Predictive Analysis of Structural Damage in Submerged Structures: A Case Study Approach Using Machine Learning
This study focuses on the development of a machine learning (ML) model to elaborate on predictions of structural damage in submerged structures due to ocean states and subsequently compares it to a real-life case of a 6-month experiment with a benthic lander bearing a multitude of sensors. The ML mo...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Fluids |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2311-5521/10/1/10 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588513938243584 |
|---|---|
| author | Alexandre Brás dos Santos Hugo Mesquita Vasconcelos Tiago M. R. M. Domingues Pedro J. S. C. P. Sousa Susana Dias Rogério F. F. Lopes Marco L. P. Parente Mário Tomé Adélio M. S. Cavadas Pedro M. G. P. Moreira |
| author_facet | Alexandre Brás dos Santos Hugo Mesquita Vasconcelos Tiago M. R. M. Domingues Pedro J. S. C. P. Sousa Susana Dias Rogério F. F. Lopes Marco L. P. Parente Mário Tomé Adélio M. S. Cavadas Pedro M. G. P. Moreira |
| author_sort | Alexandre Brás dos Santos |
| collection | DOAJ |
| description | This study focuses on the development of a machine learning (ML) model to elaborate on predictions of structural damage in submerged structures due to ocean states and subsequently compares it to a real-life case of a 6-month experiment with a benthic lander bearing a multitude of sensors. The ML model uses wave parameters such as height, period and direction as input layers, which describe the ocean conditions, and strains in selected points of the lander structure as output layers. To streamline the dataset generation, a simplified approach was adopted, integrating analytical formulations based on Morison equations and numerical simulations through the Finite Element Method (FEM) of the designed lander. Subsequent validation involved Fluid–Structure Interaction (FSI) simulations, using a 2D Computational Fluid Dynamics (CFD)-based numerical wave tank of the entire ocean depth to access velocity profiles, and a restricted 3D CFD model incorporating the lander structure. A case study was conducted to empirically validate the simulated ML model, with the design and deployment of a benthic lander at 30 m depth. The lander was monitored using electrical and optical strain gauges. The strains measured during the testing period will provide empirical validation and may be used for extensive training of a more reliable model. |
| format | Article |
| id | doaj-art-d747fa4f4a5c43e7bb5666e8bc39366a |
| institution | Kabale University |
| issn | 2311-5521 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Fluids |
| spelling | doaj-art-d747fa4f4a5c43e7bb5666e8bc39366a2025-01-24T13:32:35ZengMDPI AGFluids2311-55212025-01-011011010.3390/fluids10010010Predictive Analysis of Structural Damage in Submerged Structures: A Case Study Approach Using Machine LearningAlexandre Brás dos Santos0Hugo Mesquita Vasconcelos1Tiago M. R. M. Domingues2Pedro J. S. C. P. Sousa3Susana Dias4Rogério F. F. Lopes5Marco L. P. Parente6Mário Tomé7Adélio M. S. Cavadas8Pedro M. G. P. Moreira9INEGI, Institute of Science and Innovation in Mechanical Engineering and Industrial Engineering, Campus da FEUP, R. Dr. Roberto Frias 400, 4200-465 Porto, PortugalINEGI, Institute of Science and Innovation in Mechanical Engineering and Industrial Engineering, Campus da FEUP, R. Dr. Roberto Frias 400, 4200-465 Porto, PortugalINEGI, Institute of Science and Innovation in Mechanical Engineering and Industrial Engineering, Campus da FEUP, R. Dr. Roberto Frias 400, 4200-465 Porto, PortugalINEGI, Institute of Science and Innovation in Mechanical Engineering and Industrial Engineering, Campus da FEUP, R. Dr. Roberto Frias 400, 4200-465 Porto, PortugalINEGI, Institute of Science and Innovation in Mechanical Engineering and Industrial Engineering, Campus da FEUP, R. Dr. Roberto Frias 400, 4200-465 Porto, PortugalINEGI, Institute of Science and Innovation in Mechanical Engineering and Industrial Engineering, Campus da FEUP, R. Dr. Roberto Frias 400, 4200-465 Porto, PortugalDepartment of Mechanical Engineering, Faculdade de Engenharia, Universidade do Porto, R. Dr. Roberto Frias s/n, 4200-465 Porto, PortugalPROMETHEUS, School of Technology and Management (ESTG), Polytechnic Institute of Viana do Castelo, Avenida do Atlântico n° 644, 