Predictive maintenance has been one of important applications of data science technology that creates a predictive model by collecting numerous data related to management targeted equipment. It does not predict equipment failure with just one or two signs, but quantifies and models numerous symptoms and historical data of actual failure. Statistical methods were used a lot in the past as this predictive maintenance method, but recently, many machine learning-based methods have been proposed. Such proposed machine learning-based methods are preferable in that they show more accurate prediction performance. However, with the exception of some learning models such as decision tree-based models, it is very difficult to explicitly know the structure of learning models (Black-Box Model) and to explain to what extent certain attributes (features or variables) of the learning model affected the prediction results. To overcome this problem, a recently proposed study is an explainable artificial intelligence (AI). It is a methodology that makes it easy for users to understand and trust the results of machine learning-based learning models. In this paper, we propose an explainable AI method to further enhance the explanatory power of the existing learning model by targeting the previously proposedpredictive model [5] that learned data from a core facility (Hyper Compressor) of a domestic chemical plant that produces polyethylene. The ensemble prediction model, which is a black box model, wasconverted to a white box model using the Explainable AI. The proposed methodology explains the direction of control for the major features in the failure prediction results through the Explainable AI. Through this methodology, it is possible to flexibly replace the timing of maintenance of the machine and supply and demand of parts, and to improve the efficiency of the facility operation through proper pre-control.

Volatile organic compounds (VOCs) in plants are various organic compounds with small molecular weight and high vapor pressure. The metabolomics approach was recently introduced to analyze VOCs involved in biological processes, such as abiotic and biotic stresses, spatial and temporal distribution, and genotypic differences. In addition, this approach is widely used in combination with identification of VOCs analysis and statistical analysis using multivariate analysis, such as principal component analysis (PCA), partial least squares-discriminant analysis (PLS-DA), hierarchical cluster analysis (HCA), etc. First, in this review, the current condition of the metabolomics approach to analyze VOCs synthesized in plants using head space-solid phase microextraction coupled with gas chromatography-mass spectrometry (HS-SPME-GC-MS) is discussed. In addition, metabolomics approach, such as extraction and analysis of VOCs using HS-SPME-GC-MS, conversion, and processing of mass spectral (MS) data, a database for VOCs identification, useful statistical methods, and statistical tools and applications, are explained. Finally, multi-omics in combination with other omics techniques, such as genomics, transcriptomics, etc. are suggested as prospects of a metabolomics approach for VOC analysis in floricultural plants using HS-SPMEGC- MS. Therefore, the metabolomics approach of HS-SPMEGC- MS will facilitate our understanding of VOCs synthesized in plants. Furthermore, the multi-omics approach will help understand gene functions involved in the biosynthesis of VOCs and help develop new development cultivars with nicer floral scents by contributing to the development of the floricultural industry.

Maritime monitoring requirements have been beyond human operators capabilities due to the broadness of the coverage area and the variety of monitoring activities, e.g. illegal migration, or security threats by foreign warships. Abnormal vessel movement can be defined as an unreasonable movement deviation from the usual trajectory, speed, or other traffic parameters. Detection of the abnormal vessel movement requires the operators not only to pay short-term attention but also to have long-term trajectory trace ability. Recent advances in deep learning have shown the potential of deep learning techniques to discover hidden and more complex relations that often lie in low dimensional latent spaces. In this paper, we propose a deep autoencoder-based clustering model for automatic detection of vessel movement anomaly to assist monitoring operators to take actions on the vessel for more investigation. We first generate gridded trajectory images by mapping the raw vessel trajectories into two dimensional matrix. Based on the gridded image input, we test the proposed model along with the other deep autoencoder-based models for the abnormal trajectory data generated through rotation and speed variation from normal trajectories. We show that the proposed model improves detection accuracy for the generated abnormal trajectories compared to the other models.

In the early 1960s, US Air Force lost missile launch bases during ICBM development by a defect in the missile design and operation plan. U.S. DoD realized the limitation of the existing accident prevention method. Therefore, the weapon development required system safety activity, and procurement projects of U.S. DoD applied MIL-STD-882(System Safety). Development projects of U.S. DoD more emphasized the importance of system safety after the space shuttle Challenger exploded in 1986. Currently, Airworthiness certification for military aircraft uses system safety to minimize accidents. The domestic defense aviation R&D projects also use the system safety for the airworthiness certification. However, non-aviation weapon R&D projects rarely applied system safety. This paper presents a system safety application method for domestic weapon R&D projects by studying the U.S. military standards/organizations and domestic defense aviation projects.

When compact HVAC is applied to a building, various variables exist in performing the functions of air conditioning, ventilation, and hot water supply of the building, and various experimental and empirical evaluations according to the energy performance evaluation method of the building occur. We are going to present research data for preparing domestic evaluation standards for energy evaluation methods for compact HVAC and zero-energy buildings to be applied in the future.

