Journal Articles
2026
- IJSSA bibliometric literature review of integrated data and model based diagnosis approaches for the industry 4.0Luis Enciso-Salas, Gustavo Pérez-Zuñiga, Javier Sotomayor-Moriano, and 6 more authorsInternational Journal of Systems Science, 2026
The increasing presence of Cyber-Physical Systems and the Internet of Things has accelerated the digital transformation of industrial environments, commonly known as Industry 4.0. In this context, Artificial Intelligence techniques are increasingly used to support automatic diagnostic tasks. This paper presents a systematic literature review of hybrid diagnostic systems that combine Model-Based Diagnosis (MBD), which relies on physical models to detect abnormal behaviour, and Data-Based Diagnosis (DBD), which uses machine learning to identify faults from data. The review has two objectives: (i) to examine how MBD and DBD methods have been combined to improve diagnostic performance, and (ii) to identify integration opportunities through existing machine learning frameworks to support reusable and adaptive solutions. A bibliometric analysis was conducted following a simplified PRISMA 2020 methodology. From over 1300 records, 75 articles were selected and analysed. Most hybrid systems adopt a serial architecture where DBD classifiers analyze residuals from MBD for fault detection and isolation. The most common applications are found in smart manufacturing and energy systems, and as for the most used machine learning techniques. Challenges remain regarding real-time scalability, interpretability, and standardisation. This review provides a structured foundation for designing explainable, efficient, and reusable diagnostic solutions for Industry 4.0.
@article{Enciso-Salas11062026, title = {A bibliometric literature review of integrated data and model based diagnosis approaches for the industry 4.0}, author = {Enciso-Salas, Luis and Pérez-Zuñiga, Gustavo and Sotomayor-Moriano, Javier and Chanthery, Elodie and Sepúlveda-Oviedo, Edgar Hernando and Subias, Audine and Travé-Massuyès, Louise and Garcia, Rodrigo and Aguilar, Jose}, journal = {International Journal of Systems Science}, publisher = {Taylor \& Francis}, volume = {57}, number = {8}, pages = {2415--2442}, year = {2026}, doi = {10.1080/00207721.2025.2550562}, url = {https://doi.org/10.1080/00207721.2025.2550562}, keywords = {fault-diagnosis,artificial-intelligence,industry-4-0,review,journal}, }
2025
- SEAFramework for effective PV system instrumentation focused on fault diagnosisEdgar Hernando Sepúlveda-Oviedo, and Bruno EstibalsSolar Energy Advances, 2025
A comprehensive framework for instrumentation in photovoltaic (PV) systems is proposed to enhance fault detection accuracy and diagnostic capability across varied PV applications. The framework is structured around four key components: (i) system design considerations, which include PV topology, scale, and sensor placement strategies to maximize detection sensitivity; (ii) data acquisition, detailing sensor selection, sampling rate optimization, and communication protocols adaptable to different configurations; (iii) data management and preprocessing, encompassing storage strategies, data quality control, and normalization pipelines; and (iv) a review of existing monitoring platforms, identifying their limitations for fault-specific diagnostics. Unlike existing standards such as International Electrotechnical Commission (IEC) 61724, which focus on performance monitoring, this framework is explicitly tailored to address diagnostic challenges, offering a fault-oriented perspective on instrumentation design. It provides structured guidelines for aligning spatial resolution, sensor types, and data granularity with the specific needs of fault localization and characterization. The framework also promotes scalable and cost-effective solutions by balancing the trade-offs between instrumentation complexity and diagnostic accuracy. By emphasizing dynamic sampling strategies and preprocessing workflows, the framework supports the development of more responsive and reliable monitoring architectures. This contribution aims to guide practitioners and researchers in improving the resilience, maintainability, and performance of PV systems through more intelligent and diagnosis-ready instrumentation infrastructures.
@article{SEPULVEDAOVIEDO2025100112, title = {Framework for effective PV system instrumentation focused on fault diagnosis}, author = {Sepúlveda-Oviedo, Edgar Hernando and Estibals, Bruno}, journal = {Solar Energy Advances}, volume = {5}, pages = {100112}, year = {2025}, doi = {https://doi.org/10.1016/j.seja.2025.100112}, url = {https://www.sciencedirect.com/science/article/pii/S2667113125000257}, issn = {2667-1131}, keywords = {fault-diagnosis,renewable-energy,photovoltaic-systems,instrumentation,journal}, } - Energy AIArtificial intelligence in photovoltaic fault diagnosis: A Natural Language-Based Topic-tSNE Fusion analysisEdgar Hernando Sepúlveda-Oviedo, Louise Travé-Massuyès, Audine Subias, and 2 more authorsEnergy and AI, 2025
Timely fault detection in photovoltaic systems is critical for ensuring energy efficiency, reliability, and cost-effectiveness. However, the nonlinear and weather-dependent behavior of photovoltaic systems poses challenges for accurate diagnosis. This study presents a large-scale review of 983 scientific publications on artificial intelligence-based photovoltaic fault detection, using a novel methodology called Topic-tSNE Fusion. This approach integrates topic modeling, dimensionality reduction, and expert analysis to extract and visualize dominant research themes. Four key machine learning paradigms are identified: supervised, unsupervised, semi-supervised, and reinforcement learning. Among them, supervised methods, particularly neural networks and support vector machines, are the most frequently applied, showing accuracies above 95% in controlled conditions. The analysis also reveals growing use of semi-supervised and hybrid approaches to overcome data scarcity. Commonly monitored variables include irradiance, voltage, and current, while the most studied faults are shading, open-circuit, and degradation. Several open-access datasets supporting fault diagnosis research are catalogued. Overall, the proposed method enables a more objective and scalable review process and uncovers emerging trends, such as the shift toward lightweight artificial intelligence for edge deployment and frugal diagnostic architectures. The methodology is scalable and adaptable to other domains facing similar challenges in knowledge synthesis and system monitoring.
