Damage Identification in Structural Health Monitoring: A Brief Review from its Implementation to the Use of Data-Driven Applications

Quantification of the Uncertainty in Ultrasonic Wave Speed in Concrete: Application to Temperature Monitoring with Embedded Transducers

This article presents an overall examination of how small temperature fluctuations affect P-wave velocity (Vp) measurements and their uncertainties in concrete using embedded piezoelectric transducers. This study highlights the fabrication of custom transducers tailored for long-term concrete monitoring. Accurate and reliable estimation of ultrasonic wave velocities is challenging, since they can be impacted by multiple experimental and environmental factors. In this work, a reliable methodology incorporating correction models is introduced for the quantification of uncertainties in ultrasonic absolute and relative velocity measurements. The study identifies significant influence quantities and suggests uncertainty estimation laws, enhancing measurement accuracy. Determining the onset time of the signal is very time-consuming if the onset is picked manually. After testing various methods to pinpoint the onset time, we selected the Akaike Information Criterion (AIC) due to its ability to produce sufficiently reliable results. Then, signal correlation was used to determine the influence of temperature (20 °C to 40 °C) on Vp in different concrete samples. This technique proved effective in evaluating velocity changes, revealing a persistent velocity decrease with temperature increases for various concrete compositions. The study demonstrated the capability of ultrasonic measurements to detect small variations in the state of concrete under the influence of environmental variables like temperature, underlining the importance of incorporating all influencing factors.

Optimal Sensor Placement for Vibration-Based Damage Localization Using the Transmittance Function

A methodology for optimal sensor placement is presented in the current work. This methodology incorporates a damage detection framework with simulated damage scenarios and can efficiently provide the optimal combination of sensor locations for vibration-based damage localization purposes. A classic approach in vibration-based methods is to decide the sensor locations based, either directly or indirectly, on the modal information of the structure. While these methodologies perform very well, they are designed to predict the optimal locations of single sensors. The presented methodology relies on the Transmittance Function. This metric requires only output information from the testing procedure and is calculated between two acceleration signals from the structure. As such, the outcome of the presented method is a list of optimal combinations of sensor locations. This is achieved by incorporating a damage detection framework that has been developed and tested in the past. On top of this framework, a new layer is added that evaluates the sensitivity and effectiveness of all possible sensor location combinations with simulated damage scenarios. The effectiveness of each sensor combination is evaluated by calling the damage detection framework and feeding as inputs only a specific combination of acceleration signals each time. The final output is a list of sensor combinations sorted by their sensitivity.

MARSBot: A Bristle-Bot Microrobot with Augmented Reality Steering Control for Wireless Structural Health Monitoring

Microrobots are effective for monitoring infrastructure in narrow spaces. However, they have limited computing power, and most of them are not wireless and stable enough for accessing infrastructure in difficult-to-reach areas. In this paper, we describe the fabrication of a microrobot with bristle-bot locomotion using a novel centrifugal yaw-steering control scheme. The microrobot operates in a network consisting of an augmented reality headset and an access point to monitor infrastructures using augmented reality (AR) haptic controllers for human-robot collaboration. For the development of the microrobot, the dynamics of bristle-bots in several conditions were studied, and multiple additive manufacturing processes were investigated to develop the most suitable prototype for structural health monitoring. Using the proposed network, visual data are sent in real time to a hub connected to an AR headset upon request, which can be utilized by the operator to monitor and make decisions in the field. This allows the operators wearing an AR headset to inspect the exterior of a structure with their eyes, while controlling the surveying robot to monitor the interior side of the structure.

