Segmentation over Complexity: Evaluating Ensemble and Hybrid Approaches for Anomaly Detection in Industrial Time Series

TL;DR

This paper compares complex hybrid models and feature engineering techniques against simple ensemble methods for anomaly detection in industrial time series, finding that simpler models often perform better in real-world scenarios.

Contribution

The study demonstrates that simple ensemble models with segmentation outperform complex hybrid architectures in industrial anomaly detection tasks.

Findings

Ensemble achieved AUC-ROC of 0.976

Simple models provided 100% early detection

Complex approaches underperformed compared to simple ensembles

Abstract

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.