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.

Authors:

• Lihui Ma
• Kunlun Xin
• Suiqing Liu

Keywords:

• Metamodeling
• model calibration
• radial basisfunction
• water distribution system
• water quality model.

References:

[1] P. Boulos, T. Altman, P. Jarriage and F. Collevati. "Discrete Simulation
Approach for Network Water Quality Models." Journal of Water
Resources Planning And Management, vol 121(1), pp. 49-60, 1995.
[2] L. A. Rossman, P. F. Boulos and T. Altman. "Discrete Volume-Element
Method for Network Water-Quality Models." Water Resources Planning
and Management, vol 119(5), pp. 505-517, 1993.
[3] T. Walski, Z. Wu and W. Hartell. "Performance of Automated Calibration
for Water Distribution Systems". Proceedings Of The 2004 World Water
and Environmental Resources Congress, Salt Lake City, UT, USA,2004,
ASCE.
[4] S. Lingireddy and L. E. Ormsbee. "Optimal Network Calibration Model
Based on Genetic Algorithms". Proceedings of the 26th Annual Water
Resources Planning and Management Conference, Tempe, Arizona,
USA, 1999, ASCE.
[5] R. G├│mez, D. Salas and J. Saldarriaga. "Several Configurations and
Aggregation Levels in Neural Networks for Water Distribution Networks
Calibration". Proceedings Of The 2004 World Water and Environmental
Resources Congress, Salt Lake City, UT, USA,2004, ASCE.
[6] D. L. Boccelli and J. G. Uber. "Incorporating Spatial Correlation in a
Markov Chain Monte Carlo Approach for Network Model Calibration".
Proceedings of the 2005 World Water and Environmental Resources
Congress, Anchorage, Alaska, USA,2005, ASCE.
[7] B. G. Van and B. Waanders. "Application of Optimization Methods to
Calibration of Water Distribution Systems". Proceedings of The 2004
World Water and Environmental Resources Congress, Salt Lake City,
UT, USA,2004, ASCE.
[8] D. Salas, R. G├│mez and J. Saldarriaga. "Water Distribution Network
Calibration with Fuzzy Logic". Proceedings of the 2004 World Water and
Environmental Resources Congress, Salt Lake City, UT, USA,2004,
ASCE.
[9] L. Ainola, T. Koppel, K. Tiiter and A. Vassiljev. "Water Network Model
Calibration Based on Grouping Pipes with Similar Leakage and
Roughness Estimates". 2000 Joint Conference on Water Resources
Engineering and Water Resources Planning & Management,
Minneapolis, Minnesota, USA,2000, ASCE ; L. E. Ormsbee and S.
Lingireddy. "Calibrating Hydraulic Network Models " Amerian Water
Works Association, vol 89 (2), pp. 42-50, 1997; M. Greco and G. D.
Giudice. "New Approach to Water Distribution Network Calibration."
Journal of Hydraulic Engineering, vol 125(8), pp. 849-854, 1999; K. E.
Lansey, W. El-Shorbagy, I. Ahmed, J. Araujo and C. T. Haan.
"Calibration Assessment and Data Collection for Water Distribution
Networks." Journal of Hydraulic Engineering, vol 127(4), pp. 270-279,
2001.
[10] C. A. Bush and J. G. Uber. "Sampling Design and Methods for Water
Distribution Model Calibration." Journal of Water Resources Planning
and Management, vol 124(6), pp. 334-345, 1998; D. Y. Sumer, D. A. Sier,
J. Roach, S. Schladweiler, U. Yenal and K. Lansey. "Impact of Data
Collection and Calibration of Water Distribution Models on Model-Based
Decisions". Proceedings Of The 2004 World Water and Environmental
Resources Congress, Salt Lake City, UT, USA,2004, ASCE.
[11] P. J. Skipworth, J. Machell and A. Saul. "Explicit Consideration of Spatial
Flowrate Distribution in Network Model Calibration". Proceedings of the
World Water and Environmental Resources Congress, Orlando, Florida,
USA,2001, ASCE. Z. Y. Wu. "Optimal Calibration Method for Water
Distribution Water Quality Model." Environmental Science and Health
Part A, vol 41, pp. 1-16, 2006.
[12] Z. Y. Wu. "Water Quality Model Calibration by Means of Fast Messy
Genetic Algorithm". Proceedings of the 2005 World Water and
Environmental Resources Congress, Anchorage, Alaska, USA,2005,
ASCE.
[13] S. H. Maier, R. S. Powell and C. A. Woodwar. "Calibration and
Comparison of Chlorine Decay Models for a Test Water Distribution
System." Water Research, vol 34(8), pp. 2301-2309, 2000.
