Edgar Hernando Sepúlveda-Oviedo

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

This work is developed on the experimental platform provided by Quantom. This platform has known faulty panels and healthy panels. The Quantom company specializes in the monitoring of PV plants and the diagnosis of performance losses, helping its clients to make the right choice to optimize the production of their plants. The main challenge of this work is to carry out the diagnosis in situ and in real time.