The correct control and prediction of Wastewater Treatment Plants
poses an important goal in order to avoid
breaking the environmental balance and to always keep the system in
stable operating conditions. In this respect, it is known that
qualitative information --coming from microscopic examinations
and subjective remarks-- has a deep influence on the activated
sludge process, especially in the total amount of effluent suspended
solids (TSS), one of the measures of overall plant performance.
The strong interrelation between variables,
their heterogeneity, and the very high amount of missing information
make the use of traditional techniques difficult, or even impossible.
Despite this problems, and through the use of
several soft computing methods --rough set theory and artificial
neural networks, mainly-- acceptable prediction models are found that
show the interplay between variables and give insight to
the dynamics of the process.