Janghoon Seo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Janghoon Seo has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Dong-Woo Park
School of Electrical and Control Engineering Autonomous Vehicle System Engineering Major Tongmyong University Busan Korea
3 shared publications - Bonguk Koo
Department of Smart Ocean Mobility Engineering, Changwon National University, Changwon 51140, Republic of Korea
2 shared publications Dong-Woo Park
2 shared publicationsHyun Sik Yoon
2 shared publications- Hyun Sik Yoon
Department of Naval Architecture and Ocean Engineering, Pusan National University, 2, Busandaehak-ro 63beon-gil, Geumjeong-gu, Busan 46241, Republic of Korea
2 shared publications - Jae Hwan Jung
Senior Researcher, Deep Ocean Engineering Research Center KRISO, Busan, Republic of Korea
2 shared publications
Latest Publications
- Open Access
- 13 August 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (16) , 8083
DQN-Based Operational Path Planning for Autonomous Fishing Vessel Safety in Waves
Developing autonomous navigation systems for small fishing vessels is required to improve path-tracking robustness and mitigate severe wave-induced roll motions. This study proposes a Deep Q-Network (DQN)-based operational path planning methodology that explicitly incorporates roll motion reduction into the reward function, combining a maneuvering model with hydrodynamic analyses. Simulation results under varying wave directions and heights demonstrate that the vessel actively adjusts its heading to minimize the roll response. Based on statistical evaluations across five independent runs, the proposed model effectively reduced the average and maximum roll responses by an average of 3% and 2%, respectively, under the evaluated wave headings at a wave height of 1.0 m, while maintaining operational path tracking, despite a slight increase in the total operational path length. Future research will focus on integrating complex environmental conditions with wind and current, and performing the model test for the validation of the established DQN model.
- 13 August 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (16) , 8083
Open AccessDQN-Based Operational Path Planning for Autonomous Fishing Vessel Safety in Waves
Developing autonomous navigation systems for small fishing vessels is required to improve path-tracking robustness and mitigate severe wave-induced roll motions. This study proposes a Deep Q-Network (DQN)-based operational path planning methodology that explicitly incorporates roll motion reduction into the reward function, combining a maneuvering model with hydrodynamic analyses. Simulation results under varying wave directions and heights demonstrate that the vessel actively adjusts its heading to minimize the roll response. Based on statistical evaluations across five independent runs, the proposed model effectively reduced the average and maximum roll responses by an average of 3% and 2%, respectively, under the evaluated wave headings at a wave height of 1.0 m, while maintaining operational path tracking, despite a slight increase in the total operational path length. Future research will focus on integrating complex environmental conditions with wind and current, and performing the model test for the validation of the established DQN model.
- 7 June 2026
- Published by Elsevier in Ocean Engineering
- Vol. 362
An integrated methodology for barge skeg design combining deep neural networks and particle swarm optimization
- 7 June 2026
- Published by Elsevier in Ocean Engineering
- Vol. 362
An integrated methodology for barge skeg design combining deep neural networks and particle swarm optimization
- 15 October 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Structural Stability and Dynamics
- Vol. 25 (23)
Numerical Approach to Air-Gap Assessment of Overhanging Wind Turbine Blades on a WTIV Under Various Environmental Conditions
This study investigates the safety of overhanging wind turbine blades during transportation on a wind turbine installation vessel (WTIV) by analyzing the air-gap between the blade tip and the wave surface under various environmental conditions. Both hydrodynamic analysis, based on radiation–diffraction theory, and computational fluid dynamics (CFD) analysis, including viscous effects and a regular design wave approach, are conducted. Hydrodynamic analysis indicates that beam wave directions constitute the most critical conditions for air-gap, with resonance effects significantly reducing the safety margin. The resonance effect reduced the air-gap margin by approximately 52% and 51% in transportation and installation and extreme conditions, respectively. CFD analysis generally estimates more conservative air-gap values and indicates the generation of pressure on the submerged blade tip. A maximum difference of approximately 24% is observed between the CFD and hydrodynamic analyses. The findings highlight the necessity of carefully considering wave height and period relative to the WTIV’s motion characteristics to ensure safe operations and prevent blade submersion. This research establishes a valuable approach for evaluating air-gap and pressure on overhanging blades, highlighting the importance of appropriate selection of operating environmental conditions. Further study should focus on model tests and alternative arrangements to further validate these results.
