Journal of the Korean Society for Aviation and Aeronautics (한국항공운항학회지)

The Korean Society for Aviation and Aeronautics (한국항공운항학회)
권호 표지
DOI QR코드

DOI QR Code

An Empirical Study on Aircraft Repair Parts Prediction Model Using Machine Learning

머신러닝을 이용한 항공기 수리부속 예측 모델의 실증적 연구

  • 이창호 (한서대학교 항공운항관리학과) ;
  • 김웅이 (한서대학교 항공정보산업대학원) ;
  • 최연철 (한서대학교 항공교통물류학과)
  • Received : 2018.12.12
  • Accepted : 2018.12.26
  • Published : 2018.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

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.

Keywords

HHOHB8_2018_v26n4_101_f0001.png 이미지

Fig 1. US Air Force RFM operating concept

HHOHB8_2018_v26n4_101_f0002.png 이미지

Fig 2. Procedures for the development of the German air force prediction model

HHOHB8_2018_v26n4_101_f0003.png 이미지

Fig 3. Air Force requirement calculation process

HHOHB8_2018_v26n4_101_f0004.png 이미지

Fig 5. Comparing the demand accrual rate when applying machine learning

Table 1. Defense field repair parts demand forecasting technique

HHOHB8_2018_v26n4_101_t0001.png 이미지

Table 2. KIDA's machine learning forecast

HHOHB8_2018_v26n4_101_t0002.png 이미지

Fig 4. Input variable selection

HHOHB8_2018_v26n4_101_t0003.png 이미지

Table 3. Detailed list of input variables

HHOHB8_2018_v26n4_101_t0004.png 이미지

Table 4. Predicted demand items by applying 5 kinds of machine learning

HHOHB8_2018_v26n4_101_t0005.png 이미지

Table 5. Detailed rate of demand accrual when applying machine learning

HHOHB8_2018_v26n4_101_t0006.png 이미지

Table 6. Confusion Matrix on machine learning model forecasts

HHOHB8_2018_v26n4_101_t0007.png 이미지

Table 7. Confusion Matrix by variable group of k-NN model

HHOHB8_2018_v26n4_101_t0008.png 이미지

References

  1. Se-jong Choi, "A study on aviation MRO industries and growth strategy in korean MRO", Journal of the Aviation Management Society of Korea, 15(2), 2017, pp. 3-19
  2. Se-hun Park, "Improvement method of forecasting method of aircraft repair parts", 2007, Air Force University. pp. 25-34
  3. KIDA, "Development of repair parts demand forecasting model", 2014, pp. 10-20
  4. Jin-ung Kim, "Method of development to supply demand forecasting : Case of an appurtenance", Master Thesis, Chongnam National University, Daejeon. Feb 1998. pp. 9-21
  5. Gi-Duck Chang, Gun-Wook Jun, "Scientific direction of repair part requirement management", The Weekly Defense Review, Vol 918(02-47), KIDA, 2002
  6. Young-Jin Park, Gun-Wook Jun, "A demand forecasting for aircraft spare parts using ARMIA", Journal of the Military Operations Research Society of Korea, 2008, Vol 34(2), pp. 79-101
  7. Myoung-Rye Kim, "Research of the scheme for improving a repairing request estimating hitting ratio", Master Thesis, Gwangju University, Gwangju. Feb 2012. pp. 32-42
  8. Sung-Jong Joo, "Military unit inventory reduction plan", KIDA, 2002
  9. Sung-In Jo, "A study on systematization of fleet repair parts management method", Air Force Headquarters, 2010. pp. 45-56
  10. Mi-Sun Sun, Je-woong Woo, Hyeck-Soo Lee, "A study on the efficiency of the US Army repair", KIDA, 2010
  11. Gaudette, K., Blazer, D. and Alcorn, H. K. "Managing Air Forces depot consumables - The big picture", Air Force Journal of Logistics, Vol. XXVI, No. 4, 2002, P. 5
  12. Jae-Hyun Shin, "A study on the empirical effectiveness analysis for repair parts requirement calculation system improvement" PhD Thesis, Daejeon University, Daejeon, Aug 2016, pp. 16-22, 56-86
  13. KIDA, Major achievements and development directions, 2017