A Hybrid Physics-Informed and Data-Driven Approach for Predicting the Fatigue Life of Concrete Using an Energy-Based Fatigue Model and Machine Learning

I began my research journey in 2021 when I had the opportunity to pursue a Master of Technology in Structural Engineering at a prestigious Indian institute, the Indian Institute of Technology (IIT) Mandi. During this time, I worked under the guidance of my former advisor, Dr. Sandip Kumar Saha, Associate Professor at IIT Mandi. My master’s dissertation focused on studying the effect of earthquake excitation direction on the floor response spectrum (FRS) in multi-story buildings. The primary objective was to simulate the behavior of residential buildings during earthquakes, analyze the influence of the excitation angle on the FRS, and develop a machine learning model to predict FRS based on specific building characteristics and the ground response spectrum. After completing my master’s degree in 2023, I worked as a Senior Project Scientist at IIT Delhi for three months with Prof. Vasant Matsagar, investigating the effect of a single tuned mass damper on the fatigue life of wind turbine towers. During this period, I was fortunate to meet Prof. Adnan Ibrahimbegovic, who offered me the opportunity to join the University of Technology of Compiègne, France, as a PhD student at the end of 2023. Currently, I am pursuing my PhD studies, where my primary scientific objective is to develop a predictive numerical model for composite structures to quantify the risk of fatigue failure under long-term dynamic loads, including extreme events.

My research began at UC Berkeley, where I collaborated with E.L. Wilson and R.L. Taylor to develop unified models for complex structures. Our 1990 paper on membranes, published in the International Journal for Numerical Methods in Engineering, became a foundational reference, with implementations in the widely used SAP software setting industry standards. Later, at EPFL in Switzerland, I advanced nonlinear structural analysis, notably finite rotations, with models integrated into R.L. Taylor’s FEAP software. As a professor in France, I led interdisciplinary research teams, fostering collaborations with leading institutions like UC Berkeley and EP Montreal. My team’s work on the multi-scale modeling of failure in massive structures under extreme conditions produced highly cited papers and awards such as the 2006 Engineering Computations Best Paper Award. All these works were the basis for my graduate textbook Nonlinear Solid Mechanics: Theoretical Formulations and Finite Element Solution Methods, which was published in French, English, and ex-Yugoslav languages. I have mentored 40 doctoral students and postdocs, many of whom are now in prestigious academic or industry roles worldwide. With 600+ publications, including 220+ peer-reviewed papers (h-index: 42, Scopus), my contributions have earned awards like the 2005 Humboldt Research Award and a 2022 nomination to the Academy of Europe.