DCs

Yunfan Zhang

Originally from China, Yunfan obtained his Bachelor’s degree in Process Equipment and Control Engineering in 2019 from the China University of Petroleum (East China). He then finished his Diplom’s degree (equivalent to a Master’s degree) in 2023 in Mechanical Engineering with a specialization in Manufacturing Technology at Dresden University of Technology (TU Dresden). During this period, Yunfan worked as a research assistant at Fraunhofer Institute for Machine Tools and Forming Technology (IWU) and Helmholtz-Zentrum Dresden-Rossendorf (HZDR). He finished his Diplom’s thesis under the co-supervision of TU Dresden and HZDR, having the topic “High-Quality Reconstruction of Real Space Structures from X-ray Holography Using Conditional Wavelet Flow.” In this work, he developed a generative deep learning model for reverse image reconstruction.

In June 2024, Yunfan began his PhD journey at the Faculty of Civil Engineering and Geosciences at Delft University of Technology (TU Delft). His research is focused on “Uncertainty Quantification and Reduction for Industrial Critical Components Using Data-Driven Approaches.” This has the aim of enhancing the quality and reliability of manufacturing sectors by introducing the idea of uncertainty quantification and developing context-based machine learning algorithms. His work is funded by the APRIORI doctoral network for the first three years and by TU Delft for the final year.

Renan Barros

Renan was born and raised in Fortaleza, Brazil. He obtained his bachelor's degree in Civil Engineering in 2021 and his master's degree in 2023, both from the Universidade Federal do Ceará. His master's thesis proposed a novel NURBS-based general Quasi-3D kinematic theory to account for both material and geometric nonlinear effects in functionally graded plates. His past research efforts also include Isogeometric Analysis, other kinematic theories and multiple types of analysis. Renan started his PhD in TU Delft in May 2024 in the position "Uncertainty quantification of physics-based and machine learning models of critical industrial components", as Doctoral Candidate 2 of the Horizon Europe DN APRIORI project, linked to the Marie Sklodowska Curie Actions program.

Maedeh Kabiripoor

Maedeh Kabiripoor, from Iran, began her journey as a mechanical engineer. She started her academic path at Isfahan University of Technology, earning a Bachelor of Science in Mechanical Engineering from 2013 to 2018, focusing on Mechatronics. This foundation sparked her interest in sound and vibrations.

Driven by curiosity, Maedeh continued her studies at the same university, earning a master’s degree in mechanical engineering from 2019 to 2022. During this time, she explored the behavior of sound in metamaterials with different geometries. Guided by esteemed professors, she researched how various geometric and mechanical properties affect wave propagation, leading to the publication of one article and the submission of another paper.

Maedeh's professional journey from 2021 to 2024 allowed her to apply her academic knowledge to real-world challenges. She gained valuable experience in sound and audio tests while working for a major home appliance company in Iran, contributing to the development of advanced acoustic solutions. Her communication and teamwork skills were honed through active participation in university associations.

Currently, Maedeh is leading an exciting project aimed at advancing the industrial applications of metamaterials. She is developing strategies to measure the effects of local variations in density and geometry on the stop-band behavior of 3D-printed locally resonant metamaterials. By assessing the spread on the designed stopband location and width, she focuses on both acoustic and vibrational resonances. Her work involves quantifying uncertainties in geometry, density, and stiffness distributions, and creating design rules for different resonator geometries. Using Bayesian approaches, Maedeh is linking the nominal CAD design to performance, accounting for manufacturing uncertainties. This innovative approach promises significant advancements for the industrial applications of metamaterials.

Lorenzo Seghesio

Lorenzo, born and raised in Aosta, Italy, holds a Master's degree in Mechatronic Engineering (2022) and a Minor in Mechanical Engineering (2020) from Politecnico di Torino. During his Erasmus experience at California State University, Los Angeles, he completed his Master's thesis titled "System Integration, Localization, and Control Implementation for an Autonomous Mobile Service Robot." After graduation, he worked for a year and a half as a software design engineer for automotive applications at a company in Turin.

In January 2025, Lorenzo began his PhD at KU Leuven with the title "Quality Control within Injection Moulding Exploiting Data and Physical Models". He is the Doctoral Candidate number 5 in the APRIORI international consortium, funded by the Marie Skłodowska-Curie Actions programme.