@article{SEPULVEDAOVIEDO2025100558, title = {Artificial intelligence in photovoltaic fault diagnosis: A Natural Language-Based Topic-tSNE Fusion analysis}, author = {Sepúlveda-Oviedo, Edgar Hernando and Travé-Massuyès, Louise and Subias, Audine and Pavlov, Marko and Alonso, Corinne}, journal = {Energy and AI}, volume = {21}, pages = {100558}, year = {2025}, doi = {https://doi.org/10.1016/j.egyai.2025.100558}, url = {https://www.sciencedirect.com/science/article/pii/S2666546825000904}, issn = {2666-5468}, keywords = {fault-diagnosis,renewable-energy,photovoltaic-systems,artificial-intelligence,review,journal} } - ECM:XA review of operational factors affecting photovoltaic system performanceEdgar Hernando Sepúlveda-OviedoEnergy Conversion and Management: X, 2025
The reduction in manufacturing costs of photovoltaic (PV) systems has driven significant growth in the PV industry. This expansion has shifted the current challenge from constructing new PV systems to maximizing the performance and longevity of installed PV modules. PV performance is influenced by two major categories of factors: environmental and operational. While environmental factors, such as dust and temperature, have been extensively studied, operational factors — critical for optimizing system efficiency — have not received the same level of attention. This study analyzes 102 articles focusing on operational factors such as PV technology, tilt and orientation angles, surface properties, height, and component aging, while also examining their interaction with environmental factors, particularly dust. In addition, the study compiles a set of standardized metrics aimed at quantifying efficiency losses and enabling consistent comparisons across studies. Finally, this review outlines a roadmap identifying key research gaps and provides recommendations for improving PV system performance. This roadmap offers valuable insights for researchers, engineers, and policymakers to better understand and address the operational factors that influence the efficiency and lifespan of PV systems.
@article{SEPULVEDAOVIEDO2025100942, title = {A review of operational factors affecting photovoltaic system performance}, author = {Sepúlveda-Oviedo, Edgar Hernando}, journal = {Energy Conversion and Management: X}, volume = {26}, pages = {100942}, year = {2025}, doi = {https://doi.org/10.1016/j.ecmx.2025.100942}, url = {https://www.sciencedirect.com/science/article/pii/S2590174525000741}, issn = {2590-1745}, keywords = {renewable-energy,photovoltaic-systems,review,journal} } - ESRImpact of environmental factors on photovoltaic system performance degradationEdgar Hernando Sepúlveda-OviedoEnergy Strategy Reviews, 2025
The rapid expansion of photovoltaic (PV) systems underscores the need to understand environmental factors affecting their performance, degradation, and economic viability. This study comprehensively reviews 175 articles, classifying environmental factors such as atmospheric deposits (dust, sea salt, pollen), meteorological conditions (wind, temperature, humidity, rainfall, snowfall, hailstorms), shading, and solar irradiation variability. A novel multilevel classification of degradation modes is introduced, identifying failure mechanisms and their impacts. Key findings reveal performance losses of up to 60%–70% due to combined factors, while mitigation strategies, such as wind-induced cooling, can improve power output by 14.25%, and snow accumulation results in up to 12% annual energy losses. Performance metrics like Performance Loss Rate (PLR) and Degradation Rate (DR) are evaluated to quantify long-term impacts, with economic implications including potential revenue losses and maintenance costs. For instance, addressing dust accumulation in arid regions could save 20%–30% in annual cleaning costs while reducing energy inefficiencies. Recent advancements in AI-driven predictive maintenance are highlighted as pivotal for optimizing system performance and minimizing costs. This integrated analysis provides actionable insights for researchers, engineers, and policymakers, emphasizing the need for tailored strategies to enhance PV resilience and economic sustainability. By addressing the interaction of environmental factors and introducing standardized metrics, this study fills critical research gaps, offering a roadmap for improving PV system reliability, reducing operational costs, and supporting the transition to sustainable energy under diverse environmental conditions.
@article{SEPULVEDAOVIEDO2025101682, title = {Impact of environmental factors on photovoltaic system performance degradation}, author = {Sepúlveda-Oviedo, Edgar Hernando}, journal = {Energy Strategy Reviews}, volume = {59}, pages = {101682}, year = {2025}, doi = {https://doi.org/10.1016/j.esr.2025.101682}, url = {https://www.sciencedirect.com/science/article/pii/S2211467X25000458}, issn = {2211-467X}, keywords = {renewable-energy,photovoltaic-systems,review,journal} } - Energy Rep.Optimizing PV maintenance: Methods, cleaning frequency, and a selection protocolEdgar Hernando Sepúlveda-OviedoEnergy Reports, 2025
Dust accumulation significantly reduces the efficiency of Photovoltaic (PV) systems, with energy losses reaching up to 50% in arid and semi-arid regions. This study presents a comprehensive review of PV cleaning methods, analyzing both passive (natural mitigation, coated surfaces, architectural solutions) and active methods (manual cleaning, water-based systems, electromechanical techniques, robotic cleaning, and piezoelectric approaches). A systematic evaluation of their operational principles, effectiveness, and economic implications is conducted, considering environmental constraints and site-specific conditions. A key contribution of this study is the assessment of optimal cleaning frequency, identifying how climatic and geographical factors influence maintenance schedules. Additionally, a novel Strategic PV Cleaning Optimization Method (SPV-COM) is introduced, offering a structured, multi-criteria decision-making framework to compare and rank cleaning methods based on technical performance, economic feasibility, and long-term sustainability. This methodology integrates operational costs and maintenance requirements to ensure an adaptive selection process that aligns with real-world PV installations. The proposed framework is scalable and applicable to diverse PV cleaning technologies, supporting decision-making in both small-scale and large-scale installations. The findings highlight, for example, the economic trade-offs between water-intensive methods and emerging autonomous solutions, as well as the need for region-specific strategies. By addressing critical gaps in prior studies, this work provides a structured approach to optimizing PV maintenance, contributing to improved efficiency, cost reduction, and sustainable energy production.
