Despite the growing availability of sensing and data in general, we remain unable to fully characterize many in-service engineering systems and structures from a purely data-driven approach. The vast data and resources available to capture human activity are unmatched in our engineered world, and, even in cases where data could be referred to as “big,” they will rarely hold information across operational windows or life spans. This paper pursues the combination of machine learning technology and physics-based reasoning to enhance our ability to make predictive models with limited data. By explicitly linking the physics-based view of stochastic processes with a data-based regression approach, a derivation path for a spectrum of possible Gaussian process models is introduced and used to highlight how and where different levels of expert knowledge of a system is likely best exploited. Each of the models highlighted in the spectrum have been explored in different ways across communities; novel examples in a structural assessment context here demonstrate how these approaches can significantly reduce reliance on expensive data collection. The increased interpretability of the models shown is another important consideration and benefit in this context.

Physics-informed neural networks (PINNs), which are a recent development and incorporate physics-based knowledge into neural networks (NNs) in the form of constraints (e.g., displacement and force boundary conditions, and governing equations) or loss function, offer promise for generating digital twins of physical systems and processes. Although recent advances in PINNs have begun to address the challenges of structural health monitoring, significant issues remain unresolved, particularly in modeling the governing physics through partial differential equations (PDEs) under temporally variable loading. This paper investigates potential solutions to these challenges. Specifically, the paper will examine the performance of PINNs enforcing boundary conditions and utilizing sensor data from a limited number of locations within it, demonstrated through three case studies. Case Study 1 assumes a constant uniformly distributed load (UDL) and analyzes several setups of PINNs for four distinct simulated measurement cases obtained from a finite element model. In Case Study 2, the UDL is included as an input variable for the NNs. Results from these two case studies show that the modeling of the structure’s boundary conditions enables the PINNs to approximate the behavior of the structure without requiring satisfaction of the PDEs across the whole domain of the plate. In Case Study (3), we explore the efficacy of PINNs in a setting resembling real-world conditions, wherein the simulated measurment data incorporate deviations from idealized boundary conditions and contain measurement noise. Results illustrate that PINNs can effectively capture the overall physics of the system while managing deviations from idealized assumptions and data noise.

Population-based structural health monitoring (PBSHM) systems use data from multiple structures to make inferences of health states. An area of PBSHM that has recently been recognized for potential development is the use of multitask learning (MTL) algorithms that differ from traditional single-task learning. This study presents an application of the MTL approach, Joint Feature Selection with LASSO, to provide automatic feature selection. The algorithm is applied to two structural datasets. The first dataset covers a binary classification between the port and starboard side of an aircraft tailplane, for samples from two aircraft of the same model. The second dataset covers normal and damaged conditions for pre- and postrepair of the same aircraft wing. Both case studies demonstrate that the MTL results are interpretable, highlighting features that relate to structural differences by considering the patterns shared between tasks. This is opposed to single-task learning, which improved accuracy at the cost of interpretability and selected features, which failed to generalize in previously unobserved experiments.

The decreasing cost and improved sensor and monitoring system technology (e.g., fiber optics and strain gauges) have led to more measurements in close proximity to each other. When using such spatially dense measurement data in Bayesian system identification strategies, the correlation in the model prediction error can become significant. The widely adopted assumption of uncorrelated Gaussian error may lead to inaccurate parameter estimation and overconfident predictions, which may lead to suboptimal decisions. This article addresses the challenges of performing Bayesian system identification for structures when large datasets are used, considering both spatial and temporal dependencies in the model uncertainty. We present an approach to efficiently evaluate the log-likelihood function, and we utilize nested sampling to compute the evidence for Bayesian model selection. The approach is first demonstrated on a synthetic case and then applied to a (measured) real-world steel bridge. The results show that the assumption of dependence in the model prediction uncertainties is decisively supported by the data. The proposed developments enable the use of large datasets and accounting for the dependency when performing Bayesian system identification, even when a relatively large number of uncertain parameters is inferred.

Lamb waves are a growing method for the Non-Destructive Testing and Evaluation (NDT&E) and structural health monitoring (SHM) of aerospace vehicles. These guided waves can propagate over large distances and have a strong tendency to interact with damage. Whilst several methods exist for the modelling of Lamb wave propagation, this paper is the first to introduce a first principles numerical model that can efficiently and accurately predict the behaviour of Lamb waves. The numerical model is easier to understand and implement compared with analytical solutions and significantly faster than discretised numerical methods. The numerical model is presented in detail for an isotropic and homogenous plate, along with validation against the industry accepted, WaveForm Revealer 3 (WFR3) software. The results show a mean correlation across all assessed parameters of 90.4% and 96.6% for the symmetric and antisymmetric modes, respectively. Further discussion is provided on future developments to the model, including on the topic of high temperature effects, anisotropic materials and edge reflections.

