Downdraft gasifier identification via neural networks
Keywords:downdraft gasifier, identification, neural network, producer gas
This research presents the identification of producer gas resulting from the conversion of a given type of biomass in a downdraft gasifier, the use of a neural network (NN) to predict the identity for a given biomass type and the comparison of the NN prediction to measured results of biomass fuel conversions. Each type of biomass has different characteristics which affect the composition of the producer gas and thus its effective energy content. This research predicts the composition of the producer gas from the characteristics of the biomass by creating a mathematical model using a neural network. The model is then used to run simulations which are compared to actual measured values from experiments and then the accuracy of the simulations are verified with Simulink/MATLAB. The results show that the simulation predicts the CO content of producer gas with an average error of 1.73%, 7.01% for H2, and 1.58% for CH4. The simulation predicts the higher heating value with an average error of 0.73% and a lower heating value with an average error of 0.81%.
Beale, M. H., Hagan, M. T., & Demuth, H. B. (1992-2013 a). Neural Network ToolboxTM User’s Guide. The MathWorks, Inc.
Beale, M. H., Hagan, M. T., & Demuth, H. B. (1992-2013 b). Neural Network ToolboxTM Reference. The MathWorks, Inc.
Chenxi, S., Ruthut, L., & Sukanya,T. (2011). Coal conversion and utilization for reducing CO2 emissions from a power plant. Retrieved November 7, 2018, from https://www.ems.psu.edu/~elsworth/courses/egee580/2011/Final%20Reports/coal_igcc_report.pdf
Homduang, N., Dudsade, N., & Sasujit, K. (2015). Testing and Performance Analysis of Gasifier System for Grain Drying. The proceedings of the 8th Thailand Renewable Energy for Community Conference (pp.103-108). Faculty of Engineering. Rajamangala University of Technology Thanyaburi, Thailand.
Ingle, N. A., & Lakade, S. S. (2015). Design and development of downdraft gasifier to generate producer gas. Energy Procedia, 90, 423-431. Retrieved November 11, 2018, from https://www.sciencedirect.com/science/article/pii/S1876610216314199
Janpong, S., Areerak, K-L., & Areerak, K-N. (2011), A literature survey of neural network applications for shunt active power filters. International Journal of Electrical and Computer Engineering, 5(12) 1688-1694.
Jareansuk, N., & Patarakeadvit, T. (2015). Design of heat-recirculating system that affect combustion reaction in reduction zone for downdraft gasifier. . Retrieved November 10, 2018, from http://research.rmutsb.ac.th/fullpaper/2558/2558240240347.pdf
Jittabut, P., Waewsak, J., Mani, M., Buaphet, P., Panichayunon, P., & Namsan, U. (2010). Potential of producer gas production from sawdust by using steam injection and air injection: A case study of Phatthalung Province. Thaksin University Journal, 13(2), 56-64.
Kowkasikum, T. (1994). Power plant engineering. Technology Promotion Association (Thailand-Japan), Thailand.
Montuori, L., Vargas, C., & Alcázar-Ortega, M. (2015). Impact of the throat sizing on the operating arameters in an experimental fixed bed gasifier: Analysis, evaluation and testing. Renewable Energy, 83, 615-625.
Narongthong, K., & Sottigulanun, K. (2013). Solid node of bamboo gasifier. A project for the degree of Bachelor of Mechanical Engineering, Rangsit University, Thailand.
Sanjay Gupta, S. (2006). Technology of Biomass Gasification. New Delhi, India: Tata McGraw Hill Publishing Company Private Limited.
Sivakumar, S., Ragunathan, S., & Elango, N. (2014). Design and optimization analysis of 5 kWe Downdraft Gasifier. Journal of Chemical and Pharmaceutical Sciences, Special Issue 4: December 2014, 141-143.
Widrow, B., & Lehr, M. A. (1990). 30 years of adaptive neural networks: perceptron, Madaline, and backpropagation. Proceedings of The IEEE, 78(9), 1415-1442. DOI: 10.1109/5.58323
How to Cite
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.