Artificial neural network models for biomass gasification in fluidized bed gasifiers

b i o m a s s a n d b i o e n e r g y ( ) e2 Available online at www.sciencedirect.com http://www.elsevier.com/locate/biombioe Artificial neural network models for biomass gasification in fluidized bed gasifiers Maria Puig-Arnavat a, J Alfredo Herna´ndez b, Joan Carles Bruno a,*, Alberto Coronas a a Universitat Rovira i Virgili, Dept Eng Meca`nica, Av Paăsos Catalans 26, 43007 Tarragona, Spain Universidad Autonoma del Estado de Morelos, Centro de Investigacio´n en Ingenierı´a y Ciencias Aplicadas (CIICAp), Av Universidad No 1001 Col Chamilpa, 62209 Cuernavaca, Mexico b article info abstract Article history: Artificial neural networks (ANNs) have been applied for modeling biomass gasification Received April 2012 process in fluidized bed reactors Two architectures of ANNs models are presented; one for Received in revised form circulating fluidized bed gasifiers (CFB) and the other for bubbling fluidized bed gasifiers 16 November 2012 (BFB) Both models determine the producer gas composition (CO, CO2, H2, CH4) and gas Accepted 10 December 2012 yield Published experimental data from other authors has been used to train the ANNs Available online 28 January 2013 The obtained results show that the percentage composition of the main four gas species in producer gas (CO, CO2, H2, CH4) and producer gas yield for a biomass fluidized bed gasifier Keywords: can be successfully predicted by applying neural networks ANNs models use in the input Biomass layer the biomass composition and few operating parameters, two neurons in the hidden Gasification layer and the backpropagation algorithm The results obtained by these ANNs show high Artificial neural network agreement with published experimental data used R2 > 0.98 Furthermore a sensitivity Simulation analysis has been applied in each ANN model showing that all studied input variables are Fluidized bed important ª 2012 Elsevier Ltd All rights reserved Introduction Biomass gasification is a highly efficient and clean conversion process that converts different biomass feedstocks to a wide variety of products for various applications In this context, modern use of biomass is considered a very promising clean energy option for reducing energy dependency and greenhouse gas emissions; biomass is considered to be CO2-neutral Biomass gasification can be considered in advanced applications in developed countries, and also for rural electrification in isolated installations or in developing countries In addition, it is the only renewable energy source that can directly replace fossil fuels as it is widely available and allows continuous power generation and synthesis of different fuels and chemicals Gasification conversion process can be defined as a partial thermal oxidation, which results in a great proportion of gaseous products (carbon dioxide, hydrogen, carbon monoxide, water and other gaseous hydrocarbons), little quantities of char, ash and several condensable compounds (tars and oils) Air, steam or oxygen can be supplied to the reaction as gasifying agents The quality of gas produced varies according to the gasifying agent used and the operating conditions selected Consequently, it is necessary to simulate biomass gasification process for scale-up, industrial control strategies, performance calculation after modifying the operating conditions, etc Mathematical models aim to study the thermochemical processes during the gasification of the biomass and to evaluate the influence of the main input variables on the * Corresponding author Tel.: ỵ34 977257068; fax: ỵ34 977559691 E-mail addresses: maria.puig@urv.cat (M Puig-Arnavat), juancarlos.bruno@urv.cat (J.C Bruno) 0961-9534/$ e see front matter ª 2012 Elsevier Ltd All rights reserved http://dx.doi.org/10.1016/j.biombioe.2012.12.012 280 b i o m a s s a n d b i o e n e r g y ( ) e2 Input layer ( i) Table e Characteristics of input and output variables in the ANN model for CFB gasifiers Range Input variables for the ANNs Ash content of dry biomass (g kgÀ1) Moisture content of wet biomass (g kgÀ1) Carbon content of dry biomass (g kgÀ1) Oxygen content of dry biomass (g kgÀ1) Hydrogen content of dry biomass (g kgÀ1) Equivalence ratio (ER) (À) Gasification temperature (Tg) ( C) Output variables for the various ANNs Producer gas yield (at 298 K, 103 kPa), (m3 kgÀ1) Gas composition (volume fraction, dry basis) H2 content (%) CH4 content (%) CO2 content (%) CO content (%) i=1 Ash Hidden layer Output layer Weights IWj,i Moisture 4e33.4 35e220 476.6e529.9 383.8e435.5 54.3e78.6 0.19e0.64 701e861 LWk,j C j=1 ER producer gas composition and calorific value However, the operation of a biomass gasifier depends on several complex chemical reactions, including several steps like: pyrolysis, thermal cracking of vapors to gas and char, gasification of char, and partial oxidation of combustible gas, vapors and char Due to the complexity of the gasification process coupled with the sensitivity of the product’s distribution to the operating conditions; many idealized assumptions have to be made in the development of these models Different kinds of models have been implemented for gasification systems, including equilibrium, kinetic and artificial neural networks According to Villanueva et al [1], equilibrium models are considered a good approach when simulating entrained-flow gasifiers in chemical process simulators or for downdraft fixed-bed gasifiers, as long as high temperature and high gas residence time are achieved in the throat By contrast, updraft fixed-bed, dual fluidized-bed and stand-alone fluidized-bed gasifiers should be modeled by revised equilibrium models or, in some extreme cases, by detailed rate-flow models A detailed review of recent biomass gasification models is available elsewhere [2,3] (CO, CO2 ,H ,CH or Gas yield) k=1 H 1.72e3.30 3.00e7.30 1.20e4.60 13.94e18.30 6.90e21.40 Output O i=7 Tg j=2 b1j b2k biases Fig e ANN model structure to predict producer gas composition and gas yield from biomass gasification in a CFB gasifier Artificial neural networks (ANNs) have been extensively used in the field of pattern recognition; signal processing, function approximation and process simulation However, they almost have not been used in the field of biomass gasification modeling Only few references can be found in the literature covering this field [4e6] ANNs are useful when the primary goal is outcome prediction and important interactions of complex nonlinearities exist in a data set like for biomass gasification, because they can approximate arbitrary nonlinear functions One of the characteristics of modeling based on artificial neural networks is that it does not require the mathematical description of the phenomena involved in the process, and might therefore prove useful in simulating and up-scaling complex biomass gasification process Guo et al [4] developed a hybrid neural network model to predict the product yield and gas composition of biomass gasification in an atmospheric pressure steam fluidized bed gasifier They used as input variables the bed temperature and the stock residence time Taking into account only these two input Table e Characteristics of input and output variables in the ANN model for BFB gasifiers Range Input variables for the ANNs Ash content of dry biomass (g kgÀ1) Moisture content of wet biomass (g kgÀ1) Carbon content of dry biomass (g kgÀ1) Oxygen content of dry biomass (g kgÀ1) Hydrogen content of dry biomass (g kgÀ1) Equivalence ratio (ER) (À) Gasification temperature (Tg) ( C) Steam to dry biomass ratio (VB) (kg kgÀ1) Output variables for the various ANNs Producer gas yield (at 298 K, 103 kPa), (m3 kgÀ1) Gas composition (volume fraction, dry basis) H2 content (%) CH4 content (%) CO2 content (%) CO content (%) 5.5e11.0 62.8e250 458.9e505.4 411.1e471.8 56.4e70.8 0.19e0.47 700e900 0e0.04 1.17e3.42 4.97e26.17 2.40e6.07 9.82e18.60 10e29.47 Fig e ANN model structure to predict producer gas composition and gas yield from biomass gasification in a BFB gasifier b i o m a s s a n d b i o e n e r g y ( ) e2 Fig e Comparison of the experimental results with the results calculated by ANN for CFB gasifiers 281 282 b i o m a s s a n d b i o e n e r g y ( ) e2 variables, forced the authors to develop four ANNs, one for each biomass feedstock considered Even the results showed that the ANNs developed could reflect the real gasification process; it would have been more interesting to develop just one but more general model for the biomass gasifier in study and accounting for different biomass feedstocks Brown et al [5] developed a reaction model for computation of products compositions of biomass gasification in an atmospheric air gasification fluidized bed reactor They combined the use of an equilibrium