Soft sensors with white- and black-box approaches for a wastewater treatment process

The increasing degradation of water resources makes it necessary to monitor and control process variables that may disturb the environment, but which may be very difficult to measure directly, either because there are no phys ical sensors available, or because these are too expensive. In this work, t wo soft sensors are proposed for monitoring concentrations of nitrate (NO) and ammonium (NH) ions, and of carbonaccous matter (CM) during nitrificatio n of wastewater. One of them is based on reintegration of a process model t o estimate NO and NH and on a feedforward neural network to estimate CM. Th e other estimator is based on Stacked Neural Networks (SNN), an approach th at provides the predictor with robustness. After simulation, both soft sens ors were implemented in an experimental unit using FIX MMI (Intellution, In c) automation software as an interface between the process and MATLAB 5.1 ( The Mathworks Inc.) software.