EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Unsupervised Anomaly Detection for Water Pump Fault Identification Under Extreme Class Imbalance

Mochamad Rizal Fauzan, Ghayrie Habsy Alghifary, Muhamad Husen

Journal of Information System Exploration and Research · 08.10.2026 · 4 (4) · 463-472

DOI: 10.52465/joiser.v4i4.114 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Information System Exploration and Research, online erschienen am 08.10.2026. Verfasst von Mochamad Rizal Fauzan und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Water pump fault detection in industrial systems is challenged by extreme class imbalance, where anomalous states account for less than 7% of operational data and labeled fault examples are scarce. This paper presents a comparative evaluation of three unsupervised anomaly detection approaches Isolation Forest (IF), Long Short-Term Memory Autoencoder (LSTM-AE), and One-Dimensional Convolutional Neural Network Autoencoder (1D-CNN-AE) applied to a real-world multivariate water pump sensor dataset comprising 220,320 one-minute observations across 51 sensors. All models are trained exclusively on normal operational data, eliminating dependence on fault labels. A sliding-window preprocessing pipeline (W = 30 timesteps) with a scaler fitted only on normal training data ensures no temporal data leakage. Anomaly thresholds are derived statistically (mean + 3σ) from reconstruction errors on the normal test partition. Using a chronological 60/40 train-test split and threshold-free metrics, Isolation Forest achieves AUROC = 0.9973 and Recall = 0.9850, while LSTM-AE yields F1 = 0.9218 and Precision = 0.8892. The results reveal a fundamental sensitivity-selectivity trade-off across unsupervised paradigms and provide actionable guidance for deploying anomaly detection in water infrastructure monitoring systems.

Zitieren

APA

Fauzan, M. R., Alghifary, G. H., & Husen, M. (2026). Unsupervised Anomaly Detection for Water Pump Fault Identification Under Extreme Class Imbalance. Journal of Information System Exploration and Research, 4(4), 463-472. https://doi.org/10.52465/joiser.v4i4.114

Vancouver

Fauzan MR, Alghifary GH, Husen M. Unsupervised Anomaly Detection for Water Pump Fault Identification Under Extreme Class Imbalance. Journal of Information System Exploration and Research. 2026;4(4):463-472. doi:10.52465/joiser.v4i4.114

BibTeX
@article{Fauzan2026,
  author = {Fauzan, Mochamad Rizal and Alghifary, Ghayrie Habsy and Husen, Muhamad},
  title = {Unsupervised Anomaly Detection for Water Pump Fault Identification Under Extreme Class Imbalance},
  journal = {Journal of Information System Exploration and Research},
  year = {2026},
  volume = {4},
  number = {4},
  pages = {463--472},
  doi = {10.52465/joiser.v4i4.114}
}
Kostenlos starten →