Applying a machine learning method for cumulative fatigue damage estimation of the IEA 15MW wind turbine with monopile support structures - Research and report

Aug 5, 2026

Upload by Violet

Offshore bottom-fixed wind turbine support structures carry nearly all system mass and loading and must satisfy a design life exceeding 20 years under harsh marine conditions. Fatigue validation typically requires thousands of time-consuming simulations, especially for the fatigue limit state, making optimization slow. The study applies a machine learning method (AK-DA approach) to estimate cumulative fatigue damage for an IEA 15MW monopile support structure under multiple wind-wave conditions, using a joint wind-wave occurrence distribution from an Atlantic Sea site. Results show over 55× efficiency improvement with ~1% error.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Abstract

Introduction

Offshore wind turbine support structures and fatigue limit state

Fatigue damage estimation challenges and prior approaches

Method overview and case study

AK-DA machine learning approach

Wind-wave joint probability model and conditions

Results and discussion

Efficiency and accuracy of cumulative fatigue damage estimation

PAPER • OPEN ACCESS Applying a machine learning method for cumulative fatigue damage estimation of the IEA 15MW wind turbine with monopile support structures To cite this article: C Ren and Y Xing 2023 IOP Conf. Ser. : Mater. Sci. Eng. 1294 012014 View the article online for updates and enhancements. You may also like -Influence of soil properties on the shift in natural frequencies of a monopilesupported 5MW offshore wind turbine under scour Satish Jawalageri, Soroosh Jalilvand and Abdollah Malekjafarian -Integrated Multidisciplinary Constrained Optimization of Offshore Support Structures Rad Haghi, Turaj Ashuri, Paul L C van der Valk et al. -Simulation and numerical analysis of offshore wind turbine with monopile foundation S Lokesh Ram and R Mohana This content was downloaded from IP address [81.167.240.217](81.167.240.217) on 27/12/2023 at 08:58 IOP Conf. Series: Materials Science and Engineering 1294 (2023) 012014 doi:10.1088/1757-899X/1294/1/012014 Applying a machine learning method for cumulative fatigue damage estimation of the IEA 15MW wind turbine with monopile support structures C Ren* and Y Xing Department of Mechanical and Structural Engineering and Materials Science, University of Stavanger, Norway E-mail: [chao.ren@uis.no](chao.ren@uis.no) Abstract. Offshore support structures are critical for offshore bottom-fixed wind turbines, as they bear nearly all the mass and loading of wind turbine systems. In addition, the support structures are generally subjected to a harsh environment and require a design life of more than 20 years. However, the design validation of the support structure normally needs thousands of simulations, especially considering the fatigue limit state. Each simulation is quite time-consuming. This makes the design optimization of wind turbine support structures lengthy. Therefore, an effective approach for estimating the fatigue damage of wind turbine support structures is essential. This work uses a machine learning method named the AKDA approach for cumulative fatigue damage of wind turbine support structures. An offshore site in the Atlantic Sea is studied, and the related joint probability distribution of wind-wave occurrences is adopted in this work. The IEA 15MW wind turbine with monopile support structure is investigated, and different wind-wave conditions are considered. The cumulative fatigue damage of the monopile support structure is estimated by the AK-DA approach. The numerical results showed that this machine learning approach can efficiently and accurately estimate the cumulative fatigue damage of the monopile support structure. The efficiency is increased more than 55 times with an error of around 1% . The AK-DA approach can highly enhance the design efficiency of offshore wind support structures. 1. Introduction In pursuing sustainable energy solutions, wind power has emerged as a prominent source of renewable electricity generation. Many works [1, 2, 3, 4, 5, 6] have been carried out for wind turbine structures. Yang et al.[1] did a reliability-based design of wind turbine sub-structure optimization. Wang and Kolios [3] proposed a framework for system reliability assessment of offshore monopiles considering soil-solid interaction and harsh marine environments. Ren et al.[2, 5] compared different dynamic simulation approaches of wind turbine jacket foundations and carried out structural reliability analysis of jacket structures with machine learning approaches. Yu et al. [6] built a predictive model for the mooring line failure diagnosis and motion control. To increase wind power generation, the new trend is to install wind turbines offshore, as offshore wind has higher and uniform wind speeds. Offshore wind turbines are commonly classified into bottom-fixed and floating wind turbines (FWTs) . Compared to the bottom-fixed wind turbines, the technologies of FWTs are not yet mature. Therefore, the installed offshore wind turbines are mostly b

FAQs

Why is fatigue validation computationally expensive for offshore wind turbine support structures?

Fatigue limit-state assessment needs accurate coverage of many wind-wave combinations over the structure’s lifetime, leading to thousands of load cases and time-consuming simulations.

What machine learning method is used for cumulative fatigue damage estimation?

The study uses an AK-DA approach specifically designed to estimate cumulative fatigue damage efficiently.

How effective is the AK-DA approach compared with conventional simulation-based validation?

Numerical results indicate more than 55× increased efficiency with an error of around 1%, while maintaining accurate cumulative fatigue damage estimates.

Aug 5, 2026

Upload by Violet