The LH11-1 FPSO is an 80,000 t cylindrical structure that is responsible for the processing, storage, and offloading of process oil from existing and newly developed oilfields. In this paper, a full probabilistic analysis was developed based on very detailed CFD simulation results to evaluate ventilation, gas dispersion, explosion, and fire scenarios. A detailed fire and explosion risk analysis of LH11-1 FPSO was performed based on NORSOK Z-013 and FABIG Technical Note 11. The risk-based calculations were performed applying FLACS, KFX, and DNV GLEXPRESS Fire. Finally, the oil and gas dispersion, fire, and explosion consequence risks were calculated under the credible combination of leak frequency and leak location. By this probabilistic risk analysis, it was found that the west wind could generate optimal ventilation conditions for the topside process area of FPSO compared to other wind directions, while the hull region was poorly ventilated for all wind directions. The explosion risk analysis showed that the FPSO system would take no action in terms of explosion risk according to the acceptance criteria of 10-4occ/year. Meanwhile, the fire risk analysis demonstrated that the PR1 first and second deck, PR2 first and second deck, process deck, offloading on starboard, and the base of the flare tower would have different impacts from the fire, and the PR1 first deck and PR2 first deck at the topside deck would be severely impacted regions.
Recent years have witnessed the increasing risk of subsea gas leaks with the development of offshore gas exploration, which poses a potential threat to human life, corporate assets, and the environment. The optical imaging-based monitoring approach has become widespread in the field of monitoring underwater gas leakage, but the shortcomings of huge labor costs and severe false alarms exist due to related operators’ operation and judgment. This study aimed to develop an advanced computer vision-based monitoring approach to achieve automatic and real-time monitoring of underwater gas leaks. A comparison analysis between the Faster Region Convolutional Neural Network (Faster R-CNN) and You Only Look Once version 4 (YOLOv4) was conducted. The results demonstrated that the Faster R-CNN model, developed with an image size of 1280 × 720 and no noise, was optimal for the automatic and real-time monitoring of underwater gas leakage. This optimal model could accurately classify small and large-shape leakage gas plumes from real-world datasets, and locate the area of these underwater gas plumes.
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.