A Thrust Allocation Method for Efficient Dynamic Positioning of a Semisubmersible Drilling Rig Based on the Hybrid Optimization Algorithm

Zhao, Luman,Roh, Myung-Il Hindawi Limited 2015 Mathematical problems in engineering Vol.2015 No.-

<P>A thrust allocation method was proposed based on a hybrid optimization algorithm to efficiently and dynamically position a semisubmersible drilling rig. That is, the thrust allocation was optimized to produce the generalized forces and moment required while at the same time minimizing the total power consumption under the premise that forbidden zones should be taken into account. An optimization problem was mathematically formulated to provide the optimal thrust allocation by introducing the corresponding design variables, objective function, and constraints. A hybrid optimization algorithm consisting of a genetic algorithm and a sequential quadratic programming (SQP) algorithm was selected and used to solve this problem. The proposed method was evaluated by applying it to a thrust allocation problem for a semisubmersible drilling rig. The results indicate that the proposed method can be used as part of a cost-effective strategy for thrust allocation of the rig.</P>

Hardware-in-the-loop simulation of an offshore support vessel crane combined with physics-based analysis

Luman Zhao(조로만),Myung-Il Roh(노명일),Seung-Ho Ham(함승호),Xing Li(이성),Hyewon Lee(이혜원) (사)한국CDE학회 2016 한국 CAD/CAM 학회 학술발표회 논문집 Vol.2016 No.동계

COLREGs-compliant multiship collision avoidance based on deep reinforcement learning

Zhao, Luman,Roh, Myung-Il Elsevier 2019 Ocean engineering Vol.191 No.-

<P><B>Abstract</B></P> <P>Developing a high-level autonomous collision avoidance system for ships that can operate in an unstructured and unpredictable environment is challenging. Particularly in congested sea areas, each ship should make decisions continuously to avoid collisions with other ships in a busy and complex waterway. Furthermore, recent reports indicate that a large number of marine collision accidents are caused by or are related to human decision failures concerning a lack of situational awareness and failure to comply with the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs). In this study, we propose an efficient method to overcome multiship collision avoidance problems based on the Deep Reinforcement Learning (DRL) algorithm by expanding our previous study (Zhao et al., 2019). The proposed method directly maps the states of encountered ships to an ownship's steering commands in terms of rudder angle using the Deep Neural Network (DNN). This DNN is trained over multiple ships in rich encountering situations using the policy-gradient based DRL algorithm. To address multiple encountered ships, we classify them into four regions based on COLREGs, and consider only the nearest ship in each region. We validate the proposed collision avoidance method in a variety of simulated scenarios with thorough performance evaluations, and demonstrate that the final DRL controller can obtain time efficient and collision-free paths for multiple ships. Simulation results indicate that multiple ships can avoid collisions with each other while following their own predefined paths simultaneously. In addition, the proposed approach demonstrates its excellent adaptability to unknown complex environments with various encountered ships.</P> <P><B>Highlights</B></P> <P> <UL> <LI> This study deals with a multiship collision avoidance problem in congested sea areas. </LI> <LI> A COLREGs-compliant method for multiship collision avoidance is proposed based on deep reinforcement learning. </LI> <LI> A novel strategy is used to solve the problem by categorizing target ships into four regions defined by COLREGs. </LI> <LI> The proposed method is applied to a wide range of problems, from single collision avoidance to multiple collision avoidance. </LI> </UL> </P>

Antisway Control of a Crane on an Offshore Support Vessel Based on the Hardware-in-the-Loop Simulation

Zhao, Luman,Roh, Myung-Il,Ham, Seung-Ho International Society of Offshore and Polar Engine 2018 International journal of offshore and polar engine Vol.28 No.2

<P>Ship-mounted cranes are used widely in the transportation and installation of heavy loads at sea. To minimize the sway motion induced by the harsh environment, the cranes are equipped with antisway-compensation equipment. To effectively test the feasibility of the antisway algorithms at the early design stage, the hardware-in-the-loop simulation (HILS) technique can efficiently be used for the proposed technique of this study. In this study, it is applied to the example of the antisway control of a crane on an offshore support vessel during the installation operation of subsea equipment using the HILS.</P>

Optimal Thrust Allocation for Dynamic Positioning of Deep-sea Working Vessel

Zhao, Luman,Roh, Myung-Il,Hong, Jeong-Woo Korean Society of Ocean Engineers 2015 Journal of advanced research in ocean engineering Vol.1 No.2

In this study, a thruster allocation method of a deep-sea working vessel was proposed with the aims of producing the demanded generalized forces and moment for dynamic positioning while at the same time minimizing total power. For this, an optimization problem for thrust allocation was mathematically formulated with design variables, objective function, and constraints. The genetic algorithms (GA) was used to solve the formulated problem. The proposed method was applied to an example of finding optimal thrust allocation of the deep-sea working vessel having 5 thrusters. The result showed that the method could be used to determine better strategy for thruster allocation of the vessel as compared to existing study.

Integrated method of analysis, visualization, and hardware for ship motion simulation

Seung-Ho Ham,Myung-Il Roh,Luman Zhao 한국CDE학회 2018 Journal of computational design and engineering Vol.5 No.3

Traditionally, graphs were the only way to show the results of ship motion analyses. They did not usually impose any feeling about how fast the ship could move or how large the positions of the ship changed. Currently, integrated simulations combining physics-based analyses with IT technologies, such as virtual reality (VR), motion platforms, or other hardware, can offer a potential solution. In ship motion analyses, the dynamic ship response can be obtained by considering the environmental loads, such as ocean waves, and VR technology can be used to visualize the analysis results in the virtual world. We can see the ship motion relative to textures of real objects, including the water and sky, as if in the real world. The results calculated from the ship motion analysis can also be transferred to the motion platform to generate real-istic movements. However, it is not easy to integrate three different technologies in one system because they have different purposes and have been developed individually. To solve this problem, an integrated simulation framework based on three different technologies is proposed. The proposed framework can be used to synchronize the simulation time and exchange the data through the middleware using a stan-dardized data structure. Furthermore, we can easily add new components or remove the existing compo-nents in the simulation. To verify the efficiency and applicability of the proposed framework, the motion simulation of a drillship is applied.

