Yazar "Marquez, Fausto Pedro Garcia" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Adaptive FEM-BPNN model for predicting underground cable temperature considering varied soil composition
    (Elsevier - Division Reed Elsevier India Pvt Ltd, 2024) Al-Dulaimi, Abdullah Ahmed; Guneser, Muhammet Tahir; Hameed, Alaa Ali; Marquez, Fausto Pedro Garcia; Gouda, Osama E.
    In underground cables of power systems, the maximum temperature of the cable is a crucial factor in determining its capacity. According to standards, the permissible operating temperature for the XLPE cable conductor under steady-state conditions is 90 degree celsius - a limit that should not be exceeded. Exceeding this temperature may lead to a thermal breakdown in the cable insulation, thereby resulting in interruption of the electrical power supply. Many factors affect the cable temperature, particularly through the processes of heat dissipation and diffusion from the cable into its surroundings. These factors include soil types and compositions, cable installation configuration, and thermo physical properties; therefore, accurate analysis of these factors is crucial for cable loading. In this study, the finite element method (FEM) is employed to predict the cable temperature considering different soil compositions and to present a new approach for the thermal analysis of an underground cable system. The novel approach considers various environmental conditions including single-layer and multi-layer soil types, homogeneous and non-homogeneous soil compositions, two configuration types - flat and trefoil - as well as two types of backfill materials, specifically sand-cement mixture backfill (SCMB) and fluidized thermal backfill (FTB), and dry zones to offer deeper insight into a thermal analysis. Given that the FEM requires the construction of a complex geometric model within an optimal operating condition to obtain results with high accuracy-a process that can often be complex as well as not adaptable because it depends on constant mathematical calculation-This paper presents a novel approach FEM-BPNN that uses an adaptive Backpropagation neural networks (BPNN) model as its mainstay. The proposed BPNN model exploits historical data from FEM to refine its predictive power, therefore, increasing its efficiency and accuracy. Furthermore, the model is subject to an optimization process, adjusting and refining its internal parameters in response to new data, with the ultimate goal of improving the predictive model capabilities for the temperature of underground power cables. The results underscored the high performance of FEM in the simulation, and it was observed that FEM yielded results closely aligned with those of the IEC standard. Moreover, the proposed FEM-BPNN demonstrated exceptional accuracy, achieving a low RMSE score of 0.008. It also exhibited impressive performance in the linear regression analysis, with an R-2 value of 0.99. These metrics collectively signify the robustness and efficacy of the model.
  • Küçük Resim Yok
    Öğe
    Performance Analysis of Classification and Detection for PV Panel Motion Blur Images Based on Deblurring and Deep Learning Techniques
    (Mdpi, 2023) Al-Dulaimi, Abdullah Ahmed; Guneser, Muhammet Tahir; Hameed, Alaa Ali; Marquez, Fausto Pedro Garcia; Fitriyani, Norma Latif; Syafrudin, Muhammad
    Detecting snow-covered solar panels is crucial as it allows us to remove snow using heating techniques more efficiently and restores the photovoltaic system to proper operation. This paper presents classification and detection performance analyses for snow-covered solar panel images. The classification analysis consists of two cases, and the detection analysis consists of one case based on three backbones. In this study, five deep learning models, namely visual geometry group-16 (VGG-16), VGG-19, residual neural network-18 (RESNET-18), RESNET-50, and RESNET-101, are used to classify solar panel images. The models are trained, validated, and tested under different conditions. The first case of classification is performed on the original dataset without preprocessing. In the second case, extreme climate conditions are simulated by generating motion noise; furthermore, the dataset is replicated using the upsampling technique to handle the unbalancing issue. For the detection case, a region-based convolutional neural network (RCNN) detector is used to detect the three categories of solar panels, which are all_snow, no_snow, and partial. The dataset of these categories is taken from the second case in the classification approach. Finally, we proposed a blind image deblurring algorithm (BIDA) that can be a preprocessing step before the CNN (BIDA-CNN) model. The accuracy of the models was compared and verified; the accuracy results show that the proposed CNN-based blind image deblurring algorithm (BIDA-CNN) outperformed other models evaluated in this study.