ISOPE

_ Predicting the ultimate bearing capacity of a deep-sea pipeline on the soft clayey seabed is crucial to on-bottom stability and global buckling analyses. Based on the slip-line field theory, an analytical solution is derived for the undrained bearing capacity of an obliquely loaded pipeline on a clayey seabed obeying the Tresca criterion. For a wished-in-place pipeline, the failure mechanisms and the corresponding pipe-soil interface conditions are proposed for the vertical and the lateral instability mode separately. Based on the derived slip-line field solution, a series of failure envelopes are established for various pipe-soil interface conditions. The analytical solutions match well with the previous numerical and theoretical results. The parametric study indicates that the embedment-to-diameter ratio and the loading angle are the key parameters for the bearing capacity of an obliquely loaded pipeline. Introduction Soft clayey sediments are widely distributed in the deep waters (see Liu et al., 2021). The deep-sea pipelines are commonly laid directly on the seabed, where the pipelines may penetrate partially or even completely into the soil during their service period (DNV GL, 2017). Under the action of ocean currents, a partially embedded pipeline would suffer an oblique hydrodynamic loading, including the drag (horizontal) and the lift (vertical) force. While a deep-sea pipeline transports oil and gas with high temperature and high pressure, axial compressive forces could be induced along the pipeline (Taylor and Gan, 1986). Under the external (hydrodynamic forces) and/or the internal (axial compressive forces due to the rise of temperature and pressure) loads, the pipeline may break away from its original location while forfeiting the on-bottom stability (Gao et al., 2007), and even buckle globally along the seabed surface (Bruton et al., 2006). Therefore, a reliable assessment of the ultimate bearing capacity for an obliquely loaded pipeline on the clayey seabed is essential to predicting the instability of deep-sea pipelines (Fredsøe, 2016; Gao, 2017).

International Journal of Offshore and Polar Engineering

doi: 10.17736/ijope.2022.cl21

ISOPE

ISOPE-22-32-4-473

clayey seabed, correlation, deep-sea pipeline, envelope, oblique loading, obliquely, offshore pipeline, pipe, pipe-soil interaction, pipe-soil interface, pipeline, slip-line field solution, ultimate bearing capacity, Upstream Oil & Gas, White

Country: North America > United States (0.89)

Genre: Research Report (0.34)

Industry: Energy > Oil & Gas > Upstream (1.00)

SPE Disciplines: Facilities Design, Construction and Operation > Pipelines, Flowlines and Risers > Offshore pipelines (1.00)

Zha, Ruosi (Sun Yat-Sen University, Zhuhai) | Zhao, Weiwen (Shanghai Jiao Tong University, Shanghai) | Wan, Decheng (Shanghai Jiao Tong University, Shanghai)

Numerical Study on Water Entry of Projectiles with Various Head Shapes by a Multiphase Moving Particle Semi-implicit Method

_ In this paper, the low-speed water entry of four projectiles with various head types is numerically studied by using an improved multiphase moving particle semi-implicit (MPS) method. The projectiles are composed of a solid circular cylinder with L/D=4.5 and different head shapes, including a hemispherical head and three cone-shaped heads (90°~150°). During the water entry of these free-falling projectiles, splashing water, the deformed free surface, and the cavity evolution behind the cylinder are presented, which show agreement with experimental data. The vertical velocities and forces obtained by the multiphase MPS method are given. The influences of varying head shapes on the motion of the projectiles and the generation and closure of cavities are analyzed. Introduction There widely exist water entry phenomena in the defense industry and ocean engineering with a fluid-structure interaction and multiphase flow. Water entry by a projectile involving cavity formation and collapse has been investigated theoretically. For example, Lee et al. (1997) developed an analytical model for the cavity dynamics to study the high-speed water entry of a sphere. It was indicated that a cavity can be characterized as a deep closure prior to closure at the surface for high-speed water entry, and the time of deep closure was constant, which was independent of the impact velocity. Mirzaei et al. (2020) proposed a transient model to predict the shape of the oblique water entry cavity for a cylindrical projectile at different angles. The predicted projectile attitude and the trajectory of the projectile agreed well with the experimental data. Experimental studies on both low-speed and high-speed water entry with cavities have also been extensively carried out by using high-speed cameras. For example, Truscott and Techet (2009a, 2009b) and Techet and Truscott (2011) experimentally studied the trajectories, forces, and cavity formation behind spinning hydrophobic and hydrophilic spheres after water entry in the MIT Experimental Hydrodynamics Laboratory at the Massachusetts Institute of Technology. The splash and cavity of spheres’ water entry with varying spin rates and impact velocities were compared. Yang et al. (2014) conducted a series of experiments of low-speed water entry of projectiles with different head types. The snapshots of the cavity-running phase under different velocity and entry angle conditions were recorded by high-speed photography, and the influences of head types on the characteristics of cavity formation and closure were analyzed. The oblique high-speed water entry of projectiles was investigated by Song et al. (2020). The deflection of trajectories and the evolution of supercavities were analyzed.

