• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.1
• /
• pp.53-59
• /
• 2021

The marine transport industry generally applies new technologies later than other transport industries, such as airways and railways. Vessels require efficient operation, and their performance and lifespan depend on the level of maintenance and management. Many studies have shown that corrective maintenance (CM) and time-based maintenance (TBM) have restrictions with respect to enabling efficient maintenance of workload and cost to improve operational efficiency. Predictive maintenance (PdM) is an advanced technology that allows monitoring the condition and performance of a target machine to predict its time of failure and helps maintain the key machinery in optimal working conditions at all times. This study presents the development of a marine predictive maintenance (MPdM; maritime predictive maintenance) method based on applying PdM to the marine environment. The MPdM scheme is designed by considering the special environment of the marine transport industry and the extreme marine conditions. Further, results of the study elaborates upon the concept of MPdM and its necessity to advancing marine transportation in the future.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.141-148
• /
• 2022

Recently, reinforcement learning combined with deep neural network technology has achieved remarkable success in various fields such as board games such as Go and chess, computer games such as Atari and StartCraft, and robot object manipulation tasks. However, such deep reinforcement learning describes states, actions, and policies in vector representation. Therefore, the existing deep reinforcement learning has some limitations in generality and interpretability of the learned policy, and it is difficult to effectively incorporate domain knowledge into policy learning. On the other hand, dNL-RRL, a new relational reinforcement learning framework proposed to solve these problems, uses a kind of vector representation for sensor input data and lower-level motion control as in the existing deep reinforcement learning. However, for states, actions, and learned policies, It uses a relational representation with logic predicates and rules. In this paper, we present dNL-RRL-based policy learning for transportation mobile robots in a manufacturing environment. In particular, this study proposes a effective method to utilize the prior domain knowledge of human experts to improve the efficiency of relational reinforcement learning. Through various experiments, we demonstrate the performance improvement of the relational reinforcement learning by using domain knowledge as proposed in this paper.

• Journal of Navigation and Port Research
• /
• v.46 no.4
• /
• pp.338-343
• /
• 2022

As the revitalization of the global maritime industry continues, the number of foreign ships navigating the maritime territories of maritime neighboring countries has rapidly increased. However, large-scale marine accidents have occurred, caused by the insufficient establishment of a system for management and operation relative to vessels' safety-condition. To address that, the IMO has granted the right to exercise port state control, especially for foreign vessels, to countries with jurisdiction over maritime territories with strengthening regulations and guidelines. In particular, the Republic of Korea, as a member of the TOKYO MOU, is conducting PSC, but as of 2020, the proportion of foreign ships was three times higher than that of national ships that called in domestic ports. However, the inspection rate was low at 9% which has not met the recommended level by the TOKYO MOU. Thus, this study conducted an IPA analysis as well as content analysis, by collecting the practical opinions and views of PSCO through objective questionnaires and written expert interviews, for improving the efficiency and effectiveness of domestic PSC. As a result, it was derived that the importance and performance related to human factors such as life on board, working environment, and response to safety accidents should be improved in to raise the quality of PSC inspection. Additionally, the work environment and performance of PSC in domestic ports for foreign vessels could be improved, if multifaceted support bases are established, for administrative unification of related tests for PSC, recruitment of PSCO, activation of the defection-reporting system, reorganization of the PSC execution group, etc.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.2
• /
• pp.314-323
• /
• 2022

Vessel Traffic Services (VTS) operators perform traffic management tasks using VTS systems and sensor equipment designated as VTS facilities to promote the safety and efficiency of vessel traffic. The necessary VTS information for effective operations could be obtained through the additional access of various information channels other than the designated VTS facility. To unify these various information access windows, the development of the VTS cloud system is in progress. In this study, the operational information analysis for VTS was performed through VTS tasks-facility linkage analysis to identify the user required information according to the introduction of the VTS cloud system. The VTS task analysis was performed through research of the international and domestic literature, and expert interviews. The necessary information were identified and linked according to the VTS facilities. As a result of the analysis, 37 categories of necessary information were identified for internal and external information windows, and 8 information windows were selected other than the present VTS equipment. The identified user requirements would be applied to the structure design of the VTS cloud system. In the future, it is necessary to update user requirements through scenario-based user operation analysis and to conduct additional research on the system interface design.

