• 한국정보시스템학회지:정보시스템연구
• /
• 제31권3호
• /
• pp.197-220
• /
• 2022

Purpose The purpose of this study is to identifies the demand pattern categorization of repair parts of Automotive After-sales Service(A/S) and proposes a demand prediction model for Auto repair parts using Long Short-Term Memory (LSTM) of artificial neural networks (ANN). The optimal parts inventory quantity prediction model is implemented by applying daily, weekly, and monthly the parts demand data to the LSTM model for the Lumpy demand which is irregularly in a specific period among repair parts of the Automotive A/S service. Design/methodology/approach This study classified the four demand pattern categorization with 2 years demand time-series data of repair parts according to the Average demand interval(ADI) and coefficient of variation (CV²) of demand size. Of the 16,295 parts in the A/S service shop studied, 96.5% had a Lumpy demand pattern that large quantities occurred at a specific period. lumpy demand pattern's repair parts in the last three years is predicted by applying them to the LSTM for daily, weekly, and monthly time-series data. as the model prediction performance evaluation index, MAPE, RMSE, and RMSLE that can measure the error between the predicted value and the actual value were used. Findings As a result of this study, Daily time-series data were excellently predicted as indicators with the lowest MAPE, RMSE, and RMSLE values, followed by Weekly and Monthly time-series data. This is due to the decrease in training data for Weekly and Monthly. even if the demand period is extended to get the training data, the prediction performance is still low due to the discontinuation of current vehicle models and the use of alternative parts that they are contributed to no more demand. Therefore, sufficient training data is important, but the selection of the prediction demand period is also a critical factor.

• 한국국방경영분석학회지
• /
• 제30권2호
• /
• pp.96-107
• /
• 2004

This paper deals with $\ulcorner$Requirement Decision Model for Repair Parts supplied by the Government$\lrcorner$ which is to reduce Aircraft Contract Maintenance Cost. It aims to find solutions to the fundamental problems of the Aircraft Contract Maintenance System. Under the current Aircraft Contract Maintenance System, it is hard to forecast the exact demand of repair parts, so support rate of Repair Parts supplied by the Government is restricted under 50 percent. It is inevitable to purchase Repair Parts from the firm with much higher price than those of Government source. However, absence of fixed demand pattern makes it difficult to improve accuracy of demand forecast. As a solution to these problems, this model prevents a cost increase due to the unit price difference between Repair Parts supplied by the Government and Repair Parts purchased by the Firm. It also reflects demand characteristics of each repair part, and prevents continual stock increase by setting an upper limit on the amount of Repair Parts supplied by the Government. The effectiveness of this model is verified by empirical analysis using the latest raw data. By applying this model to real situation, we expect to reduce about 4 billion won every year.

• 한국산학기술학회논문지
• /
• 제22권3호
• /
• pp.234-241
• /
• 2021

군에서는 수요예측에 대한 중요성을 인식하여 수리부속에 대해 예측 정확도 향상을 위한 많은 연구가 이루어지고 있다. 수리부속 수요예측은 예산 운영과 장비 가동률 측면에서 매우 중요한 요소가 되고 있다. 그러나 현재 군에서 적용중인 시계열 모형으로는 수요량의 변동과 발생주기가 일정하지 않은 간헐적 수요에 대해서는 예측에 한계가 있는 실정이다. 따라서, 본 연구는 공군 패트리어트 수리부속의 간헐적 수요에 대한 예측 정확도를 제고하는 방법을 제시하고자 하였다. 이를 위해서 2013년부터 2019년까지의 701개의 수리부속 소모개수를 토대로 수요 유형을 구분하여 수리부속의 간헐적 수요 자료를 수집하였다. 또한, 장비 고장에 영향을 줄 수 있는 외부 요인으로는 기온, 장비운영시간을 식별하여 입력변수로 선정하였다. 그 후, 소모개수와 외부 요인을 통해 군에서 적용하는 시계열 모형과 제안하는 데이터 마이닝 모형으로 예측을 실시하여 모형별 예측 정확도를 판단했다. 예측 결과로 기존의 시계열 모형과 비교하여 데이터 마이닝 모형의 예측 정확도가 높았으며, 그 중 다층 퍼셉트론 모형이 가장 우수한 성능을 보였다.

• 한국국방경영분석학회지
• /
• 제4권1호
• /
• pp.57-68
• /
• 1978

In forecasting the demand rate of repair parts for old tank types under the limited historical data, this reportan alyzes which techniques give the smallest forecasting error, also economic repair limits and the return for additional repair costs are formulated as a mathematical model

• 한국항공운항학회지
• /
• 제26권4호
• /
• pp.101-109
• /
• 2018

In order to predict the future needs of the aircraft repair parts, each military group develops and applies various techniques to their characteristics. However, the aircraft and the equipped weapon systems are becoming increasingly advanced, and there is a problem in improving the hit rate by applying the existing demand prediction technique due to the change of the aircraft condition according to the long term operation of the aircraft. In this study, we propose a new prediction model based on the conventional time-series analysis technique to improve the prediction accuracy of aircraft repair parts by using machine learning model. And we show the most effective predictive method by demonstrating the change of hit rate based on actual data.