- 15 October 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Structural Stability and Dynamics
- Vol. 25 (23)
Numerical Approach to Air-Gap Assessment of Overhanging Wind Turbine Blades on a WTIV Under Various Environmental Conditions
This study investigates the safety of overhanging wind turbine blades during transportation on a wind turbine installation vessel (WTIV) by analyzing the air-gap between the blade tip and the wave surface under various environmental conditions. Both hydrodynamic analysis, based on radiation–diffraction theory, and computational fluid dynamics (CFD) analysis, including viscous effects and a regular design wave approach, are conducted. Hydrodynamic analysis indicates that beam wave directions constitute the most critical conditions for air-gap, with resonance effects significantly reducing the safety margin. The resonance effect reduced the air-gap margin by approximately 52% and 51% in transportation and installation and extreme conditions, respectively. CFD analysis generally estimates more conservative air-gap values and indicates the generation of pressure on the submerged blade tip. A maximum difference of approximately 24% is observed between the CFD and hydrodynamic analyses. The findings highlight the necessity of carefully considering wave height and period relative to the WTIV’s motion characteristics to ensure safe operations and prevent blade submersion. This research establishes a valuable approach for evaluating air-gap and pressure on overhanging blades, highlighting the importance of appropriate selection of operating environmental conditions. Further study should focus on model tests and alternative arrangements to further validate these results.
- 3 October 2025
- Published by Elsevier in Ocean Engineering
- Vol. 342
Optimization of a mooring system applying a deep neural network under multi-directional environmental conditions
- 3 October 2025
- Published by Elsevier in Ocean Engineering
- Vol. 342
Optimization of a mooring system applying a deep neural network under multi-directional environmental conditions
- Open Access
- 31 December 2024
- Published by The Korean Society of Ocean Engineers in Journal of Ocean Engineering and Technology
- Vol. 38 (6) , 336-349
Evaluation of the Seakeeping Performance Indices for Enhancing Crew Safety and Workability in Small Fishing Vessels
This study evaluated the applicability of the seakeeping performance indices for assessing the safety and crew workability of small fishing vessels, considering the high incidence of accidents in this type of vessel and the limited research on the impact of vessel motion on crew safety. Hydrodynamic analyses of 16 fishing vessels were conducted and the responses of roll, pitch, MII (Motion induced interruption), and MSI (Motion sickness incidence) were derived under various environmental conditions. A three-dimensional panel method based on potential flow theory was used to assess the motion responses of the vessels. Viscous roll damping coefficients were derived from computational fluid dynamics simulations for three representative vessels and applied to the remaining vessels. The results suggested that the magnitude of the seakeeping performance indices varied according to the vessel dimensions and main particulars. In particular, MII exceeded the established criteria for most vessels except in the lowest environmental condition, highlighting the need for criteria specific to small fishing vessels. The study also examined the influence of the forward speed on the indices and found that roll and pitch responses increase with the speed while MSI decreases marginally. Overall, these findings may help enhance the safety of vessels and crew members in small fishing vessels.
- 31 December 2024
- Published by The Korean Society of Ocean Engineers in Journal of Ocean Engineering and Technology
- Vol. 38 (6) , 336-349
Open AccessEvaluation of the Seakeeping Performance Indices for Enhancing Crew Safety and Workability in Small Fishing Vessels
This study evaluated the applicability of the seakeeping performance indices for assessing the safety and crew workability of small fishing vessels, considering the high incidence of accidents in this type of vessel and the limited research on the impact of vessel motion on crew safety. Hydrodynamic analyses of 16 fishing vessels were conducted and the responses of roll, pitch, MII (Motion induced interruption), and MSI (Motion sickness incidence) were derived under various environmental conditions. A three-dimensional panel method based on potential flow theory was used to assess the motion responses of the vessels. Viscous roll damping coefficients were derived from computational fluid dynamics simulations for three representative vessels and applied to the remaining vessels. The results suggested that the magnitude of the seakeeping performance indices varied according to the vessel dimensions and main particulars. In particular, MII exceeded the established criteria for most vessels except in the lowest environmental condition, highlighting the need for criteria specific to small fishing vessels. The study also examined the influence of the forward speed on the indices and found that roll and pitch responses increase with the speed while MSI decreases marginally. Overall, these findings may help enhance the safety of vessels and crew members in small fishing vessels.
