A Neural Network Model for Estimating the Bio-oil from the Pyrolysis of Waste

The purpose of this study is to estimate the bio-oil from the pyrolysis process of waste products in terms of moisture, constant carbon, volatile matter and ash. The results of 41 different studies were used to modeling. We use the neural network model as a policy tool in the evaluation and prediction bio-oil from the pyrolysis process of waste products. Statistical method was used to determine the optimal values of the neural network parameters. The results of comparisons between two Multi- Layer Perceptron (MLP) and Radial Basis Function (RBF) neural networks showed that the RBF has a high ability to estimate the bio-oil. The value of correlation coefficient between experimental and predicted bio-oil by RBF was equal to 0.99. The neural network evaluation results showed that it can be used as a tool to estimate the production of bio-oil and it has been used in bio-oil production management decisions.