Hybrid modeling scheme for PM concentration prediction of electrostatic precipitators

Abstract A hybrid modeling scheme for electrostatic precipitators (ESPs) integrating particulate matter (PM) removal mechanism and the data-driven compensation method is presented in this article. The structure of the training and coupling method for the mechanism model, which considers electrodynamics, including corona discharging, particle charging, and removal, and the data-driven method that was trained based on operation data to compensate for the distortion and flaw of the mechanism model was constructed. Design parameters and operation data of an ESP in a coal-fired power plant were collected for model training, and prediction performances were compared. Different combinations of correction factors, including exponential, proportional, and bias, were studied. The form with the highest prediction R2 of 0.889 on the training set and 0.867 on the validation set was chosen as the mechanism part of the model. Deep neural networks with the highest R2 of 0.885 on the training set and 0.857 on the validation set were also trained as a comparison group. The performance of the hybrid model achieved a R2 of 0.933 on the training set and 0.887 on the validation set and outperformed the mechanism and data-driven models, thereby indicating that the hybrid modeling method could enhance prediction performance while maintaining the generalization capability of the PM removal mechanism in ESP.

[1]  Walther Deutsch,et al.  Bewegung und Ladung der Elektrizitätsträger im Zylinderkondensator , 1922 .

[2]  Mehdi Khashei,et al.  A novel hybrid classification model of artificial neural networks and multiple linear regression models , 2012, Expert Syst. Appl..

[3]  K. Cen,et al.  Characteristics of negative DC corona discharge in a wire–plate configuration at high temperatures , 2015 .

[4]  Gene Cooperman.  A unified efficiency theory for electrostatic precipitators , 1984 .

[5]  Chuen-Tinn Tsai,et al.  The Predictive Method for the Submicron and Nano-Sized Particle Collection Efficiency of Multipoint-to-Plane Electrostatic Precipitators , 2013 .

[6]  Qiang Yao,et al.  Evaluation of various particle charging models for simulating particle dynamics in electrostatic precipitators , 2010 .

[7]  Chuen-Jinn Tsai,et al.  A Modified Deutsch-Anderson Equation for Predicting the Nanoparticle Collection Efficiency of Electrostatic Precipitators , 2012 .

[8]  A. Mizuno,et al.  Electrostatic precipitation , 2000 .

[9]  Aibing Yu,et al.  Toward the Development of an Integrated Multiscale Model for Electrostatic Precipitation , 2013 .

[10]  J. Porteiro,et al.  Three-dimensional model of electrostatic precipitators for the estimation of their particle collection efficiency , 2016 .

[11]  K. Cen,et al.  An experimental study on the effects of temperature and pressure on negative corona discharge in high-temperature ESPs , 2016 .

[12]  Chao Chen,et al.  A hybrid model for wind speed prediction using empirical mode decomposition and artificial neural networks , 2012 .

[13]  Manfred Morari,et al.  Hybrid Model Predictive Control of the Step-Down DC–DC Converter , 2008, IEEE Transactions on Control Systems Technology.

[14]  Jianzhou Wang,et al.  A hybrid model for PM₂.₅ forecasting based on ensemble empirical mode decomposition and a general regression neural network. , 2014, The Science of the total environment.

[15]  Tianyou Chai,et al.  Nonlinear multivariable adaptive control using multiple models and neural networks , 2007, Autom..

[16]  K. Cen,et al.  Particle migration and collection in a high-temperature electrostatic precipitator , 2015 .

[17]  M. Mitchner,et al.  Experimental study of the effect of turbulent diffusion on precipitator efficiency , 1982 .

[18]  P. Lawless,et al.  Particle charging bounds, symmetry relations, and an analytic charging rate model for the continuum regime , 1996 .

[19]  C. Zheng,et al.  A stochastic simulation for the collection process of fly ashes in single-stage electrostatic precipitators , 2008 .

[20]  K. Cen,et al.  Electric agglomeration modes of coal-fired fly-ash particles with water droplet humidification , 2017 .

[21]  K. Cen,et al.  Numerical simulation on the fine particle charging and transport behaviors in a wire-plate electrostatic precipitator , 2016 .

[22]  W. Pan,et al.  Fine particulate matter emission and size distribution characteristics in an ultra-low emission power plant , 2016 .

[24]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[25]  M. Abdel-Salam,et al.  Corona-induced pressures, potentials, fields and currents in electrostatic precipitator configurations , 2007 .

[26]  Jen-Shih Chang,et al.  Corona discharge processes , 1991 .

[27]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[28]  Gaofeng Xu,et al.  Energy-saving optimal control for a factual electrostatic precipitator with multiple electric-field stages based on GA , 2013 .

[29]  K. W. Lee,et al.  Theoretical model of electrostatic precipitator performance for collecting polydisperse particles , 2001 .

[30]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[31]  Aibing Yu,et al.  Numerical Modelling of ESP for Design Optimization , 2015 .

[32]  Andreas Zintl,et al.  Electrostatic Precipitator Control Systems , 2010, IEEE Industry Applications Magazine.

[33]  Anne E Carpenter,et al.  Opportunities and obstacles for deep learning in biology and medicine , 2017, bioRxiv.

[34]  Heng-Tze Cheng,et al.  Wide & Deep Learning for Recommender Systems , 2016, DLRS@RecSys.

[35]  Fine particle migration and collection in a wet electrostatic precipitator , 2017, Journal of the Air & Waste Management Association.

[36]  Junghui Chen,et al.  Data-driven sensor fault diagnosis systems for linear feedback control loops , 2017 .

[37]  Benito Navarrete,et al.  Dimensional analysis for assessing the performance of electrostatic precipitators , 2010 .

[38]  N. Grass,et al.  Fuzzy logic-based power control system for multi field electrostatic precipitators , 2000, Conference Record of the 2000 IEEE Industry Applications Conference. Thirty-Fifth IAS Annual Meeting and World Conference on Industrial Applications of Electrical Energy (Cat. No.00CH37129).

[39]  Jiayi Cao,et al.  Reinforcement learning-based real-time power management for hybrid energy storage system in the plug-in hybrid electric vehicle , 2018 .

[40]  Fu Xiao,et al.  A short-term building cooling load prediction method using deep learning algorithms , 2017 .

[41]  Shou-Nan Li,et al.  An efficient wet electrostatic precipitator for removing nanoparticles, submicron and micron-sized particles , 2014 .

[42]  Gene Cooperman,et al.  A New Current-Voltage Relation for Duct Precipitators Valid for Low and High Current Densities , 1981, IEEE Transactions on Industry Applications.

[43]  Zhao Zhibin,et al.  Investigations of the Collection Efficiency of an Electrostatic Precipitator with Turbulent Effects , 1994 .

[44]  K. Gnana Sheela,et al.  Neural network based hybrid computing model for wind speed prediction , 2013, Neurocomputing.