산업경영시스템학회지 (Journal of Korean Society of Industrial and Systems Engineering)

  • 제47권2호
  • /
  • Pages.30-39
  • /
  • 2024
  • /
  • 2005-0461(pISSN)
  • /
  • 2287-7975(eISSN)
한국산업경영시스템학회 (Society of Korea Industrial and System Engineering)
권호 표지
DOI QR코드

DOI QR Code

생산 및 제조 단계의 검사 데이터를 이용한 유도탄 탐색기의 고장 분류 연구

Study on Failure Classification of Missile Seekers Using Inspection Data from Production and Manufacturing Phases

  • 정예은 (경기대학교 일반대학원 산업시스템공학과) ;
  • 김기현 (경기대학교 일반대학원 산업시스템공학과) ;
  • 김성목 (경기대학교 일반대학원 산업시스템공학과) ;
  • 이연호 (LIG넥스원 PGM IPS연구소) ;
  • 김지원 (LIG넥스원 PGM IPS연구소) ;
  • 용화영 (LIG넥스원 PGM IPS연구소) ;
  • 정재우 (LIG넥스원 PGM IPS연구소) ;
  • 박정원 (경기대학교 산업시스템공학과) ;
  • 김용수 (경기대학교 산업시스템공학과)
  • Ye-Eun Jeong (Department of Industrial & Systems Engineering, Kyonggi University Graduate School) ;
  • Kihyun Kim (Department of Industrial & Systems Engineering, Kyonggi University Graduate School) ;
  • Seong-Mok Kim (Department of Industrial & Systems Engineering, Kyonggi University Graduate School) ;
  • Youn-Ho Lee (PGM Integrated Product Support R&D, LIG Nex1) ;
  • Ji-Won Kim (PGM Integrated Product Support R&D, LIG Nex1) ;
  • Hwa-Young Yong (PGM Integrated Product Support R&D, LIG Nex1) ;
  • Jae-Woo Jung (PGM Integrated Product Support R&D, LIG Nex1) ;
  • Jung-Won Park (Department of Industrial & Systems Engineering, Kyonggi University) ;
  • Yong Soo Kim (Department of Industrial & Systems Engineering, Kyonggi University)
  • 투고 : 2024.03.11
  • 심사 : 2024.04.11
  • 발행 : 2024.06.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

This study introduces a novel approach for identifying potential failure risks in missile manufacturing by leveraging Quality Inspection Management (QIM) data to address the challenges presented by a dataset comprising 666 variables and data imbalances. The utilization of the SMOTE for data augmentation and Lasso Regression for dimensionality reduction, followed by the application of a Random Forest model, results in a 99.40% accuracy rate in classifying missiles with a high likelihood of failure. Such measures enable the preemptive identification of missiles at a heightened risk of failure, thereby mitigating the risk of field failures and enhancing missile life. The integration of Lasso Regression and Random Forest is employed to pinpoint critical variables and test items that significantly impact failure, with a particular emphasis on variables related to performance and connection resistance. Moreover, the research highlights the potential for broadening the scope of data-driven decision-making within quality control systems, including the refinement of maintenance strategies and the adjustment of control limits for essential test items.

키워드

과제정보

이 논문은 2022년 정부(방위사업청)의 재원으로 국방기술진흥연구소의 지원을 받아 수행된 연구임(KRIT-CT-22-081, 무기체계 CBM+ 특화연구센터).

