Due to the quality and error of the data itself, historical automatic identification system (AIS) data was insufficient used to predict navigation risk at sea, but it adequately used to train decision-making neural networks. This paper presents a real AIS ship navigation environment with a rule-based and a neural-based decision processes with frame motion and training the decision network using a deep reinforcement learning algorithm. Rule-based decision-making has several applications in the field of adaptive systems, expert systems, and decision support systems, it also including general ship navigation which regulated by the convention on the international regulations for preventing collisions at sea (COLREGs). However, if someone intend to achieve full unmanned ship navigation without any remote control at the open sea, a rule-based decision-making system cannot be implemented alone. With the growing amount of data, complex sea environment, different collision scenarios, the agent-based decision has become an important role in transportation. For ships, combined rule-based and neural-based decision-making is the only option. It has become progressively challenging to satisfy autonomous decision-making development requirements. This study uses deep reinforcement learning to evaluate the performance of decision-making efficiency under different AIS data input shapes. The results show that the decision neural network trained with AIS data has good robustness and a high ability to achieve collision avoidance. Furthermore, using the same methodology, include instructive guidance for processing radar, camera, ENC, etc., respond to different risk perception tasks in different scenarios. It has important implications for fully unmanned navigation.

For the operability evaluation of an offshore unit, it is usual to adopt specific working limiting criteria dealing with ship motions and accelerations. These criteria given by operators reflect the ability of the vessel (or crew) to accomplish a precise target in an operative scenario with different meteorological conditions. However, an offshore vessel needs also to keep a determined position and heading during working operations. That means designers or operators have to consider criteria associated both with seakeeping and station keeping to evaluate the effective operability of the vessel. Traditionally, early design stage operability analyses do not combine seakeeping and station keeping predictions, which are referring to different working environments. Here, an innovative procedure allows to evaluate the joint operability of an offshore unit, adopting scatter diagrams for local environmental conditions. The method has been applied on a Pipe-Laying vessel, assessing the global operability for different areas of commercial interest.

The traditional industry approach to drilling riser joint inspection and maintenance has centered on recertification of riser joints at fixed five-yearly intervals. There are significant potential efficiencies to be gained from moving to a condition-based maintenance regime where inspection intervals are determined based on the actual usage of the riser joint. One of the critical factors driving the requirement for inspection is the fatigue damage sustained by the riser joint during use. This paper describes a unique drilling riser joint fatigue tracking system that uses the latest digital technologies, advanced automation processes and a state-of-the-art finite element model of the drilling riser to provide an accurate and efficient solution to the challenge of long-term riser joint fatigue tracking. The architecture and operation of the system is described in detail and the application of a fracture mechanics-based approach to fatigue calculation versus the traditional S-N curve-based approach is discussed.

The motion analysis of floating offshore structures is a major design aspect which has to be considered in the early design stage. The existing design environment E4 is an open software framework, which is being developed by the Institute of Ship Design and Ship Safety, comprising various methods for design and analysis of mainly ship-type structures. In context of the development to enhance the design environment E4 for offshore applications this paper presents a method to calculate the response motions of semi-submersibles in regular waves. The linearised equations of motion are set up in frequency domain in six degrees of freedom and the seakeeping behaviour is calculated in terms of the amplitudes of the harmonic responses. The hydrodynamic forces onto the slender elements of the semi-submersible are accounted for by a Morison approach. As the drag and damping forces depend quadratically on the amplitudes, these forces are linearised by an energy-equivalence principle. The resulting response amplitude operators of the semi-submersible are validated by comparison with model tests. The method represents a fast computational tool for the analysis of the seakeeping behaviour of floating offshore structures consisting of slender elements with circular cross sections in the early design stage.

