Model predictive control for chlorine dosing of drinking water treatment based on support vector machine model

Chlorine is the most common disinfectant used in drinking water treatment. To meet the desired disinfection level and restrict the formation of harmful disinfectant by-products, the chlorine dosage should be adjusted in real time to cope with the varying influent water quality and to ensure that the free chlorine residual (FCR) of the clear-water reservoir outlet is within the prescribed limits. This control objective is difficult to achieve by the conventional proportional integral derivative (PID) feedback controls or manual control because of the complicated dynamics of the chlorination process. This study proposes a model predictive control (MPC) scheme for chlorine dosing, in which FCR can be predicted by the support vector machine (SVM) model. Both of the simulation and experimental results show that the proposed MPC scheme has better control performance than the conventional PID feedback control scheme because of the SVM predictions being accurate and the MPC outperforming the PID, and that it can effectively stabilize the quality of treated water.

[1]  G. White The Handbook of Chlorination and Alternative Disinfectants , 1992 .

[2]  Desmond F. Lawler,et al.  Analyzing Disinfection Kinetics and Reactor Design: A Conceptual Approach Versus the SWTR , 1993 .

[3]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[4]  Federico Girosi,et al.  An Equivalence Between Sparse Approximation and Support Vector Machines , 1998, Neural Computation.

[5]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

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

[7]  B. Gao,et al.  Evaluation of aluminum-silicate polymer composite as a coagulant for water treatment. , 2002, Water research.

[8]  G. Craun,et al.  Update on the control of iGiardia/i in water supplies. , 2002 .

[9]  S. Joe Qin,et al.  A survey of industrial model predictive control technology , 2003 .

[10]  David A. Cornwell,et al.  Demonstrating Cryptosporidium Removal using spore monitoring at lime‐softening plants , 2003 .

[11]  Sayan Mukherjee,et al.  Choosing Multiple Parameters for Support Vector Machines , 2002, Machine Learning.

[12]  G. Goodwin,et al.  Finite constraint set receding horizon quadratic control , 2004 .

[13]  Mohamed Cheriet,et al.  Optimizing resources in model selection for support vector machines , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[14]  D. Reckhow,et al.  DBP formation during chlorination and chloramination: Effect of reaction time, pH, dosage, and temperature , 2008 .

[15]  F. Vagliasindi,et al.  Differential absorbance study of effects of temperature on chlorine consumption and formation of disinfection by-products in chlorinated water. , 2008, Water research.

[16]  U. von Gunten,et al.  Reactions of chlorine with inorganic and organic compounds during water treatment-Kinetics and mechanisms: a critical review. , 2008, Water research.

[17]  Yuan Ren,et al.  Determination of Optimal SVM Parameters by Using GA/PSO , 2010, J. Comput..

[18]  Mircea Vasile Cristea,et al.  MPC vs. PID. The advanced control solution for an industrial heat integrated fluid catalytic cracking plant , 2011 .

[19]  Zhou Xianmin A new method with high confidence for validation of computer simulation models of flight systems , 2012 .

[20]  Y. Hosaka Examination of Rechlorination at Water Supply Stations Using a Model for Residual Chlorine Consumption , 2012 .

[21]  No-Suk Park,et al.  Application of neuro-fuzzy PID controller for effective post-chlorination in water treatment plant , 2012 .

[22]  K. Terashima,et al.  Residual chlorine management based on quantitative estimation of chlorine consumption by inner wall surfaces of distribution pipes , 2012 .

[23]  Hongjie Chen,et al.  Comparison on landslide nonlinear displacement analysis and prediction with computational intelligence approaches , 2014, Landslides.

[24]  Daniel E. Quevedo,et al.  Stability Analysis of Quadratic MPC With a Discrete Input Alphabet , 2013, IEEE Transactions on Automatic Control.

[25]  M. R. Templeton,et al.  Chlorinated and nitrogenous disinfection by-product formation from ozonation and post-chlorination of natural organic matter surrogates. , 2014, Chemosphere.

[26]  W. Uhl,et al.  A variable reaction rate model for chlorine decay in drinking water due to the reaction with dissolved organic matter. , 2015, Water research.

[27]  S. Tesfamariam,et al.  Framework for optimizing chlorine dose in small- to medium-sized water distribution systems: A case of a residential neighbourhood in Lahore, Pakistan , 2015 .

[28]  Panagiotis D. Christofides,et al.  A method for handling batch-to-batch parametric drift using moving horizon estimation: Application to run-to-run MPC of batch crystallization , 2015 .

[29]  Dayou Liu,et al.  Evolving support vector machines using fruit fly optimization for medical data classification , 2016, Knowl. Based Syst..

[30]  Wei Wang,et al.  Predictive control of nonlinear continuous networked control systems with large time-varying transmission delays and transmission protocols , 2016, Autom..

[31]  Shreyas Sundaram,et al.  Sampling-based explicit nonlinear model predictive control for output tracking , 2016, 2016 IEEE 55th Conference on Decision and Control (CDC).

[32]  Cheng Soon Ong,et al.  Learning SVM in Kreĭn Spaces , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[33]  S.J.S. Sant'Anna,et al.  Comparing support vector machine contextual approaches for urban area classification , 2016 .

[34]  H. Furumai,et al.  Chlorine Dose Determines Bacterial Community Structure of Subsequent Regrowth in Reclaimed Water , 2016 .

[35]  Shiyou Yang,et al.  A Modified Particle Swarm Optimization Algorithm for Global Optimizations of Inverse Problems , 2016, IEEE Transactions on Magnetics.

[36]  Gregery T. Buzzard,et al.  Output-Tracking Quantized Explicit Nonlinear Model Predictive Control Using Multiclass Support Vector Machines , 2017, IEEE Transactions on Industrial Electronics.

[37]  Darko Zibar,et al.  Machine Learning Techniques for Optical Performance Monitoring From Directly Detected PDM-QAM Signals , 2017, Journal of Lightwave Technology.

[38]  Yangyang Chen,et al.  Research on parameter selection method for support vector machines , 2017, Applied Intelligence.

[39]  Vu C. Dinh,et al.  Support Vector Machine Informed Explicit Nonlinear Model Predictive Control Using Low-Discrepancy Sequences , 2017, IEEE Transactions on Automatic Control.

[40]  Jianping Yuan,et al.  Globally robust explicit model predictive control of constrained systems exploiting SVM‐based approximation , 2017 .

[41]  N. Graham,et al.  Predicting chloroform production from organic precursors. , 2017, Water research.

[42]  Wenjian Cai,et al.  Robust model predictive control of discrete nonlinear systems with time delays and disturbances via T–S fuzzy approach , 2017 .