Development of a CFD-Based Artificial Neural Network Metamodel in a Wastewater Disinfection Process with Peracetic Acid

Abstract

Computational fluid dynamics (CFD) have been applied to predict the performance of chemical water treatment disinfection systems in recent decades. However, computation times remain sufficiently long and prevent their use in optimal design. As an alternative, the use of an artificial neural network (ANN) metamodel to simulate CFD results was assessed. The ANN metamodel was trained by a series of CFD simulations of peracetic acid (PAA) disinfection characteristics in a chemical treatment reactor in the wastewater treatment process. The design space was sampled by applying a quasi-random sampling technique. A total of 40 CFD cases with 11 variables were obtained and used as input to the training process of the metamodel development. Metamodels were developed to predict disinfectant residual concentration and a microbial inactivation rate on full-scale reactors. The performance of the ANN-based metamodel is evaluated by comparison to CFD simulation results and pilot-scale experimental measurements. As a mathematical approximation method to a high dimensional nonlinear system, the ANN-based metamodel shows its ability to provide an efficient yet accurate solution to the wastewater disinfection process with PAA.