Damage Identification Research Articles

Damage identification of truss bridges based on feature transferable digital twins

In this study, a novel damage identification method based on feature transferable digital twins is proposed to improve the damage identification accuracy of truss bridges. Specifically, a finite element model is employed as a benchmark digital model to obtain simulated data for multiple types of truss damage scenarios. The simulated data from the model and the measured signals from the truss bridge are fed into the deep residual sub-domain adaptation network for feature alignment to identify truss bridge damage. The effectiveness of the proposed method is verified by a truss experiment, where the classification accuracies of the training and validation datasets reach more than 80 % and 77 %, respectively. The classification accuracy of the method is maximally improved by 54.51 % compared to conventional identification approaches. The results show that the method has the potential to extract and transfer knowledge of damage patterns from finite element models to identify truss bridge damage.

A novel damage identification method based on acceleration response sensitivity and finite element model updating: Numerical and experimental

The utilization of time-domain data for structural damage diagnosis and finite element model updating has several benefits, such as direct implementation of the measured data with no requirement for domain changing and susceptibility to structural damages. This study introduces a straightforward sensitivity relation for the measured acceleration response, avoiding the requirement for computational techniques like direct differentiation methods. The proposed equation establishes a linear relationship between variations of the structural parameters and structural responses. The proposed sensitivity equation operates at the level of improved equations and exhibits greater accuracy compared to the current approaches. The numerical evaluation of the proposed sensitivity equation on two offshore jacket platforms reveals the accuracy of the proposed method. Additionally, an experimental case study to examine the efficacy and validation of the introduced sensitivity relation in real-world settings demonstrates the procedure’s viability. The numerical and experimental results reveal the accuracy of the proposed sensitivity equation.

SVM-assisted damage identification in cantilever steel beam using vibration-based method

SVM-assisted damage identification in cantilever steel beam using vibration-based method

Entropy Wavelet-Based Method to Increase Efficiency in Highway Bridge Damage Identification

Highway bridges are crucial civil constructions for the transport infrastructure, which require proper attention from the corresponding institutions of each country and constant financing for their adequate maintenance; this is important because different types of damage can be generated within these structures, caused by natural disasters, among other sources, and the heavy loads they transport every day. Therefore, the development of simple, efficient, and low-cost methods is of vital importance, allowing us to identify damage in a timely manner and avoid bridges collapsing. As reported in a previous work, the wavelet energy accumulation method (WEAM) and its corresponding application in the Rio Papaloapan Bridge (RPB) represented an important advance within the field. Despite identifying damage in bridges with precision and at a low cost, there are several aspects to improve in that method. Therefore, in this work, that method was improved, eliminating several steps, and meaningfully reducing the computational burden by implementing an algorithm based on the Shannon entropy, thus giving way to the new entropy wavelet-based method (EWM). This new method was applied directly with regard to the real-life RPB, in both its healthy and damaged conditions. Also, its corresponding numerical model based on the finite element method in its healthy condition and different damage scenarios were carried out. The results indicate that the new EWM retains the advantages of WEAM, and it allows for damage identification to be completed more efficiently, increasing the precision by approximately 0.11%, and significantly reducing the computing time required to obtain results by 5.67 times.

Damage Identification of Simple Supported Bridges Under Moving Loads Based on Variational Mode Decomposition and Deep Learning

