ISBB IJSBB 2018, 1, 1. http://isbb.site/journal/index.php/ijsbb Prediction of biodiesel production from palm fatty acid distillate using artificial neural network Obie Farobie 1,* 1 Surfactant and Bioenergy Research Center, Bogor Agricultural University. Jl. Pajajaran No.1, Kampus IPB Baranangsiang Bogor 16144, Indonesia * Correspondence: obiefarobie@gmail.com Abstract: Sustainable and low cost feedstock, i.e. palm fatty acid distillate (PFAD) is one of potential source to be utilized in biodiesel industry. Non-catalytic biodiesel production using supercritical technology is considered as a promising method to treat feedstock containing high free fatty acid (FFA) such as PFAD owing to no catalyst needed and no sensitive to the presence of FFA. However, there has been no previous study to predict biodiesel production from PFAD. In this study, artificial neural network was used to predict biodiesel yield from PFAD for the first time. The experimental data of biodiesel yield conducted by varying 3 input factors, i.e. temperature, oil-to-methanol molar ratio, and residence time were used to elucidate artificial neural network model in order to predict biodiesel yield. The objective this study is to assess how accurately this artificial neural network model to predict biodiesel yield from PFAD conducted under supercritical methanol condition. The result shows that artificial neural network is a powerful tool for modeling and predicting biodiesel yield proven by a high value of coefficient of determination (R) of 0.999, 0.998, and 0.998 for training, validation, and testing, respectively. Using this approach, the highest biodiesel yield was determined of 1.00 mol/mol (corresponding to the actual biodiesel yield of 0.99 mol/mol) that was achieved at 270 °C, PFAD-to- methanol molar ratio of 1:6 within 20 min residence time. Keywords: artificial neural network; biodiesel; PFAD; supercritical ________________________________________________________________________________________ 1. Introduction Energy crisis and global warming have driven many researchers to search an alternative fuel. Biodiesel has a good potential to replace petroleum-derived diesel fuel owing to its biodegradability [1-2], low particulate matter and CO exhaust emission [3], and high flash point (˃ 130) [4]. Biodiesel production under supercritical conditions is a promising method to treat oil containing high free fatty acid (FFA) since transesterification of triglyceride and esterification of FFA occur simultaneously [5-9]. In addition, transesterification reaction can be proceeded within short reaction time as well as easier separation and purification steps [10-14]. The modeling of biodiesel production to predict the effect of process parameters such as residence time, temperature, and oil-to-reactant molar ratio on biodiesel yield have moved from the complex analytical equations, costly and time consuming trial and error searches to powerful and efficient methods. Artificial Neural Networks (ANN), one of the most widely technique to classify and to predict the response, has been proven to be far more effective at forecasting than more conventional linear techniques such as regression analysis. During the past few years, this method had been successfully applied in different areas of engineering and science due to its capability to analyze incomplete data [15-16]. However, there has been no study in ANN approach to predict biodiesel yield from PFAD. Hence, this study aims to predict biodiesel yield from PFAD under supercritical condition. In this study, three input factors consisted of residence time, temperature, and oil- to-methanol molar ratio, and one output response, biodiesel yield, were included into the optimization study as shown in Figure 1.