Machine Learning Weather Soft-Sensor for Advanced Control of Wastewater Treatment Plants

Control of wastewater treatment plants (WWTPs) is challenging not only because of their high nonlinearity but also because of important external perturbations. One the most relevant of these perturbations is weather. In fact, different weather conditions imply different inflow rates and substance (e.g., N-ammonia, which is among the most important) concentrations. Therefore, weather has traditionally been an important signal that operators take into account to tune WWTP control systems. This signal cannot be directly measured with traditional physical sensors. Nevertheless, machine learning-based soft-sensors can be used to predict non-observable measures by means of available data. In this paper, we present novel research about a new soft-sensor that predicts the current weather signal. This weather prediction differs from traditional weather forecasting since this soft-sensor predicts the weather conditions as an operator does when controling the WWTP. This prediction uses a model based on past WWTP influent states measured by only a few physical and widely applied sensors. The results are encouraging, as we obtained a good accuracy level for a relevant and very useful signal when applied to advanced WWTP control systems.

[1]  Xiao Fan Wang,et al.  Soft sensing modeling based on support vector machine and Bayesian model selection , 2004, Comput. Chem. Eng..

[2]  Mahesh Pal,et al.  Random forest classifier for remote sensing classification , 2005 .

[3]  Francesco Corona,et al.  Data-derived soft-sensors for biological wastewater treatment plants: An overview , 2013, Environ. Model. Softw..

[4]  S. Svoronos,et al.  Control issues and challenges in wastewater treatment plants , 2006, IEEE Control Systems.

[5]  Αλέξανδρος Π. Αλεξανδρίδης.  Evolving RBF neural networks for adaptive soft-sensor design , 2015 .

[6]  Guohai Liu,et al.  Model optimization of SVM for a fermentation soft sensor , 2010, Expert Syst. Appl..

[7]  Z. Zou,et al.  Statistical regression modeling for energy consumption in wastewater treatment. , 2019, Journal of environmental sciences.

[8]  Raquel Dormido,et al.  Tackling the start-up of a reinforcement learning agent for the control of wastewater treatment plants , 2017, Knowl. Based Syst..

[9]  Pramod K. Varshney,et al.  Decision tree regression for soft classification of remote sensing data , 2005 .

[10]  Jorge Rodríguez,et al.  Rule-based diagnosis and supervision of a pilot-scale wastewater treatment plant using fuzzy logic techniques , 2002, Expert Syst. Appl..

[11]  Junfei Qiao,et al.  Model predictive control of dissolved oxygen concentration based on a self-organizing RBF neural network , 2012 .

[12]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[13]  Ulf Jeppsson,et al.  Benchmark Simulation Model no. 1 (BSM1) , 2008 .

[14]  Haizhen Yang,et al.  Prediction analysis of a wastewater treatment system using a Bayesian network , 2013, Environ. Model. Softw..

[15]  Bogdan Gabrys,et al.  Data-driven Soft Sensors in the process industry , 2009, Comput. Chem. Eng..

[16]  Hong Guo,et al.  Prediction of effluent concentration in a wastewater treatment plant using machine learning models. , 2015, Journal of environmental sciences.

[17]  Kris Villez,et al.  Soft-sensing with qualitative trend analysis for wastewater treatment plant control , 2018 .

[18]  N. Altman.  An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression , 1992 .

[19]  Contributions from M. Walpole.  The Millennium Development Goals Report , 2008 .

[20]  Majid Bagheri,et al.  Modeling and optimization of activated sludge bulking for a real wastewater treatment plant using hybrid artificial neural networks-genetic algorithm approach , 2015 .

[21]  P A Vanrolleghem,et al.  On-line monitoring equipment for wastewater treatment processes: state of the art. , 2003, Water science and technology : a journal of the International Association on Water Pollution Research.

[22]  Félix Hernández-del-Olmo,et al.  An emergent approach for the control of wastewater treatment plants by means of reinforcement learning techniques , 2012, Expert Syst. Appl..

[23]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

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

[25]  Hiromasa Kaneko,et al.  Estimation of predictive accuracy of soft sensor models based on data density , 2013 .

[26]  R. Vilanova,et al.  Economic optimization of Wastewater Treatment Plants using Non Linear Model Predictive Control , 2015, 2015 19th International Conference on System Theory, Control and Computing (ICSTCC).

[27]  Gregory F. Cooper,et al.  A Bayesian method for the induction of probabilistic networks from data , 1992, Machine Learning.

[28]  B. Holenda,et al.  Dissolved oxygen control of the activated sludge wastewater treatment process using model predictive control , 2008, Comput. Chem. Eng..

[29]  Yan-Lin He,et al.  Data driven soft sensor development for complex chemical processes using extreme learning machine , 2015 .

[30]  M. Pardo,et al.  Random forests and nearest shrunken centroids for the classification of sensor array data , 2008 .

[31]  H. D. Stensel,et al.  Wastewater Engineering: Treatment and Reuse , 2002 .

[32]  Sylvie Gillot,et al.  The COST Simulation Benchmark: Description and Simulator Manual , 2001 .

[33]  Orlando Belo,et al.  Wastewater Treatment Plant Performance Prediction with Support Vector Machines , 2013, ICDM.

[34]  Raquel Dormido,et al.  Energy and Environmental Efficiency for the N-Ammonia Removal Process in Wastewater Treatment Plants by Means of Reinforcement Learning , 2016 .

[35]  Mogens Henze,et al.  Activated sludge models ASM1, ASM2, ASM2d and ASM3 , 2015 .

[36]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[37]  Chang-won Kim,et al.  Evaluation of the k-nearest neighbor method for forecasting the influent characteristics of wastewater treatment plant , 2016, Frontiers of Environmental Science & Engineering.

[38]  F Hernández-Sancho,et al.  Energy saving in WWTP: Daily benchmarking under uncertainty and data availability limitations. , 2016, Environmental research.

[39]  J. B. Copp.  The COST Simulation Benchmark-Description and Simulator Manual , 2001 .

[40]  Wei Qiu,et al.  Fuzzy model-based predictive control of dissolved oxygen in activated sludge processes , 2014, Neurocomputing.

[41]  Ulf Jeppsson,et al.  Benchmarking of Control Strategies for Wastewater Treatment Plants , 2014 .