The capability of hydrodynamic cavitation (HC) of degrading organic pollutants in water effluents is evaluated through the implementation of an Artificial Neural Network (ANN) analysis. Thanks to the construction and training of a multilayer ANN, the energy efficiency of the process has been correlated to measurable variables. These last have been accurately chosen in order to propose a novel modeling approach in the field of HC water treatment. One of the main peculiarity of the proposed model is to choose the ANN input neurons among both operating variables and physical-chemical characteristics of the pollutants. In this way, a powerful tool for prediction, optimization and control of the process, is realized. Preliminary results on the ANN training and on the simulation of factor influences are presented.
"Application of ANN to Hydrodynamic Cavitation: Preliminary Results on Process Efficiency Evaluation"
MUSMARRA, Dino
2014
Abstract
The capability of hydrodynamic cavitation (HC) of degrading organic pollutants in water effluents is evaluated through the implementation of an Artificial Neural Network (ANN) analysis. Thanks to the construction and training of a multilayer ANN, the energy efficiency of the process has been correlated to measurable variables. These last have been accurately chosen in order to propose a novel modeling approach in the field of HC water treatment. One of the main peculiarity of the proposed model is to choose the ANN input neurons among both operating variables and physical-chemical characteristics of the pollutants. In this way, a powerful tool for prediction, optimization and control of the process, is realized. Preliminary results on the ANN training and on the simulation of factor influences are presented.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
