Project experience
| Time | Role | Project name |
|---|---|---|
| 2021-2023 | PI | Erasmus+/EEC project “Romanian - Norwegian Strategic Cooperation in Maritime Higher Education for Enhancement human Capital and Knowledge Base in the Field of Marine Intelligent Technologies”, Project partner: Academia Naval 'Mircea cel Batran'(Total budget: 162 M Euros). |
| 2020-2021 | PI | RFF Møre og Romsdal project “A Dashboard System for Maritime Crane Condition Monitoring”, Project partners: Seaonics AS, and Offshore Simulation Centre (Total budget: 1.0 M NOK). |
| 2020-2023 | Key member | IKTPLUSS project “Remote Control Centre for Autonomous Ship Support”, Project partners: Harbin Engineering University, Vard Electro AS, Offshore Simulation Centre, Ålesund Kunnskapspark. (Total budget: 9 M NOK) |
| 2019-2020 | PI | RFFMIDT project "Dynamic Motion Planning Based on Trajectory Prediction in Close-range Manoeuvring", Project partners: Offshore Simulation Centre (Total budget: 1.6 M NOK). |
| 2019-2022 | Key member | EU project "Arrowhead Tools for Engineering of Digitalisation Solutions", Project partners: 82 partners from 18 European countries (Total budget: 92 M Euros). |
| 2018-2022 | Key member | Knowledge-building Project for Industry-MAROFF KPN, "Digital Twins for Vessel Life Cycle Service (TwinShip)", Project partners: DNV GL, NTNU, Rolls Royce Marine, Ålesund Kunnskapspark AS (ÅKP) and SINTEF Aalesund (Total budget: 32 M NOK). |
| 2018-2021 | PI | Innovation Project for the Industrial Sector IPN, “Towards Ship Autonomy in Harbour Manoeuvring and Intelligent Docking”, Project partners: Rolls-Royce Marine AS, SINTEF Aalesund and Offshore Simulation Centre (Total budget: 10 M NOK, granted but withdrawn due to company merger). |
| 2017-2018 | Key member | RFFMIDT project "An Integrated Sensor Fusion System for Fatigue and Awareness Assessment in Demanding Marine Operation", Project partners: Offshore Simulation Center (Total budget: 1.6 M NOK). |
| 2016-2017 | PI | RFFMIDT project "An Approach toward Optimal Control of Ship Maneuvering in Offshore Operations", Project partners: Rolls-Royce Marine AS, Offshore Simulation Center (Total budget: 1.0 M NOK). |
| 2014-2018 | Key member | Knowledge-building Project for Industry-MAROFF KPN, "Integrated Marine Operation Simulator Facilities for Risk Assessment Including Human Factors (IMPROVE)", Project partners: DNV GL, NTNU, Offshore Simulation Centre, Stanford University (Total budget: 13.8 M NOK). |
| 2014-2015 | Key member | RFFMIDT project "Gunnerus- a full-scale laboratory for testing future marine technology in close collaboration between industry and academia", Project partners: Rolls-Royce Marine AS (Total budget: 1.5 M NOK). |
Project description
2020-present: A Dashboard System for Maritime Crane Condition Monitoring
As the PI of the RFF Møre og Romsdal project, Guoyuan proposed to take the Palfinger crane on the Gunnerus R/V vessel as the testbed to develop a dashboard system that will visualize crane operational condition in a fashion of real-time data plot and 3D simulation, and implement crane operation evaluation and maintenance tools based on historical operation data. In particular, the project will utilize historical sensor data to identify system parameters of the crane model, build tools to reproduce crane operations via real-time sensor data, and assess operational safety.
2020-present: Remote Control Centre for Autonomous Ship Support
This project aims to establish a remote control centre for on-board support of autonomous ships. In particular, efforts will be put on the sub-area “autonomy and remote control technology” by analyzing historical/real-time ship data and modelling sophisticated planner, predictor and controller, thereby establishing remote supporting platform. The system will be developed to serve for ships that are either autonomous or remote-controlled for safety and reliability enhancement. I am responsible for “ship performance optimization” and “human-in-the-loop control” working package in the project.
2019-present: Arrowhead Tools for Engineering of Digitalisation Solutions
This is an EU H2020 project. The aim is to create technology tools for the next generation of solutions in digitization and automation for the European industry. I join the project as the project coordinator for NTNU Aalesund. Our task is to develop digital twin of crane for structural monitoring. More information please see the project description.
