Search

The paper presents a wireless system integrated with a machine learning (ML) model for structural health monitoring (SHM) of carbon fiber reinforced polymer (CFRP) structures, primarily targeting aerospace applications. The system collects data via carbon nanotube (CNT) piezoresistive sensors embedded within CFRP coupons, wirelessly transmitting these data to a central server for processing. A deep neural network (DNN) model predicts mechanical properties and can be extended to forecast structural failures, facilitating proactive maintenance and enhancing safety. The modular design supports scalability and can be embedded within digital twin frameworks, offering significant benefits to aircraft operators and manufacturers. The system utilizes an ML model with a mean absolute error (MAE) of 0.14 on test data for forecasting mechanical properties. Data transmission latency throughout the entire system is less than one second in a LAN setup, highlighting its potential for realtime monitoring applications in aerospace and other industries. However, while the system shows promise, challenges such as sensor reliability under extreme environmental conditions and the need for advanced ML models to handle diverse data streams have been identified as areas for future research. [ABSTRACT FROM AUTHOR]

The constant improvement and developments in Artificial Intelligence/Machine learning models coupled with increased computing power have led to the incorporation of AI/ML for simulating learning and problem‐solving in simple and complex engineering systems. This latent uncertainty and unpredictable characteristics of AI‐enabled systems challenges engineers and industry stakeholders who care about ensuring the right systems are built (system validation). Digital Twins are an excellent example of such AI‐enabled systems due to their data‐dependent nature when tasked with replicating, monitoring, and updating physical assets for structural health monitoring and control. However, Digital Twins' system validation has not been well‐researched. This study delves into existing research and frameworks for validating Digital Twins and proposes a novel model‐centric validation framework based on system identification techniques. As a case study, we apply this model‐centric validation framework towards partially validating a Digital Twin for a single‐heat‐pipe test article for a Microre‐actor Agile Non‐nuclear Experimental Testbed. [ABSTRACT FROM AUTHOR]

Additive manufacturing (AM) offers new possibilities in soft robotics as materials can easily be combined in multi-material designs. Proper sensing is essential for the soft actuators to interact with the surroundings successfully. By fabricating sensors through AM, sensors can be embedded directly into the components during manufacturing. This paper investigates NinjaTek Eels electrical resistance response to strain and the feasibility of using the material to create strain sensors. Strain sensors were 3D-printed out of NinjaTek Eel, a soft conductive TPU, and was tested during cyclic loading. A custom resistance–strain test rig was developed for measuring sensor behavior. The rig was calibrated for electric resistance, able to measure electric resistance as a function of strain. A parabolic response curve was observed during cyclic loading, which led to ambiguous readings. A 10-specimen validation test was conducted, evaluating the statistical variation for the first 100 loading cycles. The validation test showed that the sensor is capable of accurate and predictable readings during single load cases and cyclic loading, with the overall root mean square error being 66.9 Ω. Combining two sensors of different cross-sections gave promising results in terms of calibrating. By monitoring load cycles and strain rates, calibration can also be achieved by machine learning models by the microcontroller used to extract data. The presented work in this article explores the potential of using conductive TPUs as sensors embedded in products such as soft robotics, life monitoring of products with structural, and digital twins for live product to user feedback. [ABSTRACT FROM AUTHOR]

Numerical modeling tools are essential in aircraft structural design, yet they face challenges in accurately reflecting real-world behavior due to factors like material properties scatter and manufacturing-induced deviations. This article addresses the potential impact of digital twins on overcoming these limitations and enhancing model reliability through advanced updating techniques based on machine learning. Digital twins, which are virtual replicas of physical systems, offer a promising solution by integrating sensor data, operational inputs, and historical records. Machine learning techniques enable the calibration and validation of models, combining experimental inputs with simulations through continuous updating processes that refine digital twins, improving their accuracy in predicting structural behavior and performance throughout an aircraft's life cycle. These refined models enable real-time monitoring and precise damage assessment, supporting decision making in diverse contexts. By integrating sensor data and updating techniques, digital twins contribute to improved design and maintenance operations by providing valuable insights into structural health, safety, and reliability. Ultimately, this approach leads to more efficient and safer aviation operations, demonstrating the potential of digital twins to revolutionize aircraft structural analysis and design. This article explores various advancements and methodologies applicable to structural assessment, leveraging machine learning tools. These include the utilization of physics-informed neural networks, which enable the handling of diverse uncertainties. Such approaches empower a more informed and adaptive strategy, contributing to the assurance of structural integrity and safety in aircraft structures throughout their operational life. [ABSTRACT FROM AUTHOR]