We need data such as the number of lanes for lane change on the road as well as environmental and object recognition of the road for the autonomous vehicle of the future. This study proposed an algorithm that recognizes the left and right lanes and the center lane while driving differently from the black box image taken from a car. In general, deep learning does not recognize lanes individually but recognizes all lanes as only one lane. Therefore, using YOLO's object recognition function, the left and right lanes and the center lane were detected as different lanes, and a heuristic method was applied to recognize multi-lanes as more correct lanes. As a result of the performance evaluation, we confirmed that the proposed method detects the lane more accurately than Fast R-CNN and only YOLOv2.

The role of QR Code robots in smart logistics is great. Cognitive robots, such as logistics robots, were mostly used to adjust routes and search for peripheral sensors, cameras, and recognition signs attached to walls. However, recently, the ease of making QR Codes and the convenience of producing and attaching a lot of information within QR Codes have been raised, and many of these reasons have made QR Codes recognizable as visions and others. In addition, there have been cases in developed countries and Korea that control several of these robots at the same time and operate logistics factories smartly. This representative case is the KIVA robot in Amazon. KIVA robots are only operated inside Amazon, but information about them is not exposed to the outside world, so a variety of similar robots are developed and operated in several places around the world. They are applied in various fields such as education, medical, silver, military, parking, construction, marine, and agriculture, creating a variety of application robots. In this work, we are developing a robot that can recognize its current position, move and control in the directed direction through two-dimensional QR Codes with the same horizontal and vertical sides, and the error is to create a QR Code robot with accuracy to reach within 3mm. This paper focuses a study on the application of QR Code position recognition during the development of QR Code-aware indoor mobility robots.

본 연구에서는 비용매 유도 상분리법을 이용하여 폴리에테르이미드 계열의 중공사형 분리막을 제조하였다. 제조 된 중공사막의 모폴로지 조절을 위해 첨가제로는 THF, Ethanol, LiNO3를 사용하였다. 또한 높은 수소분리막의 개발을 위해 모폴로지와 기체투과성능을 특성평가를 통해 방사조건을 최적화하였다. 그 결과 THF의 함량이 증가할수록 수소/이산화탄소 선택도가 증가하였다. 하지만 trade-off 관계로 인하여 투과율은 감소하였다. Ethanol을 첨가하였을 때는 finger-like 구조를 나타냈고, LINO3를 첨가하였을 때 Sponge 구조를 보였다. 특히, PDMS 코팅층을 최적화한 중공사막의 경우, 투과율은 40 GPU, 수소/이산화탄소 선택도는 5.6을 나타냈다.

본 연구에서는 낮은 막 저항을 가지는 알칼리 수전해 시스템 적용을 위한 격리막 제조를 위하여 PPS (Polyphenylene sulfide)를 지지체로 사용하고 Polysulfone과 무기물 첨가제를 이용하여 격리막을 제조한 뒤, 지지체의 두께와 다공도에 대한 영향을 분석하였다. 지지체로 사용된 PPS 펠트를 온도(100°C, 150°C, 200°C)와 압력(1톤, 2톤, 3톤, 5톤)의 변수를 두어 압축을 진행 하여 두께를 조절하고자 하였으며, 무기입자로서 친수성이 높고 내알칼리성이 뛰어난 BaTiO3와 ZrO2를 사용하여 polysulfone과 함께 슬러리를 제조하고 압축한 PPS 펠트 위에 캐스팅하여 다공성 격리막을 제조할 수 있었다. 전자주사현미경(SEM)을 통해 압축 조건에 따른 분리막의 모폴로지 변화를 확인하고, 기공도를 계산하였으며, 압축 조건이 증가할수록 두께와 기공도가 감소하는 경향을 확인하였다. 수전해용 격리막으로서 사용이 가능한지를 확인하기 위하여 다양한 특성 평가를 진행하였다. 기계적강도를 측정한 결과 압축 조건(온도와 압력)이 증가할수록 인장강도가 점차 증가하는 경향을 확인하였다. 최종적으로 내알칼리성 테스트 를 통하여 제조한 다공성 격리막이 우수한 내알칼리성을 가지는 것을 확인하였고, I-V 테스트를 통하여 100°C와 150°C 조건에서 압축된 막들이 기존의 압축하지 않은 막보다 낮은 전압을 가지며 성능이 향상되었다는 것을 확인하였다.

