Israel Alejandro Hernández-González
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Israel Alejandro Hernández-González has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Enrique García-Macías
University of Granada
6 shared publications - Filippo Ubertini
University of Perugia
6 shared publications - José Solís-Hernández
CEMOSA
4 shared publications - Paula Lopez-Arevalo
CEMOSA
2 shared publications - Antonio Vallecillo-Morcillo1 shared publication
- Elisa Tomassini
University of Perugia
1 shared publication
Latest Publications
- Open Access
- 18 November 2026
- Published by Springer Nature
- p. 541-548
Data-Driven Evaluation of Viaduct Pot Bearings: Condition Assessment and Anomaly Detection Using LVDT Sensors
This study presents a methodology for structural health monitoring (SHM) of viaducts using Linear Variable Differential Transformer (LVDT) sensors installed on pot bearings. The aim is to use continuous LVDT measurements to evaluate and predict bearing condition and potential degradation. Two complementary approaches are proposed: (1) condition assessment based on regulatory standards and (2) data-driven anomaly detection techniques. The first approach focuses on accumulated sliding distance; a key parameter derived from LVDT data and is evaluated according to legislation. The second approach analyzes vibration responses during train passages to estimate dynamic properties of the bearings, mainly natural frequencies and damping ratios. This methodology combines signal filtering, Blind Source Separation (BSS), and system identification methods such as the Natural Excitation Technique (NExT) and the Ibrahim Time Domain (ITD) approach. From the identified parameters, time series are constructed and evaluated in real time using control charts and multivariate statistical tools, such as Hotelling’s T 2 . By combining both techniques, this approach enhances the early detection of bearing anomalies and contributes to predictive maintenance strategies. The integration of LVDT monitoring with advanced data analysis provides a robust framework for real-time SHM and improved management of viaduct infrastructure.
- 18 November 2026
- Published by Springer Nature
- p. 541-548
Open AccessData-Driven Evaluation of Viaduct Pot Bearings: Condition Assessment and Anomaly Detection Using LVDT Sensors
This study presents a methodology for structural health monitoring (SHM) of viaducts using Linear Variable Differential Transformer (LVDT) sensors installed on pot bearings. The aim is to use continuous LVDT measurements to evaluate and predict bearing condition and potential degradation. Two complementary approaches are proposed: (1) condition assessment based on regulatory standards and (2) data-driven anomaly detection techniques. The first approach focuses on accumulated sliding distance; a key parameter derived from LVDT data and is evaluated according to legislation. The second approach analyzes vibration responses during train passages to estimate dynamic properties of the bearings, mainly natural frequencies and damping ratios. This methodology combines signal filtering, Blind Source Separation (BSS), and system identification methods such as the Natural Excitation Technique (NExT) and the Ibrahim Time Domain (ITD) approach. From the identified parameters, time series are constructed and evaluated in real time using control charts and multivariate statistical tools, such as Hotelling’s T 2 . By combining both techniques, this approach enhances the early detection of bearing anomalies and contributes to predictive maintenance strategies. The integration of LVDT monitoring with advanced data analysis provides a robust framework for real-time SHM and improved management of viaduct infrastructure.
- Open Access
- 18 November 2026
- Published by Springer Nature
- p. 387-393
Real-Time Monitoring Platform for Railway Bridges Using Operational Modal Analysis and Artificial Intelligence
This paper presents a digital platform for real-time Structural Health Monitoring (SHM) of railway bridges, integrating Operational Modal Analysis (OMA), machine learning, and artificial intelligence (AI). The system allows continuous assessment of bridge performance under traffic without service interruption. Modal parameters are extracted using subspace identification to detect subtle changes in dynamic behavior. Environmental effects are compensated through data-driven models based on principal component analysis and temperature-frequency correction. AI-based metamodels enable localization of structural anomalies, if present. The platform features a digital twin interface that visualizes the evolution of dynamic parameters over time, along with control charts to identify potential failure mechanisms. The system is currently implemented on the Huertas de Mateo Viaduct, a prestressed concrete railway bridge in Minglanilla (Cuenca), on the Madrid–Valencia high-speed rail line. This deployment demonstrates the platform’s capacity to monitor structural condition and support sustainable maintenance planning. The proposed solution contributes to user-centered and green mobility by improving safety and efficiency in railway infrastructure through advanced monitoring technologies.