This document discusses the integration of machine learning (ML), Internet of Things (IoT), and digital twin (DT) technologies and their transformative potential across various fields. The authors highlight the challenges posed by the vast amounts of data generated by IoT and the need for advanced tools like ML to process and extract meaningful insights from this data. They also explore the concept of digital twins, which create virtual replicas of physical entities and enable real-time simulation and optimization. The document includes a collection of research papers that showcase the innovative applications of these technologies in areas such as maintenance scheduling, healthcare services, structural integrity, safety management, security, traffic control, and physical activity coaching. The authors hope that readers will find inspiration and insights from these studies to drive further innovation in this dynamic field. [Extracted from the article]

Environmental effects may lead to cracking, stiffness loss, brace damage, and other damages in bridges, frame structures, buildings, etc. Structural Health Monitoring (SHM) technology could prevent catastrophic events by detecting damage early. In recent years, Deep Learning (DL) has developed rapidly and has been applied to SHM to detect, localize, and evaluate diverse damages through efficient feature extraction. This paper analyzes 337 articles through a systematic literature review to investigate the application of DL for SHM in the operation and maintenance phase of facilities from three perspectives: data, DL algorithms, and applications. Firstly, the data types in SHM and the corresponding collection methods are summarized and analyzed. The most common data types are vibration signals and images, accounting for 80% of the literature studied. Secondly, the popular DL algorithm types and application areas are reviewed, of which CNN accounts for 60%. Then, this article carefully analyzes the specific functions of DL application for SHM based on the facility's characteristics. The most scrutinized study focused on cracks, accounting for 30 percent of research papers. Finally, challenges and trends in applying DL for SHM are discussed. Among the trends, the Structural Health Monitoring Digital Twin (SHMDT) model framework is suggested in response to the trend of strong coupling between SHM technology and Digital Twin (DT), which can advance the digitalization, visualization, and intelligent management of SHM. [ABSTRACT FROM AUTHOR]

Recent developments in networked and smart sensors have significantly changed the way Structural Health Monitoring (SHM) and asset management are being carried out. Since the sensor networks continuously provide real-time data from the structure being monitored, they constitute a more realistic image of the actual status of the structure where the maintenance or repair work can be scheduled based on real requirements. This review is aimed at providing a wealth of knowledge from the working principles of sensors commonly used in SHM, to artificial-intelligence-based digital twin systems used in SHM and proposes a new asset management framework. The way this paper is structured suits researchers and practicing experts both in the fields of sensors as well as in asset management equally. [ABSTRACT FROM AUTHOR]

Structural health monitoring (SHM) of bridges is constantly upgraded by researchers and bridge engineers as it directly deals with bridge performance and its safety over a certain time period. This article addresses some issues in the traditional SHM systems and the reason for moving towards an automated monitoring system. In order to automate the bridge assessment and monitoring process, a mechanism for the linkage of Digital Twins (DT) and Machine Learning (ML), namely the Support Vector Machine (SVM) algorithm, is discussed in detail. The basis of this mechanism lies in the collection of data from the real bridge using sensors and is providing the basis for the establishment and calibration of the digital twin. Then, data analysis and decision-making processes are to be carried out through regression-based ML algorithms. So, in this study, both ML brain and a DT model are merged to support the decision-making of the bridge management system and predict or even prevent further damage or collapse of the bridge. In this way, the SHM system cannot only be automated but calibrated from time to time to ensure the safety of the bridge against the associated damages. [ABSTRACT FROM AUTHOR]

Structural damage is inherent in civil engineering structures, and bridges are no exception. It is vital to monitor and keep track of damage in bridge structures as a result of multiple mechanical, environmental and traffic-induced factors. Monitoring the formation and propagation of structural damage is also pertinent for enhancing the service life of bridges. Bridge health monitoring (BHM) has always been an active research area for engineers and stakeholders. While all monitoring techniques intend to provide accurate and decisive information on the remaining useful life, safety, integrity and serviceability of bridges, maintaining uninterrupted operation of a bridge relies strongly on understanding the development and propagation of damage. BHM methods have been extensively researched on bridges over the decades, and new methodologies have started to be used by domain experts, especially within the last decade. Emerging methods, as the products of technology advancements, have resulted in handy tools that have been quickly adopted by bridge engineers. State-of-the-art techniques such as lidar, photogrammetry, virtual reality, augmented reality, digital twins, computer vision, machine learning and deep learning are now integrated parts of the new-generation of BHM operations. This paper presents a brief overview of these latest BHM technologies. [ABSTRACT FROM AUTHOR]

