Structural Health Monitoring Techniques Research Articles

Augmented Reality-Based Real-Time Visualization for Structural Modal Identification.

In the era of aging civil infrastructure and growing concerns about rapid structural deterioration due to climate change, the demand for real-time structural health monitoring (SHM) techniques has been predominant worldwide. Traditional SHM methods face challenges, including delays in processing acquired data from large structures, time-intensive dense instrumentation, and visualization of real-time structural information. To address these issues, this paper develops a novel real-time visualization method using Augmented Reality (AR) to enhance vibration-based onsite structural inspections. The proposed approach presents a visualization system designed for real-time fieldwork, enabling detailed multi-sensor analyses within the immersive environment of AR. Leveraging the remote connectivity of the AR device, real-time communication is established with an external database and Python library through a web server, expanding the analytical capabilities of data acquisition, and data processing, such as modal identification, and the resulting visualization of SHM information. The proposed system allows live visualization of time-domain, frequency-domain, and system identification information through AR. This paper provides an overview of the proposed technology and presents the results of a lab-scale experimental model. It is concluded that the proposed approach yields accurate processing of real-time data and visualization of system identification information by highlighting its potential to enhance efficiency and safety in SHM by integrating AR technology with real-world fieldwork.

Acoustic Emission, A Non-Destructive Technique - An Overview

Abstract: With increasing number of structures approaching their design life, it became very important for the designers and operators to develop innovative Structural Health Monitoring (SHM) techniques. Structural Health Monitoring (SHM) is the process of monitoring or assessing the condition of a structure in order to gather information on its current state by tracking variables like vibration, strain, stress and other physical phenomena, responses and conditions. It seeks to assist in nondestructive evaluations aimed to detect location and extent of damage, calculate the remaining life of an asset and predict upcoming accidents. Acoustic Emission technique is a passive monitoring approach based on the detection of elastic waves in structural components generated by damages, such as the initiation and propagation of cracks, the failure of steel wires, and the failure of bonds. Its primary goal is to detect, locate, and assess the intensity of damage in a non-invasive way, both when the structure is in-service and during load tests. Its application in SHM (Structural Health Monitoring) started much later compared to other fields, such as the aerospace industry. The interest has increased because elastic waves generated by damages propagate throughout the structure; therefore, it is possible to remotely detect damages in areas that are not easily accessible to visual inspections and direct measurements

Enhancing Seismic Resilience: Evaluating Buildings with Passive Energy Dissipation Strategies

Structures are recommended to be designed and constructed with the integration of structural health monitoring techniques to ensure that they can dissipate a large amount of energy without considerable damage when subjected to earthquakes. Hysteretic (H), friction (F), viscous (V), and viscoelastic (VE) dampers were employed in this study to observe the response of buildings using the commercially available software ETABS. The effect of different dampers along with configurations on three prototype concrete buildings (3, 5, and 10-storey) was studied by performing a time history analysis. Initially, the response of the buildings was observed in terms of storey drifts, base shear, and displacement without using dampers, while gradually increasing the damping ratio from 0 to 40%. Subsequently, the response of the buildings was evaluated in terms of displacements and base shear using various types of dampers with different configurations. The analysis results demonstrated that the effectiveness of viscous and viscoelastic dampers is higher for 3 and 5-storey buildings, while friction and hysteresis dampers are more suitable for 10-storey buildings. This information enables informed decisions regarding the performance and maintenance of dampers, contributing to the overall resilience and durability of structures in seismic events.

Optimal tuning of three deep learning methods with signal processing and anomaly detection for multi-class damage detection of a large-scale bridge

Long-span bridges play a crucial role in urbanization, connecting communities across vast obstacles. Structural health monitoring techniques have been deployed on these bridges, generate large amounts of data through sensor measurements, requiring data-driven approaches like deep learning (DL) for effective analysis. However, feature extraction from time-domain vibration response signals poses challenges for DL methods. To address this, the study proposes utilizing signal processing techniques such as the multivariate empirical mode decomposition (MEMD) and Wavelet transform (WT) to extract essential features for damage classification. The incorporation of MEMD and WT aims to overcome limitations and process nonstationary and nonlinear signals effectively. Three DL techniques, long-short-term memory (LSTM), one dimensional convolutional neural network (1D-CNN), multi-layer perceptron (MLP) are tuned and applied to Structural Health Monitoring of Tianjin Yonghe Bridge (located in China) as a real-world case study, in order to detect its condition by Deep signal anomaly detection and identify types of the damage. A powerful meta-heuristic algorithm called Observer-Teacher-Learner-Based Optimization, is used to optimize both hyperparameters and architecture of each DL models. The results demonstrate that the optimally tuned DLs are successful in identifying types of damage, as well as the condition of the structure, for the Tianjin Yonghe Bridge. The average accuracy values are obtained as 98.13, 97.96, and 97.79 for 1D-CNN, LSTM, and MLP, respectively. Such optimally tuned DLs are evaluated as effective solutions for detecting damage on large-scale bridges by extracting statistical time-domain and time–frequency domain features using the WT and MEMD.