Aiming at rapid and economical damage detection of a large number of simple supported bridges, a new structural damage identification method under moving load based on variational mode decomposition (VMD) and deep learning is proposed. Firstly, a moving vehicle is used as an exciting load to invoke structural damage feature and enhance the signal-to-noise ratio, and the structural vertical acceleration response is extracted by a finite element simulating analysis under various damage cases. In order to simulate the influence of noise and expand the samples, Gaussian white noise is added to the extracted data, and then the response signal is decomposed into a series of intrinsic mode functions (IMFs) using VMD, and the optimal IMF component is selected as the damage sample of the structure. Then, a one-dimensional convolutional neural network (CNN) model is built and trained by the various samples of damage. The vibration response of the practical bridge is processed and inputted by the trained CNN model to identify the location of the damage and degree of the structure. Finally, the effectiveness and anti-noise performance of the proposed method are verified through numerical analysis and a simply supported beam bridge model experiment. The results show that the average identification accuracy of the numerical simulations and experimental is 93.4% and 86.8% with 20% Gaussian white noise, respectively. Sensors at different locations have almost the same identification effect for various cases of damage, so it is possible to identify structural damage only using a small amount of accelerometer.

Diagnosis of retinal damage using Resnet rescaling and support vector machine (Resnet-RS-SVM): a case study from an Indian hospital.

This study aims to address the challenge of identifying retinal damage in medical applications through a computer-aided diagnosis (CAD) approach. Data was collected from four prominent eye hospitals in India for analysis and model development. Data was collected from Silchar Medical College and Hospital (SMCH), Aravind Eye Hospital (Tamil Nadu), LV Prasad Eye Hospital (Hyderabad), and Medanta (Gurugram). A modified version of the ResNet-101 architecture, named ResNet-RS, was utilized for retinal damage identification. In this modified architecture, the last layer's softmax function was replaced with a support vector machine (SVM). The resulting model, termed ResNet-RS-SVM, was trained and evaluated on each hospital's dataset individually and collectively. The proposed ResNet-RS-SVM model achieved high accuracies across the datasets from the different hospitals: 99.17% for Aravind, 98.53% for LV Prasad, 98.33% for Medanta, and 100% for SMCH. When considering all hospitals collectively, the model attained an accuracy of 97.19%. The findings demonstrate the effectiveness of the ResNet-RS-SVM model in accurately identifying retinal damage in diverse datasets collected from multiple eye hospitals in India. This approach presents a promising advancement in computer-aided diagnosis for improving the detection and management of retinal diseases.

Evaluation of novel PCR-based method to assess gill injuries in fish caused by the cnidarian Ectopleura larynx

Gill disease is a major threat to aquaculture of Atlantic salmon, with an unknown and likely underestimated contribution from cnidarians such as jellyfish and biofouling hydroids. To better understand the risk and thus enable mitigation, technology for the certain identification of cnidarian-related gill damage is needed. We used the hydroid Ectopleura larynx in a case study to determine whether the exposure of salmon to nematocyst-bearing hydrozoans can be deducted via non-destructive PCR-based methods. In a field experiment, we evaluated (i) whether swabbing the inside of the gill operculum in farmed Salmo salar and subsequent PCR analysis can provide quantifiable information about the presence of E. larynx material in the gill chamber and, if so, (ii) whether the screening results correlate with histological assessments of gill damage. The developed PCR methods were able to detect the presence of biofouling hydroids in ambient water. However, despite exposure to suspended hydroid particle concentrations that did result in gill damage in some salmon, quantitative PCR results did not correlate with histological gill assessments. For opercular swabs to serve as a diagnostic tool for detecting biofouling-mediated gill damage in live salmon, increased specificity of genetic markers and improved sampling methods are needed.Animal trial permit no. 24252 (granted 06.07.2020, Norwegian Food Safety Authority).

A New Approach to Structural Damage Identification Based on Power Spectral Density and Convolutional Neural Network