International Journal of Offshore and Polar Engineering

doi: 10.17736/ijope.2022.ak50

ISOPE

ISOPE-22-32-4-402

cavity, cylinder, Engineering, equation, Fluid Dynamics, head shape, interface, method, model 1, multiphase flow, numerical study, particle, Particle Method, particle semi-implicit method, projectile, Simulation, Upstream Oil & Gas, water entry

Country:

Asia > China (0.47)
North America > United States > Massachusetts (0.24)

Genre: Research Report (0.54)

Industry: Energy > Oil & Gas > Upstream (1.00)

SPE Disciplines:

Reservoir Description and Dynamics > Reservoir Fluid Dynamics > Multiphase flow (0.89)
Reservoir Description and Dynamics > Reservoir Simulation (0.83)

_ This paper presents an approach for calculating the time-variant reliability of floating structures under corrosion deterioration. Based on in situ corrosion measurement data in the South China Sea, a corrosion prediction model is established. Ultimate strength under discrete stochastic extreme load events for the large floating structures is chosen as the time-dependent limit state. An effective method for time-variant reliability assessment subjected to corrosion deterioration is established based on conditional probability theory. The estimation of instantaneous failure probability for a typical floating structure is calculated by the first-order reliability method. Results show that severe corrosion deterioration degrades ultimate strength and reduces time-variant reliability over time. Introduction Time-variant reliability attracts attention from industry when it comes with corrosion and fatigue in offshore floating structures. With the long-term serviceability of large floating structures, general corrosion may occur in stiffened plates and cause degradation of longitudinal or local strength. Therefore, reliability assessment of floating structures with corrosion deterioration is essential during the long-term serviceability. The progressive strength degradation has a detrimental impact on long-term safety and reliability of floating marine structures (Abbas and Shafiee, 2020). Some literature identifies corrosion as one of main failure modes, which can cause loss of reliability (Guo et al., 2008), especially for very large floating structures (VLFS), which consist of several modules, located far away from harbors. Because of the distances and sea environment involved, VLFS cannot be maintained on schedule, and the corrosion degradation needs to be considered in evaluating their service lifetime. In general, corrosion can have several subcategories: general, pitting, crevice, and galvanic. General and pitting corrosion commonly occur in marine structures. The corrosion rate measurement is used as a method to calculate corrosion depth when the corrosion is uniform. The corrosion mainly leads to thickness reduction of plates and results in reduction of the hull girder section modulus of floating structures (Guedes Soares and Garbatov, 1999).

International Journal of Offshore and Polar Engineering

doi: 10.17736/ijope.2022.jc875

ISOPE

ISOPE-22-32-4-457

Country: Asia > China (0.87)

Genre:

Research Report > New Finding (0.34)
Research Report > Experimental Study (0.34)

Industry: Energy > Oil & Gas > Upstream (0.36)

SPE Disciplines:

Well Completion > Well Integrity > Subsurface corrosion (tubing, casing, completion equipment, conductor) (1.00)
Facilities Design, Construction and Operation > Pipelines, Flowlines and Risers > Materials and corrosion (1.00)
Facilities Design, Construction and Operation > Offshore Facilities and Subsea Systems (1.00)

Technology:

Information Technology > Modeling & Simulation (0.49)
Information Technology > Artificial Intelligence > Machine Learning (0.34)

Numerical Study of Three-Dimensional Water Entry Problems of Complex Structures Using Particle Method

Deng, Rui (Sun Yat-sen University, Zhuhai) | Lyu, Hong-Guan (Sun Yat-sen University, Zhuhai) | Sun, Peng-Nan (Sun Yat-sen University, Zhuhai) | Huang, Xiao-Ting (Sun Yat-sen University, Zhuhai) | Wu, Tie-Cheng (Sun Yat-sen University, Zhuhai)