@article{SEPULVEDAOVIEDO20251578, title = {Optimizing PV maintenance: Methods, cleaning frequency, and a selection protocol}, author = {Sepúlveda-Oviedo, Edgar Hernando}, journal = {Energy Reports}, volume = {14}, pages = {1578-1605}, year = {2025}, doi = {https://doi.org/10.1016/j.egyr.2025.07.008}, url = {https://www.sciencedirect.com/science/article/pii/S2352484725004238}, issn = {2352-4847}, keywords = {renewable-energy,photovoltaic-systems,predictive-maintenance,journal} } - HeliyonA formal statechart model of immediate neonatal adaptation guidelinesEdgar Hernando Sepúlveda-Oviedo, Leonardo Enrique Bermeo Clavijo, and Luis Carlos Méndez–CórdobaHeliyon, 2025
Research highlights the importance of applying physiological criteria for optimal umbilical cord clamping, underlining its lasting advantages. In response, the Division of Pediatrics, Perinatology, and Neonatology at the National University of Colombia has pioneered the Immediate Neonatal Adaptation Guideline, focusing on Physiologically-based Cord Clamping. This study has two main objectives: The first is to represent the medical guideline through a statechart model to enhance clarity and detail. Secondly, to evaluate the effectiveness of statechart models in depicting medical guidelines for educational and training purposes within a human-centric framework. In this study, a group of medical professionals and engineers designed the statechart model for the Immediate Neonatal Adaptation guideline through a progressive refinement method. The model comprises 20 states, 38 events, and 4 superstates, offering clear visual language for its evaluation by an interdisciplinary panel of engineers and health professionals. This visual representation facilitates a more explicit identification of patient states, criteria, and clinical indicators involved in the procedure. Feedback indicates general satisfaction with the Versatility, Usability, Scalability and Moderate visual complexity of the model.
@article{SEPULVEDAOVIEDO2025e42784, title = {A formal statechart model of immediate neonatal adaptation guidelines}, author = {Sepúlveda-Oviedo, Edgar Hernando and {Bermeo Clavijo}, Leonardo Enrique and {Carlos Méndez–Córdoba}, Luis}, journal = {Heliyon}, volume = {11}, number = {4}, pages = {e42784}, year = {2025}, doi = {https://doi.org/10.1016/j.heliyon.2025.e42784}, url = {https://www.sciencedirect.com/science/article/pii/S240584402501165X}, issn = {2405-8440}, keywords = {biomedical,biomedical-modeling,journal} }
2024
- EAAIAn ensemble learning framework for snail trail fault detection and diagnosis in photovoltaic modulesEdgar Hernando Sepúlveda-Oviedo, Louise Travé-Massuyès, Audine Subias, and 2 more authorsEngineering Applications of Artificial Intelligence, 2024
This research proposes a method for detecting subtle faults named snail trails for their visual similarity with the trail of a snail in photovoltaic modules. Snail trails do not significantly reduce panel performance but they are the main cause of serious panel deterioration such as microcracks and delamination and can go so far as to set the panel on fire. To detect these faults, this research uses an ensemble learning framework, named ensemble learning for diagnosis, which combines several complementary learning algorithms, namely Support Vector Machines, K-Nearest Neighbors, and Decision Trees. A set of features is obtained by extracting the time–frequency characteristics and statistics from the photovoltaic current signal of the photovoltaic panel. This is followed by a feature selection and dimensionality reduction step that delivers the input to the learning algorithms. The approach presented in this study is experimentally validated, independently for the 4 seasons of the year, with data from a real photovoltaic string of 16 panels. The results demonstrate that the proposed approach can efficiently classify healthy panels and panels with snail trails efficiently. Interestingly, the method only requires the electrical current signal, measured on panels with data acquisition systems that are standard in the photovoltaic industry. The genericity of the approach makes it a good candidate for detecting other photovoltaic faults and for solving diagnosis problems in other domains.
@article{SEPULVEDAOVIEDO2024109068, title = {An ensemble learning framework for snail trail fault detection and diagnosis in photovoltaic modules}, author = {Sepúlveda-Oviedo, Edgar Hernando and Travé-Massuyès, Louise and Subias, Audine and Pavlov, Marko and Alonso, Corinne}, journal = {Engineering Applications of Artificial Intelligence}, volume = {137}, pages = {109068}, year = {2024}, doi = {https://doi.org/10.1016/j.engappai.2024.109068}, issn = {0952-1976}, keywords = {fault-diagnosis,renewable-energy,photovoltaic-systems,journal} } - BBEEffect of timing of umbilical cord clamping and birth on fetal to neonatal transition: OpenModelica-based virtual simulator-based approachEdgar Hernando Sepúlveda-Oviedo, Leonardo Enrique Bermeo Clavijo, and Luis Carlos Méndez-CórdobaBiocybernetics and Biomedical Engineering, 2024
The transition from fetal to newborn condition involves complex physiological adaptations for extrauterine life. A crucial event in this process is the clamping of the umbilical cord, which can be categorized as immediate or delayed. The type of clamping significantly influences the hemodynamics of the newborn. In this study, we developed a simulator based on existing cardiovascular models to better understand this practice. The simulator covers the period from late gestation to 24 h after birth and faithfully reproduces flow patterns observed in real-life situations (as evaluated by clinical specialists), considering factors such as the timing of cord clamping and the altitude of the birth location. It also reproduces blood pressure values reported in clinical data. Under similar conditions, the simulation results indicate that delayed cord clamping leads to increased oxygen concentration and improved blood volume compared to immediate cord clamping. Delayed cord clamping also had a positive impact on sustained placental respiration. Furthermore, this study provides further evidence that umbilical cord clamping should be based on physiological criteria rather than predefined time intervals.
@article{SEPULVEDAOVIEDO2024716, title = {Effect of timing of umbilical cord clamping and birth on fetal to neonatal transition: OpenModelica-based virtual simulator-based approach}, author = {Sepúlveda-Oviedo, Edgar Hernando and {Bermeo Clavijo}, Leonardo Enrique and Méndez-Córdoba, Luis Carlos}, journal = {Biocybernetics and Biomedical Engineering}, volume = {44}, number = {3}, pages = {716-730}, year = {2024}, doi = {https://doi.org/10.1016/j.bbe.2024.08.008}, issn = {0208-5216}, keywords = {biomedical,biomedical-modeling,journal} }
2023
- HeliyonFault diagnosis of photovoltaic systems using artificial intelligence: A bibliometric approachEdgar Hernando Sepúlveda-Oviedo, Louise Travé-Massuyès, Audine Subias, and 2 more authorsHeliyon, 2023
Conventional fault detection methods in photovoltaic systems face limitations when dealing with emerging monitoring systems that produce vast amounts of high-dimensional data across various domains. Accordingly, great interest appears within the international scientific community for the application of artificial intelligence methods, which are seen as a highly promising solution for effectively managing large datasets for detecting faults. In this review, more than 620 papers published since 2010 on artificial intelligence methods for detecting faults in photovoltaic systems are analyzed. To extract major research trends, in particular to detect most promising algorithms and approaches overcoming excessive time calculations, a conventional bibliographic survey would have been extremely difficult to complete. That is why this study proposes to carry out a review with an innovative approach based on a statistical method named Bibliometric and a Expert qualitative content analysis. This methodology consists of three stages. First, a collection of data from databases is carried out with all precautions to achieve a large, robust, high-quality database. Second, multiple bibliometric indicators are chosen based on the objectives to be achieved and analyzed to assess their real impact, such as the quantity and nature of publications, collaborative connections among organizations, researchers, and countries or most cited articles. Finally, the Expert qualitative content analysis carried out by experts identifies the current and emerging research topics that have the greatest impact on fault detection in photovoltaic systems using artificial intelligence.
