing"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,12]]},"references-count":66,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2020,12,1]]}},"URL":"https:\/\/doi.org\/10.1115\/1.4047173","relation":{},"ISSN":["1530-9827","1944-7078"],"issn-type":[{"value":"1530-9827","type":"print"},{"value":"1944-7078","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6,12]]},"article-number":"061007"}}