A Damage Localization Approach for Rahmen Bridge Based on Convolutional Neural Network

The results of numerical simulations to test a method to locate and estimate the severity of damage in a structure in the blind mode, by using the simulated data from a four-story steel frame structure analyzed at the Univ. of British Columbia, are reported here. The blind simulated data include the response in the time domain of the undamaged structure and the responses of the structure with two sets of simulated damage conditions. Elements of the theory utilized here for damage detection and localization (the so-called damage index method) are first summarized. Modal analyses are performed to extract the modal characteristics (i.e., resonant frequencies and mode shapes) for the undamaged structure (designated, Case 1) and the damaged structures (here designated, Damage Cases 2 and 3). The results of the modal analyses are reported in detail. Using the proposed nondestructive damage evaluation technique, the predicted damage locations, and estimation of the damage severity are provided for the two damage cases. The actual locations of damage in the test structure for each of the damage cases were revealed subsequent to the damage predictions proposed by the writers during the 16th International Modal Analysis Conference. The predicted damage locations and severity estimates are compared with the damage inflicted in the original test cases. The current method correctly predicts the inflicted damage locations and provides realistic estimates of the associated damage severities.

In this paper, a structural health monitoring (SHM) system based on multi-scale cross-sample entropy (MSCE) is proposed for detecting damage locations in multi-bay three-dimensional structures. The location of damage is evaluated for each bay through MSCE analysis by examining the degree of dissimilarity between the response signals of vertically-adjacent floors. Subsequently, the results are quantified using the damage index (DI). The performance of the proposed SHM system was determined in this study by performing a finite element analysis of a multi-bay seven-story structure. The derived results revealed that the SHM system successfully detected the damaged floors and their respective directions for several cases. The proposed system provides a preliminary assessment of which bay has been more severely affected. Thus, the effectiveness and high potential of the SHM system for locating damage in large and complex structures rapidly and at low cost are demonstrated.

Automatic damage type classification and severity quantification using signal based and nonlinear model based damage sensitive features

Damage in structures can negatively affect their functionality and safety and leads to failure. Thus it is very important to monitor structures for occurrence, location and severity of damage. Structural health monitoring techniques provide information on the life expectancy of structures simultaneously detects and locates structural damage. Damage identification of structures based on vibration has always been important subjects and are being rapidly used to damage and location of structures. Artificial Neural Networks (ANNs) as a soft computing method using dynamic parameters of structures have been utilized increasingly for structural damage detection due to their excellent pattern recognition capability. Dynamic parameters of structure are easy to implement for damage identification and can directly linked to the topology of structure. This study presents the application of ANN for damage identification in steel beams using dynamic parameters. For identification of severity and location of damage, at first, five individual neural networks corresponding to mode 1 to mode 5 are considered. At the second step, a method based on neural network ensemble is proposed to combine the outcomes of the individual neural networks to a single network. Ensemble results were evaluated and discussed according to the differences between predicted output by ANN and desire data (target data) obtained from experimental modal analysis of structure.KeywordsArtificial neural networksMean square errorModal analysisDamage detectionNeural network ensemble

A two-step method for damage identification in moment frame connections using support vector machine and differential evolution algorithm

Deep learning (also known as deep structured learning, hierarchical learning, or deep machine learning) is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using a deep graph with multiple processing layers, composed of multiple linear and nonlinear transformations. Deep learning has been characterized as a class of machine learning algorithms with the following characteristics [257]: • They use a cascade of many layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. The algorithms may be supervised or unsupervised and applications include pattern analysis (unsupervised) and classification (supervised). • They are based on the (unsupervised) learning of multiple levels of features or representations of the data. Higher-level features are derived from lower-level features to form a hierarchical representation. • They are part of the broader machine learning field of learning representations of data. • They learn multiple levels of representations that correspond to different levels of abstraction; the levels form a hierarchy of concepts. These definitions have in common: multiple layers of nonlinear processing units and the supervised or unsupervised learning of feature representations in each layer, with the layers forming a hierarchy from low-level to high-level features. Various deep learning architectures such as deep neural networks, convolutional deep neural networks, deep belief networks (DBN), and recurrent neural networks have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition, and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. In this chapter we start in Section 7.1 with an introduction, giving a brief history of this field, the relevant literature, and its applications. Then we study some basic concepts of deep learning such as convolutional neural networks, recurrent neural networks, backpropagation algorithm, restricted Boltzmann machines, and deep learning networks in Section 7.2. Then we illustrate three examples for Apache Spark implementation for mobile big data (MBD), user moving pattern extraction, and combination with nonparametric Bayesian learning, respectively, in Sections 7.3 through 7.5. Finally, we have summary in Section 7.6.

