Towards a model of input–output behaviour of wastewater treatment plants using soft computing techniques

摘要: Abstract Wastewater Treatment Plants (WWTPs) control and prediction under a wide range of operating conditions is an important goal in order to avoid breaking environmental balance, keeping the system stable suitable decision-making. In this respect, availability models characterizing WWTP behaviour as dynamic necessary first step. However, due high complexity processes heterogeneity, incompleteness imprecision data, finding poses substantial problems. work, approach via soft computing techniques sought, particular, by experimenting with fuzzy heterogeneous time-delay neural networks characterize time variation outgoing variables. Experimental results show that these are able statistically satisfactory sense also they perform better than other well-established network models.