1,721,194 research outputs found
Condition monitoring of mooring systems for Floating Offshore Wind Turbines using Convolutional Neural Network framework coupled with Autoregressive coefficients
Full text linkThis research presents a novel approach proposed for the monitoring of mooring systems in Floating Offshore Wind Turbines (FOWTs), employing a combination of Convolutional Neural Networks (CNNs) and Auto-Regressive (AR) models. CNN finds broad application in monitoring intricate structures, as they adeptly handle noisy response data without necessitating profound domain expertise. The precision of CNNs relies on the extraction of meaningful features from input data, necessitating meticulous data curation and labeling for optimal computational efficiency and accurate estimation. Emphasis is placed on the preference for feature-rich small datasets over voluminous yet sparse datasets, aiming to enable CNNs to discern crucial patterns more effectively and mitigate issues such as overfitting and extensive preprocessing. The novelty of the proposed approach lies in the integration of AR models, which serve to compress data and enhance damage-sensitive characteristics in the input for CNNs. This integration involves deploying regression models fitted to historical responses, parameterized with AR coefficients sensitive to damage, and further classifying severity using CNNs. The sequential nature of this approach addresses challenges such as vanishing/exploding gradients, particularly for extended historical data, while also attenuating the impact of noise and irrelevant information through data compression. The study explores the effectiveness of the coupled AR-CNN method in monitoring FOWT mooring lines, with a specific focus on two levels of damage identification: detection with classification and damage severity across diverse damage and operational scenarios. The modified methodology exhibits superior outcomes by conducting a performance analysis against traditional CNNs and other machine-learning methods, highlighting the potential of the AR-CNN strategy to improve the precision of FOWT mooring line condition monitoring. These findings underscore the AR-CNN strategy's potential to enhance the accuracy of FOWT mooring line condition monitoring
Effects of the mooring line configuration on the dynamics of a point absorber
No full textThe aim of this paper is to study the dynamics of a floating body with characteristics comparable to a point absorber wave energy converter with different mooring systems, in geometrical configuration or in the materials. To this purpose, the dynamics of a moored buoy is investigated. The point absorber is modeled as a spherical buoy in plane two-dimensional motion, and it is studied under the action of irregular unidirectional wind-generated waves, moored to the seabed by means of one, two or three mooring lines. Two different sets of moorings are considered, and typical wires and chains used in offshore technology are considered, leading to a total of 6 case studies. A quasi-static approach is used for modeling the restoring forces needed to keep buoy into station, using an innovative iterative procedure able to predict for each time instant and for each cable the lay down length of the cable, being each mooring line allowed to be taut or slack. Approaches in the time and frequency domains are used to obtain the system responses in intermediate waters, where these facilities are usually installed. Results for all case studies are compared both in terms of statistics of response and tensions on the top of the cable. © 2013 by ASME
Integrated damage detection and time-series data augmentation for floating offshore mooring systems via variational semi-supervised learning
Full text linkThe dynamics and stability of the semi-submersible offshore platforms are significantly impacted by the degradation of the mooring system. Identifying structural integrity issues in mooring systems through a data-driven approach is challenging due to the infrequency of damage events and the difficulties in recording them. To address these challenges, this study proposes the Time-Series Variational Semi-Supervised Learning (TSVSSL) framework, which effectively bridges the gap between supervised and unsupervised learning by leveraging unlabelled data for damage detection. The proposed framework features a distinctive training procedure in which the encoder-decoder and classifier components are trained concurrently. This process produces a well-clustered latent representation that enhances damage detection and supports class-specific artificial data generation. A numerical study using simulated responses of a 5 MW semi-submersible FOWT under varying metocean conditions demonstrated that the proposed framework outperformed existing deep learning methods in damage detection, achieving superior accuracy, precision, recall, and F1 score. Further, a rejection sampling technique is also introduced to effectively generate artificial data that closely aligns with actual time series displacement response. The novelty of the proposed framework lies in its dual focus on damage detection and artificial data generation marking a significant advancement in the data-driven assessment of mooring systems
Coupled surge-heave-pitch dynamic modeling of spar-moonpool-riser interaction
No full textDue to the rather intense ongoing development of deep water gas and oil fields, the technical community has devoted considerable attention to the dynamic behavior of Spar floating systems. Spar dynamics exhibits a highly nonlinear behavior due to the presence of various components such as mooring lines, moonpool, and risers. Certain studies have focused on the reduction of the heave response of single-degree-of-freedom Spar models due to the oscillations of water entrapped in the moonpool through the partially closed bottom plates. In this paper, a novel coupled six-degree-of-freedom analytical model of a Spar system comprising top tensioned risers is proposed. The model accounts for the interactions among the Spar hull kinematics (heave, surge, and pitch), the riser kinematics (heave and surge), and the moonpool. This model involves six coupled differential equations comprising nonlinearities associated not only with stiffness and damping but also with inertia terms. A dynamic analysis is performed by subjecting the model to JONSWAP ocean wave spectrum compatible extreme forces (corresponding to the 100 year wave) and to moments applied to the center of gravity computed by means of a standard motion simulation program. Both numerical and analytical techniques (statistical linearization including inertia terms) are used for the determination of the response of the proposed dynamic model, both in the time and the frequency domains. Related parameter study results are reported, including ones pertaining to the dependence of the Spar system motion on the degree of opening of the bottom plates. © 2011 American Society of Mechanical Engineers
