An active learning framework for the rapid assessment of galvanic corrosion

Venkatraman, Aditya; Katona, Ryan Michael; Maestas, Demitri; Roop, Matthew Lawrence; Noell, Philip James; Montes de Oca Zapiain, David

doi:10.1038/s41529-024-00476-4

An active learning framework for the rapid assessment of galvanic corrosion

Journal Article · Tue May 21 00:00:00 EDT 2024 · npj Materials Degradation

DOI:https://doi.org/10.1038/s41529-024-00476-4· OSTI ID:2371080

^[1]; ^[1]; Maestas, Demitri ^[1]; Roop, Matthew Lawrence ^[2]; ^[1]; ^[1]

Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Univ. of New Mexico, Albuquerque, NM (United States)

The current present in a galvanic couple can define its resistance or susceptibility to corrosion. However, as the current is dependent upon environmental, material, and geometrical parameters it is experimentally costly to measure. To reduce these costs, Finite Element (FE) simulations can be used to assess the cathodic current but also require experimental inputs to define boundary conditions. Due to these challenges, it is crucial to accelerate predictions and accurately predict the current output for different environments and geometries representative of in-service conditions. Machine learned surrogate models provides a means to accelerate corrosion predictions. However, a one-time cost is incurred in procuring the simulation and experimental dataset necessary to calibrate the surrogate model. Therefore, an active learning protocol is developed through calibration of a low-cost surrogate model for the cathodic current of an exemplar galvanic couple (AA7075-SS304) as a function of environmental and geometric parameters. The surrogate model is calibrated on a dataset of FE simulations, and calculates an acquisition function that identifies specific additional inputs with the maximum potential to improve the current predictions. This is accomplished through a staggered workflow that not only improves and refines prediction, but identifies the points at which the most information is gained, thus enabling expansion to a larger parameter space. The protocols developed and demonstrated in this work provide a powerful tool for screening various forms of corrosion under in-service conditions.

View Accepted Manuscript (DOE)

Research Organization:: Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA)

Grant/Contract Number:: NA0003525

OSTI ID:: 2371080

Report Number(s):: SAND--2024-07153J

Journal Information:: npj Materials Degradation, Journal Name: npj Materials Degradation Journal Issue: 1 Vol. 8; ISSN 2397-2106

Publisher:: SpringerCopyright Statement

Country of Publication:: United States

Language:: English

References (42)

