Development and experimental validation of a prototype system for Machine Learning based SHM in composite aerostructures

PurposeDespite the fast progress in structural health monitoring (SHM), the efficient use in practice of emerging techniques for large civil engineering structures is still a challenge. This paper outlines a practical framework to optimize both the number and the locations of sensors to measure frequency response functions (FRFs) that will be processed and used to predict the location and the damage level in a model of an existing suspension bridge.Design/methodology/approachSensors number and placement (SNPO) procedure is proposed and carried out on a 3D FE model of the 502 m long Oued Dib suspension bridge (Algeria) to determine the degrees of freedom (DOFs) that will receive the sensors. For this purpose, accessible candidate positions on the model are first determined and then reduced by taking the DOFs with the lowest values of the Fisher information matrix (FIM) associated with each of the DOFs taken individually. A genetic algorithm with an objective function equal to the square root of the sum of the squares of the non-diagonal elements of the MAC matrix and a mutation function that allows increasing and decreasing the number of the chromosomes (sensors) of the individuals showed stable convergence to optimal solutions. FRFs at sensor positions generated from the 3D FE model and altered with artificial noise to simulate experimental conditions have been used to constitute a database to train and test a feed-forward neural network.FindingsA framework for SHM integrating a genetic algorithm to optimize both the number and placement of the sensors on the structure.Research limitations/implicationsThe procedure can be applied only for single predefined/potential damage detection.Practical implicationsThe evidence from this study suggests that the proposed procedure provides a consistent framework to implement a SHM scheme for existing large infrastructures.Social implicationsVital infrastructures require special structural protection that can be achieved through effective SHM. This study contributes to the deployment of SHM for existing civil engineering structures.Originality/valueIn addition to the integrated SHM framework proposed in this study, the latter includes an efficient genetic algorithm capable to optimize both the number and the placement of the sensors.

Applications of Machine Learning (ML) algorithms in Structural Health Monitoring (SHM) have become of great interest in recent years owing to their superior ability to detect damage and deficiencies in civil engineering structures. With the advent of the Internet of Things, big data and the colossal and complex backlog of aging civil infrastructure assets, such applications will increase very rapidly. ML can efficiently perform several analyses of clustering, regression and classification of damage in diverse structures, including bridges, buildings, dams, tunnels, wind turbines, etc. In this systematic review, the diverse ML algorithms used in this domain have been classified into two major subfields: vibration-based SHM and image-based SHM. The efficacy of deploying ML algorithms in SHM has been discussed and detailed critical analysis of ML applications in SHM has been provided. Accordingly, practical recommendations have been made and current knowledge gaps and future research needs have been outlined.

Dose assessment of radionuclides dispersion from Bushehr nuclear power plant stack under normal operation and accident conditions

This paper presents a methodology for a structural health monitoring (SHM) system based on optical backscatter reflectometry (OBR) fibre optic networks. The study focuses on the use of machine learning methods to monitor the microdeformation of a drone fuselage and to detect and discriminate be-tween different types of damage when the structure is subjected to static loads. A total of 1500 points are measured for each load, providing a comprehensive understanding of the structural response. In addition, four types of damage, in-cluding partial disbonding at different locations, are induced with varying de-grees of extension to evaluate the sensitivity and accuracy of the SHM system. The results show that the OBR-based SHM system is capable of detecting and localising damage with high accuracy, indicating its potential as a reliable and effective tool for real-time structural health monitoring in aerospace applica-tions. The methodology presented in this study could be extended to other types of structures and damage scenarios, contributing to the development of more advanced and effective SHM systems. Keywords: Machine Learning, OBR sensor network, Unmanned Aerial Vehi-cle, Drone.

Recent advancements in sensor technology, as well as fast progress in internet-based cloud computation; data-driven approaches in structural health monitoring (SHM) are gaining prominence. The majority of time is utilized for reviewing & analyzing the data received from various sensors deployed in structures. This data analysis helps in understating the structural stability and its current state with certain limitations. Considering this fact, integration with Machine Learning (ML) in SHM has attracted significant attention among researchers. This paper is principally aimed at understanding and reviewing of vast literature available in sensor-based data-driven approaches using ML. The implementation and methodology of vibration-based, vision-based monitoring, along with some of the ML algorithms used for SHM are discussed. Nevertheless, a perspective on the importance of data-driven SHM in the future is also presented. Conclusions are drawn from the review discuss the prospects and potential limitations of ML approaches in data-driven SHM applications.KeywordsStructural health monitoringData drivenMachine learningVibration-basedVision-based

Fatigue performance of additively manufactured (AM) components is still uncertain and inconsistent. Structural health monitoring (SHM) systems offer a solution to continuously monitor the structural integrity of a structure. The effective Structural Health Monitoring (eSHM) system is the first SHM principle developed with the principal purpose to monitor AM components. The eSHM principle exploits the design freedom offered by AM to integrate a capillary inside the component. The capillary is put under low vacuum and the pressure is monitored during the operation of the component. As-built AM surfaces report elevated surface roughness and are one of the principle causes of premature fatigue initiation and fatigue failure. The current study will investigate the effect of a chemical etching (CE) post-process on the capillary surface and evaluate its effect on the fatigue performance.

