Title :
Neural-MPC for N-removal in activated-sludge plants
Author :
Goldar, A. ; Revollar, S. ; Lamanna, R. ; Vega, P.
Author_Institution :
Processes & Syst. Dept., Simon Bolivar Univ., Caracas, Venezuela
Abstract :
A nonlinear model predictive controller based on neural networks is designed in this paper to regulate the nitrogen removal in the activated-sludge process. The benchmark simulation model (BSM1) is used to implement the predictive controller and to study its behavior in different situations. Also input-output data are gathered from the benchmark for the neural networks training. Control results under dry-weather perturbations are satisfactory when compared to other types of NLMPC.
Keywords :
learning (artificial intelligence); neurocontrollers; nitrogen; nonlinear control systems; perturbation techniques; predictive control; sludge treatment; N; NLMPC; activated-sludge plants; benchmark simulation model; dry-weather perturbations; neural network training; neural-MPC; nitrogen removal; nonlinear model predictive controller; Effluents; Mathematical model; Neural networks; Nitrogen; Predictive models; Process control; Tuning;
Conference_Titel :
Control Conference (ECC), 2014 European
Conference_Location :
Strasbourg
Print_ISBN :
978-3-9524269-1-3
DOI :
10.1109/ECC.2014.6862361