This paper deals with state of the art in structural health monitoring (SHM) methods in offshore and marine structures. Most SHM methods have been developed for onshore infrastructures. Few studies are available to implement SHM technologies in offshore and marine structures. This paper aims to fill this gap and highlight the challenges in implementing SHM methods in offshore and marine structures. The present work categorises the available techniques for establishing SHM models in oil rigs, offshore wind turbine structures, subsea systems, vessels, pipelines and so on. Additionally, the capabilities of proposed ideas in recent publications are classified into three main categories: model-based methods, vibration-based methods and digital twin methods. Recently developed novel signal processing and machine learning algorithms are reviewed and their abilities are discussed. Developed methods in vision-based and population-based approaches are also presented and discussed. The aim of this paper is to provide guidelines for selecting and establishing SHM in offshore and marine structures. [ABSTRACT FROM AUTHOR]

Output-only structural health monitoring is a highly active research direction because it is a promising methodology for building digital twin applications providing near-real-time monitoring results of the structure. However, one of the technical bottlenecks is how to work effectively with multiple high-dimensional vibration signals. To address this question, this study develops a two-stage data-driven framework based on various advanced techniques, such as time-series feature extractions, self-learning, graph neural network, and machine learning algorithms. At first, multiple features in statistical, time, and spectral domains, are extracted from raw vibration data; then, they subsequently enter a graph convolution network to account for the spatial correlation of sensor locations. After that, the high-performance adaptive boosting machine learning algorithm is leveraged to assess structures' health states. This method allows for learning a lower-dimensional yet informative representation of vibration data; thus, the subsequent monitoring tasks could be performed with reduced time complexity and economical computational resources. The performance of the proposed method is qualitatively and quantitatively demonstrated through two examples involving both numerical and experimental structural data. Furthermore, comparison and robustness studies are carried out, showing that the proposed approach outperforms various machine learning/deep learning-based methods in terms of accuracy and noise/missing-robustness. [ABSTRACT FROM AUTHOR]

This paper presents a predictive computational framework for surrogate modeling of pressure field and optimization of pressure sensor placement for wind engineering applications. Firstly, a machine learning-derived surrogate model, trained by high-fidelity simulation data using finite element-based CFD and informed by a turbulence model, is developed to construct the full-field pressure from scattered sensor measurements in near real-time. Then, the surrogate pressure model is embedded in another neural network (NN) for optimizing pressure sensor placement. The goal of the NN-based optimizer is to learn the best layout of a fixed number of pressure sensors over the structural surface to deliver the most accurate full-field pressure prediction for various inflow wind conditions. We deploy the model to a representative low-rise building subjected to different wind conditions. The performance of the proposed framework is assessed by comparing the predicted results with finite element-based CFD simulation results. The framework shows excellent accuracy and efficiency, which could be potentially integrated with structural health monitoring to enable digital twins of civil structures. [ABSTRACT FROM AUTHOR]

Health monitoring of structures using ultrasonic guided waves is an evolving technology with potential applications in monitoring pipelines, civil bridges, and aircraft components. However, the sensitivity of guided waves to external parameters affects the reliability of monitoring systems based on them. These influencing factors and experimental related factors cannot be perfectly modeled, which give rise to the discrepancy between numerical simulations and experimental measurements. Therefore, it is important to address this inevitable discrepancy and generate close-to-experiment simulations. In this work, we present a deep learning-based Digital Twin framework containing multi-fidelity modeling to reduce the discrepancy between measurements and simulations and a deep generative model to generate close-to-experiment guided wave responses by harnessing the vital characteristics of the two sources. These realistic simulations (close to experiment) can then be used in assessing the reliability of health monitoring system by generating probability of detection curves. Furthermore, they can also be used for augmenting the training data for a machine learning algorithm. We use a measurement dataset corresponding to crack propagation and simulations to validate the proposed framework. The results show that the discrepancy is indeed reduced to a great extent, furthermore, we also show that this framework enables the computation of probability of detection from close-to-experiment data as a direct consequence of rapid generation of realistic simulations. • Structural health monitoring based on ultrasonic guided waves. • Discrepancy reduction between simulations and experiments. • A novel unifed deep neural network model blending simulations and experiments. • Enhanced ultrasonic guided waves signals generation. • Discrepancy quantification through phase and amplitude based misfit metrics. • Metamodel based computation of probability of detection. [ABSTRACT FROM AUTHOR]