Coupled surge-heave-pitch dynamic modeling of spar-moonpool-riser interaction
No full textDue to the ongoing rather intense development of deep water gas and oil fields, the technical community has been increasingly focusing its attention to the dynamic behavior of Spar floating structures. Spar dynamics exhibits a highly non-linear behavior due to the presence of various components such as mooring lines, moonpool, and risers (Spanos et al., 2005). In this regard Gupta et al, 2008a, have studied the reduction of the heave response in a single degree-of-freedom spar model due to the oscillations of water entrapped in the moonpool through the partially closed bottom plates. In this paper a novel coupled six-degree-of-freedom analytical model of a Spar system tensioned by TTR risers is proposed. The model accounts for the interactions among spar hull motions (heave, surge and pitch), the riser motion (heave and surge), and the moonpool. This model involves six coupled nonlinear differential equations comprising nonlinearity terms associated not only with stiffness and damping but also with inertia terms. A dynamic analysis is performed by subjecting the model to JONSWAP ocean wave spectrum compatible extreme forces (corresponding to the 100 yr wave); and to moments applied to the center of gravity computed by means of standard motion program. Both numerical and semi-analytical techniques (equivalent linearization including inertial terms) are used for the determination of the response of the proposed dynamic model both in the time and frequency domains. Some parameter study results are reported, including ones pertaining to the dependence of the spar motion on the open guide plates. Copyright © 2009 by ASME
Non-linear random wave groups with a superimposed current
No full textIn this paper a new solution for non-linear random wave groups in the presence of a uniform current is obtained, by extending to the second-order the Boccotti's 'Quasi-Determinism' (QD) theory. The second formulation of the QD theory gives the mechanics of linear random wave groups when a large crest-to-trough wave height occurs. Here the linear QD theory is firstly applied to the wave-current interaction. Therefore the non-linear expressions both of free surface displacement and velocity potential are obtained, to the second-order in a Stokes' expansion. Finally some numerical applications are presented in order to analyze both the wave profile and the wave kinematics. Copyright © 2006 by ASME
On the assessment of extreme forces on a floating spar wind turbine
No full textA model based on the Quasi-Determinism theory is used in this paper to evaluate the most probable extreme excitations and their time histories on a 3-degree-of-freedom (i.e. surge, heave and pitch motions) model of a floating spar-type 5 MW wind turbine. Numerical simulations of forces in the time domain on the hull and tower of the structure have been carried out using FAST, accounting for the hydrodynamic characteristics of the floater by means of WAMIT. Sea wave forces and joint wave and wind forces have been calculated, under the hypothesis of typical wave surface elevation and wind velocity power density functions. In particular, different case studies have been chosen accounting for operational conditions of significant wave height and wind speed in a site in the Atlantic Ocean. An approach based on the Quasi-determinism theory is then used in order to assess, for each case study, the time history of all the components of the excitations when the maximum of one component of the forces occurs. Studies about the validity of the model and the qualitative and quantitative anomaly of the simulations with respect to the herein presented approach are also included. © 2014 Taylor & Francis Group, London
Diagnosis of the health status of mooring systems for floating offshore wind turbines using autoencoders
Full text linkFloating offshore wind turbines (FOWTs) show promise in terms of energy production, availability, and sustainability, but remain unprofitable due to high maintenance costs. This work proposes a deep learning algorithm to detect mooring line degradation and failure by monitoring the dynamic response of the publicly available DeepCWind OC4 semi-submersible platform. This study implements an autoencoder capable of predicting multiple forms of damage occurring at once, with various levels of severity. Given the scarcity of real data, simulations performed in OpenFAST, recreating both healthy and damaged mooring systems, are used to train and validate the algorithm. The novelty of the proposed approach consists of using a set of key statistical metrics describing the platform's displacements and rotations as input layer for the autoencoder. The statistics of the responses are calculated at 33-minute-long sea states under a broad spectrum of metocean and wind conditions. An autoencoder is trained using these parameters to discover that the proposed algorithm is capable of detecting mild anomalies caused by biofouling and anchor displacements, with correlation coefficients up to 98.51% and 99.16%, respectively. These results are encouraging for the continuous health monitoring of FOWT mooring systems using easily measurable quantities to plan preventive maintenance actions adequately
On linearization of Morison force given by high three-dimensional sea wave groups
No full textIn-line loading on slender marine structures may be computed by means of the Morison equation, which includes the inertia term (depending on wave acceleration) and the drag term (depending on square velocity). In the presence of random sea waves (either two- or three-dimensional waves), the Morison equation needs a linearization in the drag term, in order to obtain the force spectrum. In this paper, the Boccotti's Quasi-Determinism theory is applied for the calculation of the drag force given by high three-dimensional wave groups. It is shown that when a crest-to-trough wave of given height H occurs on a vertical pile, the quotient between maxima of sectional drag Morison force and of force given by linearization (both calculated at a fixed depth z) is equal to C times H / Hs, where Hs is the significant wave height. The coefficient C is equal to 1.25 for narrow-band spectra, whatever be the value of z is. For the three-dimensional random wave groups it is obtained that C is equal to 1.25 for z close to 0; the value of C slightly decreases on approaching the bottom. Then, it is shown that the Borgman linearization is not conservative for the calculation of extreme drag forces in three-dimensional waves: for example the maximum drag Morison force given by a wave height H equal to 2 times Hs, is close to 2.3 times the maximum force given by linearization. The results are finally validated by the means of Monte Carlo simulations of random sea waves. © 2007 Elsevier Ltd. All rights reserved
- …
