Tropical cyclones (TCs) are the most destructive weather systems that form over the tropical oceans, with 90 storms forming globally every year. The timely detection and tracking of TCs are important for advanced warning to the affected regions. As these storms form over the open oceans far from the continents, remote sensing plays a crucial role in detecting them. Here we present an automated TC detection from satellite images based on a novel deep learning technique. In this study, we propose a multi-staged deep learning framework for the detection of TCs, including, (i) a detector -Mask Region-Convolutional Neural Network (R-CNN), (ii) a wind speed filter, and (iii) a classifier -CNN. The hyperparameters of the entire pipeline is optimized to showcase the best performance using Bayesian optimization. Results indicate that the proposed approach yields high precision (97.10%), specificity (97.59%), and accuracy (86.55%) for test images.
Rigid subsea jumper systems are typically used as interface between subsea structures and are required to accommodate significant static and dynamic loads. Due to constraints imposed by in-line planar jumpers (e.g. U shaped and M shaped jumpers), the industry is shifting towards the use of multi-planar jumper systems (e.g., Z-shaped jumpers). These multi-planar jumper systems have increased tolerance to end displacements and can be tailored to accommodate cyclic end motions of subsea structures. Multi-planar systems, however, come with unique challenges of their own including the coupling of flexural and torsional responses under vortex induced vibrations (VIV), fluid induced vibration (FIV) and slugging. In particular, the development of hydrodynamic slug flow is a common occurrence in oil and gas pipelines. It is understood to be initiated by instabilities of wave on the gas-liquid interface. It is also understood that slug flows are the source of vibration within pipework when a change of direction occurs e.g. 90° bend at a subsea riser base or top side piping. In standard slug flow vibration analysis, averaged slug frequency and length are used to calculate the force generated. In the case of a multi-planar rigid jumper, several changes of direction occur within a short length of pipe. After each bend the characteristics of the slug flow are modified. It is necessary to accurately capture these changes in order to reproduce the forces generated at critical points along the jumper length. This paper presents a methodology for analyzing slugging induced fatigue that has been developed in an on-going study undertaken by MCS Kenny for design of multi-planar rigid jumper systems. In this methodology, Computational Fluid Dynamics (CFD) is used to accurately simulate the flow within the jumper and provide pressure fluctuations on the internal pipe wall for the vibration analysis. The pressure fluctuations are then incorporated in a Finite Element (FE) model of the jumper system and further used to determine the slugging fatigue damage. CFD (Star-ccm+) and FE (Flexcom, ABAQUS) software programs are used to accurately capture the response of the jumper system. Key conclusions and challenges overcome during the course of this study are presented herein.
Evaluation of corroded chain link for continued use or life extension is a challenging task for the industry. ABS, together with fifteen (15) participating organizations, initiated the Fatigue of Corroded Chains (FoCCs) Joint Industry Project (JIP) in 2016. The objective of the FoCCs JIP is to investigate methodologies for assessing remaining fatigue life of the corroded mooring chain used for floating production systems. The JIP scope includes fatigue testing in labs and finite element analysis (FEA) of corroded chain samples retrieved from six floating production facilities in West Africa and the North Sea. The participating organizations include oil majors, chain manufactures, consulting firms, and classification societies, which represent a pool of broad range of mooring knowledge and experience. Knowledge gained from the JIP will be summarized and used toward the development of guidance notes for assessing fatigue life of corroded mooring chain for the industry. Six sets of mooring chain samples with different corrosion conditions have been collected, cleaned and digitally scanned for fatigue testing and FEA. Procedures for testing and analysis have been developed with the objective of establishing commonly accepted methods. Different FEA procedures have been studied for making a better prediction of stress ranges of the corroded chain links. The findings from the fatigue testing and FEA will be utilized as basis for further development of the methods for fatigue assessment of corroded mooring chain. This paper summarizes the tests and FE analysis work for the selected chain samples. The JIP research work has found that corrosion, either general corrosion or local/pitting corrosion, can significantly reduce the chain fatigue capacity. The location and the geometry of corrosion pits have more impact on fatigue lives than the pit size. The JIP study has shown that FE analysis is an effective tool to capture the hot spot of corroded chain links and can provide insight in their fatigue performance. Different methods on the assessment of the stress range of a hot spot are compared and discussed.
Vortex‐induced vibration (VIV) fatigue is one of the failure mechanisms of riser systems. Failure occurs due to the fatigue of the structure in vibration. VIV is caused by the motion of risers or other structures to shed vortices when exposed to fluid flow (such as currents and waves) impinging on the structure. The response of the structure is dependent on the natural frequencies of the structure and the frequency at which the structure sheds vortices (shedding frequency). Several physical quantities affect the VIV response such as the dimensions, stiffness, damping, and mass of the structure. VIV results in catastrophic failure of the riser system and is a critical that either the structure by design has low fatigue damage due to VIV or some external VIV suppressing devices are used to ensure safe operations. This article discusses the theory/concepts of VIV and the unique aspects of each riser system (TTRs, SCRs, flexibles, etc.) that need to be accounted for in the fatigue evaluation. The final section of this article introduces the typical suppressing devices that are used. This article focuses on the concepts relevant for riser VIV, and further reading is presented toward the end, for those readers interested in gaining more in‐depth understanding of the topic.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.