Application of Neurogenetic Modeling in Optimization of Water Treatment Plant Based on the Temporal Monitoring of Water Input Quality

Abstract

This article addresses methods to adjust operating requirements in water treatment plants (WTPs) in order to increase the efficiency of water treatment plants based on the nature of the water inflows into the systems. In the past, various studies have suggested that the quality of water inflow into the WTP has an impact on the efficiency and economic viability of operating treatment plants. Among all other quality parameters, the concentration of dissolved oxygen (DO) is one of the basic indicators about the overall quality of the water. Identification of a temporal pattern can help the engineers to adapt the WTP operations and can save the unnecessary wasting of plant resources. That is why the present article has proposed a new model that can predict the temporal patterns of various chemical parameters with the help of an analytic neuronal network. The model was applied to the case of a WTP that responds to a peri-urban catchment, leading to regular variations in the DO of water inflow. According to the performance metrics utilized the model was able to predict the temporal pattern at a lag of 1 hour.

Control and soft sensing strategies for a wastewater treatment plant using a neuro-genetic approach

“…Bagheri et al (2015) developed hybrid artificial neural network-GA models to predict the sludge volume index (SVI) accurately, where genetic algorithms were used to optimize weights and thresholds of the neural network models. A method to increase the efficiency of water treatment plants which adjusts operating requirements based on the nature of the water was presented in De (2019) , preventing the unnecessary waste of plant resources. Nevertheless, to our best knowledge, there are hardly any works where neural networks and GAs are applied together for the optimum control of wastewater treatment plants.…”