해군 시스템의 디지털 트윈을 활용한 수리부속 예측

최진우¹ ; 장정민²^{, *} ; 박성호³

1해군소령/해군 전력분석시험평가단 체계분석처 군수운영분석담당
2해군소령/해군본부 군수참모부 기뢰전함/지원함담당
3해군소령/해군본부 정보작전참모부 작전계획담당

Spare Parts Prediction Using Digital Twins of Naval Systems

Jin-woo Choi¹ ; Jeong-Min Jang²^{, *} ; Sung-Ho Park³

1LCDR, Manager of Logistics Operation Analysis, Force Analysis Test & Evaluation Group, ROK Navy
2LCDR, Manager of the Mine Warfare ship/Support ship, Logistics Staff Office, ROK Navy HQ
3LCDR, Manager of Operation Planning, Information and Operation Staff Office, ROK Navy HQ

Correspondence to: ^*Jeong-Min Jang Fax: +82-504-371-1882 E-mail: jjwjdals@naver.com

초록

본 연구에서는 해군 시스템의 디지털 트윈 모델의 구축 방법을 설명하고 이를 활용하여 수리부속 수요를 예측한다. 모델의 성능은 대한민국 해군이 활용중인 OASIS 모델의 핵심 알고리즘인 VARI-METRIC과 비교한다. 디지털 트윈 모델은 총수명간 수리부속 예측, 누적 재고량의 변화, CSP 예측 분야에서 모두 VARI-METRIC보다 우수하였다. 디지털 트윈 모델은 광범위한 확장성을 가진다는 측면에서 지속적인 연구가 필요하다.

Abstract

In this study, a method for constructing a digital twin model of a naval system is explained and used to predict demand for spare parts. The performance of the model is compared with VARI-METRIC, a key algorithm of the OASIS model used by the Republic of Korea Navy. The digital twin model was superior to VARI-METRIC in all areas of predicting spare parts over the lifespan, change in cumulative inventory, and predicting CSP. The digital twin model requires continuous research in terms of its extensive scalability.

Keywords:

Digital Twin, Spare Part, Demand Prediction, Total Life Cycle

키워드:

디지털 트윈, 수리부속, 수요예측, 총 수명주기

References

Choi. J. W., 2022, Failure Function Based Intermediate Level Maintenance System for Naval Battleships. Korean National Defense University, Doctoral dissertation, pp. 1-185.
Slay, F.M. et al., 1996, Optimizing Spares Support: The Aircraft Sustainability Model. Technical Report AF501MR1, Logistics Management Institute, Washington D.C., 1996.
Choi, J. W., & Moon, S. A., 2022, Rare Event Simulation by Combining Trend and Probability: An Application to Naval Ship Critical Failures. Industrial Engineering & Management Systems, Vol. 21, No. 1, pp. 128-136. [https://doi.org/10.7232/iems.2022.21.1.128]
Moon, H. J., & Choi, J. W., 2021, Hierarchical spline for time series prediction: An application to naval ship engine failure rate. Applied AI Letters, Vol. 2, No. 1, e22. [https://doi.org/10.1002/ail2.22]