American Society of Civil Engineers


General Regression Neural Networks for Modeling Disinfection Residual in Water Distribution Systems


by R. J. May, (Centre for Applied Modelling in Water Engineering, School of Civil and Environmental Engineering, University of Adelaide, North Terrace, Adelaide, South Australia 5005), H. R. Maier, (Centre for Applied Modelling in Water Engineering, School of Civil and Environmental Engineering, University of Adelaide, North Terrace, Adelaide, South Australia 5005), G. C. Dandy, (Centre for Applied Modelling in Water Engineering, School of Civil and Environmental Engineering, University of Adelaide, North Terrace, Adelaide, South Australia 5005), and J. B. Nixon, (United Water International Pty. Ltd., GPO Box 1875, Adelaide, South Australia 5001)
Section: Water Distribution Systems Analysis, pp. 1-8, (doi:  http://dx.doi.org/10.1061/40737(2004)446)

     Access full text
     Purchase Subscription
     Permissions for Reuse  

Document type: Conference Proceeding Paper
Part of: Critical Transitions in Water and Environmental Resources Management
Abstract: Water treatment plant (WTP) operators set disinfectant levels such that a balance is maintained between achieving adequate disinfection and minimising the undesirable effects of excessive disinfection residuals. Control systems for the optimal maintenance of disinfection residuals are based upon a model that attempts to describe the non-linear dynamics of the water distribution system (WDS). A system identification approach, based on artificial neural networks (ANNs), offers an expedient methodology for the development of control-oriented models. An advantage of ANNs is their ability to describe non-linear systems with greater accuracy than linear empirical models that are traditionally used for system identification. In this paper, the parallel development of a general regression neural network (GRNN) model and an autoregressive model with exogenous inputs (ARX) is described for the Myponga WDS in South Australia. The results indicate the superiority of the GRNN model and support further investigation of WDS control systems that incorporate ANN identification models.


ASCE Subject Headings:
Water treatment plants
Neural networks
Disinfection
Water distribution systems