Wastewater treatment plant monitoring via a deep learning approach

Type
Conference Paper

Authors
Harrou, Fouzi
Dairi, Abdelkader
Sun, Ying
Senouci, Mohamed

KAUST Department
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Statistics Program

Online Publication Date
2018-05-04

Print Publication Date
2018-02

Date
2018-05-04

Abstract
This paper presents a fault detection method based on an unsupervised deep learning to monitor operating conditions of wastewater treatment plants (WWTPs). This method uses Deep Belief Networks (DBNs) model and one-class support vector machine (OCSVM). Here, DBN model is introduced to account for nonlinear aspects of WWTPs, while OCSVM is employes to reliably detect a fault in WWTP. The developed DBN-OCSVM approach has been tested through practical application on data from a decentralized wastewater treatment plant in Golden, CO, USA. Results show the effectiveness of the developed approach to monitor the WWTP.

Citation
Harrou F, Dairi A, Sun Y, Senouci M (2018) Wastewater treatment plant monitoring via a deep learning approach. 2018 IEEE International Conference on Industrial Technology (ICIT). Available: http://dx.doi.org/10.1109/ICIT.2018.8352410.

Acknowledgements
This publication is based upon work supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No: OSR-2015-CRG4-2582

Publisher
Institute of Electrical and Electronics Engineers (IEEE)

Journal
2018 IEEE International Conference on Industrial Technology (ICIT)

Conference/Event Name
19th IEEE International Conference on Industrial Technology, ICIT 2018

DOI
10.1109/ICIT.2018.8352410

Additional Links
https://ieeexplore.ieee.org/document/8319212/

Permanent link to this record