Segmentation over Complexity: Evaluating Ensemble and Hybrid Approaches for Anomaly Detection in Industrial Time Series
This provides practical guidance for engineers working with imbalanced industrial time series data, though it's an incremental finding about model simplicity.
The study tackled anomaly detection in industrial steam turbine time series data by comparing complex feature engineering and hybrid models against a simple ensemble approach. The Random Forest + XGBoost ensemble outperformed all complex methods with an AUC-ROC of 0.976, F1-score of 0.41, and 100% early detection.
In this study, we investigate the effectiveness of advanced feature engineering and hybrid model architectures for anomaly detection in a multivariate industrial time series, focusing on a steam turbine system. We evaluate the impact of change point-derived statistical features, clustering-based substructure representations, and hybrid learning strategies on detection performance. Despite their theoretical appeal, these complex approaches consistently underperformed compared to a simple Random Forest + XGBoost ensemble trained on segmented data. The ensemble achieved an AUC-ROC of 0.976, F1-score of 0.41, and 100% early detection within the defined time window. Our findings highlight that, in scenarios with highly imbalanced and temporally uncertain data, model simplicity combined with optimized segmentation can outperform more sophisticated architectures, offering greater robustness, interpretability, and operational utility.