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.

Considering the features of body repair for automotive body where same damage and repair conditions does not exist in car accident, it is essential to acquire know-how and continuously approach new materials and new technologies on the site of maintenance where the theoretical instruction of textbook cannot react accurately minute by minute. Especially, in case of car repair from unexpected accidents such as body repair or dent repair, it is difficult to satisfy vehicle owners despite their request. Accordingly, this study researched the better maintenance technology to restore to its original state with more improved technology as vehicle owners wish. This study made time to repair reduced by 98% and the cost reduced by 79.6% through the accurate diagnostic technique before repair and maintenance technologies of body crash analysis applying property of high-speed tensile. It also obtains intangible effects including prevention of environmental pollution and maximization of vehicle owners satisfaction.

During the latter part of Joseon Dynasty, Local Confucian School(Geochanghyanggyo) had served as a government school and left many official documents on the educational construction. The construction of Local Confucian School(Geochanghyanggyo), which was recorded in official documents, was diverse, and most of them were reconstructed. Construction-works recorded in an official document was drafted in two ways. One was in the same format as the accounting records and the other was written in the diary format by date. The construction cost was mainly financed by selling the land owned. Of course, with the help of the government, they could receive some of the essential timber and expenses for the construction. The management and maintenance of educational construction was entrusted by a manager called ‘Chaji(次知)’. Then there were employees called ‘Jeonjik(殿直)’ and ‘Gojik(庫直)’ and they were paid for their work.

Machines and facilities are physically or chemically degenerated by continuous usage. The representative type of the degeneration is the wearing of tools, which results in the process mean shift. According to the increasing wear level, non-conforming products cost and quality loss cost are increasing simultaneously. Therefore, a preventive maintenance is necessary at some point . The problem of determining the maintenance period (or wear limit) which minimizes the total cost is called the ‘process mean shift problem’. The total cost includes three items: maintenance cost (or adjustment cost), non-conforming cost due to the non-conforming products, and quality loss cost due to the difference between the process target value and the product characteristic value among the conforming products. In this study, we set the production volume as a decreasing function rather than a constant. Also we treat the process variance as a function to the increasing wear rather than a constant. To the quality loss function, we adopted the Cpm+, which is the left and right asymmetric process capability index based on the process target value. These can more reflect the production site. In this study, we presented a more extensive maintenance model compared to previous studies, by integrating the items mentioned above. The objective equation of this model is the total cost per unit wear. The determining variables are the wear limit and the initial process setting position that minimize the objective equation.

다양한 산업에서 강조되고 있는 정비의 중요성은 각 분야에 다양한 정비전략을 적용하도록 만들었다. 해양산업 역시 그에 따른 정비전략의 변화가 있었으나 타 산업 대비 그 속도가 느려 실제 적용이 되지 않은 채 과거 시행되고 있던 방식을 유지하는 경우가 많다. 특히 선박은 기존에 행해왔던 방식의 정비전략을 사용하고 있는 편이며 해상의 조건에서 선박은 새로운 정비전략의 개발을 필요로 하고있다. 이에 선박예지정비모델은 기기의 정비가 필요한 시점을 예지하여 조치할 수 있는 정비전략으로서 선박이 항해 중에 처할 수 있는 정비 관련 위험요소들을 줄여 주는 모델이다. 본 연구는 선박예지정비모델의 개발을 위한 연구 중의 하나로서, LNG선박 입거사양서의 텍스트 데이터 분석을 통한 결과를 원문의 내용을 바탕으로 해석해보았다. 공통된 정비항목 조합을 도출하여 선박 내 다른 기기들 사이에 작용하고 있는 상호연관성을 발견하고 이를 앞으로 개발될 선박예지정비모델에 적용하고자 한다.

해양 운송 산업은 특성상 항공 및 철도 등의 다른 운송 산업보다 비교적 늦게 신기술이 적용되는 산업이다. 현재 대부분의 선박은 기계장치 및 시스템에 문제가 발생하거나 운용 시간 기반으로 정비를 하는 사후 정비(Corrective Maintenance, CM)와 예방 정비 (Preventive Maintenance, PM)에 속하는 시간 기반 정비(TBM, Time Based Maintenance)가 적용되고 있다. 그러나 높은 유지보수 비용이 요구되고, 육상의 즉각적인 지원이 어려우며, 선박이 멈추면 즉시 위험에 노출되는 해양 환경에서 운영되는 선박에서 과도한 단순 정비로 인한 인력과 비용 낭비, 예측되지 못한 고장 및 결함으로 유발되는 사고 등으로 인해 운용 효율화 측면에서 기존 정비법에 대한 한계점이 문제시 되고 있다. 예지 정비(Predictive Maintenance, PdM)는 진보된 기술로 기계의 상태 및 성능을 모니터링하여 고장시기를 예측하여 정비하는 방법으로 핵심 기계장치가 항상 최상의 작동 상태를 효율적으로 유지할 수 있도록 한다. 본 논문은 해양 환경에서 PdM의 적용성에 중점을 둔 해양 예지 정비(MPdM, Maritime Predictive Maintenance)에 대해 고안하였으며, 제시된 MPdM은 지리적 고립과 극한 해양 상황 등 해양 운송 산업의 특수한 환경을 고려하여 설계되었다. 본 논문은 선진 미래 해양 운송을 가능하게 하는 MPdM이라는 개념과 그 필요성을 제안한다.

