9 results
Now showing1 - 9 of 9
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Comparative analysis of explainable artificial intelligence methods in sensor fault diagnosis for vibration-based structural health monitoringReliable structural health monitoring (SHM) depends on accurate analysis of sensor data as well as on fault-free operation of sensors collecting the data, which is usually ensured via sensor fault diagnosis (FD). Artificial intelligence (AI) models have shown promising po-tential for sensor FD, mainly exploiting the pattern-learning capabilities in the sensor data. However, the logic behind AI predictions is often opaque, limiting practitioner trust and adop-tion in autonomous SHM systems. To counteract the aforementioned limitation, explainable artificial intelligence (XAI) has emerged, aiming to improve transparency of AI models by in-dicating which aspects of input sensor data influence AI-derived predictions. Nevertheless, XAI applications in SHM remain rare, and most studies focus on the feasibility of applying XAI for SHM rather than practical aspects, such as the reliability and robustness of XAI explanations. This study investigates explanation robustness in XAI-based sensor FD for vibration-based SHM through a comparative analysis of different XAI methods. In particular, AI models are trained on sensor data, and synthetic faults are injected in the sensor data, simulating realistic sensor faults. Explanation robustness is analyzed using attribution consistency (Spearman rank correlation coefficient), and attribution stability (coefficient of variation) across multiple fault scenarios, comparing gradient-based and perturbation-based XAI methods. Validation tests are presented using acceleration response data, collected from a pedestrian bridge. The vali-dation results show that gradient-based methods demonstrate higher explanation robustness than perturbation-based methods when explaining vibration-based sensor fault patterns. Fu-ture work will extend the comparative analysis to distinguish between anomalies caused by sensor faults and anomalies arising from changes in structural dynamic behavior.Publicationtype: Conference Paper7 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Digital twins in civil engineeringA plenitude of digital twin reviews have been published in recent years, most of which, however, focus on project-specific digital twin implementations or specific application areas within civil engineering. The architecture, including the composition of internal elements, and schemas of digital twins have not been studied yet in a universally applicable and systematic manner. In this study, a multivocal review of digital twins in civil engineering is conducted, combining a systematic literature review and a gray literature review to capture both peer-reviewed literature and industry practices. To achieve a shared understanding of digital twins in civil engineering, a systematic survey of definitions, schemas, system architectures, and internal elements of digital twins is conducted. Drawing from the results of the review, (i) a definition, (ii) a pattern for a schema, and (iii) a reference architecture for digital twins are proposed, serving as a blueprint for facilitating digital twin implementations in civil engineering.Publicationtype: Journal Article19 7 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Quantum and quantum-inspired computing in civil engineeringQuantum computing is expected to offer solutions to computational problems that are otherwise computationally intractable. Although the core technology is still being developed, quantum-inspired computing already has been offering practical advantages for several computationally challenging problems. Despite the promising potential of both quantum computing and quantum-inspired computing, applications in civil engineering remain underexplored. This study aims to lay the foundation for future adoption by introducing the fundamental principles of quantum computing and quantum-inspired computing and by conducting a multivocal literature review. The review provides insights into the current research landscape in civil engineering and offers a detailed analysis of potential use cases and application areas. The findings are expected to serve as a foundation for guiding future research endeavors and practical deployments of quantum computing and quantum-inspired computing in civil engineering, as these technologies continue to mature.Publicationtype: Journal Article24 25 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Decentralized sensor fault diagnosis for wireless structural health monitoring systems using Artificial Intelligence of Things(DEStech Publications, 2025-09); ; ; ; Structural health monitoring (SHM) is a non-destructive evaluation technique that utilizes sensor data for assessing the condition of civil infrastructure. Sensors in SHM systems may experience faults, which may influence the accuracy, reliability, and performance of SHM systems. The timely detection, isolation, and accommodation of sensor faults in SHM systems has been the focus of sensor fault diagnosis (FD) approaches, which have increasingly been employing artificial intelligence (AI) algorithms due to the effectiveness of AI in sensor FD. However, current AI-based FD approaches require transmitting large amounts of raw sensor data to centralized servers for offline analysis, resulting in inefficiencies as well as computational burdens on centralized servers. This paper introduces a decentralized sensor fault diagnosis (DSFD) approach for wireless SHM systems using Artificial Intelligence of Things (AIoT). In particular, AI-based FD models are embedded into wireless sensor nodes of SHM systems to detect, isolate, and accommodate sensor faults. By embedding the FD models into the wireless sensor nodes, only high-level information, specifically the status of the sensors, is transmitted to centralized servers. As a result, data transmission inefficiencies as well as computational burdens on centralized servers are reduced. The proposed DSFD approach is validated in a controlled laboratory experiment, in which custom- built wireless senor nodes are installed on a test structure that is dynamically excited using a shake table. After training and embedding the AI-based FD models into the custom-built wireless sensor nodes, sensor faults are artificially injected into the sensor data, demonstrating the ability of the DSFD approach to diagnose sensor faults in a decentralized manner. The results of the validation test corroborate the capability of the proposed approach to efficiently ensure the accuracy, reliability, and performance of SHM systems.Publicationtype: Conference Paper5 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Decision making in structural health monitoring using large language models(DEStech Publications, 2025-09); ; ; ; Structural health