@article{SEPULVEDAOVIEDO2023e21491, title = {Fault diagnosis of photovoltaic systems using artificial intelligence: A bibliometric approach}, author = {Sepúlveda-Oviedo, Edgar Hernando and Travé-Massuyès, Louise and Subias, Audine and Pavlov, Marko and Alonso, Corinne}, journal = {Heliyon}, volume = {9}, number = {11}, pages = {e21491}, year = {2023}, doi = {https://doi.org/10.1016/j.heliyon.2023.e21491}, issn = {2405-8440}, keywords = {fault-diagnosis,renewable-energy,photovoltaic-systems,artificial-intelligence,review,journal} }
2022
- AEIFeature extraction and health status prediction in PV systemsEdgar Hernando Sepúlveda-Oviedo, Louise Travé-Massuyès, Audine Subias, and 2 more authorsAdvanced Engineering Informatics, 2022
Diagnosis aims at predicting the health status of components and systems. In photovoltaic systems, it is vital to guarantee energy production and extend the useful life of photovoltaic power plants. Multiple prediction and classification algorithms have been proposed for this purpose in the literature. The accuracy of these algorithms depends directly on the quality of the data and the features with which they are tuned or trained. In this paper, an innovative approach for predicting the health status of photovoltaic systems is proposed, which includes a feature selection stage. This approach first discriminates severely affected photovoltaic panels using basic electrical features. In a second step, it discriminates the other faulty panels using more elaborated time–frequency features and selecting the most relevant features through correlation and variance analysis. Finally, the approach predicts the health status of photovoltaic panels using a nonlinear regression method named partial least squares. This later is then combined with linear discriminant analysis and compared. The approach is validated with real current data from a photovoltaic plant composed of twelve photovoltaic panels with power between 205 and 240 Wp in three health states, namely broken glass, healthy, and big snail trails. The results obtained show that the proposed approach efficiently predicts the three health states. It determines the level of degradation of the panels, which indicates priorities to corrective and predictive maintenance actions. Furthermore, it is cost-effective since it uses only electrical measurements that are already available in standard photovoltaic data acquisition systems. Above all, the approach is generic and it can be easily extrapolated to other diagnosis problems in other domains.
@article{SEPULVEDAOVIEDO2022101696, title = {Feature extraction and health status prediction in PV systems}, author = {Sepúlveda-Oviedo, Edgar Hernando and Travé-Massuyès, Louise and Subias, Audine and Alonso, Corinne and Pavlov, Marko}, journal = {Advanced Engineering Informatics}, volume = {53}, pages = {101696}, year = {2022}, doi = {https://doi.org/10.1016/j.aei.2022.101696}, issn = {1474-0346}, keywords = {fault-diagnosis,renewable-energy,photovoltaic-systems,predictive-maintenance,journal} } - JMETOpenModelica-based virtual simulator for the cardiovascular and respiratory physiology of a neonateEdgar Hernando Sepúlveda-Oviedo, Leonardo Enrique Bermeo Clavijo, and Luis Carlos Méndez CórdobaJournal of Medical Engineering & Technology, 2022PMID: 35172686
There is a lack of medical simulation tools that can be understood and used, at the same time, by researchers, teachers, clinicians and students. Regarding this issue, in this work we report a virtual simulator (developed in OpenModelica) that allow to experiment with the fundamental variables of the cardiovascular and respiratory system of a neonate. We extended a long-tested lumped parameter model that represents the cardiovascular and respiratory physiology of a neonate. From this model, we implemented a physiological simulator using Modelica. The fidelity and versatility of the reported simulator were evaluated by simulating seven physiological scenarios: two of them representing a healthy infant (newborn and 6-months old) and five representing newborns affected by different heart diseases. The simulator properly and consistently represented the quantitative and qualitative behaviour of the seven physiological scenarios when compared with existing clinical data. Results allow us to consider the simulator reported here as a reliable tool for researching, training and learning. The advanced modelling features of Modelica and the friendly graphical user interface of OpenModelica make the simulator suitable to be used by a broad community of users. Furthermore, it can be easily extended to simulate many clinical scenarios.
@article{SEPULVEDAOVIEDO2022179, title = {OpenModelica-based virtual simulator for the cardiovascular and respiratory physiology of a neonate}, author = {Sepúlveda-Oviedo, Edgar Hernando and Clavijo, Leonardo Enrique Bermeo and Córdoba, Luis Carlos Méndez}, journal = {Journal of Medical Engineering \& Technology}, publisher = {Taylor \& Francis}, volume = {46}, number = {3}, pages = {179--197}, year = {2022}, doi = {10.1080/03091902.2022.2026500}, url = {https://doi.org/10.1080/03091902.2022.2026500}, note = {PMID: 35172686}, keywords = {biomedical,biomedical-modeling,journal} }
Patents
2023
- PatentMéthode de détection de défauts dans une installation photovoltaïqueEdgar Hernando Sepúlveda-Oviedo, Louise Travé-Massuyès, Audine Subias, and 2 more authorsSep 2023
This patent proposes a method for the automated detection of faults in photovoltaic installations. The invention aims to identify anomalies and performance-degrading conditions affecting solar energy systems, enabling early fault diagnosis, improved operational reliability, and more efficient maintenance strategies. By facilitating the continuous monitoring of photovoltaic assets, the proposed approach contributes to enhancing energy production, reducing downtime, and supporting the safe operation of solar power plants.