Analysis of Structural Health Monitoring Data with Correlated Measurement Error by Bayesian System Identification: Theory and Application

Measurement error is non-negligible and crucial in SHM data analysis. In many applications of SHM, measurement errors are statistically correlated in space and/or in time for data from sensor networks. Existing works solely consider spatial correlation for measurement error. When both spatial and temporal correlation are considered simultaneously, the existing works collapse, as they do not possess a suitable form describing spatially and temporally correlated measurement error. In order to tackle this burden, this paper generalizes the form of correlated measurement error from spatial correlation only or temporal correlation only to spatial-temporal correlation. A new form of spatial-temporal correlation and the corresponding likelihood function are proposed, and multiple candidate model classes for the measurement error are constructed, including no correlation, spatial correlation, temporal correlation, and the proposed spatial-temporal correlation. Bayesian system identification is conducted to achieve not only the posterior probability density function (PDF) for the model parameters, but also the posterior probability of each candidate model class for selecting the most suitable/plausible model class for the measurement error. Examples are presented with applications to model updating and modal frequency prediction under varying environmental conditions, ensuring the necessity of considering correlated measurement error and the capability of the proposed Bayesian system identification in the uncertainty quantification at the parameter and model levels.

A Systematic Literature Review of Predictive Maintenance for Defence Fixed-Wing Aircraft Sustainment and Operations

In recent decades, the increased use of sensor technologies, as well as the increase in digitalisation of aircraft sustainment and operations, have enabled capabilities to detect, diagnose, and predict the health of aircraft structures, systems, and components. Predictive maintenance and closely related concepts, such as prognostics and health management (PHM) have attracted increasing attention from a research perspective, encompassing a growing range of original research papers as well as review papers. When considering the latter, several limitations remain, including a lack of research methodology definition, and a lack of review papers on predictive maintenance which focus on military applications within a defence context. This review paper aims to address these gaps by providing a systematic two-stage review of predictive maintenance focused on a defence domain context, with particular focus on the operations and sustainment of fixed-wing defence aircraft. While defence aircraft share similarities with civil aviation platforms, defence aircraft exhibit significant variation in operations and environment and have different performance objectives and constraints. The review utilises a systematic methodology incorporating bibliometric analysis of the considered domain, as well as text processing and clustering of a set of aligned review papers to position the core topics for subsequent discussion. This discussion highlights state-of-the-art applications and associated success factors in predictive maintenance and decision support, followed by an identification of practical and research challenges. The scope is primarily confined to fixed-wing defence aircraft, including legacy and emerging aircraft platforms. It highlights that challenges in predictive maintenance and PHM for researchers and practitioners alike do not necessarily revolve solely on what can be monitored, but also covers how robust decisions can be made with the quality of data available.

Multivariate empirical mode decomposition-based structural damage localization using limited sensors

In this article, multivariate empirical mode decomposition is proposed for damage localization in structures using limited measurements. Multivariate empirical mode decomposition is first used to decompose the acceleration responses into their mono-component modal responses. The major contributing modal responses are then used to evaluate the modal energy for the respective modes. A damage localization feature is proposed by calculating the percentage difference in the modal energies of damaged and undamaged structures, followed by the determination of the threshold value of the feature. The feature of the specific sensor location exceeding the threshold value is finally used to identify the location of structural damage. The proposed method is validated using a suite of numerical and full-scale studies. The validation is further explored using various limited measurement cases for evaluating the feasibility of using a fewer number of sensors to enable cost-effective structural health monitoring. The results show the capability of the proposed method in identifying as minimal as 2% change in global modal parameters of structures, outperforming the existing time-frequency methods to delineate such minor global damage.

Damage Classification Using Supervised Self-Organizing Maps in Structural Health Monitoring

