Physics-Informed, Data-Driven Model for Atmospheric Corrosion of Carbon Steel Using Bayesian Network
Atmospheric corrosion is a significant challenge faced by the aviation industry as it considerably affects the structural integrity of an aircraft operated for long periods. Therefore, an appropriate corrosion deterioration model is required to predict corrosion problems. However, practical applicat...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-07-01
|
Series: | Materials |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1944/16/15/5326 |
_version_ | 1797586435234070528 |
---|---|
author | Taesu Choi Dooyoul Lee |
author_facet | Taesu Choi Dooyoul Lee |
author_sort | Taesu Choi |
collection | DOAJ |
description | Atmospheric corrosion is a significant challenge faced by the aviation industry as it considerably affects the structural integrity of an aircraft operated for long periods. Therefore, an appropriate corrosion deterioration model is required to predict corrosion problems. However, practical application of the deterioration model is challenging owing to the limited data available for the parameter estimation. Thus, a high uncertainty in prediction is unavoidable. To address these challenges, a method of integrating a physics-based model and the monitoring data on a Bayesian network (BN) is presented herein. Atmospheric corrosion is modeled using the simulation method, and a BN is constructed using GeNie. Moreover, model calibration is performed using the monitoring data collected from aircraft parking areas. The calibration approach is an improvement over existing models as it incorporates actual environmental data, making it more accurate and applicable to real-world scenarios. In conclusion, our research emphasizes the importance of precise corrosion models for predicting and managing atmospheric corrosion on carbon steel. The study results open new avenues for future research, such as the incorporation of additional data sources to further improve the accuracy of corrosion models. |
first_indexed | 2024-03-11T00:23:11Z |
format | Article |
id | doaj.art-2ae5eb4bf70142919538567343d61e70 |
institution | Directory Open Access Journal |
issn | 1996-1944 |
language | English |
last_indexed | 2024-03-11T00:23:11Z |
publishDate | 2023-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Materials |
spelling | doaj.art-2ae5eb4bf70142919538567343d61e702023-11-18T23:11:50ZengMDPI AGMaterials1996-19442023-07-011615532610.3390/ma16155326Physics-Informed, Data-Driven Model for Atmospheric Corrosion of Carbon Steel Using Bayesian NetworkTaesu Choi0Dooyoul Lee1Department of Weapon System, Korea National Defense University, Nonsan 33021, Republic of KoreaDepartment of Weapon System, Korea National Defense University, Nonsan 33021, Republic of KoreaAtmospheric corrosion is a significant challenge faced by the aviation industry as it considerably affects the structural integrity of an aircraft operated for long periods. Therefore, an appropriate corrosion deterioration model is required to predict corrosion problems. However, practical application of the deterioration model is challenging owing to the limited data available for the parameter estimation. Thus, a high uncertainty in prediction is unavoidable. To address these challenges, a method of integrating a physics-based model and the monitoring data on a Bayesian network (BN) is presented herein. Atmospheric corrosion is modeled using the simulation method, and a BN is constructed using GeNie. Moreover, model calibration is performed using the monitoring data collected from aircraft parking areas. The calibration approach is an improvement over existing models as it incorporates actual environmental data, making it more accurate and applicable to real-world scenarios. In conclusion, our research emphasizes the importance of precise corrosion models for predicting and managing atmospheric corrosion on carbon steel. The study results open new avenues for future research, such as the incorporation of additional data sources to further improve the accuracy of corrosion models.https://www.mdpi.com/1996-1944/16/15/5326model calibrationBayesian networkatmospheric corrosioncarbon steel |
spellingShingle | Taesu Choi Dooyoul Lee Physics-Informed, Data-Driven Model for Atmospheric Corrosion of Carbon Steel Using Bayesian Network Materials model calibration Bayesian network atmospheric corrosion carbon steel |
title | Physics-Informed, Data-Driven Model for Atmospheric Corrosion of Carbon Steel Using Bayesian Network |
title_full | Physics-Informed, Data-Driven Model for Atmospheric Corrosion of Carbon Steel Using Bayesian Network |
title_fullStr | Physics-Informed, Data-Driven Model for Atmospheric Corrosion of Carbon Steel Using Bayesian Network |
title_full_unstemmed | Physics-Informed, Data-Driven Model for Atmospheric Corrosion of Carbon Steel Using Bayesian Network |
title_short | Physics-Informed, Data-Driven Model for Atmospheric Corrosion of Carbon Steel Using Bayesian Network |
title_sort | physics informed data driven model for atmospheric corrosion of carbon steel using bayesian network |
topic | model calibration Bayesian network atmospheric corrosion carbon steel |
url | https://www.mdpi.com/1996-1944/16/15/5326 |
work_keys_str_mv | AT taesuchoi physicsinformeddatadrivenmodelforatmosphericcorrosionofcarbonsteelusingbayesiannetwork AT dooyoullee physicsinformeddatadrivenmodelforatmosphericcorrosionofcarbonsteelusingbayesiannetwork |