In the field of structural health monitoring, vibration-based damage identification remains a formidable challenge. Key to this challenge is the establishment of a reliable association between observed vibration characteristics and the actual state of structural damage (e.g. stiffness reduction). This association not only accurately indicates the presence of damage, but also the location and severity of the damage. To solve this complex pattern identification problem, a large number of approaches, including deep learning, have emerged in recent years. In this paper, we propose a new structural damage identification method that utilizes the vibration information of the structure and a convolutional neural network based on Alex NET improvement. The method consists of calculating the acceleration response power spectral density of damaged and undamaged structures under impact loading separately, and then making a difference between the two power spectral data, and subsequently introducing these power spectral difference data into the convolutional neural network for training. The use of power spectral density analysis as a preprocessing step converts the time-domain signals into frequency-domain signals, and this conversion allows the convolutional neural network to capture and learn from the specific frequency characteristics of the data, thus facilitating the learning process of the neural network model. In this paper, the effectiveness of the method is critically evaluated through numerical simulation and experimental validation, and 3% and 5% noise are added to the numerical study to test the robustness of the method. During the convolution neural network training process, the optimal training mean squared error (MSE) is [Formula: see text] in the case of no noise addition; the optimal training MSE is [Formula: see text] in the case of noise addition. Both the results of simulations and experiments confirm the high accuracy and good robustness of the method in localizing structural damage.

Damage Identification of Full-Scale Steel Truss Structure Based on Model Condensation and Mean-Value Normalization Regularization Techniques

Structural health monitoring and damage identification aim to detect the internal damage and evaluate the health conditions of the practical engineering structure, which has been the most popular research field for several decades. The sensitivity-based method incorporated with the regularization techniques is the classical and useful approach, and it can obtain accurate damage detection results. However, with the development of civil engineering structures, this classical method faces two problems: one is it is only applied to simple structures rather than full-scale structures, and second is the iterative calculation efficiency is lower. Therefore, aiming at these drawbacks, the two improvement strategies have been introduced to the original method for its enhancement in the application potential and computational efficiency. The proposed method has been verified based on two examples, i.e., a numerical steel truss with 144 elements and a full-scale experimental steel truss with 160 elements. The results prove that the proposed method has better efficiency and good application potential in the practical full-scale engineering structure.

Towards a comprehensive damage identification of structures through populations of competing models

Model-based damage identification for structural health monitoring (SHM) remains an open issue in the literature. Along with the computational challenges related to the modeling of full-scale structures, classical single-model structural identification (St-Id) approaches provide no means to guarantee the physical meaningfulness of the inverse calibration results. In this light, this work introduces a novel methodology for model-driven damage identification based on multi-class digital models formed by a population of competing structural models, each representing a different failure mechanism. The forward models are replaced by computationally efficient meta-models, and continuously calibrated using monitoring data. If an anomaly in the structural performance is detected, a model selection approach based on the Bayesian information criterion (BIC) is used to identify the most plausibly activated failure mechanism. The potential of the proposed approach is illustrated through two case studies, including a numerical planar truss and a real-world historical construction: the Muhammad Tower in the Alhambra fortress.

Feature extraction based on dynamic response measurements for structural damage identification: a comparative study

ABSTRACT Sudden unexpected loads, such as wind and earthquakes, can cause significant damage and notable changes in the characteristics of structures. Additionally, unfavorable environmental conditions can lead to erosion and deterioration of materials and structural integrity. Therefore, structural health monitoring (SHM) and damage identification have become critical concerns in civil engineering. Feature extraction from dynamic response measurements is a crucial aspect of structural damage identification. Various methods and techniques have been developed to extract features for identifying damage and monitoring the health of structures. This paper presents a comparative study of three different damage-sensitive features: resonant frequency, discrete wavelet transform component energy (DWTCE), and wavelet packet transform component energy (WPTCE), which are used in damage identification. The displacement and acceleration responses were used in the feature extraction process. This study assesses the sensitivity of each feature to structural damage using a derivative-based method. The results showed that WPTCE extracted from the acceleration response data can effectively capture structural damage due to its high sensitivity.

