META: Deep Learning Pipeline for Detecting Anomalies on Multimodal Vibration Sewage Treatment Plant Data

Simeon Krastev, Aukkawut Ammartayakun, Kewal Mishra, Harika Koduri, Eric Schuman, Drew Morris, Yuan Feng, Sai Bandi, Chun-Kit Ngan, Andrew Yeung, Jason Li, Nigel Ko, Fatemeh Emdad, Elke Rundensteiner, Heiton Ho, T. Wong, Jolly Chan

2024

Abstract

In this paper, we propose a hybrid anomaly detection pipeline, META, which integrates Multimodal-feature Extraction (ME) and a Transformer-based Autoencoder (TA) for predictive maintenance of sewage treatment plants. META uses a three-step approach: First, it employs a signal averaging method to remove noise and improve the quality of signals related to pump health. Second, it extracts key signal properties from three vibration directions (Axial, Radial X, Radial Y), fuses them, and performs dimensionality reduction to create a refined PCA feature set. Third, a Transformer-based Autoencoder (TA) learns pump behavior from the PCA features to detect anomalies with high precision. We validate META with an experimental case study at the Stonecutters Island Sewage Treatment Works in Hong Kong, showing it outperforms state-of-the-art methods in metrics like MCC and F1-score. Lastly, we develop a web-based Sewage Pump Monitoring System hosting the META pipeline with an interactive interface for future use.

Paper Citation

in Harvard Style

Krastev S., Ammartayakun A., Mishra K., Koduri H., Schuman E., Morris D., Feng Y., Bandi S., Ngan C., Yeung A., Li J., Ko N., Emdad F., Rundensteiner E., Ho H., Wong T. and Chan J. (2024). META: Deep Learning Pipeline for Detecting Anomalies on Multimodal Vibration Sewage Treatment Plant Data. In Proceedings of the 16th International Joint Conference on Computational Intelligence - Volume 1: NCTA; ISBN 978-989-758-721-4, SciTePress, pages 461-474. DOI: 10.5220/0013031600003837

in Bibtex Style

@conference{ncta24,
author={Simeon Krastev and Aukkawut Ammartayakun and Kewal Mishra and Harika Koduri and Eric Schuman and Drew Morris and Yuan Feng and Sai Bandi and Chun-Kit Ngan and Andrew Yeung and Jason Li and Nigel Ko and Fatemeh Emdad and Elke Rundensteiner and Heiton Ho and T. Wong and Jolly Chan},
title={META: Deep Learning Pipeline for Detecting Anomalies on Multimodal Vibration Sewage Treatment Plant Data},
booktitle={Proceedings of the 16th International Joint Conference on Computational Intelligence - Volume 1: NCTA},
year={2024},
pages={461-474},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013031600003837},
isbn={978-989-758-721-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computational Intelligence - Volume 1: NCTA
TI - META: Deep Learning Pipeline for Detecting Anomalies on Multimodal Vibration Sewage Treatment Plant Data
SN - 978-989-758-721-4
AU - Krastev S.
AU - Ammartayakun A.
AU - Mishra K.
AU - Koduri H.
AU - Schuman E.
AU - Morris D.
AU - Feng Y.
AU - Bandi S.
AU - Ngan C.
AU - Yeung A.
AU - Li J.
AU - Ko N.
AU - Emdad F.
AU - Rundensteiner E.
AU - Ho H.
AU - Wong T.
AU - Chan J.
PY - 2024
SP - 461
EP - 474
DO - 10.5220/0013031600003837
PB - SciTePress