A road network is the key foundation of any nation's critical infrastructure. Pavements represent one of the longest-living structures, having a post-construction life of 20–40 years. Currently, most attempts at maintaining and repairing these structures are performed in a reactive and traditional fashion. Recent advances in technology and research have proposed the implementation of costly measures and time-intensive techniques. This research presents a novel automated approach to develop a cognitive twin of a pavement structure by implementing advanced modelling and machine learning techniques from unmanned aerial vehicle (e.g., drone) acquired data. The research established how the twin is initially developed and subsequently capable of detecting current damage on the pavement structure. The proposed method is also compared to the traditional approach of evaluating pavement condition as well as the more advanced method of employing a specialized diagnosis vehicle. This study demonstrated an efficiency enhancement of maintaining pavement infrastructure. [ABSTRACT FROM AUTHOR]

Analogous to an experiment, a structural health monitoring (SHM) system may be thought of as an information-gathering mechanism. Gathering the information that is representative of the structural state and correctly inferring its meaning helps engineers (decision-makers) mitigate possible losses by taking appropriate actions (risk-informed decision-making). However, the design, research, development, installation, maintenance, and operation of an SHM system are an expensive endeavor. Therefore, the decision to invest in new information is rationally justified if the reduction in the expected losses by utilizing newly acquired information is more than the intrinsic cost of the information acquiring mechanism incurred over the lifespan of the structure. This article investigates the economic advantage of installing an SHM system for inference of the structural state, risk, and lifecycle management by using the value of information (VoI) analysis. Among many possible choices of SHM system designs (different information-gathering mechanisms), pre-posterior decision analysis can be used to select the most feasible design. Traditionally, the cost–benefit analysis of an SHM system is carried out through pre-posterior decision analysis that helps one evaluate the benefit of an experiment or an information-gathering mechanism using the expected value of information metric. This study proposes an alternate normalized metric that evaluates the expected reward ratio (benefit/gain of using an SHM system) relative to the investment risk (cost of SHM over the lifecycle). The analysis of evaluating the relative benefit of various SHM system designs is carried out by considering the concept of the VoI, by performing pre-posterior analysis, and the idea of a perfect experiment is discussed. [ABSTRACT FROM AUTHOR]

The monitoring of infrastructure assets using sensor networks is becoming increasingly prevalent. A digital twin in the form of a finite element (FE) model, as commonly used in design and construction, can help make sense of the copious amount of collected sensor data. This paper demonstrates the application of the statistical finite element method (statFEM), which provides a principled means of synthesizing data and physics-based models, in developing a digital twin of a self-sensing structure. As a case study, an instrumented steel railway bridge of 27:34m length located along the West Coast Mainline near Staffordshire in the UK is considered. Using strain data captured from fiber Bragg grating sensors at 108 locations along the bridge superstructure, statFEM can predict the "true" system response while taking into account the uncertainties in sensor readings, applied loading, and FE model misspecification errors. Longitudinal strain distributions along the two main I-beams are both measured and modeled during the passage of a passenger train. The statFEM digital twin is able to generate reasonable strain distribution predictions at locations where no measurement data are available, including at several points along the main I-beams and on structural elements on which sensors are not even installed. The implications for long-term structural health monitoring and assessment include optimization of sensor placement and performing more reliable what-if analyses at locations and under loading scenarios for which no measurement data are available. [ABSTRACT FROM AUTHOR]