Significance of Using Scanning Electron Microscopy with Energy Dispersive X-ray Spectrometry (SEM-EDX) for Analysis of Evidence Material in Forensic Sciences

Forensic applications of Scanning Electron Microscopy (SEM) are found mostly in areas where there is a need for good imaging at relatively high magnifications. SEM enables the forensic scientist to examine specimens at much higher magnification than those possible with optical microscopy and without the difficulties of specimen preparation associated with conventional electron microscope. Physicochemical examinations of gunshot residues, called also chemical ballistics, are helpful, e.g. in identification of damages and injuries as the effect of the use of firearms (with indicating the entrance and exit of projectile), estimation of the shooting distance and also establishing, whether a person has used a firearm. It is discussed in details that Scanning Electron Microscopy with Energy Dispersive X-Ray Spectroscopy (SEM-EDX) can serve as a powerful tool for forensic scientists to classify and discriminate evidence material because they can simultaneously examine the morphology and the elemental composition of objects.

Drive-by Bridge Damage Detection Using Continuous Wavelet Transform

Bridges serve as vital engineering structures crafted to facilitate secure and effective transportation networks. Throughout their life-cycle, they withstand various factors, including diverse environmental conditions, natural hazards, and substantial loads. Recent bridge failures underscore the significant risks posed to the structural integrity of bridges. Damage detection techniques, being core components of structural health monitoring, play a crucial role in objectively assessing bridge conditions. This article introduces a novel framework for identifying damage in bridges utilizing continuous wavelet analysis of accelerations recorded using two sensors mounted on a vehicle traversing the bridge. The proposed method leverages changes in the static response of the bridge, which has proven to be more sensitive to damage than its dynamic counterpart. By doing so, the method eliminates the reliance on modal parameters for damage identification, addressing a significant challenge in the field. The proposed framework also addresses key challenges encountered by drive-by monitoring methods. It mitigates the adverse effects of road roughness by utilizing residual accelerations and efficiently detects and locates damage even in the absence of corresponding data from an undamaged bridge. Numerical investigations demonstrate the robustness of the proposed method against various parameters, including damage location and extent, vehicle speeds, road roughness levels, different boundary conditions, and multi-damage scenarios.

LSTM-Based Autoencoder with Maximal Overlap Discrete Wavelet Transforms Using Lamb Wave for Anomaly Detection in Composites

Lamb-wave-based structural health monitoring is widely acknowledged as a reliable method for damage identification, classification, localization and quantification. However, due to the complexity of Lamb wave signals, especially after interacting with structural components and defects, interpreting these waves and extracting useful information about the structure’s health is still a major challenge. Deep-learning-based strategy offers a great opportunity to address such challenges as the algorithm can operate directly on raw discrete time-domain signals. Unlike traditional methods, which often require careful feature engineering and preprocessing, deep learning can automatically extract relevant features from the raw data. This paper proposes an autoencoder based on a bidirectional long short-term memory network (Bi-LSTM) with maximal overlap discrete wavelet transform (MODWT). layer to detect the signal anomaly and determine the location of the damage in the composite structure. MODWT decomposes the signal into multiple levels of detail with different frequency resolution, capturing both temporal and spectral features simultaneously. Comparing with vanilla Bi-LSTM, this approach enables the model to greatly enhance its ability to detect and locate structural damage in structures, thereby increasing safety and efficiency.

Damage assessment of High-Stress brittle surrounding rock masses in a deep Large-Span High-Sidewall underground Cavern: In situ measurement and numerical simulation

Excavation within high-stress brittle rock masses often encounters severe problem of structural damage in deep underground engineering, necessitating a significant scientific demand for accurately assessing the damage to surrounding rock masses through in-situ measurement and numerical simulations. This study reports detailed findings from an exhaustive investigation on the damage characteristics and underlying mechanisms in the high-stress brittle surrounding rock masses during excavation at the Shuangjiangkou (SJK) underground caverns. These findings were obtained through a comprehensive long-term in situ measurement using multi-point extensometer monitoring, borehole digital optical televiewer observing, and acoustic testing. Based on a deep understanding of the damage and failure mechanisms peculiar to the SJK high-stress brittle surrounding rock masses, a new damage index specifically designed for high-stress brittle rock masses was developed. This index is formulated by incorporating the failure approach concept into a modified Hoek−Brown criterion adapted for high-stress brittle rock masses. Comparison between the numerical predictions and in situ measuring results of the excavation damage zones during layered excavation of the SJK underground powerhouse revealed remarkable concordance. This consistency validates that the newly proposed damage index has good applicability and reliability for quantifying excavation-induced damage in high-stress brittle surrounding rock masses. These research findings are poised to provide valuable insights into the damage identification of brittle surrounding rock masses subjected to high-stress excavation, contributing to optimize excavation design and enhance the safety and sustainability of underground engineering projects.