Integrated method of analysis, visualization, and hardware for ship motion simulation

Ham, Seung-Ho,Roh, Myung-Il,Zhao, Luman Society for Computational Design and Engineering 2018 Journal of computational design and engineering Vol.5 No.3

Traditionally, graphs were the only way to show the results of ship motion analyses. They did not usually impose any feeling about how fast the ship could move or how large the positions of the ship changed. Currently, integrated simulations combining physics-based analyses with IT technologies, such as virtual reality (VR), motion platforms, or other hardware, can offer a potential solution. In ship motion analyses, the dynamic ship response can be obtained by considering the environmental loads, such as ocean waves, and VR technology can be used to visualize the analysis results in the virtual world. We can see the ship motion relative to textures of real objects, including the water and sky, as if in the real world. The results calculated from the ship motion analysis can also be transferred to the motion platform to generate realistic movements. However, it is not easy to integrate three different technologies in one system because they have different purposes and have been developed individually. To solve this problem, an integrated simulation framework based on three different technologies is proposed. The proposed framework can be used to synchronize the simulation time and exchange the data through the middleware using a standardized data structure. Furthermore, we can easily add new components or remove the existing components in the simulation. To verify the efficiency and applicability of the proposed framework, the motion simulation of a drillship is applied.

조선 해양 분야 적용을 위한 해석, 하드웨어 및 가시화 기반의 실시간 시뮬레이션 방법

함승호(Seung-Ho Ham),노명일(Myung-Il Roh),이성(Xing Li),조로만(Luman Zhao) (사)한국CDE학회 2015 한국 CAD/CAM 학회 학술발표회 논문집 Vol.2015 No.하계

Recently, interests of ship and offshore simulators are increased for the purpose of design, production, training, engineering, safety assessment, and so on. Basically, three different kinds of technologies are required to develop such simulators in the field of naval architecture and ocean engineering; physics-based analysis, hardware, and virtual reality. In this study, a real-time simulation method based on analysis, hardware, and visualization is proposed. For this, an integrated simulation framework is proposed. To check the applicability of the proposed method, it is applied to motion analysis of a drillship. The result shows that the proposed method can be used for various purposed in the field of naval architecture and ocean engineering.

조선소 생산 작업 지원을 위한 VR 기반 협업 시뮬레이션에 관한 연구

이성(Xing Li),함승호(Seung-Ho Ham),조로만(Luman Zhao),하솔(Sol Ha),노명일(Myung-Il Roh) (사)한국CDE학회 2015 한국 CAD/CAM 학회 학술발표회 논문집 Vol.2015 No.동계

In shipbuilding production, several types of cranes are simultaneously used to effectively handle a building block which is more than hundred tons. For this, one or more operators operate each crane, and the cooperation among the operators is very important. In the previous studies, the maximum tension of wire ropes of the cranes and motion of the block were analyzed computationally during lifting operation based on fixed scenarios with simulation. This couldn’t reflect the interaction during the operation which can cause unexpected results. Therefore, a collaborative simulation system for production in shipyard was developed in this study. The developed system is comprised of three parts. The first part is an input device which generates signals such as hoisting up and down of the wire ropes of the cranes. The second part is a dynamics engine which receives the signals from several operators and reflects them as a simulation scenario. The last part is a display device which is used to share simulation results between the workers and visualizes the simulation results in multi-views on the network. Finally, the developed system was applied to a block erection process which is operated by three crane operators and one commander. As a result, it is shown that the developed system can be used to simulate or train the collaborative work of the operators in shipyard.

무인수상정의 기뢰 탐지 임무 수행을 위한 통합 시뮬레이션 방법 연구

이혜원(Hye-Won Lee),노명일(Myung-Il Roh),함승호(Seung-Ho Ham),조로만(Luman Zhao),김낙완(Nak-Wan Kim),하솔(Sol Ha),우주현(Joo-Hyun Woo),정우현(Woo-Hyun Jung),유찬우(Chan-Woo Yu) (사)한국CDE학회 2017 한국CDE학회 논문집 Vol.22 No.3

The USV performs various missions including mine detection and marine reconnaissance and survey unmanned. As the autonomic software for USV takes charge of detection, decision, and command instead of human, the verification and validation (V&V) of the software is highly required at the early design stage. Due to the difficulty of such V&V before the real USV is made, the virtual prototype of USV and ocean space are adopted in this study. For mine detection mission, which is one of the most important mission of USV, four modules are developed and implemented here; scenario management and display module, USV motion analysis module, submarine topography synthesis module, and mine detection module. The mine detection module represents the control algorithm in autonomic software, and the rest of the modules are virtual prototype which represents the ocean space and hardware in USV such as GPS (Global Positioning System) and SSS (Side Scan Sonar). With the virtual prototype modules, the control algorithm in mine detection module is verified. Meanwhile, for the data communication between the modules, the ROS (Robot Operating System) is used. The ROS provides message communication function between the modules, so that each module can transmit and receive data during the simulation. To check the applicability of the proposed method, the mine detection scenario is performed using the virtual prototype of USV and ocean space. The result shows that the proposed method can be effectively used to test and develop the mine detection algorithm of autonomic software in USV.