Estimation of minimum ignition energy of explosive chemicals using gravitational search algorithm based support vector regression

Abstract

Adequate knowledge of minimum ignition energy (MIE) of a flammable chemical compound plays a significant role while handling and characterizing the hazardous materials and further ensures reliable ignition of fuel-air mixtures in many engines. Despite the significances of this parameter (MIE), its experimental determination is very dangerous, expensive and might be time consuming. The challenges associated with the experimental determination of minimum ignition energy are addressed in this present work through hybridization of gravitational search algorithm (GSA) with support vector regression (SVR) for estimating MIE using relatively few descriptors which include the number of carbon and hydrogen atoms as well as molecular weight of the compound. Novelties of this approach as compared with existing methods include (i) hybridization of GSA with SVR for modeling MIE for the first time, (ii) utilization of relatively few (three) descriptors and (iii) the ease with which the descriptors can be assessed. On the basis of root mean square error, the developed hybrid GSA-SVR shows superior performance as compared with the existing Beibei Wang et al. model with performance improvement of 24.03%. The accuracy of the proposed hybrid GSA-SVR model coupled with the ease of its implementation would definitely ensure quick estimation of MIE of compounds, prevent accidental explosion of hazardous chemicals in industry and enhance aviation safety.