Monitoring of crack repair in concrete using spherical smart aggregates based on electromechanical impedance (EMI) technique

Cracks will inevitably occur in concrete structures or members during the construction process and service life due to aging, environmental factors, external loads, etc. To improve the strength and stability of the cracked concrete structures, many methods have been proposed to repair the cracks. However, the monitoring of the repairing process and repair quality has not been fully studied. The previous studies have proved that the spherical smart aggregates (SSAs) based on the electromechanical impedance (EMI) technique have outperformed the traditional smart aggregates (SAs) based on the EMI technique in structural health monitoring of civil structures, however, SSAs have not been applied to the monitoring of the concrete crack repair. In this work, the monitoring of the concrete crack repair using the SSAs based on the EMI technique was explored. A total of eight concrete specimens were prepared, and cracks in the concrete specimens were simulated by manually cutting under laboratory conditions. According to the principle of grouting method, two repair agents including cement paste and cement mortar were used to repair the cracks. The impedance signals of 28 d were measured, and three quantitative indicators, namely root mean square deviation, mean absolute percentage deviation, and correlation coefficient deviation were used to evaluate the quality of the concrete repair effect. The results indicate that the SSAs show excellent sensitivity and stability over the traditional SAs. In addition, the normalized values of the quantitative indicators were analyzed to distinguish the types of repair agents. A mathematical expression of exponential function was also proposed by fitting the experimental data to quantitatively evaluate and predict the repair effect of concrete cracks. Further, the influences of temperature, humidity, crack depth and width on the experimental results were analyzed and discussed. The numerical simulation was also presented to validate the reasonability of the experimental results.

Structurally embedded gradient index lens for guided wave amplification in polymers

Guided wave inspection is a commonly used technique in structural health monitoring, yet there are challenges associated with ultrasonic inspection of polymeric structures due to high material damping resulting in wave attenuation. In this work, we present a structurally embedded gradient-index phononic crystal (GRIN-PC) lens for elastic wave amplification in polyvinyl chloride (PVC) structures to overcome the attenuation problem in long-range guided wave inspection. The GRIN-PC lens is made up of cylindrical brass stubs of varying heights or diameters embedded in the PVC base structure, providing a hyperbolic secant profile of refractive index distribution transverse to the wave propagation direction. We first demonstrate flexural wave focusing in a PVC plate by implementing the embedded lens design via numerical simulations and experiments. Then, the embedded GRIN-PC lens concept is implemented to PVC pipe for multi-mode wave focusing using a single lens design which is studied through numerical simulations. The proposed GRIN-PC lens design reduces the amplitude decay due to material damping by amplifying the wave energy at the focal regions of the lens. The embedded lens concept developed for polymers can also benefit other applications requiring the transmission of wave energy in structures with high material damping.

Characterization of Fatigue Damage in Hadfield Steel Using Acoustic Emission and Machine Learning-Based Methods.

Structural health monitoring (SHM) of fatigue cracks is essential for ensuring the safe operation of engineering equipment. The acoustic emission (AE) technique is one of the SHM techniques that is capable of monitoring fatigue-crack growth (FCG) in real time. In this study, fatigue-damage evolution of Hadfield steel was characterized using acoustic emission (AE) and machine learning-based methods. The AE signals generated from the entire fatigue-load process were acquired and correlated with fatigue-damage evolution. The AE-source mechanisms were discussed based on waveform characteristics and bispectrum analysis. Moreover, multiple machine learning algorithms were used to classify fatigue sub-stages, and the results show the effectiveness of classification of fatigue sub-stages using machine learning algorithms. The novelty of this research lies in the use of machine learning algorithms for the classification of fatigue sub-stages, unlike the existing methodology, which requires prior knowledge of AE-loading history and calculation of ∆K.