Engineering has many necessary fields, and Structural Health Monitoring (SHM) is one of the most important of them. Sometimes in industrial environments, it is difficult and even impossible to collect data containing different real damages. Therefore, the problem of data acquisition represents a primary challenge in designing damage detection systems. The application of digital twin methods based on simulated models and/or Machine Learning (ML) models is a practical way to solve this problem. In this approach, a digital twin is generated for a compromised structure, utilizing a physics-based model to analyze diverse damage scenarios. Subsequently, an ML model is trained using data extracted from the physics-based model, functioning as the digital twin. This research proposes a method based on a digital twin for detecting damages in structures. The data produced from a Floating Wind Turbine (FWT) model was used to evaluate the performance of the proposed digital twin-based method. For this purpose, the FWT structure was simulated using a numerical model to address the data collection problem in the face of various uncertainties, such as changing loading conditions. In line with the concept of digital twin and to reduce the computational time, a Deep Convolution Long Short-Term Memory Neural Network (DCLSTMNN) model was designed and trained only with the frequency data of various scenarios of the simulated FWT model under constant loads (deterministic loads, including constant wind speed and airy wave model) to learn the damage-sensitive features. Then, to demonstrate the robustness of the proposed model under different uncertainties, the DCLSTMNN model was evaluated using the frequency data of the simulated FWT model under variable loading conditions (including Kaimal wind model and JONSWAP wave theory). Some vibration response components unrelated to the nature of the FWT model were removed using the Complete Ensemble Empirical Mode Decomposition (CEEMD) method. Then, the reconstructed vibration responses were used to create the frequency data using the Frequency Domain Decomposition (FDD) technique. The study results show that the proposed digital twin-based method can detect the location and severity of damage more accurately than other comparable methods despite various uncertainties. • A novel digital twin-based method is proposed for learning damage-sensitive features from data of various scenarios of the simulated simple FWT model to detect damage in the complex FWT model. • A Deep Convolution Long Short-Term Memory Neural Network (DCLSTMNN) model is designed to learn features and damage detection of the complex FWT model. • The proposed DCLSTMNN is trained with extracted data from the simulated simple FWT model and then tested with extracted data from the complex FWT model. [ABSTRACT FROM AUTHOR]

• A data-driven method is proposed to evaluate the ultimate response of masonry arches. • Machine learning metamodels, in the form of artificial neural networks, are adopted. • Numerical datasets using Matlab, Python and FEM software are generated. • A fast and accurate prediction of the collapse mode and ultimate load is achieved. • Source Matlab, Python files and generated datasets accompany the article. A data-driven methodology is proposed, for the investigation of the ultimate response of masonry arches. Aiming to evaluate their structural response in a computationally efficient framework, machine learning metamodels, in the form of artificial neural networks, are adopted. Datasets are numerically built, integrating Matlab, Python and commercial finite element software. Heyman's assumptions are adopted within non-linear finite element analysis, incorporating contact-friction laws between adjacent stones, to capture failure in the arch. The artificial neural networks are trained, validated, and tested using the least square minimization technique. It is shown that the proposed scheme can be used to provide a fast and accurate prediction of the deformed geometry, the collapse mechanism and the ultimate load. Cases studies demonstrate the efficiency of the method in random, new arch geometries. Relevant Matlab/Python scripts and datasets are provided. The method can be extended towards structural health monitoring and the concept of digital twin. [ABSTRACT FROM AUTHOR]

The use of Machine Learning (ML) has rapidly spread across several fields of applied sciences, having encountered many applications in Structural Dynamics and Vibroacoustic (SD&V). An advantage of ML algorithms compared to traditional techniques is that physical phenomena can be modeled using only sampled data from either measurements or simulations. This is particularly important in SD&V when the model of the studied phenomenon is either unknown or computationally expensive to simulate. This paper presents a survey on the application of ML algorithms in three classical problems of SD&V: structural health monitoring, active control of noise and vibration, and vibroacoustic product design. In structural health monitoring, ML is employed to extract damage-sensitive features from sampled data and to detect, localize, assess, and forecast failures in the structure. In active control of noise and vibration, ML techniques are used in the identification of state-space models of the controlled system, dimensionality reduction of existing models, and design of controllers. In vibroacoustic product design, ML algorithms can create surrogates that are faster to evaluate than physics-based models. The methodologies considered in this work are analyzed in terms of their strength and limitations for each of the three considered SD&V problems. Moreover, the paper considers the role of digital twins and physics-guided ML to overcome current challenges and lay the foundations for future research in the field. • Review of machine learning applied in vibroacoustic and structural dynamics. • Basic principles of the machine learning methods commonly used are presented. • Control, structural health monitoring and design are the most relevant applications. • The current implementation scenario and challenges are reviewed for each application. • This article sheds light on trends and research opportunities merging both fields. [ABSTRACT FROM AUTHOR]

