Estimation of Isentropic Compressibility of Biodiesel Using ELM Strategy: Application in Biofuel Production Processes

Isentropic compressibility is one of the significant properties of biofuel. On the other hand, the complexity related to the experimental procedure makes the detection process of this parameter time-consuming and hard. Thus, we propose a new Machine Learning (ML) method based on Extreme Learning Machine (ELM) to model this important value. A real database containing 483 actual datasets is compared with the outputs predicted by the ELM model. The results of this comparison show that this ML method, with a mean relative error of 0.19 and R-2 values of 1, has a great performance in calculations related to the biodiesel field. In addition, sensitivity analysis exhibits that the most efficient parameter of input variables is the normal melting point to determine isentropic compressibility.

Automated summary

By utilizing the Machine Learning method based on Extreme Learning Machine, the isentropic compressibility of biofuels can be accurately modeled. The comparison with real data sets demonstrates the excellent performance of this ML approach in biodiesel calculations, with an average relative error of 0.19 and R-2 values of 1. Additionally, sensitivity analysis reveals that the normal melting point is the most influential input variable for determining isentropic compressibility.