_ Water entry problems are critical in hydrodynamics because of strong impact pressure and complex structural motions in such phenomena. This paper is dedicated to presenting a fully 3-D smoothed particle hydrodynamics (SPH) model for the water entry problems of complex structures. First, the adopted SPH model is briefly introduced. Subsequently, two water entry benchmarks are performed to validate the accuracy and stability of the utilized SPH model. Furthermore, one typical engineering application related to aircraft ditching is performed. The present SPH model is clearly demonstrated to possess satisfactory accuracy and stability for simulating water entry problems. Introduction Water entry problems of complex structures are one of the most important topics in hydrodynamics because such phenomena involve extensive complex physical processes (e.g., hydroelasticity, turbulence, cavitation, multiphase effects, and fluid–structure interaction (FSI)) (Truscott et al., 2014). For such complex FSI processes, experimental methods are one of the most reliable strategies to investigate water entry problems. Notwithstanding, two limitations block the wide use of this method in practical applications. One is that scaling effects from model tests are inevitably encountered when transforming the model measurements into full-scale data (Lugni et al., 2021). The second is that physical tests are always expensive, and many extreme case conditions are hard to reproduce in a laboratory. Therefore, the technique of computational fluid dynamics (CFD) can be a more feasible strategy in engineering designs. In terms of CFD, traditional Eulerian mesh-based methods (e.g., finite volume (FV)) have been widely adopted to simulate the water entry problems for different simple objects such as cylinders (Hou et al., 2018), wedges (K Wang et al., 2021), and spheres (Shen et al., 2022). However, applying them for complex structures with complex geometrical surfaces is relatively rare. In fact, several researchers have explored this topic by using some mature commercial packages (e.g., STAR-CCM+) (Tregde and Nestegård, 2014; Tregde, 2015; Huang et al., 2021), finding that some violent and nonlinear water surface behaviors (e.g., splashing and breaking) are hard to accurately capture because of the inherent mass nonconservation property of the FV method. Besides, although the so-called overset mesh (OM) technique can be used to realize the six-degrees-of-freedom (6DoF) motion of rigid objects in the FV framework, it is well-known that serious field discontinuities exist at the overset–background interface where flow information is exchanged between these two regions. Such a characteristic could somewhat reduce the accuracy of the FV results.

International Journal of Offshore and Polar Engineering

doi: 10.17736/ijope.2022.jc877

ISOPE

ISOPE-22-32-4-424

aircraft, appl ocean res, benchmark, complex structure, Engineering, Fluid Dynamics, lifeboat, numerical study, Particle Method, reservoir simulation, solver, sph simulation, sph solver, stability, three-dimensional water entry problem

Country:

Asia > China (0.46)
North America (0.46)

Industry: Energy > Oil & Gas (0.46)

SPE Disciplines:

Data Science & Engineering Analytics > Information Management and Systems (0.46)
Reservoir Description and Dynamics > Reservoir Simulation (0.34)
Reservoir Description and Dynamics > Reservoir Fluid Dynamics (0.34)

Technology: Information Technology (1.00)

Hydrogen Effect on Linepipe Steel and Material Compatibility to a High-pressure Hydrogen Pipeline

Ishikawa, Nobuyuki (JFE Steel Corporation) | Shimamura, Junji (JFE Steel Corporation) | Izumi, Daichi (JFE Steel Corporation) | Okano, Hiroshi (JFE Steel Corporation) | Nishihara, Yoshihiro (JFE Steel Corporation)