Current loads are important input parameters for mooring studies. To accurately predict the motions of moored vessels these quantities should be determined with confidence in the values. Traditionally, these quantities have been determined using model tests in water basins or in wind tunnels. With recent advancements in CFD modeling, the offshore industry has started using CFD as an alternative tool to compute current loads on FPSO’s. In order to help adopt CFD as a widely accepted tool, there is a need to develop confidence in CFD predictions. Therefore, a practical CFD Modeling Practice is developed within the Reproducible Offshore CFD JIP. The Modeling Practice describes the geometry modeling, computational mesh, model set-up and post-processing for these types of CFD calculations. This Modeling Practice is verified and validated by five independent verifiers against model test data, such that reproducible and accurate results can be obtained by following the Modeling Practice. This paper provides an overview of the developed Modeling Practice and the calculated CFD results from the verifiers. The CFD Modeling Practice is benchmarked against available model test results for a barge-type and a tanker-shaped FPSO. By following this Modeling Practice, the CFD predictions for CY and CMZ are within 10% from all verifiers and within 10% from the model test results. Larger differences may be obtained for CX, depending on local grid resolution and turbulence model used, but also due to larger experimental uncertainty for this quantity.

Monitoring the integrity of mooring lines on floating offshore platforms is one of the key factors in ensuring safe and productive offshore operations. Sensors, such as inclinometers, compressive load cells or strain sensors, can be used to monitor the inclination angles or tensions on mooring lines. An alternative method using only dry monitoring systems, such as DGPS (Differential Global Positioning System), Gyrocompass and/or IMU (Inertial Measurement / Motion Unit), can also be used to monitor the integrity of mooring lines. This method uses the measured motions and positions of a vessel without any information on the environmental conditions to detect mooring line failure. The detection of mooring line failure is based on detecting shifts in low-frequency periods and mean yaw angles as a function of vessel position, mass and added mass. The proposed method utilizes Artificial Neural Network (ANN) to recognize and classify patterns. The training of an ANN model requires examples/data associated with intact mooring lines and broken mooring line(s). Examples/data of broken mooring line(s) are practically available only from numerical simulations. Therefore, it is important to address these two key topics: (1) Is the real behavior of the floating offshore platform sufficiently aligned with numerical simulations? and (2) The effect of the accuracy of monitoring equipment on the performance of an ANN-based system. The first topic is reviewed briefly with its possible solution including some sensitivity tests, and this paper focuses on addressing the second topic. A system architecture is discussed in this paper along with the accuracy of the monitoring equipment. As an example, an ANN model has been trained to detect a broken mooring line of a spread-moored FPSO. This ANN model has been tested on its performance in dealing with a range of possible errors associated with the monitoring equipment. Furthermore, the tests have been carried out for a combination of variables that are not included in the ANN training, such as: vessel draft (mass), sea state conditions and directions. This paper presents the results of the tests for various variable sensitivities, which cover vessel positions, mean yaw angles and vessel drafts. These are essentially testing the tolerance of a trained ANN model against error or noise in the data. The results show that a trained ANN model can be error/noise tolerant.

This study aims to introduce the integrated approach, namely the integration of the Faster R-CNN technique and Optical gas imaging (OGI) for real-time natural gas leak detection of offshore platforms. OGI is used to record large number of leak videos which are essential to develop the desirable Faster R-CNN model. Due to the fact that the natural gas leak incidents are rare on the offshore platforms, it is difficult to record large number of the real-world leak videos by using the OGI. This study firstly proposes the strategy to simulate the OGI by the CFD tool. The proposed strategy could generate large number of virtual infrared images. Based on the infrared images, the Faster R-CNN approach is trained and its performance is tested. A case study of deep-water drilling platform is conducted. The results demonstrate the feasibility of the proposed strategy as well as the competing performance of the Faster R-CNN approach for the real-time automatic natural gas leak detection of offshore platforms.

There is an ever-increasing amount of data being recorded in oilfield operations. During drilling a well a large number of parameters is being monitored and saved, often reaching several hundreds. We are seemingly monitoring everything, from basic parameters such as Weight on Bit, Torque, and Rate of Penetration (ROP), to the exhaust temperature of engine no. 3. Unfortunately, the quality of collected data does not match the quantity. Critical sensors, such as gamma and inclination, are often lagging many meters behind the bit. Despite best efforts, sensors stop working, hard drives corrupt files, and data mud pulse telemetry uplinks fail. Methods of infilling data spanning many meters or minutes are necessary. We present a novel approach that enables reliable prediction of data lagging behind the bit through deep neural networks by merging trend-based prediction with traditional neural network approach. We were able to predict continuous inclination data in a curved section of a well with an average absolute error of only 0.4 degrees up to 20 meters from last known value.

