Deep learning base faults diagnosis of centrifugal pumps
Pollack Periodica · 08.04.2026
DOI: 10.1556/606.2026.01550 ↗Kurz gefasst
Fachartikel in der Zeitschrift Pollack Periodica, erschienen am 08.04.2026. Verfasst von Amar P. Pandhare und 8 weiteren Autor:innen. Die Arbeit nennt 132 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Centrifugal pumps are critical components in industrial systems, where early fault detection is essential to reduce downtime and maintenance costs. This study proposes a deep learning based framework for intelligent health monitoring of centrifugal pumps using time series vibration signals. Recurrent neural networks, long short term memory networks, and hybrid convolutional neural network long short term memory models are evaluated for operating condition classification and fault detection. The vibration data are preprocessed and normalized to capture temporal characteristics effectively. Experimental results based on accuracy, precision recall metrics, and confusion matrices show that the convolutional neural network long short term memory model achieves superior performance and generalization, making it suitable for fault diagnosis of rotating machinery.
Zitieren
APA
Pandhare, A. P., Naranje, V., Shukla, V., Balogh, G., Kulkarni, A., Dave, G. S., Khankal, D. V., Garse, K., & Erdei, T. I. (2026). Deep learning base faults diagnosis of centrifugal pumps. Pollack Periodica. https://doi.org/10.1556/606.2026.01550
Vancouver
Pandhare AP, Naranje V, Shukla V, Balogh G, Kulkarni A, Dave GS, et al. Deep learning base faults diagnosis of centrifugal pumps. Pollack Periodica. 2026. doi:10.1556/606.2026.01550
BibTeX
@article{Pandhare2026,
author = {Pandhare, Amar P. and Naranje, Vishal and Shukla, Vinod and Balogh, Gábor and Kulkarni, Atul and Dave, Gaurav S. and Khankal, Dhananjay V. and Garse, Komal and Erdei, Timotei István},
title = {Deep learning base faults diagnosis of centrifugal pumps},
journal = {Pollack Periodica},
year = {2026},
doi = {10.1556/606.2026.01550}
}
EUVIMED