_ In this paper, the basic material behavior and mechanical properties of linepipe steel under high-pressure hydrogen were investigated. A hydrogen exposure test was first conducted to evaluate hydrogen absorption into the steel from gaseous hydrogen at pressures of up to 25 MPa. It was found that about 0.1 ppm hydrogen was absorbed into the steel, which is the level of hydrogen absorption in a mildly sour environment. This result reminds us of the possibility of hydrogen stress cracking; accordingly, the proper material is recommended for hydrogen use. Then, fracture toughness and fatigue crack growth tests were conducted using a recently produced Grade X65 longitudinal submerged arc welded linepipe with a fine-grained bainitic microstructure, revealing excellent performance of fracture and fatigue resistance under a 21 MPa high-pressure hydrogen condition. Fatigue crack growth analysis of the hydrogen pipeline was finally conducted based on the American Society of Mechanical Engineers hydrogen pipeline design code. Introduction The infrastructure for hydrogen storage and transportation needs to be safely used for a carbon-neutral society. One of the most important issues for the integrity of a hydrogen system is material degradation caused by hydrogen. It is well understood that solute hydrogen in steel causes the degradation of material properties—so-called hydrogen embrittlement. The hydrogen effect on the mechanical properties of linepipe steels has been extensively investigated in the past decades. A slow strain rate tensile test with a smooth round bar specimen under gaseous hydrogen showed a modest loss of ductility, while yield and tensile strength do not show a large influence by hydrogen (Hoover et al., 1981; Cialone and Holbrook, 1985; Stalheim et al., 2010). On the other hand, the hydrogen effect on ductility becomes significant in the case of a notched specimen and shows a large drop in the reduction of area because a quasi-cleavage fracture appeared on the fracture surface (Hoover et al., 1981; Zhou et al., 2021). Fracture toughness is also reduced in high-pressure gaseous hydrogen (Hoover et al., 1981; Gutierrez-Solana and Elices, 1982; Cialone and Holbrook, 1985; Stalheim et al., 2010). It seems that lowgrade linepipe steels such as X42 or X52 tend to show a lower fracture toughness value in hydrogen (KIH) than more recent high-grade steels.

International Journal of Offshore and Polar Engineering

doi: 10.17736/ijope.2022.jc878

ISOPE

ISOPE-22-32-4-448

Country:

North America > United States (1.00)
Asia (0.93)

Industry:

Energy > Oil & Gas (1.00)
Energy > Renewable > Hydrogen (0.86)
Materials > Metals & Mining (0.66)

SPE Disciplines:

Well Completion > Hydraulic Fracturing (1.00)
Production and Well Operations > Production Chemistry, Metallurgy and Biology > Corrosion inhibition and management (including H2S and CO2) (0.89)
Health, Safety, Environment & Sustainability > Sustainability/Social Responsibility > Sustainable development (0.54)
Health, Safety, Environment & Sustainability > Environment > Climate change (0.54)

Buinyi, Aleksei (Marine Information Technologies) | Zhdanova, Ekaterina (Marine Information Technologies) | Evdokimov, Aleksandr (Marine Information Technologies) | Sukhikh, Natalia (Marine Information Technologies)

On the Artificial Intelligence for the Sea State Forecast Along the Northern Sea Route

_ Nowadays, the problem of short- and long-term forecasts in the Arctic region becomes more important for global logistics and engineering. Here, we present our first findings on the application of machine learning (ML) methods to oceanographic data. The Barents Sea is the region of our interest, and we focus on the analysis of wind waves and surface currents. We applied several ML models to simulate observed time series and obtained short- and long-term forecasts. The Long Short Time Memory model and XGBoost algorithms showed better results in fitting the observed curve. Introduction The Russian Arctic has changed rapidly as a result of modern climate change. It has had a significant impact on global economics and logistics. The Northern Sea Route is the key transport way in this region. But the region is still characterized by harsh hydrometeorological and ice conditions during the autumn–winter season. It is still poorly covered by regular observations. Nowadays, the problem of short- and long-term forecasting has become more important for logistics, operations, and engineering. Numerical modeling and forecasting of atmospheric, oceanic, and ice conditions should help plan safe and cost-effective routes. In response to the request, at the Marine Research Center, we are developing a complex forecasting system using numerical modeling and Artificial Intelligence methods. Recently, the application of machine learning (ML) methods in oceanography and geosciences has become more popular. Machine learning can be defined as a field of inquiry devoted to understanding and building methods that ‘learn’, that is, methods that leverage data to improve performance on some set of tasks (Mitchell, 1997). Machine learning algorithms build a model based on sample data, known as training data, to make predictions or decisions without being explicitly programmed to do so. Adytia et al. (2018) used the autoregressive integrated moving average (ARIMA) model to predict the significant wave height obtained from the SWAN numerical model with a high correlation exceeding 0.94. The results showed an accurate short-term prediction with ARIMA (2,2,2). Yang et al. (2019) described the seasonal autoregressive integrated moving average (SARIMA) as a useful tool for long-term significant wave height prediction in the South China Sea. They also based their work on the results of numerical modeling using WAVEWATCH III. However, Ali et al. (2021) concluded that ARIMA performed the worst in significant wave height prediction. The best results were obtained by gated recurrent units of the deep learning model. They also attempted to use the Long Short Time Memory (LSTM) model. There are several publications that proposed a hybrid approach for forecasting in geosciences and network training. Tsai et al. (2021) described a differential parameter learning framework to train models with complex nonlinear and nonstationary data. Tang et al. (2021) published a multicomponent hybrid model for wave height prediction. Wu et al. (2020) proposed a hybrid physics-based machine learning model and successfully trained it with the wind-driven wave data. Also, a convolutional neural network (CNN) and recurrent neural network (RNN) might be used in geosciences. Wang et al. (2020) applied CNN to obtain the forecast of the cyclone track.