4900-348 Viana do Castelo, PortugalPROMETHEUS, School of Technology and Management (ESTG), Polytechnic Institute of Viana do Castelo, Avenida do Atlântico n° 644, 4900-348 Viana do Castelo, PortugalINEGI, Institute of Science and Innovation in Mechanical Engineering and Industrial Engineering, Campus da FEUP, R. Dr. Roberto Frias 400, 4200-465 Porto, PortugalThis study focuses on the development of a machine learning (ML) model to elaborate on predictions of structural damage in submerged structures due to ocean states and subsequently compares it to a real-life case of a 6-month experiment with a benthic lander bearing a multitude of sensors. The ML model uses wave parameters such as height, period and direction as input layers, which describe the ocean conditions, and strains in selected points of the lander structure as output layers. To streamline the dataset generation, a simplified approach was adopted, integrating analytical formulations based on Morison equations and numerical simulations through the Finite Element Method (FEM) of the designed lander. Subsequent validation involved Fluid–Structure Interaction (FSI) simulations, using a 2D Computational Fluid Dynamics (CFD)-based numerical wave tank of the entire ocean depth to access velocity profiles, and a restricted 3D CFD model incorporating the lander structure. A case study was conducted to empirically validate the simulated ML model, with the design and deployment of a benthic lander at 30 m depth. The lander was monitored using electrical and optical strain gauges. The strains measured during the testing period will provide empirical validation and may be used for extensive training of a more reliable model.https://www.mdpi.com/2311-5521/10/1/10fluid–structure interactionbenthic landerstructural health monitoringmachine learning models |
| spellingShingle | Alexandre Brás dos Santos Hugo Mesquita Vasconcelos Tiago M. R. M. Domingues Pedro J. S. C. P. Sousa Susana Dias Rogério F. F. Lopes Marco L. P. Parente Mário Tomé Adélio M. S. Cavadas Pedro M. G. P. Moreira Predictive Analysis of Structural Damage in Submerged Structures: A Case Study Approach Using Machine Learning Fluids fluid–structure interaction benthic lander structural health monitoring machine learning models |
| title | Predictive Analysis of Structural Damage in Submerged Structures: A Case Study Approach Using Machine Learning |
| title_full | Predictive Analysis of Structural Damage in Submerged Structures: A Case Study Approach Using Machine Learning |
| title_fullStr | Predictive Analysis of Structural Damage in Submerged Structures: A Case Study Approach Using Machine Learning |
| title_full_unstemmed | Predictive Analysis of Structural Damage in Submerged Structures: A Case Study Approach Using Machine Learning |
| title_short | Predictive Analysis of Structural Damage in Submerged Structures: A Case Study Approach Using Machine Learning |
| title_sort | predictive analysis of structural damage in submerged structures a case study approach using machine learning |
| topic | fluid–structure interaction benthic lander structural health monitoring machine learning models |
| url | https://www.mdpi.com/2311-5521/10/1/10 |
| work_keys_str_mv | AT alexandrebrasdossantos predictiveanalysisofstructuraldamageinsubmergedstructuresacasestudyapproachusingmachinelearning AT hugomesquitavasconcelos predictiveanalysisofstructuraldamageinsubmergedstructuresacasestudyapproachusingmachinelearning AT tiagomrmdomingues predictiveanalysisofstructuraldamageinsubmergedstructuresacasestudyapproachusingmachinelearning AT pedrojscpsousa predictiveanalysisofstructuraldamageinsubmergedstructuresacasestudyapproachusingmachinelearning AT susanadias predictiveanalysisofstructuraldamageinsubmergedstructuresacasestudyapproachusingmachinelearning AT rogeriofflopes predictiveanalysisofstructuraldamageinsubmergedstructuresacasestudyapproachusingmachinelearning AT marcolpparente predictiveanalysisofstructuraldamageinsubmergedstructuresacasestudyapproachusingmachinelearning AT mariotome predictiveanalysisofstructuraldamageinsubmergedstructuresacasestudyapproachusingmachinelearning AT adeliomscavadas predictiveanalysisofstructuraldamageinsubmergedstructuresacasestudyapproachusingmachinelearning AT pedromgpmoreira predictiveanalysisofstructuraldamageinsubmergedstructuresacasestudyapproachusingmachinelearning |