Luca Lomazzi

Luca Lomazzi is an Assistant Professor of Mechanical Engineering at Politecnico di Milano. His research focuses on phononics and mechanical metamaterials, structural design and protection under extreme loading, structural health monitoring, and machine learning for computational and structural mechanics. His work combines advanced numerical modeling, experiments, and data-driven methods, with applications ranging from wave manipulation and impact protection to aerospace and naval structures. He is Task Leader in the €20M European Defence Fund FMBTech project and Scientific Coordinator of the ARNES project on naval structures subjected to underwater explosions. He has held visiting research positions at the University of Colorado Boulder and NTNU and collaborates with industrial partners in the aerospace, defense, and energy sectors. He has authored more than 50 international publications and presented his research at universities and international conferences, including Stanford and Harvard.

1. Elastic hyperbolic strip lattices

   N. H. Patino, L. Lomazzi, L. De Beni, M. Ruzzene

   Physical Review Applied 24(1), 014016 · 2025

2. Interface states in two-dimensional quasicrystals with broken inversion symmetry

   D. Beli, M. I. N. Rosa, L. Lomazzi, C. De Marqui, M. Ruzzene

   Physical Review Applied 23(2), 024039 · 2025

3. On the explainability of convolutional neural networks processing ultrasonic guided waves for damage diagnosis

   L. Lomazzi, S. Fabiano, M. Parziale, M. Giglio, F. Cadini

   Mechanical Systems and Signal Processing 183, 109642 · 2023

4. Unsupervised data-driven method for damage localization using guided waves

   L. Lomazzi, R. Junges, M. Giglio, F. Cadini

   Mechanical Systems and Signal Processing 208, 111038 · 2024

5. A dimensionless metric for quantifying fluid–structure interaction in blast-loaded plates

   G. Marchesi, L. Lomazzi, V. Aune, G. Nurick, T. J. Cloete, A. Manes

   International Journal of Mechanical Sciences 311, 111181 · 2026

1. Convolutional autoencoders and CGANs for unsupervised structural damage localization

   R. Junges, Z. Rastin, L. Lomazzi, M. Giglio, F. Cadini

   Mechanical Systems and Signal Processing, 220, 111645 · 2024

2. Enhancing Lamb wave-based damage diagnosis in composite materials using a pseudo-damage boosted convolutional neural network approach

   A. Gonzalez-Jimenez, L. Lomazzi, R. Junges, M. Giglio, A. Manes, F. Cadini

   Structural Health Monitoring, 23(3), 1514-1529 · 2024

3. Physics-Informed Neural Networks for the Condition Monitoring of Rotating Shafts

   M. Parziale, L. Lomazzi, M. Giglio, F. Cadini

   Sensors, 24(1), 207 · 2024

4. Towards a deep learning-based unified approach for structural damage detection, localisation and quantification

   L. Lomazzi, M. Giglio, F. Cadini

   Engineering Applications of Artificial Intelligence, 121, 106003 · 2023

5. Analytical and empirical methods for the characterisation of the permanent transverse displacement of quadrangular metal plates subjected to blast load: Comparison of existing methods and development of a novel methodological approach

   L. Lomazzi, M. Giglio, A. Manes

   International Journal of Impact Engineering, 154, 103890 · 2021

All group publications

• Wave Lab

  University of Colorado Boulder (USA)

• SIMLab

  Norwegian University of Science and Technology (NTNU), Norway

• Surf Flex Lab

  University of Wollongong, Australia

• DIISM

  Università Politecnica delle Marche, Italy

• Also teaching

  Advanced Machine Design

  MSc Mechanical Engineering · 10 CFU · 2nd semester · Milano Bovisa

  Lecturer: Marco Giglio

  Course sheet

• Also teaching

  Impact Engineering

  MSc Mechanical Engineering · 5 CFU · 1st semester · Milano Bovisa

  Lecturer: Andrea Manes

  Course sheet

• Lecturer

  Lab – Mechanical Engineering Applications of Deep Learning

  MSc Mechanical Engineering · 5 CFU · 2nd semester · Milano Bovisa

  Course sheet

Courses of 2026/2027, from the Politecnico’s course sheets. All the group’s courses

• AIMachine LearningImpact & BallisticsNumerical Modelling

  Machine learning for ballistic-limit prediction in multilayer protections

  The design of ballistic protection systems for ground vehicles requires fast and reliable tools to assess the ability of multilayer configurations to stop high-velocity projectiles. Experimental campaigns and high-fidelity simulations are accurate but expensive and time-consuming, while the design space is extremely large. Machine learning models trained on numerical simulation databases can provide rapid predictions of ballistic performance and support early-stage design decisions.

  Details and apply
• BlastNumerical Modelling

  Rapid prediction of fluid-structure interaction in blast-loaded plates

  Accurate estimation of fluid-structure interaction (FSI) effects is crucial for predicting the response of lightweight metallic plates subjected to air blasts. Despite numerous studies, understanding and predicting these coupling phenomena remains a challenge. Developing simplified yet reliable predictive tools enables both efficient high-fidelity simulations and the design of blast-mitigation solutions.

  Details and apply
• SHMMetamaterials

  Fractal-inspired structures for enhanced Structural Health Monitoring (SHM)

  Fractals are geometrical structures characterized by repeating patterns across multiple scales and distinctive properties such as self-similarity and scale invariance. These features have motivated their use in several fields, including materials science, acoustics, and energy systems, to design efficient multiscale systems. In Structural Health Monitoring (SHM) the dynamic behavior of fractal-inspired structures can be exploited to enhance the performance of diagnostic systems.