@patent{sepulvedaoviedo:hal-04773333, title = {{Méthode de détection de défauts dans une installation photovoltaïque}}, author = {Sepúlveda-Oviedo, Edgar Hernando and Travé-Massuyès, Louise and Subias, Audine and Pavlov, Marko and Alonso, Corinne}, number = {FR2310256}, year = {2023}, month = sep, address = {France}, doi = {https://hal.science/hal-04773333}, hal_id = {hal-04773333}, hal_version = {v1}, keywords = {fault-diagnosis,renewable-energy,patent} }
Conference Papers and Presentations
2025
- SGE 2025Suivi temps réel du SoH de batteries lithium-ionBruno Jammes, Edgar Hernando Sepúlveda-Oviedo, and Corinne AlonsoIn Symposium de Génie Électrique SGE 2025, Jul 2025
Real-time monitoring of battery State of Health (SoH) remains a major challenge, particularly in microgrids where operational constraints limit the applicability of conventional estimation methods. Within the framework of the 4BLife project, we propose an innovative approach based on the analysis of a discharge pulse applied at the end of the charging phase. The parameters of the equivalent electrical model describing the battery terminal voltage response during this current pulse are subsequently used to estimate the SoH. Based on the experimental data collected to date, the preliminary results demonstrate the relevance of the proposed methodology. After training the estimator using parameters extracted from two batteries exhibiting approximately 85% capacity degradation, we successfully predicted the degradation of two additional batteries cycled down to around 90% SoH. The proposed approach achieved a mean absolute error of approximately 1% in the worst-case scenario, while maintaining a high level of explainability, with an explainability score close to 0.9.
@inproceedings{jammes:hal-05147645, title = {{Suivi temps réel du SoH de batteries lithium-ion}}, author = {Jammes, Bruno and Sepúlveda-Oviedo, Edgar Hernando and Alonso, Corinne}, booktitle = {{Symposium de Génie Électrique SGE 2025}}, year = {2025}, month = jul, address = {Toulouse, France}, doi = {https://doi.org/10.1016/j.heliyon.2025.e42784}, keywords = {battery-systems,renewable-energy,conference}, } - SGE 2025Le projet 4BLife : intégrer le vieillissement des batteries dans le dimensionnement et la gestion des micro-réseauxSerge Pelissier, Eduardo Redondo-Iglesias, Bilal Kabalan, and 10 more authorsIn Symposium de Génie Électrique SGE 2025, Jul 2025
This paper presents the outcomes of the 4BLife project, whose objective is to integrate battery aging laws into the design and energy management of lithium-ion battery storage systems. Achieving this goal requires the development of aging models as well as performance characterization and State of Health (SoH) monitoring tools. Both laboratory and field data are exploited to identify aging models and validate the proposed SoH monitoring methodologies. Two battery technologies, namely Lithium Iron Phosphate (LFP) and Nickel Manganese Cobalt (NMC), suitable for both mobile and stationary applications, are investigated. The integration of battery aging models into the sizing and management of stationary energy storage systems is addressed through simulation studies. The validation of the impact of real operating conditions on battery degradation is currently under investigation.
@inproceedings{pelissier:hal-05148801, title = {{Le projet 4BLife : intégrer le vieillissement des batteries dans le dimensionnement et la gestion des micro-réseaux}}, author = {Pelissier, Serge and Redondo-Iglesias, Eduardo and Kabalan, Bilal and von Hohendorff Seger, Pedro and Halouani, Ayda and Jammes, Bruno and Sepúlveda-Oviedo, Edgar Hernando and Alonso, Corinne and Locment, Fabrice and Celik, Berk and Dulout, Jérémy and Lami, Youness and Birou, Camille}, booktitle = {{Symposium de Génie Électrique SGE 2025}}, year = {2025}, month = jul, address = {Toulouse, France}, doi = {https://hal.science/hal-05148801}, keywords = {battery-systems,renewable-energy,conference} }
2023
- CIMM 2023DTW K-Means clustering for fault detection in photovoltaic modulesEdgar Hernando Sepúlveda-Oviedo, Louise Travé-Massuyès, Audine Subias, and 2 more authorsIn XI Congreso Internacional de Ingeniería Mecánica, Mecatrónica y Automatización 2023, Apr 2023Oral presentation
The increase in the use of photovoltaic (PV) energy in the world has shown that the useful life and maintenance of a PV plant directly depend on the ability to quickly detect severe faults on a PV plant. To solve this problem of detection, data based approaches have been proposed in the literature. However, these previous solutions consider only specific behavior of one or few faults. Most of these approaches can be qualified as supervised, requiring an enormous labelling effort (fault types clearly identified in each technology). In addition, most of them are validated in PV cells or one PV module. That is hardly applicable in large-scale PV plants considering their complexity. Alternatively, some unsupervised well-known approaches based on data try to detect anomalies but are not able to identify precisely the type of fault. The most performant of these methods do manage to efficiently group healthy panels and separate them from faulty panels. In that way, this article presents an unsupervised approach called DTW K-means. This approach takes advantages of both the dynamic time warping (DWT) metric and the Kmeans clustering algorithm as a data-driven approach. The results of this mixed method in a PV string are compared to diagnostic labels established by visual inspection of the panels.
@inproceedings{sepulvedaoviedo:hal-04125983, title = {{DTW K-Means clustering for fault detection in photovoltaic modules}}, author = {Sepúlveda-Oviedo, Edgar Hernando and Trav{\'e}-Massuy{\`e}s, Louise and Subias, Audine and Pavlov, Marko and Alonso, Corinne}, booktitle = {{XI Congreso Internacional de Ingenier{\'i}a Mec{\'a}nica, Mecatr{\'o}nica y Automatizaci{\'o}n 2023}}, year = {2023}, month = apr, address = {Carthag{\`e}ne, Colombia}, doi = {https://laas.hal.science/hal-04125983}, note = {Oral presentation}, hal_id = {hal-04125983}, hal_version = {v1}, keywords = {renewable-energy,fault-diagnosis,conference} } - CIMM 2023Detection and classification of faults aimed at preventive maintenance of PV systems.Edgar Hernando Sepúlveda-Oviedo, Louise Travé-Massuyès, Audine Subias, and 2 more authorsIn XI Congreso Internacional de Ingeniería Mecánica, Mecatrónica y Automatización 2023, Apr 2023Oral presentation
Diagnosis in PV systems aims to detect, locate and identify faults. Diagnosing these faults is vital to guarantee energy production and extend the useful life of PV power plants. In the literature, multiple machine learning approaches have been proposed for this purpose. However, few of these works have paid special attention to the detection of fine faults and the specialized process of extraction and selection of features for their classification. A fine fault is one whose characteristic signature is difficult to distinguish to that of a healthy panel. As a contribution to the detection of fine faults (especially of the snail trail type), this article proposes an innovative approach based on the Random Forest (RF) algorithm. This approach uses a complex feature extraction and selection method that improves the computational time of fault classification while maintaining high accuracy.