During the last decades, structural health monitoring (SHM) systems are used in order to detect damage in structures. We have developed a novel structural health monitoring approach, the so-called “effective structural health monitoring” (eSHM) system. The current SHM system is incorporated into a metallic structure by means of additive manufacturing (AM) and has the possibility to advance life safety and reduce direct operative costs. It operates based on a network of capillaries that are integrated into an AM structure. The internal pressure of the capillaries is continuously monitored by a pressure sensor. When a crack nucleates and reaches the capillary, the internal pressure changes signifying the existence of the flaw. The main objective of this paper is to evaluate the crack detection capacity of the eSHM system and crack location accuracy by means of various non-destructive testing (NDT) techniques. During this study, detailed acoustic emission (AE) analysis was applied in AM materials for the first time in order to investigate if phenomena like the Kaiser effect and waveform parameters used in conventional metals can offer valuable insight into the damage accumulation of the AM structure as well. Liquid penetrant inspection, eddy current and radiography were also used in order to confirm the fatigue damage and indicate the damage location on un-notched four-point bending AM metallic specimens with an integrated eSHM system. It is shown that the eSHM system in combination with NDT can provide correct information on the damage condition of additive manufactured metals.

PurposeOne of the paramount challenges in the field of structural health monitoring (SHM) is the precise assessment of structural damage. Recently, many methods have been proposed to diagnose damage in structures using time series data. Nevertheless, these techniques are restricted in their ability to capture the bidirectional temporal and spatial relationships among the data. To remedy these shortcomings, this study proposes an advanced deep learning (DL) technique that integrates one-dimensional convolutional neural networks (1DCNN) with bidirectional long short-term memory (BiLSTM) networks, termed BiLSTM-1DCNN.Design/methodology/approachThis study proposes an advanced deep learning (DL) technique that integrates one-dimensional convolutional neural networks (1DCNN) with bidirectional long short-term memory (BiLSTM) networks, termed BiLSTM-1DCNN. The novelty of BiLSTM-1DCNN comes in its effective fusion of 1DCNN’s local feature extraction and BiLSTM’s capacity to capture long-term information from both directions (forward and backward).FindingsValidation using a dataset from the Nam O steel truss bridge demonstrates that the proposed method surpasses conventional models, including 1DCNN (87.9%), LSTM (72.5%), BiLSTM (76.1%) and LSTM-1DCNN (91.1%), achieving an accuracy rate of 96.4%. This approach provides a significant advancement in SHM, paving the way for more accurate and reliable damage detection.Research limitations/implicationsThe study’s limitations include potential overfitting due to the model’s complexity and the high computational resources required. The BiLSTM-1DCNN model’s performance is also influenced by the quality and quantity of the training data as well as the specific characteristics of the dataset. Additionally, while the model performs well in detecting damage in the Nam O steel truss bridge, its generalizability to other types of structures and environmental conditions remains untested.Practical implicationsThe BiLSTM-1DCNN model offers significant practical benefits for structural health monitoring by enhancing damage detection accuracy. Its ability to effectively capture both local features and long-term temporal dependencies makes it a valuable tool for real-time monitoring and early detection of structural issues. This can lead to more timely maintenance actions, potentially reducing repair costs and improving safety. The model’s high accuracy in detecting damage can also support infrastructure management decisions, contributing to better resource allocation and enhanced overall safety of critical structures.Social implicationsThe BiLSTM-1DCNN model’s advanced damage detection capabilities have positive social implications, such as improving the safety and reliability of public infrastructure like bridges. Enhanced structural health monitoring can reduce the risk of catastrophic failures, protecting lives and reducing accidents. By providing more accurate and timely assessments, the model can also lead to more efficient use of maintenance and repairs, ensuring that resources are allocated effectively.Originality/valueThe originality of the BiLSTM-1DCNN model lies in its innovative integration of one-dimensional convolutional neural networks (1DCNN) with bidirectional long short-term memory (BiLSTM) networks. This unique combination leverages 1DCNN’s strength in local feature extraction and BiLSTM’s capacity to capture temporal dependencies in both directions, addressing the limitations of existing methods. The model’s high accuracy in detecting structural damage, as demonstrated by its performance on the Nam O steel truss bridge dataset, highlights its value in advancing structural health monitoring technologies and offers a significant improvement over traditional approaches.

