Conference Agenda

Session

SS18 - 3: Digital Twins for Structural Health Monitoring of Complex Mechanical Systems - 3

Time:

Friday, 10/July/2026:

8:50am - 10:10am

Location: Ariane 2

Session Abstract

Organisers:

Adrien Melot, Inria, France

Basuraj Bhowmik, University of Strathclyde, United Kingdom

Susmita Naskar, University of Southampton, United Kingdom

Olivier Bareille, INSA Rouen, France

Christophe Droz, Inria, France

Digital twins (DTs) are emerging as a central paradigm for structural health monitoring (SHM) of advanced mechanical systems. They provide a virtual representation that integrates experimental data with high-fidelity models to assess the condition of a structure and predict its future evolution under operating conditions. Mechanical systems of practical interest are increasingly complex, whether due to the use of architected and metamaterials, nonlinear behavior, or multi-physical couplings. Such characteristics make the creation of accurate and efficient DTs particularly challenging. Recent advances in artificial intelligence (AI) and machine learning (ML) provide new avenues for capturing nonlinearities, multi-scale behaviors, and hidden patterns that are difficult to model using physics alone. In this context, both physics-based and data-driven approaches play a complementary role: the former provide interpretability and predictive accuracy, while the latter offer adaptability and efficiency in handling large, uncertain datasets. Hybridization between physics-based and data-driven approaches open new opportunities for SHM: on the physics-based side, improvements in reduced-order modeling, uncertainty quantification, and nonlinear simulations extend the predictive capability of physics-based models. On the data-driven side, machine learning and statistical inference provide powerful tools to extract damage-sensitive features directly from measurements, and to enhance the adaptability of DTs in uncertain environments. This mini-symposium aims to bring together contributions that advance the development of DT technologies for SHM, with a focus on accuracy, computational efficiency, and robustness. Topics of interest include (but are not limited to):

Hybridization of model-based and data-driven methods for DTs, including AI-driven model fusion, transfer learning, and multi-fidelity approaches for SHM.

Reduced-order and surrogate modeling for SHM and model updating

Modeling, computational and identification methods for metamaterials, including AI-based discovery, topology optimization, and inverse design for complex architected materials.

Nonlinear and multi-physical identification strategies for dynamical systems.

Uncertainty-aware and near-real-time DTs, for instance enabled through Bayesian deep learning and probabilistic graphical models for adaptive SHM.

Presentations

8:50am - 9:10am

Multiresolution wavelet-based reduced order model with an eye towards digital twin applications

D. Dimitriou¹, P. Kudela², M. Radzieński², D. Saravanos¹

¹University of Patras, Greece; ²Polish Academy of Sciences, Poland

The present work proposes a multiresolution (MR) reduced order model (ROM) based on Krylov subspace techniques with a focus on parameter estimation and digital twin applications. The multiresolution finite wavelet domain (MR-FWD) method is utilised as the basis modelling method, and it is reduced by the second order Arnoldi iteration (SOAR) algorithm. The structure of the discretised algebraic system of the MR-FWD method is preserved, and thus, the coarse and fine solutions of the multiresolution wavelet Galerkin approximation are available after the reduction. Interestingly, the reduced fine solutions preserve the localisation and isolation capabilities of the full model’s fine solutions, showcasing their potential to be used in model update procedures. The proposed MR-ROM is evaluated in a wave-based structural identification case study, where full-field data from a guided wave experiment in a composite plate are acquired. The measurements are decomposed into detail and approximation datasets following the discrete wavelet transform. The detail dataset(s) can be correlated with the fine solution(s) of ROM results to estimate the involved design parameters through model updating. The measurement data can also be utilised through comparisons with the total solution of the MR-ROM. Through this multiresolution updating, the parameter estimation process can be more accurate due to the filtering capacity of the multiple components, and with the synergy of SOAR reduction, the physics-based numerical part of the envisioned digital twins can approximate real-time performance.

9:10am - 9:30am

Optimising Aircraft Fleet Maintenance with Reinforcement Learning: A numerical case study

E. Petriconi, M. Giglio, C. Sbarufatti

Politecnico di Milano, Italy

Unexpected failures and inefficient maintenance plans lead to costly downtime in many industrial fields, undermining operational sustainability and overall profitability, or, in the worst scenarios, creating unsafe situations for people. These issues justify a shift towards predictive maintenance, and structural health monitoring (SHM) has emerged as a viable option. By exploiting modern hardware and software technologies, the diagnosis and prognosis of monitored structures can be performed while accounting for estimation uncertainty. In addition, for complex structures, monitoring all components is not feasible for technical or economic reasons, and a mix of condition and schedule-based maintenance approaches is still required. To fully exploit the SHM benefits, an effective decision-making process is necessary, including Opportunistic Maintenance (OM) that accounts for both scheduled stops and the Residual Useful Life (RUL) predicted by prognostic models. In this context, decision-making becomes significantly more complex when managing an entire fleet rather than a single asset, reflecting the real-world challenges companies face.
This study explores the application of Reinforcement Learning (RL) to automated decision-making in aircraft fleet maintenance, aiming to minimise operational and maintenance (O&M) life-cycle costs. The RL agent is trained and deployed within a fleet life cycle simulator that replicates real-world conditions, including mission schedules, maintenance operations, repair bases with varying capabilities, and potential unforeseen events. Each aircraft is modelled as an ensemble of subcomponents, with only a portion equipped with an SHM system that provides Remaining Useful Life (RUL) predictions, expressed as probability distributions, and fault detection. The agent leverages this data to develop an optimal maintenance policy, aligning scheduled stops for non-monitored components with necessary interventions for monitored parts. Specifically, it determines maintenance schedules and selects which components to replace based on fleet-wide data, expected mission schedules, and aircraft availability.
While the study is demonstrated using a fleet life-cycle simulator, it serves as a preliminary step toward the real-world implementation of autonomous agents. The integration of the agent within the fleet simulator, potentially based on a real scenario, enhances its capabilities as a Digital Twin, supporting management decisions. Furthermore, it leverages the potential benefits of SHM technology, encouraging broader industry adoption.

