The stability and health of offshore platforms is important due to environmental issues, the high cost of installation and the value of these types of structures in the state of the country's economy. The most important failures of offshore structures are fatigue and corrosion, long-term monitoring and inspection of these structures is necessary to detect and identify such failures along with predicting the remaining life of structural members for the management of platforms. In this article, we investigate a smart method for predicting the remaining life of members in offshore platforms with the help of machine learning. For this purpose, a real platform in the Persian Gulf environment has been modeled in SACS software, and by creating different failure scenarios in it, using the results of spectral fatigue analysis in SACS software, the remaining life of structural members has been predicted with the help of machine learning algorithms. And management approaches have been presented according to the analyzes carried out.
Nazari Ghalati, M. N., & Taghikhany, T. (2023). Predicting the useful life of offshore structure members with random forest algorithm. Journal of Civil and Environmental Engineering, (), -. doi: 10.22034/ceej.2023.56024.2244
MLA
Mohammad Nabi Nazari Ghalati; Touraj Taghikhany. "Predicting the useful life of offshore structure members with random forest algorithm". Journal of Civil and Environmental Engineering, , , 2023, -. doi: 10.22034/ceej.2023.56024.2244
HARVARD
Nazari Ghalati, M. N., Taghikhany, T. (2023). 'Predicting the useful life of offshore structure members with random forest algorithm', Journal of Civil and Environmental Engineering, (), pp. -. doi: 10.22034/ceej.2023.56024.2244
VANCOUVER
Nazari Ghalati, M. N., Taghikhany, T. Predicting the useful life of offshore structure members with random forest algorithm. Journal of Civil and Environmental Engineering, 2023; (): -. doi: 10.22034/ceej.2023.56024.2244