A Review on the Latest Advancements and Innovation Trends in Vibration-Based Structural Health Monitoring (SHM) Techniques for Improved Maintenance of Steel Slit Damper (SSD)

A Review on the Latest Advancements and Innovation Trends in Vibration-Based Structural Health Monitoring (SHM) Techniques for Improved Maintenance of Steel Slit Damper (SSD)

AI-driven Automated Operational Modal Analysis of Bridges

The growing awareness on the daunting challenge posed by ageing civil infrastructure is fostering the increasingly frequent implementation of dense Structural Health Monitoring (SHM) systems. The Italian context represents a formidable example of this trend, especially after the tragic collapse of the Morandi Bridge in 2018 and the release of the National Guidelines on the Assessment and Management of the Risk Condition of Bridges and Viaducts in 2020. This has motivated the implementation of numerous monitoring systems all throughout the national territory, many of them involving heterogeneous and dense sensor networks. The implementation of such a vast number of sensors presents new challenges at the management and decision-making levels, particularly in the signal processing and feature extraction phases. This is particularly critical for vibration-based SHM techniques, in which classical operational modal analysis (OMA) techniques are proving inefficient for handling such large monitoring databases. As an attempt to alleviate these limitations, this contribution presents the development of an AI-driven OMA technique for rapid identification of bridges. The proposed methodology consists of a multi-task deep feedforward neural network capable of extracting the independent modal components from ambient vibration records. Trained in a supervised manner by a Second Order Blind Source Identification (SOBI) method, the developed AI model can extract both the real and complex independent modal components. The effectiveness of the presented approach is illustrated through of a real-world-bridge, the Méndez-Núñez Bridge in Granada, Spain, demonstrating great potential as a computationally efficient OMA technique for on-site edge modal identification of bridges.

Semi-supervised structural damage assessment via autoregressive models and evolutionary optimization

Strategies based on Structural Health Monitoring (SHM) allow identifying the occurrence of damage in sensitive structures, such as bridges, tall buildings, dams, stadiums, among others. However, few strategies allow determining the exact damage locations and intensities through the structure’s dynamic responses, i.e., accelerations, displacements, strains, etc. Many structures around the world are reaching their service lives and yet are still being used, as their simple replacement is economically impractical. Therefore, having an advanced SHM technique may present itself as a favorable solution for evaluating the structure’s condition under changes in their vibration properties. In this paper, the four main autoregressive models (AR, ARMA, and their exogenous input counterparts ARX and ARMAX) are combined with Differential Evolution (DE) algorithm and employed to deal with multiple time series patterns of vibration signals. The procedure of model order optimization is performed both with a proposed semi-supervised objective function and compared with the well-known Akaike criterion (AIC). The semi-supervised design consists in exploring the behavior of progressive deterioration to localize the focus of it. Damage levels are calculated for each sensor based on the Mahalanobis distance (MD) of the resultant autoregressive coefficients. This enhanced framework is applied to a three-story frame and a real-world bridge (Z24 bridge). The suggested strategy reaches similar or better damage localization in all cases, while significantly outperforming the compared literature in terms of computational cost and time, making it more promising for real-time SHM.

VIBRATION-BASED DAMAGE DETECTION FOR ONE-STORY STEEL FRAME STRUCTURE USING MODE SHAPE CURVATURE

Structural health monitoring techniques, particularly vibration-based damage detection, have gained significance in assessing civil structure condition. This paper focuses on utilising mode shape curvature for damage detection in a one-story steel frame structure. The study aims to overcome traditional inspection limitations by exploring vibration-based approaches. Experimental investigation is conducted to analyse intact and damaged structural modal behaviour. Modal analysis technique extracts modal frequencies and mode shapes, enabling analysis of mode shape curvature for damage detection and localisation. Preliminary findings show that damaged structures display deviations in mode shapes and reduced natural frequencies, providing evidence of structural damage. However, a significant issue arises near the support, where unexpected patterns emerge in the Total Damage Index (TDI) with increasing damage severity. This finding challenges the expected correlation between severity levels and TDI values, highlighting the need to consider factors like fixed supports. Misleading signs of damage in some segments underscore the importance of cautious result interpretation and accounting for noise. Future studies should focus on noise resistance, false indication mitigation, and understanding segments with fixed supports to enhance mode shape curvature analysis’s reliability for damage detection in civil structures.

