• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2013년도 추계 학술논문 발표대회
• /
• pp.240-241
• /
• 2013

The maintenance management in buildings has got more important by the increasing complexity of building sizes and use. Nowadays an expectation and a possibility of BIM technology become accepted as a new construction management method, therefore many studies and legal systems of it are being suggested actively. Although orders for BIM projects are supposed to be increasing, at present the BIM information accumulated from planning and design still doesn't have its continuity at the maintenance step after completion of construction in terms of LCC. Therefore according to bim information, we set a goal of developing apartment maintenance system which is able to maintain by user viewpoint.

• 한국신뢰성학회지:신뢰성응용연구
• /
• 제15권1호
• /
• pp.1-5
• /
• 2015

This note suggests three approaches to improve reliability in developing weapon systems. The high complexity of the weapon systems make it hard to analyze and predict of those reliability. Current situations of the reliability have been reviewed in terms of logistics support analysis (LSA), warranty policy, maintenance and development. Three suggestions are notified to improve the reliability considering the complexity of the weapon systems.

• 산업경영시스템학회지
• /
• 제41권2호
• /
• pp.24-31
• /
• 2018

As a system complexity increases and technology innovation progresses rapidly, leasing the equipment is considered as an important issue in many engineering areas. In practice, many engineering fields lease the equipment because it is an economical way to lease the equipment rather than to own the equipment. In addition, as the maintenance actions for the equipment are costly and need a specialist, the lessor is responsible for the maintenance actions in most leased contract. Hence, the lessor should establish the optimal maintenance strategy to minimize the maintenance cost. This paper proposes two periodic preventive maintenance policies for the leased equipment. The preventive maintenance action of policy 1 is performed with a periodic interval, in which their intervals are the same until the end of lease period. The other policy is to determine the periodic preventive maintenance interval minimizing total maintenance cost during the lease period. In addition, this paper presents two decision-making models to determine the preventive maintenance strategy for leased equipment based on the lessor's preference between the maintenance cost and the reliability at the end of lease period. The structural properties of the proposed decision-making model are investigated and algorithms to search the optimal maintenance policy that are satisfied by the lessor are provided. A numerical example is provided to illustrate the proposed model. The results show that a maintenance policy minimizing the maintenance cost is selected as a reasonable decision as the lease term becomes shorter. Moreover, the frequent preventive maintenance actions are performed when the minimal repair cost is higher than the preventive maintenance cost, resulting in higher maintenance cost.

• International journal of advanced smart convergence
• /
• 제12권3호
• /
• pp.221-232
• /
• 2023

Recently, due to the expansion of the logistics industry, demand for logistics automation equipment is increasing. The modern logistics industry is a high-tech industry that combines various technologies. In general, as various technologies are grafted, the complexity of the system increases, and the occurrence rate of defects and failures also increases. As such, it is time for a predictive maintenance model specialized for logistics automation equipment. In this paper, in order to secure the operational reliability of the ICT/Cold-Chain Unmanned Storage, a predictive maintenance system was implemented based on the LSTM model. In this paper, a server for data management, such as collection and monitoring, and an analysis server that notifies the monitoring server through data-based failure and defect analysis are separately distinguished. The predictive maintenance platform presented in this paper works by collecting data and receiving data based on RabbitMQ, loading data in an InMemory method using Redis, and managing snapshot data DB in real time. The predictive maintenance platform can contribute to securing reliability by identifying potential failures and defects that may occur in the operation of the ICT/Cold-Chain Unmanned Storage in the future.

• 한국정보처리학회논문지
• /
• 제2권3호
• /
• pp.314-323
• /
• 1995

최근 소프트웨어에 대한 사용자의 이해가 높아짐에 따라 소프트웨어 개발자는 사 용자의 요구를 만족시키기 위해 더 많은 노력을 하게 되었다. 따라서 소프트워어는 규 모가 방대해지고 복잡해졌다. 그로인해 소프트웨어의 개발 및 유지보수 비용은 증가 되었고 개발자의 대다수는 유지보수에 투입되어 새로운 소프트웨어의 개발에 적체현 상을 가져오게 되었다. 유지보수성이 좋은 소프트웨어는 하나의 모듈에 하나의 기능 을 가지며 읽기 쉽고 복잡하지 않은 구조를 가져야 한다. 본 논문에서는 소프트웨어의 복잡성을 효과적으로 관리하기 위해 소스프로그램을 입력으로 하여 프로덕트 메트릭스 를 측정하고 요인항목들의 값을 산출하는 시스템을 설계하고 구현하였다.

• Smart Structures and Systems
• /
• 제30권6호
• /
• pp.571-582
• /
• 2022

Optimal life-cycle management is a challenging issue for deteriorating regional bridges. Due to the complexity of regional bridge structural conditions and a large number of inspection and maintenance actions, decision-makers generally choose traditional passive management strategies. They are less efficiency and cost-effectiveness. This paper suggests a deep reinforcement learning framework employing double-deep Q-networks (DDQNs) to improve the life-cycle management of deteriorating regional bridges to tackle these problems. It could produce optimal maintenance plans considering restrictions to maximize maintenance cost-effectiveness to the greatest extent possible. DDQNs method could handle the problem of the overestimation of Q-values in the Nature DQNs. This study also identifies regional bridge deterioration characteristics and the consequence of scheduled maintenance from years of inspection data. To validate the proposed method, a case study containing hundreds of bridges is used to develop optimal life-cycle management strategies. The optimization solutions recommend fewer replacement actions and prefer preventative repair actions when bridges are damaged or are expected to be damaged. By employing the optimal life-cycle regional maintenance strategies, the conditions of bridges can be controlled to a good level. Compared to the nature DQNs, DDQNs offer an optimized scheme containing fewer low-condition bridges and a more costeffective life-cycle management plan.

