Vortex-Induced Motion (VIM), which occurs as a consequence of exposure to strong current such as Loop Current eddies in the Gulf of Mexico, is one of the critical factors in the design of the mooring and riser systems for deepwater offshore structures such as Spars and multi-column Deep Draft Floaters (DDFs). The VIM response can have a significant impact on the fatigue life of mooring and riser components. In particular, Steel Catenary Risers (SCRs) suspended from the floater can be sensitive to VIM-induced fatigue at their mudline touchdown points. Industry currently relies on scaled model testing to determine VIM for design. However, scaled model tests are limited in their ability to represent VIM for the full scale structure since they are generally not able to represent the full scale Reynolds number and also cannot fully represent waves effects, nonlinear mooring system behavior or sheared and unsteady currents. The use of Computational Fluid Dynamics (CFD) to simulate VIM can more realistically represent the full scale Reynolds number, waves effects, mooring system, and ocean currents than scaled physical model tests. This paper describes a set of VIM CFD simulations for a Spar hard tank with appurtenances and their comparison against a high quality scaled model test. The test data showed considerable sensitivity to heading angle relative to the incident flow as well as to reduced velocity. The simulated VIM-induced sway motion was compared against the model test data for different reduced velocities (Vm) and Spar headings. Agreement between CFD and model test VIM-induced sway motion was within 9% over the full range of Vm and headings. Use of the Improved Delayed Detached Eddy Simulation (IDDES, Shur et al 2008) turbulence model gives the best agreement with the model test measurements. Guidelines are provided for meshing and time step/solver setting selection.

Localization problem is a significant component of the Internet of Things (IoT) and interference source localization is of great importance in the context of spectrum monitoring and management. However, it remains challenging to quickly but accurately locate an interference source from the distance, especially when little is known about the interference source. To handle this problem, a single learning algorithm can be exploited to search and locate the interference source. However, it is varying dynamics in varying environments that can make the design of such a learning algorithm intractable. In our study, we employ an unmanned aerial vehicle (UAV) to realize the localization. Moreover, a novel multimodal Q-learning framework along with its algorithm is proposed, and the framework combines pattern recognition with Q-learning. The proposed learning architecture can adjust the parameters of Q-learning algorithm dynamically based on the changing environments so as to achieve better detection precision, longer localization distance and shorter searching time. The simulation verifies multimodal Q-learning algorithm's performance on interference source localization along with its capability of adapting to environmental change. The simulation results confirm the proposed concept of multimodal Q-learning. It is shown that the multimodal Q-learning based localization algorithms can outperform various baselines in terms of both accuracy and detection distance. The searching time consumed by the UAV is also largely reduced. This observation indicates that the capability of environmental adaption introduced by the proposed multimodal framework can benefit the Q-learning algorithms.

Several recent benchmark studies have demonstrated that Computational Fluid Dynamics (CFD) is capable of capturing both nonlinear and viscous effects in offshore marine hydrodynamics and predicting well certain wave- and current-induced offshore platform motion. In order to apply CFD for practical global performance analysis of a complete hull-mooring-riser coupled floating system, we develop an advanced numerical wave basin that combines CFD, nonlinear irregular wave modeling, and finite-element mooring modeling. Specifically, CFD is used to simulate the violent free-surface flow with hull motions; nonlinear wave modeling is applied to generate a realistic wavefield and provide initial and far-field conditions to CFD for efficient long-duration simulation; and mooring modeling is two-way coupled with CFD to account for dynamic mooring response and its effects on hull motion. In this study, to demonstrate the capability of such tool, the global performance of a semi-submersible with 4 mooring lines in a 3-hour extreme sea state is simulated for both head and quartering sea. The simulation results are compared to model test data of hull motion, mooring line tension, and relative wave elevation around the hull for validation. It is shown with spectrum and statistics that the simulations predict well the platform’s global performance in all frequency ranges, including low frequency where the mooring lines have the greatest influence on the motion response. Compared to the predictions from a conventional global performance design tool that is based on diffraction analysis and empirical coefficients, the CFD results show significant improvements. The encouraging results from this study indicate that a CFD-based numerical wave basin, although still computationally expensive, is technically ready to be a complementary tool to physical wave basin for offshore platform global performance design.

In this study, a numerical wave tank was set up to simulate the free motion of a Tension Leg Platform (TLP) in extreme wave event. For better computational efficiency, a nonlinear potential flow solver is coupled with a CFD software, with the former to simulate the far-field wave domain and the latter to simulate the near-field wave domain and platform motion. In order to benchmark against model test, a five-minute time window of interest was selected from the extreme sea state in model test. The incoming irregular wave was firstly reconstructed from the measured wave time history using the nonlinear potential flow solver and then applied as input to CFD simulations for two different headings to the platform. Static offset tests and free decay tests were simulated in CFD initially to confirm that the platform and tendon properties were properly modeled. The 6-DOF platform motions were then obtained from the CFD simulations and the time histories of motion, air gap, and tendon tension were compared with model test measurements. Good agreements were achieved except for the initial transient period and low-frequency motions. In particular, the air gap or relative wave elevation compared well for all the locations around the platform. The high frequency response in tendon tension and the different tension characteristics of weather side tendons and leeside tendons were also well captured.

Online medical communities have revolutionized the way patients obtain medical-related information and services. Investigating what factors might influence patients’ satisfaction with doctors and predicting their satisfaction can help patients narrow down their choices and increase their loyalty towards online medical communities. Considering the imbalanced feature of dataset collected from Good Doctor, we integrated XGBoost and SMOTE algorithm to examine what factors and these factors can be used to predict patient satisfaction. SMOTE algorithm addresses the imbalanced issue by oversampling imbalanced classification datasets. And XGBoost algorithm is an ensemble of decision trees algorithm where new trees fix errors of existing trees. The experimental results demonstrate that SMOTE and XGBoost algorithm can achieve better performance. We further analyzed the role of features played in satisfaction prediction from two levels: individual feature level and feature combination level.