Artificial neural network based modelling approach for municipal solid waste gasification in a fluidized bed reactor

In this paper, multi-layer feed forward neural networks are used to predict the lower heating value of gas (LHV), lower heating value of gasification products including tars and entrained char (LHVp) and syngas yield during gasification of municipal solid waste (MSW) during gasification in a fluidized bed reactor. These artificial neural networks (ANNs) with different architectures are trained using the Levenberg-Marquardt (LM) back-propagation algorithm and a cross validation is also performed to ensure that the results generalise to other unseen datasets. A rigorous study is carried out on optimally choosing the number of hidden layers, number of neurons in the hidden layer and activation function in a network using multiple Monte Carlo runs. Nine input and three output parameters are used to train and test various neural network architectures in both multiple output and single output prediction paradigms using the available experimental datasets. The model selection procedure is carried out to ascertain the best network architecture in terms of predictive accuracy. The simulation results show that the ANN based methodology is a viable alternative which can be used to predict the performance of a fluidized bed gasifier.

[1]  Indranil Pan,et al.  Multi-gene genetic programming based predictive models for municipal solid waste gasification in a fluidized bed gasifier. , 2015, Bioresource technology.

[2]  Peter York,et al.  Optimisation of the predictive ability of artificial neural network (ANN) models: a comparison of three ANN programs and four classes of training algorithm. , 2005, European journal of pharmaceutical sciences : official journal of the European Federation for Pharmaceutical Sciences.

[3]  Indranil Pan,et al.  Incorporating uncertainty in data driven regression models of fluidized bed gasification: A Bayesian approach , 2016 .

[4]  Ali Reza Sepaskhah,et al.  Annual precipitation forecast for west, southwest, and south provinces of Iran using artificial neural networks , 2012, Theoretical and Applied Climatology.

[5]  Hefa Cheng,et al.  Municipal solid waste (MSW) as a renewable source of energy: current and future practices in China. , 2010, Bioresource technology.

[6]  A. Gómez-Barea,et al.  Modeling of biomass gasification in fluidized bed , 2010 .

[7]  Oliver Gohlke.  Efficiency of energy recovery from municipal solid waste and the resultant effect on the greenhouse gas balance , 2009, Waste management & research : the journal of the International Solid Wastes and Public Cleansing Association, ISWA.

[8]  Gang Xiao,et al.  Gasification characteristics of MSW and an ANN prediction model. , 2009, Waste management.

[9]  Petr Stehlík,et al.  Waste to energy – An evaluation of the environmental impact , 2010 .

[10]  Y Shen,et al.  Simulation of biomass gasification with a hybrid neural network model. , 2001, Bioresource technology.

[11]  Sumit Mukherjee,et al.  Identification of nonlinear systems from the knowledge around different operating conditions: A feed-forward multi-layer ANN based approach , 2012, 2012 2nd IEEE International Conference on Parallel, Distributed and Grid Computing.

[12]  Umberto Arena,et al.  Process and technological aspects of municipal solid waste gasification. A review. , 2012, Waste management.

[13]  Nemanja Stanisavljevic,et al.  Using ANN model to determine future waste characteristics in order to achieve specific waste management targets -case study of Serbia , 2011 .

[14]  Changqing Dong,et al.  Predicting the heating value of MSW with a feed forward neural network. , 2003, Waste management.

[15]  Helmut Rechberger,et al.  A new method to determine the ratio of electricity production from fossil and biogenic sources in waste-to-Energy plants. , 2007, Environmental science & technology.

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

[17]  T.,et al.  Training Feedforward Networks with the Marquardt Algorithm , 2004 .

[18]  Alberto Coronas,et al.  Review and analysis of biomass gasification models , 2010 .

[19]  Daniel Hoornweg,et al.  What a waste? : a global review of solid waste management , 2012 .

[20]  H. Meijer,et al.  Carbon-14 based determination of the biogenic fraction of industrial CO(2) emissions - application and validation. , 2010, Bioresource technology.

[21]  Soteris A. Kalogirou,et al.  Artificial neural networks in renewable energy systems applications: a review , 2001 .

[22]  Bo Leckner,et al.  Process aspects in combustion and gasification Waste-to-Energy (WtE) units. , 2015, Waste management.

[23]  Thomas Malkow,et al.  Novel and innovative pyrolysis and gasification technologies for energy efficient and environmentally sound MSW disposal. , 2004, Waste management.

[24]  P. Brunner,et al.  Waste to energy--key element for sustainable waste management. , 2015, Waste management.

[25]  Ni-Bin Chang,et al.  Solid waste management in European countries: a review of systems analysis techniques. , 2011, Journal of environmental management.

[26]  Chi Wai Hui,et al.  Process design and feasibility study for small scale MSW gasification , 2004 .

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

[28]  J V Tu,et al.  Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. , 1996, Journal of clinical epidemiology.

[29]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[30]  Prabir Basu,et al.  Biomass Gasification and Pyrolysis: Practical Design and Theory , 2010 .

[31]  Andrea Corti,et al.  A review of technologies and performances of thermal treatment systems for energy recovery from waste. , 2015, Waste management.

[32]  Sama Azadi,et al.  Verifying the performance of artificial neural network and multiple linear regression in predicting the mean seasonal municipal solid waste generation rate: A case study of Fars province, Iran. , 2016, Waste management.

[33]  Holger R. Maier,et al.  The effect of internal parameters and geometry on the performance of back-propagation neural networks: an empirical study , 1998 .

[34]  Shantanu Das,et al.  Artificial neural network based prediction of optimal pseudo-damping and meta-damping in oscillatory fractional order dynamical systems , 2012, IEEE-International Conference On Advances In Engineering, Science And Management (ICAESM -2012).

[35]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[36]  Dražen Lončar,et al.  Artificial neural network modelling approach for a biomass gasification process in fixed bed gasifiers. , 2014 .

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