model and ANN regressions for modeling the biomass gasification process Their objective was to improve the accuracy of equilibrium calculations and prevent the ANN model from learning mass and energy balances, thereby minimizing the experimental data requirements As a result, a complete stoichiometry was formulated, and corresponding reaction temperature difference parameters computed under the constraint of the nonequilibrium distribution of gasification products determined by mass balance and data reconciliation The ANN regressions related temperature differences to fuel composition and gasifier operating conditions This combination of equilibrium model and ANN was further investigated and improved by the same authors [6] Even though the model incorporates ANNs, it cannot be considered a pure ANN model for biomass gasification process because the most important part of the model is a stoichiometric equilibrium model In this study, two feed-forward ANNs models have been developed to simulate the biomass gasification process in bubbling and circulating fluidized bed gasifiers, respectively The aim is to obtain two models that can predict the producer gas composition and the gas yield from biomass composition and few operating parameters, like thermodynamic equilibrium models do, but avoiding the high complexity of kinetic models The experimental data reported and published by other authors has been used here to train the ANNs The resulting model predictions for different types of biomass, given by the neural networks, are investigated in detail Methods 2.1 Experimental data selection Since different kinds of biomass and different gasifiers have different gasification behavior, two ANN models are presented in this work The first one applies for circulating fluidized bed (CFB) gasifiers and the second one for bubbling fluidized bed (BFB) gasifiers Table e Weights and biases of the ANNs designed for the four major gas species of producer gas (CO, CO2, H2, CH4) and producer gas yield for ANN model for CFB gasifiers CO IWi,j À3.2006 À1.1408 LW1,j 5.4159 0.0722 À1.8333 CO2 IWi,j 1.7859 9.8078 LW1,j 4.6685 3.1087 9.1839 CH4 IWi,j 1.1889 1.4276 LW1,j 1.2490 À0.5638 À0.3493 À10.0337 À3.7749 0.4085 4.0413 À12.4537 5.0279 À2.3948 b1j À7.6506 2.1235 3.9112 À1.7017 2.6406 2.4613 3.9629 6.3563 H2 IWi,j À1.7403 À16.8436 LW1,j 3.0137 Producer gas yield IWi,j À6.8841 À6.4443 À5.7169 À1.6951 LW1,j À0.5083 0.3425 3.4878 24.2709 0.8185 1.2959 À1.9792 À2.3434 1.5775 À0.9014 3.8072 b2 12.9445 À0.9632 0.8495 1.5078 9.5719 b2 10.2800 0.6350 4.0890 À2.6040 À1.9226 b2 8.5215 2.7315 À2.5402 À4.0765 À6.6673 À7.8066 À20.5250 b2 7.8781 À0.7735 À18.7020 À3.7339 À3.6455 À9.9848 19.7080 b2 2.4497 À1.4279 À6.0075 5.3061 À0.1148 b1j 3.6063 0.0732 1.9819 À15.3984 4.4029 3.0161 b1j À3.8959 À5.2290 0.2984 0.8706 À3.3632 À3.6059 b1j 3.9094 17.6810 À1.3813 3.2875 b1j 14.6688 À0.8342 b i o m a s s a n d b i o e n e r g y ( ) e2 The selection of an appropriate set of variables for inclusion as inputs to the model is a crucial step in model development, as the performance of the final model is heavily dependent on the input variables used In this study, an extensive literature review was done to obtain experimental data that could be used to develop the ANNs models Due to the different properties and behavior of different biomasses, and to have more homogeneous data, only experimental data for wood gasification in atmospheric pressure and inert bed reactors was considered Data for circulating fluidized bed ANN model was obtained for air gasification of wood from Li et al [7] (cypress, hemlock and mixed sawdust) and van der Drift et al [8] (mixed wood) Published experimental data for bubbling fluidized bed reactors was found in the studies of Narva´ez et al [9] (pine sawdust), Campoy [10] (pellets), Kaewluan and Pipatmanomai [11] (rubber wood chips) and Lv et al [12] (pine sawdust) for air and airesteam gasification In both ANNs models, the data sets containing the information (the values of input and output variables) of different biomass gasification tests are small The data sets for CFB and BFB gasifiers contain the results of 18 and 36 tests, respectively Due to the small size of the data sets and after some preliminary validation tests and results from the literature [5,6]; 283 the number of input variables was reduced compared to the initial available ones Fixed carbon (FC) and volatile matter (VM) were considered as dependent variables because the FC ratio is proportional to both the H/C and O/C ratios [5,13,14] Considering that the gas species to be determined are CO, CO2, H2 and CH4; nitrogen and sulphur were not considered either as input variables In addition, their amount in wood is very low and, in some cases, almost negligible compared with the content of carbon (C), hydrogen (H) and oxygen (O) For this reason, the input layer for the CFB ANN model consists of seven variables: biomass moisture (MC), biomass content of ash, C, H and O, gasification temperature (Tg) and equivalence ratio (ER) In the case of BFB model, the operational variables considered for the input layer were the same than those for CFB gasifier plus another variable that stands for the ratio between the amount of steam injected and the biomass flowrate (VB) The characteristics of these input and output variables, obtained from published experimental data, are shown in Table for CFB gasifiers and in Table for BFB gasifiers 2.2 Artificial neural networks topology An artificial neural network is a system based on the operation of biological neural networks, a computational model inspired Fig e Relative impact (%) of input variables on the different outputs for the four main producer gas components and producer gas yield of the ANN model for CFB gasifiers 284 b i o m a s s a n d b i o e n e r g y ( ) e2 The outputs of each ANN were compared with targets from experimental data reported by other authors To minimize the error, the LavenbergeMarquardt backpropagation algorithm was used The system adjusted the weights of the internal connections to minimize errors between the network output and target output The performance of the different ANNs was statistically measured by RMSE and regression coefficient (R2), which were calculated with the experimental values and networks predictions in the natural neurons An ANN is composed of a large number of highly interconnected processing elements (neurons or nodes) working in unison to solve specific problems The neurons are grouped into distinct layers and interconnected according to a given architecture Each layer has a weight matrix, a bias vector and an output vector In this study, two ANNs models were developed in the Matlab environment using the Neural Network Toolbox [15] Fig and Fig illustrate the architecture of the models for CFB and BFB gasifiers, respectively Since there is no explicit rule to determine either the number of neurons in the hidden layer or the number of hidden layers, the trial and error method was applied to find the best solution by minimizing the Root Mean Square Error (RMSE) In this step of training, a study was carried out to determine the number of neurons in hidden layer which was considered to one and two neurons for both ANNs models The best obtained results (data not show) were considering two neurons in hidden layer (see Figs and 2) The ANNs models proposed in the present study consist in: 3.1 Proposed ANN model for circulating fluidized bed gasifiers Five neural networks with seven inputs, two neurons in the hidden layer and one output each, was found to be efficient in predicting producer gas composition as well as gas yield for CFB gasifiers Experimental and simulated values for CO, CO2, H2, CH4, and gas yield were compared satisfactorily through a linear regression model ( y ẳ a$x ỵ b) for each The obtained regression coefficients (R2) are presented in Fig It can be seen how all R2 values are higher than 0.99 except for the case of H2 composition that it is 0.98 According to Verma et al [16] and El Hamzaoui et al [17] to satisfy the statistical test of intercept and slope; the interval between the highest and lowest values of the intercept must contain zero and the interval between the highest and lowest values of the slope must contain one The proposed ANNs passed the test with 99.8% of confidence level This test guarantees that whole ANN model, containing five ANNs, has a satisfactory level of confidence Table gives the obtained parameters (IWj,i, LW1,j, b1j, b2) of the best fit for neurons in the hidden layer for each of the five ANN developed in the CFB model These parameters were used in the proposed model to simulate the output values In consequence, the proposed ANN model follows Eq (2): - CFB gasifier model: five ANNs, one for each output (CO, CO2, H2, CH4 and gas yield) Each ANN has one input layer with seven variables (biomass moisture (MC), biomass content of ash, C, H and O, gasification temperature (Tg) and equivalence ratio (ER)), one hidden layer with two neurons and one output - BFB gasifier model: five ANNs with eight variables in the input layer (biomass moisture (MC), biomass content of ash, C, H and O, gasification temperature (Tg), equivalence ratio (ER) and injected steam ratio (VB)), one hidden layer with two neurons and one output each ANN To test the robustness and predict the ability of the models, in both ANNs models, the data sets were divided into training (80%) and validation-test subsets (20%), randomly selected from the available database Due to the small size of the database, validation and test sets were the same In all models, a hyperbolic tangent sigmoid function (tansig) was used in the hidden layer and the linear transfer aoutput ¼ function ( purelin) was used in the output layer The input parameters were normalized in the range of 0.2e0.8 So, any samples from the training and validation-test sets ( pi) were À scaled to a new value ðpi Þ using Eq (1) [19]: À À ÁÁ 0:6$ pi À pi À À Á À Á (1) pi ẳ 0:2 ỵ max pi pi À 13 C7 B C7 B    1C7 ỵ b2   6LW1;j $B A5 @ P iẳ7 jẳ1 ỵ b1j ỵ exp À 2$ i¼1 IWj;i $pi j¼2 X where pi is the normalized input variable and pi is the input variable Results and discussion (2) To assess the relative importance of the input variables, the evaluation process based on the neural net weight matrix and Garson equation [18] was used [17,19] Garson proposed an equation based on the partitioning of connection weights The numerator describes the sums of absolute products of weights for each input while the denominator represents the sum of all weights feeding into hidden unit, taking the absolute values The proposed equation, adapted to the present ANN topology, is as presented in Eq (3): b i o m a s s a n d b i o e n e r g y ( ) e2 Fig e Comparison of the experimental results with the results calculated by ANN for BFB gasifiers 285 286 b i o m a s s a n d b i o e n e r g y ( ) e2 00 1   C B B C Pj¼2 BB IWj;i  C  C C$ LW1;j C j¼1 BBPi¼7  A @@ A i¼1 IWj;i Ii ¼ 19 > >   > = B C C Pi¼7 Pj¼2 B BB IWj;i  C  C  LW $   B C B C P 1;j i¼1 j¼1 i¼7   > > @ A @ A > > i¼1 IWj;i > > ; : > > > < 00 in all cases (around 10%) except for CO2 where it is lower (4.9%) (3) where Ii is the relative influence of the ith input variable on the output variable The relative importance of the different input variables, for each ANN, calculated using Eq (3) is shown in Fig As it can be observed, all variables have a strong effect on the different outputs (CO, CO2, H2, CH4 and producer gas yield) It can be seen how variables that account for biomass composition (C, H, O) represent between 31.7% and 54.1% of the importance on CO, CO2, H2 and CH4 prediction However, this importance is reduced to 25% for producer gas yield On the other hand ER is the most important variable for producer gas yield prediction (37.6%) while it is also important for CO and H2 (31.2 and 30.2%) and less important for CO2 (11.5%) and CH4 (12.6%) Gasification temperature has a relative constant importance 3.2 Proposed ANN model for bubbling fluidized bed gasifiers In this model, the same procedure than that applied for CFB gasifiers has been followed The topology of the five ANNs integrated in the model is the same than in the previous case However, here, eight input variables are considered instead of seven because the model also accounts for airesteam gasification and not only for air gasification like in CFB gasifiers The obtained regression coefficients (R2) when comparing experimental and simulated values for CO, CO2, H2, CH4, and gas yield are presented in Fig All R2 values are higher than 0.99 except for the case of CO2 composition that it is 0.98 The limits for the statistical test of intercept and slope were calculated In all cases, the slope contained one and the intercept contained zero Consequently, the proposed ANNs also passed the test with 99.8% of confidence level Table e Weights and biases of the ANNs for the four major producer gas species (CO, CO2, H2, CH4) and producer gas yield for the ANN model for BFB gasifiers CO IWi,j À0.9005 À4.0218 LW1,j À33.7782 À22.8979 À2.0805 CO2 IWi,j 8.6144 À0.4782 LW1,j 3.5726 À1.1591 3.9688 CH4 IWi,j À27.6038 À56.8348 LW1,j À0.4665 30.0594 À245.3845 