The paper presents an analysis of the effect of shape of primary silicon crystals on the sizes of stresses and deformations in a surface layer of A390.0 alloy by Finite Elements Method (FEM). Analysis of stereological characteristics of the studied alloy, performed based on a quantitative metallographic analysis in combination with a statistical analysis, was used for this purpose. The presented simulation tests showed not only the deposition depth of maximum stresses and strains, but also allowed for determining the aforementioned values depending on the shape of the silicon crystals. The studied material is intended for pistons of internal combustion engines, therefore the analysis of the surface layer corresponded to conditions during friction in a piston-cylinder system of an internal combustion engine having power of up to 100 kW. The obtained results showed important differences in the values of stresses and strains up to 15% between various shape of the silicon crystals. Crystals with sharp edges caused higher stresses and deformation locally than those with rounded shapes.
Five models and methodology are discussed in this paper for constructing classifiers capable of recognizing in real time the type of fuel injected into a diesel engine cylinder to accuracy acceptable in practical technical applications. Experimental research was carried out on the dynamic engine test facility. The signal of in-cylinder and in-injection line pressure in an internal combustion engine powered by mineral fuel, biodiesel or blends of these two fuel types was evaluated using the vibro-acoustic method. Computational intelligence methods such as classification trees, particle swarm optimization and random forest were applied.