🤖 AI Summary
To address high temporal uncertainty and difficulty in identifying state transitions in industrial time-series anomaly detection, this paper proposes a synergistic framework integrating piecewise preprocessing with heterogeneous ensemble learning. First, change-point detection algorithms (e.g., ChangeFinder) adaptively segment the time series to explicitly model abrupt system state transitions, thereby mitigating temporal ambiguity. Second, a heterogeneous ensemble model is constructed by fusing Random Forest, XGBoost, and LSTM, augmented with PCA-based feature decorrelation. The method innovatively combines dynamic segmentation with model diversity, establishing a novel paradigm for boundary-sensitive anomaly modeling and feature-weight optimization. Evaluated on real-world industrial datasets, the approach achieves an AUC-ROC of 0.9760—outperforming baseline methods by 11.61 percentage points—and demonstrates significantly enhanced discrimination capability for transient anomalies and concept drift.
📝 Abstract
Concerning machine learning, segmentation models can identify state changes within time series, facilitating the detection of transitions between normal and anomalous conditions. Specific techniques such as Change Point Detection (CPD), particularly algorithms like ChangeFinder, have been successfully applied to segment time series and improve anomaly detection by reducing temporal uncertainty, especially in multivariate environments. In this work, we explored how the integration of segmentation techniques, combined with a heterogeneous ensemble, can enhance anomaly detection in an industrial production context. The results show that applying segmentation as a pre-processing step before selecting heterogeneous ensemble algorithms provided a significant advantage in our case study, improving the AUC-ROC metric from 0.8599 (achieved with a PCA and LSTM ensemble) to 0.9760 (achieved with Random Forest and XGBoost). This improvement is imputable to the ability of segmentation to reduce temporal ambiguity and facilitate the learning process of supervised algorithms. In our future work, we intend to assess the benefit of introducing weighted features derived from the study of change points, combined with segmentation and the use of heterogeneous ensembles, to further optimize model performance in early anomaly detection.