This paper presents the results of studies aiming at the assessment and classification of wastewater using an electronic nose. During the experiment, an attempt was made to classify the medium based on an analysis of signals from a gas sensor array, the intensity of which depended on the levels of volatile compounds in the headspace gas mixture above the wastewater table. The research involved samples collected from the mechanical and biological treatment devices of a full-scale wastewater treatment plant (WWTP), as well as wastewater analysis. The measurements were carried out with a metal-oxide-semiconductor (MOS) gas sensor array, when coupled with a computing unit (e.g., a computer with suitable software for the analysis of signals and their interpretation), it formed an e-nose—that is, an imitation of the mammalian olfactory sense. While conducting the research it was observed that the intensity of signals sent by sensors changed with drops in the level of wastewater pollution; thus, the samples could be classified in terms of their similarity and the analyzed gas-fingerprint could be related to the pollution level expressed by physical and biochemical indicators. Principal component analysis was employed for dimensionality reduction, and cluster analysis for grouping observation purposes. Supervised learning techniques confirmed that the obtained data were applicable for the classification of wastewater at different stages of the purification process.
Gas sensor array based on multi-walled carbon nanotubes and polymer