Some Criterion-based Experimental Designs Santner, Thomas J.; Williams, Brian J.; Notz, William I. The Design and Analysis of Computer Experiments, p. 163-187 https://doi.org/10.1007/978-1-4757-3799-8_6	book	January 2003
Sensitivity Analysis and Variable Screening Santner, Thomas J.; Williams, Brian J.; Notz, William I. The Design and Analysis of Computer Experiments, p. 247-297 https://doi.org/10.1007/978-1-4939-8847-1_7	book	January 2018
Calibration Santner, Thomas J.; Williams, Brian J.; Notz, William I. The Design and Analysis of Computer Experiments, p. 299-379 https://doi.org/10.1007/978-1-4939-8847-1_8	book	January 2018
An Experimental High-Throughput to High-Fidelity Study Towards Discovering Al–Cr Containing Corrosion-Resistant Compositionally Complex Alloys Sur, Debashish; Holcombe, Emily F.; Blades, William H. High Entropy Alloys & Materials, Vol. 1, Issue 2 https://doi.org/10.1007/s44210-023-00020-0	journal	September 2023
Ensembling neural networks: Many could be better than all Zhou, Zhi-Hua; Wu, Jianxin; Tang, Wei Artificial Intelligence, Vol. 137, Issue 1-2 https://doi.org/10.1016/S0004-3702(02)00190-X	journal	May 2002
Efficiently exploiting process-structure-property relationships in material design by multi-information source fusion Khatamsaz, Danial; Molkeri, Abhilash; Couperthwaite, Richard Acta Materialia, Vol. 206 https://doi.org/10.1016/j.actamat.2020.116619	journal	March 2021
Surrogate-based sequential Bayesian experimental design using non-stationary Gaussian Processes Pandita, Piyush; Tsilifis, Panagiotis; Awalgaonkar, Nimish M. Computer Methods in Applied Mechanics and Engineering, Vol. 385 https://doi.org/10.1016/j.cma.2021.114007	journal	November 2021
Advances in understanding atmospheric corrosion of iron. II. Mechanistic modelling of wet–dry cycles Hœrlé, S.; Mazaudier, F.; Dillmann, Ph. Corrosion Science, Vol. 46, Issue 6 https://doi.org/10.1016/j.corsci.2003.09.028	journal	June 2004
Modeling bimetallic corrosion under thin electrolyte films Thébault, F.; Vuillemin, B.; Oltra, R. Corrosion Science, Vol. 53, Issue 1 https://doi.org/10.1016/j.corsci.2010.09.010	journal	January 2011
Validation of predictive model for galvanic corrosion under thin electrolyte layers: An application to aluminium 2024-CFRP material combination Palani, S.; Hack, T.; Deconinck, J. Corrosion Science, Vol. 78 https://doi.org/10.1016/j.corsci.2013.09.003	journal	January 2014
Model for corrosion of metals covered with thin electrolyte layers: Pseudo-steady state diffusion of oxygen Venkatraman, Murali Sankar; Cole, Ivan S.; Emmanuel, Bosco Electrochimica Acta, Vol. 56, Issue 20 https://doi.org/10.1016/j.electacta.2011.05.009	journal	August 2011
A transient multi-ion transport model for galvanized steel corrosion protection Topa, V.; Demeter, A. S.; Hotoiu, L. Electrochimica Acta, Vol. 77 https://doi.org/10.1016/j.electacta.2012.06.021	journal	August 2012
Simulation of the role of vibration on Scanning Vibrating Electrode Technique measurements close to a disc in plane Dolgikh, Olga; Demeter, Andrei–Stefan; Lamaka, Sviatlana V. Electrochimica Acta, Vol. 203 https://doi.org/10.1016/j.electacta.2016.01.188	journal	June 2016
A comparison of FEM results from the use of different governing equations in a galvanic cell part I: In the presence of a supporting electrolyte Moraes, C. V.; Kelly, R. G. Electrochimica Acta, Vol. 469 https://doi.org/10.1016/j.electacta.2023.143146	journal	November 2023
A comparison of FEM results from the use of different governing equations in a galvanic cell part II: Impact of low supporting electrolyte concentration Moraes, C. V.; Kelly, R. G. Electrochimica Acta, Vol. 468 https://doi.org/10.1016/j.electacta.2023.143153	journal	November 2023
Machine learning assisted materials design and discovery for rechargeable batteries Liu, Yue; Guo, Biru; Zou, Xinxin Energy Storage Materials, Vol. 31 https://doi.org/10.1016/j.ensm.2020.06.033	journal	October 2020
Bayesian analysis of parametric uncertainties and model form probabilities for two different crystal plasticity models of lamellar grains in α+β Titanium alloys Venkatraman, Aditya; McDowell, David L.; Kalidindi, Surya R. International Journal of Plasticity, Vol. 154 https://doi.org/10.1016/j.ijplas.2022.103289	journal	July 2022
Reified Bayesian modelling and inference for physical systems Goldstein, Michael; Rougier, Jonathan Journal of Statistical Planning and Inference, Vol. 139, Issue 3 https://doi.org/10.1016/j.jspi.2008.07.019	journal	March 2009
Machine learning for materials science: Barriers to broader adoption Boyce, Brad; Dingreville, Remi; Desai, Saaketh Matter, Vol. 6, Issue 5 https://doi.org/10.1016/j.matt.2023.03.028	journal	May 2023
Physics-informed machine learning assisted uncertainty quantification for the corrosion of dissimilar material joints Bansal, Parth; Zheng, Zhuoyuan; Shao, Chenhui Reliability Engineering & System Safety, Vol. 227 https://doi.org/10.1016/j.ress.2022.108711	journal	November 2022
Active learning with generalized sliced inverse regression for high-dimensional reliability analysis Yin, Jianhua; Du, Xiaoping Structural Safety, Vol. 94 https://doi.org/10.1016/j.strusafe.2021.102151	journal	January 2022
Convex Optimization Boyd, Stephen; Vandenberghe, Lieven https://doi.org/10.1017/CBO9780511804441	book	January 2004