In response to the continuing importance of offshore structures a framework for the simulation of offshore platforms is implemented in the open software environment E4. The non-commercial suite contains various methods for the ship design so that the newly developed procedures benefit from the existing knowledge. Jacket structures are installed as fixed platforms or compliant towers and play a significant role in the offshore exploitation. They are made out of hundreds of tubular steel members and each of the cylinders or cones can be seen as a simple body compared to ships. Besides the dynamic behaviour and fatigue analysis, the examination of the installation procedure especially the launch operation is of high interest. This article presents an analytical approach for the hydrostatic calculations of partially submerged cylinders. Hydrostatic forces on jacket structures are calculated by superimposing single cylinders and the results of the newly developed method are compared with a commercial simulation software. The aim is to speed up the computation time in comparison to numerical methods which is a significant advantage in the early design stage. The presented method will be the foundation for the simulation of jacket launching manoeuvres in time domain.

In modern oil/gas producing industry, vertical, 2D and 3D directed, and multilateral (branched) boreholes are drilled. Their trajectories are designed depending on the petroleum deposit depth and structure, properties of mining rocks, their hardness, heterogeneity, fracturing anisotropy, permeability, and so on. Therefore, the borehole cost and its productivity are determined by the length, smoothness, and configuration of its trajectory. To enhance efficiency of a borehole and to reduce cost of its drivage, to enlarge rate and volume of the reservoir depletion, it is proposed to use methods of optimal control for the best tracking of its trajectory. Through application of the differential geometry correlations, the mathematic model of the borehole outline in the form of nonlinear ordinary differential equations system is elaborated. Different objective functions, representing total integral curvature of the borehole axis line, its length, and cost of its drivage, are selected; additional constraints, separating allowed and forbidden zones of passing, are chosen. The functions of the trajectory curvature and torsion are used as controlling variables. The continuous correlations of the model are discretized and, further, the techniques of nonlinear programming and optimal control are employed. On the basis of the method of objective function gradient (antigradient) projection on the linearized constraint planes, the step-by-step algorithm of approaching to the optimal trajectory is elaborated. To correct the spoilt constraints, at every step of calculations, the Newton method is used. The elaborated approach is applied to optimization of deep curvilinear borehole outlines. The results of numerical analysis are discussed. It is shown that smoothing the hole trajectory permits also to diminish the contact and frictional interaction between the drill string and bore-hole wall and, by this, to decrease the resistance forces acting on the string during tripping in/out operations performing and to diminish energy expenditures for these operations fulfillment; to decrease the rate of the drill string tube wear; and to reduce the drill string sticking occurrence probability.

Generating waves inside the CFD domain is a topic of interest in the offshore and naval industry. For practical reasons it is useful to use a potential wave kinematic solver (PWKS) to generate incident waves and use this solution to initialize and propagate incident waves in the CFD solver. Protocols to transfer the wave data from PWKS to CFD solver have been developed to ensure the reproduction of the wave kinematics from a PWKS in CFD solvers. Based on the survey results from a number of PWKS and CFD solvers available, the paper presents the various ways to express the solution and what is needed to reconstruct the fields needed in the CFD.