- 18 November 2026
- Published by Springer Nature
- p. 387-393
Open AccessReal-Time Monitoring Platform for Railway Bridges Using Operational Modal Analysis and Artificial Intelligence
This paper presents a digital platform for real-time Structural Health Monitoring (SHM) of railway bridges, integrating Operational Modal Analysis (OMA), machine learning, and artificial intelligence (AI). The system allows continuous assessment of bridge performance under traffic without service interruption. Modal parameters are extracted using subspace identification to detect subtle changes in dynamic behavior. Environmental effects are compensated through data-driven models based on principal component analysis and temperature-frequency correction. AI-based metamodels enable localization of structural anomalies, if present. The platform features a digital twin interface that visualizes the evolution of dynamic parameters over time, along with control charts to identify potential failure mechanisms. The system is currently implemented on the Huertas de Mateo Viaduct, a prestressed concrete railway bridge in Minglanilla (Cuenca), on the Madrid–Valencia high-speed rail line. This deployment demonstrates the platform’s capacity to monitor structural condition and support sustainable maintenance planning. The proposed solution contributes to user-centered and green mobility by improving safety and efficiency in railway infrastructure through advanced monitoring technologies.
- Open Access
- 31 August 2026
- Published by Taylor & Francis in Digital Water
- Vol. 4 (1)
Development of a basin-scale digital twin platform for integrated water resources management
1. Water-resources management is increasingly challenged by climate variability, growing water demand and the need to balance environmental, social and economic objectives at the basin scale (Monta...
- 31 August 2026
- Published by Taylor & Francis in Digital Water
- Vol. 4 (1)
Open AccessDevelopment of a basin-scale digital twin platform for integrated water resources management
1. Water-resources management is increasingly challenged by climate variability, growing water demand and the need to balance environmental, social and economic objectives at the basin scale (Monta...
- Open Access
- 1 January 2026
- Published by Wiley in Structural Control and Health Monitoring
- Vol. 2026 (1)
Infrastructure Anomaly Detection: A Study of the Settefonti Bridge Through Continuous OMA and Artificial Intelligence
This paper presents a novel approach for anomaly detection on the Settefonti Bridge by combining advanced operational modal analysis (OMA) technique with artificial intelligence. Ambient vibration data from accelerometers is processed using the covariance‐driven stochastic subspace identification (CoV‐SSI) method to extract modal parameters, which are then analyzed using statistical pattern recognition and Hotelling’s T2 control charts. In parallel, strain gauge time series data are evaluated with deep neural network‐based autoencoders that detect anomalies via reconstruction error analysis. This integrated framework enables robust, continuous structural monitoring and facilitates early damage detection, thereby supporting timely maintenance and enhanced safety of the bridge.
- 1 January 2026
- Published by Wiley in Structural Control and Health Monitoring
- Vol. 2026 (1)
Open AccessInfrastructure Anomaly Detection: A Study of the Settefonti Bridge Through Continuous OMA and Artificial Intelligence
This paper presents a novel approach for anomaly detection on the Settefonti Bridge by combining advanced operational modal analysis (OMA) technique with artificial intelligence. Ambient vibration data from accelerometers is processed using the covariance‐driven stochastic subspace identification (CoV‐SSI) method to extract modal parameters, which are then analyzed using statistical pattern recognition and Hotelling’s T2 control charts. In parallel, strain gauge time series data are evaluated with deep neural network‐based autoencoders that detect anomalies via reconstruction error analysis. This integrated framework enables robust, continuous structural monitoring and facilitates early damage detection, thereby supporting timely maintenance and enhanced safety of the bridge.
