From Noise to Knowledge: A Comparative Study of Acoustic Anomaly Detection Models in Pumped-storage Hydropower Plants
This addresses predictive maintenance for hydropower plants, an incremental improvement as it applies existing methods to a new domain with limited prior focus.
The paper tackled acoustic anomaly detection for predictive maintenance in hydropower plants by benchmarking three machine learning models on real-world datasets, with One-Class SVM achieving ROC AUC scores of 0.966-0.998 and LSTM autoencoder scoring 0.889-0.997.
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 0.966-0.998) and minimal training time, while the LSTM autoencoder delivered strong detection (ROC AUC 0.889-0.997) at the expense of higher computational cost.