Identification and predictive control of spray tower system using artificial neural network and differential evolution algorithm

Increasing demands for high precision environmental protection measures regarding particulate matter (PM) emission from industrial productions and non-linear characteristics of spray tower system lead to the application of an intelligent control technique to adequately deal with these complexities. This includes the use of an artificial neural network (ANN) based predictive control strategy and differential evolution (DE) optimization algorithm to determines the optimal control signal, uk (liquid droplet size, dD) by minimizing the cost function such that the output is set below the allowable PM concentration. A recurrent neural network (RNN) based on non-linear autoregressive with exogenous inputs (NARX) model has been used to develop the dynamic model of the system. The data for the training was obtained from empirical model of a spray tower system which involved 500 data sets representing the process input and the output PM concentration. The control process was implemented using MATLAB code by considering two DE optimization strategies; DE/best/1/bin and DE/rand/1/bin. The effectiveness of the controllers was demonstrated for different iterations by tuning the control parameters such as the prediction horizon, weight factor and control horizon. From the control response, it can be seen that the controller for the DE/rand/1/bin does a very good job of controlling the PM below the WHO allowable emission rate of 20g/μm3.

[1]  Boris Kohnen,et al.  CFD‐Simulation von Nasswäschern Teil 1. Grundlagen und Implementierung in ein kommerzielles CFD‐Programm , 2012 .

[2]  Sandra Paterlini,et al.  Differential evolution and particle swarm optimisation in partitional clustering , 2006, Comput. Stat. Data Anal..

[3]  Phaedon C. Kyriakidis,et al.  Stochastic modeling of atmospheric pollution: a spatial time-series framework. Part II: application to monitoring monthly sulfate deposition over Europe , 2001 .

[4]  Petros Koutrakis,et al.  Prediction of daily fine particulate matter concentrations using aerosol optical depth retrievals from the Geostationary Operational Environmental Satellite (GOES) , 2012, Journal of the Air & Waste Management Association.

[5]  Nima Mohajerin,et al.  Identification and Predictive Control Using RecurrentNeural Networks , 2012 .

[6]  Lino O. Santos,et al.  A robust multi-model predictive controller for distributed parameter systems , 2012 .

[7]  Byeong-Kyu Lee,et al.  Evaluating the performance of a turbulent wet scrubber for scrubbing particulate matter , 2013, Journal of the Air & Waste Management Association.

[8]  P. Keshavarz,et al.  Simulation of a spray scrubber performance with Eulerian/Lagrangian approach in the aerosol removing process. , 2006, Journal of hazardous materials.

[9]  Chuanmin Chen,et al.  Investigation on Mercury Reemission from Limestone-Gypsum Wet Flue Gas Desulfurization Slurry , 2014, TheScientificWorldJournal.

[10]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[11]  Xiaolei Dong,et al.  A comparative study of differential evolution and genetic algorithms for optimizing the design of water distribution systems , 2012 .

[12]  Chin-Teng Lin,et al.  Nonlinear System Control Using Adaptive Neural Fuzzy Networks Based on a Modified Differential Evolution , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[13]  Goran Andersson,et al.  Model Predictive Control of Energy Storage including Uncertain Forecasts , 2011 .

[14]  Kaan Yetilmezsoy,et al.  Stochastic modeling approaches based on neural network and linear–nonlinear regression techniques for the determination of single droplet collection efficiency of countercurrent spray towers , 2007 .

[15]  M Gordon,et al.  Air-Pollution Control. , 1965, Science.

[16]  Ligang Zheng,et al.  Use of differential evolution in low NOx combustion optimization of a coal-fired boiler , 2010, 2010 Sixth International Conference on Natural Computation.

[17]  Byeong-Kyu Lee,et al.  Removal of ammonia and particulate matter using a modified turbulent wet scrubbing system , 2012 .

[18]  Kiejin Lee,et al.  Particle Removal Efficiency of Gravitational Wet Scrubber Considering Diffusion, Interception, and Impaction , 2001 .

[19]  Vesna Rankovic,et al.  Feedforward neural network and adaptive network-based fuzzy inference system in study of power lines , 2010, Expert Syst. Appl..