Data Driven Damage Detection Strategy Under Uncontrolled Environment

Modal tracking plays a vital role in structural health monitoring since changes in modal parameters help us understand a structure’s dynamic characteristics and may reflect the potential deterioration of structural performance. Although numerous modal parameter estimation (MPE) methods exist, it is not guaranteed that an MPE process will exclude all spurious modes and not lose any physical modes every time over a long-term monitoring period. Relatively large damping of a structure, poor data quality, and significant changes in structural modal parameters may make the estimated modal parameters spurious, missing, or misclassified. It makes long-term modal tracking semiautomated or manual, which constrains timely downstream applications such as anomaly detection, condition assessment, and decision making. This research aims to propose a long-term continuous automatic modal tracking algorithm based on Bayesian inference even when the modal parameters, damping, and data quality change significantly. Bayesian inference is used to determine the physical modes from the results of existing MPE methods. Both the modes identified from the most recent response set and the modal probability model from multiple previous response sets are considered in the Bayesian model to better determine the physical modes from the results of MPE. Moreover, the proposed algorithm requires only three extra hyperparameters compared to general modal tracking algorithms, and they can be quickly determined by a grid search method. The performance of the proposed algorithm is verified by a numerical example and a real-world civil structure Z24 Bridge benchmark.

Fiber optical sensors (FOS) have been widely used to ensure physical parameter monitoring such as strain, temperature, vibration, etc. Fiber Bragg grating (FBG) sensors are of interest mainly as they offer relatively easy integration, multiplexing capabilities, and other advantages. A topical area of investigation for FOS integration is structural health monitoring (SHM) and perimeter-security monitoring. Different objects and infrastructures have certain needs, such as long-distance (40+ km) placement and monitoring solutions, lack of active power supply availability on the site, etc. It is vital to study and develop specific FBG profiles to ensure optimal operation of FBG in security, perimeter, and SHM solutions. In this research, we have evaluated the areas and categories in which such FOS and FBGs, in particular, have been used regarding SHM and perimeter monitoring solutions. Authors have also studied, simulated, and experimentally tested various FBGs that can be implemented for the perimeter—security applications and in SHM solutions.

PurposeOne of the paramount challenges in the field of structural health monitoring (SHM) is the precise assessment of structural damage. Recently, many methods have been proposed to diagnose damage in structures using time series data. Nevertheless, these techniques are restricted in their ability to capture the bidirectional temporal and spatial relationships among the data. To remedy these shortcomings, this study proposes an advanced deep learning (DL) technique that integrates one-dimensional convolutional neural networks (1DCNN) with bidirectional long short-term memory (BiLSTM) networks, termed BiLSTM-1DCNN.Design/methodology/approachThis study proposes an advanced deep learning (DL) technique that integrates one-dimensional convolutional neural networks (1DCNN) with bidirectional long short-term memory (BiLSTM) networks, termed BiLSTM-1DCNN. The novelty of BiLSTM-1DCNN comes in its effective fusion of 1DCNN’s local feature extraction and BiLSTM’s capacity to capture long-term information from both directions (forward and backward).FindingsValidation using a dataset from the Nam O steel truss bridge demonstrates that the proposed method surpasses conventional models, including 1DCNN (87.9%), LSTM (72.5%), BiLSTM (76.1%) and LSTM-1DCNN (91.1%), achieving an accuracy rate of 96.4%. This approach provides a significant advancement in SHM, paving the way for more accurate and reliable damage detection.Research limitations/implicationsThe study’s limitations include potential overfitting due to the model’s complexity and the high computational resources required. The BiLSTM-1DCNN model’s performance is also influenced by the quality and quantity of the training data as well as the specific characteristics of the dataset. Additionally, while the model performs well in detecting damage in the Nam O steel truss bridge, its generalizability to other types of structures and environmental conditions remains untested.Practical implicationsThe BiLSTM-1DCNN model offers significant practical benefits for structural health monitoring by enhancing damage detection accuracy. Its ability to effectively capture both local features and long-term temporal dependencies makes it a valuable tool for real-time monitoring and early detection of structural issues. This can lead to more timely maintenance actions, potentially reducing repair costs and improving safety. The model’s high accuracy in detecting damage can also support infrastructure management decisions, contributing to better resource allocation and enhanced overall safety of critical structures.Social implicationsThe BiLSTM-1DCNN model’s advanced damage detection capabilities have positive social implications, such as improving the safety and reliability of public infrastructure like bridges. Enhanced structural health monitoring can reduce the risk of catastrophic failures, protecting lives and reducing accidents. By providing more accurate and timely assessments, the model can also lead to more efficient use of maintenance and repairs, ensuring that resources are allocated effectively.Originality/valueThe originality of the BiLSTM-1DCNN model lies in its innovative integration of one-dimensional convolutional neural networks (1DCNN) with bidirectional long short-term memory (BiLSTM) networks. This unique combination leverages 1DCNN’s strength in local feature extraction and BiLSTM’s capacity to capture temporal dependencies in both directions, addressing the limitations of existing methods. The model’s high accuracy in detecting structural damage, as demonstrated by its performance on the Nam O steel truss bridge dataset, highlights its value in advancing structural health monitoring technologies and offers a significant improvement over traditional approaches.