9:30am - 9:50am

Observer-Based Virtual Sensing for Structural Health Monitoring: Experimental Validation on a Ship Hull Model

A. Venturi¹, F. Saltari², D. Dessi¹

¹National Research Council - Institute of Marine Engineering; ²Sapienza University of Rome

Virtual sensing techniques, or soft sensing, aim at reconstructing physical quantities at locations where no direct measurements are available, enabling a complete representation of a system from sparse sensor information. These methods rely on the synergy between the measurement data, physics- or knowledge-based models, and statistical characterization of uncertainties. In recent years, virtual sensing has been consolidated into a broad set of approaches that include inverse finite-element formulations, data-driven methods, and control theory-based estimators. Among the latter, proportional observers (PO) and their multi-resolution extensions (MRPO) offer a practical alternative to Kalman-filters and “natural observers”. Their simple formulation, combined with frequency-band tuning, balances computational burden, noise robustness, and reconstruction accuracy.

This paper presents an observer-based virtual sensing (OB-VS) framework for reconstructing strain fields in ship structures using a limited number of physical sensors. The approach builds on PO and MRPO, exploiting linear relations between the measurement vector and the estimated state-space variables. The method leverages the mechanical transfer function of the structure and a statistical description of uncertainties in the frequency domain, including measurement noise, modelling inaccuracies, and unknown excitation. A key advantage of the PO formulation is that the prediction-error covariance matrix depends quadratically on the observer gain(s), ensuring the existence of a unique global minimum. The MRPO enhances this approach by defining multiple POs, each one tailored for a specific frequency band into which the signal is decomposed via wavelet multi-resolution analysis.

The methodology is applied to the experimental dataset relative to an elastic scaled ship-model campaign, performed within the “Digital Ship Structural Health Monitoring project” (dTHOR), granted by the European Defence Fund, aimed at developing a system based on innovative utilization of extensive on-board measurements, a comprehensive digital framework, and hybrid analysis and modelling. Measurements from 13 strain-gauges were utilized. Stepping forward with respect to previous 1D models, the present analysis employs a full 3D finite-element (FE) representation of the segmented hull. The observer is trained by extracting modal quantities from the FE solution (modal strains, modal mass, damping, and stiffness matrices) and constructing the corresponding transfer function. Because the FE model represents the dry hull, a correction is introduced to ensure consistency between numerical and experimental modal characteristics. The external (wave) excitation is estimated by combining acceleration, strain and rigid-body motion data.

Performance is evaluated by computing the errors in signal reconstruction both in time (Time Response Assurance Criterion) and frequency (Frequency Response Assurance Criterion). Both PO and MRPO achieve a high fidelity in predicting the strains measured by sensors not involved in the virtual sensing process. An a-posteriori comparison of several sensor layouts highlights the possibility of achieving an optimal trade-off between instrumentation effort and reconstruction accuracy based on end-user needs. The OB-VS approach keeps accurate in signal tracking even under incorrect assumptions on the external excitation, thus demonstrating its robustness.

Overall, this study highlights the potential of multi-resolution analysis for improving robustness to noise and spectral representation for real-time observer-based virtual sensing, enabling predictive digital-twin capabilities not only limited to on-board monitoring of ship structures.

9:50am - 10:10am

A novel framework for probabilistic model updating using load test data and Non-Parametric Bayesian Networks

F. Besseling^1,2, E.-m. Lourens¹

¹Delft University of Technology, Netherlands, The; ²Witteveen+Bos Consulting Engineers

Accurate model updating is essential for reliable structural assessment and performance prediction of civil infrastructure. Classical Bayesian model updating approaches, while powerful, are often limited by their reliance on predefined parametric distributions, and by the computational burden of sampling-based inference, which becomes prohibitive as the number of updating parameters increases.. These limitations hinder their applicability to complex structures where high-dimensional parameter spaces and uncertain parameter-output relations are prevalent. The restriction on the number of updating parameters often leads to a mismatch between the global-level formulation of the updating problem and the local structural behavior or failure mechanisms that are actually of interest. To address these limitations, this paper proposes a novel model updating framework that integrates load test data, Finite Element Modelling (FEM), and Non-Parametric Bayesian Networks (NPBNs). The approach uses load test measurements to calibrate FEM parameters, and employs NPBNs to efficiently capture complex dependencies among model variables. This paper presents the framework’s formulation and implementation, along with key verification steps. The flexibility and computational tractability of the NPBN-based framework make it particularly suited for structural engineering applications, contributing to more reliable data-driven asset management.