TY - GEN

T1 - Enhancing artificial neural networks applied to the optimal design of water distribution systems

AU - Andrade, Manuel A.

AU - Choi, Christopher Y.

AU - Mondaca, Mario R.

AU - Lansey, Kevin

AU - Kang, Doosun

PY - 2013

Y1 - 2013

N2 - Achieving an optimal design for a typical water distribution system (WDS) essentially involves determining which combination of pipes and arrangements will produce the most efficient and economical network. Solving the problem is a complex process, one well suited to computationally intensive heuristic methods. Including water quality constraints can pose a special challenge due to the demanding, extended-period simulations involved. Employing artificial neural networks (ANNs) can reduce the amount of computation time needed. ANNs can in fact approximate disinfectant concentrations in a fraction of the time required by a conventional water quality model. This study presents a methodology for improving the accuracy of ANNs applied to the optimal design of a WDS by means of a probabilistic approach based on the fast finding of a network similar to the optimal WDS. This work also presents a methodology to find such a network. ANNs trained with the probabilistic dataset generated using the proposed approach were shown to be more accurate than their counterparts trained with a random dataset.

AB - Achieving an optimal design for a typical water distribution system (WDS) essentially involves determining which combination of pipes and arrangements will produce the most efficient and economical network. Solving the problem is a complex process, one well suited to computationally intensive heuristic methods. Including water quality constraints can pose a special challenge due to the demanding, extended-period simulations involved. Employing artificial neural networks (ANNs) can reduce the amount of computation time needed. ANNs can in fact approximate disinfectant concentrations in a fraction of the time required by a conventional water quality model. This study presents a methodology for improving the accuracy of ANNs applied to the optimal design of a WDS by means of a probabilistic approach based on the fast finding of a network similar to the optimal WDS. This work also presents a methodology to find such a network. ANNs trained with the probabilistic dataset generated using the proposed approach were shown to be more accurate than their counterparts trained with a random dataset.

UR - http://www.scopus.com/inward/record.url?scp=84887451434&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887451434&partnerID=8YFLogxK

U2 - 10.1061/9780784412947.063

DO - 10.1061/9780784412947.063

M3 - Conference contribution

AN - SCOPUS:84887451434

SN - 9780784412947

T3 - World Environmental and Water Resources Congress 2013: Showcasing the Future - Proceedings of the 2013 Congress

SP - 648

EP - 662

BT - World Environmental and Water Resources Congress 2013

PB - American Society of Civil Engineers (ASCE)

T2 - World Environmental and Water Resources Congress 2013: Showcasing the Future

Y2 - 19 May 2013 through 23 May 2013

ER -