H2 IWi,j À2.6766 1.0173 LW1,j 13.8413 3.3581 0.0697 Producer gas yield IWi,j À5.3707 À4.1585 LW1,j À0.5422 À31.8927 À10.9772 0.3383 À0.6249 À10.2693 À1.9391 b1j 15.6788 3.6788 13.9051 À1.0988 À0.5125 0.6812 b2 12.3524 1.2177 À0.1740 À1.6145 0.5222 À9.1504 À5.2829 4.1321 1.2131 b1j 4.4389 À5.3372 À0.7413 18.4774 À12.6004 À3.4298 b2 13.4535 1.6067 À6.4298 4.8547 7.5909 À31.5068 194.6359 À31.9344 À29.1672 b1j À28.9205 À79.8145 49.1297 243.0979 85.5683 158.8235 b2 4.2972 10.8387 À82.2433 1.0029 103.3151 À1.7070 3.1264 0.7123 1.8738 b1j À1.3738 À0.7616 À1.0042 0.1026 À1.4738 1.6956 b2 13.6191 À0.0854 5.1339 2.3963 À6.0746 4.4783 2.1819 À23.2472 À5.8447 b1j 22.8709 6.0126 19.3959 6.7403 10.3177 4.6368 b2 1.7517 4.3555 4.3425 À12.2481 À1.4914 À39.6833 À2.6414 À1.0988 8.0323 1.2019 b i o m a s s a n d b i o e n e r g y ( ) e2 producer gas yield) Variables that account for biomass composition (C, H, O) always represent, like in CFB model, more than 25% of the importance of all studied outputs The importance of ER is reduced in all cases However, ER and VB together represent around 20% of importance in all cases except for CO Table shows the obtained parameters (IWj,i, LW1,j, b1j, b2) of the best fit for neurons in the hidden layer for each of the five ANN developed in the BFB model The proposed ANN model follows the same expression than the previous case but it is necessary to take into account that in this case eight inputs are considered as shown in Eq (4): aoutput 13 j¼2 C7 B X C7 B ẳ    1C7 ỵ b2   6LW1;j $B A5 @ P iẳ8 jẳ1 ỵ b1j ỵ exp 2$ iẳ1 IWj;i $pi The relative influence of the input variables was also evaluated using Eq (3) as in the CFB gasifiers’ model The relative importance of the different input variables for each ANN is shown in Fig As can be seen in the previous model, in this case, all of the variables also have a strong effect on the different outputs (CO, CO2, H2, CH4 and 287 (4) Results presented in this section and in Section 3.1 show how the percentage composition of the main four gas species in producer gas and producer gas yield for a biomass CFB or BFB gasifier can be successfully predicted by applying a neural network with two hidden neurons in the hidden layer and using backpropagation algorithm The results obtained by Fig e Relative impact (%) of input variables on the different outputs for the four main producer gas components and producer gas yield of the ANN model for BFB gasifiers 288 b i o m a s s a n d b i o e n e r g y ( ) e2 these ANNs show high agreement with published experimental data used: very good correlations (R2 > 0.98) in almost all cases and small RMSEs However, it is necessary to have in mind that ANN models are limited to a specified range of operating conditions for which they have been trained For this reason, a larger experimental database would be desirable to get improved models Conclusions Very few references can be found in the field of biomass gasification modeling The two ANN models developed in the present study for CFB and BFB gasifiers have shown the possibility that ANN may offer some contribution to research in this field Results presented show how the percentage composition of the main four gas species in producer gas and producer gas yield for a biomass CFB or BFB gasifier can be successfully predicted by applying a neural network with two hidden neurons in the hidden layer and using backpropagation algorithm The results obtained by these ANNs show high agreement with published experimental data used: very good correlations (R2 > 0.98) in almost all cases and small RMSEs According to analysis, all of the variables have a strong effect on the different outputs (CO, CO2, H2, CH4 and producer gas yield) for all ANN models Biomass composition (C, H, O) in CFB represents between 31.7% and 54.1% of the importance on CO, CO2, H2 and CH4 prediction and in BFB between 28.9% and 52.3% In the case of producer gas yield prediction, in CFB, the ER input is the most important variable (37.6%) while in BFB model decreases down to 10.8% This study is a first step and provides a good approach of the great potential of this kind of models in this field However, further additional experimental data to enlarge the database would be useful for further ANN training and improve the developed models Finally, these proposed ANNs models can be used to optimize and control the process Acknowledgments The authors