Development of a Virtual Sensor for COD Measurement in a Wastewater Treatment Plant

Abstract

[Abstract] The objective of the work is to develop a system that allows predicting, from a global perspective, the behavior of the process in a wastewater treatment plant. To do this, the chemical oxygen demand, a variable present in water, is estimated indirectly, avoiding difficult and complex measurements. This estimation is carried out in real time through the relationship between easily measured variables. This modeling will be done through the use of machine learning techniques. Different regression techniques are applied and compared. The dataset contains variables such as pH, conductivity, suspended solids and etc. In thisway, a non-physical indirect sensor is implemented. Thresholds are established for the detection of deviations in the sensor parameters