Study of artificial neural network (ANN) for pyrolysis of sawdust

The effects of emissions caused by the excessive usage of fossil fuel on global warming has became a global concern as the negative impacts continuously increase. One of the most recognized alternatives to the fossil derived energy was biofuel, which has been perceived as more environmentally friendly and used as product against climate change. Artificial neural network, ANN is a highly intelligent system that has been widely used to predict and analyze certain processes. With the aid of ANN, it is possible to model the pyrolysis of sawdust before being industrially applied and implemented. The predicted data from ANN fitting model in Matlab was determined with validation, R² achieved at 0.9811 and the MSE error was indicated at small difference of 4.9747 in validation result under 36 epochs at 25 hidden neurons. The modeling of ANN has shown great performance and potential for the application on real process modeling and control in biofuel production process.