Composite structures are generally more susceptible to impact damage than non-composite structures, and early identification of damage is the primary goal of structural health monitoring (SHM). If such damage remains undetected or reaches a critical size, it can lead to sudden collapse and catastrophic failure. Modern SHM methods aim to preserve the integrity of composite structures through continuous inspection, monitoring, and damage assessment, including detection, localization, quantification, classification, and prognosis. These methods use sensor-based technologies to assess vibration, extension, and acoustic and thermal emission. This paper provides a review of various computational methods including physics-based methods (signal processing techniques, modal analysis, and finite element model updating) and optimization methods (inverse problems, particle swarm optimization, topology optimization, genetic algorithms, time series analysis, and hybrid techniques), alongside machine learning methodologies employing neural networks as well as deep learning for damage identification in composite structures. These computational and learning-based techniques are widely applied in the development of algorithms, optimization strategies, and hybrid frameworks for SHM. The review further summarizes the applications, advantages, and limitations of each method according to structure type and damage characteristics. The key emphasis of this review is on integrating computational approaches, as well as machine learning, to enhance the efficiency of damage identification. The conclusion is drawn based on an overview of the literature, focusing on the contributions of different computational methods and machine learning for damage identification in composites.

<p>Machine learning (ML) provides a promising paradigm for discovering and modeling structural performances and conditions through the deep mining of structural health monitoring data. This paper exhibits recent progress of ML-based structural health monitoring and condition assessment for long-span bridges. A series of novel algorithms for bridge condition assessment via correlation modeling between structural responses, computer vision-assisted structural damage detection, and data mining for wind effects are introduced. First, correlation modeling between different bridge responses is investigated by both the time series data and probability distribution, further assisting bridge condition assessment. Second, several novel CNN architectures and a few-shot meta-learning framework are also established for CV-assisted bridge damage detection. Third, wind-induced vibrations of the bridge in site are identified and modeled to predicate structural responses and evaluate operation conditions. Results show that ML techniques indeed improve the state of the art in structural health monitoring and condition assessment for long-span bridges.</p>

This study presents a novel methodology for structural health monitoring (SHM), using a self-powered sensing concept, within the context of machine learning (ML) and pattern recognition (PR). The proposed method is based on the interpretation of data provided by a self-powered discrete analog wireless sensor used to measure the structural response along with an energy-efficient pulse switching technology employed for data communication. A system using such an energy-aware sensing technology demands dealing with power budgets for sensing and communication of binary data, resulting in missing and incomplete data received at the SHM processor. Numerical studies were conducted on an aircraft wing stabilizer subjected to dynamic loading to evaluate and verify the performance of the proposed methodology. Damage was simulated on a finite element model by decreasing stiffness in a region of the stabilizer’s skin. Several features, i.e., patterns or images, were extracted from the strain response of the stabilizer. The obtained features were fed into a ML methodology incorporating low-rank matrix decomposition and PR for damage diagnosis of the wing. Different ML algorithms, including support vector machine, k-nearest neighbor, and artificial neural networks, were integrated within the learning methodology to assess the performance of the damage detection approach. Different levels of harvested energy were also considered to evaluate the robustness of the damage detection method with respect to such variations. Further, reliability of the proposed methodology was evaluated through an uncertainty analysis. Results demonstrate that the developed SHM methodology employing ML is efficient in detecting damage from a novel self-powered sensor network, even with noisy and incomplete binary data.

Structural health monitoring has been increasingly used due to the advances in sensing technology and data analysis, facilitating the shift from time-based to condition-based maintenance. This work is part of the efforts which have applied structural health monitoring to the Sydney Harbour Bridge – one of Australia’s iconic structures. It combines dimensionality reduction and pattern recognition techniques to accurately and efficiently distinguish faulty components from well-functioning ones. Specifically, random projection is used for dimensionality reduction on the vibration feature data. Then, healthy and damaged patterns of bridge components are learned in the lower dimensional projected space using supervised and unsupervised machine learning methods, namely, support vector machine and one-class support vector machine. The experimental results using data from a laboratory-based building structure and the Sydney Harbour Bridge showed high feasibility of applying machine learning techniques to dimensionality reduction and damage detection in structural health monitoring. Random projection combined with support vector machine significantly reduces the computational time while maintaining the detection accuracy. The proposed method also outperformed popular dimensionality reduction techniques. The computational time of the method using random projection can be more than 200 times faster than that without using dimensionality reduction while still achieving similar detection accuracy.

