Skip to content
Politecnico di Milano, SIGMA Lab

Research

Rafael’s research focuses on Structural Health Monitoring (SHM) of composite structures using ultrasonic guided waves (UGWs). His work combines signal processing, physics-based methods, and machine-learning algorithms to detect, localise, and quantify structural damage from multi-sensor measurements. Particular attention is given to carbon-fibre-reinforced polymer (CFRP) structures, whose anisotropy and complex wave-propagation behaviour present challenges beyond those encountered in conventional metallic structures. These materials are widely used in sectors such as aerospace because of their high specific strength and stiffness.

PhD thesis

Towards Autonomous Structural Health Monitoring: From Supervised Learning to Generative Artificial Intelligence

Politecnico di Milano · 2026

Selected publications

  1. 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

  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. Mitigating the Impact of Temperature Variations on Ultrasonic Guided Wave-Based Structural Health Monitoring through Variational Autoencoders

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

    Sensors 24(5), 1494 · 2024

  4. 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

Publications

Papers per year
2023202420252026
All publications 9 papers
  1. Interpretable Dual-Network Feature-Selection Framework for Guided Wave Damage Diagnosis on Composite Panels

    R. Junges, A. Abbassi, L. Lomazzi, M. Giglio, F. Cadini, R. Rolfes

    e-Journal of Nondestructive Testing, 31(8) · Journal article · 2026

  2. Physics-Informed Machine Learning for Ultrasonic Guided Wave Full-Field Reconstruction and Damage Diagnosis

    A. Casartelli, L. Lomazzi, L. Pinello, R. Junges, M. Giglio, F. Cadini

    Proceedings of the 15th International Workshop on Structural Health Monitoring · Conference paper · 2025

  3. 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 · Journal article · 2024

  4. Convolutional autoencoder-based framework for damage localization under variable temperature

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

    e-Journal of Nondestructive Testing, 29(7) · Journal article · 2024

  5. Mitigating the Impact of Temperature Variations on Ultrasonic Guided Wave-Based Structural Health Monitoring through Variational Autoencoders

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

    Sensors, 24(5), 1494 · Journal article · 2024

  6. 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 · Journal article · 2023

  7. 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 · Journal article · 2023

  8. DAMAGE LOCALIZATION FRAMEWORKS BASED ON UNSUPERVISED DEEP LEARNING NEURAL NETWORKS

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

    Proceedings of the 14th International Workshop on Structural Health Monitoring · Conference paper · 2023

  9. Unsupervised Deep Learning Methods for Damage Localization

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

    Preprint · 2023

All group publications

Research in images

Damage probability maps on two composite panel geometries, from ultrasonic guided waves measured by the sensor network (circles); the white cross marks the actual damage.
Damage probability maps on two composite panel geometries, from ultrasonic guided waves measured by the sensor network (circles); the white cross marks the actual damage.
Unsupervised damage localisation: guided-wave signals are acquired, a convolutional autoencoder turns them into damage indices, and these build a damage probability map.
Unsupervised damage localisation: guided-wave signals are acquired, a convolutional autoencoder turns them into damage indices, and these build a damage probability map.