scholarly journals Prediction of dynamic mooring responses of a floating wind turbine using an artificial neural network

2021 ◽  
Vol 1201 (1) ◽  
pp. 012023
Author(s):  
F A Bjørni ◽  
S Lien ◽  
T Aa Midtgarden ◽  
G Kulia ◽  
A Verma ◽  
...  
Keyword(s):  
Machine Learning ◽  
Wind Turbine ◽  
Wave Height ◽  
Significant Wave Height ◽  
Learning Methods ◽  
Mooring Lines ◽  
Peak Period ◽  
Significant Wave ◽  
Machine Learning Methods ◽  
Artificial Neural

Abstract Numerical simulations in coupled aero-hydro-servo-elastic codes are known to be a challenge for design and analysis of offshore wind turbine systems because of the large number of design load cases involved in checking the ultimate and fatigue limit states. To alleviate the simulation burden, machine learning methods can be useful. This article investigates the effect of machine learning methods on predicting the mooring line tension of a spar floating wind turbine. The OC3 Hywind wind turbine with a spar-buoy foundation and three mooring lines is selected and simulated with SIMA. A total of 32 sea states with irregular waves are considered. Artificial neural works with different constructions were applied to reproduce the time history of mooring tensions. The best performing network provides a strong average correlation of 71% and consists of two hidden layers with 35 neurons, using the Bayesian regularisation backpropagation algorithm. Sea states applied in the network training are predicted with greater accuracy than sea states used for validation of the network. The correlation coefficient is primarily higher for sea states with lower significant wave height and peak period. One sea state with a significant wave height of 5 meters and a peak period of 9 seconds has an average extreme value deviation for all mooring lines of 0.46%. Results from the study illustrate the potential of incorporating artificial neural networks in the mooring design process.

Semi-Empirical Crest Distributions of Long-Crest Nonlinear Waves of Three-Hour Duration

2017 ◽  
Author(s):  
Zhenjia (Jerry) Huang ◽  
Qiuchen Guo
Keyword(s):  
Nonlinear Wave ◽  
Wave Height ◽  
Model Test ◽  
Significant Wave Height ◽  
Spectral Peak ◽  
Wave Crest ◽  
Empirical Formulas ◽  
Peak Period ◽  
Significant Wave ◽  
Semi Empirical

In wave basin model test of an offshore structure, waves that represent the given sea states have to be generated, qualified and accepted for the model test. For seakeeping and stationkeeping model tests, we normally accept waves in wave calibration tests if the significant wave height, spectral peak period and spectrum match the specified target values. However, for model tests where the responses depend highly on the local wave motions (wave elevation and kinematics) such as wave impact, green water impact on deck and air gap tests, additional qualification checks may be required. For instance, we may need to check wave crest probability distributions to avoid unrealistic wave crest in the test. To date, acceptance criteria of wave crest distribution calibration tests of large and steep waves of three-hour duration (full scale) have not been established. The purpose of the work presented in the paper is to provide a semi-empirical nonlinear wave crest distribution of three-hour duration for practical use, i.e. as an acceptance criterion for wave calibration tests. The semi-empirical formulas proposed in this paper were developed through regression analysis of a large number of fully nonlinear wave crest distributions. Wave time series from potential flow simulations, computational fluid dynamics (CFD) simulations and model test results were used to establish the probability distribution. The wave simulations were performed for three-hour duration assuming that they were long-crested. The sea states are assumed to be represented by JONSWAP spectrum, where a wide range of significant wave height, peak period, spectral peak parameter, and water depth were considered. Coefficients of the proposed semi-empirical formulas, comparisons among crest distributions from wave calibration tests, numerical simulations and the semi-empirical formulas are presented in this paper.

Development of Operational Limit Diagrams for Offshore Lifting Procedures

2015 ◽  
Author(s):  
Leonardo Roncetti ◽  
Fabrício Nogueira Corrêa ◽  
Carl Horst Albrecht ◽  
Breno Pinheiro Jacob
Keyword(s):  
Wave Height ◽  
Significant Wave Height ◽  
Technological Development ◽  
Automatic Generation ◽  
Dynamic Responses ◽  
Offshore Platforms ◽  
Peak Period ◽  
Significant Wave ◽  
Wave Heights ◽  
Offshore Crane