Liquid crystal elastomers (LCEs) are programmable materials par excellence. I review the history and state of the art of LCE materials and processing development from the perspective of the important remaining step of moving out of the academic research lab and applying LCEs as soft actuators or strain sensors. After a brief introduction for the non-expert of what LCEs are and which their main advantages and limitations are, I discuss the key breakthroughs that LCE research has undergone over its 50-year history. Building on this and drawing from fresh results from on-going research, I consider possible future development trajectories that would help address the outstanding key obstacles to reach mass production at competitive cost. I end with discussing a selected set of application scenarios with good opportunities for LCEs to perform functions that no other material could deliver. Specifically, I focus on responsive buildings incorporating LCE actuator fibres and sheets/ribbons, structural health monitoring with LCE strain sensors monitoring crack growth and propagation or alerting residents of buildings exposed to dangerous levels of deformation, and kinetic and responsive garments incorporating LCE fibre actuators and/or strain sensors.

The monitoring of infrastructure assets using sensor networks is becoming increasingly prevalent. A digital twin in the form of a finite element (FE) model, as commonly used in design and construction, can help make sense of the copious amount of collected sensor data. This paper demonstrates the application of the statistical finite element method (statFEM), which provides a principled means of synthesizing data and physics-based models, in developing a digital twin of a self-sensing structure. As a case study, an instrumented steel railway bridge of $ 27.34\hskip1.5pt \mathrm{m} $ length located along the West Coast Mainline near Staffordshire in the UK is considered. Using strain data captured from fiber Bragg grating sensors at 108 locations along the bridge superstructure, statFEM can predict the “true” system response while taking into account the uncertainties in sensor readings, applied loading, and FE model misspecification errors. Longitudinal strain distributions along the two main I-beams are both measured and modeled during the passage of a passenger train. The statFEM digital twin is able to generate reasonable strain distribution predictions at locations where no measurement data are available, including at several points along the main I-beams and on structural elements on which sensors are not even installed. The implications for long-term structural health monitoring and assessment include optimization of sensor placement and performing more reliable what-if analyses at locations and under loading scenarios for which no measurement data are available.

This work is concerned with damage detection in a commercial 52-meter wind turbine blade during fatigue testing. Different artificial damages are introduced in the blade in the form of laminate cracks. The lengths of the damages are increased manually, and they all eventually propagate and develop into delaminations during fatigue loading. Strain gauges, acoustic emission sensors, distributed accelerometers, and an active vibration monitoring system are used to track different physical responses in healthy and damaged states of the blade. Based on the recorded data, opportunities and limitations of the different sensing systems for blade structural health monitoring are investigated.

Proper monitor planning is a vital component of structural health monitoring (SHM) project. An extremely important part of the monitor planning is the placement of sensors, usually in the form of acceleration sensors. For the placement of three-dimensional acceleration sensors, the state of practice is to select the sensor configuration by previous experiences. However, this results in a waste of many sensors. A novel method called siege ant colony algorithm (SAC) is proposed in this paper. This method is built on the previous ant colony optimization (ACO) in the direction of improving efficiency and accuracy when applied to optimal sensor placement (OSP) problems in large-scale structure monitoring. This method is applied and compared with standard approaches using the Hanjiang transmission tower.

Structural Health Monitoring (SHM) takes advantage of the recent advances in nanotechnology and sensing in order to monitor the behavior of a structure, assess its performance and identify damage at an early stage. Monitoring the state of strain throughout an entire structure is essential to determine its state of stress, detect potential residual stresses after fabrication, and also to help to establish its integrity. The Carbon nanotube thread was integrated into three-dimensional braiding materials and used for the first time as a sensor to monitor strain and also to detect damage in the three-dimensional braided composite material.

In this paper a literature review about the application of carbon nanotubes thread for sensors and smart materials used for SHM of braiding structures is presented. The test data show the braided angle is important parameter for structural health monitoring of three-dimensional. The research will provide a new integrated and distributed technologies for the built-in carbon nanotube sensor to detect the health of composite. The subject will provide the new idea and method for the development of smart composite materials research and application.

Cet article porte sur l'utilisation de techniques d'analyse de processus statistiques pour la détection et la localisation d'endommagements structuraux à partir de mesures vibratoires.La première approche proposée dans ce travail se base sur la méthode d'identification des sous-espaces stochastiques pour construire un modèle de Kalman représentatif de l'état initial (de référence) de la structure. Ce modèle est alors utilisé pour réaliser une prédiction des réponses nouvellement mesurées. L'analyse statistique de l'erreur de reconstruction du modèle permet de définir un critère de détection de l'apparition d'un défaut. L'intérêt de cette méthode est que seule l'identification du modèle pour les données de référence est nécessaire. La détection de l'endommagement peut alors être effectuée de manière automatique par surveillance de la structure sans nécessiter de nouvelle identification.Dans la seconde approche, l'analyse en composantes principales des réponses est utilisée pour extraire les directions principales (les caractéristiques) permettant de définir un sous-espace représentatif du comportement dynamique de la structure. Le moindre changement dans la réponse d'un capteur affecte l'espace sous-tendu par l'ensemble de tous les capteurs. Par conséquent, la comparaison entre les sous-espaces correspondant respectivement à la structure saine et la structure actuelle (potentiellement endommagée) permet de détecter l'apparition éventuelle d'un endommagement. L'analyse en composantes principales peut également être réalisée sur un sous-ensemble de capteurs dans le but de localiser le(s) capteur(s) responsable(s) de l'apparition du défaut, et par conséquent, la sous-structure endommagée.