최근 건설시장에 4차 산업혁명기술의 급속한 확산과 도입, 적용이 트랜드로 부각되고 있다. BIM 기술은 4차 산업혁명 기술의 근간을 이루는 다차원 정보체계이다. 이러한 정보기반체계를 활용한 하천분야도 유지관리를 위한 현행화 방안 등 적극적인 연구검토가 되고 있다. 최근 하천 전문가들의 하천분야 BIM도입 효과에 필요성을 반영하여 적극적인 연구와 현행화 작업을 해야 된다. 그리고 첨단기술을 반영한 시설물 유지관리 정보체계를 활성화하고 관리계획 수립 및 운영을 위해서는 다양한 정보체계를 구축하기 위한 도구 및 지원소프트웨어의 개발이 반드시 필요할 것으로 전망된다. 하천시설의 유지운영을 위한 연구로 기본적으로 기존 도면자료를 이용하여 3차원 정보모델을 구축하고 이를 활용한 손상을 점검하고 정보화하며 보수보강을 위한 자료로 활용토록 하는 것이다. 이는 기존 도면방식에 없는 정보체계를 하천시설물을 3D 모델링과 함께 유지관리정보를 속성으로 구축하는 방법을 연구하여 유지운영을 위한 점검, 손상 관리를 보다 효과적이고 활용성이 높은 관리방안을 제시하고자 하였다.

In the process of cutting large aircraft parts, the tool may be abnormally worn or damaged due to various factors such as mechanical vibration, disturbances such as chips, and physical properties of the workpiece, which may result in deterioration of the surface quality of the workpiece. Because workpieces used for large aircrafts parts are expensive and require strict processing quality, a maintenance plan is required to minimize the deterioration of the workpiece quality that can be caused by unexpected abnormalities of the tool and take maintenance measures at an earlier stage that does not adversely affect the machining. In this paper, we propose a method to indirectly monitor the tool condition that can affect the machining quality of large aircraft parts through real-time monitoring of the current signal applied to the spindle motor during machining by comparing whether the monitored current shows an abnormal pattern during actual machining by using this as a reference pattern. First, 30 types of tools are used for machining large aircraft parts, and three tools with relatively frequent breakages among these tools were selected as monitoring targets by reflecting the opinions of processing experts in the field. Second, when creating the CNC machining program, the M code, which is a CNC auxiliary function, is inserted at the starting and ending positions of the tool to be monitored using the editing tool, so that monitoring start and end times can be notified. Third, the monitoring program was run with the M code signal notified from the CNC controller by using the DAQ (Data Acquisition) device, and the machine learning algorithms for detecting abnormality of the current signal received in real time could be used to determine whether there was an abnormality. Fourth, through the implementation of the prototype system, the feasibility of the method proposed in this paper was shown and verified through an actual example.

Currently, there are two types of trainer in Korea : basic and advanced. Both models have been in operation for more than 10 years, and compared to the early stage of operation, reliability has gradually improved and failure rates have also entered a trend of stabilization. Therefore, it is necessary to extend the maintenance period considering economic feasibility. This study investigates the three maintenance period calculation methods: NAVAIR 00-25-403 [17], DOD, U.S. [4], CERL and US Army [3], with intention to extend the maintenance period of the trainer from current 200 hours to 400 hours. In addition, the maintenance period was calculated by the three methods with actual operational data. Common standards and procedures were established to apply operational data to the existing maintenance period calculation methods, the required reliability indicators were derived, and the maintenance periods was calculated based on the results, additionally, a review on the field applicability of the three maintenance cycles was conducted. An on-site interviews were conducted with the calculation results, and 11 out of the 15 items were expected to be extended by 400 hours. It was suggested that the remaining 4 items could be extended to 400 hours by supplementing the inspection method through additional analysis such as functional analysis, inspection content verification, and site connection.

Valves are widely used in various industrial fields, such as plants, vessels and shipbuilding. In particular, the performance of the valve is an important factor that can influence the performance of the entire system. Therefore, in this basic study to establish a national technical qualification in the domestic field of valve maintenance, demands for the fields of valves and major congruence were analyzed focusing on the industrial facility curriculum of Korea Polytechnics, and level-differentiated trial examinations were applied to relevant majors to standardize the developed valve tester. The trial examination result displayed that in the highest level of difficulty, in the medium level of difficulty and in the lowest level of difficulty, the pass rate was 0%, 17.86% and 39.29% respectively.