2019-2020: Dynamic Motion Planning Based on Trajectory Prediction in Close-range Manoeuvring
Guoyuan is the PI of the RFF Midt-Norge project. The main project goal is to develop a dynamic path-planning system for Offshore Simulation Centre (OSC) AS to aid manoeuvre in close-range encounters, and therefore provide more reasonable and on-time suggestions in form of visualized trajectories during intensive testing of manoeuvring autonomous ships. In the project, Guoyuan is responsible for problem formulation of path optimization in close-range manoeuvring, developing a hybrid path-planning scheme that combines optimization technologies with prediction algorithms, and a case study and verification in OSC simulator.
2018-present: Digital Twins for Vessel Life Cycle Service (TwinShip)
The goal of this research is to develop digital twins of maritime systems and operations, which is an open virtual simulator as the next generation of marine industrial infrastructure not only for overall system design, allowing configuration of systems and verification of operational performance, but also more focusing to provide early warning, life cycle service support, and system behavior prediction. As the leader in WP2, Guoyuan is responsible for system design of digital twins for maritime prediction and maintenance, and for developing tools for early warning, prediction, and optimization based on digital twins for maritime industry.
2018-present: Towards Ship Autonomy in Harbour Manoeuvring and Intelligent Docking
Guoyuan is the PI of this IPN project. The main goal of the project is to develop robust and efficient maneuvering system using artificial intelligence for on-board supporting of flexible docking operation, and contribute to a strong Norwegian maritime offshore industry through world leading competence and knowledge in the fields of ship intelligence. Guoyuan has designed five working packages from environmental perception, structural modeling, motion planning, human-in-the-loop control to semi/ automatic docking control. The project was granted by the Research Council of Norway, but withdrawn by industrial partners due to company merger.
2017-2018: DeepTek Pre-project
This pre-project is supported by the Offshore Simulation Centre (OSC) AS. It aims to investigate a hybrid control mode of a rig for dynamic positioning (DP) applications. The rig is moored with four wires anchored in the seabed and employed with six thrusters, both of which can compensate environmental effects. In most of the time, only the mooring system is responsible for DP applications. Unless the limitations of the mooring system such as the limited winch force reach, the thruster system will be in charge of the task to eliminate environmental disturbances. In the project, Guoyuan is responsible for developing the hybrid control system and verify it in the OSC commercial simulator.
2017-2018: An Integrated Sensor Fusion System for Fatigue and Awareness Assessment in Demanding Marine Operation
The main project goal is to develop methods and tools for Offshore Simulation Centre (OSC) to help understand human operator’s working situation with greater accuracy, and therefore a more reliable evaluation of fatigue and awareness assessment during a demanding marine operation could be made. Guoyuan was in charge of the first working package, focusing on concept design of a multi-sensor fusion system for fatigue and awareness assessment in demanding offshore operations.
2014-2018: Integrated Marine Operation Simulator Facilities for Risk Assessment Including Human Factors (IMPROVE)
The primary objective of this project is to develop a new integrated architecture for planning and execution of demanding marine operations, with corresponding risk evaluation tools that take human factors, focusing on situational awareness, into the consideration. This will serve the industry for the purpose of improving operational effectiveness and safety through the use of simulator facilities. There are three working packages in the project, including (1) simulation facilities integration, (2) integrating marine operation training program, and (3) risk assessment. Guoyuan was the leader of working package (1), focusing on integrating multiple sensors into the simulation, such as eye tracker, heart rate sensor, body temperature sensors, oxygen level sensors and blood pressure sensors.
2016-2017: An Approach toward Optimal Control of Ship Maneuvering in Offshore Operations
Guoyuan is the PI of the RFF Midt-Norge project. He proposed the idea and started to work on it from 2016. The project aims to develop a new control scheme that will provide operators with a good understanding and prediction of the ship’s maneuvering behavior together with an iterative optimization method in order to accomplish safe and efficient maneuvering during demanding operations. Neural-network-based learning module has been utilized for ship status prediction, together with an optimizer on the control system for ship maneuvering in demanding operations. They have achieved good results including one journal paper and two conference papers. The result was also verified in a professional simulator (the Offshore Simulator Centre AS). See project information here.
2014-2015: MS GUNNERUS Project for Fine Ship Maneuvering
This project aims to develop an adaptive neural-network-based controller for fine maneuvering of surface vessels applying on offshore applications. Guoyuan is the project leader who not only theoretically analyzed and designed the controller but also carried out related experiments on the CyberShip II ship model. Without any prior knowledge of the vessel, the controller can approximate the unknown nonlinear dynamics of the vessel taking advantage of online learning ability. The results show the effectiveness of the controller for providing good transient and steady state performance in fine maneuvering.