선박 메인 엔진의 이상 탐지와 원인 규명: 내부 센서 및 외부 환경 요인을 고려한 설명 가능한 인공지능 기반 방법론 = Anomaly Detection and Root Cause Analysis of Ship Main Engines: Explainable Artificial Intelligence-Based Methodology Considering Internal Sensors and External Environmental Factors

다국어 초록 (Multilingual Abstract)

The main engine of a ship plays a crucial role in providing propulsion. In recent times, there has been growing interest in a data-driven monitoring approach that utilizes sensor data to complement the preventive maintenance-centered maintenance strategy. Previous studies have proposed methodologies that apply anomaly detection algorithms to the sensor data within the main engine. However, these methodologies have limitations as they only focus on analyzing internal sensor data and fail to consider external factors such as operating conditions, marine environment, and weather. Additionally, the use of black-box approaches makes it challenging to determine the specific factors causing anomalies. To address these limitations, this study introduces a method that employs Explainable Artificial Intelligence (XAI) techniques to identify the causes of anomalies in ship main engines. The proposed method involves calculating anomaly scores using Variational AutoEncoder on collected sensor data and training a separate model to predict anomaly scores by considering external factors like operating conditions and weather. Furthermore, the SHAP (Shapley Additive Explanations) technique is utilized to quantify the contributions of external factors to the anomaly scores. This enables the analysis of individual data features and facilitates both local and global analysis for identifying the causes of anomalies and diagnosing faults. The proposed methodology was validated through a case study using data collected from a container ship over an 18-month period, demonstrating its effectiveness in identifying the causes of anomalies in the ship’s main engine.

참고문헌 (Reference)

1 김동현 ; 이지환 ; 이상봉 ; 정봉규, "앙상블 기법을 이용한 선박 메인엔진 빅데이터의 이상치 탐지" 한국수산해양기술학회 56 (56): 384-394, 2020

2 Chen, T., "XGBoost: A Scalable Tree Boosting System" 785-794, 2016

3 An, J, "Variational autoencoder based anomaly detection using reconstruction probability" Special lecture on IE

4 Raptodimos, Y., "Using artificial neural network-self-organising map for data clustering of marine engine condition monitoring applications" 13 (13): 649-656, 2018

5 Vanem, E., "Unsupervised anomaly detection based on clustering methods and sensor data on a marine diesel engine" 20 (20): 217-234, 2021

6 Geiger, A., "Tadgan: Time series anomaly detection using generative adversarial networks" IEEE 33-43, 2020

7 Deris, S., "Ship maintenance scheduling by genetic algorithm and constraint-based reasoning" 112 (112): 489-502, 1999

8 Capezza, C., "Ship fuel consumption monitoring and fault detection via partial least squares and control charts of navigation data" 67 : 375-387, 2019

9 Hinton, G. E., "Reducing the dimensionality of data with neural networks" 313 (313): 504-507, 2006

10 Breiman, L., "Random Forests" 45 (45): 5-32, 2001

11 Velasco-Gallego, C., "RADIS: A real-time anomaly detection intelligent system for fault diagnosis of marine machinery" 204 : 117634-, 2022

12 Opitz, D., "Popular Ensemble Methods: An Empirical Study" 11 : 169-198, 1999

13 Aggarwal, C. C., "Outlier Analysis" Springer International Publishing 2017

14 Ellefsen, A. L., "Online fault detection in autonomous ferries: Using fault-type independent spectral anomaly detection" 69 (69): 8216-8225, 2020

15 Boullosa, D., "Monitoring through T2 Hotelling of cylinder lubrication process of marine diesel engine" 110 : 32-38, 2017

16 Cheliotis, M., "Machine learning and data-driven fault detection for ship systems operations" 216 : 107968-, 2020

17 Malhotra, P., "Long Short Term Memory Networks for Anomaly Detection in Time Series" 2015 : 89-, 2015

18 Ke, G, "LightGBM: A Highly Efficient Gradient Boosting Decision Tree" Curran Associates, Inc 30 : 2017

19 Niu, Z., "LSTM-based VAE-GAN for time-series anomaly detection" 20 (20): 3738-, 2020

20 김도희 ; 한영재 ; 김혜미 ; 강성필 ; 김기훈 ; 배혜림, "LSTM-AutoEncoder를 활용한 선박 메인엔진의 이상 탐지 및 라벨링" 사)한국빅데이터학회 7 (7): 125-137, 2022

21 Lazakis, I., "Investigating an SVM-driven, one-class approach to estimating ship systems condition" 14 (14): 432-441, 2019

22 Goodfellow, I., "Generative adversarial networks" 63 (63): 139-144, 2020

23 김동현 ; 이상봉 ; 이지환, "Gaussian Mixture Model을 이용한 선박 메인 엔진 빅데이터의 이상치 탐지" 한국자료분석학회 22 (22): 1473-1489, 2020

24 Kowalski, J., "Fault diagnosis of marine 4-stroke diesel engines using a one-vs-one extreme learning ensemble" 57 : 134-141, 2017

25 Liznerski, P., "Explainable deep one-class classification"

26 Wong, C. W., "Explainable Tree-Based Predictions for Unplanned 30-Day Readmission of Patients With Cancer Using Clinical Embeddings" 5 : 155-167, 2021

27 Park, S., "Explainable Anomaly Detection for District Heating Based on Shapley Additive Explanations" 762-765, 2020

28 Kim, D., "Explainable Anomaly Detection Framework for Maritime Main Engine Sensor Data" 21 (21): 5200-, 2021

29 Ruff, L., "Deep semi-supervised anomaly detection"

30 Ruff, L., "Deep one-class classification" PMLR 4393-4402, 2018

31 Pang, G., "Deep Learning for Anomaly Detection: A Review" 54 (54): 1-38, 2022

32 Lundberg, S. M., "Consistent Individualized Feature Attribution for Tree Ensembles"

33 Cipollini, F., "Condition-based maintenance of naval propulsion systems:Data analysis with minimal feedback" 177 : 12-23, 2018

34 Bergman, L, "Classification-Based Anomaly Detection for General Data"

35 Prokhorenkova, L, "CatBoost: Unbiased boosting with categorical features" Curran Associates, Inc 31 : 2018

36 Kingma, D. P., "Auto-encoding variational bayes"

37 Wang, M., "An Explainable Machine Learning Framework for Intrusion Detection Systems" 8 : 73127-73141, 2020

38 Tan, Y., "A comparative investigation of data-driven approaches based on one-class classifiers for condition monitoring of marine machinery system" 201 : 107174-, 2020

39 Bentéjac, C., "A comparative analysis of gradient boosting algorithms" 54 (54): 1937-1967, 2021

40 Lundberg, S. M, "A Unified Approach to Interpreting Model Predictions" Curran Associates, Inc 30 : 2017