A Maritime Industry Experience for Vessel Operational Anomaly Detection: Utilizing Deep Learning Augmented with Lightweight Interpretable Models

Abstract: This study presents an industry experience showcasing a vessel operational anomaly detection approach that utilizes semi-supervised deep learning models augmented with lightweight interpretable surrogate models, applied to an industrial sensorized vessel, called TUCANA. We leverage standard and Long Short-Term Memory (LSTM) autoencoders trained on normal operational data and tested with real anomaly-revealing data. We then provide a projection of the inference results on a lower-dimension data map generated by t-distributed stochastic neighbor embedding (t-SNE), which serves as an unsupervised baseline and shows the distribution of the identified anomalies. We also develop lightweight surrogate models using random forest and decision tree to promote transparency and interpretability for the inference results of the deep learning models and assist the engineer with an agile assessment of the flagged anomalies. The approach is empirically evaluated using real data from TUCANA. The empirical results show higher performance of the LSTM autoencoder -- as the anomaly detection module with effective capturing of temporal dependencies in the data -- and demonstrate the practicality of the lightweight surrogate models in providing helpful interpretability, which leads to higher efficiency for the engineer's decision-making.