• Industrial Engineering and Management Systems
• /
• 제2권1호
• /
• pp.63-70
• /
• 2003

In this study, we employed an arithmetic process (AP) approach to resolve gearbox maintenance problems. The approach is realistic and direct in modelling the characteristics of a deteriorating system such as a gearbox since a decreasing AP can model a gearbox's successive operating times and an increasing AP can model the corresponding consecutive repair times. First of all, two test statistics were used to check whether the process is arithmetic or not. Next, model parameters of the AP were estimated using the simple linear regression method. Finally, the optimal replacement policy based on minimising the long-run average cost per day was determined for each type of gearbox.

• 한국국방경영분석학회지
• /
• 제16권1호
• /
• pp.142-150
• /
• 1990

This paper combines research in the areas of replacement and machine interference. Although over the past three decades there has been a great deal of research in the area of optimal replacement for stochastically deteriorating equipment and research dealing with machine interference problems : there has been a lack of research when these two areas are combined. However, the melding of these two well-known areas yields a very practical problem which demands theoretical investigation. In this paper we derive the steady state probabilities with a control limit policy for a two-machine one repairman problem. The control policy is a simple age dependent control described by the control limit, $t^{*}$. Once $t^{*}$ is fixed, the steady state probabilites that one, two, and no machines are working will be obtained.

• 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.

• 한국측량학회지
• /
• 제31권1호
• /
• pp.79-87
• /
• 2013

본 연구는 대체비용법을 이용하여 수치지형도 갱신사업의 편익을 분석하는 방법을 제안하였다. 대체비용법은 분석하고자 하는 사업의 기능을 기존 시장의 재화 또는 서비스의 기능으로 대체하는데 필요한 최소 비용으로 해당 사업의 편익을 측정하는 방법이다. 따라서 도시군관리계획수립과 같은 지방자치단체의 18개 행정 업무에서 1/5,000 수치지형도의 갱신에 관한 요구를 조사한 후 이들 요구를 현황측량 및 현장조사 용역으로 대체하기 위한 비용 모형을 건설분야 표준품셈과 GIS 기업을 대상으로 수행된 설문 결과를 이용하여 수립하였다. 그 결과 조사대상 지방차지단체에서 갱신사업의 연간 편익은 265,960,999원으로 측정되었다. 또한 0.5년에서 4년까지 갱신주기를 변화하면서 비용편익비를 분석하여 최적 갱신주기를 탐색하였다.

• 한국터널지하공간학회 논문집
• /
• 제22권5호
• /
• pp.575-589
• /
• 2020

최근 국내 터널에서 지속적으로 증가하고 있는 쉴드 TBM 공법의 주된 굴착도구는 디스크 커터로 굴진과정에서 자연스럽게 마모가 발생하고 이는 TBM의 굴진효능을 현저히 저하시키기 때문에 적절한 시기에 교체하는 것이 중요하다. 따라서 본 연구에서는 디스크 커터 교체 여부를 판단할 수 있는 예측 모델을 머신러닝 기법을 사용한 방법으로 제안하였다. 이를 위해 국내 기 시공된 쉴드 TBM 현장의 데이터 중 디스크 커터 소모에 상관성이 높은 굴진데이터(TBM 기계데이터, 지반정보 등)와 교체이력을 입력데이터로 사용하여 다양한 머신러닝 분류기법 중 서포트 벡터 머신, 최근접이웃 알고리즘, 의사결정트리 알고리즘을 사용하여 최적의 예측 모델을 구축하고 모델의 성능을 평가하기 위하여 분류성능평가 지표로 비교 분석하였다.

• 품질경영학회지
• /
• 제52권1호
• /
• pp.43-56
• /
• 2024

Purpose: The injection molding process, crucial for plastic shaping, encounters difficulties in sustaining product quality when replacing injection machines. Variations in machine types and outputs between different production lines or factories increase the risk of quality deterioration. In response, the study aims to develop a system that optimally adjusts conditions during the replacement of injection machines linked to molds. Methods: Utilizing a dataset of 12 injection process variables and 52 corresponding sensor variables, a predictive model is crafted using Decision Tree, Random Forest, and XGBoost. Model evaluation is conducted using an 80% training data and a 20% test data split. The dependent variable, classified into five characteristics based on temperature and pressure, guides the prediction model. Bayesian optimization, integrated into the selected model, determines optimal values for process variables during the replacement of injection machines. The iterative convergence of sensor prediction values to the optimum range is visually confirmed, aligning them with the target range. Experimental results validate the proposed approach. Results: Post-experiment analysis indicates the superiority of the XGBoost model across all five characteristics, achieving a combined high performance of 0.81 and a Mean Absolute Error (MAE) of 0.77. The study introduces a method for optimizing initial conditions in the injection process during machine replacement, utilizing Bayesian optimization. This streamlined approach reduces both time and costs, thereby enhancing process efficiency. Conclusion: This research contributes practical insights to the optimization literature, offering valuable guidance for industries seeking streamlined and cost-effective methods for machine replacement in injection molding.

• 전기학회논문지
• /
• 제62권11호
• /
• pp.1511-1519
• /
• 2013

This paper proposes the allocation method for capacitor-reactor banks in a distribution system with dispersed generators to reduce the installation costs, the maintenance costs and minimize the loss of electrical energy. The expected lifetime and maintenance period of devices with moving parts depends on the total number of operations, which affects the replacement and maintenance period for aging equipment under a limited budget. In this paper, the expected device lifetimes and the maintenance period are included in the formulation, and the optimal operation status of the devices is determined using a genetic algorithm. The optimal numbers and locations for capacitor-reactor banks are determined based on the optimal operation status. Simulation results in a 69-bus distribution system with the dispersed generator show that the proposed technique performs better than conventional methods.

• 한국산업융합학회 논문집
• /
• 제24권5호
• /
• pp.581-587
• /
• 2021

In recent years, contamination of drinking water sources has emerged as a serious social problem, such as a large number of impurities in tap water or groundwater or the supply of suitable water due to rust of pipes. Although the government and public institutions are implementing various measures to protect water sources, they cannot improve water quality in a short period of time because of the enormous cost involved. Therefore, in recent years, preference has been given to a device that converts tap water, which is hard water, into soft water by installing a separate water softener at the faucet from which tap water is discharged. However, the existing filtration device has a problem that filtration performance is gradually lowered when impurities accumulate in the filter, requiring continuous filter replacement. In this study, the optimal design of the filter housing was performed to develop a water softener that can be washed when impurities accumulate on the filter inside the water softener connected to the faucet. For optimal design of the filter housing, fluid and fluid-structural interaction analysis were performed on the design pressure to determine the shape and thickness of the housing, and design review was performed through prototype.

• International Journal of Quality Innovation
• /
• 제7권3호
• /
• pp.15-23
• /
• 2006

A spare ordering policy is considered for planned maintenance. Introducing the ordering, uptime, downtime, inventory costs and salvage value, we derive the expected cost effectiveness. The problem is to determine jointly the ordering time for a spare and the preventive replacement time for the operating unit which maximize the expected cost effectiveness. Some properties regarding the optimal policy are derived, and a numerical example is included to explain the proposed model.

• 품질경영학회지
• /
• 제20권1호
• /
• pp.39-47
• /
• 1992

This paper is concerned with cost analysis and determination of warranty period in a stepdown warranty policy. Manufacturer's warranty cost is analyzed for nonrepairable item, where the warranty is assumed to be renewed at any failure within the warranty period. It is shown that from this result in free replacement policy, pro-rata policy and hybrid policy can be easily calculated. The method of determining optimal warranty period is also explored.