- Open Access
- 10 January 2025
- Published by Anil K Agrawal, LLC in International Journal of Bridge Engineering, Management and Research
- Vol. 2 (1) , 21425007-1:16
Leveraging Artificial Intelligence to unlock Next-Generation SHM software: Advanced Feature Extraction and Damage Identification
The significant socio-economic impacts of aging infrastructure have driven the growing implementation of Structural Health Monitoring (SHM) worldwide as a key preventive maintenance strategy. However, scaling SHM systems nationwide presents significant hardware and software challenges, particularly in managing densely instrumented structures and deploying effective damage identification algorithms. This explains the circumstance that most SHM software tools are custom-built by specialized research groups, limiting technology transfer. In this context, although still in its early stages, the latest advances in Artificial Intelligence (AI) offer promising solutions to overcome these scalability issues. In this line, this work introduces the latest developments of MOVA/MOSS, a comprehensive SHM software platform developed by the authors that leverages AI to accelerate feature extraction in vibration-based systems and generate digital twins for quasi real-time damage identification. The potential of the developed platform is demonstrated through a real-world structure, the Mendez Nuñez Bridge in Spain, highlighting AI’s potential in facilitating the widespread adoption of SHM.
- 10 January 2025
- Published by Anil K Agrawal, LLC in International Journal of Bridge Engineering, Management and Research
- Vol. 2 (1) , 21425007-1:16
Open AccessLeveraging Artificial Intelligence to unlock Next-Generation SHM software: Advanced Feature Extraction and Damage Identification
The significant socio-economic impacts of aging infrastructure have driven the growing implementation of Structural Health Monitoring (SHM) worldwide as a key preventive maintenance strategy. However, scaling SHM systems nationwide presents significant hardware and software challenges, particularly in managing densely instrumented structures and deploying effective damage identification algorithms. This explains the circumstance that most SHM software tools are custom-built by specialized research groups, limiting technology transfer. In this context, although still in its early stages, the latest advances in Artificial Intelligence (AI) offer promising solutions to overcome these scalability issues. In this line, this work introduces the latest developments of MOVA/MOSS, a comprehensive SHM software platform developed by the authors that leverages AI to accelerate feature extraction in vibration-based systems and generate digital twins for quasi real-time damage identification. The potential of the developed platform is demonstrated through a real-world structure, the Mendez Nuñez Bridge in Spain, highlighting AI’s potential in facilitating the widespread adoption of SHM.
- Open Access
- 1 July 2024
- Published by NDT.net GmbH & Co. KG in e-Journal of Nondestructive Testing
- Vol. 29 (7)
Multi-Task AI-driven undetermined blind source identification for modal identification of large scale structures
The effective management of aging infrastructure represents a critical concern globally, exerting profound socio-economic influences and occupying a prominent position on the political agenda. The escalating occurrences of catastrophic collapses in recent years underscore the pressing requirement for efficient Structural Health Monitoring (SHM) strategies. These strategies play a pivotal role in aiding decision-making processes related to prioritizing interventions and rehabilitation efforts. Among SHM systems, those utilizing Operational Modal Analysis (OMA) through vibration-based techniques have gained popularity due to their non-destructive nature, comprehensive damage assessment capabilities, and relative ease of automation. Despite their advantages, current OMA methods encounter significant scalability challenges, primarily attributable to extensive computational demands and the necessity for substantial expert involvement. In this context, recent advancements in the field of artificial intelligence (AI) present a promising solution to address these scalability issues, opening the door for the development of next-generation SHM systems. This study introduces an innovative Multitask Learning Deep Neural Network (MTL-DNN) model designed for rapid and automated blind source modal identification of structures. Integrating the concepts of undetermined second-order blind source identification (SOBI) into the architecture of the network, the proposed model can reveal the independent modal components present in the raw response acceleration data with minimum computational burden. The presented results demonstrate the quasi-instantaneous modal identification capabilities of the proposed architecture, enabling the estimation of more components than the number of sensors.
