Data-driven soft-sensors for online monitoring of batch processes with different initial conditions

Abstract A soft-sensing methodology applicable to batch processes operated under changeable initial conditions is presented. These cases appear when the raw materials specifications differ from batch to batch, different production scenarios should be managed, etc. The proposal exploits the capabilities of the machine learning techniques to provide practical soft-sensing approach with minimum tuning effort in spite of the fact that the inherent dynamic behavior of batch systems are tracked through other online indirect measurements. Current data modeling techniques have been also tested within the proposed methodology to demonstrate its advantages. Two simulation case-studies and a pilot-plant case-study involving a complex batch process for wastewater treatment are used to illustrate the problem, to assess the modeling approach and to compare the modeling techniques. The results reflect a promising accuracy even when the training information is scarce, allowing significant reductions in the cost associated to batch processes monitoring and control.

[1]  I. Grossmann,et al.  An algorithm for the use of surrogate models in modular flowsheet optimization , 2008 .

[2]  O. B. Ayodele,et al.  Artificial Neural Networks, Optimization and Kinetic Modeling of Amoxicillin Degradation in Photo-Fenton Process Using Aluminum Pillared Montmorillonite-Supported Ferrioxalate Catalyst , 2012 .

[3]  Joos Vandewalle,et al.  Predictive Control Using Fuzzy Models Applied to a Steam Generating Unit , 1998 .

[4]  Sten Bay Jørgensen,et al.  A systematic approach for soft sensor development , 2007, Comput. Chem. Eng..

[5]  Mohamed Meselhy Eltoukhy,et al.  The use of artificial neural network (ANN) for modeling of COD removal from antibiotic aqueous solution by the Fenton process. , 2010, Journal of hazardous materials.

[6]  Orlando M. Alfano,et al.  Kinetic study of the photo-Fenton degradation of formic acid: Combined effects of temperature and iron concentration , 2009 .

[7]  Sanjeev S. Tambe,et al.  Soft-sensor development for fed-batch bioreactors using support vector regression , 2006 .

[8]  Roberto Guardani,et al.  Modeling the kinetics of a photochemical water treatment process by means of artificial neural networks , 1999 .

[9]  Dale E. Seborg,et al.  Optimal selection of soft sensor inputs for batch distillation columns using principal component analysis , 2005 .

[10]  G. Matheron.  Principles of geostatistics , 1963 .

[11]  Moisès Graells,et al.  Modeling and Simulation of Complex Nonlinear Dynamic Processes Using Data Based Models: Application to Photo-Fenton Process , 2015 .

[12]  Luiz Augusto da Cruz Meleiro,et al.  ANN-based soft-sensor for real-time process monitoring and control of an industrial polymerization process , 2009, Comput. Chem. Eng..

[13]  Dražen Slišković,et al.  Adaptive soft sensor for online prediction and process monitoring based on a mixture of Gaussian process models , 2013, Comput. Chem. Eng..

[14]  Timothy Masters,et al.  Practical neural network recipes in C , 1993 .

[15]  D. Bonvin,et al.  Optimization of batch reactor operation under parametric uncertainty — computational aspects , 1995 .

[16]  Antonio Durán,et al.  Neural networks simulation of photo-Fenton degradation of reactive blue 4 , 2006 .

[17]  Lei Wu,et al.  Adaptive soft sensor modeling framework based on just-in-time learning and kernel partial least squares regression for nonlinear multiphase batch processes , 2014, Comput. Chem. Eng..

[18]  Li Wang,et al.  Adaptive Soft Sensor Development Based on Online Ensemble Gaussian Process Regression for Nonlinear Time-Varying Batch Processes , 2015 .

[19]  J Kocijan,et al.  Application of Gaussian processes for black-box modelling of biosystems. , 2007, ISA transactions.

[20]  Fatiha Souahi,et al.  Experimental study and artificial neural network modeling of tartrazine removal by photocatalytic process under solar light. , 2017, Water science and technology : a journal of the International Association on Water Pollution Research.