Condition monitoring of mooring systems for Floating Offshore Wind Turbines using Convolutional Neural Network framework coupled with Autoregressive coefficients

This research presents a novel approach proposed for the monitoring of mooring systems in Floating Offshore Wind Turbines (FOWTs), employing a combination of Convolutional Neural Networks (CNNs) and Auto-Regressive (AR) models. CNN finds broad application in monitoring intricate structures, as they adeptly handle noisy response data without necessitating profound domain expertise. The precision of CNNs relies on the extraction of meaningful features from input data, necessitating meticulous data curation and labeling for optimal computational efficiency and accurate estimation. Emphasis is placed on the preference for feature-rich small datasets over voluminous yet sparse datasets, aiming to enable CNNs to discern crucial patterns more effectively and mitigate issues such as overfitting and extensive preprocessing.The novelty of the proposed approach lies in the integration of AR models, which serve to compress data and enhance damage-sensitive characteristics in the input for CNNs. This integration involves deploying regression models fitted to historical responses, parameterized with AR coefficients sensitive to damage, and further classifying severity using CNNs. The sequential nature of this approach addresses challenges such as vanishing/exploding gradients, particularly for extended historical data, while also attenuating the impact of noise and irrelevant information through data compression.The study explores the effectiveness of the coupled AR-CNN method in monitoring FOWT mooring lines, with a specific focus on two levels of damage identification: detection with classification and damage severity across diverse damage and operational scenarios. The modified methodology exhibits superior outcomes by conducting a performance analysis against traditional CNNs and other machine-learning methods, highlighting the potential of the AR-CNN strategy to improve the precision of FOWT mooring line condition monitoring. These findings underscore the AR-CNN strategy’s potential to enhance the accuracy of FOWT mooring line condition monitoring.

Damage Identification in Steel Girders of Highway Bridges Utilizing Vibration Based Methods and Convolution Neural Network in the Presence of Noise

Damage Identification in Steel Girders of Highway Bridges Utilizing Vibration Based Methods and Convolution Neural Network in the Presence of Noise

Spectral Analysis of Pink Mealy Bug Damaged Mulberry Plants Using Hyperspectral Radiometry

