Maestría en Ingeniería - Énfasis en Ingeniería Eléctrica
URI permanente para esta colecciónhttp://hdl.handle.net/11349/33432
Examinar
Envíos recientes
Ítem Sistema de localización automático de fallas por el método de ondas viajeras(Universidad Distrital Francisco José de Caldas) Ladino Pérez, John Alexis; Espinel Ortega, Alvaro; Espinel Ortega Alvaro [0000-0002-7747-7718]This research presents a methodology for the fault location in high-voltage transmission lines, combining traveling wave analysis with deep learning models. The proposed approach integrates electromagnetic simulations performed in ATPDraw, automated event generation using Python, and a robust signal processing pipeline that includes high-frequency filtering and modal transformation. The resulting current waveforms—extracted from both terminals of the transmission line—serve as input to a deep neural network composed of convolutional and recurrent layers (CNN-LSTM), trained to classify the fault position along the line with one-percent granularity. To evaluate the effectiveness of different model configurations, a comparative study was conducted involving eight architectures with varying levels of complexity. Each model was trained under identical conditions using a large dataset of simulated fault events spanning a wide range of fault types, positions, and impedances. Metrics such as global accuracy, macro-averaged F1-score, and per-class performance were used to guide the model selection. The final architecture, which includes one convolutional layer followed by two LSTM layers and dense output neurons, achieved a validation accuracy close to 99%. The training dataset was generated with a sampling rate of 1 MHz and a temporal window of 1.5 milliseconds, sufficient to capture both the initial wavefronts and relevant reflections at the remote terminals. High-pass filtering with a Butterworth response was applied to preserve the transient components of interest, while the Clarke transformation facilitated the decoupling of phase interactions by projecting the signals into the α–β frame. These preprocessed signals were then standardized and used to train the model in a supervised manner. Model performance was analyzed in detail, not only in terms of overall metrics, but also through the inspection of the confusion matrix and class-specific errors. The analysis revealed that most misclassifications occurred between neighboring classes, typically within a ±2% error margin, which remains operationally acceptable in most fault location scenarios. Nonetheless, a group of underperforming classes—mostly located in the central portion of the line was identified and examined in a reduced confusion matrix. These difficulties are attributed to the intrinsic similarity of the waveforms and the physical proximity between adjacent fault points. The proposed methodology demonstrated strong generalization capabilities and consistent behavior throughout the entire classification domain. Its design allows for future extensions, such as incorporating voltage signals, adapting the approach to more complex network topologies, or deploying the trained model on embedded hardware for real-time applications. Overall, the study provides a reliable and scalable solution for automated fault location in transmission systems, leveraging the strengths of both physical modeling and data-driven learning.Ítem Estudio de riesgo por rayos en Colombia a partir de la correlación entre mortalidad, densidad de descargas a tierra y densidad poblacionalVillamil Sierra, Daniel Esteban; Rojas Cubides, Herbert Enrique; Santamaría Piedrahita, Francisco; 0000-0003-1253-6964; Rojas Cubides, Herbert Enrique [0000-0003-1253-6964]This research comprehensively exposes the application of remote sensing and geolocation for the tracking and evaluation of lightning flashes by using historical lightning incidence information provided by the Vaisala Inc® GLD360 lightning detection system. It also presents the methodology for calculating the ground flash density (GFD) through the geoprocessing of cloud-to-ground lightning data, both annual and multi-year, and the generation of maps indicating the distribution of GFD across Colombian territory. Subsequently, with the support of Geographic Information System (GIS) tools, the results of a methodology proposed in the United States to analyze the statistical correlation between GFD, population density (PD), and lightning mortality in the Colombian context are presented, at both municipal and provincial levels. For this purpose, GFD results are used in conjunction with PD information obtained from the most recent National Population and Housing Census (CNPV) and public records of lightning deaths made available by the National Administrative Department of Statistics (DANE). Finally, focusing on the estimation of lightning risk, the process of implementing the " Resilient Interventions - Municipal Disaster Risk Index Adjusted by Capacities" guide, developed by the National Planning Department (DNP), is detailed. For this, several criteria related to risk and capacity that the calculation possesses in each municipality for the municipal lightning risk index adjusted by capacities (lightning MRIC) are described. From this, a ranking is produced where the ten municipalities with the highest lightning MRIC are analyzed, and it is explained why in some of these territories there are no records of lightning deaths by DANE.