Dynamic response reconstruction for structural health monitoring using densely connected convolutional networks

The authors have been developing a new tiny (~12 mm cube and <4 g) Bluetooth wireless accelerometer unit based upon the technology that is prevalent in modern Smart Phones and Smart Watches. The primary intended application of this unit is for training/teaching purposes in vibration-based Experimental Modal Analysis (EMA) approaches for Structural System Identification (SSI) and Structural Health Monitoring (SHM). Digitised tri-axial acceleration data from a single unit can be streamed using purpose-specific software on a notebook or tablet at up to 400 Hz where the longest clear distance of this unit from the streaming device, (smart phone, tablet, laptop computer), is less than approx. 15 m. It is anticipated that tri-axial data synchronously captured from up to 8 accelerometer units at a sweep rate of 100 Hz per set, can be achieved on completion of the second stage of development of this system. This will certainly be suitable for use on model structures for teaching purposes, but also for industrial use (machinery; on-board vehicles; smaller structures) where the clear distance from the computer (or tablet) to these units is less than approx. 15 m. This paper focuses on the performance testing of a collection of commercially available accelerometers and compares these against the capabilities being aimed for in our new miniature accelerometer units.

The Lamb wave approach in Structural Health Monitoring (SHM) mainly cares the defects detection. It relies on the analysis of signals for physical propagation. In this paper, a sparse representation approach for modeling the signal scattering in discretized monitoring area is proposed. The overcomplete dictionary can be determined explicitly by the Lamb wave propagation theory with columns reflecting the signals at time instant. Through introducing the dictionary learning method, the signal scattering from defects can be formed as a sparse coding problem with the learnt dictionary from the given data. It has the potential to conquer the complex structure condition for thin-wall plate. The experiments illustrates the effectiveness of the presented approach.

The increasing use of composite materials in aerospace, automotive, and civil engineering demands robust approaches for structural health monitoring (SHM) and failure prediction. Due to their high strength-to-weight ratio and corrosion resistance, fiberreinforced polymers (FRPs) are essential in modern lightweight structures such as unmanned aerial vehicles (UAVs) [1]. However, they remain prone to fiber breakage, matrix cracking, and interlaminar delamination, which are often difficult to detect visually, making real-time monitoring critical for safety. This study presents a structural analysis of a carbon-fiber UAV wing using finite element analysis (FEA) in ANSYS to evaluate stress distributions, deformations, and failure modes under various loading scenarios, including progressive damage and fatigue. The Hashin and Tsai–Wu criteria were implemented to differentiate fiber- and matrix-dominated failures, including interlaminar fracture. Numerical results were compared with experimental data from the literature [5] to validate the approach. These results support the integration of FEA with SHM systems using Fiber Bragg Grating (FBG) sensors and Digital Twins for lightweight, sustainable composite structures in aerospace and civil infrastructure.

Crucial mechanical systems and civil structures or infrastructures, such as bridges, railways, buildings, wind turbines, aeroplanes and more are subjected during their lifetime to natural deterioration of their structural integrity [...]

The structures damage conditions assessment requires numerous precautions to ensure the safety of people during site visits and inspections. Among several methods providing useful information about the conservation status of the structures, dynamic monitoring techniques are suitable to retrieve the global behavior of the buildings. The anomalous features diagnosis of the structural dynamic response is an index of alterations of the material state and, in the worst cases, is related to the presence of damaged structural elements. This paper proposes the use of remote control systems for the structural evaluation of the damage state of buildings and describes the results achieved in an interesting application: the experimental dynamic analysis carried out on the inaccessible damaged bell tower of the Church of Santi Giacomo and Filippo in Mirandola (Italy). The study is based on observations performed using the IBIS-S ground-based radar interferometer to remotely measure the displacements of several elements of the building above 0.01 mm amplitude. This totally noninvasive and nondestructive approach has proved to be reliably implemented as a useful method to structural health monitoring procedures and especially for extensive and fast inspection analyses aiming at the first evaluation of the damage level and the soundness of slender buildings after earthquakes.

