Applicability of machine learning approaches for structural damage detection of offshore wind jacket structures based on low resolution data
| Autor: | Debora Cevasco, Athanasios Kolios, Ursula Smolka, J. Tautz-Weinert |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
History
Damage detection business.industry Computer science 020209 energy Supervised learning 020101 civil engineering 02 engineering and technology Machine learning computer.software_genre Novelty detection 0201 civil engineering Computer Science Applications Education System dynamics Offshore wind power SCADA 0202 electrical engineering electronic engineering information engineering Artificial intelligence Structural health monitoring business Focus (optics) computer TC |
| Zdroj: | Journal of Physics: Conference Series |
| ISSN: | 1742-6588 1070-9622 |
| DOI: | 10.5281/zenodo.7426495 |
| Popis: | Structural damage in offshore wind jacket support structures are relatively unlikely due to the precautions taken in design but it could imply dramatic consequences if undetected. This work explores the possibilities of damage detection when using low resolution data, which are available with lower costs compared to dedicated high-resolution structural health monitoring. Machine learning approaches showed to be generally feasible for detecting a structural damage based on SCADA data collected in a simulation environment. Focus is here given to investigate model uncertainties, to assess the applicability of machine learning approaches for reality. Two jacket models are utilised representing the as-designed and the as-installed system, respectively. Extensive semi-coupled simulations representing different operating load cases are conducted to generate a database of low-resolution signals serving the machine learning training and testing. The analysis shows the challenges of classification approaches, i.e. supervised learning aiming to separate healthy and damage status, in coping with the uncertainty in system dynamics. Contrarily, an unsupervised novelty detection approach shows promising results when trained with data from both, the as-designed and the as-installed system. The findings highlight the importance of investigating model uncertainties and careful selection of training data. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text