M.Eng student, Rensselaer Polytechnic Institute, Department of Mechanical, Aerospace and Nuclear Engineering
Physics-informed machine learning for fatigue and lifing—developing surrogates that predict crack-growth rate and life across diverse geometries, materials, and load spectra with embedded Paris/Walker and fracture-mechanics constraints. I build reproducible FE/SIF data pipelines, emphasize calibrated uncertainty for defendable decisions, and automate FEA post-processing to accelerate lifing workflows. Validation against handbook/NASGRO-style references and analytical checks is a core focus.
Dimitrije Randjelovic is an M.Eng. candidate in Aerospace Engineering at Rensselaer Polytechnic Institute (RPI), affiliated with the Intelligent Structural Systems Laboratory (ISSL). His work centers on physics-informed machine learning for arbitrary crack growth, fatigue, and lifing, building on hands-on experience automating FEA post-processing and Strength–Life documentation on the Rotors Team at MTU Aero Engines North America. He is fluent in Python, MATLAB, Calculix/NX NASTRAN, Siemens NX, and SolidWorks, and leverages this stack to create reproducible analysis pipelines for lifing and fracture-mechanics workflows