Lifting operations with offshore cranes are fundamental for proper functioning of a platform. Despite the great technological development, offshore cranes load charts only consider the significant wave height as parameter of environmental load, neglecting wave period, which may lead to unsafe or overestimated lifting operations. This paper aims to develop a method to design offshore crane operational limit diagrams for lifting of personnel and usual loads, in function of significant wave height and wave peak period, using time domain dynamic analysis, for a crane installed on a floating unit. The lifting of personnel with crane to transfer between a floating unit and a support vessel is a very used option in offshore operations, and this is in many cases, the only alternative beyond the helicopter. Due to recent fatal accidents with lifting operations in offshore platforms, it is essential the study about this subject, contributing to the increase of safety. The sea states for analysis were chosen covering usual significant wave heights and peak periods limits for lifting operations. The methodology used the SITUA / Prosim software to obtain the dynamic responses of the personnel transfer basket lifting and container loads on a typical FPSO. Through program developed by the author, it was implemented the automatic generation of diagrams as a function of operational limits. It is concluded that using this methodology, it is possible to achieve greater efficiency in the design and execution of personnel and routine load lifting, increasing safety and a wider weather window available.

Comparison of Bivariate Models of the Distribution of Significant Wave Height and Peak Wave Period

2007 ◽  
Author(s):  
Catarina S. Soares ◽  
C. Guedes Soares
Keyword(s):  
Wave Height ◽  
Significant Wave Height ◽  
Bivariate Normal Distribution ◽  
Wave Period ◽  
Peak Period ◽  
Data Set ◽  
Significant Wave ◽  
The North ◽  
Bivariate Models ◽  
The North Sea

This paper presents the results of a comparison of the fit of three bivariate models to a set of 14 years of significant wave height and peak wave period data from the North Sea. One of the methods defines the joint distribution from a marginal distribution of significant wave height and a set of distributions of peak period conditional on significant wave height. Other method applies the Plackett model to the data and the third one applies the Box-Cox transformation to the data in order to make it approximately normal and then fits a bivariate normal distribution to the transformed data set. It is shown that all methods provide a good fit but each one have its own strengths and weaknesses, being the choice dependent on the data available and applications in mind.

scholarly journals A Comparison of Machine Learning Methods in a High-Dimensional Classification Problem

2014 ◽  
Vol 5 (3) ◽  
pp. 82-96 ◽  
Author(s):  
Marijana Zekić-Sušac ◽  
Sanja Pfeifer ◽  
Nataša Šarlija
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Classification Accuracy ◽  
Classification Problem ◽  
High Dimensional ◽  
Nearest Neighbour ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Dimensional Classification ◽  
Artificial Neural

Abstract Background: Large-dimensional data modelling often relies on variable reduction methods in the pre-processing and in the post-processing stage. However, such a reduction usually provides less information and yields a lower accuracy of the model. Objectives: The aim of this paper is to assess the high-dimensional classification problem of recognizing entrepreneurial intentions of students by machine learning methods. Methods/Approach: Four methods were tested: artificial neural networks, CART classification trees, support vector machines, and k-nearest neighbour on the same dataset in order to compare their efficiency in the sense of classification accuracy. The performance of each method was compared on ten subsamples in a 10-fold cross-validation procedure in order to assess computing sensitivity and specificity of each model. Results: The artificial neural network model based on multilayer perceptron yielded a higher classification rate than the models produced by other methods. The pairwise t-test showed a statistical significance between the artificial neural network and the k-nearest neighbour model, while the difference among other methods was not statistically significant. Conclusions: Tested machine learning methods are able to learn fast and achieve high classification accuracy. However, further advancement can be assured by testing a few additional methodological refinements in machine learning methods.

Spectral Modeling of Sea States With Multiple Wave Systems

1992 ◽  
Vol 114 (4) ◽  
pp. 278-284 ◽  
Author(s):  
C. Guedes Soares ◽  
M. C. Nolasco
Keyword(s):  
Wave Height ◽  
Significant Wave Height ◽  
Theoretical Models ◽  
Wave System ◽  
Spectral Parameters ◽  
Peak Period ◽  
Multiple Wave ◽  
Significant Wave ◽  
General Acceptance ◽  
Spectral Models

The spectral models of individual wave systems have one peak and are described by theoretical models that have gained general acceptance. This work deals with sea states with more than one wave system, leading to spectral models with two or more peaks. Use is made of spectra derived from measurements off the Portuguese Coast and data is provided as to their probability of occurrence as well as about the dependence of the spectral parameters on the significant wave height and peak period. It is shown that wind-dominated and swell-dominated two-peaked spectra tend to occur in different areas of the scatter diagram. The spectral parameters of the two-peaked spectra show little correlation with significant wave height and peak period.

Sign in / Sign up

Export Citation Format

Share Document