Improvements in computing capacity have allowed computers today to execute increasingly complex tasks. One of the main benefits of these improvements is the possibility of developing machine learning algorithms, of which the fields of application are extensive and varied. However, an area in which this type of algorithms acquires an increasing relevance is structural health monitoring (SHM), where inspection strategies and guided wave-based approaches make the evaluation of the structural conditions of an aircraft, vessel or building among others possible, by detecting and classifying existing damages. The use of sensors, data acquisition systems (DAQ) and computation has also allowed these damage detection and classification tasks to be carried out automatically. Despite today's advances, it is still necessary to continue with the development of more robust, reliable, and low-cost structural health monitoring systems. For this reason, this work contemplates three key points: (i) the configuration of a data acquisition system for signal gathering from an an active piezoelectric (PZT) sensor network; (ii) the development of a damage classification methodology based on signal processing techniques (normalization and PCA), from which the models that describe the structural conditions of the plate are built; and (iii) the use of machine learning algorithms, more specifically, three variants of the self-organizing maps called CPANN (counterpropagation artificial neural network), SKN (supervised Kohonen) and XYF (X-Y fused Kohonen). The data obtained allowed one to carry out an experimental validation of the damage classification methodology, to determine the presence of damages in two aluminum plates of different sizes, where masses were added to change the vibrational responses captured by the sensor network and a composite (CFRP) plate with real damages, such as delamination and cracks. This classification methodology allowed one to obtain excellent results by validating the usefulness of the SKN and XYF networks in damage classification tasks, showing overall accuracies of 73.75% and 72.5%, respectively, according to the cross-validation process. These percentages are higher than those obtained in comparison with other neural networks such as: kNN, discriminant analysis, classification trees, partial least square discriminant analysis, and backpropagation neural networks, when the cross-validation process was applied.

Attention-Based Deep Recurrent Neural Network to Forecast the Temperature Behavior of an Electric Arc Furnace Side-Wall

Structural health monitoring (SHM) in an electric arc furnace is performed in several ways. It depends on the kind of element or variable to monitor. For instance, the lining of these furnaces is made of refractory materials that can be worn out over time. Therefore, monitoring the temperatures on the walls and the cooling elements of the furnace is essential for correct structural monitoring. In this work, a multivariate time series temperature prediction was performed through a deep learning approach. To take advantage of data from the last 5 years while not neglecting the initial parts of the sequence in the oldest years, an attention mechanism was used to model time series forecasting using deep learning. The attention mechanism was built on the foundation of the encoder–decoder approach in neural networks. Thus, with the use of an attention mechanism, the long-term dependency of the temperature predictions in a furnace was improved. A warm-up period in the training process of the neural network was implemented. The results of the attention-based mechanism were compared with the use of recurrent neural network architectures to deal with time series data, such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). The results of the Average Root Mean Square Error (ARMSE) obtained with the attention-based mechanism were the lowest. Finally, a variable importance study was performed to identify the best variables to train the model.

Modelling and Validation of a Guided Acoustic Wave Temperature Monitoring System

The computer modelling of condition monitoring sensors can aide in their development, improve their performance, and allow for the analysis of sensor impact on component operation. This article details the development of a COMSOL model for a guided wave-based temperature monitoring system, with a view to using the technology in the future for the temperature monitoring of nozzle guide vanes, found in the hot section of aeroengines. The model is based on an experimental test system that acts as a method of validation for the model. Piezoelectric wedge transducers were used to excite the S0 Lamb wave mode in an aluminium plate, which was temperature controlled using a hot plate. Time of flight measurements were carried out in MATLAB and used to calculate group velocity. The results were compared to theoretical wave velocities extracted from dispersion curves. The assembly and validation of such a model can aide in the future development of guided wave based sensor systems, and the methods provided can act as a guide for building similar COMSOL models. The results show that the model is in good agreement with the experimental equivalent, which is also in line with theoretical predictions.

Supervised Distributed Multi-Instance and Unsupervised Single-Instance Autoencoder Machine Learning for Damage Diagnostics with High-Dimensional Data—A Hybrid Approach and Comparison Study

