Development of the Multifactorial Computational Models of the Solid Propellants Combustion by Means of Data Science Methods - Phase I

Abstract

In this paper, we present the results of usage of data science methods, in particular artificial neural networks, for the creation of new multifactor computational models for prediction of burn rate of the solid propellants (SP). The analytical system PolyAnalyst and analytical platform Loginom were used for the model creation. The particular model developed was for burn rate prediction of double base propellants with thermite additives, both nano and micro by means of training the ANN using experimental data published in scientific literature. The basis (script) of a creation of Data Wharehouse of SP combustion was developed. The Data Wharehouse can be supplemented by new data in automated mode and serve as a basis for creating new generalized combustion models of SP and thus the beginning of work in a new direction of combustion science, which the authors propose to call �Propellant Combustion Genome� (by analogy with a very famous Materials Genome Initiative (MGI)). Propellant Combustion Genome opens possibilities for accelerating the advanced propellants development.