[14] J. J. Vasconcelos, L. A. Rossman, W. M. Grayman, P. F. Boulos and R. M.
Clark. "Kinetics of Chlorine Decay." American Water Works
Association, vol 89(7), pp. 54-65, 1997.
[15] R. A. Kilmera, A. E. Smithb and L. J. Shuman. "Computing Confidence
Intervals for Stochastic Simulation Using Neural Network Metamodels."
Computers & Industrial Engineering, vol 36, pp. 391-407, 1999.
[16] D. J. Fonseca, D. O. Navaresse and G. P. Moynihan. "Simulation
Metamodeling through Artificial Neural Networks." Engineering
Applications of Artificial Intelligence, vol 16, pp. 177-183, 2003.
[17] H. Fang, M. Rais-Rohani, Z. Liu and M. F. Horstemeyer. "A Comparative
Study of Metamodeling Methods for Multiobjective Crashworthiness
Optimization." Computers and Structures, vol 83 pp. 2121-2136, 2005.
[18] J. P. C. Kleijnen and R. G. Sargent. "A Methodology for Fitting and
Validating Metamodels in Simulation." European Journal of Operational
Research, vol 120, pp. 14-29, 2000.
[19] S. Tunali and I. Batmaz. "A Metamodeling Methodology Involving Both
Qualitative and Quantitative Input Factors." European Journal of
Operational Research, vol 150, pp. 437-450, 2003.
[20] M. F. Hussain, R. R. Barton and S. B. Joshi. "Metamodeling: Radial Basis
Functions, Versus Polynomials." European Journal of Operational
Research, vol 138, pp. 142-154, 2002.
[21] S. Lingireddy and L. E. Ormsbee. "Neural Networks in Optimal
Calibration of Water Distribution Systems." Artificial Neural Networks
for Civil Engineers: Advanced Features and Applications, vol, pp. 53-76,
1998.
[22] D. R. Broad, G. C. Dandy and H. R. Maier. "A Metamodeling Approach
to Water Distribution System Optimization". Proceedings Of The 2004
World Water and Environmental Resources Congress, Salt Lake City,
UT, USA,2004, ASCE; D. R. Broad, G. C. Dandy and H. R. Maier.
"Water Distribution System Optimization Using Metamodels." Journal of
Water Resources Planning and Management, vol 131(3) pp. 172-180,
2005a; D. R. Broad, H. R. Maier, G. C. Dandy and J. B. Nixon4.
"Estimating Risk Measures for Water Distribution Systems Using
Metamodels". Proceedings of the 2005 World Water and Environmental
Resources Congress, Anchorage, Alaska, USA,2005b, ASCE.
[23] S. Haykin. Neural Networks: A Comprehensive Foundation (2nd
Edition), Prentice-Hall, Inc,1999.
[24] A. Shahsavand and A. Ahmadpour. "Application of Optimal Rbf Neural
Networks for Optimization and Characterization of Porous Materials."
Computers and Chemical Engineering, vol 29 pp. 2134-2143, 2005.
[25] R. Jin, W. Chen and T. W. Simpson. "Comparative Studies of
Metamodelling Techniques under Multiple Modeling Criteria." Struct
Multidiscip Optim, vol 23, pp. 1-13, 2001.
[26] R. G. Regis and C. A. Shoemaker. "Constrained Global Optimization of
Expensive Black Box Functions Using Radial Basis Functions.Pdf."
Journal of Global optimization, vol 31(1), pp. 153-171, 2005.
[27] K. C. Giannakoglou, D. I. Papadimitriou and I. C. Kampolis.
"Aerodynamic Shape Design Using Evolutionary Algorithms and New
Gradient-Assisted Metamodels." Computer Methods in Applied
Mechanics and Engineering, vol 195 pp. 6312-6329, 2006.
[28] H. M. Gutmann. "A Radial Basis Function Method for Global
Optimization." Journal of Global Optimization, vol 19(3), pp. 201-227,
2001.
[29] H. Sarimveis, A. Alexandridis, S. Mazarakis and G. Bafas. "A New
Algorithm for Developing Dynamic Radial Basis Function Neural
Network Models Based on Genetic Algorithms." Computers and
Chemical Engineering, vol 28, pp. 209-217, 2004.
[30] R. A. Kilmer, A. E. Smith and L. J. Shuman. "Computing Confidence
Intervals for Stochastic Simulation Using Neural Network Metamodels."
Computers and Industrial Engineering, vol 36, pp. 391-407, 1999.
[31] R. M. Clark and R. C. Haught. "Characterizing Pipe Wall Demand:
Implications for Water Quality Modeling." Water Resources Planning and
Management, vol 131(3), pp. 208-217, 2005; R. M. Clark and R. C.
Haught. "Characterizing the Pipe Wall Demand for Free Chlorine in
Metallic Pipes". Proceedings Of The 2004 World Water and
Environmental Resources Congress, Salt Lake City, UT, USA, 2004,
ASCE.