Comparative analysis of maximum deflection estimation in Single Span Steel Box Girder Bridge: Tiltmeter vs strain gauge approach for structural health monitoring

Floating covers used in waste water treatment plants are one of the many structures formed with membrane materials. These structures are usually large and can spread over an area measuring 470 m × 170 m. The aim of this paper is to describe recent work to develop an innovative and effective approach for structural health monitoring (SHM) of such large membrane-like infrastructure. This paper will propose a potentially cost-effective non-contact approach for full-field strain and stress mapping using an unmanned aerial vehicle (UAV) mounted with a digital camera and a global positioning system (GPS) tracker. The aim is to use the images acquired by the UAV to define the geometry of the floating cover using photogrammetry. In this manner, any changes in the geometry of the floating cover due to forces acting beneath resulting from its deployment and usage can be determined. The time-scale for these changes is in terms of weeks and months. The change in the geometry can be implemented as input conditions to a finite element model (FEM) for stress prediction. This will facilitate the determination of the state of distress of the floating cover. This paper investigates the possibility of using data recorded from a UAV to predict the strain level and assess the health of such structures. An investigation was first conducted on a laboratory sized membrane structure instrumented with strain gauges for comparison against strains, which were computed from 3D scans of the membrane geometry. Upon validating the technique in the laboratory, it was applied to a more realistic scenario: an outdoor test membrane structure and capable UAV were constructed to see if the shape of the membrane could be computed. The membrane displacements were then used to calculate the membrane stress and strain, state demonstrating a new way to perform structural health monitoring on membrane structures.

Acoustic emission (AE) is a phenomenon that occurs in materials that are exposed to stress. Defects in the material, such as cracks can grow and release energy in the form of a mechanical wave that propagates through the material. With the help of piezoelectric sensors, the mechanical wave is converted into an electrical signal. The signals are recorded by the measuring system and are available for further processing. Acoustic emission as a method that records and processes the incoming signals in real time is therefore very suitable for 24/7 long-term structural health monitoring. With new approaches in data processing, acoustic emission can be moved from the classic periodic test approach to an online monitoring process. The in-service monitoring brings measuring challenges with it, like application on hot surfaces and inside explosion hazard areas. New developments in hardware and software provide tailor-made solutions for a variety of monitoring tasks. The use of artificial intelligence algorithms helps to improve the analysis of measurement data and guarantees safe operation of pressure equipment and infrastructure around-the-clock. Some examples of continuous monitoring are shown on pressure vessels from the industry sector and on infrastructure buildings e.g., steel bridges. Also, a new lean system approach in structural health monitoring with acoustic emission is presented.

Structural damage in buildings is often initiated by small cracks in lightweight brick elements, which, if undetected, may compromise structural safety. This study developed a vibration-based classification system using the ADXL345 accelerometer, Fast Fourier Transform (FFT), and Extreme Learning Machine (ELM) for early detection of such damage. Vibration data were collected along three axes (X, Y, and Z) with excitation frequencies ranging from 10–50 Hz. FFT analysis revealed clear distinctions between intact and cracked bricks, where cracked samples exhibited higher amplitudes and multiple resonance peaks. These frequency-domain features were then processed by ELM classifier. ELM achieved high computational efficiency and demonstrated strong predictive capability, correctly classifying 7,855 intact and 4,548 cracked samples. However, it also produced 1,879 false positives and 5,100 false negatives, resulting in an RMSE of 0.548. While the model proved more accurate in identifying intact bricks, its sensitivity to crack detection remains a challenge. Overall, FFT–ELM framework shows promising potential as a fast, non-destructive, and scalable approach for structural health monitoring, with further refinements needed to improve detection accuracy of damaged materials.

