Abstract
In the context of industrial factories and energy producers, unplanned outages are highly costly and difficult to service. However, existing acoustic-anomaly detection studies largely rely on generic industrial or synthetic datasets, with few focused on hydropower plants due to limited access. This paper presents a comparative analysis of acoustic-based anomaly detection methods, as a way to improve predictive maintenance in hydropower plants. We address key challenges in the acoustic preprocessing under highly noisy conditions before extracting time- and frequency-domain features. Then, we benchmark three machine learning models: LSTM AE, K-Means, and OC-SVM, which are tested on two real-world datasets from the Rodundwerk II pumped-storage plant in Austria, one with induced anomalies and one with real-world conditions. The One-Class SVM achieved the best trade-off of accuracy (ROC AUC 0.997–0.998) and minimal training time, while the LSTM autoencoder delivered strong detection (ROC AUC 0.997-0.999) at the expense of higher computational cost.
Keywords: Industrial Machinery, Acoustic Anomaly Detection, Predictive Maintenance, Machine learning
How to Cite:
Khamaisi, K., Keller, N., Krummenacher, S., Huber, V., Fässler, B. & Rodrigues, B., (2025) “From Noise to Knowledge: A Comparative Study of Acoustic Anomaly Detection Models in Pumped-storage Hydropower Plants”, IoT Workshop Proceedings 1(1), 17-24. doi: https://doi.org/10.34749/3061-1008.2025.3
Rights: Copyright © 2025 The author(s)
Downloads:
Download PDF
56 Views
12 Downloads