본 연구에서는 polyketone (PK)을 이용하여 전기방사 조건에 따른 섬유 형상의 특성 변화와 유수분리 가능성을 확인해 보았다. 고습과 저습 조건에서는 마이크론 직경의 섬유가 형성되었으며, 특히 고습에서는 섬유의 표면이 거칠게 변한 것이 확인되었다. 섬유 직경을 micro에서 nano로 변경하기 위하여 방사용액에 염을 추가하였으며, 그 결과 섬유 직경이 약 90% 감소하는 것을 확인할 수 있었다. 제조된 rPK-LNC와 PK-H로 유수분리 특성을 확인하기 위해 oil/water 에멀션으로 중 력 조건에서 유수분리를 진행하였으며 total organic carbon (TOC)와 탁도를 측정하여 특성을 분석하였다. 제거율 확인결과 탁도가 TOC와 동일한 경향성을 나타내는 것이 확인되었다. 따라서 본 연구에서는 고분자의 방사조건과 염의 유무에 따른 분리막의 섬유 형상과 물리적 특성변화와 이를 이용한 유수분리 특성에 대해 연구하였다.

PURPOSES : The purpose of this study is to evaluate an asphalt mixture via field application to utilize basalt aggregates produced on Jeju Island for a warm mix asphalt (WMA). METHODS : Using commercially available WMA additives, an indoor experiment is conducted on low- and high-void aggregates among basalt aggregates on Jeju Island. The physical properties of the WMA mixture are evaluated using one solid type and two liquid types of WMA additive. To evaluate the applicability of the WMA additives, air void, saturation, aggregate void, Marshall stability, flow number, indirect tensile strength, and toughness tests are performed. For the field application of WMA using basalt aggregates, three types of pavements (HMA, WMA-Solid, and WMA-liquid) are constructed. When applying the pavements in the field, an anti-stripping agent is incorporated to improve the water resistance while considering the characteristics of the basalt aggregate. Samples are acquired via plant and field coring to evaluate the properties of the materials applied in the field. RESULTS : In the indoor test for analyzing the applicability of the commercialized WMA additives to basalt aggregates, all tests except the indirect tensile strength test show results that satisfy the standards. All test results, including that from the indirect tensile strength test, satisfy the standard values in the test that uses the sample material obtained from the plant. Similarly, in the test with field cores, all test results satisfy the standard values. Therefore, the experimental value in the field application is generally higher than the test value in the indoor experiment. It is inferred that this is due to the difference between the basalt aggregates used in the indoor and field experiments, as well as the addition of the anti-stripping agent. CONCLUSIONS : Basalt aggregates produced on Jeju Island can be used for WMA pavements, as demonstrated via indoor experiments and field applications. However, owing to the characteristics of basalt aggregates, a method for improving water resistance should be considered, and tests to determine the indirect tensile strength should be performed using various basalt aggregates. In addition, because various basalt aggregates exist owing to the diverse geology characteristics of Jeju Island, they should be evaluated via more experiments and field applications.

PURPOSES : The purpose of this study is to preliminarily examine the field applicability of modular pavement marking tape (PMT) to increase the lane awareness of motorists on existing roadways. METHODS : A pavement marking tape (PMT) comprises an adhesion layer and a paint coating layer. The adhesion layer is prepared using gussasphalt-based materials that have properties similar to those of existing asphalt materials. Thermal adhesion is performed to adhere the tape to the pavement. For the paint coating layer, polyurea materials are selected after reviewing the existing materials suitable for pavement lane marking. To conduct field evaluations on the adhesion layer, monitoring is performed after the pilot deployment of the PMT is completed. Twelve samples are prepared to investigate the optimal ratios for the mixture of paint coating layer materials. The durability of the PMT is examined using a turntable road-marking test system (RPA) with a wheel load on the samples. A total of 50,000 RPA, equivalent to P4, is performed. The performance is evaluated by capturing the retroreflectivity measure, which is used as an indicator of the pavement marking performance. The PMT is utilized on a roadway segment with significant heavy vehicle traffic, and continuous monitoring is performed to examine its performance in the field. RESULTS : Based on a visual inspection of the adhesion layer material, no significant issue is observed in terms of the adhesion performance of the PMT. Furthermore, the overall retroreflectivity obtained from the RPA exceeds 300 mcd/m2·lux. It is discovered that the optimal ratios for the mixture of polyurea and binder for the paint coating layer are 4:6 and 2:8, respectively, which results in a retroreflectivity that is 90% or above the initial retroreflectivity. Using a prototype of the PMT for field tests, a performance evaluation is conducted by analyzing the retroreflectivity measured after 2 and 7 weeks from the prototype deployment. The retroreflectivity measured for the first 2 weeks after the deployment appears acceptable for field use. However, the retroreflectivity is reduced significantly when it is measured 7 weeks after deployment, resulting in the necessity for a more reliable material that can retain long-term durability. CONCLUSIONS : The lane awareness of a motorist is crucial for accident mitigation under not only nighttime driving, but also severe weather conditions. In this regard, modular PMT is expected to increase the lane awareness of motorists, thereby improving the quality of lane marking materials. In this study, various exploratory field tests are conducted to analyze the field applicability of the PMT. It is noteworthy that the results presented herein are obtained from preliminary performance evaluations of the PMT. Hence, further investigations pertaining to the long-term durability of PMTs must be conducted using advanced test equipment such as an accelerated pavement tester.