An innovative wireless passive system for impact detection on large-scale composite airframe structures is presented. The wireless system is designed to operate with a sensor network for onboard of aircraft for structural health monitoring, of composite airframe. The wireless systems efficient design allows for low power consumption, wireless communication capability, system robustness and large sensing area. The system is evaluated on a large-scale stiffened composite fuselage under different operational conditions. It is demonstrated that it is possible to detect impact events with different impact energy levels and impact locations over a large monitoring area. This work provides a potential solution for aircraft on-board structural health monitoring with no human intervention. This sensing system can be also adapted to other Internet of Things and structural health monitoring applications.

<ns3:p>Assess the thermomechanical performance of pultruded glass-fibre-reinforced polymer (GFRP) rods containing an embedded distributed fibre-optic sensor (DFOS) for structural health monitoring (SHM). Quantify the impact of integrating the sensor on the curing behaviour, thermal stability and mechanical properties, and compare this with nominally identical rods without a sensor.Two rod variants were pultruded: one containing a sensor (OS-GFRP) and one without (No-OS-GFRP). The epoxy matrix was tuned using rheology, and the DFOS was embedded on axis without a protective coating. Differential scanning calorimetry (DSC) was employed to analyse the glass transition, residual curing, and degradation onset. It was followed by quasi-static tests (tensile, three-point bending and short-beam shear), while Charpy impact tests were used to quantify energy absorption. Microscopic studies (optical and SEM-EDS) examined the quality of the interphase and the presence of defects.The integration of embedded Distributed Fibre Optic Sensing (DFOS) was achieved without materially compromising the composite’s structural integrity or load-bearing capacity. Thermally, DFOS did not systematically reduce the glass transition temperature or thermal stability. Mechanically, while the axial modulus decreased by approximately 6% and shear properties were modestly lower, the mean tensile strength was maintained, flexural strength increased by ~8%, and impact energy absorption rose by 9% with less scatter. Microscopy revealed that minor local interphase perturbations, such as micro-voids, were consistent with the small penalties to shear properties. Overall, the presence of DFOS enables sensing functionality, with any compromises being minor and predictable, and process tuning can effectively mitigate manufacturing inconsistencies.The observed differences, particularly with regard to shear and scatter, suggest that the interphase is sensitive to both curing kinetics and local defects. Therefore, future work should focus on optimising the curing process around the optical fibre, refining the interphase chemistry, and investigating fatigue, creep, and durability in alkaline and concrete environments.Pultruded GFRP rods with on-axis distributed fibre-optic sensors (DFOS) are a robust, easy-to-install solution for structural health monitoring (SHM) of concrete and civil infrastructure. They provide distributed strain and temperature measurements with minimal impact on structural performance, enabling data-driven maintenance and safety.Demonstrates a production-feasible route to integrate DFOS during pultrusion, links DSC-diagnosed local curing phenomena to small but interpretable mechanical deltas, and evidences that embedded sensing can coexist with near-baseline thermomechanical properties in GFRP rods.</ns3:p>