Structural health monitoring (SHM) is a promising technique for in-service inspection of technical structures in a broad field of applications in order to reduce maintenance efforts as well as the overall structural weight. SHM is basically an inverse problem deriving physical properties such as damages or material inhomogeneity (target features) from sensor data. Often models defining the relationship between predictable features and sensors are required but not available. The main objective of this work is the investigation of model-free distributed machine learning (DML) for damage diagnostics under resource and failure constraints by using multi-instance ensemble and model fusion strategies and featuring improved scaling and stability compared with centralised single-instance approaches. The diagnostic system delivers two features: A binary damage classification (damaged or non-damaged) and an estimation of the spatial damage position in case of a damaged structure. The proposed damage diagnostics architecture should be able to be used in low-resource sensor networks with soft real-time capabilities. Two different machine learning methodologies and architectures are evaluated and compared posing low- and high-resolution sensor processing for low- and high-resolution damage diagnostics, i.e., a dedicated supervised trained low-resource and an unsupervised trained high-resource deep learning approach, respectively. In both architectures state-based recurrent artificial neural networks are used that process spatially and time-resolved sensor data from experimental ultrasonic guided wave measurements of a hybrid material (carbon fibre laminate) plate with pseudo defects. Finally, both architectures can be fused to a hybrid architecture with improved damage detection accuracy and reliability. An extensive evaluation of the damage prediction by both systems shows high reliability and accuracy of damage detection and localisation, even by the distributed multi-instance architecture with a resolution in the order of the sensor distance.

Health Monitoring of Large-Scale Civil Structures: An Approach Based on Data Partitioning and Classical Multidimensional Scaling

A major challenge in structural health monitoring (SHM) is the efficient handling of big data, namely of high-dimensional datasets, when damage detection under environmental variability is being assessed. To address this issue, a novel data-driven approach to early damage detection is proposed here. The approach is based on an efficient partitioning of the dataset, gathering the sensor recordings, and on classical multidimensional scaling (CMDS). The partitioning procedure aims at moving towards a low-dimensional feature space; the CMDS algorithm is instead exploited to set the coordinates in the mentioned low-dimensional space, and define damage indices through norms of the said coordinates. The proposed approach is shown to efficiently and robustly address the challenges linked to high-dimensional datasets and environmental variability. Results related to two large-scale test cases are reported: the ASCE structure, and the Z24 bridge. A high sensitivity to damage and a limited (if any) number of false alarms and false detections are reported, testifying the efficacy of the proposed data-driven approach.

Distributed Fibre Optic Sensor-Based Continuous Strain Measurement along Semicircular Paths Using Strain Transformation Approach

Distributed fibre optic sensors (DFOS) are popular for structural health monitoring applications in large engineering infrastructure because of their ability to provide spatial strain measurements continuously along their lengths. Curved paths, particularly semicircular paths, are quite common for optical fibre placement in large structures in addition to straight paths. Optical fibre sensors embedded in a curved path configuration typically measure a component of strain, which often cannot be validated using traditional approaches. Thus, for most applications, strain measured along curved paths is ignored as there is no proper validation tool to ensure the accuracy of the measured strains. To overcome this, an analytical strain transformation equation has been developed and is presented here. This equation transforms the horizontal and vertical strain components obtained along a curved semicircular path into a strain component, which acts tangentially as it travels along the curved fibre path. This approach is validated numerically and experimentally for a DFOS installed on a steel specimen with straight and curved paths. Under tensile and flexural loading scenarios, the horizontal and vertical strain components were obtained numerically using finite element analysis and experimentally using strain rosettes and then, substituted into the proposed strain transformation equation for deriving the transformed strain values. Subsequently, the derived strain values obtained from the proposed transformation equation were validated by comparing them with the experimentally measured DFOS strains in the curved region. Additionally, this study has also shown that a localised damage to the DFOS coating will not impact the functionality of the sensor at the remaining locations along its length. In summary, this paper presents a valid strain transformation equation, which can be used for transforming the numerical simulation results into the DFOS measurements along a semicircular path. This would allow for a larger scope of spatial strains measurements, which would otherwise be ignored in practice.