• 한국국방경영분석학회지
• /
• 제37권1호
• /
• pp.147-159
• /
• 2011

Recently, the military service period has been shortened continuously. Meanwhile, more skilled airmen are needed as the complexity of weapon systems increase. This phenomenon could lead to a disastrous result such as deteriorating the level of the readiness and the fighting power. We suggest a method to improve recruit's maintenance capability rapidly by assigning airmen to jobs appropriate to their characteristics using Datamining methods (K-menas and CART). We focus on the assigning method for air force's air-munition maintenance airmen since they are requested more skilled than other airmen. Grouping airmen with k-means method and devising classification rule with CART algorithm, we found that airmen's proficiency arrival period could be shortened by 1.79 months when they are assigned in the suggested way.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제28권10호
• /
• pp.720-731
• /
• 2001

구조적 개발 방법론에 적용하도록 만들어진 복잡도 척도들을 클래스의 상속성, 다형성, 메시지 전달 그리고 캡슐화와 같은 객체지향의 개념에 직접적으로 적용할 수 없다. 또한 기존의 객체지향 소프트웨어에 대한 척도의 연구는 프로그램의 복잡도나, 설계 단계의 척도가 대부분이었다. 실제로 분석단계 클래스의 복잡도를 낮춤으로서 시스템의 개발 노력이나 비용 및 유지보수 단계에서의 노력이 크게 줄어들게 되므로, 분석 클래스에 대한 복잡도를 측량하기 위한 척도가 필요하다. 본 논문에서는 객체지향 개발방법론인 RUP(Rational Unified Process)의 분석 단계에서 추출되는 분석 클래스에 대해서 복잡도를 측정할 수 있는 새로운 척도를 제안한다. 협력 복잡도CC(Collaboration Complexity)는 가능한 협력의 최대 수로서 클래스가 잠재적으로 얼마나 복잡할 수 있는지를 측정하기 위한 척도이며, 각 협력자들의 인터페이스를 이해하는 것과 관련된 총체적 어려움을 측정하는 인터페이스 복잡도 IC(Interface Complexity)를 정의하였다. 제안된 척도는 Weyuker의 9가지 공리적 성질에 대하여 이론적인 검증을 하였으며, 텍스트 마이닝 기법을 사용하여 사용자의 질문에 자동으로 응답하는 시스템의 분석 클래스에 대하여 제안된 척도를 적용하여 복잡도를 측정하였다. 제안된 CC와 IC의 값과 Chidamber와 Kemerer가 제안된 CBO와 WMC의 값을 비교해 본 결과, 제안된 복잡도 척도의 계산결과 값이 큰 클래스의 경우에는 설계 이후 단계에서도 역시 복잡도가 커지게 되는 것을 알 수 있었다. 이로써 소프트웨어개발 주기의 초기에 클래스에 대한 복잡도를 평가해 보고, 나머지 단계에 필요한 시간과 노력을 예측함으로써 보다 비용-효과적인 객체지향 소프트웨어를 개발할 수 있는 가능성이 높아질 것으로 기대된다.

• 한국컴퓨터정보학회논문지
• /
• 제11권3호
• /
• pp.281-289
• /
• 2006

소프트웨어 개발환경이 웹 기반으로 급격히 전환되고 있으나 웹 소프트웨어 품질 측정 메트릭이나 추정 모델에 대한 연구는 매우 미흡한 실정이다. 본 연구는 웹 소프트웨어의 위험도가 객체 속성과 상관관계가 있는지 선형회귀 방법을 사용하여 분석하였고, 실무에서 사용되고 있는 중형이상의 6개 시스템을 대상으로 규모와 클래스 수(NOC), 규모와 메소드 수(NOM) 및 복잡도와 클래스 수(NOC), 복잡도와 메소드 수(NOM)에 관한 적정 모델을 제안하였다. 실험에 사용한 6 시스템 중 5 시스템(S06 제외)의 규모(LOC)와 NOM이 높은 관련성을 보였고 4 시스템(S04 & S06 제외)의 복잡도와 NOM, 복잡도와 NOC가 높은 관련성을 보였다. 여기서 웹 소프트웨어 구조를 이루는 서버, 클라이언트. HTML 세 요소 각각의 복잡도를 비교하였는데, 두 시스템(S04, S06)은 각 요소의 복잡도 차이가 비교적 높았으며 1시스템(S06)은 HTML 복잡도가 크게 치우쳐 있었다. 즉 위험도를 미리 추정하여 유지보수성을 향상시키기 위해서는 NOM으로 추정가능 하도록 세 요소의 복잡도를 균일하게 유지해야 함을 제시한다.

• 대한안전경영과학회지
• /
• 제25권4호
• /
• pp.141-151
• /
• 2023

Recently, due to the expansion of the logistics industry, demand for logistics automation equipment is increasing. The modern logistics industry is a high-tech industry that combines various technologies. In general, as various technologies are grafted, the complexity of the system increases, and the occurrence rate of defects and failures also increases. As such, it is time for a predictive maintenance model specialized for logistics automation equipment. In this paper, in order to secure the operational safety and reliability of the parcel loading system, a predictive maintenance platform was implemented based on the Naive Bayes-LSTM(Long Short Term Memory) model. The predictive maintenance platform presented in this paper works by collecting data and receiving data based on a RabbitMQ, loading data in an InMemory method using a Redis, and managing snapshot DB in real time. Also, in this paper, as a verification of the Naive Bayes-LSTM predictive maintenance platform, the function of measuring the time for data collection/storage/processing and determining outliers/normal values was confirmed. The predictive maintenance platform can contribute to securing reliability and safety by identifying potential failures and defects that may occur in the operation of the parcel loading system in the future.