Station-keeping is one of the important factors in the design of offshore platforms. Some offshore platforms, such as Spar, Semi-submersible and FPSO, use mooring lines as a mean for station-keeping. Tensions in the mooring lines are one of the key factors in station-keeping. The design of an offshore platform and its mooring lines is based on computed motions of the platform and associated mooring line tensions from numerical simulations using a software code on the basis of metocean criteria. This paper presents an Artificial Neural Network (ANN) model for the prediction of mooring line tensions based on the motions of the platform. This ANN model is trained with time histories of vessel motions and corresponding mooring line tensions for a range of sea states from the results of numerical simulations. After the model is trained, it can reproduce with great fidelity and very fast the mooring line tensions. In addition, it can generate accurate mooring line tensions for sea states that were not included in the training, and this demonstrates that the model has captured the knowledge for the underlying physics between vessel motions and mooring line tensions. The paper presents an example of the training and the validation of the model for a semi-submersible offshore platform for a range of sea states. The training of the ANN model employed a back-propagation learning algorithm. In this algorithm the computed output error is back-propagated through the neural network to modify the connection weights between neurons. The training started with a small number of hidden neurons, and the model grew adaptively by adding hidden neurons until either the target output convergence is achieved or a maximum number of additional hidden neurons is reached. The ANN model discovers nonlinear relationships between the input and output variables during training. The paper presents comparison of time series of mooring line tensions for sea states that were and were not included in the training between those from the numerical simulations and those computed by the trained ANN model. Fatigue assessment is also used to quantitatively measure the accuracy of the ANN model prediction of the time series of mooring line tensions. The paper presents the results of fatigue assessment using various stages of the ANN models with different number of hidden neurons. This shows that the additional hidden neurons improve the prediction of the ANN model of the mooring line tensions for sea states that were and were not included in the training. This approach of prediction of mooring line tensions based on vessel motions using ANN model paves the way to the development of an ANN-based monitoring system. Also, this ANN study demonstrates a great potential for the use of a more general and comprehensive ANN model to help monitor the dynamic behavior of floating systems and forecast problems before they occur by detecting deviations in historic patterns.

Artificial Intelligence (AI) has gained popularity in recent years for offshore engineering applications, and one such challenging application is detection of mooring line failure of a floating offshore platform. For most types of floating offshore platforms, accurately detecting any mooring line damage and/or failures is of great interest to their operators. This paper demonstrates the use of an Artificial Neural Network (ANN) model for detecting mooring line failure for a spread-moored FPSO. The ANN model representation, in terms of its input variables, is based on assessing when changes in a platform’s motion characteristics are in-fact indicators of a mooring line failure. The output of the ANN model indicates the status condition for the mooring lines (intact or failed). This ANN model only requires GPS / DGPS monitoring data and does not require data on the environmental conditions at the platform. Since the mass of an FPSO changes with the stored volume of oil, the vessel’s mass is also an input variable. The ANN training uses the results from numerical simulations of a spread-moored FPSO with fourteen mooring lines. The numerical simulations create the FPSO’s response to a range of metocean conditions for 360-degree directions, and they cover several levels of vessel draft (mass). Furthermore, the simulations cover both the intact mooring configuration and the full permutation where each of the fourteen mooring lines is modeled as broken at the top. The global performance analysis of the FPSO is presented in a different paper (Part 2 of these paper series). The training of the ANN model employs a back-propagation learning algorithm and an automatic method for determining the size of ANN hidden layers. The trained ANN model can detect mooring line failure, even for vessel draft (mass), sea states and environmental directions that are not included in the training data. This demonstrates that the ANN model can recognize and classify patterns associated with mooring line failure and separate such patterns from those associated with intact mooring lines under conditions not included in the original training data. This study reveals a great potential for using an ANN model to monitor the station keeping integrity of a floating offshore platform with changing storage, or mass status, and to detect mooring line failure using only the vessel’s mass and deviations in the platform’s motions derived from GPS / DGPS data.

For three different marginal fields with different payloads, two variations of Technip's wet tree HVS semisubmersible are designed for dry tree application and evaluated on the basis of riser tensioner stroke and deck acceleration. These dry tree suitable hulls also have reduced vertical heave motion at the SCR porch and improve quayside integration and commissioning of topsides to the hull. A key element for the dry tree platform is the riser tensioning system which supports the direct vertical production risers from a subsea wellhead to a topside production tree. These riser tensioners provide additional hull heave stiffness, and effectively reduce the overall natural heave period of the hull. Conventional semisubmersible designs have excessive heave response in harsh environments, resulting in tensioner stroke ranges that are beyond the stroke ranges of field proven conventional riser tensioner equipment. The HVS class semisubmersible with reduced heave and VIM response was chosen as the basis for the dry tree semisubmersible designs in order to achieve riser tensioner stroke ranges within the capability of field proven riser tensioners. The main characteristic of the HVS class of semisubmersible is the redistribution of displacement from the pontoons to the lower part of the column. This is accomplished with a column step, which has the appearance of a blister, located partially around the lower part of column. This redistribution reduces the vertical hydrodynamic excitation, and the heave response. The column step breaks also the coherence of the vortex shedding along the length of column and consequently suppresses the vortex induced motion. The dry tree adaptations of the HVS class semisubmersible include pontoon plates that increase the heave natural period through added mass, and the outcome is reduced heave motion for seastates with high peak periods. The pontoon plates are simple structures to fabricate and have additional benefit of enhancing structural rigidity. The contribution of the pontoon plates to the hull steel weight is minimal. With optimal design of the pontoon plates, the resulting dry tree hulls support the top tensioned risers without the need of a keel guide. The dry tree hull forms have been designed using Computational Fluid Dynamic (CFD) analysis. Extensive CFD work was performed in order to finalize the dry tree designs.

The mitigation of Vortex Induced Motion (VIM) of the HVS (Heave and VIM Suppressed) semisubmersible is investigated through extensive comparisons between CFD analysis and VIM model test results. It is shown that the lower VIM response of the HVS semisubmersible results from the break in coherence of vortex shedding along the length of column due to the column step. The present CFD application was carried out on the basis of in-house best practices for VIM analysis of multi-column floaters. The analysis results show excellent comparison with the model test results. The present findings and methodology can be applied to optimize semisubmersible hull designs for suppressed VIM response.

Following the successful application of CFD-based Numerical Wave Basin (NWB) to GBS, TLP and Semisubmersible platforms [1–4], the same methodology has been applied to simulate FPSO hull motion responses to irregular waves. It has been found that the NWB modeling practices developed for the other floater types must be modified for application to an FPSO. This paper describes how the NWB modeling practices have been improved, and then compares results from NWB simulations with those from physical model testing.