Contacts
Phone: +39.02.2399.6355
E-mail: francesco.cadini@polimi.it
Secretary's Office of the RL Machine and Vehicle Design
Licia Simonelli
Phone: +39.02.2399.8212
E-mail: licia.simonelli@polimi.it@polimi.it
Francesco Cadini is assistant professor at the Department of Mechanical Engineering of the Politecnico di Milano. His research interests include the quantitative treatment of uncertainties for risk assessment and mitigation in mechanical, aerospace and structural systems. His activities are mainly focused on i) diagnostic and prognostic (structural health monitoring - SHM - and prognostics and health management - PHM) and ii) rare-event structural reliability analysis, robust (RDO) and reliability-based design optimization (RBDO). The main algorithmic tools employed and/or developed are: i) stochastic filtering (sequential Monte Carlo algorithms - particle filters, etc.) for state estimation, ii) efficient Monte Carlo sampling of rare events (variance reduction methods), iii) machine learning (neural networks, deep learning, kriging, support vector machines, etc.) for classification, regression, model identification and time series prediction and iv) advanced optimization tools (e.g., evolutionary algorithms).
Metrics overview (02/2021)
- Approximately 100 publications in International journals (63) and proceedings of international conferences (Scopus: 72).
- H-index: 19, H-index (10y): 12, H-index (5y): 7 (Scopus).
- Citations: 1047, cit. (10y): 653, cit. (5y): 278 (Scopus).
Work Experience
- January 2018 – present. Politecnico di Milano, Milano, Italy. Assistant professor (scientific area ING-IND/14) at the Department of Mechanics of the Politecnico di Milano.
- July 2005 – December 2017. Politecnico di Milano, Milano, Italy. Assistant professor (scientific area ING-IND/18) at the Department of Energy of the Politecnico di Milano.
Education
- May 2006. Politecnico di Milano - Department of Nuclear Engineering, Milano, Italy. Ph.D. in “Radiation science and engineering”.
- September 2003. University of California, Los Angeles (UCLA), USA. Master’s in science in Aerospace Engineering at the Henri Samueli School of Engineering and Applied Science.
- February 2000. Politecnico di Milano - Department of Nuclear Engineering, Milano, Italy. Degree in Nuclear Engineering.
Thesis Proposals
Thesis CMV 003/2023 - Deep learning for structural integrity: Graph neural networks - Prof. Francesco Cadini, Luca Lomazzi
Thesis CMV 004/2023 - Deep learning for structural integrity: Physics-informed neural networks - Prof. Francesco Cadini, Luca Lomazzi
Thesis CMV 005/2023 - Deep learning for inverse eigenvalue problems in structural mechanics - Prof. Francesco Cadini, Luca Lomazzi
Thesis CMV 006/2023 - Structural health monitoring and machine learning: supevised vs unsupervised approaches - Prof. Francesco Cadini, Luca Lomazzi
Thesis CMV 007/2023 - Machine learning-based surrogate modelling of a lunar rover Digital Twin for real-time operations - Prof. Francesco Cadini, Lucio Pinello
Thesis CMV 008/2023 - Integration of anomalies and defects in a lunar rover Digital Twin for performing damage diagnosis and prognosis - Prof. Francesco Cadini, Lucio Pinello
Thesis CMV 009/2023 - Prognostics and Health Management of lithium-ion batteries exploiting multi-physics digital twin (DT) and machine learning (ML) - Prof. Francesco Cadini, Yiqi Jia, Lorenzo Brancato
Thesis CMV 010/2023 - Offering an achievable and advanced health monitoring strategy for structural batteries - Prof. Francesco Cadini, Yiqi Jia, Lorenzo Brancato
Thesis CMV 016/2023 - Application of machine learning in prediction of low-velocity impact response of hybrid composites - Prof. Marco Giglio, Prof. Andrea Manes, Prof. Francesco Cadini, Dayou Ma
Thesis CMV 017/2023 - Modelling of nanocomposites - Prof. Marco Giglio, Prof. Andrea Manes, Prof. Francesco Cadini
Thesis CMV 025/2023 - Numerical characterisation of blast loaded structures and development of machine learning-based surrogate models - Prof. Marco Giglio, Prof. Andrea Manes, Prof. Francesco Cadini
Thesis CMV 006/2024 - Numerical analysis of composite representative volume elements and development of machine learning-based surrogate models - Prof. Marco Giglio, Prof. Andrea Manes, Prof. Francesco Cadini