would like to thank the European Commission for the financial support received as part of the European Project Polycity (Energy networks in sustainable communities) (TREN/ 05FP6EN/S07.43964/51381) Nomenclature ANN BFB b1, b2 CFB ER FC IW, LW MC VM artificial neural network bubbling fluidized bed biases circulating fluidized bed equivalence ratio (À) mass fraction% of fixed carbon in dry biomass matrix weight mass fraction% of H2O mass fraction% of volatile matter in dry biomass H I O C p À p R2 RMSE Tg VB mass fraction% of hydrogen content in dry biomass relative influence of an input variable on the output variable (%) mass fraction% of oxygen content in dry biomass mass fraction% of carbon content in dry biomass input to the ANN model normalized input to the ANN model correlation coefficient root mean square error gasification temperature ( C) steam to dry biomass mass ratio (kg kgÀ1) Subscripts i number of neurons in the input layer j number of neurons in the hidden layer k number of neurons in the output layer references [1] Villanueva AL, Gomez-Barea A, Revuelta E, Campoy M, Ollero P Guidelines for selection of gasifiers modelling strategies In: Proceedings of the 16th European Biomass Conference and Exhibition; 2008 June 2e6, Valencia, Spain ETA-Florence Renewable Energies; 2008 p 980e6 [2] Puig-Arnavat M, Bruno JC, Coronas A Review and analysis of biomass gasification models Renew Sustain Energ Rev 2010; 14(9):2841e51 [3] Go´mez-Barea A, Leckner B Modeling of biomass gasification in fluidized bed Prog Energy Combust Sci 2010;36(4):444e509 [4] Guo B, Li D, Cheng C, Lu Z, Shen Y Simulation of biomass gasification with a hybrid neural network model Bioresour Technol 2001;76(2):77e83 [5] Brown D, Fuchino T, Marechal F Solid fuel decomposition modelling for the design of biomass gasification systems In: Marquardt W, Pantelides C, editors Proceedings of the 16th European Symposium on Computer Aided Process Engineering and 9th International Symposium on Process Systems Engineering, July 9e13, 2006; GarmischPartenkirchen, Germany p 1661e1666 [6] Brown D, Fuchino T, Marechal F Stoichiometric equilibrium modelling of biomass gasification: validation of artificial neural network temperature difference parameter regressions J Chem Eng Jpn 2007;40(3):244e54 [7] Li XT, Grace JR, Lim CJ, Watkinson AP, Chen HP, Kim JR Biomass gasification in a circulating fluidized bed Biomass Bioenergy 2004;26(2):171e93 [8] van der Drift A, Van Doorn J, Vermeulen JW Ten residual biomass fuels for circulating fluidized-bed gasification Biomass Bioenergy 2001;20(1):45e6 [9] Narva´ez I, Orı´o A, Aznar MP, Corella J Biomass gasification with air in an atmospheric bubbling fluidized bed Effect of six operational variables on the quality of the produced raw gas Ind Eng Chem Res 1996;35(7):2110e20 [10] Campoy M Gasificacio´n de biomasa y residuos en lecho fluidizado: estudios en planta piloto [PhD thesis] University of Seville; 2009 [11] Kaewluan S, Pipatmanomai S Potential of synthesis gas production from rubber wood chip gasification in a bubbling fluidized bed gasifier Energy Convers Manage 2011;52(1): 75e84 [12] Lv P, Xiong ZH, Chang J, Wu C, Chen Y, Zhu J An experimental study on biomass airesteam gasification in a fluidized bed Bioresour Technol 2004;95(1):95e101 b i o m a s s a n d b i o e n e r g y ( ) e2 [13] van Krevelen DW Graphical-statistical method for the study of structure and reaction processes of coal Fuel 1950;29:269e84 [14] Jenkins BM, Baxter LL, Miles TR, Miles TR Combustion properties of biomass Fuel Process Technol 1998;54(1):17e46 [15] Demuth H, Beale M, Hagan M Neural network toolboxTM user’s guide Natick MA: The Mathworks Inc; 2010 [16] Verma SP, Andaverde J, Santoyo E Application of the error propagation theory in estimates of static formation temperatures in geothermal and petroleum boreholes Energy Convers Manage 2006;47(20):3659e71 289 [17] El Hamzaoui Y, Hernandez JA, Silva-Martinez S, Bassam A, Alvarez A, Lizama-Bahena C Optimal performance of COD removal during aqueous treatment of alazine and gesaprim commercial herbicides by direct and inverse neural network Desalination 2011;227(1e3):325e37 [18] Garson GD Interpreting neural-network connection weights AI Expert 1991;6:47e51 [19] Khataee AR, Mirzajani O UV/peroxydisulfate oxidation of C I Basic Blue 3: modeling of key factors by artificial neural network Desalination 2010;251(1e3):64e9