Neural Network Identification of N-Removal Process in Waste Water Treatment Plants

• DOI: 10.2316/p.2014.809-051
• Publication Date: 2014-03-31T14:29:13Z
• Authors: Alejandro Goldar; Silvana R. Revollar; Rosalba Lamanna; Pastora Vega
• Keywords: 0209 industrial biotechnology; 02 engineering and technology; 6. Clean water

A nonlinear model with neural networks structure is identified in this paper from input-output data of the activated-sludge process. The simulation protocol BSM1 is used as a benchmark to gather the operating data used for the neural networks training and validations. The neural model is constituted by two feed-forward neural networks to estimate oxygen and nitrates concentrations. The performance of each NN is assessed as a virtual sensor for variable estimation, or as a predictive model for process control purposes.