찰옥수수 재배기간 중에 조명나방의 발육태별 밀도 변화와 옥수수의 피해 양상, 유기합성살충제 처리 효과 조사를 통해 1세대 조명나방 유 충에 대한 적절한 방제시기를 결정하였다. 수원 지방에서 2016년 4월 20일에 일미찰 옥수수를 파종하고 7월 26일(옥수수 호숙기)에 수확하였다. 성페로몬트랩 조사에서 1화기(월동세대) 성충은 5월 29일 최대발생 피크를, 5월 31일에 50% 누적 발생을 보였다. 1세대 조명나방 유충의 대부 분은 찰옥수수 생식생장기 초기인 7월 초까지 발육하였다. 1세대 조명나방 유충은 먼저 말린 잎 안에서 가해하고 이후 수술과 줄기로 이동하여 가 해하고, 마지막으로 줄기와 이삭으로 이동하여 가해하였다. 시기별로 살충제를 처리한 후 피해 억제 효과를 검정한 결과, 찰옥수수 9~11엽기 (late whorl stage)(6월 10~17일)가 에토펜프록스 유제의 유효한 처리시기였고, 6~7엽기(mid-whorl stage)(6월 3일)가 카보퓨란 입제의 유효한 처리시기였다. 이 시기들은 두 살충제에 대해 성충 최대포획일 12~19일 후와 5일 후였고, 50% 누적발생일 기준으로는 2일씩 앞당겨졌다.

Laser cladding a surface treatment process that grants superior characteristics such as toughness, hardness, and corrosion resistance to the surface, and rebuilds cracked molds; as such, it can be a strong tool to prolong service life of mold steel. Furthermore, compared with the other similar coating processes – thermal spray, etc., laser cladding provides superior bonding strength and precision coating on a local area. In this study, surface characteristics are studied after laser cladding of low carbon steel using 18%Cr-2.5%Ni-Fe powder (Rockit404), known for its high hardness and excellent corrosion resistance. A diode laser with wavelength of 900-1070 nm is adopted as laser source under argon atmosphere; electrical power for the laser cladding process is 5, 6, and 10 kW. Fundamental surface characteristics such as crossectional microstructure and hardness profile are observed and measured, and special evaluation, such as a soldering test with molten ALDC12 alloy, is conducted to investigate the corrosion resistance characteristics. As a result of the die-soldering test by immersion of low carbon alloy steel in ALDC12 molten metal, the clad layer's soldering thickness decreases.

오늘날 선박국적의 가장 큰 특징은 선박소유자의 국적과 선박의 국적이 서 로 다를 수 있으며, 이것이 편의치적제도(Flags of convenience, 이하 ‘FOC’라 함)라는 명분으로 허용되고 있다는 점이다. 그런데 선박은 국제항해를 통한 국 가 간의 이동이 매우 잦기 때문에 국적의 확인이 매우 수시로 이루어진다. 국적의 확인은 전통적으로 선박에 게양된 국기의 국적을 인지하는 방식으로 이루어져 왔다. 그런데 전파항해의 발전과 통신의 안전을 목적으로 해상이동업 무식별부호가 만들어지고 국제해사기구(International Maritime Organization, 이 하 ‘IMO’라 함)에서 국제해운에 종사하는 선박을 대상으로 AIS(Automatic Identification System) 설치가 의무화되면서 선박의 국적식별수단이 선박에 게 양된 국기에서 해상이동업무식별부호 내의 국적을 나타내는 코드인 해상식별 부호로 변화하게 되었다. 그러나 해상식별부호를 통한 선박국적의 식별은 유엔해양법협약에 언급된 국적증명수단이 아니기 때문에 실제 분쟁에서 국적확인 수단으로 인정받을 수 있는지 모호하다. 이러한 의문은 AIS 송출 신호상의 국적으로 선박국적을 식별 하고 있는 현재의 국가실행과 괴리가 있다고 볼 수 있다. 또한 제재대상 국가 의 선박이 해당 부호를 무단으로 변경할 수 있기 때문에 선박의 식별이 더욱 어려워지고 있다. 이를 해결하기 위해서는 먼저 해상이동업무식별부호 내의 국적정보인 해상 식별부호의 효력을 명확히 할 필요가 있고, 해상이동업무식별부호를 교호로 사 용하거나 무단으로 변경하는 경우에 대한 규제조치를 마련할 필요가 있다.