Identification of crashworthiness indicators of column energy absorbers with triggers in the form of cylindrical embossing on the lateral edges using artificial neural networks

The paper presents the possibility of neural network application in order to identify most advantageous design variants column energy absorbers terms achieved absorption indicators. Design absorber made standard thin-walled square aluminium profile with triggers form four identical cylindrical embossments on lateral edges were considered. These differ diameter trigger, its depth and position. geometrical parameters trigger are crucial for performance absorber. following indicators studied: PCF (Peak Crushing Force), MCF (Mean CLE (Crash Load Efficiency), SE (Stroke Efficiency) TE (Total Efficiency). On basis numerical studies validated by experimentation, a has been created aim predicting above-mentioned indices an acceptable error specified demonstrates that use effective multilayer perceptron can successfully speed up process, saving time multivariate time-consuming analyses.