Wastewater is a harsh environment for any instrumentation, however sensors implementation is fundamental in Water Resource Recovery Facilities. The study focuses on DO, pH, ORP, MLSS and ammonium sensors, with a specific attention on the last because of its promising application for ammonium-based aeration control. A software sensor is developed based on a Neural Network model with Principal Components Analysis as preprocessing of the raw data collected at a full-scale facility for a seasonal cycle. The soft-sensor predicts ammonium based on the other water quality data, to improve the hardware sensor robustness and enhance fault detection.
Author(s)F. Cecconi1; ,2; Y. Ito3; D. Rosso1; ,2;
Author affiliation(s)Department of Civil and Environmental Engineering, University of California, Irvine, CA1; Water-Energy Nexus Center, University of California2; Horiba Advanced Techno Co, Ltd.3
SourceProceedings of the Water Environment Federation
Document typeConference Paper
PublisherWater Environment Federation
Print publication date Oct, 2020
DOI10.2175/193864718825157814
Volume / Issue
Content sourceWEFTEC
Copyright2020
Word count260