The continuous Non-Destructive Evaluation of assets for long-term assurance of performance has led to several developments over the deployment of a Real-Time Structural Health Monitoring (SHM) system. Considering the challenges involved under the implementation of an SHM system for the applications working under harsh environmental conditions with limited access to power sources this work is aimed to contribute towards overcoming those challenges by using the noise from the structure’s machinery or any ambient source as an alternative energy source and employing Fiber Optics based sensing, for its applicability under harsh environments. The required SHM system is realized with the cross-correlation of a fully diffused noise field, sensed using the Fiber Bragg Grating (FBG) sensors at two random locations. With no control on the input received as noise, to this end, a method is developed based on a Deep Learning framework, which is aimed towards a Universal Deployment of the passive SHM system. The methodology is designed to perform the health monitoring of the system, independent of the input perturbations. The validation performed on simulation data has demonstrated the feasibility of the developed technique towards the required kind of passive SHM system.

Deep learning (DL) algorithms have significantly improved the accuracy of vibration-based structural damage detection (SDD). However, conventional DL methods are difficult to extract complex discriminative damage features, and these methods cannot quantify damage severity for more accurate damage assessment. To address these limitations, this study proposes a vibration-based SDD method with a convolutional transformer (ConvFormer) network, which is designed for damage identification, localization, and quantification. This approach integrates one-dimensional convolutional neural networks with Transformer encoders to effectively extract spatial and temporal correlation features from raw vibration acceleration signals. Specifically, the network is employed for multi-classification tasks to identify and localize damage, while also performing regression tasks to predict damage severity. The proposed method is compared with several baseline models and state-of-the-art methods using simulated data from a steel frame, laboratory data from a grandstand simulator, and field experimental data from the full-scale Z24 Bridge. The ConvFormer model exhibits superior detection performance in different scenarios. Furthermore, the reliability of the proposed method is validated through experiments on noise immunity, few-shot learning, and unbalanced sample.

PurposeThe aim of this study was to analyse and review deep learning convolutional neural networks for detecting and diagnosing early-stage dental caries on periapical radiographs.Materials and MethodsIn order to conduct this review, the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed. Studies published from 2015 to 2021 under the keywords (deep convolutional neural network) AND (caries), (deep learning caries) AND (convolutional neural network) AND (caries) were systematically reviewed.ResultsWhen dental caries is improperly diagnosed, the lesion may eventually invade the enamel, dentin, and pulp tissue, leading to loss of tooth function. Rapid and precise detection and diagnosis are vital for implementing appropriate prevention and treatment of dental caries. Radiography and intraoral images are considered to play a vital role in detecting dental caries; nevertheless, studies have shown that 20% of suspicious areas are mistakenly diagnosed as dental caries using this technique; hence, diagnosis via radiography alone without an objective assessment is inaccurate. Identifying caries with a deep convolutional neural network-based detector enables the operator to distinguish changes in the location and morphological features of dental caries lesions. Deep learning algorithms have broader and more profound layers and are continually being developed, remarkably enhancing their precision in detecting and segmenting objects.ConclusionClinical applications of deep learning convolutional neural networks in the dental field have shown significant accuracy in detecting and diagnosing dental caries, and these models hold promise in supporting dental practitioners to improve patient outcomes.

Rubber mounts are widely used as a component to prevent structures from vibration damages associated with various sources that making lifespan at stake. Frequent change of rubber mount can be a waste yet the inspection for faulty rubber mount is impractical. Advancement in technology eases structural health monitoring (SHM) through sensors combined with deep learning (DL) approach. This paper aims to investigate application practicality of DL to detect level of cracks in rubber mounts through vibration signals. Neural network models based on Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) and their combinations were developed. An experimental setup simulating bridge structure with rubber isolators supporting its base was created. Cracks were induced on the rubber mount to simulate failure conditions. 5Hz and 10Hz constant sine waves along with simulated bridge waveform from an actual bridge excitation were employed. Neural networks were applied with Bayesian approach via dropout layer to reduce overfitting and increase reliability. Results show the highest accuracy achieved by hybrid CNN-LSTM with 99.9% while CNN with 89.0% in the standard sine wave and bridge excitation scenario respectively. Overall, the study shown the practicality and capability of neural network as a SHM approach for crack detection of rubber mount.

