Development of an electronic nose to characterize water quality parameters and odor concentration of wastewater emitted from different phases in a wastewater treatment plant

For public health consideration, it is important to ensure the wastewater discharged from wastewater treatment plant is within the regulatory limits. This problem can be effectively solved by improving the accuracy and rapid characterization of water quality parameters and odor concentration of wastewater. In this paper, we proposed a novel solution to realize the precisive analysis of water quality parameters and odor concentration of wastewater by the electronic nose device. The main work of this paper was divided into three steps: 1) recognizing waste-water samples qualitatively from different sampling points, 2) analyzing the correlation between electronic nose response signals and water quality parameters and odor concentration, and 3) predicting the odor concentration and water quality parameters quantitatively. Combined with different feature extraction methods, support vector machine and linear discriminant analysis were applied as classifiers to recognize samples at different sampling points, which reported the best recognition rate of 98.83%. Partial least squares regression was applied to complete the second step, and R2 was reaching 0.992. As for the third step, ridge regression was used to predict water quality parameters and odor concentration with the RMSE less than 0.9476. Thus, electronic noses can be applied to determine water quality parameters and odor concentrations in the effluent discharged from waste-water plants.

Automated summary

In this paper, a novel solution is proposed to achieve the precise analysis of water quality parameters and odor concentration of wastewater using an electronic nose device. The method involves three steps: qualitative recognition of wastewater samples, correlation analysis between electronic nose response signals and water quality parameters and odor concentration, and quantitative prediction of odor concentration and water quality parameters. The proposed method achieved satisfactory results, with a recognition rate of 98.83%, a R2 value of 0.992, and an RMSE value less than 0.9476.