- 1 July 2024
- Published by NDT.net GmbH & Co. KG in e-Journal of Nondestructive Testing
- Vol. 29 (7)
Open AccessMulti-Task AI-driven undetermined blind source identification for modal identification of large scale structures
The effective management of aging infrastructure represents a critical concern globally, exerting profound socio-economic influences and occupying a prominent position on the political agenda. The escalating occurrences of catastrophic collapses in recent years underscore the pressing requirement for efficient Structural Health Monitoring (SHM) strategies. These strategies play a pivotal role in aiding decision-making processes related to prioritizing interventions and rehabilitation efforts. Among SHM systems, those utilizing Operational Modal Analysis (OMA) through vibration-based techniques have gained popularity due to their non-destructive nature, comprehensive damage assessment capabilities, and relative ease of automation. Despite their advantages, current OMA methods encounter significant scalability challenges, primarily attributable to extensive computational demands and the necessity for substantial expert involvement. In this context, recent advancements in the field of artificial intelligence (AI) present a promising solution to address these scalability issues, opening the door for the development of next-generation SHM systems. This study introduces an innovative Multitask Learning Deep Neural Network (MTL-DNN) model designed for rapid and automated blind source modal identification of structures. Integrating the concepts of undetermined second-order blind source identification (SOBI) into the architecture of the network, the proposed model can reveal the independent modal components present in the raw response acceleration data with minimum computational burden. The presented results demonstrate the quasi-instantaneous modal identification capabilities of the proposed architecture, enabling the estimation of more components than the number of sensors.
- 23 June 2024
- Published by Springer Nature
- p. 435-447
Incorporating Digital Twins and Artificial Intelligence for Next-Generation SHM Software
- 23 June 2024
- Published by Springer Nature
- p. 435-447
Incorporating Digital Twins and Artificial Intelligence for Next-Generation SHM Software
- 22 June 2024
- Published by Springer Nature
- p. 113-124
Quasi-instantaneous Operational Modal Analysis of Bridges Through AI-Driven Blind Source Separation
- 22 June 2024
- Published by Springer Nature
- p. 113-124
Quasi-instantaneous Operational Modal Analysis of Bridges Through AI-Driven Blind Source Separation
- Open Access
- 6 April 2024
- Published by Springer Nature in Engineering with Computers
- Vol. 40 (5) , 3157-3174
Towards a comprehensive damage identification of structures through populations of competing models
Model-based damage identification for structural health monitoring (SHM) remains an open issue in the literature. Along with the computational challenges related to the modeling of full-scale structures, classical single-model structural identification (St-Id) approaches provide no means to guarantee the physical meaningfulness of the inverse calibration results. In this light, this work introduces a novel methodology for model-driven damage identification based on multi-class digital models formed by a population of competing structural models, each representing a different failure mechanism. The forward models are replaced by computationally efficient meta-models, and continuously calibrated using monitoring data. If an anomaly in the structural performance is detected, a model selection approach based on the Bayesian information criterion (BIC) is used to identify the most plausibly activated failure mechanism. The potential of the proposed approach is illustrated through two case studies, including a numerical planar truss and a real-world historical construction: the Muhammad Tower in the Alhambra fortress.
- 6 April 2024
- Published by Springer Nature in Engineering with Computers
- Vol. 40 (5) , 3157-3174
Open AccessTowards a comprehensive damage identification of structures through populations of competing models
Model-based damage identification for structural health monitoring (SHM) remains an open issue in the literature. Along with the computational challenges related to the modeling of full-scale structures, classical single-model structural identification (St-Id) approaches provide no means to guarantee the physical meaningfulness of the inverse calibration results. In this light, this work introduces a novel methodology for model-driven damage identification based on multi-class digital models formed by a population of competing structural models, each representing a different failure mechanism. The forward models are replaced by computationally efficient meta-models, and continuously calibrated using monitoring data. If an anomaly in the structural performance is detected, a model selection approach based on the Bayesian information criterion (BIC) is used to identify the most plausibly activated failure mechanism. The potential of the proposed approach is illustrated through two case studies, including a numerical planar truss and a real-world historical construction: the Muhammad Tower in the Alhambra fortress.
- Open Access
- 22 February 2024
- Published by Elsevier in Mechanical Systems and Signal Processing
- Vol. 211
AI-driven blind source separation for fast operational modal analysis of structures
- 22 February 2024
- Published by Elsevier in Mechanical Systems and Signal Processing
- Vol. 211
Open AccessAI-driven blind source separation for fast operational modal analysis of structures