  Details and apply
• Metamaterials

  Programmable metamaterials for adaptive mechanical behavior

  Programmable metamaterials are engineered materials whose mechanical properties can be dynamically altered through embedded actuation and control mechanisms. A defining feature is closed-loop adaptivity: the material senses its state (e.g., load, strain) and tunes its properties (e.g. stiffness, damping) accordingly, enabling adaptive behavior under changing conditions.Thanks to this, it is possible to realize structures that autonomously adapt their mechanical response to improve performance, robustness, and safety.

  Details and apply
• SHMMetamaterials

  Design and application of metamaterials computational capabilities for damage diagnosis

  Mechanical metamaterials are structural components engineered and designed to exhibit properties that go beyond the intrinsic characteristics of the base material itself. Given the vast design space offered by the numerous geometries and solutions that can be employed to achieve a wide range of different properties, these metamaterials can be used to perform actual computations. Thanks to this, it is possible to exploit the computing capabilities of mechanical metamaterials to highlight and facilitate the detection of specific structural damages.

  Details and apply
• SHMAIDeep Learning

  Graph neural networks for damage diagnosis

  SHM systems aim to detect and diagnose damage in real time. Conventional methods, such as numerical analysis, can be computationally expensive and less efficient for large-scale or complex structures. Graph Neural Networks (GNNs) offer a promising solution by leveraging sensor networks as graphs, where nodes represent sensors and edges capture physical interactions. The objective of this thesis is to validate and enhance the use of GNNs for diagnosing damage within SHM systems.

  Details and apply
• SHMSensingAIMachine Learning

  Dataset and algorithms for damage diagnosis in real-world scenarios

  Structural Health Monitoring (SHM) systems aim to detect and diagnose damage in real time. Traditional acquisition systems for SHM are highly accurate but exhibit significant limitations in terms of weight, size, cost, portability, and power consumption. Therefore, the development of systems capable of overcoming these constraints is increasingly crucial to enhance their applicability. Moreover, in the context of SHM, the use of Machine Learning (ML) plays a central role, making it essential to integrate ML even into computationally constrained systems through appropriate optimizations and customizations. In this context, our research project is built up as follows:

  Details and apply
• SHMElastic WavesAIDeep Learning

  Damage Localization using Autoencoders for Varying Temperatures and Frequencies

  Damage localization through the analysis of ultrasonic guided waves can be influenced by an array of cofounding factors e.g., temperature and humidity. Besides, the choice of excitation frequency affects not only the sensitivity of the waves but also the size of damage that can be detected. In this context, properly trained convolutional autoencoders that leverage the temperature and frequency information as points in their latent space might be able to overcome such drawbacks and provide a more robust damage localization framework.

  Details and apply
• AIMachine LearningMetamaterialsExperimentalTheoreticalNumerical Modelling

  Generative Design of Disordered Mechanical Metamaterials for Tailored Dynamic Response

  Use machine learning and inverse design to generate disordered architectures with prescribed mechanical behavior under dynamic loading.

  Details and apply
• MetamaterialsExperimentalNumerical Modelling

  Mechanical Neural Networks: Topology Optimization of Computational Unit Cells

  Design optimized mechanical unit cells that process mechanical inputs and realize targeted computational or logic-like responses.

  Details and apply
• Elastic WavesMetamaterialsExperimentalTheoreticalNumerical Modelling

  Rainbow Effects and Wave Control in Spatially Graded Mechanical Metamaterials

  Investigate how spatial grading can localize, steer, and filter elastic waves, producing tunable rainbow effects.

  In collaboration with the Wave Lab, University of Colorado Boulder

  Details and apply
• MetamaterialsMaterialsExperimentalTheoreticalNumerical Modelling

  Magnetorheological Elastomer Metamaterials for Tunable Mechanical Response

  Develop architected elastomeric materials whose stiffness and deformation response can be controlled through an external magnetic field.

  Details and apply
• Elastic WavesMetamaterialsExperimentalTheoreticalNumerical Modelling

  Active Wave Control and Rainbow Effects in Magnetorheological Fluid-Based Phononic Crystals

  Design phononic crystals with magnetorheological-fluid inclusions to magnetically tune wave propagation, band gaps, and rainbow localization.

  In collaboration with the Wave Lab, University of Colorado Boulder

  Details and apply
• Elastic WavesMetamaterialsExperimentalTheoreticalNumerical Modelling

  Wave Dynamics in Twisted TPMS Metamaterials under Irreversible Deformation

  Study how permanent deformation and twist modify elastic-wave propagation in triply periodic minimal-surface metamaterials.

  In collaboration with Università Politecnica delle Marche

  Details and apply
• SHMElastic WavesMetamaterialsExperimentalTheoreticalNumerical Modelling

  Fractal Mechanical Metamaterials for Elastic Wave Control and Structural Health Monitoring

  Explore fractal architectures for wave filtering and localization, and exploit their wave response for damage detection.

  Details and apply
• SHMElastic WavesMetamaterialsExperimentalTheoreticalNumerical Modelling

  Non-Hermitian Exceptional Points for Enhanced Structural Health Monitoring

  Investigate exceptional-point phenomena in mechanical systems to enhance sensitivity to small structural changes and damage.

  In collaboration with the Wave Lab, University of Colorado Boulder

  Details and apply

All thesis topics can incorporate machine learning and data-driven methods, including surrogate modeling, optimization, generative and inverse design, and physics-informed learning, depending on the student's interests and background.

All thesis topics