Prelude Floating Liquefied Natural Gas (FLNG) facility reached a significant milestone in June 2018 when gas was introduced onboard for the first time as part of the facility startup process, loaded from an LNG carrier moored in side-by-side (SBS) configuration. This first offshore LNG SBS operation allowed Prelude’s utilities to switch from running on diesel to running on gas. SBS mooring is the base case configuration for of floading both LNG and Liquefied Petroleum Gas (LPG) into product carriers using Marine Loading Arms (MLA) once the Prelude FLNG facility is fully operational. These complex and weather sensitive operations are expected to take place on a weekly basis. This means critical decisions about weather-window and timing should be supported as much as possible by predictive analysis and modelling of environment forecasts to reduce the risks. Prelude Floating Liquefied Natural Gas (FLNG) is designed to offload Liquefied Natural Gas (LNG) and Liquefied Petroleum Gas (LPG) to carrier vessels moored in a side-by-side (SBS) configuration, using Marine Loading Arms (MLA) technology. For onshore terminals or small/medium FLNG, the traditional design of MLA (Double Counterweight Marine Arm – DCMA), featuring a vertical riser, can be used. However due to the exceptional freeboard of Prelude a new type of MLA was designed, namely the Offshore Loading Arm Footless (OLAF), without vertical riser in order to reach the LNG or LPG manifolds located as far as about 16 meters below the MLA base. Thanks to the OLAF design, the length and weight of the articulated MLA sections is reduced in comparison with conventional DCMA, and so are the dynamic loads applied by the MLA on the vessel manifold, which was mandatory to remain below the acceptable stress limit of standard LNG/LPG carrier manifolds. OLAF employs the field proven targeting system (TS) allowing the connection and disconnection of the MLA to the vessel manifold in dynamic conditions. This paper describes the assumptions and process to design and validate this new system — in terms of overall geometry and structural design, while verifying project feasibility, aiming at a reliable design of all components and minimizing the risks during operations. The key challenges and lessons learnt are also discussed. This innovative type of MLA had to be thoroughly designed and tested before being manufactured and assembled on the FLNG. The innovation management was also coupled with the additional challenge imposed by the expected highly dynamic conditions of relative motion between vessels that were never encountered for such systems in the past. MLA were designed with the objective to cover the operable envelope induced by berthing, mooring and relative motion criteria, so that it should not become an additional criterion in general. Since such an envelope is larger for this offshore application compared to sheltered terminals, this objective was particularly challenging but could be met thanks to the OLAF design. The SBS hydrodynamic numerical model is based on potential theory and includes multi-body coupling, non-linear mooring characteristics and coupling with sloshing. This model was calibrated using wave basin tests with a good agreement, and was used to determine the maximum operable environments and associated MLA envelope, using a 39-year hindcast for various LNG carriers and considering a scenario with different criteria and loading conditions. More than 100,000 time-domain simulations were required to evaluate non-linear quantities on a reduced set of environment ‘bins’. The new OLAF-type MLA was developed using these hydrodynamic simulations. Specific processes — based on spectral screening and selection using relevant criteria — were used to identify and select, in a systematic way, the designing load cases for connecting, connected, and emergency disconnection cases, while complying with the maximum allowable loads of conventional LNG and LPG carrier manifolds. An instrumented 1:4 OLAF scale model was built and tested with 6 degrees of freedom hexapods reproducing the motions on both sides of the OLAF which enabled us to confirm a 10% accuracy of the numerical studies results. The actual OLAF were dynamically tested with a full scale motion simulator before shipment to the yard for installation. The successful first operations were performed safely and confirmed the validity of the design. Measurements are now collected onboard Prelude to verify the design and when possible improve the accuracy of numerical modelling.

This paper addresses the performance evaluation of an empirical time domain Vortex Induced Vibrations (VIV) model which has been developed for several years at NTNU. Unlike the frequency domain which is the existing VIV analysis method, the time domain model introduces new vortex shedding force terms to the well known Morison equation. The extra load terms are based on the relative velocity, a synchronization model and additional empirical coefficients that describe the hydrodynamic forces due to cross-flow (CF) and In-line (IL) vortex shedding. These hydrodynamic coefficients have been tuned to fit experimental data and by considering the results from the one of existing frequency domain VIV programs, VIVANA, which is widely used for industrial design. The feature of the time domain model is that it enables to include the structural non-linearity, such as variable tension, and time-varying flow. The robustness of the new model’s features has been validated by comparing the test results in previous researches. However, the riser used in experiments has a relatively small length/diameter (L/D) ratio. It implies that there is a need for more validation to make it applicable to real riser design. In this study, the time domain VIV model is applied to perform correlation studies against the Hanøytangen experiment data for the case of linear sheared current at a large L/D ratio. The main comparison has been made with respect to the maximum fatigue damage and dominating frequency for each test condition. The results show the time domain model showed reasonable accuracy with respect to the experimental and VIVANA. The discrepancy with regard to experiment results needs to be further studied with a non-linear structural model.

