한국융합학회논문지 (Journal of the Korea Convergence Society)

  • 제13권3호
  • /
  • Pages.23-31
  • /
  • 2022
  • /
  • 2233-4890(pISSN)
  • /
  • 2713-6353(eISSN)
한국융합학회 (Korea Convergence Society)
권호 표지
DOI QR코드

DOI QR Code

PCA 및 변수 중요도를 활용한 냉동컨테이너 고장 탐지 방법론 비교 연구

A Comparative Study on the Methodology of Failure Detection of Reefer Containers Using PCA and Feature Importance

  • 이승현 (동아대학교 경영정보학과) ;
  • 박성호 (동아대학교 경영정보학과) ;
  • 이승재 (동아대학교 경영정보학과) ;
  • 이희원 (동아대학교 경영정보학과) ;
  • 유성열 (부산카톨릭대학교 경영정보학과) ;
  • 이강배 (동아대학교 경영정보학과)
  • 투고 : 2021.12.10
  • 심사 : 2022.03.20
  • 발행 : 2022.03.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 연구는 H해운사에서 제공받은 Starcool사의 실제 냉동 컨테이너 운영데이터를 분석하였다. H사의 현장 전문가와 인터뷰를 통해 4가지 고장 알람 중 Critical 및 Fatal Alarm만 고장으로 정의하였고, 냉동 컨테이너 특성상 모든 변수를 사용하는 것은 비용측면에서 비효율을 초래하는 것을 확인하였다. 이에 본 연구는 특성 중요도 및 PCA 기법을 통한 냉동 컨테이너 고장 탐지 방법을 제시한다. 모델의 성능 향상을 위해 XGBoost, LGBoost 등과 같은 트리계열 모델을 통해 변수 중요도(Feature Importance)를 기반으로 변수 선택(Feature selcetion)을 하고 선택되지 않은 변수는 PCA를 사용하여 전체 변수의 차원을 축소시켜 각 모델별로 지도학습을 수행한다. 부스팅 기반의 XGBoost, LGBoost 기법은 본 연구에서 제안하는 모델의 결과가 62개의 모든 변수를 사용한 지도 학습의 결과보다 재현율(Recall)이 각각 0.36, 0.39씩 향상되는 되는 결과를 보였다.

This study analyzed the actual frozen container operation data of Starcool provided by H Shipping. Through interviews with H's field experts, only Critical and Fatal Alarms among the four failure alarms were defined as failures, and it was confirmed that using all variables due to the nature of frozen containers resulted in cost inefficiency. Therefore, this study proposes a method for detecting failure of frozen containers through characteristic importance and PCA techniques. To improve the performance of the model, we select variables based on feature importance through tree series models such as XGBoost and LGBoost, and use PCA to reduce the dimension of the entire variables for each model. The boosting-based XGBoost and LGBoost techniques showed that the results of the model proposed in this study improved the reproduction rate by 0.36 and 0.39 respectively compared to the results of supervised learning using all 62 variables.

키워드

과제정보

This work was partly supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (No.2020-0-02091,Development and Commercialization of IoT-based refrigerated container real-time monitoring and BigData / AI-based failure predictive service platform to strengthen competitiveness of shipping & logistics company)

