The mooring systems give stability to the floating platforms against environmental conditions, stabilizing the platform with mooring lines attached to the seabed. The mooring systems are among the main components that guarantee the safety of the staff and the various operations carried out on the platforms. The current approaches used to monitor mooring lines are inefficient as line tension sensors are expensive to install, maintain, and have durability problems. This article presents the development of two neural networkbased machine learning systems: a Multilayer Perceptron (MLP) and a Long Short-Term Memory (LSTM). They are able to detect mooring line failure in near real-time based on the comparison between measured and predicted motion. The implemented systems were trained and evaluated with simulated motion data generated using real environmental conditions measured in the Campos Basin, in Rio de Janeiro, Brazil. The results showed the MLP and LSTM models were able to detect a failure in the mooring lines, with increasing difference between the predicted and the measured motions when there is a line breakage. A comparison between the two machine learning models revealed the LSTM model performed better at predicting the motions of the platform. INDEX TERMSMooring line failure, failure detection, machine learning, neural networks, floating production storage and offloading.
Petrobras, through its Research Center and in cooperation with Universities and Research Institutes, has invested in the development of new concept of platform, aiming to minimize the movements of the structure to work in the field of oil and gas in ultra-deep water. One of these developments is related with a Mono-Column conception provided with a moonpool. In the OMAE2005 Conference, an experimental study of the behavior of this concept was presented, showing the influence of the diameter of the opening of the moonpool base in the heave and pitch motions. A new experimental program was carried out in LabOceano/COPPE/UFRJ, to study the influence of different skirts and the influence of variation of the external diameter along the vertical axis in the behavior of the monocolumn in waves. In this new experimental program a storage unit was tested.
Model test verification of floater systems in ultra-deep water meets limitations when it comes to available laboratory sizes. Systems in depths beyond 1000–1500 m cannot be tested at reasonable scales without the truncation of the mooring and riser system. The development of methods and procedures to overcome this problem has been addressed through extensive research programs at MARINTEK (VERIDEEP, VERIDEEP Extension, NDP, DEMO2000). This led to a hybrid verification procedure which combines reasonable truncation principles, model tests of the truncated system, and numerical simulations, to estimate the system’s response at full depth. There is, however, still a need to address the actual influence from the truncation procedure, and from the integration with simulations, on the final extrapolated full depth results. This paper presents a case study for the validation of the procedure, that compares full depth model test results of a semisubmersible in water depth 1250m against the extrapolated full depth results obtained from a truncated system of 500m. Results are presented for line tension and vessel responses in 3 seastates. In general the extrapolated full depth results were found to be in good agreement with the full depth model tests. However, the results confirmed expectation that the low frequency response has the greater uncertainties and presents the greatest challenge for the procedure.
MonoBr is the name of a concept of a mono-column structure with a moon-pool developed by PETROBRAS to operate in deep water. A set of tests has been carried out at LabOceano / COPPE / UFRJ to analyze its behavior in waves. Different configurations of the moon-pool entrance have been tested. The main objective of the measurements carried out is to determine the influence of different restrictions on the behavior of the vertical motion of the structure. Results of these measurements are presented and discussed in the paper.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.