International Journal of Offshore and Polar Engineering

doi: 10.17736/ijope.2022.jc870

ISOPE

ISOPE-22-32-4-411

algorithm, application, Artificial Intelligence, Barent Sea, deep learning, forecast, forecasting, international journal, lstm, machine learning, neural network, northern sea route, prediction, predictor, sarima, sea state forecast, Upstream Oil & Gas, wind energy, XGBoost

Country:

North America > Trinidad and Tobago > Trinidad > Arima > Arima (0.66)
North America > United States (0.46)
Asia > China (0.35)

Genre: Research Report > New Finding (0.48)

Industry:

Energy > Renewable > Wind (0.69)
Energy > Oil & Gas > Upstream (0.68)
Transportation (0.66)
Energy > Renewable > Ocean Energy (0.47)

SPE Disciplines:

Data Science & Engineering Analytics > Information Management and Systems > Neural networks (1.00)
Data Science & Engineering Analytics > Information Management and Systems > Artificial intelligence (1.00)

Technology: Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (1.00)

Le, Minh (Offshore Subsea Engineering, Saipem SA) | Ahmed-Kogri, Mamadou (Offshore Subsea Engineering, Saipem SA) | Stableford, Richard (Offshore Subsea Engineering, Saipem SA) | Giry, Eric (Offshore Subsea Engineering, Saipem SA)

Lined Pipe Testing and Finite Element Modelling for Reel-lay Application

_ In this paper, a numerical model is proposed for mechanically lined pipe (MLP). Laser-based scanning techniques were used to capture local straining of the liner and digital imaging correlation of the backing steel outer during simulated reeling trials. This included wrinkling generated by an unexpected anomaly near the transition area of one test string. Data were collected before, during, and after reeling. The numerical model developed to simulate the bending trial corresponds well with test data, proving the method useful for further MLP modelling studies. Introduction MLP is a cost-effective solution to transmit corrosive hydrocarbon fluids. A carbon steel host pipe shelters a thin tube made of CRA. The thin tube is inserted and expanded to fit the inner surface of the host pipe. A specific failure mode can occur based on delamination and collapse of the liner, known as “wrinkling,” when installed by reel laying (Vasilikis and Karamanos, 2012) or under repeated large bending (Bartolini et al., 2017). Several works were performed to address specifically the conditions that may trigger a wrinkle either from a numerical perspective or from combining experimental and numerical studies (Toguyeni and Banse, 2012). Some studies proposed criteria to anticipate the situation where liner wrinkling may occur (e.g., DNV, 2018; Tkaczyk et al., 2020; Le et al., 2021). Test campaigns were reported in recent years with dedicated instrumentation based on laser scanning to quantify the liner response and calibrate FEA (e.g., Focke et al., 2007). High-resolution measurements generate a large amount of data that require specific processing to get a valuable interpretation such as the one described by Harrison et al. (2016). Some test programmes focused on local features, such as a weld (Jones et al., 2021) or a liner imperfection (Pépin et al., 2019), that could initiate a wrinkle. However, to the authors’ knowledge, there has been no MLP bending test involving an anomaly that specifically triggers a wrinkle that is measured with high-resolution instrumentation and simulated through FEA. This paper proposes a comparison between experimental and numerical experience for such a case.