[21]  O. Nelles.  Nonlinear System Identification: From Classical Approaches to Neural Networks and Fuzzy Models , 2000 .

[22]  Donald R. Jones,et al.  Efficient Global Optimization of Expensive Black-Box Functions , 1998, J. Glob. Optim..

[23]  Sang W. Joo,et al.  Modeling and optimization of photocatalytic/photoassisted-electro-Fenton like degradation of phenol using a neural network coupled with genetic algorithm , 2014 .

[24]  A. Khataee,et al.  Photocatalytic degradation of ciprofloxacin by synthesized TiO2 nanoparticles on montmorillonite: Effect of operation parameters and artificial neural network modeling , 2015 .

[25]  Nicodemo Di Pasquale,et al.  Optimization Algorithms in Optimal Predictions of Atomistic Properties by Kriging. , 2016, Journal of chemical theory and computation.

[26]  Marianthi G. Ierapetritou,et al.  Feasibility and flexibility analysis of black-box processes Part 1: Surrogate-based feasibility analysis , 2015 .

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

[28]  Thomas J. Santner,et al.  The Design and Analysis of Computer Experiments , 2003, Springer Series in Statistics.

[29]  M. Reuss,et al.  A mechanistic model for penicillin production , 2007 .

[30]  M. Ierapetritou,et al.  A kriging method for the solution of nonlinear programs with black‐box functions , 2007 .

[31]  A. Oladipo,et al.  High-Performance Nanocatalyst for Adsorptive and Photo-Assisted Fenton-Like Degradation of Phenol: Modeling Using Artificial Neural Networks , 2017 .

[32]  Robert Gustavsson,et al.  Control of specific carbon dioxide production in a fed-batch culture producing recombinant protein using a soft sensor. , 2015, Journal of biotechnology.

[33]  Antonio Espuña,et al.  Data-Driven Dynamic Modeling of Batch Processes Having Different Initial Conditions and Missing Measurements , 2017 .

[34]  Runze Li,et al.  Design and Modeling for Computer Experiments , 2005 .

[35]  A. O'Hagan,et al.  Bayesian calibration of computer models , 2001 .

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

[37]  Liwei Wang,et al.  A new sensitivity-based adaptive control vector parameterization approach for dynamic optimization of bioprocesses , 2016, Bioprocess and Biosystems Engineering.

[38]  Eva Balsa-Canto,et al.  Dynamic optimization of bioprocesses: efficient and robust numerical strategies. , 2005, Journal of biotechnology.

[39]  M. Graells,et al.  Photonic efficiency of the photodegradation of paracetamol in water by the photo-Fenton process , 2014, Environmental Science and Pollution Research.

[40]  Andy J. Keane,et al.  Recent advances in surrogate-based optimization , 2009 .

[41]  Bruce E. Ankenman,et al.  Comparison of Gaussian process modeling software , 2016, 2016 Winter Simulation Conference (WSC).

[42]  D G Krige,et al.  A statistical approach to some mine valuation and allied problems on the Witwatersrand , 2015 .

[43]  Jack P. C. Kleijnen,et al.  Regression and Kriging metamodels with their experimental designs in simulation: A review , 2017, Eur. J. Oper. Res..

[44]  J. E. Cuthrell,et al.  Simultaneous optimization and solution methods for batch reactor control profiles , 1989 .

[45]  Messias Borges Silva,et al.  Prediction via Neural Networks of the Residual Hydrogen Peroxide used in Photo‐Fenton Processes for Effluent Treatment , 2007 .

[46]  A. O'Hagan,et al.  Curve Fitting and Optimal Design for Prediction , 1978 .

[47]  Joos Vandewalle,et al.  Fuzzy modeling and identification. A guide for the user , 1997 .

[48]  Bogdan Gabrys,et al.  Review of adaptation mechanisms for data-driven soft sensors , 2011, Comput. Chem. Eng..