Recent developments in data science are enabling new opportunities for marine and offshore operators to adopt a more effective asset management strategy. The crux of this strategy is to combine data analytics with maintenance records and operational experience to reduce unplanned downtime. This case study focuses on the assimilation and utilization of diverse and mostly unstructured data, which up until now was largely untapped in the marine and offshore industries. The information extracted from such sources is used to identify key trends in equipment reliability and to improve the understanding of assets’ conditions. Such insights are particularly useful for marine and offshore operators in making critical decisions relating to machinery: optimal resource allocation; proactive planning for planned maintenance events and maximizing overall asset availability. From a Classification Society’s perspective such as American Bureau of Shipping (ABS), this allows operators and/or owners to derive Class-based benefits like Condition-Based Maintenance (CBM).

The pre-shrouded vane (PSV) in front of propeller is a kind of energy-saving device which can change the inflow to improve the received power of the propeller. The device needs to be optimized according to the flow field of the stern. Most of the existing design methods rely on the experience of the designer. In order to improve the design efficiency of PSV and obtain a design scheme with higher energy-saving effect, this paper presents an optimization and analysis method for PSV in front of propeller based on agent model. Aiming at an 110000dwt oil tanker, 11 design parameters such as stator angle and duct radius are determined by means of parameterization. The design parameters are sampled by Latin hypercube sampling method (LH), and the sample space with 300 samples is generated. The energy-saving effect of each sample is analyzed by CFD method. The data set is formed and next divided into training set and test set. Then, machine learning methods are used to build the agent model of sample space. The error of each model in the test set is analyzed. To obtain the best model, the performance of several models in the test set and training set is considered. The applicability of different models is also highly considered. On this basis, the sensitivity analysis method is used to analyze the sensitivity of each design parameter. Then, the main influencing parameters are found. Finally, particle swarm optimization and genetic algorithm are compared to optimize the design parameters of PSV for 110000dwt oil tanker. The optimization results are verified by CFD method. The results show that the artificial neural network model is better on this dataset, and the model error on test set is less than 1% compared with the CFD result. The optimal solution by genetic algorithm method is better than all the sample points, and a better design scheme of PSV is obtained.

This paper covers the generic procedure for the creation and usage of a complete system simulation for propulsion systems of ships with focus on complex hybrid systems. Due to the large number of available components and challenging operational profiles, there is no longer a single best solution, especially in specialized shipbuilding. On top of that even minor changes in the propulsion system can have a substantial impact on plant performance and vessel behavior. Thus, the early design stage is crucial. The design procedure usually incorporates the selection and dimensioning of available components and concepts. Once this has been done, the dynamic behavior can be analyzed using the developed system simulation environment. With the knowledge gained the needed alterations in the concept can be identified and implemented in the subsequent design iteration circle. Based on the example of an offshore anchor handling vessel, the integration potential of a hybrid propulsion system is examined and evaluated according to the aforementioned procedure. The applied tool is a system simulation environment developed in the Department of Marine Engineering, consisting of a distributed co-simulation of the existing ship design environment E4 and Matlab ® Simulink ® .

