Data-Driven Modeling for UGI Gasification Processes via an Enhanced Genetic BP Neural Network With Link Switches

In this brief, an enhanced genetic back-propagation neural network with link switches (EGA-BPNN-LS) is proposed to address a data-driven modeling problem for gasification processes inside United Gas Improvement (UGI) gasifiers. The online-measured temperature of crude gas produced during the gasification processes plays a dominant role in the syngas industry; however, it is difficult to model temperature dynamics via first principles due to the practical complexity of the gasification process, especially as reflected by severe changes in the gas temperature resulting from infrequent manipulations of the gasifier in practice. The proposed data-driven modeling approach, EGA-BPNN-LS, incorporates an NN-LS, an EGA, and the Levenberg-Marquardt (LM) algorithm. The approach cannot only learn the relationships between the control input and the system output from historical data using an optimized network structure through a combination of EGA and NN-LS but also makes use of the networks gradient information via the LM algorithm. EGA-BPNN-LS is applied to a set of data collected from the field to model the UGI gasification processes, and the effectiveness of EGA-BPNN-LS is verified.

[1]  Chan Ghee Koh,et al.  Modified genetic algorithm strategy for structural identification , 2006 .

[2]  Donghai Li,et al.  Active disturbance rejection control for the ALSTOM gasifier benchmark problem , 2013 .

[3]  Teresa Bernarda Ludermir,et al.  An Optimization Methodology for Neural Network Weights and Architectures , 2006, IEEE Transactions on Neural Networks.

[4]  Derong Liu,et al.  Data-Driven Neuro-Optimal Temperature Control of Water–Gas Shift Reaction Using Stable Iterative Adaptive Dynamic Programming , 2014, IEEE Transactions on Industrial Electronics.

[5]  Y. Cao.  NONLINEAR MODEL PREDICTIVE CONTROL FOR THE ALSTOM GASIFIER , 2006 .

[6]  Zhuo Wang,et al.  From model-based control to data-driven control: Survey, classification and perspective , 2013, Inf. Sci..

[7]  J. C. Bruno,et al.  Artificial neural network models for biomass gasification in fluidized bed gasifiers. , 2013 .

[8]  Sophia Kluge,et al.  Coal Gasification And Its Applications , 2016 .

[9]  T. Srinivas,et al.  Thermodynamic Equilibrium Model and Exergy Analysis of a Biomass Gasifier , 2009 .

[10]  Andrew Pike,et al.  Alstom Benchmark Challenge II on Gasifier Control , 2006 .

[11]  Rich Caruana,et al.  Overfitting in Neural Nets: Backpropagation, Conjugate Gradient, and Early Stopping , 2000, NIPS.

[12]  Hao Yu,et al.  Improved Computation for Levenberg–Marquardt Training , 2010, IEEE Transactions on Neural Networks.

[13]  B. Babu,et al.  Modeling and simulation of reduction zone of downdraft biomass gasifier : Effect of char reactivity factor , 2006 .

[14]  Shiro Usui,et al.  Mutation-based genetic neural network , 2005, IEEE Transactions on Neural Networks.

[15]  Peter J. Angeline,et al.  An evolutionary algorithm that constructs recurrent neural networks , 1994, IEEE Trans. Neural Networks.

[16]  Denny K. S. Ng,et al.  A hybrid optimisation model for the synthesis of sustainable gasification-based integrated biorefinery , 2012 .

[17]  Hak-Keung Lam,et al.  Tuning of the structure and parameters of a neural network using an improved genetic algorithm , 2003, IEEE Trans. Neural Networks.

[18]  Leonardo Tognotti,et al.  Assessment of syngas composition variability in a pilot-scale downdraft biomass gasifier by an extended equilibrium model. , 2013, Bioresource technology.

[19]  B. Kulkarni,et al.  Development of data-driven models for fluidized-bed coal gasification process , 2012 .

[20]  Erwin Bolthausen,et al.  BERNOULLI'S LAW OF LARGE NUMBERS , 2013, ASTIN Bulletin.

[21]  Ligang Zheng,et al.  Comparison of Shell, Texaco, BGL and KRW gasifiers as part of IGCC plant computer simulations , 2005 .

[22]  A. Belghit,et al.  A two phase model of high temperature steam-only gasification of biomass char in bubbling fluidized bed reactors using nuclear heat , 2011 .

[23]  Fu Zhao,et al.  Modelling coal gasification with a hybrid neural network , 1997 .

[24]  B. Meyer,et al.  Numerical simulation of coal gasification at circulating fluidised bed conditions , 2007 .

[25]  Gao Shi-wang.  Development status and tendency of coal gasification technology with dry coal feed in China , 2004 .

[26]  Germano Lambert-Torres,et al.  A genetic-based neuro-fuzzy approach for modeling and control of dynamical systems , 1998, IEEE Trans. Neural Networks.

[27]  M. Michelini,et al.  A two-phase one-dimensional biomass gasification kinetics model , 2001 .

[28]  Gwo-Ruey Yu,et al.  Quantum-Based Algorithm for Optimizing Artificial Neural Networks , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[29]  John R. Bunt,et al.  Identification of the reaction zones occurring in a commercial-scale Sasol–Lurgi FBDB gasifier , 2008 .

[30]  Carlos Roberto Altafini,et al.  Prediction of the working parameters of a wood waste gasifier through an equilibrium model , 2003 .

[31]  Derong Liu,et al.  Adaptive Dynamic Programming for Optimal Tracking Control of Unknown Nonlinear Systems With Application to Coal Gasification , 2014, IEEE Transactions on Automation Science and Engineering.

[32]  L. T. Fan,et al.  Mathematical model for the fluid-bed gasification of biomass materials. Application to feedlot manure , 1981 .

[33]  G. Astolfi,et al.  Application of a New Dataset Selection Procedure for the Prediction of the Syngas Composition of a Gasification Plant , 2012 .

[34]  A. Ghaly,et al.  Two phase biomass air-steam gasification model for fluidized bed reactors: Part I-model development , 2002 .

[35]  Tung-Kuan Liu,et al.  Tuning the structure and parameters of a neural network by using hybrid Taguchi-genetic algorithm , 2006, IEEE Trans. Neural Networks.

[36]  Dong Ling Tong,et al.  Genetic Algorithm-Neural Network (GANN): a study of neural network activation functions and depth of genetic algorithm search applied to feature selection , 2010, Int. J. Mach. Learn. Cybern..

[37]  J. Werther,et al.  Experimental investigation and modeling of gasification of sewage sludge in the circulating fluidized bed , 2005 .

[38]  Ching-Chih Tsai,et al.  Parallel Elite Genetic Algorithm and Its Application to Global Path Planning for Autonomous Robot Navigation , 2011, IEEE Transactions on Industrial Electronics.

[39]  Xin Yao,et al.  Evolutionary programming made faster , 1999, IEEE Trans. Evol. Comput..

[40]  Xiukun Yang,et al.  Use of genetic artificial neural networks and spectral imaging for defect detection on cherries , 2000 .

[41]  Xi Chen,et al.  Dynamic modeling and simulation of shell gasifier in IGCC , 2011 .