International Journal of Offshore and Polar Engineering

doi: 10.17736/ijope.2022.jc869

ISOPE

ISOPE-22-32-4-463

Country:

Asia (0.68)
Europe (0.46)
North America > United States > California (0.28)

Genre:

Research Report > New Finding (0.48)
Research Report > Experimental Study (0.48)

Industry:

Energy > Oil & Gas > Upstream (0.68)
Materials > Metals & Mining > Steel (0.48)

SPE Disciplines:

Data Science & Engineering Analytics (0.93)
Facilities Design, Construction and Operation > Pipelines, Flowlines and Risers > Offshore pipelines (0.46)
Facilities Design, Construction and Operation > Pipelines, Flowlines and Risers > Piping design and simulation (0.35)

Technology: Information Technology > Artificial Intelligence > Vision (0.34)

Pogorelova, Alexandra V. (Sholem Aleichem Amur State University, Birobidzhan) | Kozin, Victor M. (Institute of Machining and Metallurgy FEB RUS) | Zemlyak, Vitaly L. (Sholem Aleichem Amur State University, Birobidzhan)

The Effect of an Ice Cover on the Trimming Moment of Submarines

_ This article touches on the unsteady rectilinear motion of a submarine in a liquid under an ice cover. Ice cover is modeled by a viscoelastic ice plate. The viscoelastic properties of ice are described using the Kelvin–Voigt model. A free-surface fluid flow past a system of sources and sinks is used to simulate the motion of three submarine hull forms. The authors analyzed the effects of ice plate thickness, submergence depth, water depth, hull form, the length-to-diameter ratio of a submarine, and the speed of uniform motion (Froude number) on the trimming moment of a submarine. Trim angle and vertical displacement of a steady moving submarine model is measured experimentally in a towing tank. Introduction The near-surface operation of a submarine is inherently an asymmetric problem, whereas operation in a deep-water condition is assumed to be symmetric (Dawson, 2014). This is due to the interaction between a submerged body and a flexible freesurface boundary, which gives rise to a wave resistance, vertical lift force, and trimming moment (Griffin, 2002). The wave resistance, lift force, and trimming moment occur through the interaction effect that exists when the hydrodynamic pressure field of a body generates free-surface waves, which, in turn, generate a nonuniform hydrostatic pressure distribution surrounding a body (Dawson, 2014). Note that hydrodynamic loads acting on a body, steady moving near a free surface, have been studied quite fully. Havelock (1917, 1931a, 1931b), Kinoshita and Inui (1953), Wigley (1953), and Farell (1973) were the fathers of these studies in the framework of the theory of potential motion of an ideal incompressible fluid. Doctors and Beck (1987), Weinblum et al. (1950), Gertler (1950), Farrell and Güven (1973), Gourlay and Dawson (2015), and Crook (1994) continued studying these problems, both theoretically and experimentally. Note that under modern conditions, during the development of the Arctic, submarines were forced to move under an ice cover. The problem of the influence of an ice cover on hydrodynamic loads acting on submarines is of interest. Pogorelova et al. (2020) and Zemlyak et al. (2022) investigated the wave resistance and lifting force acting on a slender body and a spheroid advancing under an elastic plate. However, the moments acting on submerged bodies under an ice cover have not been well studied.

International Journal of Offshore and Polar Engineering

doi: 10.17736/ijope.2022.jc872

ISOPE

ISOPE-22-32-4-440

calculation, coefficient, Dawson, effect, equation, extremum, ice cover, international journal, Magnitude, Model III, polar engineering, Reservoir Characterization, resistance, spheroid, submarine, submergence, Upstream Oil & Gas

Country:

North America > United States (0.68)
Asia (0.47)
Oceania > Australia (0.46)

Genre: Research Report > New Finding (0.48)

Industry: Energy > Oil & Gas > Upstream (0.66)

SPE Disciplines: Reservoir Description and Dynamics > Reservoir Characterization (0.34)

Technology: Information Technology (0.46)

Liu, Qiang (Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou), Shenzhen) | Feng, Xingya (Southern University of Science and Technology, Shenzhen) | Tang, Tianning (University of Oxford, Oxford)

