• Tanayos Arisariyawong Department of Mechanical Engineering, Faculty of Engineering, Srinakharinwirot University.
  • Chaiwiwat Sudsaward Department of Mechanical Engineering, Faculty of Engineering, Srinakharinwirot University.
  • Nattapol Chokewiwattana Department of Mechanical Engineering, Faculty of Engineering, Srinakharinwirot University.
  • Worachat Sooksomkhan Department of Mechanical Engineering, Faculty of Engineering, Srinakharinwirot University.
  • Sommas Kaewluan Department of Mechanical Engineering, Faculty of Engineering, Srinakharinwirot University.


Biomass Burner, Dynamic Modeling, Data-Driven Modeling


 Biomass burner is widely used, since it is a renewable process energy eliminating agricultural wastes and reducing environmental problems. The burner temperature is an important parameter in determining the stability and efficiency of the biomass burner. Therefore, this research presents the flame temperature prediction of biomass burner using data-driven modeling. The inputs of the model were the temperature inside the gasifier, syngas temperature and the equivalence ratio. The output of the model was the flame temperature of the biomass burner. In this experiment, the predictive performance was compared between a nonlinear autoregressive network with exogenous inputs neural networks (NARXNN) and a response surface method model (RSM). From the experimental results shown that NARXNN provided better predictive results than RSM with mean squared error  = 0.6859 and correlation coefficient  = 0.9999 in the teaching data,  = 0.7979 and  = 0.9999 in the testing data. The improvement for the better prediction causes of using complicating structure of the model with the history data values of variables to increase the prediction accuracy.


Download data is not yet available.


A. C. Caputo, P. Mario, P. M. Pelagagge, and S. Federica. (2005). Economics of biomass energy utilization in combustion and gasification plants: effect of logisitic variable. Biomass and Bioenergy, 14(28), 35-51.

V. Yang, Sharifi, and J. Swithenbank. (2004). Effect of air flow rate and fuel moisture on the burning behaviours of biomass and simulated municipal solid wastes in packed beds. Fuel, 82(83), 1553-1562.

Babu, B.V., and Sheth, P.N. (2004). Modeling and simulation of downdraft biomass gasifier. In Proceedings of International Symposium & 57th Annual Session of IIChE in association with AIChE (CHEMCON-2004). pp. 170-176. Mumbai.

Helena L. Chum, and Ralph P. Overend. (2001). Biomass and renewable fuels. Fuel Processing Technology, 24(71), 187-195.

Schuster, G., Loffler, G., Weigl, K., and Hofbauer, H. (2001). Biomass steam gasification – an extensive parametric modeling study. Bioresource Technology, 10(77), 71-79.

Garcı´a-Bacaicoa, P., Serrano, S., Berrueco, C., and Ceamanos, J. (2004). Study on the gasification of sewage sludge for power production in a dual fueled engine. In The 2nd World Conf. and Technology Exhibition on Biomass for Energy, Industry and Climate Protection. Roma.

C.R. Altafini, P. Wander, and R. Barreto. (2003). Prediction of the working parameters of a wood waste gasifier through an equilibrium model. Energy Conversion and Management, 23(44), 2763-2777.

A.K. Sharma. (2011, February). Modeling and simulation of a downdraft biomass gasifier 1. Model development and validation. Energy Conversion and Management, 31(52), 1386-1396.

D. Baruah, and D.C. Baruah. (2014, November). Modeling of biomass gasification. Renewable and Sustainable Energy Reviews, 17(39), 806-815.

Del Rio-Chanona EA, Ahmed NR, Wagner J, Lu Y, Zhang D., and Jing K. (2019). Comparison of physics-based and data-driven modelling techniques for dynamic optimisation of fed-batch bioprocesses. Biotechnol Bioeng, 116(11), 2971-2982.

D. L. Marino, M. Anderson, K. Kenney, and M. Manic. (2018). Interpretable Data-Driven Modeling in Biomass Preprocessing. In The 11th International Conference on Human System Interaction (HSI). pp. 291-297. Poland.

Abolfazl Simorgh, Abolhassan Razminia, and Vladimir I. Shiryaev. (2019). Data-driven identification of a continuous type bioreactor. Energy Sources, 116(11), 2971-2982.

Cau G, Tola V., and Pettinau A. (2015). A steady state model for predicting performance of small‐scale up‐draft coal gasifiers. Fuel, 152, 3-12.

Mutlu AY, and Yucel O. (2018). An artificial intelligence based approach to predicting syngas composition for downdraft biomass gasification. Energy, 165, 895-901.

Satonsaowapak, Jittarat, Tosaphol Ratniyomchai, Thanatchai Kulworawanichpong, Padej Pao-la-or, Boonruang Marungsri, Anant Oonsivilai. (2010). Gasifier system identification for biomass power plants using response surface method. WSEAS Transactions on Systems, 9(6), 320-325.

Faridi Ibtihaj Khurram, Tsotsas Evangelos, Heineken Wolfram, Koegler Marcus, Kharaghan, Abdolreza. (2021). Dynamic Modeling for Temperature Prediction in a Fluidized Bed Biomass Gasification Process. SSRN. Retrieved November 15, 2021, from

Damijan Cerinski, Jakov Baleta, Hrvoje Mikulčić, Robert Mikulandrić, and Jin Wang. (2020). Dynamic modelling of the biomass gasification process in a fixed bed reactor by using the artificial neural network. Cleaner Engineering and Technology, 1(1), 1-12.

T. Pimparat, P. Tumruangsri, and S. Sandod. (2017). Development of Agricultural Residue Biomass Pellet Burner. Engineering Project Report, B.Eng. (Mechanical Engineering). Nakornnayok. Faculty of Engineering, Srinakharinwirot University.

E. Diaconescu. (2008). The Use of NARX Neural Networks to Predict Chaotic Time Series. WSEAS Transactions on computer research, 3(3), 182-191.

S. Haykin. (1994). Neural networks, A Comprehensive Foundation. New Jersey. Prentice Hall.




How to Cite

Arisariyawong, T. ., Sudsaward, C. ., Chokewiwattana, N. ., Sooksomkhan, W. ., & Kaewluan, S. . (2023). DATA-DRIVEN MODELING FOR TEMPERATURE PREDICTION OF BIOMASS BURNER. Srinakharinwirot University Journal of Sciences and Technology, 15(29, January-June), Article 249757 (1–14). Retrieved from