• Smart Structures and Systems
• /
• v.29 no.4
• /
• pp.625-640
• /
• 2022

Maglev rail joints are vital components serving as connections between the adjacent F-type rail sections in maglev guideway. Damage to maglev rail joints such as bolt looseness may result in rough suspension gap fluctuation, failure of suspension control, and even sudden clash between the electromagnets and F-type rail. The condition monitoring of maglev rail joints is therefore highly desirable to maintain safe operation of maglev. In this connection, an online damage detection approach based on three-dimensional (3D) convolutional neural network (CNN) and time-frequency characterization is developed for simultaneous detection of multiple damage of maglev rail joints in this paper. The training and testing data used for condition evaluation of maglev rail joints consist of two months of acceleration recordings, which were acquired in-situ from different rail joints by an integrated online monitoring system during a maglev train running on a test line. Short-time Fourier transform (STFT) method is applied to transform the raw monitoring data into time-frequency spectrograms (TFS). Three CNN architectures, i.e., small-sized CNN (S-CNN), middle-sized CNN (M-CNN), and large-sized CNN (L-CNN), are configured for trial calculation and the M-CNN model with excellent prediction accuracy and high computational efficiency is finally optioned for multiple damage detection of maglev rail joints. Results show that the rail joints in three different conditions (bolt-looseness-caused rail step, misalignment-caused lateral dislocation, and normal condition) are successfully identified by the proposed approach, even when using data collected from rail joints from which no data were used in the CNN training. The capability of the proposed method is further examined by using the data collected after the loosed bolts have been replaced. In addition, by comparison with the results of CNN using frequency spectrum and traditional neural network using TFS, the proposed TFS-CNN framework is proven more accurate and robust for multiple damage detection of maglev rail joints.

• Korean Journal of Construction Engineering and Management
• /
• v.23 no.6
• /
• pp.30-42
• /
• 2022

OSC is a type of supply chain and value chain that spans the entire process of construction production (planning, design, construction, maintenance, etc.). It is a method of producing the final object by manufacturing it in a factory, transporting it to the site, installing and construction. This research as is the construction cost was compared for each case A, which applied the PC method, and case B, which applied the RC method. In the case of applying the PC method (excluding the PC design cost), compared to the case where only the RC method was applied, the frame construction cost per unit quantity (m³) increased by about 70% (50% based on the total RC construction type). Of the total frame construction cost of PC method application, PC accounted for 90.2%, 'PC manufacturing cost' 54.8%, 'PC assembly cost' 28.5%, and 'transportation cost' accounted for 6.89%. Also a decision-making framework that can consider both costs and benefits was established. In the case of benefits, the construction period, defect repair, disaster occurrence, energy efficiency, noise/dust/waste, and greenhouse gas emission indicators reflecting OSC technical advantages were presented. It can contribute to providing a basis for helping decision-making on the introduction of PC apartment houses using OSC.

• Journal of Digital Convergence
• /
• v.20 no.5
• /
• pp.463-476
• /
• 2022

After industrialization in the past, the automobile industry has continued to grow centered on internal combustion engines, but is facing a major change with the recent 4th industrial revolution. Most companies are preparing for the transition to electric vehicles and autonomous driving. Therefore, in this study, topic modeling was performed based on LDA algorithm by collecting 4,002 domestic papers and 68,372 overseas papers that contain keywords related to CASE (Connectivity, Autonomous, Sharing, Electrification), which represent future automobile trends. As a result of the analysis, it was found that domestic research mainly focuses on macroscopic aspects such as traffic infrastructure, urban traffic efficiency, and traffic policy. Through this, the government's technical support for MaaS (Mobility-as-a-Service) is required in the domestic shared car sector, and the need for data opening by means of transportation was presented. It is judged that these analysis results can be used as basic data for the future automobile industry.