This paper presents an experimental study on the detection and localization of damage in a steel plate using vibration-based methods. Dynamic impulse tests were conducted on both undamaged and damaged plate to determine changes in modal parameters, such as eigenfrequencies and mode shapes. Several damage detection methods, including the Modal Assurance Criterion (MAC), Coordinate Modal Assurance Criterion (COMAC), Mode Shape Curvature (MSC), Mode Shape Curvature Square (MSCS), and Damage Index (DI), were applied. The results showed that while MAC and COMAC effectively detected damage, they did not provide information about the location. MSC and MSCS indices demonstrated improved damage localization, with the MSCS being particularly effective. The DI index provided the clearest and most accurate representation of the damage location. These findings highlight the potential of these methods for non-destructive testing and structural health monitoring.

Growing incidents of structural damage and failures underscore the urgent need for more advanced Structural Health Monitoring (SHM) solutions. While Multi-Temporal Interferometric Synthetic Aperture Radar (MT-InSAR) has revolutionised SHM by enabling automated, long-term, and large-scale displacement monitoring of structures using Persistent Scatterers (PSs), its applicability is often constrained by the unpredictable spatial distribution of PSs. Conventional suitability assessments that rely primarily on PS density fail to account for the underlying structural behaviours, limiting their reliability. This paper introduces a novel structural-based inverse approach that uniquely integrates MT-InSAR characteristics with structural response modelling to overcome these limitations. Unlike existing approaches, the method explicitly evaluates whether observed surface displacements adequately represent a target damage mechanism by comparing outputs from a pseudo sensor with those from a virtual MT-InSAR sensor. If this condition is satisfied, it then determines the minimum required number and optimal spatial arrangement of ideal PSs using modified pivoted QR factorisation, where satellite-induced positional uncertainties are rigorously modelled through Radial Basis Function kernels. The proposed method was validated on a quay wall in Amsterdam using Finite Element Method (FEM) simulations of three distinct damage mechanisms. Results demonstrate its unique capability to quantitatively assess displacement representativeness and to pinpoint ideal PSs for robust monitoring. Leveraging these insights, the method was further applied to evaluate MT-InSAR monitoring feasibility across Amsterdam’s historic centre, successfully identifying quay wall segments amenable to reliable observation. This work represents a significant advancement in MT-InSAR-based SHM, providing a more targeted and structurally informed approach for real-world infrastructure monitoring. • Developed a structural-based inverse approach to evaluate MT-InSAR for SHM. • Integrates structural information with MT-InSAR position uncertainties. • Overcomes limitations of PS-density methods via structure-informed evaluation. • Scalable for large-region SHM, demonstrated using MT-InSAR data from Amsterdam. • Enables intelligent SHM by linking PS distributions to structural mechanisms.

A vibration-based approach for health monitoring of tie-rods under uncertain environmental conditions

As newer and more reliable ways of construction were developed, civilization began to spread out further and retain functional infrastructure for longer periods of time.[...]

The aim of the present paper is to evaluate structural health monitoring (SHM) techniques based on modal analysis for crack detection in small wind turbine blades. A finite element (FE) model calibrated to measured modal parameters will be introduced to cracks with different sizes along one edge of the blade. Changes in modal parameters from the FE model are compared with data obtained from experimental tests. These comparisons will be used to validate the FE model and subsequently discuss the usability of SHM techniques based on modal parameters for condition monitoring of wind turbine blades.

This paper proposes a hybrid structural health monitoring (SHM) solution for a smart composite patch repair for aircraft structures based on piezoelectric (PZT) and fibre optic (FO) sensors to monitor the integrity of a the bondline and detect any degradation. FO sensors are used to acquire guided waves excited by PZT transducers to allow the advantages of both sensor technologies to be utilised. One of the main challenges of guided wave based detection methodologies is to distinguish the effect of temperature on the propagating waves, from that of an existing damage. In this research, the application of the hybrid SHM system is tested on a composite step sanded repair coupon under operational condition (temperature variation) representative of an aircraft for the first time. The sensitivity of the embedded FO sensor in recording the strain waves is compared to the signals acquired by PZT sensors under varying temperature. A novel compensation algorithm is proposed to correct for the effect of the temperature on the embedded FO sensor spectrum in the hybrid set-up. The repaired specimen is then impacted with a drop mass to cause barely visible impact damage (BVID). The hybrid SHM system is then used to detect the damage, and its diagnosis results are compared to a PZT only based smart repair solution. The results show promising application of the hybrid solution for monitoring bondline integrity as well as highlighting challenges of the embedding of FO sensors for a reliable and repeatable diagnosis.