- Open Access
- 1 December 2024
- Published by Walter de Gruyter GmbH in Polish Maritime Research
- Vol. 31 (4) , 4-20
Evaluation of Prediction Performances of Deep Learning Models for the Aerodynamic Characteristics of Flettner Rotors
This study investigates the prediction of the aerodynamic characteristics of Flettner rotors through three deep learning models. Various numbers of Flettner rotors, arrangements, and spin ratios are employed to consider these effects in the dataset. For the training of deep learning models, a dataset of aerodynamic force coefficients and flow fields is generated using Computational Fluid Dynamics (CFD). Three deep learning architectures (U-net, Encoder-Decoder, and Decoder models) are employed and trained to predict the aerodynamic characteristics of Flettner rotors. Three deep learning models are established through a training stage with a hyperparameter study and by altering the number of layers. The aerodynamic force coefficients and flow fields are predicted by established deep learning models and show small absolute errors compared to those from the CFD analysis. Moreover, predicted flow fields reflect the flow characteristics according to the difference of spin ratio and arrangement of Flettner rotors. In conclusion, the established deep learning models demonstrate rapid and robust predictions of aerodynamic force coefficients and flow fields for Flettner rotors under varying arrangements and spin ratios. Furthermore, a significant reduction in computational time is measured when comparing the analysis time of CFD simulations to the training and testing time of the deep learning models.
- 1 December 2024
- Published by Walter de Gruyter GmbH in Polish Maritime Research
- Vol. 31 (4) , 4-20
Open AccessEvaluation of Prediction Performances of Deep Learning Models for the Aerodynamic Characteristics of Flettner Rotors
This study investigates the prediction of the aerodynamic characteristics of Flettner rotors through three deep learning models. Various numbers of Flettner rotors, arrangements, and spin ratios are employed to consider these effects in the dataset. For the training of deep learning models, a dataset of aerodynamic force coefficients and flow fields is generated using Computational Fluid Dynamics (CFD). Three deep learning architectures (U-net, Encoder-Decoder, and Decoder models) are employed and trained to predict the aerodynamic characteristics of Flettner rotors. Three deep learning models are established through a training stage with a hyperparameter study and by altering the number of layers. The aerodynamic force coefficients and flow fields are predicted by established deep learning models and show small absolute errors compared to those from the CFD analysis. Moreover, predicted flow fields reflect the flow characteristics according to the difference of spin ratio and arrangement of Flettner rotors. In conclusion, the established deep learning models demonstrate rapid and robust predictions of aerodynamic force coefficients and flow fields for Flettner rotors under varying arrangements and spin ratios. Furthermore, a significant reduction in computational time is measured when comparing the analysis time of CFD simulations to the training and testing time of the deep learning models.
- 30 August 2024
- Published by Elsevier in Ocean Engineering
- Vol. 312
Prediction of three-dimensional flow characteristics for cylinders with wavy geometric disturbance using deep learning models
- 30 August 2024
- Published by Elsevier in Ocean Engineering
- Vol. 312
Prediction of three-dimensional flow characteristics for cylinders with wavy geometric disturbance using deep learning models
- Open Access
- 21 August 2024
- Published by Walter de Gruyter GmbH in Polish Maritime Research
- Vol. 31 (3) , 4-14
Numerical Study on the Effect of Weight Variables on the Roll Damping Coefficients for a Fishing Vessel
The roll damping coefficient is essential when considering the viscous effect in the potential-based hydrodynamic analysis of fishing vessels; it is an important factor in the roll motion response. The present study performs free roll decay simulations, altering weight variables using Computational Fluid Dynamics (CFD) to investigate the correlation between the roll damping coefficient and the weight variation of a fishing vessel. The time series of roll amplitude and roll damping coefficient are compared, for varying vertical and longitudinal centres of gravity and radii of gyration in roll motion. As the vertical centre of gravity increases, both the roll decay period and the roll damping coefficient also increase. The roll decay period tends to increase with the increase in the radius of gyration during roll motion, while the roll damping coefficient exhibits a decrease. A longitudinal centre of gravity has a limited effect on free roll decay characteristics. The roll damping coefficients between the maximum and minimum combinations of weight variables show significant differences. The findings of the present study could enhance the understanding of the safety of fishing vessels based on their loading conditions. Consequently, future research could further improve the results obtained in the present study by considering various hull shapes and speeds.
