Maintaining the expected position is critical to the overall safe operation of a floating oil platform. Mooring systems are critical to the integrity of the platform. Relying on instrumentation for monitoring the mooring line tensions represents multi-faceted challenges. Therefore, alternative methods have been introduced across the industry to reduce the costs and complexities of maintaining these systems. The paper discusses implementation of the Position Response Learning System (PRLS), a novel concept for addressing the integrity of mooring systems. PRLS is based on emerging data technologies and particularly machine learning that bridges the gap between a variety of global position measurements of the oil-platform and the mooring integrity paradigm. Machine learning enables learning from large amount of data without explicit programming. The PRLS concept does not require expensive line-tension measurement systems, but rather the global motion systems enhanced with the metocean monitoring. The global motion systems that include DGPS and MRU are typically already installed on oil platforms. In addition to measured data, PRLS can utilize a plethora of other data sources, including numerical simulations, model test data, and most importantly, the real-time and archived field data other than the line tensions. When the data are coupled with machine learning methods, they provide reliable, robust, and cost-effective solutions to address the integrity of the mooring system in real time of the oil platform. The article illustrates how the PRLS can identify a mooring line failure and even indicate which of the mooring line fails. Preliminary results based on the simulated data show that the accuracy of such predictions is better than 98%. The PRLS runs in the background independent of other integrity monitoring systems. It requires retraining periodically with new field data to improve the prediction robustness and accuracy. PRLS may be deployed on all types of floating platforms under a relatively moderate capital expense, and with very low operational costs when compared to high capital and operational expenses of a subsea mooring line monitoring system.

Integrated Marine Monitoring Systems (IMMS) are designed to help operators to reduce operational risk by providing information about the environment and the platform responses in real time. In spite of efforts to keep monitoring systems in working condition by following planned maintenance and upgrades, some sensors may fail intermittently or may generate spurious data. Quite often, intervention to repair or to replace a faulty sensor is either difficult, or even not feasible. This paper discusses various methods to estimate critical platform integrity parameters with satisfactory confidence in the cases when direct measurements are temporarily unavailable or questionable. Methods such as Artificial Neural Network and Extended Kalman Filter have been employed and specifically tuned to particular challenges. Estimated results for the missing data, such as platform position or riser loads, are reliable as they have been validated against historically good data. The merit of the paper is to present the methods that can increase reliability of the IMMS, enhance safety, reduce operational risk and decrease cost in maintaining expensive offshore systems.

No abstract

Vortex Induced Motions (VIM) of a floater are the result of the exciting forces by vortex shedding on the hull, causing response near the resonant period of any of the six degrees of freedom motions. VIM is currently a critical design component for risers and moorings on floaters, particularly in the deepwater Eastern and Central Gulf of Mexico (GoM).There have been a number of publications on spar VIM numerical modeling and on physical model testing procedures and results. Due to complexity of the VIM phenomenon, model tests are still considered the best approach to validate other tools, such CFD models or simplified numerical models dependent on empirical coefficients. However, little work has been reported on assessing the differences between field data and model test predictions.This paper examines field measurements of motions of a truss spar when the spar experienced multiple high current events in the GoM between the years 2006 and 2011. The motion data are studied to see if VIM lock-in occurred during any of these periods of high current events. Assumptions and procedures for estimating the reduced velocity (U R ) and A/D ratio using field observations are summarized. Comparison between the design guide based on the model tests and the field measurements are also presented. SummaryThe paper examines possible VIM events for the Constitution truss spar based on several hindcast GoM loop-current events over the duration of five years. The events are selected to match the design practice when VIM is expected to occur.The field data for these events are processed and the full-scale results compared with the model test results and design basis. The conclusion of this study is that both the model test results and VIM design parameters are conservative for the platform responses observed in the first five years of operation. It is recommended that an industry wide study is needed to establish industry guidelines for VIM prediction that more accurately reflect calibration to measured floater VIM response. These guidelines can then be used in design process not only for spars but also for other types of offshore structures.

Marine and structural integrity monitoring for offshore platforms is the cornerstone for managing operational risk and safety. Measuring platform responses and loads enables comparisons with design values thus ensuring that the risk does not exceed the designed limits. This paper discusses an advanced data management that is based on machine learning, a set of specialized computer programs that can learn and generalize the platform responses from measured data. The programs should produce sufficiently accurate predictions in previously unseen cases. Examples provided in the paper address capabilities for forecasting the marine and structural integrity parameters.