참고문헌

  1. B. Castelein, H. Geerlings & R. Van Duin. (2020). The reefer container market and academic research: A review study. Journal of Cleaner Production, 256, 120654. DOI : 10.1016/j.jclepro.2020.120654
  2. A. Kan, T. Wang, D. Zhu & D. Cao. (2021). The characteristics of cargo temperature rising in reefer container under refrigeration-failure condition. International Journal of Refrigeration, 123, 1-8. DOI : 10.1016/j.ijrefrig.2020.12.007
  3. N. Hoffmann, R. Stahlbock & S. Voss. (2020). A decision model on the repair and maintenance of shipping containers. Journal of Shipping and Trade, 5(1), 1-21. DOI : 10.1186/s41072-020-00070-2
  4. S. K. Park, Y. G. Park & Y. R. Shin. (2012). A Study on the Improvement of Damage to Reefer Container Cargo. Journal of Navigation and Port Research, 36(10), 803-810. DOI : 10.5394/KINPR.2012.36.10.803
  5. G. S. Gim, H. S. Shon, K. H. Ryu & S. H. Lee. (2013). Performance of PCA Algorithm for Multivariate Data Analysis. In Proceedings of the Korea Information Processing Society Conference (pp. 1264-1266). Korea Information Processing Society. DOI : 10.3745/PKIPS.Y2017M11A.1264
  6. K. B. Lee, S. H. Park, S. H. Sung & D. M. Park. (2019). A Study on the Prediction of CNC Tool Wear Using Machine Learning Technique. Journal of the Korea Convergence Society, 10(11), 15-21. DOI : 10.15207/JKCS.2019.10.11.015
  7. Y. D. Yun, Y. W. Yang, H. S. Ji & H. S. Lim. (2017). Development of Smart Senior Classification Model based on Activity Profile Using Machine Learning Method. Journal of Cleaner Production, 8(1), 25-34. DOI : 10.15207/JKCS.2017.8.1.025
  8. T. Chen & C. Guestrin. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 785-794. DOI : 10.1145/2939672.2939785
  9. A. Priyam, G. R. Abhijeeta, A. Rathee & S. Srivastava. (2013). Comparative analysis of decision tree classification algorithms. International Journal of current engineering and technology, 3(2), 334-337.
  10. R. Tian, F. Chen & S. Dong. (2021). Compound Fault Diagnosis of Stator Interturn Short Circuit and Air Gap Eccentricity Based on Random Forest and XGBoost. Mathematical Problems in Engineering, 2021. DOI : 10.1155/2021/2149048
  11. M. J. Oh, E. S. Choi, K. W. Roh, J. S. Kim & W. S. Jo. (2021). A Study on the Design of Supervised and Unsupervised Learning Models for Fault and Anomaly Detection in Manufacturing Facilities. The Korean Journal of BigData, 6(1), 23-35. DOI : 10.5394/KINPR.2012.36.10.803
  12. S. Cateni, M. Vannucci, M. Vannocci & V. Colla. (2012). Variable selection and feature extraction through artificial intelligence techniques. Multivariate Analysis in Management, Engineering and the Science, 103-118. DOI : 10.5772/53862
  13. Z. Du, B. Fan, X. Jin & J. Chi. (2014). Fault detection and diagnosis for buildings and HVAC systems using combined neural networks and subtractive clustering analysis. Building and Environment, 73, 1-11. DOI : 10.1016/j.buildenv.2013.11.021
  14. D. A. T. Tran, Y. Chen, H. L. Ao & H. N. T. Cam. (2016). An enhanced chiller FDD strategy based on the combination of the LSSVR-DE model and EWMA control charts. International Journal of Refrigeration, 72, 81-96. DOI : 10.1016/j.ijrefrig.2016.07.024
  15. D. Li, G. Hu & C. J. Spanos. (2016). A data-driven strategy for detection and diagnosis of building chiller faults using linear discriminant analysis. Energy and Buildings, 128, 519-529. DOI : 10.1016/j.enbuild.2016.07.014
  16. R, Huang et al. (2018). An effective fault diagnosis method for centrifugal chillers using associative classification. Applied Thermal Engineering, 136, 633-642. DOI : 10.1016/j.applthermaleng.2018.03.041
  17. G. LI et al. (2016). An improved fault detection method for incipient centrifugal chiller faults using the PCA-R-SVDD algorithm. Energy and Buildings, 116, 104-113. DOI : 10.1016/j.enbuild.2015.12.045
  18. R. Yan, Z. Ma, Y. Zhao & G. Kokogiannakis. (2016). A decision tree based data-driven diagnostic strategy for air handling units. Energy and Buildings, 133, 37-45. DOI : 10.1016/j.enbuild.2016.09.039
  19. K. B. Lee, S. H. Park, H. W. Lee, S. J. Lee & S. H. Lee. (2021). A study on the 3-step classification algorithm for the diagnosis and classification of refrigeration system failures and their types. Journal of the Korea Convergence Society, 12(8), 31-37. DOI : 10.15207/JKCS.2021.12.8.031
  20. G. Chandrashekar& F. Sahin. (2014). A survey on feature selection methods. Computers & Electrical Engineering, 40(1), 16-28. DOI : 10.1016/j.compeleceng.2013.11.024
  21. H. J. Han, D. K. Ko & H. C. Choe. (2019). Prediction and Analyzing Factor Affection Financial Stress of Household Using Machine Learning: Application of XGBoost. Journal of Consumer Studies, 30(2), 21-43. DOI : 10.35736/JCS.30.2.2