Toward estimating standard enthalpy of combustion of pure chemical compounds: extreme learning machine approach

One of the effective thermochemical properties in the determination of heat process efficiency is the combustion enthalpy changes during complete combustion of the compounds. According to the importance of this property in different processes, the main aim of this work is selected as the development of extreme learning machine (ELM) approach to predict the combustion enthalpy in terms of functional groups. To achieve this goal, a comprehensive data set containing 4,590 experimental enthalpy points is used for the preparation and validation of ELM. To investigate the accuracy of the ELM approach in the estimation of the enthalpy, various visual and statistical comparisons are used. These comparisons lead into R ² value of one and low error values for overall phase. The standard deviation, root mean squared error, and mean relative error for overall phase are determined to be 11.18, 14.92, and 0.28, respectively. The relative deviations between the estimated and actual enthalpy points are below 8%. According to the statistical and graphical results, ELM algorithm has great potential in the prediction of enthalpy of combustion for pure chemical materials.