@inproceedings{sepulvedaoviedo:hal-04125988, title = {{Detection and classification of faults aimed at preventive maintenance of PV systems.}}, author = {Sepúlveda-Oviedo, Edgar Hernando and Trav{\'e}-Massuy{\`e}s, Louise and Subias, Audine and Pavlov, Marko and Alonso, Corinne}, booktitle = {{XI Congreso Internacional de Ingenier{\'i}a Mec{\'a}nica, Mecatr{\'o}nica y Automatizaci{\'o}n 2023}}, year = {2023}, month = apr, address = {Carthag{\`e}ne, Colombia}, organization = {{Universidad Nacional de Colombia}}, doi = {https://laas.hal.science/hal-04125988}, note = {Oral presentation}, hal_id = {hal-04125988}, hal_version = {v1}, keywords = {renewable-energy,fault-diagnosis,conference} }
2022
- GEETS 2022Extraction de signatures et prédiction de l’état de santé des centrales photovoltaïquesEdgar Hernando Sepúlveda-OviedoIn Congrès annuel de l’Ecole Doctorale GEETS 2022, Apr 2022Oral presentation
A new artificial intelligence approach and a data acquisition platform oriented towards fault detection in PV systems are proposed. The condition of the panels is distinguished using hierarchical clustering, time-frequency analysis, and statistical dimensionality reduction and feature extraction. Fault detection is performed using Partial Least Squares (PLS) and validated with a proposed PLS-Linear Discriminant Analysis (PLS-LDA). The data acquisition platform can capture 16 signals at millisecond speed. The results of this study surpass those obtained with conventional methods.
@inproceedings{sepulvedaoviedo:hal-04290156, title = {{Extraction de signatures et pr{\'e}diction de l'{\'e}tat de sant{\'e} des centrales photovolta{\"i}ques}}, author = {Sepúlveda-Oviedo, Edgar Hernando}, booktitle = {{Congr{\`e}s annuel de l'Ecole Doctorale GEETS 2022}}, year = {2022}, month = apr, address = {Toulouse, France}, organization = {{Ecole Doctorale G{\'e}nie Electrique, Electronique, T{\'e}l{\'e}communications et Sant{\'e}}}, doi = {https://hal.science/hal-04290156}, note = {Oral presentation}, hal_id = {hal-04290156}, hal_version = {v1}, keywords = {renewable-energy,conference} }
2021
- CIMM 2021Hierarchical clustering and dynamic time warping for fault detection in photovoltaic systemsEdgar Hernando Sepúlveda-Oviedo, Louise Travé-Massuyès, Audine Subias, and 2 more authorsIn X Congreso Internacional CIMM Ingeniería Mecánica, Mecatrónica y Automatización, May 2021Oral presentation
Safety and energy efficiency of PV plants can be affected by failures in any component of the plant if the degradation is not detected and corrected quickly. This is why fault detection and diagnosis (FDD) methods have a critical role to play in this application domain. FDD methods are classified into two large groups: i) based on models; and ii) based on data. In the first group, a high level of expert knowledge is necessary. In the second, a large volume of data is required to train the machine learning algorithms. This paper proposes to experiment Dynamic Time Warping (DWT) followed by Hierarchical Clustering (HC) as a data-driven approach. The results of this method are compared with the diagnosis labels assessed by visual inspection of the panels.
@inproceedings{sepulvedaoviedo:hal-03355362, title = {{Hierarchical clustering and dynamic time warping for fault detection in photovoltaic systems}}, author = {Sepúlveda-Oviedo, Edgar Hernando and Trav{\'e}-Massuy{\`e}s, Louise and Subias, Audine and Alonso, Corinne and Pavlov, Marko}, booktitle = {{X Congreso Internacional CIMM Ingenier{\'i}a Mec{\'a}nica, Mecatr{\'o}nica y Automatizaci{\'o}n}}, year = {2021}, month = may, address = {Bogot{\'a} (virtual), Colombia}, doi = {https://hal.science/hal-03355362}, note = {Oral presentation}, hal_id = {hal-03355362}, hal_version = {v1}, keywords = {renewable-energy,fault-diagnosis,conference} }
2018
- CBA 2018Modelo del procedimiento de adaptación de neonatal inmediata: una aplicación de sistemas de eventos discretos en neonatologíaEdgar Hernando Sepúlveda-Oviedo, Leonardo Enrique Bermeo Clavijo, and Luis Carlos Méndez CórdobaIn XXII Congresso Brasileiro de Automática, Sep 2018
Modeling and simulation are of increasing importance in medical education and research. Medical guidelines and protocols are systematically and consensually developed statements designed to assist healthcare professionals in determining how to proceed in specific circumstances. Abstractly, a medical guideline or protocol can be represented as a discrete event model, making this a promising application field for such models. In this article, we present a finite automaton model for the Immediate Neonatal Adaptation Procedure developed by the School of Perinatology and Neonatology at the National University of Colombia. The model developed in this work enhances the original flowchart of the procedure in terms of comprehension, consistency, and level of detail.
