Periodica Polytechnica (Budapest University of Technology and Economics)
Not a member yet
22160 research outputs found
Sort by
A U-Net Model for Urban Land Cover Classification Using VHR Satellite Images
Get PDFUrban settings are dynamic, constantly changing, and presenting a wide range of surface materials with high diversity in both spatial and spectral variation. As a result, mapping urban growth, evaluating infrastructure, managing water resources, and monitoring natural land cover become more complex tasks. Urban applications have made considerable progress thanks to the abundance of VHR orbital data and the recent development of artificial intelligence strategies especially neural networks. Convolutional neural networks have the potential to significantly enhance the analysis of urban land cover by addressing the limitations of traditional techniques. U-Net is a popular neural network for land cover analysis in remote sensing images. The current research presents a CNN model employing U-Net for image semantic segmentation in urban study area using both spectral and spatial context of VHR satellite data. The proposed model is trained, validated, and tested for VHR satellite image classification into five urban classes: water, vegetation, bare soil, road, and building. The CNN semantic segmentation results are compared to maximum likelihood image classification outcomes for validation and stability evaluation. A confusion matrix is applied to the classified scenes to determine the overall accuracy, producer's and user's accuracy, and Kappa coefficient using 400 random points with their corresponding ground truth. The U-Net image semantic segmentation technique achieved an overall accuracy of 87.50% and Kappa coefficient of 0.8395 which outperforms the maximum likelihood classification method with an overall accuracy of 83.25% and Kappa coefficient of 0.7812
Iterative Numerical Approximation Technique for 3D Eddy Current Models in Harmonic Regime Based on the Electromagnetic T-Formulation and the Finite Element Method
Get PDFIn this paper, an iterative numerical approximation technique is used for analyzing the distribution of eddy currents density in conductive materials plates by using the electromagnetic T-formulation and the Biot-Savart law, solved by the finite element method. The proposed approach allows for the meshing of the different parts of the studied system separately, including the sensor and the conductive plate, without the need for an air region. Firstly, this approach reduces the number of unknown variables by avoiding the air region of the system's mesh. Secondly, it simplifies the consideration of the sensor's motion without the need to remesh the system. For this purpose, a calculation code has been developed for solving an electromagnetic three-dimensional non-destructive testing model. This latter permits the resolution of JSEAM # 6 Benchmark problem to validate the proposed method. The impedance variation due to the presence of a defect are evaluated. The obtained results are compared with the experimental ones found in the literature. These results reveal a good agreement, which proves the validity of the proposed method
Air Excess Coefficient and Irreversibility Value Analysis of Gas Turbines
Get PDFGas turbines used in natural gas cycle power plants have been researched in terms of energy efficiency. Gas turbines used in power generation plants have a very complex structure because they contain many components. In order to determine the thermodynamic performance of this system, the efficiency of each component and the increase in entropy of each component were calculated using exergy analysis. Irreversibility was chosen as the main parameter and used for thermodynamic optimization of production. The system consists of many components. An increase in the irreversibility of a single component causes an increase in the irreversibility of other components. The effect of gas turbine pressure ratio and excess air percentage on fuel consumption, fuel exergy, combustion chamber exergy change and irreversibility change was investigated. It was observed that the increase in compressor pressure ratio increased irreversibility. Maximum irreversibility was observed in the combustion chamber. Irreversibility was compared with the excess air used in the combustion chamber. The air excess coefficient was examined as percentages of 100%, 200%, and 300%, respectively. The compression pressure ratio was examined for air excess coefficient percentage values from 3 to 40
Numerical Simulation of GFRP-reinforced Rectangular Concrete Beams and Proposed Design Expressions