• 시스템엔지니어링학술지
• /
• 제13권1호
• /
• pp.79-88
• /
• 2017

For the PBL contract, it is necessary for the contracting parties to share information regarding the reasonable inventory-level and the cost of its repair parts for the estimated demand. There are various models which can be used for this purpose. Among them, V-METRIC model is considered to be the most efficient and is most frequently applied. However, this model is usually used for optimizing the inventory level of the repair parts of the system under operation. The model uses a time series forecast model to determine the demand rate, which is a mandatory input factor for the model, based on past field data. However, since the system at the deployment stage has no operational performance record, it is necessary to find another alternative to be used as the demand rate of the model application. This research applies the V-METRIC model to find the optimal inventory level and cost estimation for repairable items to meet the target operational availability, which is a key performance indicator, at the time of the PBL contract for the deployment system. This study uses the calculated value based on the allocated MTBF to the system as the demand rate, which is used as input data for the model. Also, we would like to examine changes in inventory level and cost according to the changes in target operational availability and MTBF allocation.

• 산업경영시스템학회지
• /
• 제38권1호
• /
• pp.110-117
• /
• 2015

Spare part management is very important to products that have large number of parts and long lifecycle such as automobile and aircraft. Supply chain must support immediate procurement for repair. However, it is not easy to handle spare parts efficiently due to huge stock keeping units. Qualified forecasting is the basis for the supply chain to achieve the goal. In this paper, we propose an agent based modeling approach that can deal with various factors simultaneously without mathematical modeling. Simulation results show that the proposed method is reasonable to describe demand generation process, and consequently, to forecast demand of spare parts in long-term perspective.

• 한국기계가공학회지
• /
• 제20권9호
• /
• pp.1-10
• /
• 2021

Recently, the repair and recycling of damaged mechanical parts via metal additive manufacturing processes have been industrial points of interest. This is because the repair and recycling of damaged mechanical parts can reduce energy and resource consumption. The directed energy deposition(DED) process has various advantages such as the possibility of selective deposition, large building space, and a small heat-affected zone. Hence, it is a suitable process for repairing damaged mechanical parts. The shaft is a core component of various mechanical systems. Although there is a high demand for the repair of the shaft, it is difficult to repair with traditional welding processes because of the thermal deformation problem. The objective of this study is to propose a repair procedure for a damaged shaft using the DED process and discuss its applications. Three types of cases, including a small shaft with a damaged surface, a medium-size shaft with a worn bearing joint, and a large shaft with serious damage, were repaired using the proposed procedure. The microstructure and hardness were examined to discuss the characteristics of the repaired component. The efficiency of the repair of the damaged shaft is also discussed.

• Journal of Computational Design and Engineering
• /
• 제3권1호
• /
• pp.53-62
• /
• 2016

The current trends of product customization and repair of high value parts with individual defects demand automation and a high degree of flexibility of the involved manufacturing process chains. To determine the corresponding requirements this paper gives an overview of manufacturing process chains by distinguishing between horizontal and vertical process chains. The established way of modeling and programming processes with CAx systems and existing approaches is shown. Furthermore, the different types of possible adaptions of a manufacturing process chain are shown and considered as a cascaded control loop. Following this it is discussed which key requirements of repair process chains are unresolved by existing approaches. To overcome the deficits this paper introduces repair features which comprise the idea of geometric features and defines analytical auxiliary geometries based on the measurement input data. This meets challenges normally caused by working directly on reconstructed geometries in the form of triangulated surfaces which are prone to artifacts. Embedded into function blocks, this allows the use of traditional approaches for manufacturing process chains to be applied to adaptive repair process chains.

• 한국경제지리학회지
• /
• 제22권2호
• /
• pp.160-177
• /
• 2019

본 논문은 광치 도요타사를 사례로 한 일본계 자동차 메이커의 중국 시장 딜러 분포와 수리 및 보수용 부품의 관리 체제에 대해 검토한다. 조사 방법으로, 광치 도요타사의 어느 딜러를 통하여, 딜러의 전국적인 분포 상황과 부품물류창고의 입지 상황, 수리 및 보수용 부품의 재고 상황과 배송 시스템 등에 대한 정보를 입수했다. 조사 결과로, 당사는 전국에 437개 점포에 딜러가 있으나, 인구비율 등을 고려하면 점포의 분포가 해안 지역에 치우치고 있으며, 근년 자동차의 수요가 높아지고 있는 내륙 지역 진출이 늦어지고 있다. 한편으로, 지역별 GDP 총액과 점포 수 사이에 높은 상관관계가 있으며, 당사에서는 비교적 경제규모가 작은 내륙 지역의 소비자를 대상으로 한 저가격의 차종을 판매하는 것보다, 경제규모가 큰 해안 지역의 대도시에서 고가의 자동차를 판매하는 것을 중요시하고 있다. 그리고 당사의 점포수가 확대되지 않는 요인으로써, 당사가 중요시하는 충분한 사후 서비스를 운영하는 딜러를 확보하는 것이 어렵다는 점이 꼽힌다. 당사에서는 딜러에게 수리 및 보수용 부품 중, 최저 1,500점 이상의 재고를 확보하도록 하는 방침을 살피고 있다. 또한 보수용 부품을 교환할 경우, 고객에게 충분한 설명을 하는 것과 동의를 얻는 것으로 하여금 고객 만족도를 높이는 것을 딜러에게 요청하고 있다. 그렇기 때문에, 당사의 딜러에게 장기적인 시점으로 사업을 계속할 수 있는 자금력이 필요로 하지만, 이러한 딜러가 한정적인 점과 메이커와 딜러 사이의 이익 배분이 어려운 점이 지적된다.