monitoring (SHM) is fundamental in decision making for damage identification and prescriptive maintenance of civil infrastructure. Traditional decisionmaking methods often fall short in integrating heterogeneous sensor data, inherent to SHM, and the natural language processing required to interpret, e.g., inspection reports, expert assessments, and historical documentation relevant to prescriptive maintenance. To address these limitations, this study introduces a framework for integrating large language models (LLMs) into SHM workflows, facilitating decision making in damage identification and prescriptive maintenance. The proposed framework links convolutional neural networks (CNNs) with generative LLMs. Unlike approaches based solely on prompt engineering, this study applies task-specific fine-tuning via low-rank adaptation (LoRA) to the Mistral-7B-Instruct-v0.1 model, using CNN-generated output and damage metadata as input. The results demonstrate – apart from the proof of concept – a successful generalization to previously unseen CNN-generated output, enabling context-sensitive damage identification. In conclusion, integrating LLMs into SHM workflows allows synthesizing heterogeneous sensor data and natural language, thus enhancing decision making for damage identification and prescriptive maintenance of civil infrastructure.Publicationtype: Conference Paper20 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , A decentralized digital twinning approach for wireless structural health monitoring systemsSince the introduction of wireless technologies in structural health monitoring (SHM), researchers have focused on exploiting the computational capabilities of wireless sensor nodes via embedded computing approaches that enable on-board data analysis, in lieu of wirelessly transmitting large amounts of data. Embedded computing for wireless SHM has largely been based on data-driven analysis methods, which only implicitly account for the physics governing the structural behavior. However, the increasing digitalization of societal activities, including structural maintenance, is frequently associated with digital twinning, which builds upon continuous exchange of data between the digital and the physical world and, often, upon physics-based modeling. In this context, this paper presents an approach for integrating digital twins into wireless SHM systems. Given the distributed nature of wireless sensor networks, characterized by the quasi-independent operation of wireless sensor nodes, the digital twins are designed in a decentralized manner, leveraging the computational power of wireless sensor nodes. In particular, the decentralized digital twins are represented by partial finite element (FE) models of a structure being monitored that are embedded in the wireless sensor nodes and “live” and “evolve” in tandem with the structure. The wireless sensor nodes use the partial FE models and structural response data locally collected to collaboratively assess the structural condition. The proposed approach is validated via laboratory tests, the results of which showcase the capability of the approach to yield reliable estimates of the structural condition.Publicationtype: Conference Paper21 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , BIM-based human-robot collaboration for building inspections using mixed reality(European Council on Computing in Construction (EC3), 2025-07); ; ; 13 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , An embedded computing approach for vibration-based system identification using reduced-order finite elementsSystem identification (SID) constitutes a focal point in experimental testing of civil infrastructure as well as in structural health monitoring (SHM). Conventional SID approaches have relied on creating finite element (FE) models of civil infrastructure assets and on calibrating the models against in-situ derived information from testing equipment or against SHM data. FE models are capable of providing valuable information on the structural condition. However, the equations governing the FE method are coupled, usually calling for centralized data collection, which may be unsuitable for modern wireless SHM systems that employ independently operating wireless sensor nodes. In this paper, a SID approach for making full use of FE models on board wireless sensor nodes is presented, based on embedded computing and on reduced-order finite elements. Specifically, FE models of civil infrastructure assets are reduced, using model-order reduction, and partitioned into partial models, which represent different substructures and are computationally efficient for embedment in wireless sensor nodes. Using the partial models and structural response data from the substructures, insights into the structural condition of the civil infrastructure assets are obtained. The proposed approach is suitable for vibration-based SID, applied as part of long-term SHM strategies, and implementable in wireless SHM systems. Validation tests using SHM data recorded from a real-world road bridge showcase the validity of the proposed SID approach.Publicationtype: Conference Paper14 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Physics-based wireless structural health monitoring and control using temporal finite elements(Institute of Structural Analysis and Antiseismic Research National Technical University of Athens, 2025-06); ; ; Integrating structural control into wireless structural health monitoring systems typically entails implementing control algorithms that predict counteracting forces for keeping the structural response within acceptable bounds. Control algorithms usually involve data-driven analysis, implemented in wireless sensor networks as feedback-loop systems. Although effective, data-driven analysis for structural control hardly accounts for the physics underlying the structural behavior. In an attempt to implement structural control in an intuitive manner for engineers, this work suggests an embedded structural control method that builds upon physics-based modeling, using the finite element method for analysis. In particular, the proposed physics-based wireless structural health monitoring and control (SHMC) method bases the prediction of control forces on temporal finite elements (TFE), which integrate the time dimension into the well-known FE spatial shape functions. Prior to embedment, the TFE models are reduced to (i) decrease the computational burden on the sensor nodes and (ii) match the discretization of the TFE models with the degrees of freedom measured by the SHMC system. The proposed SHMC method is implemented in a prototype wireless SHMC system and validated in laboratory tests on a model frame structure mounted on a shake table. The results showcase the capability of the physics-based wireless SHMC method to retain the structural response within previously defined bounds.Publicationtype: Conference Paper28