• International Journal of Naval Architecture and Ocean Engineering
• /
• v.13 no.1
• /
• pp.208-222
• /
• 2021

Managing with the presence of sea ice is the primary challenge in the operation of floating platforms in the Arctic region. It is widely accepted that offshore structures operating in Arctic conditions need station-keeping methods as well as ice management by icebreakers. Dynamic Positioning (DP) is one of the station-keeping methods that can provide mobility and flexibility in marine operations. The presence of sea ice generates complex external forces and moments acting on the vessel, which need to be counteracted by the DP system. In this paper, an icevaning control algorithm is proposed that enables Arctic offshore vessels to perform DP operations. The proposed icevaning control enables each vessel to be oriented toward the direction of the mean environmental force induced by ice drifting so as to improve the operational safety and reduce the overall thruster power consumption by having minimum external disturbances naturally. A mathematical model of an Arctic offshore vessel is summarized for the development of the new icevaning control algorithm. To determine the icevaning action of the Arctic offshore vessel without any measurements and estimation of ice conditions including ice drift, task and null space are defined in the vessel model, and the control law is formulated in the task space. A backstepping technique is utilized to handle the nonlinearity of the Arctic offshore vessel's dynamic model, and the Lyapunov stability theory is applied to guarantee the stability of the proposed icevaning control algorithm. Experiments are conducted in the ice tank of the Korea Research Institute of Ships and Ocean Engineering to demonstrate the feasibility of the proposed approach.

• Nuclear Engineering and Technology
• /
• v.54 no.5
• /
• pp.1674-1685
• /
• 2022

The ball valve is an important device in the pipeline transportation system of nuclear power plants. Its operational stability and safety directly affect the normal working of nuclear power plants. In this study, the transient numerical simulation of the opening and closing process of a ball valve was conducted on the basis of the flow interruption capability experiment of the ball valve by using the moving mesh method and inlet and outlet variable boundary conditions. The flow rate and pressure difference with time of the opening and closing process of the ball valve were studied. The internal flow characteristics of the ball valve under different relative openings were analyzed in conjunction with the typical back-step flow structure. Results show that the transient numerical results agree well with the experimental results. The internal flow characteristics of the ball valve are similar at the same opening during opening and closing process. At small opening, the spool and outlet channels easily form a back-step flow structure. The disappearance and generation of backflow vortices during opening and closing occur at 85% opening and 75% opening, respectively. With the decrease in opening degree, the difference in vortex core area in the flow channel of the ball valve spool in the opening and closing process gradually appears. The research results provide some reference value for the design and optimization of ball valves.

• Nuclear Engineering and Technology
• /
• v.54 no.1
• /
• pp.49-60
• /
• 2022

Motivated by the high-resolution properties of high-order Weighted Essentially Non-Oscillatory (WENO) and flux limiter (FL) for steep-gradient problems and the robust convergence of Jacobian-free Newton-Krylov (JFNK) methods for nonlinear systems, the preconditioned JFNK fully implicit high-order WENO and FL schemes are proposed to solve the transient two-phase two-fluid models. Specially, the second-order fully-implicit BDF2 is used for the temporal operator and then the third-order WENO schemes and various flux limiters can be adopted to discrete the spatial operator. For the sake of the generalization of the finite-difference-based preconditioning acceleration methods and the excellent convergence to solve the complicated and various operational conditions, the random vector instead of the initial condition is skillfully chosen as the solving variables to obtain better sparsity pattern or more positions of non-zero elements in this paper. Finally, the WENO_JFNK and FL_JFNK codes are developed and then the two-phase steep-gradient problem, phase appearance/disappearance problem, U-tube problem and linear advection problem are tested to analyze the convergence, computational cost and efficiency in detailed. Numerical results show that WENO_JFNK and FL_JFNK can significantly reduce numerical diffusion and obtain better solutions than traditional methods. WENO_JFNK gives more stable and accurate solutions than FL_JFNK for the test problems and the proposed finite-difference-based preconditioning acceleration methods based on the random vector can significantly improve the convergence speed and efficiency.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.4
• /
• pp.63-77
• /
• 2023

This study applies reinforcement learning to effectively operate expressway hard shoulder running (HSR). An HSR algorithm was developed, and its effectiveness was evaluated using the VISSIM microscopic simulation program. The simulation evaluated two aspects: mobility and safety. The DQN-based HSR algorithm found speed improvement of up to 26 km/h. Compared to the current method, the difference in the number of conflicts was not significant. Considering the results, a DQN-based HSR operation has a clear effect, and it is necessary to consider adjusting the current operational criteria.