Get PDFRebar corrosion, which has emerged as a primary detrimental factor, significantly impacts the structural performance, durability, and overall serviceability of reinforced concrete (RC) structures. In response to this issue, the growing use of GFRP, which offers superior corrosion resistance compared to steel, highlights the need to compare its performance with traditional steel-reinforced beams. To address this need, this study aims to evaluate the flexural behavior of beams reinforced solely with GFRP rebar and assess their structural performance relative to steel-reinforced beams. To achieve this, finite element models of both steel-reinforced and GFRP-reinforced beams were developed using ANSYS software. The analysis focused on load-bearing capacities, displacement characteristics, and crack patterns, and included the calculation of strain energies corresponding to collapse prevention performance limits. Overall, the study concludes that these modifications enhance design guidelines for GFRP-reinforced beams, offering improved practical applications in structural design. Significant findings include the proposed modification to the minimum reinforcement ratio equation in ACI 440.1R-15 for GFRP-reinforced concrete, the introduction of a suggested strain reduction factor for GFRP rebar, and the revision of the effective moment of inertia equation with coefficients of 0.05 and 0.95. These revisions improved the general performance indicator to 1.17, yielding better results compared to other equations in the literature. The study concludes that these modifications enhance design guidelines for GFRP-reinforced beams, offering improved practical applications in structural design
The Effect of the Layup on the Stability of Composite Cylindrical Shells
Get PDFFiber reinforced plastic laminated composites have conquered greater and greater territory in the field of engineering in the past decades for their high strength to weight ratio. By varying the layup structure their behavior can easily be modified. One of the applications, that is investigated in this article is the slit tube or cylindrical shell, that used as a structural element undergoes bending. These shells indifferent from their material may experience the snap-through phenomenon (this depends both on the material and geometry) in which the shell flattens and loses its stability to bending. Depending on the layup bistable behavior also can be achieved, i.e., the shell would have two different shapes that are in equilibrium without any constraint. In this article the effect of the layup is investigated both on the bistable behavior and the snap-through phenomenon. Geometric limitations for the bistability are calculated based on a simple beam model from the literature. The same model is used to find the snap-through moment for these shells as a function of the orientation angle. It is also proven that the flattening of the shell cannot be evaded by changing the layup structure. The results are confirmed by FE simulations where applicable
Analyzing Some Aspects of Robot-oriented Design Approach at Material Handling and Manipulation Systems of On-site Automated Construction Technologies
Get PDFThe construction sector is one of the fields of industries where automation and robotics are the least widely applied in our present day. This is in consequence of some characteristics of the construction industry, like the unique nature of the establishments, and the uncontrolled environmental circumstances on-site. However, with the present development level of robotics and with the spread of applications of AI-based technologies there is considerable chance for acceleration of development in this sector too. For the development of automated construction operations, it is essential to understand the most important principles in this regard, like robot-oriented design (ROD). In the present paper analysis of on-site automated construction technologies, which are already in use in the construction industry, is conducted, considering how the ROD approach prevails over the material handling and the applied manipulation types. In the case of material feed, there are still many technologies, where manual material handling is performed even if the technologies are applied on a relatively high level of autonomy. Regarding the automated construction processes the applied types of manipulations and the types of joints are analyzed. Robotic arms with various joint types are widely used in many industries. In the case of automated construction technologies, however, some joint types are more frequently applied than others. In the present paper, statistics are given about the occurrence of the various types, and an attempt is made to reveal the background of the observations
Kreatív-produktív történetalkotás – Az alkotás öröme és a siker élménye játék a művészetekben órán
No full textTanulmányomban egy óvodapedagógus szakos hallgatók körében projektszemléletben, az élménypedagógia eszközeit alkalmazó, a résztvevők produktív fantáziájának fejlesztését célul tűző kutatás részeredményeit mutatom be. A vizsgálat fókuszában egy komplex tevékenységrendszert felölelő projektfeladat elkészítése áll a kezdetektől a végső produktum elkészültéig. A kutatás résztvevői folyamatalapú írásstratégiával, kreatív írástechnikákat alkalmazva, zenei impulzus hatására hozták létre saját meséiket, melyeket ezt követően különböző technikákkal vizualizáltak, és végül minden hallgató elkészítette saját digitális történetét is