전 세계 90 %의 인구가 WHO의 연평균 미세먼지 노출 기준(10 ㎍/㎥)을 초과한 공기를 흡입하고 있다. 전 세계적으로 육상뿐 만 아니라 해양에서 발생하는 질소산화물에 대한 규제를 통해 2차 오염물질, 초미세먼지 저감에 대해 노력하고 있으며 국내에서는 선박에서 미세먼지 발생의 주요한 원인인 황 함유량 저감과 환경친화적 선박의 개발 및 보급 등을 통해 깨끗한 해양환경 조성을 위한 노력을 하고 있다. 디젤엔진 유해 배출가스 저감을 위한 기술 중 압력 손실이 적고 높은 집진 효율 및 NOx의 제거와 유지 관리의 장점이 많은 전기 집진기의 수요와 중요성이 증가하고 있다. 본 연구는 총톤수 999톤급 선박의 2,427 kW 선박용 디젤엔진의 미세먼지 저감을 목적으로 개발된 전기 집진기를 예지보전단계에서 고장모드영향분석을 통해 장비 품질을 높여 선박 내에서의 내구연한을 높이고자 위험 우선순위 도출하였다. 위험 우선순위는 고장모드 241(poor dust capture efficiency)이 RPN 180으로 가장 높았다. Collecting electrode 에서 가장 많은 고위험 고장모드를 검출하여 집중관리 부품으로 관리해야 할 필요가 있었으며 원인으로 진동과 핀 풀림으로 인한 유 격 불량이 가장 많이 검출되었다. 핀 풀림 역시 근본적으로는 선체 또는 장비에서 발생하는 진동이 원인이 되어 발생할 수 있는 사항이기 때문에 핀 풀림이 발생하는 개소에 보완이 필요하겠다.

PURPOSES : The aim of this study is to determine the maintenance costs for a reasonable preliminary feasibility study, feasibility study, or evaluation METHODS : This study was based on government budget execution and budget execution data for expressways, national highways, cable-supported bridges and long-tunnels. For the expressway, data obtained from the Korea Expressway Corporation were used. For the national highway, data was obtained from the Ministry of Land, Infrastructure and Transport. Similarly, data collected from expressway maintenance costs and the Korea Infrastructure Safety and Technology Corporation were used for long tunnels and cable-supported bridges, respectively. The items for highway maintenance cost were reclassified more rationally to facilitate the calculation of the maintenance costs. The replacement cycle for each item was also calculated based on the budget expenditure data. RESULTS : The results of this study showed the standard maintenance cost model for expressways, national highways, cable-supported bridges, and long-tunnels. In other words, a basis for predicting reasonable maintenance costs was prepared for a feasibility study. CONCLUSIONS : The reliability of the maintenance cost results was improved and it was more consistent with actual costs compared to the results of previous studies. It can be used as a basis for estimating the maintenance cost of a preliminary feasibility study and feasibility evaluation in the future.

Data on the crude protein requirements of elk doe are nonexistent and the data are essential for their management in Korea. Therefore, this study was conducted to evaluate the crude protein requirement for maintenance of elk doe. Three female elk deer were used in 3 × 3 Latin square design with three diets containing three levels of crude protein (CP) that contained low crude protein (approximately 12%), medium crude protein (15%), and high crude protein (18%). Each three elk doe trials included a 14-day preliminary period and a 5-day collection period. Crude protein intake was 4.83, 6.26, and 9.00 g/d for 12%, 15%, and 18% of CP level, respectively. Crude protein balances were 1.04, 1.41, and 4.14 for 12%, 15%, and 18% of CP level, respectively. The maintenance requirement for CP from the regression equation between CP intake and CP balance were 3.70 g/BW0.75.

This paper investigates the stress-reducing preventive maintenance model through numerical experiments. The preventive maintenance model is used to analyze the relationship between related conditions and variables to gain insight into the efficient operation of the system when performing preventive maintenance in real-world situations. Various preventive maintenance models have been developed over the past decades and their complexity has increased in recent years. Increasing complexity is essential to reflect reality, but recent models can only be interpreted through numerical experiments. The stress-reducing preventive maintenance is a newly introduced preventive maintenance concept and can only be interpreted numerically due to its complexity, and has received little attention because the concept is unfamiliar. Therefore, for information purposes, this paper investigates the characteristics of the stress-reducing preventive maintenance and the relationship between parameters and variables through numerical experiments. In particular, this paper is focusing on the economic feasibility of stress-reducing preventive maintenance by observing changes in the optimal preventive maintenance period in response to changes in environmental stress and the improvement factor. As a result, when either the environmental stress or the improve effect of stress-reducing preventive maintenance is low, it is not necessary to carry out the stress-reducing preventive maintenance at excessive cost. In addition, it was found that the age reduction model is more economical than the failure rate reduction model.