• International Journal of Computer Science & Network Security
• /
• v.23 no.8
• /
• pp.177-189
• /
• 2023

Malware detection is an increasingly important operational focus in cyber security, particularly given the fast pace of such threats (e.g., new malware variants introduced every day). There has been great interest in exploring the use of machine learning techniques in automating and enhancing the effectiveness of malware detection and analysis. In this paper, we present a deep recurrent neural network solution as a stacked Long Short-Term Memory (LSTM) with a pre-training as a regularization method to avoid random network initialization. In our proposal, we use global and short dependencies of the inputs. With pre-training, we avoid random initialization and are able to improve the accuracy and robustness of malware threat hunting. The proposed method speeds up the convergence (in comparison to stacked LSTM) by reducing the length of malware OpCode or bytecode sequences. Hence, the complexity of our final method is reduced. This leads to better accuracy, higher Mattews Correlation Coefficients (MCC), and Area Under the Curve (AUC) in comparison to a standard LSTM with similar detection time. Our proposed method can be applied in real-time malware threat hunting, particularly for safety critical systems such as eHealth or Internet of Military of Things where poor convergence of the model could lead to catastrophic consequences. We evaluate the effectiveness of our proposed method on Windows, Ransomware, Internet of Things (IoT), and Android malware datasets using both static and dynamic analysis. For the IoT malware detection, we also present a comparative summary of the performance on an IoT-specific dataset of our proposed method and the standard stacked LSTM method. More specifically, of our proposed method achieves an accuracy of 99.1% in detecting IoT malware samples, with AUC of 0.985, and MCC of 0.95; thus, outperforming standard LSTM based methods in these key metrics.

• Nuclear Engineering and Technology
• /
• v.55 no.9
• /
• pp.3423-3440
• /
• 2023

In this work, a multivariate time-series machine learning meta-model is developed to predict the transient response of a typical nuclear power plant (NPP) undergoing a steam generator tube rupture (SGTR). The model employs Recurrent Neural Networks (RNNs), including the Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and a hybrid CNN-LSTM model. To address the uncertainty inherent in such predictions, a Bayesian Neural Network (BNN) was implemented. The models were trained using a database generated by the Best Estimate Plus Uncertainty (BEPU) methodology; coupling the thermal hydraulics code, RELAP5/SCDAP/MOD3.4 to the statistical tool, DAKOTA, to predict the variation in system response under various operational and phenomenological uncertainties. The RNN models successfully captures the underlying characteristics of the data with reasonable accuracy, and the BNN-LSTM approach offers an additional layer of insight into the level of uncertainty associated with the predictions. The results demonstrate that LSTM outperforms GRU, while the hybrid CNN-LSTM model is computationally the most efficient. This study aims to gain a better understanding of the capabilities and limitations of machine learning models in the context of nuclear safety. By expanding the application of ML models to more severe accident scenarios, where operators are under extreme stress and prone to errors, ML models can provide valuable support and act as expert systems to assist in decision-making while minimizing the chances of human error.

• Journal of Smart Tourism
• /
• v.2 no.1
• /
• pp.5-19
• /
• 2022

Smart tourism is seen as a revolution in the tourism industry, involving innovative and transformative theoretical-practical approaches for the sector. As a result of its application in the tourist context, benefits can be seen such as more sustainable practices, greater mobility and better accessibility in destinations, evolution of processes and experiences of tourists. Much of this is achieved through the support of technological solutions. However, despite the immense expectations, and the many researches carried out on it, a literature summary regarding the dimensions that can be observed in each application of this smart tourism has not yet been proposed. Therefore, supported by the PRISMA recommendation, this research proposed to carry out an integrative review of the literature on smart tourism (in its different levels of application, such as the city, the destination and the smart tourism region), with the objective of mapping the dimensions that underlie it. Thus, from an initial scope of 833 intellectual productions obtained, inputs were found for the dimensions in 363 of them after a thorough analysis. The compilation of data obtained from these productions supported the proposition of 14 operational dimensions of smart tourism, namely: collaboration, technology, sustainability, experience, accessibility, knowledge management, innovation management, human capital, marketing, customized services, transparency, safety, governance and mobility. With this set of dimensions, it is envisaged that the implementation of smart tourism projects can present more comprehensive and assertive results. In addition, shortcomings and opportunities for new research that support the evolution of the theory and practice of smart tourism are highlighted.