Vibration-based approach for structural health monitoring of ultra-high-performance concrete bridge

The present paper takes place in the context of identification problems: the aim is to propose a new approach for the detection of damages within large structures via the deployment of a set of moving sensors. The goal of the method is to optimally control the motion of the swarm driving the sensors in the optimal measurement regions, in order to perceive the field as clean as possible and to enhance the identification of any possible irregularity along the structure. The optimal control of the sensors motion and the consequent damage identification are achieved through a two-step strategy. The first one is based on: i) models for the dynamics of the structure, for the dynamics of the sensors; ii) LQR control logic to define the optimal trajectory of the swarm. The second step includes the identification of the damage module: the process of data analysis is investigated through use of the technique based on Empirical Mode Decomposition, combined with the Hilbert-Huang Transform.KeywordsStructural Health MonitoringMoving SensorsOptimal ControlEmpirical Mode DecompositionHilbert-Huang Transform

Ultrasonic guided waves offer the possibility of inspecting large areas from a small number of sensor positions. However, inspection of complex structures is difficult as the reflections from different features overlap. Subtraction techniques appear to be a promising approach for Structural Health Monitoring (SHM) since they can identify changes in the measured signal by comparison of the recorded time trace with the available baselines for the undamaged structure. In this work, our aim is to establish whether temperature compensation techniques are also able to cope with the changes caused by liquid loading or the effects of non uniform temperature responses of materials in adhesive bonds.

We present a simulation-based classification approach for large deployed structures with localized operational excitations. The method extends the two-level Port-Reduced Reduced-Basis Component (PR-RBC) technique to provide faster solution estimation to the hyperbolic partial differential equation of time-domain elastodynamics with a moving load. Time-domain correlation function-based features are built in order to train classifiers such as Artificial Neural Networks and Support-Vector Machines and perform damage detection. The method is tested on a bridge-shaped structure with a moving vehicle (playing the role of a digital twin) in order to detect cracks’ existence. Such problem has 45 parameters and shows the merits of the two-level PR-RBC approach and of the correlation function-based features in the context of operational excitations, other nuisance parameters and added noise. The quality of the classification task is enhanced by the sufficiently large synthetic training dataset and the accuracy of the numerical solutions, reaching test classification errors below 0.1% for disjoint training set of size 7 × 103 and test set of size 3 × 103. Effects of the numerical solutions accuracy and of the sensors locations on the classification errors are also studied, showing the robustness of the proposed approach and the importance of constructing a rich and accurate representation of possible healthy and unhealthy states of interest.

Currently, strength prediction based on damage pattern recognition of fibre-reinforced composite materials mainly relies on unsupervised clustering methods, which suffer from relatively limited evaluation metrics for clustering outcomes. This study proposes a strength prediction approach for fibre-reinforced composites based on acoustic emission and supervised damage pattern recognition. Firstly, three types of acoustic emission tests were designed to capture the characteristic acoustic emission signals of pure damage modes (fibre fracture, matrix cracking, interface debonding). These signal features were utilised to construct corresponding damage pattern datasets and train a supervised model, achieving a cross-validation accuracy of 92.94%. Subsequently, based on the trained model, the acoustic emission events collected during the tensile failure process of fibre-reinforced composite were distinguished, and the residual strength was predicted using a time series prediction model, yielding performance of MAE = 0.97, RMSE = 1.59, and R 2 = 97.58%. Finally, the prediction results were compared with those derived from unsupervised clustering. The findings demonstrate that the supervised recognition-based approach delivers superior predictive outcomes. This indicates that the supervised identification method offers greater advantages in damage pattern recognition for fibre-reinforced composites. Consequently, this provides a novel approach for structural health monitoring of composite materials.

Today's commercial and military aircraft require significant manpower resources to provide operational readiness and safety of flight. Aging aircraft fleets are much in need of new and innovative health-monitoring methods to prevent catastrophic failure and reduce life-cycle costs. The key items to be addressed are describing in situ structural integrity characteristics of corrosion and barely visible impact damage (BVID) to determine the 'damage susceptibility.' This paper presents a new concept for performing onboard real-time monitoring using conductive polymer sensor array technology.