The objective of this paper is to present a method for monitoring the natural frequency of a fixed offshore platform and to utilize the raw data to proactively monitor and predict structural degradation of the platform using machine learning. This can enable operators to predict critical member failure and guide timing of operational decisions and interventions, thus helping reduce cost of ownership, particularly for ageing assets. A Natural Frequency Response Monitoring (NFRM) system utilizes accelerometers and Fast Fourier Transform (FFT) to measure the sway and torsional frequencies of a fixed offshore platform. A significant structural event is detected by a shift in the natural response of the platform. A machine learning model (or digital twin) can be trained on this accelerometer data to replicate the platform response and determine the fatigue damage accumulation in platform members. The model, which can be re-trained to maintain accuracy, acts as a near real-time fatigue tracker with the NFRM system acting as a verification tool. A proof of concept case study is presented and demonstrates how Finite Element Analysis (FEA) simulations and measured data can be used to develop a machine learning model. The combination of an NFRM system with machine learning has the potential to assist operators in the prediction and identification of structural changes prior to them becoming critical. Knowledge of the actual fatigue damage in key platform members on a near real-time basis allows for proactive planning of inspections or repairs, as well as confidence in the structural performance of the platform, which can justify life extension.

For ultra-deepwater subsea wells, a riser system is required to conduct completion, intervention/workover and end of life activities. For ultra-deepwater riser systems with high temperature and pressure requirements, the intervention riser system often requires vessel interface optimization to achieve acceptable design response. The upper riser can be configured in several different ways, each with its own benefit from a safety, risk and performance perspective. This paper compares the riser response for various vessel interfaces for ultra-deepwater applications. As discussed above, intervention riser structural response is sensitive to the riser configuration at the vessel interface. For a typical intervention riser, due to ultra-deepwater and high tension requirements, the functional tension load may utilize up to 40% of yield strength thus decreasing the capacity available to accommodate bending and pressure loads. Vessel operators have options to modify the system configuration to improve the strength and fatigue response of the riser. The different vessel interface options include the tension lift frame (TLF) to vessel interface, the top tension application method and the use or otherwise of a surface tree dolly. Upper riser assembly (URA) loads may be optimized by use of rotary wear bushings, a cased wear joint assembly or flexjoints as a part of the stack-up. The various riser-vessel interface options are evaluated and compared in this paper. This paper highlights the riser design challenges for ultra-deepwater applications.

The offshore industry is faced with a tough financial market, requiring innovative solutions in order to reduce costs and increase operational efficiency. This includes solutions to ensure that maintaining the structural integrity of North Sea platforms is achieved as cost-effectively as possible without increasing risk or compromising safety. Regular general visual inspection of fixed platforms for structural damage, by ROV fly-by, is a commonly used technique. There are two main concerns with this technique. Firstly, these inspections are costly to perform and secondly, damage may occur shortly after a scheduled inspection and go undetected until the next inspection. Both of these concerns are addressed through real-time structural monitoring. This uses automation of frequency detection and signal processing in order to avoid equipment and personnel mobilisations and provide immediate notification of potential damage. Inspections can then be conducted only when required and targeted at a specific area of interest, resulting in a significant reduction in overall integrity management costs. A platform monitoring system can be used on both manned and unmanned platforms and can be installed during construction or retrofitted to an older installation. A platform monitoring system, also known as Natural Frequency Response Monitoring (NFRM), works by measuring the natural frequency response of the platform under wave loading. The structural failure of a member will alter the natural frequency of the platform and the monitoring system will detect the change and alert the Operator. Prior to implementing this technique a screening study of the change in platform response following damage to critical members is necessary in order to ensure that incidents will be reliably detected. This paper presents a case study of a NFRM screening study prior to installation of the system on a North Sea platform. The structural analysis used to confirm the suitability of the NFRM system and the Learn more at www.2hoffshore.com 2 SPE-186121-MS method for specifying the monitoring system itself are described. An indicative cost of procuring and installing the NFRM system is also presented.