@inproceedings{sepulvedaoviedo:hal-04290210, title = {{Modelo del procedimiento de adaptaci{\'o}n de neonatal inmediata: una aplicaci{\'o}n de sistemas de eventos discretos en neonatolog{\'i}a}}, author = {Sepúlveda-Oviedo, Edgar Hernando and Bermeo Clavijo, Leonardo Enrique and M{\'e}ndez C{\'o}rdoba, Luis Carlos}, booktitle = {{XXII Congresso Brasileiro de Autom{\'a}tica}}, year = {2018}, month = sep, address = {Jo{\~a}o Pessoa, Brazil, Brazil}, doi = {10.20906/CBA2022/500}, url = {https://hal.science/hal-04290210}, hal_id = {hal-04290210}, hal_version = {v1}, keywords = {biomedical,biomedical-modeling,conference} } - COBENGE 2018Desarrollo de una herramienta de simulación cardiovascular neonatal para la enseñanza y la investigaciónEdgar Hernando Sepúlveda-Oviedo, Leonardo Enrique Bermeo Clavijo, and Luis Carlos Méndez CórdobaIn XLVI Congresso Brasileiro de Educação em Engenharia (COBENGE) e no 1º Simpósio Internacional de Educação em Engenharia da ABENGE, Sep 2018Oral presentation
The work presented in this article is framed in the field of medical simulator development based on models. The purpose of this work is to accelerate interdisciplinary research and enhance the skills, dexterity, and expertise of healthcare professionals without invasive practices on the patient. To this end, we propose an educational simulator of neonatal cardiovascular physiology, implemented in Modelica based on the analogy with a hydraulic model. This tool allows for the simulation of the normal state of a newborn, cardiac pathologies such as coarctation of the aorta and transposition of the great arteries. It also enables visualization of physiological variables like pressure, volume, blood flow, elastance, vascular resistance, and relationships such as ventricular pressure-volume to assess the cardiac cycle. This work is a first step in the development of simulators of complete neonatal physiology that allow evaluating the patient’s evolution with the application of a treatment. The development of these tools facilitates the reduction of human error and allows for testing without consequences for patients. Keywords: Simulation, Neonate, Cardiovascular Physiology, Cardiac Pathology, Teaching in Medicine and Biomedicine.
@inproceedings{sepulvedaoviedo:hal-04290220, title = {{Desarrollo de una herramienta de simulaci{\'o}n cardiovascular neonatal para la ense{\~n}anza y la investigaci{\'o}n}}, author = {Sepúlveda-Oviedo, Edgar Hernando and Bermeo Clavijo, Leonardo Enrique and M{\'e}ndez C{\'o}rdoba, Luis Carlos}, booktitle = {{XLVI Congresso Brasileiro de Educa{\c c}{\~a}o em Engenharia (COBENGE) e no 1º Simp{\'o}sio Internacional de Educa{\c c}{\~a}o em Engenharia da ABENGE}}, year = {2018}, month = sep, address = {Salvador (Bahia), Brazil}, doi = {https://hal.science/hal-04290220}, note = {Oral presentation}, hal_id = {hal-04290220}, hal_version = {v1}, keywords = {biomedical,biomedical-modeling,conference} }
2015
- CIIMA 2015Mecanismo Planar 2R con articulaciones complacientes para simulación de caminata bipedaJuan F López-Prieto, Jhonatan D Piza, Edgar Hernando Sepúlveda-Oviedo, and 2 more authorsIn Memorias, IV Congreso Internacional de Ingeniería Mecatrónica y Automatización - CIIMA 2015, Sep 2015
In general, applications related to research on bipedal walking have been oriented towards simulating the biomechanics of human movement. The purpose of this work was the research, design, and implementation of a model that meets the necessary characteristics for control, joint stiffness, and energy management in 2R mechanisms for human walking. The prototype will be used to investigate force and torque control for under-actuated mechanisms and compliant joint control. The project focused primarily on the design of Rotational Series Elastic Actuators (RSEA) for each joint. The RSEAs enable energy reduction during operation and smooth movement, in addition to accurate torque measurement through spring angular deflection. The system can restrict movement to simulate the angles used by a human leg during walking and can also generate movement routines for evaluating the mechanism itself and the trajectories required in research. For this, it is important to consider that variables like force, torque, and speed were implemented at a 1:1.5 scale relative to the real magnitudes of a human leg and at a 1:12 scale relative to the mass.
@inproceedings{lopez2015mecanismo, title = {Mecanismo Planar 2R con articulaciones complacientes para simulaci{\'o}n de caminata bipeda}, author = {L{\'o}pez-Prieto, Juan F and Piza, Jhonatan D and Sepúlveda-Oviedo, Edgar Hernando and Sora, Vanessa A and Ram{\'\i}rez, Ricardo E}, booktitle = {Memorias, IV Congreso Internacional de Ingeniería Mecatrónica y Automatización - CIIMA 2015}, publisher = {Universidad EIA}, pages = {1--12}, year = {2015}, doi = {https://revistabme.eia.edu.co/index.php/mem/article/view/813}, keywords = {conference,mechatronics} }
Theses
2023
- PhD ThesisDetection and diagnosis of faults and performance losses in high-power photovoltaic power plantsEdgar Hernando Sepúlveda-OviedoFeb 2023Prix de thèse de l’école doctorale GEETS, 2024. Best Oral Presentation Award at the GEETS Doctoral School Conference, 2022.
The increase in the use of photovoltaic energy in the world has shown that the life and maintenance of a PV plant are strongly linked to its ability to detect failures that may occur over time. Therefore, the more a defect is detected, to carry out corrective or even preventive maintenance of the defective part, the more optimal the production of the photovoltaic system is maintained, thus reducing the cost of maintenance. Fault diagnosis requires strict control by a data acquisition system that constitutes a substantial database. This so-called "data"-driven approach must be associated with a feature extraction system to constitute a system for diagnosing performance losses or even failures. Currently, the development of this type of platform is limited by the high complexity of building an acquisition system aimed at diagnosing faults that can vary depending on weather conditions, the performance of inverters or optimizers, among others. The objective of this thesis is the development of fault diagnosis methods for photovoltaic installations embedded in a physical system for data acquisition, treatment and detection of faults in real time, respecting industrial limitations and taking into account the cost/benefit compromise in productivity or uptime. Beyond the early detection of the failure, an attempt will be made to identify the type of failure to establish a classification of the latter based on their impact in terms of damage and repair cost. To address the issues discussed above and as a contribution to effective fault diagnosis in photovoltaic systems, this paper proposes a new approach for feature extraction and health state prediction in photovoltaic systems. Our approach is based on five stages: i) data acquisition and preprocessing; ii) dynamic time warp hierarchical clustering; iii) feature extraction; iv) selection of characteristics and v) prediction of health status. The approach is applied on real data based on a commercial data acquisition platform and on data acquisition and its specific treatment with a high sampling frequency obtained by a specific platform designed and validated during this thesis. The experimental tests have been made in several real PV power plants.