A systematic review of data fusion techniques for optimized structural health monitoring

Advancements in structural health monitoring (SHM) techniques have spiked in the past few decades due to the rapid evolution of novel sensing and data transfer technologies. This development has facilitated the simultaneous recording of a wide range of data, which could contain abundant damage-related features. Concurrently, the age of omnipresent data started with massive amounts of SHM data collected from large-size heterogeneous sensor networks. The abundance of information from diverse sources needs to be aggregated to enable robust decision-making strategies. Data fusion is the process of integrating various data from heterogeneous sources to produce more useful, accurate, and reliable information about system behavior. This paper reviews recent developments in data fusion techniques applied to SHM systems. The theoretical concepts, applications, benefits, and limitations of current methods and challenges in SHM are presented, and future trends in data fusion methods are discussed. Furthermore, a set of criteria is proposed to evaluate contents and information from original and review papers in this field, and a road map is provided discussing possible future work.

The temperature effects on embedded PZT signals in structural health monitoring for composite structures with different thicknesses

Ultrasonics guided waves (GWs) are established as an effective structural health monitoring technique for detecting damage in composite structures. However, for GWs to be applied reliably in service, the effect of temperature needs to be accounted for baseline damage detection approaches. Previous studies have focused on developing temperature compensation methods for surface-mounted transducers. In this paper, an extensive investigation has been carried out to develop an effective temperature compensation method for GWs generated by embedded transducers in different thickness composites. To accomplish this, Laser Doppler Vibrometer experiments were carried out to obtain wavenumbers generated by embedded transducers and to compare them against surface mounted cases. The consistent trend observation of dispersion curves between surface-mounted and embedded PZTs serves as a foundation for conducting analysis of the embedded signals with the effect of temperature. Following that, GW propagation has been studied in three quasi-isotropic composites of 2 mm, 4 mm and 9 mm thicknesses. Based on the established temperature database with measurements from − 50 °C to 70 °C, a temperature compensation methodology has been developed and validated with the temperature difference of 30 °C. It demonstrates that the temperature effect on the embedded PZTs is lower in comparison to surface mounted PZTs, and the temperature compensation of a single thickness composite is scalable to other panels thickness. This novel methodology proves beneficial in reducing the scale of the experimental campaign required, which holds significant value for actual aeronautical structures characterized by variable composite thicknesses across different sections, such as in fuselage panels or wing boxes.

Interpretation of Bridge Health Monitoring Data from Satellite InSAR Technology

This paper presents a study on applying satellite Interferometric Synthetic Aperture Radar (InSAR) technology for the remote monitoring of road bridges and interpreting the results from a structural standpoint. The motivation behind this study arises from the widespread deterioration observed in many road bridges worldwide, leading to the need for large-scale, economic, and effective structural health monitoring (SHM) techniques. While traditional contact-type sensors have cost sustainability limitations, remote sensing techniques, including satellite-based InSAR, offer interesting alternative solutions. The objective of this study is three-fold: (i) to process InSAR data specifically for road bridges in operational conditions through the Multi-Temporal InSAR technique and extract displacement time series of reflective targets on their decks; (ii) to interpret the observed millimetric bridge displacements to verify the consistency with expected response to environmental loads and the possibility to detect unexpected behaviours; and (iii) to investigate the correlation between bridge displacements and environmental loads as temperature and river water flow variations. The study focuses on the multi-span prestressed concrete A22 Po River Bridge in Italy, utilising a dataset of X-Band HIMAGE mode Stripmap images acquired over eight years by the satellite constellation COSMO-SkyMed. The study demonstrates the effectiveness of InSAR-based SHM in detecting temperature-induced displacements and identifying different bridge spans simply by studying the sign of the correlation between displacements and temperature variation. It also reveals an unexpected behaviour in a portion of the bridge retrofitted to prevent scour issues a few years before the dataset start date. Furthermore, the correlation between pier displacements and river level variations underscores the importance of considering environmental factors and the geotechnical characteristics of the foundation soils in bridge monitoring. The results obtained from this study are significant with a view to using this satellite InSAR-based monitoring for early detection of anomalous bridge behaviour on a large scale.