Trajectory Identification for Moving Loads by Multicriterial Optimization

Moving load is a fundamental loading pattern for many civil engineering structures and machines. This paper proposes and experimentally verifies an approach for indirect identification of 2D trajectories of moving loads. In line with the "structure as a sensor" paradigm, the identification is performed indirectly, based on the measured mechanical response of the structure. However, trivial solutions that directly fit the mechanical response tend to be erratic due to measurement and modeling errors. To achieve physically meaningful results, these solutions need to be numerically regularized with respect to expected geometric characteristics of trajectories. This paper proposes a respective multicriterial optimization framework based on two groups of criteria of a very different nature: mechanical (to fit the measured response of the structure) and geometric (to account for the geometric regularity of typical trajectories). The state-of-the-art multiobjective genetic algorithm NSGA-II is used to find the Pareto front. The proposed approach is verified experimentally using a lab setup consisting of a plate instrumented with strain gauges and a line-follower robot. Three trajectories are tested, and in each case the determined Pareto front is found to properly balance between the mechanical response fit and the geometric regularity of the trajectory.

Copula-Based Uncertainty Quantification (Copula-UQ) for Multi-Sensor Data in Structural Health Monitoring

The problem of uncertainty quantification (UQ) for multi-sensor data is one of the main concerns in structural health monitoring (SHM). One important task is multivariate joint probability density function (PDF) modelling. Copula-based statistical inference has attracted significant attention due to the fact that it decouples inferences on the univariate marginal PDF of each random variable and the statistical dependence structure (called copula) among the random variables. This paper proposes the Copula-UQ, composing multivariate joint PDF modelling, inference on model class selection and parameter identification, and probabilistic prediction using incomplete information, for multi-sensor data measured from a SHM system. Multivariate joint PDF is modeled based on the univariate marginal PDFs and the copula. Inference is made by combing the idea of the inference functions for margins and the maximum likelihood estimate. Prediction on the PDF of the target variable, using the complete (from normal sensors) or incomplete information (due to missing data caused by sensor fault issue) of the predictor variable, are made based on the multivariate joint PDF. One example using simulated data and one example using temperature data of a multi-sensor of a monitored bridge are presented to illustrate the capability of the Copula-UQ in joint PDF modelling and target variable prediction.

Determining the Fracture Process Zone Length and Mode I Stress Intensity Factor in Concrete Structures via Mechanoluminescent Technology

The mechanoluminescent (ML) technology that is being developed as a new and substitutive technology for structural health monitoring systems (SHMS) comprises stress/strain sensing micro-/nanoparticles embedded in a suitable binder, digital imaging system, and digital image processing techniques. The potential of ML technology to reveal the fracture process zone (FPZ) that is commonly found in structural materials like concrete and to calculate the stress intensity factor (SIF) of concrete, which are crucial for SHMS, has never been done before. Therefore, the potential of ML technology to measure the length of the FPZ and to calculate the SIF has been demonstrated in this work by considering a single-edge notched bend (SENB) test of the concrete structures. The image segmentation approach based on the histogram of an ML image as well the skeletonization of an ML image have been introduced in this work to facilitate the measurement of the length of ML pattern, crack, and FPZ. The results show ML technology has the potential to determine fracture toughness, to visualize FPZ and cracks, and to measure their lengths in structural material like concrete, which makes it applicable to structural health monitoring systems (SHMS) to characterize the structural integrity of structures.

Applying Deep Learning to Continuous Bridge Deflection Detected by Fiber Optic Gyroscope for Damage Detection

Improving the accuracy and efficiency of bridge structure damage detection is one of the main challenges in engineering practice. This paper aims to address this issue by monitoring the continuous bridge deflection based on the fiber optic gyroscope and applying the deep-learning algorithm to perform structural damage detection. With a scale-down bridge model, three types of damage scenarios and an intact benchmark were simulated. A supervised learning model based on the deep convolutional neural networks was proposed. After the training process under ten-fold cross-validation, the model accuracy can reach 96.9% and significantly outperform that of other four traditional machine learning methods (random forest, support vector machine, k-nearest neighbor, and decision tree) used for comparison. Further, the proposed model illustrated its decent ability in distinguishing damage from structurally symmetrical locations.