A Machine Learning Model for Wave Prediction Based on Support Vector Machine

_ In this paper, we propose a least square support vector machine (LSSVM) model to predict ocean wave elevations in a random sea state. The frequency and time domain characteristics of historical wave data were both considered in the proposed model. The wave data following a JONSWAP (Joint North Sea Wave Project) spectrum measured through an indoor wave tank experiment were used for the study. The measured time series were transformed to the frequency domain by the fast Fourier transform and divided into five bands by a filtering method. With the time series corresponding to each band, the LSSVM model was trained separately and used to predict future time series. The proposed model is shown to greatly extend the prediction time length, making it more effective for the application of short-term real-time wave prediction. Both wave elevations and wave forces were studied as applications of the model. Introduction Real ocean waves can be characterized as irregular, random, and highly nonlinear. Although theoretical and numerical models have long been developed to understand the behavior of ocean waves, it remains a challenge to make real-time predictions. A variety of prediction methods have been developed. For computational models, wave parameters are simulated and predicted by solving equations based on theoretical models, such as the wave model proposed by the Wamdi Group (1988). This method could make good predictions for waves in deep-sea areas, but it has certain limitations of application for nearshore areas with complex terrain. In recent years, artificial intelligence methods such as machine learning techniques have attracted much attention from researchers in various fields because the emergence of these methods effectively makes up for the shortcomings of conventional prediction methods. The machine learning (ML) method could make statistical predictions based on historical data, which has been widely applied in the prediction of energy consumption, traffic flow, rainfall, stock price and other fields, and has great potential in marine engineering applications (Gopinath and Dwarakish, 2015).

International Journal of Offshore and Polar Engineering

doi: 10.17736/ijope.2022.jc879

ISOPE

ISOPE-22-32-4-394

application, Artificial Intelligence, decomposition, elevation, Engineering, international journal, machine learning, machine learning model, neural network, ocean energy, polar engineering, prediction, prediction accuracy, sery, spectrum, subfrequency, Support Vector Machine, wave prediction, wind energy

Country:

Asia > China (0.48)
North America > United States (0.46)
Europe > United Kingdom > North Sea (0.24)
(3 more...)

Industry:

Energy > Renewable > Ocean Energy (0.49)
Energy > Renewable > Wind (0.46)

SPE Disciplines: Data Science & Engineering Analytics > Information Management and Systems > Artificial intelligence (1.00)

Technology: Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning > Support Vector Machines (1.00)

Lee, Jeoungkyu (Seoul National University, Seoul) | Ahn, Yangjun (Sungshin Women’s University, Seoul) | Kim, Yonghwan (Seoul National University, Seoul) | Jung, Junhyung (Daewoo Shipbuilding & Marine Engineering Co., Ltd.)

Sloshing Phenomenon Occurring in the Foremost Two Tanks of LNG Carrier

_ Herein, to predict the sloshing pressure for the No. 1 and No. 2 tanks of a liquefied natural gas carrier, a series of sloshing model tests were performed and the obtained results were analyzed. By statistically approaching the experimentally measured pressure, the differences by position in each tank were analyzed. At this time, the sloshing impact pressures caused by the ship motion in various irregular sea conditions were measured. The loading conditions were tested for the full-load conditions of 95%, 80%, 70%, and 10% load for the ballast condition based on the tank height. Among the sea state conditions, the representative angle of incidence, significant wave height, and periodic conditions were chosen and the results were summarized. Notably, the sloshing impact pressures generated in the No. 1 and No. 2 tanks of different shapes and positions can be compared by simultaneously installing the two tanks on the motion platform. Introduction The sloshing phenomenon is a flow caused by the movement of the tank containing the fluid, which impacts the tank wall. Particularly, for a liquefied natural gas (LNG) carrier, studies on the sloshing phenomenon have been actively performed for the safety design of cargo holds because large amounts of LNG impact the tank wall due to the vessel movement. Since the sloshing phenomenon exhibits strong nonlinearity, experimental studies have been actively performed. Classification has also driven experimental analysis (American Bureau of Shipping, 2006; Bureau Veritas, 2011; Det Norske Veritas Germanischer Lloyd, 2014; Lloyd’s Register, 2009). Additionally, due to computer performance improvements, sloshing studies employing computational fluid dynamics (CFD) are gradually being conducted. For example, Liu and Lin (2008) developed a numerical model for the nonlinear sloshing flow in a three-dimensional rectangular tank. Yang et al. (2016) analyzed the velocity field and impact pressure by comparing the CFD and the particle image velocimetry results for a two-dimensional sloshing impact.

International Journal of Offshore and Polar Engineering

doi: 10.17736/ijope.2022.pf23

ISOPE

ISOPE-22-32-4-434

Country:

Europe (0.68)
North America > United States (0.48)
Asia (0.48)

Genre:

Research Report > Experimental Study (0.86)
Research Report > New Finding (0.68)

Industry:

Energy > Oil & Gas > Midstream (1.00)
Transportation > Freight & Logistics Services > Shipping > Tanker (0.62)

SPE Disciplines: Facilities Design, Construction and Operation > Natural Gas Conversion and Storage > Liquified natural gas (LNG) (1.00)

Technology: Information Technology (1.00)