• Structural Engineering and Mechanics
• /
• v.86 no.6
• /
• pp.715-730
• /
• 2023

Broad studies have addressed the issue of structural element damage identification, however, rubber bearing, as a key component of load transmission between the superstructure and substructure, is essential to the operational safety of a bridge, which should be paid more attention to its health condition. However, regarding the limitations of the traditional bearing damage detection methods as well as few studies have been conducted on this topic, in this paper, inspired by the model updating-based structural damage identification, a two-stage bearing damage identification method has been proposed. In the first stage, we deduce a novel bearing damage localization indicator, called element relative MSE, to accurately determine the bearing damage location. In the second one, the prior knowledge of bearing damage localization is combined with sailfish optimization (SFO) to perform the bearing damage estimation. In order to validate the feasibility, a numerical example of a 5-span continuous beam is introduced, also the noise robustness has been investigated. Meanwhile, the effectiveness and engineering applicability are further verified based on an experimental simply supported beam and actual engineering of the I-40 Bridge. The obtained results are good, which indicate that the proposed method is not only suitable for simple structures but also can accurately locate the bearing damage site and identify its severity for complex structure. To summarize, the proposed method provides a good guideline for the issue of bridge bearing detection, which could be used to reduce the difficulty of the traditional bearing failure detection approach, further saving labor costs and economic expenses.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.1220-1220
• /
• 2022

Constructionarium Ltd is a not-for-profit organisation which delivers a residential, experiential, immersive learning opportunity to university students from across the built environment education sector. Since 2002, the Constructionarium education model has been available to students in engineering, construction management and architecture at a purpose built, 19-acre multi-disciplinary training facility in Bircham Newton, England simulating real site life and reflecting site processes, practices and health and safety requirements. The unique approach of Constructionarium puts experiential learning and sustainability at the heart of everything. In a week, students develop a practical understanding of the construction process, develop transferable skills, build a team and are exposed to the latest in sustainable technologies. Experiential learning is what differentiates a Constructionarium project from regular field trips or site visits. At Constructionarium the focus is on learning by participation rather than learning through theory or watching a demonstration. The projects cannot be replicated in a classroom or on campus. Using the hands-on construction of scaled down versions of iconic structures from around the world, students learn that it requires the involvement of the whole construction team to successfully complete their project. Skills such as communication, planning, budgeting, time management and decision making are woven into a week-long interrelationship with industry professionals, academic mentors and trades workers. Working together to enhance transferable skills brings the educational environment into the reality of completing an actual construction project handled by the students. Constructionarium has used this transformational learning model to educate thousands of students from all over the United Kingdom, Europe and Asia. Texas A&M University in the United States has sent multiple teams of students from its Department of Construction Science every operational year since 2016.

• Journal of the Korean Society of Systems Engineering
• /
• v.19 no.2
• /
• pp.59-73
• /
• 2023

Due to the steady growth of the online shopping market and contact-free consumption, the volume of parcels in South Korea continues to increase. However, there is a lack of manpower for delivery workers to handle the growing parcel volume, leading to frequent accidents related to delivery work. As a result, the government and local authorities strive to enhance last-mile logistics efficiency. As one of these measures, unmanned parcel storage lockers are installed and utilized to handle last-mile deliveries. However, the existing parcel storage involves the inconvenience of couriers having to put each parcel in each locker, and this is somewhat insufficient to relieve the workload of delivery workers. In this study, we propose parcel storage devices that use active loading technology to minimize the workload of delivery workers, extract operation risk factors to apply this system to actual sites, and establish risk reduction methods based on the ALARP concept. Through this study, we have laid the groundwork for improving the safety of the system by identifying and proposing mitigation measures for the risk factors associated with the proposed parcel storage devices utilizing active loading technology. When applied in practical settings in the future, this foundation will contribute to the development of a more efficient and secure system. By applying the ALARP concept, a systems engineering technique used in this research, to the development and maintenance of storage devices leveraging active loading technology, it is thought to make the development process more systematic and structured. Furthermore, through the risk management of the proposed system, it is anticipated that a systematic approach to quality management can be employed to minimize defects and provide a stable system. This is expected to be more useful than the existing unmanned parcel storage devices.