Mulberry (Morus spp.) foliage forms a sole food to silkworms, Bombyx mori L. Its quality plays a pivotal role in superior silk fiber production. Like any other plants, mulberry is susceptible to detrimental diseases and infested by insect pests. Many sucking pests cause damage to mulberry among which, pink mealybug causes severe damage leading to significant loss in mulberry leaf yield (12-25 %). Conventional approaches to assess and manage damage caused by pink mealybugs demand substantial manpower and expertise, resulting in time-consuming and inefficient processes. However, leveraging modern tools and technologies like remote sensing has emerged as a remarkably effective strategy for crop protection and management.Specifically, hyperspectral remote sensing proves invaluable by furnishing insights into the biophysical and biochemical traits of crops. This is achieved through the recording of narrow wave bands that reflect specific plant characteristics. The main objectives were to understand the spectral reflectance characteristics of healthy and pink mealy bug damaged mulberry crops, to identify the optimal spectral bands and vegetative indices for detecting pink mealy bug damage in mulberry and to explore the feasibility of estimating pest damage levels based on the spectral properties of mulberry crops. Top of FormAt the mulberry garden of the Department of Sericulture, Tamil Nadu Agricultural University (TNAU), Coimbatore, studies were conducted on spectral analysis of pink mealy bug damaged mulberry plants using hyperspectral radiometry during 2018. In this trial, at 15-day intervals during the active damage stage, the percentage damage was observed in plots infested with pink mealy bugs and those that were healthy. Measurements of spectral reflectance across various wavelengths and vegetation indices (VIs) were taken using a hyperspectral radiometer. The analysis included evaluating the sensitivity of different spectral bands and VIs to pink mealybug damage, along with employing correlation and regression analyses between the extent of pest damage and the VIs. The findings revealed distinct differences in the spectral reflectance profiles of mulberry plants compared to their healthy counterparts. Typically, affected plants exhibited increased reflectance in the red (620–680 nm) and green (520–590 nm) bands and reduced near-infrared (NIR) reflectance (770–860 nm). The average values of the Normalized Difference Vegetation Index (NDVI), Green Red Vegetation Index (GRVI), and Ratio Vegetation Index (RVI) were significantly lower in the pink mealybug-damaged plants across all measurements. Notably, red reflectance demonstrated the greatest sensitivity to pink mealybug-induced damage. The study highlighted the Simple Ratio (SR) index as particularly effective for identifying pest damage. Damage estimation by pink mealybugs was refined using linear regression models based on spectral indices, specifically NDVI, RVI, and GRVI. The correlation intensity analysis pinpointed the green region at 516.73 nm as showing the most significant negative correlation (r = -0.02), whereas the highest positive correlation with pink mealybug damage was observed in the NIR region (r = 0.77), underscoring the precise wavelengths and indices most indicative of pest impact. Thus, using hyperspectral radiometry identification of damage caused by pink mealy bug possible, through analysis of spectral bands and indices.

Damage localization on reinforced concrete slab structure using electromechanical impedance technique and probability-weighted imaging algorithm

Damage localization plays a key role in structural damage identification and health monitoring. This paper proposed a new damage localization approach using electromechanical impedance/admittance (EMI/EMA) technique integrated with probability-weighted imaging algorithm based on Gaussian distribution. The proposed approach comprises five steps namely measurement of the EMA signature from an array of piezoelectric ceramic lead zirconate titanate (PZT) transducers, computation of statistic damage indicator, establishment of regression model for the indicator, damage visualization via Gaussian distribution and final damage localization. Experimental validation of the approach was conducted on a reinforced concrete (RC) slab with artificial crack damages detected by using an array of surface-bonded PZT patches. Comparative studies on localization accuracy were performed by utilizing root mean square deviation (RMSD), baseline-changeable RMSD namely RMSDk, mean absolute percentage deviation (MAPD) and correlation coefficient (CC). Experimental results demonstrated that the proposed approach could achieve precise localization of concrete crack with error as small as 0 mm, and that using RMSDk index exhibited the highest localization accuracy in average. The proposed approach promoted the capability of the EMI technique in characterization of concrete structural damages.

Study on Damage Inference of Parker Trusses Based on Bayesian Principles

The assessment of the health condition and safety of engineering structures is currently a research focus in the field of civil engineering. The traditional deterministic model for damage recognition is limited by the fine reading of field inspections and the accuracy of experts, resulting in a low recognition rate. Structural damage identification methods that consider uncertainty have been developed due to modelling errors, observation noise, system time variability, and other factors that lead to uncertainty. This study focuses on the Parker truss structure, and a two-dimensional planar finite element model is established by setting various key parameters such as prior distribution, stiffness, modulus of elasticity, node distribution, and external loading. The model is updated using the Bayesian updating principle. This principle is then combined with the finite element model. Opensees software is used for programming, and the Monte Carlo random sampling technique is used for structural damage inference. The study results demonstrate that the method can accurately identify the damage level of Parker truss structures with high robustness. The method can be of reference significance and practical value for identifying damage in truss structures.