Abstract
The paper presented the methodology for the construction of a soft sensor used for activated sludge bulking identification. Devising such solutions fits within the current trends and development of a smart system and infrastructure within smart cities. In order to optimize the selection of the data-mining method depending on the data collected within a wastewater treatment plant (WWTP), a number of methods were considered, including: artificial neural networks, support vector machines, random forests, boosted trees, and logistic regression. The analysis conducted sought the combinations of independent variables for which the devised soft sensor is characterized with high accuracy and at a relatively low cost of determination. With the measurement results pertaining to the quantity and quality of wastewater as well as the temperature in the activated sludge chambers, a good fit can be achieved with the boosted trees method. In order to simplify the selection of an optimal method for the identification of activated sludge bulking depending on the model requirements and the data collected within the WWTP, an original system of weight estimation was proposed, enabling a reduction in the number of independent variables in a model—quantity and quality of wastewater, operational parameters, and the cost of conducting measurements.
Highlights
The processes occurring in the environment, including urban areas, are very difficult to describe.These changes are dynamic in nature and are governed by a number of external factors, that are random, anthropogenic and local.Sensors 2020, 20, 1941; doi:10.3390/s20071941 www.mdpi.com/journal/sensorsTaking into account that many of them affect the operational costs of infrastructure, urban development, and the comfort of city residents, it is necessary to predict, control and optimize these factors [1,2].This approach results in the development of the so-called smart system and infrastructure within smart cities [3,4,5]
The results of the analyses presented above show that the soft sensor model developed based on the selection of a data-mining method for sludge bulking simulation takes into account both the number of the wastewater quality indicators and the bioreactor operating parameters, as well as the costs of their determination
The reliability of the input data for the soft sensor model is an important criterion, as shown by a detailed analysis of sensitivity which enabled an assessment of the effect of one, two or three independent variable(s) on the results of calculation of the activated sludge bulking
Summary
Taking into account that many of them affect the operational costs of infrastructure, urban development, and the comfort of city residents, it is necessary to predict, control and optimize these factors [1,2] This approach results in the development of the so-called smart system and infrastructure within smart cities [3,4,5]. Due to the complex process mechanisms and the influence of numerous factors, great quantities of data have to be collected using sensors This enables us to identify their dynamics and create so-called soft sensors based on the devised the mathematical models [6,7,8]. Luccarni et al [13]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