Comparative Analysis between Singular Spectral Analysis and Empirical Mode Decomposition for Structural Damage Detection

Context: In recent years, thanks to technological advances in instrumentation and digital signal processing, noninvasive methods to detect structural damage have become increasingly important. Vibration-based structural health monitoring (SHM) techniques allow detecting the presence and location of damage from permanent changes in the fundamental frequencies of signals. A successfully employed method for damage detection is empirical mode decomposition (EMD). Another method, less used in this field of study, is singular spectral analysis (SSA). This paper describes both methods and presents a simulation study aimed at comparing them and identifying which one is more effective in detecting structural damage. Method: The methods of a reference study known as benchmark SHM were applied to facilitate the comparison. To evaluate the effectiveness of both methods, Monte Carlo simulation was employed. To control the random noise and other factors inherent to the simulation, the procedure was repeated 1.000 times for each type of damage. Results: In the case of severe damage, both methods showed a good performance. However, when the damage was slight, the changes in the fundamental frequency were not apparent. However, a significant change in the amplitude level was observed. In this case, SSA obtained the best results. Conclusions: The EMD and SSA methods, together with high-pass filtering, detected severe damage when the acceleration records had low or no noise. When the acceleration records were contaminated with noise, the likelihood of EMD detecting the damage decreased dramatically. One of the advantages of SSA over EMD is that, for moderate or mild damage patterns, the former does not require filters or the use of the Hilbert-Huang transform to detect damage. In general, it was found that SSA was more effective in detecting damage.

Assessing Weak Adhesion in Single Lap Joints Using Lamb Waves and Machine Learning Methods for Structural Health Monitoring

The use of adhesive joints has become increasingly popular in various industries due to their many benefits, such as low weight and good mechanical performance. However, adhesive joints can suffer from defects, one of them being weak adhesion. This defect poses a significant risk to structural integrity and can lead to premature failure, but is hard to detect using existing nondestructive testing methods. Therefore, there is a need for an effective technique that can detect weak adhesion in single-lap joints (SLJ) to prevent failure and assist in maintenance, namely in the framework of structural health monitoring. This paper presents a novel approach utilizing machine learning and Lamb Waves (LW) to determine the level of weak adhesion. Firstly, a numerical model of SLJs with different levels of weak adhesion is created and an original approach is proposed for its validation with data from real samples so that reliable LW data can further be easily generated to train and test any other data-driven algorithm for tackling damage. Secondly, a damage detection method is proposed, based on artificial neural networks and fed with simulated data, to determine the level of damage in SLJs, independent of their location. The results show that the simulation model can be validated with a small set of experimental data, being capable of replicating real damage in SLJs. Additionally, the use of simulated data in the training algorithm can increase the accuracy of the simulation model up to 26% when compared to only considering experimental data. The adopted artificial neural network for detecting weak adhesion emerges as a promising approach, yielding a precision of over 95%. Thus, machine learning and LW data can be used to improve the reliability and accuracy of adhesive bonding quality control, as well function as a technique for structural health monitoring, which can enhance the safety and durability of bonded structures.

Damage Metrics for Void Detection in Adhesive Single-Lap Joints

Structural Health Monitoring (SHM) techniques, such as Electromechanical Impedance Spectroscopy (EMIS), aim to continuously monitor structures for defects, thus avoiding the need for regular maintenance. While attention has been given to the application of EMIS in the automatic detection of damage in metallic and composite components, integrity monitoring of structural adhesive joints has been comparatively neglected. This paper investigated the use of damage metrics with electrical impedance measurements to detect defects in Single-Lap Joints (SLJs) bonded with a modified epoxy adhesive. Traditional metrics using statistical and distance-based concepts, such as the Root-Mean-Squared Deviation, RMSD, or the Correlation Coefficient, CC, are addressed at detecting voids in the adhesive layer and are applied to five different spectral frequency ranges. Furthermore, new damage metrics have been developed, such as the Average Canberra Distance, ACD, which enables a reduction of possible outliers in damage detection, or the complex Root-Mean-Squared Deviation, cRMSD, which allows for the use of both the real and imaginary components of the impedance, enabling better damage detection in structural adhesive joints. Overall, damage detection is achieved, and for certain spectral conditions, differentiation between certain damage sizes, using specific metrics, such as the RMSD or cRMSD, may be possible. Overall, the RMSD or cRMSD values from damaged SLJs tend to be double the metric values from undamaged joints.