A technical study of an innovative steel catenary riser (SCR) installation technology is presented in this paper. This installation technology maneuvers the hull through ballasting to align its riser porch with the riser, which is philosophically different from conventional riser installation that relies on an array of tugging winches to catch and pull riser into positions of the riser porches. The technology has been applied to the installation of eight SCRs on the Delta House production semi-submersible (second end) and, subsequently, five tieback SCRs (first end). We demonstrate that equipment arrangement, riser adaptor fabrication, and ballasting process remain the same for both first end and second end operations, resulting in a robust solution for riser installation. The technology has been proven safe in operations and efficient in saving installation time and cost. This paper focuses on the technical aspects of the riser installation technology, from concept development, technical qualification, to numerical simulations. Vessel positioning and riser-hull clearance during all steps of riser pull-in and installation, as well as planning for ballast water transfer required throughout the process, is prepared with an in-house program based on rigid body rotation. Numerical simulations are performed to identify critical stages of the riser pull-in and to examine the clearance from the pull-in wire or the riser to the hull. The dependence of the minimum clearance on a few parameters related to riser installation is determined and discussed. More numerical simulations are performed to assess the vessel motion response and its dynamic effect on riser-hull clearance and to establish environmental limits for riser installation operation. Discussions are provided for potential challenges of the technology when it is applied to different production and export risers in various water depths.

This paper addresses the nonlinear amplifications in the upwelling crests of air gap responses from the wave basin model test of a deep draft semi-submersible in extreme wave condition. Contributions from nonlinear incident waves, vessel motions and wave-body interactions are analyzed separately. Results from the analyses suggest that, nonlinear amplification factors are larger than predictions from second order corrected model for incident and diffracted waves. Low frequency roll and pitch motions will induce larger nonlinear negative vertical motions for points in down-wave area, thus worsen air gap performance. Upwellings are highly related to diffracted wave elevations. Local run-ups due to highly nonlinear wave-body interactions around column walls could result in the nonlinear amplification factors in this area to be up to 230%.

Over the last decades LNG and bulk terminals have been constructed in many countries. Many of these terminals have been located in sheltered sites without significant influence of swell and wind seas. As the worldwide gas market continues to grow supplying domestic, industrial and power plant projects, there is a continuous interest in new LNG terminals. With the growing gas demand LNG terminals are planned at exposed sites where the need of a breakwater is important for the ability of the facility to maintain operations and to ensure survivability of the terminal infrastructure. Studies are carried out for LNG terminal concept with the main focus on the need for a breakwater protecting the facility which will have significant impact on the CAPEX (Capital Expenditure). The mooring layout of the FSU/FSRU and LNG carrier whether perpendicular or parallel to the breakwater in addition to the planned operations determine the protection area behind the breakwater. The objective of this study is to establish design curves relating the different environmental and terminal parameters such as wave conditions, berthing facility layout, protection area and breakwater layout. These curves are derived based on the results of numerical simulations for wave transformation process of offshore waves propagating inside the terminal area. More than 700 cases are carried out in this study considering a range of wave periods, breakwater lengths, breakwater type (caisson and rubble mound), facility area dimensions and two incoming waves direction, i.e perpendicular and oblique. The simulations are carried out using the software REFONDE which is based on resolving the mild slope equation for irregular waves. The results of the study are presented in the form of curves and generalized to be used by terminal developers, designers and contractors for general guidance in future projects. Up to the authors’ knowledge, such curves for the design of marine terminals are not available at present. From this overview, a design methodology is developed to determine breakwater layouts during the early planning phase of project considering wave conditions, facility layout and terminal operations.

Due to the limitation of cabin space, FPSO domestic water pipe network system has the characteristics of long water delivery distance, more bending of pipeline and frequent opening and closing of valves, etc. The above characteristics are very likely to cause water hammer in the pipeline, resulting in increased risk of safe operation of pipe network system. In this paper, a FPSO domestic water system was taken as the research object. In view of the water hammer problem in the pipe network system, the model of FPSO domestic water system was established by using dynamic fluid analysis software AFT-Impulse, combined with the factors affecting the water hammer phenomenon (such as pipe diameter, velocity of wave, pipe length, pipeline roughness and valve closing time), the steady state analysis and transient analysis of multi-working conditions and multi-scenarios were realized to determine the main control factors. Based on the influence of main control factors, a comparison scheme of water hammer protection in FPSO domestic water system was proposed. Through the transient analysis of AFT-Impulse software under multi-working conditions, the optimal scheme of water hammer protection for FPSO domestic water system was obtained, which provided guarantee for the safe operation of the system.