As one of the most common structural forms in port engineering, the operation environment of high-pile wharf is quite harsh and complex, and its pile foundation often produces structural damage of different degrees. Until now, there is a lack of efficient, safe and economic damage detection methods. A novel and precise real-time structural damage detection (SDD) method using both finite element modelling (FEM) and 1D convolutional neural networks (CNNs) is established in this study. The results indicate that the proposed method could accurately identify the presence and location of damage in real time. The results also demonstrated that the proposed 1D CNNs based model are more sensitive to the longitudinal and lateral displacement responses of the high-pile wharf structure.

Damage localization for composite structure using guided wave signals with Gramian angular field image coding and convolutional neural networks

Knowledge of the damage location in composite structures is a necessary output for both Non-Destructive Evaluation (NDE) and Structural Health Monitoring (SHM). Although several damage localization approaches using a triangulation method and Time-of-Flight (ToF) of guided waves have been reported in literature, the damage localization technique is still not mature for composite structures with complex material properties, varying thickness and complex geometries. This paper investigates the development of a new approach for SHM and damage localization using a guided wave based active sensing system. In contrast to the traditional ellipse method, the proposed method does not require the information of structural thickness, ToF, or the estimation of group velocities of each guided wave mode at different propagation angles, which is one of the main limitations of most current ToF methodologies involving composites. This approach uses time-frequency analysis to calculate the difference of the ToF of the converted modes for each sensor signal. The damage location and the group velocity are obtained by solving a set of nonlinear equations. The proposed method can be used for composite structures with unknown lay-up and thickness. To validate the proposed method, experiments were conducted on both composite plates and stiffened composite panels. Eight piezoelectric (PZT) transducers were surface-bonded on each composite specimen and used in four pairs. The PZT transducers in each pair were bonded close to each other. In the PZT array, one PZT transducer from one PZT pair was used as the actuator and the other three pairs were used as sensors. A windowed cosine signal was used as the excitation signal. The locations of the delaminations in the composite specimens were validated using a flash thermography system. The accuracy of the proposed method in localizing delaminations was examined through comparison with the experimental measurements.

Structural damage identification is a critical task in civil engineering for ensuring the safety and serviceability of infrastructures. Traditional methods often rely on manually selected features from vibration data, which may lack sensitivity to incipient or localized damage. In recent years, convolutional neural networks (CNNs) have demonstrated remarkable capability in automatically extracting discriminative features from raw data, providing a powerful data-driven alternative for structural health monitoring. This paper proposes a novel structural damage identification method based on a CNN framework. Numerical simulations of the free vibration of a simply supported beam were conducted using the finite element method. The modal strain energy of the first-order element was collected as the primary damage-sensitive feature. Through batch automatic calculation, a comprehensive dataset encompassing various damage scenarios—including different locations and severity levels—was efficiently generated to serve as training, validation, and testing samples for the network. The proposed CNN model was specifically designed and implemented in MATLAB to adapt to the characteristics of the structural damage detection data. This study systematically verifies the recognition performance of the CNN from three key aspects: identification of single damage location, quantification of damage severity at a single location, and detection of multiple damage locations. The results indicate that the CNN can not only accurately identify the location of structural damage with high precision but also achieve a considerable level of accuracy in quantifying the degree of damage, demonstrating its strong potential for comprehensive damage assessment in engineering structures.

The Dutch road infrastructure contains a large number of concrete bridges and viaducts. Malfunction of these bridges and viaducts has large financial consequences. To avoid malfunctions of bridges, bridges need to be inspected frequently and actions should be taken when required. The reliability of the inspections of the health of a bridge could be increased by monitoring the deflections and/or the vibrations of the bridge. The main idea of a Structural Health Monitoring system is that degradation of a bridge results in detectable changes in the deflections and in the modal properties of the bridge. The results of data-driven modal calculations of an existing concrete bridge have been compared with the results of Finite Element modal calculations of this bridge to investigate whether this comparison can be used to predict damage in the bridge. The effect of fatigue and localized corrosion damage on the deflections of a Reinforced Concrete beam was investigated by laboratory tests. The effect of fatigue and localized corrosion damage on the deflections and on the first natural frequency of a Reinforced Concrete beam was predicted by Finite Element calculations and probabilistic calculations. It was concluded from the tests and from the calculations that deflections and natural frequencies cannot be used as indicator for fatigue damage in concrete bridges.