Using Radial Basis Function Neural Networks to Calibrate Water Quality Model

Modern managements of water distribution system (WDS) need water quality models that are able to accurately predict the dynamics of water quality variations within the distribution system environment. Before water quality models can be applied to solve system problems, they should be calibrated. Although former researchers use GA solver to calibrate relative parameters, it is difficult to apply on the large-scale or medium-scale real system for long computational time. In this paper a new method is designed which combines both macro and detailed model to optimize the water quality parameters. This new combinational algorithm uses radial basis function (RBF) metamodeling as a surrogate to be optimized for the purpose of decreasing the times of time-consuming water quality simulation and can realize rapidly the calibration of pipe wall reaction coefficients of chlorine model of large-scaled WDS. After two cases study this method is testified to be more efficient and promising, and deserve to generalize in the future. Keywords—Metamodeling, model calibration, radial basis function, water distribution system, water quality model.

[1]  Hans-Martin Gutmann,et al.  A Radial Basis Function Method for Global Optimization , 2001, J. Glob. Optim..

[2]  Dominic L. Boccelli,et al.  Incorporating Spatial Correlation in a Markov Chain Monte Carlo Approach for Network Model Calibration , 2005 .

[3]  Bart G. van Bloemen Waanders.  Application of Optimization Methods to Calibration of Water Distribution Systems , 2004 .

[4]  Paul F. Boulos,et al.  DISCRETE SIMULATION ApPROACH FOR NETWORK-WATER-QUALITY MODELS , 1995 .

[5]  Daniel J. Fonseca,et al.  Simulation metamodeling through artificial neural networks , 2003 .

[6]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[7]  T. Simpson,et al.  Comparative studies of metamodelling techniques under multiple modelling criteria , 2001 .

[8]  Robert M. Clark,et al.  Characterizing The Pipe Wall Demand For Free Chlorine In Metallic Pipes , 2004 .

[9]  James G. Uber,et al.  Sampling Design Methods for Water Distribution Model Calibration , 1998 .

[10]  K. Giannakoglou,et al.  Aerodynamic shape design using evolutionary algorithms and new gradient-assisted metamodels , 2006 .

[11]  Jack P. C. Kleijnen,et al.  A methodology for fitting and validating metamodels in simulation , 2000, Eur. J. Oper. Res..

[12]  R. Powell,et al.  Calibration and comparison of chlorine decay models for a test water distribution system , 2000 .

[13]  Srinivasa Lingireddy,et al.  Optimal Network Calibration Model Based on Genetic Algorithms , 1999 .

[14]  Holger R. Maier,et al.  Estimating Risk Measures for Water Distribution Systems using Metamodels , 2005 .

[15]  Haralambos Sarimveis,et al.  A new algorithm for developing dynamic radial basis function neural network models based on genetic algorithms , 2002, Comput. Chem. Eng..

[16]  Adrian J. Saul,et al.  Explicit Consideration of Spatial Flowrate Distribution in Network Model Calibration , 2001 .

[17]  Srinivasa Lingireddy,et al.  Neural Networks in Optimal Calibration of Water Distribution Systems , 1998 .

[18]  Juan Saldarriaga,et al.  Several Configurations and Aggregation Levels in Neural Networks for Water Distribution Networks Calibration , 2004 .

[19]  Juan Saldarriaga,et al.  Water Distribution Network Calibration with Fuzzy Logic , 2004 .

[20]  Christine A. Shoemaker,et al.  Constrained Global Optimization of Expensive Black Box Functions Using Radial Basis Functions , 2005, J. Glob. Optim..

[21]  Robert M. Clark,et al.  Characterizing Pipe Wall Demand: Implications for Water Quality Modeling , 2005 .

[22]  Sanjay B. Joshi,et al.  Metamodeling: Radial basis functions, versus polynomials , 2002, Eur. J. Oper. Res..

[23]  A. Shahsavand,et al.  Application of optimal RBF neural networks for optimization and characterization of porous materials , 2005, Comput. Chem. Eng..

[24]  Larry J. Shuman,et al.  Computing confidence intervals for stochastic simulation using neural network metamodels , 1999 .

[25]  Holger R. Maier,et al.  A Metamodeling Approach to Water Distribution System Optimization , 2004 .

[26]  P. Boulos,et al.  Discrete Volume‐Element Method for Network Water‐Quality Models , 1993 .

[27]  Inci Batmaz,et al.  A metamodeling methodology involving both qualitative and quantitative input factors , 2003, Eur. J. Oper. Res..

[28]  Masoud Rais-Rohani,et al.  A comparative study of metamodeling methods for multiobjective crashworthiness optimization , 2005 .

[29]  T. Koppel,et al.  Water Network Model Calibration Based on Grouping Pipes with Similar Leakage and Roughness Estimates , 2000 .

[30]  Zheng Y. Wu.  Water Quality Model Calibration by Means of Fast Messy Genetic Algorithm , 2005 .

[31]  Derya Sumer.  Impact of Data Collection and Calibration of Water Distribution Models on Model-Based Decisions , 2004 .

[32]  Thomas M. Walski,et al.  Performance of Automated Calibration for Water Distribution Systems , 2004 .

[33]  W. Grayman,et al.  Kinetics of chlorine decay , 1997 .