• Journal of The Korea Institute of Healthcare Architecture
• /
• v.28 no.3
• /
• pp.47-54
• /
• 2022

Purpose: This study presents the analysis on space usage of delivery departments in regional public hospitals. The results intention is to achieve improvement of the delivery environment for the mothers and newborns regarding exposure prevention and efficient infection control. The purpose of this study is to provide fundamental data for architectural plans and guidelines for the delivery department. Method: The investigation and analysis were based on research papers, legal systems, public medical statistical data, and the architectural floor plan drawing. For research, 20 regional public hospitals with an operating delivery room were excluded. Regarding data accessibility, 15 regional public hospitals were selected. Results: To overcome the increased vulnerability of the delivery department, the research results of basic data is provided for the establishment to address urgent needs and rapid response. Thus, the research results are as follows: Firstly, the delivery department needs to respond promptly according to the type of patients. For example, in a case of emergency surgery, a connected circulation plan with the related departments is needed. Secondly, for the environment of the delivery area, alleviating anxiety is imperative for pregnant patients and guardians, labor, childbirth, and recovery. Therefore, these needs must be addressed for treatment space and circulation. Lastly, the delivery department is classified into three areas for analysis: access area, treatment area, and support area. In most of the delivery departments of the 15 selected hospitals, there is no space for the access and support area except for the labor and delivery rooms in the treatment area. For the access area, a waiting area, changing room for pregnant women and guardians, and a storage space for contaminated linens are required for infection prevention, safety, and efficiency. For the treatment area, childbirth processes and circulation should have space reserved for labor, delivery, recovery, examination, and treatment. In preparation for an emergency during childbirth, emergency response measures and supporting space needs to be established. For the support area, circulation and rooms are to be designed for medical staff support, activity space, storage and transportation of equipment, and urgent medical treatment. Implications: Along with the low fertility rate and the decrease of medical institutions that operate delivery departments, for the purpose of establishing a public medical service system and a healthy medical environment for mothers and newborns, the researched information demonstrates basic data on space plan of delivery departments in regional public hospitals.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.35 no.6
• /
• pp.603-609
• /
• 2022

Passivation quality is mainly governed by epitaxial growth of crystalline silicon wafer surface. Void-rich intrinsic a-Si:H interfacial layer could offer higher resistivity of the c-Si surface and hence a better device efficiency as well. To reduce the resistivity of the contact area, a modification of void-rich intrinsic layer of a-Si:H towards more ordered state with a higher density is adopted by adapting its thickness and reducing its series resistance significantly, but it slightly decreases passivation quality. Higher resistance is not dominated by asymmetric effects like different band offsets for electrons or holes. In this study, multilayer of intrinsic a-Si:H layers were used. The first one with a void-rich was a-Si:H(I₁) and the next one a-SiO_x:H(I₂) were used, where a-SiO_x:H(I₂) had relatively larger band gap of ~2.07 eV than that of a-Si:H (I₁). Using a-SiO_x:H as I₂ layer was expected to increase transparency, which could lead to an easy carrier transport. Also, higher implied voltage than the conventional structure was expected. This means that the a-SiO_x:H could be a promising material for a high-quality passivation of c-Si. In addition, the i-a-SiO_x:H microstructure can help the carrier transportation through tunneling and thermal emission.

• Korean journal of applied entomology
• /
• v.61 no.4
• /
• pp.539-548
• /
• 2022

In recent decades, the world has entered a new era in terms of the number and variety of biological invasions, due to economic progress and transportation efficiency. Biological invasion is becoming more likely as demand for foreign fresh foods and decorative goods grows. Alien species continue to infiltrate Korea in a variety of ways, and disturb on the insect fauna of Korea. The goal of plant quarantine is to decrease the economic impact of alien pests on the agriculture and forestry industries. In this study, we focused on insects found in imported cut flowers from 1996 to 2020 using pest information system. Overall, 147,160 cut flowers (159 items) were imported into Korea from 69 countries during this time period. Throughout this time, 467 species of insects were found in all imported cut flowers to Korea, total 13,757 detections. They were classified as provisional regulated pests in 273 species, quarantine managed pests in 78 species, and non-quarantine pests in 118 species. Thysanoptera and Hemiptera had the largest number of alien insect detections (more than 80% of the alien insects) among the nine orders. The outcomes of this study have highlighted the need for ongoing inspection activities targeted at preventing quarantine alien pests from entering or incursion in Korea.