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

[50]  Osvaldo Chiavone-Filho,et al.  Application of artificial neural network for modeling of phenol mineralization by photo-Fenton process using a multi-lamp reactor. , 2014, Water science and technology : a journal of the International Association on Water Pollution Research.

[51]  Jose A. Casas,et al.  Application of high-temperature Fenton oxidation for the treatment of sulfonation plant wastewater , 2015 .

[52]  Zoltan K. Nagy,et al.  Model based control of a yeast fermentation bioreactor using optimally designed artificial neural networks , 2007 .

[53]  Mehdi Ahmadi,et al.  Predicting Fenton modification of solid waste vegetable oil industry for arsenic removal using artificial neural networks , 2012 .

[54]  A. Khataee,et al.  Application of artificial neural networks for modeling of the treatment of wastewater contaminated with methyl tert-butyl ether (MTBE) by UV/H2O2 process. , 2005, Journal of hazardous materials.

[55]  Dongxiang Zhang,et al.  Soft Sensor Development Based on the Hierarchical Ensemble of Gaussian Process Regression Models for Nonlinear and Non-Gaussian Chemical Processes , 2016 .

[56]  A. Cabrera Reina,et al.  Modelling photo-Fenton process for organic matter mineralization, hydrogen peroxide consumption and dissolved oxygen evolution , 2012 .

[57]  S. A. Dadebo,et al.  Dynamic optimization of constrained chemical engineering problems using dynamic programming , 1995 .

[58]  Yiqi Liu,et al.  Development of multiple-step soft-sensors using a Gaussian process model with application for fault prognosis , 2016 .

[59]  A Durán,et al.  Dynamic behavior of hydroxyl radical in sono-photo-Fenton mineralization of synthetic municipal wastewater effluent containing antipyrine. , 2017, Ultrasonics sonochemistry.

[60]  Zengliang Gao,et al.  Just-in-time kernel learning with adaptive parameter selection for soft sensor modeling of batch processes , 2012 .

[61]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[62]  Sten Bay Jørgensen,et al.  Data-Driven Modeling of Batch Processes , 2003 .

[63]  Josiah C. Hoskins,et al.  Artificial neural network models for knowledge representation in chemical engineering , 1990 .

[64]  Moisès Graells,et al.  Dynamic kriging based fault detection and diagnosis approach for nonlinear noisy dynamic processes , 2017, Comput. Chem. Eng..

[65]  G. Uma,et al.  ANFIS based sensor fault detection for continuous stirred tank reactor , 2011, Appl. Soft Comput..

[66]  Bhaskar D. Kulkarni,et al.  Development of a soft sensor for a batch distillation column using support vector regression techniques , 2007 .

[67]  Ghydaa M. Jaid,et al.  The use of artificial neural network (ANN) for the prediction and simulation of oil degradation in wastewater by AOP , 2014, Environmental Science and Pollution Research.

[68]  Raphael T. Haftka,et al.  Surrogate-based Analysis and Optimization , 2005 .

[69]  Antonio Espuña,et al.  Applying Metamodels and Sequential Sampling for Constrained Optimization of Process Operations , 2014, ICAISC.

[70]  José A. Caballero,et al.  Rigorous design of distillation columns using surrogate models based on Kriging interpolation , 2015 .

[71]  Hiromasa Kaneko,et al.  Classification of the Degradation of Soft Sensor Models and Discussion on Adaptive Models , 2013 .

[72]  Jeongho Cho,et al.  Quasi-sliding mode control strategy based on multiple-linear models , 2007, Neurocomputing.

[73]  A. Fernández-Alba,et al.  Occurrence and persistence of organic emerging contaminants and priority pollutants in five sewage treatment plants of Spain: two years pilot survey monitoring. , 2012, Environmental pollution.

[74]  Pierantonio Facco,et al.  Moving average PLS soft sensor for online product quality estimation in an industrial batch polymerization process , 2009 .

[75]  Sarah Belkacem,et al.  Study of oxytetracycline degradation by means of anodic oxidation process using platinized titanium (Ti/Pt) anode and modeling by artificial neural networks , 2017 .