@phdthesis{sepulvedaoviedo:tel-04888632, title = {{Detection and diagnosis of faults and performance losses in high-power photovoltaic power plants}}, author = {Sepúlveda-Oviedo, Edgar Hernando}, school = {{Université Paul Sabatier - Toulouse III}}, year = {2023}, month = feb, number = {2023TOU30019}, doi = {10.70675/f41da6adz254az4879z8899ze166892a91b5}, type = {Theses}, url = {https://laas.hal.science/tel-04888632}, note = {Prix de thèse de l'école doctorale GEETS, 2024. Best Oral Presentation Award at the GEETS Doctoral School Conference, 2022.}, hal_id = {tel-04888632}, hal_version = {v2}, keywords = {fault-diagnosis,renewable-energy,photovoltaic-systems,artificial-intelligence,thesis} }
2020
- Master’s thesisEstudio de la práctica del pinzamiento del cordón umbilical usando análisis computacional de la información bibliográfica, modelos de eventos discretos y modelos dinámicos.Edgar Hernando Sepúlveda-OviedoUniversité Nationale de Colombie, Mar 2020Master’s thesis
Science, technology, and innovation are increasingly becoming indispensable tools for scientific advancement in medicine, enabling the development of new methodologies for medical education and training, such as simulation-based medical education and competency-based medical education. Motivated by this, we proposed and developed the following three methodologies as teaching strategies for research, training, and education in medicine: (i) computational analysis of large volumes of information (MEDICAL BIG DATA); (ii) modeling of clinical protocols as discrete event systems; and (iii) designing medical simulators based on physiological models. Using computational analysis of information, we processed available data on umbilical cord clamping. This allowed us to obtain relevant information regarding terminology and time ranges in the classification of cord clamping, associated pathologies, and promising new lines of research. This methodology enabled us to: (i) propose a standardization of terms related to conventional clamping types and the timing that defines them; (ii) globally detect pathological terms associated with the optimal timing of umbilical cord clamping; and (iii) identify the emerging trend of physiology-based cord clamping (PBCC) and the appearance of interesting research terms such as gestational age, altitude, or twin status. Using the methodology of representing clinical protocols as Discrete Event Systems (DES), we developed a model based on finite automata formalism with a visual extension of Statecharts. This model represents the immediate neonatal adaptation developed by the School of Perinatology and Neonatology at the National University of Colombia. This versatile, user-friendly, scalable, and visually moderately complex tool supports teaching and training in neonatology. The proposed model expands the original flowchart of the procedure in terms of comprehension, consistency, and detail level. This development allows for systematic exploration of different clinical scenarios, strengthening students’ learning from the beginning of their professional careers and improving their understanding of concepts. Finally, we designed two simulators based on physiological mathematical models. The first simulator approximately represents the normal physiological behavior of a neonate and a child, as well as simulating heart conditions such as Tetralogy of Fallot, transposition of the great arteries, aortic coarctation, patent ductus arteriosus, non-congenital aortic stenosis, and others. The second simulator evaluates physiological changes occurring at birth, due to umbilical cord clamping, and as a result of altitude at birth. This simulator models ductus arteriosus closure, elimination of placental circulation, increased systemic vascular pressure and resistance, reduced pulmonary vascular pressure and resistance, and the transition of respiratory function from the placenta to the lungs, among others. These simulators were implemented in the specialized language Modelica with an intuitive graphical interface that allows healthcare professionals to use it without prior knowledge of modeling or programming. The goal of this work is to accelerate interdisciplinary research and enhance healthcare personnel’s skills, abilities, and expertise without invasive practices on patients. Additionally, it represents a significant step forward in developing simulation tools for researching the interaction between healthcare professionals and patients.
@mastersthesis{sepulvedaoviedo:tel-04427662, title = {{Estudio de la pr{\'a}ctica del pinzamiento del cord{\'o}n umbilical usando an{\'a}lisis computacional de la informaci{\'o}n bibliogr{\'a}fica, modelos de eventos discretos y modelos din{\'a}micos.}}, author = {Sepúlveda-Oviedo, Edgar Hernando}, school = {{Universit{\'e} Nationale de Colombie}}, year = {2020}, month = mar, doi = {https://hal.science/tel-04427662}, note = {Master's thesis}, hal_id = {tel-04427662}, hal_version = {v1}, keywords = {biomedical,biomedical-modeling,thesis} }
Software and Data
2021
- SoftwarePatientEvoPhysio SimulatorEdgar Hernando Sepúlveda-Oviedo, Luis Carlos Méndez Córdoba, and Leonardo Enrique Bermeo ClavijoJan 2021Software
PatientEvoPhysio is an open-source Modelica library developed for the simulation and analysis of human cardiovascular and respiratory physiology across different stages of life, including fetal, neonatal, pediatric, and adult populations. The library provides a modular framework for studying physiological evolution under normal conditions, pathological scenarios, and clinical interventions. Built upon a component-based architecture, the library integrates mathematical models of blood circulation, cardiac mechanics, oxygen transport, pulmonary and placental respiration, vascular resistance, and congenital heart diseases. It includes validated physiological scenarios such as neonatal cardiovascular adaptation, fetal-to-neonatal transition, aortic stenosis, coarctation of the aorta, patent ductus arteriosus, Tetralogy of Fallot, and transposition of the great arteries. Developed in Modelica and compatible with Physiolibrary, PatientEvoPhysio serves as a research and educational platform for physiological simulation, medical training, and the investigation of cardiovascular and respiratory disorders. The library has supported several scientific publications related to neonatal physiology, fetal circulation, and the impact of umbilical cord clamping on neonatal adaptation.
@softwareversion{sepulvedaoviedo:hal-04423817v1, title = {{PatientEvoPhysio Simulator}}, author = {Sepúlveda-Oviedo, Edgar Hernando and M{\'e}ndez C{\'o}rdoba, Luis Carlos and Bermeo Clavijo, Leonardo Enrique}, publisher = {{Edgar Hernando Sep{\'u}lveda-Oviedo}}, year = {2021}, month = jan, doi = {10.5281/zenodo.10054995}, zenodo = {10054995}, url = {https://laas.hal.science/hal-04423817}, note = {Software}, version = {1.0}, repository = {https://github.com/ehsepulvedao/PatientEvoPhysio}, license = {CC BY NC}, hal_id = {hal-04423817}, hal_version = {v1}, keywords = {software}, }