- 21 August 2024
- Published by Walter de Gruyter GmbH in Polish Maritime Research
- Vol. 31 (3) , 4-14
Open AccessNumerical Study on the Effect of Weight Variables on the Roll Damping Coefficients for a Fishing Vessel
The roll damping coefficient is essential when considering the viscous effect in the potential-based hydrodynamic analysis of fishing vessels; it is an important factor in the roll motion response. The present study performs free roll decay simulations, altering weight variables using Computational Fluid Dynamics (CFD) to investigate the correlation between the roll damping coefficient and the weight variation of a fishing vessel. The time series of roll amplitude and roll damping coefficient are compared, for varying vertical and longitudinal centres of gravity and radii of gyration in roll motion. As the vertical centre of gravity increases, both the roll decay period and the roll damping coefficient also increase. The roll decay period tends to increase with the increase in the radius of gyration during roll motion, while the roll damping coefficient exhibits a decrease. A longitudinal centre of gravity has a limited effect on free roll decay characteristics. The roll damping coefficients between the maximum and minimum combinations of weight variables show significant differences. The findings of the present study could enhance the understanding of the safety of fishing vessels based on their loading conditions. Consequently, future research could further improve the results obtained in the present study by considering various hull shapes and speeds.
- 30 December 2023
- Published by The Korean Society of Marine Environment and Safety in Journal of the Korean Society of Marine Environment & Safety
- Vol. 29 (7) , 958-963
Motion Response Estimation of Fishing Boats Using Deep Neural Networks
- 30 December 2023
- Published by The Korean Society of Marine Environment and Safety in Journal of the Korean Society of Marine Environment & Safety
- Vol. 29 (7) , 958-963
Motion Response Estimation of Fishing Boats Using Deep Neural Networks
- Open Access
Deep Learning Models for the Evaluation of the Aerodynamic and Thermal Performance of Three-Dimensional Symmetric Wavy Wings
The present study initially evaluates the feasibility of deep learning models to predict the flow and thermal fields of a wing with a symmetric wavy disturbance as the passive flow control. The present study developed the encoder–decoder (ED) and convolutional neural network (CNN) models to predict the characteristics of flow and heat transfer on the surface of three-dimensional wavy wings in a wide range of parameters, such as the aspect ratio, wave amplitude, wave number, and the angle of attack. Computational fluid dynamics (CFD) is used to generate the dataset of the deep learning models. Various tests are carried out to examine the predictive performance of the architectures for two deep learning models. The CNN and ED models demonstrated a quantitatively predictive performance for aerodynamic coefficients and Nusselt numbers, as well as a qualitative prediction for pressure contours, limiting streamlines, and Nusselt contours. The predicted results well reconstructed the spiral vortical formation and the separation delay by the limiting streamlines. It is expected that the present established deep learning methods are useful to perform the parametric study to find the conditions to provide efficient aerodynamic and thermal performances.
Open AccessDeep Learning Models for the Evaluation of the Aerodynamic and Thermal Performance of Three-Dimensional Symmetric Wavy Wings
The present study initially evaluates the feasibility of deep learning models to predict the flow and thermal fields of a wing with a symmetric wavy disturbance as the passive flow control. The present study developed the encoder–decoder (ED) and convolutional neural network (CNN) models to predict the characteristics of flow and heat transfer on the surface of three-dimensional wavy wings in a wide range of parameters, such as the aspect ratio, wave amplitude, wave number, and the angle of attack. Computational fluid dynamics (CFD) is used to generate the dataset of the deep learning models. Various tests are carried out to examine the predictive performance of the architectures for two deep learning models. The CNN and ED models demonstrated a quantitatively predictive performance for aerodynamic coefficients and Nusselt numbers, as well as a qualitative prediction for pressure contours, limiting streamlines, and Nusselt contours. The predicted results well reconstructed the spiral vortical formation and the separation delay by the limiting streamlines. It is expected that the present established deep learning methods are useful to perform the parametric study to find the conditions to provide efficient aerodynamic and thermal performances.