Machine learning methods for anomaly classification in wastewater treatment plants.
Autor: | Bellamoli F; University of Trento, Department of Information Engineering and Computer Science, via Sommarive 9, Trento, 38123, Italy; ETC Sustainable Solutions Srl, via dei Palustei 16, Trento, 38121, Italy. Electronic address: francesca.bellamoli@unitn.it., Di Iorio M; D-3 Srl, via dei Palustei 16, Trento, 38121, Italy., Vian M; ETC Sustainable Solutions Srl, via dei Palustei 16, Trento, 38121, Italy., Melgani F; University of Trento, Department of Information Engineering and Computer Science, via Sommarive 9, Trento, 38123, Italy. |
---|---|
Jazyk: | angličtina |
Zdroj: | Journal of environmental management [J Environ Manage] 2023 Oct 15; Vol. 344, pp. 118594. Date of Electronic Publication: 2023 Jul 18. |
DOI: | 10.1016/j.jenvman.2023.118594 |
Abstrakt: | Modern wastewater treatment plants base their biological processes on advanced control systems which ensure compliance with discharge limits and minimize energy consumption responding to information from on-line probes. The correct readings of probes are particularly crucial for intermittent aeration controllers, which rely on real-time measurements of ammonia and oxygen in biological tanks. These data are also an important resource for developing artificial intelligence algorithms that can identify process or sensor anomalies, thus guiding the choices of plant operators and automatic process controllers. However, using anomaly detection and classification algorithms in real-time wastewater treatment is challenging because of the noisy nature of sensor measurements, the difficulty of obtaining labeled real-plant data, and the complex and interdependent mechanisms that govern biological processes. This work aims at thoroughly exploring the performance of machine learning methods in detecting and classifying the main anomalies in plants operating with intermittent aeration. Using oxygen, ammonia and aeration power measurements from a set of plants in Italy, we perform both binary and multiclass classification, and we compare them through a rigorous validation procedure that includes a test on an unknown dataset, proposing a new evaluation protocol. The classification methods explored are support vector machine, multilayer perceptron, random forest, and two gradient boosting methods (LightGBM and XGBoost). The best performance was achieved using the gradient boosting ensemble algorithms, with up to 96% of anomalies detected and up to 84% and 62% of anomalies classified correctly on the first and second datasets respectively. Competing Interests: Declaration of competing interest The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: Francesca Bellamoli reports financial support was provided by ETC Sustainable Solutions srl. Francesca Bellamoli, Marco Vian reports a relationship with ETC Sustainable Solutions srl that includes: employment. (Copyright © 2023 The Authors. Published by Elsevier Ltd.. All rights reserved.) |
Databáze: | MEDLINE |
Externí odkaz: |
načítá se...