DOI QR코드

DOI QR Code

A Study on Intermittent Demand Forecasting of Patriot Spare Parts Using Data Mining

데이터 마이닝을 이용한 패트리어트 수리부속의 간헐적 수요 예측에 관한 연구

  • Park, Cheonkyu (2nd Air Defense Missile Brigade, Airforce) ;
  • Ma, Jungmok (Department of Defense Science, Korea National Defense University)
  • 박천규 (공군 제2방공유도탄여단) ;
  • 마정목 (국방대학교 국방과학학과)
  • Received : 2020.12.11
  • Accepted : 2021.03.05
  • Published : 2021.03.31

Abstract

By recognizing the importance of demand forecasting, the military is conducting many studies to improve the prediction accuracy for repair parts. Demand forecasting for repair parts is becoming a very important factor in budgeting and equipment availability. On the other hand, the demand for intermittent repair parts that have not constant sizes and intervals with the time series model currently used in the military is difficult to predict. This paper proposes a method to improve the prediction accuracy for intermittent repair parts of the Patriot. The authors collected intermittent repair parts data by classifying the demand types of 701 repair parts from 2013 to 2019. The temperature and operating time identified as external factors that can affect the failure were selected as input variables. The prediction accuracy was measured using both time series models and data mining models. As a result, the prediction accuracy of the data mining models was higher than that of the time series models, and the multilayer perceptron model showed the best performance.

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.

Keywords

References

  1. Defense Agency for Technology and Quality(DTaQ), Defense Science and Technology Glossary[Internet], DTaQ, c2017 [cited 2017], Available From: http://dtims.dtaq.re.kr:8070/search/detail/term.do?tmnl_id=T0007321 (accessed Oct. 25 2020)
  2. Y. J. Lee, Ministry of Defense "Reduce 12.9 billion won by increasing the accuracy of demand forecasting" [Internet], Yunhapnews, c2017 [cited 2017 Nov. 24], Available From: https://www.yna.co.kr/view/AKR20171124043200014?input=1195m (accessed Oct. 25, 2020)
  3. S. H. Kang, Patriot battery shuts down for 132 days[Internet], Newsis, c2013 [cited 2013 Oct. 14], Available From: https://newsis.com/ar_detail/view.html?ar_id=NISX20131014_0012431822&cID=10301&pID=10300 (accessed Oct. 25, 2020)
  4. Airforce Headquarters, Maintenance of Repair parts, p.69, Airforce Headquarters, 2019, pp.12.
  5. Airforce Logistics Command, '17 Research Results of Demand Forecasting Improvement Techniques, p.25, Airforce Logistics Command, 2017, pp.12.
  6. H. T. Kim, S. H. Kim, "Data mining based army repair parts demand forecast", Journal of the Korean Data & Information Science Society, Vol.30, No.2, pp.429-444, March 2019. DOI: https://doi.org/10.7465/jkdi.2019.30.2.429
  7. J. D. Kim, H. J. Lee "A Study on Forecasting Spare Parts Demand based on Data-Mining", Journal of the Internet Computing and Services, Vol.18, No.1, pp.121-129, February 2017. DOI: https://doi.org/10.74726/jksii.2017.18.1.121
  8. J. S. Kim, J. S. Hwang, J. W. Jung "A New LSTM Method Using Data Decomposition of Time Series for Forecasting the Demand of Aircraft Spare Parts", Korean Management Science Review, Vol.37, No.2, pp.1-18, June 2020. DOI: https://doi.org/10.7737/KMSR.2020.37.2.001
  9. J. D. Croston, "Forecasting and Stock Control for Intermittent Demands", Operational Research Quarterly, Vol.23, pp.289-303, September 1972. DOI: https://doi.org/10.1057/jors.1972.50
  10. D. W. Choi, A Data Mining Approach for Forecasting the Demand of Accidental Automobile Spare Parts with External Factors, Master's thesis, Yonsei University of Information Industrial Engineering, Seoul, Korea, pp.5-8, 2013.
  11. M. K. Park, J. G. Baek, "Demand Forecast of Spare Parts for Low Consumption with Unclear Pattern", Journal of the KIMST, Vol.21, No.4, pp.529-540, August 2018. DOI: https://doi.org/10.9766/KIMST.2018.21.4.529
  12. B. H. Oh, A study on weapon system spare parts intermittent demand forecasting using deep learning, Master's thesis, Korea University of Information and Communication, Seoul, Korea, pp.2-10, 2017.
  13. T. G. Kim, J. M. Ma "A Data Mining Approach for Intermittent Demand Forecasting of Aircraft Spare Parts - Focusing on the E-737(AEW&C: Airborne Early Warning & Control) Spare Parts -", Journal of the AMSOK, Vol.16, No.4, pp.155-164, August 2018. DOI: https://doi.org/10.30529/amsok.2018.16.4.008
  14. A. Ghobbar, C. Friend, "Evaluation of forecasting methods for intermittent parts demand in the field of aviation: a predictive model", Computer and Operation Research, Vol.30, No.1, pp.2097-2114, December 2003. DOI: https://doi.org/10.1016/S0305-0548(02)00125-9
  15. Airforce Air Defence Missile Command, '15 Operational equipment defect analysis and management measures, p.19, Airforce Air Defence Missile Command, 2015, pp.10-14.
  16. Galit Shmueli, Nitin R. Patel, Peter C. Bruce, Data Mining for Business Intelligence, p.455, E&B PLUS, 2012, pp.23-24, 265-272.