Characterizing damage evolution of CF/PEKK composites under tensile loading through multi-instrument structural health monitoring techniques

This study investigates the damage behavior of autoclave consolidated carbon fiber/Polyetherketoneketone (CF/PEKK) laminates manufactured by the automated fiber placement (AFP) lay-up process. The damage evaluation of autoclave consolidated samples is studied using a multi-instrument nondestructive monitoring approach. The effect of autoclave consolidation on the microstructure of the laminate is examined via void analysis based on density measurement, thermal analysis, and optical microscopy. The results reveal that the void content is achieved as 0.46% and there is 81.81% increase in the degree of crystallinity following the autoclave consolidation. Moreover, acoustic emission (AE), digital image correlation (DIC), and infrared thermography (IRT) results are cross-correlated to further understand the damage development. The evolution of clustered AE data during mechanical loading is used to divide the failure of the laminate into two stages, each of which signifies a different dominancy in failure modes. Scanning electron microscopy (SEM) is employed to associate damage characteristics with failure monitoring techniques.

Propagation of material uncertainty in modal parameters and its influence in damage quantification of shear buildings

Structural health monitoring (SHM) plays a crucial role in post-disaster mitigation in investigating the serviceability of an existing structure. The physical properties, namely mass density, cross-sectional area, Poisson’s ratio, modulous of elasticity, etc., vary spatially throughout a real system. These uncertainties propagate in the modal parameters involved in SHM techniques. In this study, the elastic modulous has been considered the primary source of uncertainty. A detailed literature survey has been performed to identify the suitable probability distribution recommended for defining material uncertainty. Although the Gaussian distribution cannot replicate realistic material behaviour, its explicit implementation makes it prevalent. However, based on the principle of maximum entropy, the gamma distribution is the most appropriate recommendation among all non-Gaussian continuous distributions ranging [0, ∞). The Karhunen–Loève (KL) expansion has been adopted to discretize the stochastic field to determine the spectral mass and stiffness of a multi-damaged axially vibrating prismatic cantilever bar-type structure. Closed-form orthogonal pairs of eigensolutions of the KL expansion considering (Adhikari and Friswell, 2010) exponential covariance function have been derived. The expressions for spectral mass and stiffness for a multi-damaged cantilever bar considering material uncertainty have been developed. The uncertainty propagation in the modal properties has been estimated. The complete procedure has been followed to identify uncertainty propagation in damage severity of a common class of civil structures like shear buildings. The influence of material uncertainty in determining the damage severity of a structure with numerable degrees of freedom using a non-destructive approach has been explored. Extensive simulations have been performed to evaluate the effectiveness of the present study in a multi-damaged bar as well as shear building. Statistical parameters, namely mean and standard deviation of natural frequencies, modal displacement and damage severity have been determined. The uncertainty propagation has been reflected in the mean value for varying input stochasticity. However, the standard deviation remained consistent for undamaged as well as damaged structure irrespective of material uncertainty type. Considering gamma distribution in material stochasticity, the spread of uncertainty propagation has been more than the Gaussian distribution. However, experimental studies need to be performed further to investigate the stochastic behaviour in modal parameters of a real structure.

Anti-interference damage localization in composite overwrapped pressure vessels using machine learning and ultrasonic guided waves

This paper describes a structural health monitoring (SHM) technique for composite overwrapped pressure vessels (COPVs), which utilizes machine learning (ML) algorithms to achieve anti-interference damage localization based on ultrasonic guided waves. Firstly, this study developed a multi-channel guided wave signal automatic acquisition system and established a comprehensive dataset comprising multi-region damage/health signals from composite pressure vessels. Subsequently, based on the interaction between guided wave features and damage, a feature extraction-ML based anti-interference damage localization scheme was proposed. This scheme achieved robust damage localization through steps such as data cleaning, feature extraction, feature selection, and ML-based damage localization. Furthermore, this study introduced the guided wave-temporal convolutional network (GW-TCN) model based on deep learning method. The GW-TCN model integrates the temporal correlation and the multi-channel physical properties of guided waves, while leveraging the advantages of deep learning's adaptive feature extraction. It effectively mitigates the vibration and sensor failure interferences that mimic real operational conditions, enabling precise damage localization. Finally, through validation on multiple data samples, it was demonstrated that the model exhibits good generalization ability. The research findings will contribute to the advancement of composite pressure vessel SHM technology, paving the way for improved safety and reliability in industrial applications.