참고문헌

  1. Breiman, L., Random Forests, Machine Learning, 2001, Vol. 45, No. 1, pp. 5-32. https://doi.org/10.1023/A:1010933404324
  2. Chae, S.G., Kim, G.R., Bae, A.-Y., and Bae, S.J., Failure Diagnosis and Prediction for a Thermal Power Plant Generator using fastICA, Journal of Applied Reliability, 2021, Vol. 21, No. 4, pp. 341-351. https://doi.org/10.33162/JAR.2021.12.21.4.341
  3. Chawla, N.V., Bowyer, K.W., Hall, L.O. and Kegelmeyer, W. P., SMOTE: synthetic minority over-sam-pling technique, JAIR, 2002, Vol. 16, pp. 321-357. https://doi.org/10.1613/jair.953
  4. Chen, T. and Guestrin, C., XGBoost: A scalable tree boosting system, in Proc. of 22nd ACM SIGKDD Int. Conf. on Knowl. Discovery and Data Mining, Aug. 2016, pp. 785-794.
  5. Choi, E.-J., Han, J.-H., and Hong, S.-K., Performance Improvement of Transfer Learning-based Motor Fault Diagnosis Using Mix-up Data Considering Data Imbalance, KIEE, 2023, Vol. 72, No. 2, pp. 255-262. https://doi.org/10.5370/KIEE.2023.72.2.255
  6. Donoho, D.L., High-dimensional Data Analysis: The Curses and Blessings of Dimensionality, AMS Conference on Math Challenges of the 21st Century, 2000 pp. 1-32.
  7. Fleeman, E.L., Tactical Missile Design, American Institute of Aeronautics and Astronautics Reston, 2nd Ed., 2006.
  8. Friedman, J.H., Greedy function approximation: A gradient boosting machine, Ann. of Statist., 2001, Vol. 29, No. 5, pp. 1189-1232. https://doi.org/10.1214/aos/1013203451
  9. Haixiang, G., Yijing, L., Shang, J., Mingyun, G., Yuanyue, H., and Bing, G., Learningfromclass-imbalanceddata: Reviewof methodsand applications, Expert systems with applications, 2017, Vol. 73, No. 1, pp. 220-239. https://doi.org/10.1016/j.eswa.2016.12.035
  10. Kim, S., Ejike, A.U., and Hur, J., A Study on Fault Classification of Solenoid Pumps based on Multi-Layer Perceptron, Journal of Applied Reliability, 2021, Vol. 21, No. 1, pp. 12-19. https://doi.org/10.33162/JAR.2021.3.21.1.12
  11. Kim, S.J., Khan, A., Sohn, J.W., and Kim, H.S., Deep Learning based Fault Diagnosis in Laminated Composites using Augmented Data, Spring Conference of the Korean Society of Mechanical Engineers, 2022, Busan, Korea, pp. 374-375.
  12. Lee, S., Park, S., Lee, S., Lee, H., Yu, S., and Lee, K., A Comparative Study on the Methodology of Failure Detection of Reefer Containers Using PCA and Feature Importance, Journal of The Korea Convergence Society, 2022, Vol. 13, No. 3, pp. 23-31. https://doi.org/10.15207/JKCS.2022.13.03.023
  13. Lee, S.H. and Kim, Y.S., A Pre-processing Process Using TadGAN-based Time-series Anomaly Detection, Journal of Korean Society for Quality Management, 2022, Vol. 50, No. 3, pp. 459-471.
  14. Lee, Y., Yong, H., Jung, J., and Kim, J., Development of Dormant Missile Health Monitoring Methodology based on Environmental Data, Journal of Applied Reliability, 2022, Vol. 22, No. 3, pp. 219-228. https://doi.org/10.33162/JAR.2022.9.22.3.219
  15. Mao, W., He, L., Yan, Y., and Wang, J., Online Sequential Prediction of Bearings Imbalanced Fault Diagnosis by Extreme Learning Machine, MSSP, 2017, Vol. 83, pp. 450-473. https://doi.org/10.1016/j.ymssp.2016.06.024
  16. Menardi, G. and Torelli, N., Training and assessing classification rules with imbalanced data, Data Mining and Knowledge Discovery, 2014, Vol. 28, No. 1, pp. 92-122. https://doi.org/10.1007/s10618-012-0295-5
  17. Mourtzis, D., Vlachou, E., and Milas, N., ndustrial Big Data as a Result of IoT Adoption in Manufacturing, Procedia CIRP, 2016, Vol. 55, pp. 290-295. https://doi.org/10.1016/j.procir.2016.07.038
  18. Pearson, K., On Lines and Planes of Closest Fit to Systems of Points in Space, The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science, 1901, Vol. 2, No. 11, pp. 559-572. https://doi.org/10.1080/14786440109462720
  19. Seo, C.-Y., Suh, Y.-J., and Kim, D.-J., Study on Fault Detection of a Gas Pressure Regulator Based on Machine Learning Algorithms, JKSCI, 2020, Vol. 25, No. 4, pp. 19-27.
  20. Seo, Y., Lee, K., Lee, Y., and Kim, J., Reliability Prediction Based on Field Failure Data of Guided Missile, Journal of Applied Reliability, 2018, Vol. 18, No. 3, pp. 250-259. https://doi.org/10.33162/JAR.2018.09.18.3.250
  21. Si, J., Jeong, J., Jeong, M., and Kim, S., Anomaly Detection of Injection Molding using Statistics-based Feature Selection and Generative Adversarial Learning, JKIIT, 2023, Vol. 21, No. 4, pp. 11-20. https://doi.org/10.14801/jkiit.2023.21.4.11
  22. Tibshirani, R., Regression shrinkage and selection via the Lasso, Journal of the Royal Statistical Society Series B: Statistical Methodology, 1996, Vol. 58, No. 1, pp. 267-288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x
  23. Wei, J., Huang, H., Yao, L., Hu, Y., Fan, Q., and Huang, D., New imbalanced bearing fault diagnosis method based on Sample-characteristic Oversampling TechniquE (SCOTE) and multi-class LS-SVM, Applied Soft Computing, 2021, Vol. 101, p. 107043.