Despite the generally long life span of concrete structures, they cannot be considered maintenance-free. Several incidents of catastrophic failures remind the engineering world that monitoring of structures is imperative nowadays both for prevention of loss of life and property and also for effective infrastructure management based on a usually finite budget. Due to the variety of structural sizes, shapes, and uses, as well the possible vulnerabilities of the different types of structures, different tools must be used, many times complementary, in order to lead to reliable assessment results. Indeed, the reliability of in situ implementation is a key issue for any health monitoring technique along with other characteristics such as testing speed and cost-effectiveness. Several nondestructive testing (NDT) techniques have already been established, showing their suitability in certain aspects of material and structural characterization and behavior monitoring. As an example, the use of ultrasonic pulse velocity can be mentioned, the correlation of which with the quality of concrete is well documented. Other techniques based on elastic waves such as impact and impulse response, as well as the radar method, have proven their suitability in distinguishing delaminations and inhomogeneities. The assessment based on the above-mentioned methods as well as a number of others, like acoustic emission, radiography, vibration modal analysis, and slightly destructive surface strength methods in conjunction with visual inspection, provides a valuable platform for decision making concerning the maintenance, based on more robust engineering criteria than solely the experience of the engineer. However, it is a common impression that most NDT techniques have not at all reached their full potential especially with regard to in situ implementation. Therefore, the current special issue intends to examine all possible tools for economic and timely infrastructure condition assessment, with emphasis on reliability and connection of the monitoring results with the proper maintenance action that should be taken. The challenges are even higher since new and innovative materials are being increasingly used. These materials include high performance concrete, textile reinforced concrete, and nanomodified and recycled materials, which offer better capabilities for sustainable structures; however their assessment through the same techniques used for conventional concrete should not be taken for granted. In this special issue, the latest advances in different topics of civil structural health monitoring (SHM) are highlighted. More specifically, recent findings in elastic wave methods (acoustic emission, impact-echo, and ultrasonics) are reported. Vibration methodologies which are the most suitable for global bridge SHM are discussed, while the use of radar is reviewed and applied. Advancements in automated robotic inspection and online monitoring of bridge components are also discussed. The issue includes studies on corrosion detection, reinforcing and self-sensing elements for SHM. Algorithms incorporating pattern recognition clustering for the characterization of the location and degree of damage could not but be a strong part of the issue, while monitoring of self-healing and textile-reinforced materials is also discussed. The dual importance of monitoring of old structures is stressed out: their structural safety as well as their cultural heritage significance. The methodologies are successfully tested in several case studies as reported herein. We believe that the present special issue reflects on the recent advances in SHM and NDT for civil structures and materials complemented with insightful findings of various assessment techniques. We wish to thank all the authors for submitting their work in the issue and their patience during the review process. Dimitrios G. Aggelis Ninel Alver Hwa Kian Chai

This study explores the growing influence of artificial intelligence (AI) on structural health monitoring (SHM), a critical aspect of infrastructure maintenance and safety. This study begins with a bibliometric analysis to identify current research trends, key contributing countries, and emerging topics in AI-integrated SHM. We examine seven core areas where AI significantly advances SHM capabilities: (1) data acquisition and sensor networks, highlighting improvements in sensor technology and data collection; (2) data processing and signal analysis, where AI techniques enhance feature extraction and noise reduction; (3) anomaly detection and damage identification using machine learning (ML) and deep learning (DL) for precise diagnostics; (4) predictive maintenance, using AI to optimize maintenance scheduling and prevent failures; (5) reliability and risk assessment, integrating diverse datasets for real-time risk analysis; (6) visual inspection and remote monitoring, showcasing the role of AI-powered drones and imaging systems; and (7) resilient and adaptive infrastructure, where AI enables systems to respond dynamically to changing conditions. This review also addresses the ethical considerations and societal impacts of AI in SHM, such as data privacy, equity, and transparency. We conclude by discussing future research directions and challenges, emphasizing the potential of AI to enhance the efficiency, safety, and sustainability of infrastructure systems.

Structural Health Monitoring (SHM) is a condition-based maintenance technology using sensing systems. In SHM, the use of domain knowledge is essential: it motivates the use of machine learning approaches; it can be used to extract damage sensitive features and interpret the results by machine learning. This work focuses on two SHM problems: damage identification and substructure clustering. Our solutions to address them are based on machine learning techniques and robust feature extraction using domain knowledge. In the first problem, damage sensitive features were extracted using a frequency domain decomposition, followed by a robust one-class support vector machine for damage detection. In the second problem, a novel clustering technique and spectral moment feature were utilised for substructure grouping and anomaly detection. These methods were evaluated using data from lab-based structures and data collected from the Sydney Harbour Bridge. We obtained high damage detection accuracies and were able to assess damage severity. Furthermore, the clustering technique was able to group substructures of similar behaviour and detect spatial anomalies.