Efficient Global Optimization of Expensive Black-Box Functions Jones, Donald R.; Schonlau, Matthias; Welch, William J. Journal of Global Optimization, Vol. 13, Issue 4, p. 455-492 https://doi.org/10.1023/A:1008306431147	journal	January 1998
Active learning-assisted neutron spectroscopy with log-Gaussian processes Teixeira Parente, Mario; Brandl, Georg; Franz, Christian Nature Communications, Vol. 14, Issue 1 https://doi.org/10.1038/s41467-023-37418-8	journal	April 2023
Machine-learning-guided descriptor selection for predicting corrosion resistance in multi-principal element alloys Roy, Ankit; Taufique, M. F. N.; Khakurel, Hrishabh npj Materials Degradation, Vol. 6, Issue 1 https://doi.org/10.1038/s41529-021-00208-y	journal	January 2022
A computational approach for mapping electrochemical activity of multi-principal element alloys Yuwono, Jodie A.; Li, Xinyu; Doležal, Tyler D. npj Materials Degradation, Vol. 7, Issue 1 https://doi.org/10.1038/s41529-023-00409-7	journal	November 2023
Autonomous experiments using active learning and AI Ren, Zhichu; Ren, Zekun; Zhang, Zhen Nature Reviews Materials, Vol. 8, Issue 9 https://doi.org/10.1038/s41578-023-00588-4	journal	August 2023
Dynamic, adaptive sampling during nanopore sequencing using Bayesian experimental design Weilguny, Lukas; De Maio, Nicola; Munro, Rory Nature Biotechnology, Vol. 41, Issue 7 https://doi.org/10.1038/s41587-022-01580-z	journal	January 2023
Designing computer experiments with multiple types of factors: The MaxPro approach Joseph, V. Roshan; Gul, Evren; Ba, Shan Journal of Quality Technology, Vol. 52, Issue 4 https://doi.org/10.1080/00224065.2019.1611351	journal	June 2019
Maximum projection designs for computer experiments Joseph, V. Roshan; Gul, Evren; Ba, Shan Biometrika, Vol. 102, Issue 2 https://doi.org/10.1093/biomet/asv002	journal	March 2015
Bayesian Optimal Design of Experiments for Inferring the Statistical Expectation of Expensive Black-Box Functions Pandita, Piyush; Bilionis, Ilias; Panchal, Jitesh Journal of Mechanical Design, Vol. 141, Issue 10 https://doi.org/10.1115/1.4043930	journal	July 2019
Reinforcement Learning-Based Sequential Batch-Sampling for Bayesian Optimal Experimental Design Ashenafi, Yonatan; Pandita, Piyush; Ghosh, Sayan Journal of Mechanical Design, Vol. 144, Issue 9 https://doi.org/10.1115/1.4054631	journal	June 2022
Editors’ Choice—Natural Convection Boundary Layer Thickness at Elevated Chloride Concentrations and Temperatures and the Effects on a Galvanic Couple Katona, R. M.; Carpenter, J. C.; Knight, A. W. Journal of The Electrochemical Society, Vol. 168, Issue 3 https://doi.org/10.1149/1945-7111/abeb29	journal	March 2021
Accelerating FEM-Based Corrosion Predictions Using Machine Learning Montes de Oca Zapiain, David; Maestas, Demitri; Roop, Matthew Journal of The Electrochemical Society, Vol. 171, Issue 1 https://doi.org/10.1149/1945-7111/ad1e3c	journal	January 2024
Editors' Choice—Electrolyte Film Thickness Effects on the Cathodic Current Availability in a Galvanic Couple Liu, C.; Srinivasan, J.; Kelly, R. G. Journal of The Electrochemical Society, Vol. 164, Issue 13 https://doi.org/10.1149/2.1641713jes	journal	January 2017
Atmospheric corrosion modeling Simillion, Hans; Dolgikh, Olga; Terryn, Herman Corrosion Reviews, Vol. 32, Issue 3-4 https://doi.org/10.1515/corrrev-2014-0023	journal	October 2014
Development of the Electrochemical Theory of Metallic Corrosion Tomashov, N. D. CORROSION, Vol. 20, Issue 1 https://doi.org/10.5006/0010-9312-20.1.7t	journal	January 1964
A Review of the Application of Finite Element Method (FEM) to Localized Corrosion Modeling Liu, Chao; Kelly, Robert G. CORROSION, Vol. 75, Issue 11 https://doi.org/10.5006/3282	journal	September 2019
Future Frontiers in Corrosion Science and Engineering, Part III: The Next “Leap Ahead” in Corrosion Control May Be Enabled by Data Analytics and Artificial Intelligence Scully, John R.; Balachandran, Prasanna V. Corrosion, Vol. 75, Issue 12 https://doi.org/10.5006/3432	journal	December 2019
Galvanic Corrosion Between Coated Al Alloy Plate and Stainless Steel Fasteners, Part 2: Application of Finite Element Method and Machine Learning to Study Galvanic Current Distributions Marshall, R. Skelton; Define, K. A.; Rosner, R. S. Corrosion, Vol. 79, Issue 2 https://doi.org/10.5006/4153	journal	December 2022
Supplementary Data and Codes for "An Active Learning Framework for the Rapid Assessment of Galvanic Corrosion" Venkatraman, Aditya Zenodo https://doi.org/10.5281/zenodo.10655559	dataset	January 2024
Gaussian Processes for Machine Learning Rasmussen, Carl Edward; Williams, Christopher K. I. The MIT Press https://doi.org/10.7551/mitpress/3206.001.0001	book	January 2005

Similar Records

Physics-informed machine learning assisted uncertainty quantification for the corrosion of dissimilar material joints

Journal Article · Sat Jul 09 00:00:00 EDT 2022 · Reliability Engineering and System Safety · OSTI ID:2418029

Uncertainty Quantification for Dissimilar Material Joints Under Corrosion Environment

Conference · Thu Nov 10 23:00:00 EST 2022 · Volume 3A: 48th Design Automation Conference (DAC) · OSTI ID:2341618

Related Subjects

36 MATERIALS SCIENCE

An active learning framework for the rapid assessment of galvanic corrosion

Citation Formats

References (42)

Similar Records

Related Subjects