Emily E Carvajal C

Emily E Carvajal C is a Research Engineer at Materialise HQ and enrolled as a PhD student at KU Leuven as DC6 within the framework of the Marie Curie Fellowship for the APRIORI project. Her main research interest is the use of AI/ML techniques for the analysis of multimodal and multidimensional data in multidisciplinary contexts. Her PhD research is focused on the use of data-driven models for first-time right metal additive manufacturing in part production workflow. The research is supervised by Dr. Michele Pavan and Professor Frank Naets.

Benham Firoozi

Behnam was born in Shiraz, Iran. He began his research career as a research assistant at Kharazmi University in Tehran (2014–2019), contributing to the nonlinear analysis of MEMS structures and energy harvesters. In 2019, he was awarded a fellowship to join the Vibration and Acoustic Laboratory (VAL) at Özyeğin University in Istanbul, where he earned his master’s degree in 2021. During his tenure at VAL (2019–2023), Behnam conducted his thesis on vibration-based damage detection in mechanical structures and participated in projects focused on optimization-based methods for unbalance detection in rotating machinery, optimal design of microchannel heat sinks, deep learning for energy forecasting, and vibration-based piezoelectric energy harvesting.

Over the course of his career, he has published five Q1 journal papers and served as a reviewer for high-impact journals in mechanical engineering and computer science, including IEEE/ASME Transactions on Mechatronics, Soft Computing, Engineering with Computers, and Scientific Reports. In December 2023, he joined the Solid and Computational Mechanics group in the Department of Materials and Production at Aalborg University, Denmark, under the Marie Skłodowska-Curie Actions program, where he is undertaking a project focused on vibration analysis and wave propagation in thin-walled structures.

Hirenkumar Patel

Hiren Patel completed his Master’s degree in Applied Mechanics from IIT Madras, India in 2020, where he focused on Reduced-Order Modeling and Vibration Control of Deterministic and Stochastic Systems. His research involved developing computationally efficient models, significantly reducing computational time for both deterministic and stochastic control systems.

During his master’s, Hiren worked as a Project Associate at ARDB, DRDO, where he contributed to FEA modeling of electromechanical systems and developed experimental setups for active vibration control using D-Space. This experience deepened his expertise in structural dynamics, vibration analysis, and numerical modeling.

In 2021, Hiren joined Caterpillar as an Associate Engineer, where he applied Machine Learning and Deep Learning techniques for fault diagnosis of gear failures using high-frequency vibration data. He also worked on Reduced-Order Modeling of Power Train and Driveline Components, leveraging in-house tools for bearing performance analysis. Additionally, he developed Python-based GUI tools to improve process efficiency and data management.

Currently, Hiren is pursuing a PhD at Aalborg University (AAU), with Grundfos as an industrial partner, focusing on digital twins and reduced-order models for mechanical components to predict their useful life. His research explores how to develop real-time failure prediction systems, under the supervision of Prof. Sergey at AAU and Kim at Grundfos, with funding from APRIORI.

Iman Hosseini

He earned his Master’s degree from Ural Federal University in Yekaterinburg, Russia, in 2018. During his studies, he focused on applying machine learning techniques to predict labor migration patterns and optimize educational trajectories. Subsequently, he worked as a developer and programming instructor, specializing in Python, C#, PostgreSQL, and MS SQL Server. He provided training to various companies and educational institutions in Saint Petersburg, Russia, equipping professionals with essential programming skills.

Before this, he earned a Bachelor’s degree in Computer Engineering and worked as a Software Developer in Iran. With over 15 years of experience in desktop and database development, he has contributed to various projects, including the development of payroll systems for government agencies, educational software for the Department of Telecommunications, hotel management systems for the hospitality industry, purchase and sales applications, optimizing automation processes, and enhancing system efficiency and user experience. He has also collaborated with cross-functional teams to integrate payment processing, inventory management, and reporting features, ensuring seamless business operations.

He is currently a Ph.D. candidate at the Jožef Stefan Institute (JSI), where he is actively engaged in research as part of the prestigious Marie Curie Fellowship within the APRIORI project. His research focuses on developing active learning methodologies and strategic approaches to improve the explainability of machine learning models. By enhancing model transparency and interpretability, his work aims to provide deeper insights into classification predictions while minimizing the need for manual data labeling.