With the advancement of aerospace technology, the importance of Structural Health Monitoring (SHM) in ensuring the safety of critical equipment has become increasingly evident. Nickel-based superalloys are widely utilized in key components such as turbine blades and turbine disks due to their exceptional high-temperature performance. Accurate measurement of residual stress is crucial for enhancing material reliability and extending the service life of components, particularly in single-crystal nickel-based superalloys where measurement becomes complex due to anisotropy. In this study, a novel method based on a particle swarm optimization algorithm is proposed to improve the precision of crystal orientation measurement and pole figure calibration. This method establishes a local extremum filtering technique and a standard pole figure model, thereby optimizing the measurement process and addressing the limitations of traditional methods when dealing with high-index crystal planes. Experimental validation is conducted on single-crystal turbine blades subjected to different shot peening intensities, demonstrating significant improvements in measurement efficiency and accuracy. This approach provides a new solution for structural health monitoring in the aerospace field.

ABSTRACTThe structural stiffness of a blade changes when it is defective, which affects its modal parameters. Consequently, modal parameters can be crucial to investigating defects. Therefore, developing a model that can accurately analyze the modal parameters of healthy and defective blades is essential. This study proposes a high‐fidelity finite element (FE) model development method based on multiobjective optimization. Three 10‐kW‐class wind turbine blades were manufactured, and the modal parameter changes due to debonding damage were measured. The initial FE model was constructed using structural drawings and considering specific material properties. Subsequently, the modal analysis results were compared with the experimental results. The analysis errors of normal and abnormal blades were expressed as cost functions and multiobjective optimization was performed. Machine learning–based predictive models facilitated time‐ and cost‐effective optimization, enabling modal updating that simultaneously reflects modal parameter changes for various blade models. Because accurately predicting the dynamic characteristics of blades by various defect locations and sizes is crucial for blade damage detection, the proposed method is significant for damage detection research.

With the continuous advancement of infrastructure development, ensuring the health and safety of existing structures has become increasingly critical. Structural Health Monitoring (SHM) plays a vital role in assessing the integrity and longevity of buildings, bridges, and other infrastructures. However, traditional monitoring methods often face challenges related to efficiency, accuracy, and cost-effectiveness. The rapid development of Artificial Intelligence (AI) has opened new opportunities for SHM, offering intelligent, automated, and highly precise monitoring solutions. By integrating AI with SHM, it is possible to enhance detection accuracy, improve predictive maintenance, and significantly reduce operational costs. This paper aims to provide a comprehensive summary of AI technologies that have been successfully applied in the field of SHM. By reviewing current advancements, we seek to contribute to the ongoing development of intelligent monitoring systems and offer new perspectives on the future integration of AI in SHM.

Strain is an important parameter reflecting structural state, which is particularly important in the field of structural health monitoring (SHM). It can be used to evaluate the mechanical properties, failure behavior, crack development and residual stress of structural members and materials. It is particularly important in the field of structural health monitoring (SHM). In this paper, a new type of large gauge strain sensor is proposed. The proposed sensor is based on micro vision and uses a camera to capture small displacement. The packaging structure of strain sensor with sensing gauge length of about 50 cm is designed. In order to realize the monitoring in the field environment, the microscopic images in the experiment are obtained by webcam, which has broad application prospects. In the field of view of the camera, the maximum distance that the probe in the sensor can move is certain, but when the sensing gauge distance increases, the accuracy of strain measurement will be improved. The strain data obtained by the sensor is compared with the data obtained by FBG sensors to verify the measurement accuracy. It is found that the measurement accuracy is suitable for SHM of infrastructure.