• This paper presents a feed-forward neural network for predicting hydroelastic response of VLFS. • The Levenberg-Marquardt optimisation techniques is shown to provide higher prediction accuracy. • The ANN is trained using dataset generated by finite element-boundary element method.The trained machine is used to predict the hydroelastic response under regular and irregular sea. • ANN is useful for applications such as structural health monitoring and digital twin. The response of a very large floating structure (VLFS) must take into consideration the elastic deformation of the structure (commonly termed hydroelastic response) under wave action. Conventionally, the hydroelastic response could be computed by using the coupled finite element-boundary element (FE-BE) method, where the mat-like structure is modelled using plate theory and the water modelled using the potential theory. The FE-BE method requires the structure to be discretised into finer elements and the wetted surface boundary to be represented by smaller panels to accurately capture the hydroelastic response of the structure. Thus, the coupled FE-BE method could be computationally expensive when the structure gets larger or when subjected to waves of smaller wavelengths. To accelerate the computational time in predicting the hydroelastic response of the VLFS, a surrogate model trained using the feed-forward neural network is proposed. The hydroelastic responses under different wavelengths, structural stiffnesses and wave directions are first generated where these data are split into three groups for training, validation, and testing (prediction) purposes. The accuracy of the prediction in terms of correlation coefficient R is compared for the different train datasets, the number of neurons and hidden layers as well as the optimisation techniques. The finding shows that an accuracy of close to 99% to the ground truth could be achieved with only 80% of the train dataset. The hydroelastic response under irregular wave conditions predicted using the feed-forward neural network framework is also presented. [ABSTRACT FROM AUTHOR]

Finite element method (FEM) based high-fidelity simulation can be computationally demanding and time-consuming as engineering problems become more complicated. It is thus necessary to develop a surrogate model that only requires a small amount of computational time but retains sufficient accuracy. A graph neural network (GNN) based framework is proposed as a general surrogate model for FEM to simulate the Von Mises stress distribution. The mesh body is embedded to a graph and a novel global attribute representation is introduced to capture the geometry and boundary conditions while overcoming the common problem of over smoothing in graph deep learning. The challenge to deal with varying geometry and boundary conditions is overcome by the proposed model and thus it outperforms existing methods such as proper orthogonal decomposition (POD) and greedy algorithm in terms of generalization. Numerical experiments are given to demonstrate the capability of the model developed and the results show that the proposed model not only accurately predicts the stress distribution but also speed-ups hundreds of times faster compared to a FEM-based simulator, enabling real-time structural response analysis for the application of digital twin and structural health monitoring. It is indicated that GNNs can be a powerful tool for resolving complex physical problems, thereby assisting in advancing science and enhancing engineering productivity. • A surrogate model is developed to accelerate the numerical simulation. • Global attributes are proposed to mitigate potential issues with graph deep learning. • Accurate prediction of physical quantities of interest is achieved. • Significant improvements in prediction speed over numerical simulation are achieved. • Powerful generalizability is obtained through the use of graph neural networks. [ABSTRACT FROM AUTHOR]

Distributed fiber optic sensors have exhibited superior capabilities in monitoring cracks in engineering structures through measuring detailed strain distributions. However, manually interpreting the measurements from long distributed sensors deployed in large-scale structures is time-consuming, labor-intensive, and subject to human errors. This paper proposes to automate the identification, localization, quantification, and visualization of cracks through intelligent interpretation of strain distributions measured from distributed fiber optic sensors based on machine learning. Based on these intelligent capabilities, a live digital twin model based on building information modeling is developed to visualize cracks. The digital twin model is updatable with real-time measurements from strain distributions from distributed fiber optic sensors. The proposed approach is evaluated via laboratory testing of a concrete beam. The results show that the proposed approach achieves high accuracy in interpretation of sensor data for crack monitoring. This research advances the capabilities of structural health monitoring using distributed fiber optic sensors. [Display omitted] • Automatic interpretation of strain distributions from distributed fiber optic sensors is enabled. • Machine learning approaches are presented to identify, locate, quantify, and visualize cracks. • A digital twin model is developed to visualize cracks and updated by real-time measurement. • Unsupervised and supervised learning approaches achieve high accuracy and high efficiency. [ABSTRACT FROM AUTHOR]