Elektrik Programı / Electric Programme
Elektrik Programına ait koleksiyonlar bu alt bölümde listelenir.
https://hdl.handle.net/20.500.12294/378
2024-03-29T11:53:33Z
2024-03-29T11:53:33Z
Prediction of Wind Speed Using Artificial Neural Networks and ANFIS Methods (Observation Buoy Example)
Inan, Timur
Baba, Ahmet Fevzi
https://hdl.handle.net/20.500.12294/3242
2023-02-08T15:32:01Z
2020-01-01T00:00:00Z
Prediction of Wind Speed Using Artificial Neural Networks and ANFIS Methods (Observation Buoy Example)
Inan, Timur; Baba, Ahmet Fevzi
Estimation of the wind speed plays an important role in many issues such as route determination of ships, efficient use of wind roses, and correct planning of agricultural activities. In this study, wind velocity estimation is calculated using artificial neural networks (ANN) and adaptive artificial neural fuzzy inference system (ANFIS) methods. The data required for estimation was obtained from the float named E1M3A, which is a float inside the POSEIDON float system. The proposed ANN is a Nonlinear Auto Regressive with External Input (NARX) type of artificial neural network with 3 layers, 50 neurons, 6 inputs and 1 output. The ANFIS system introduced is a fuzzy inference system with 6 inputs, 1 output, and 3 membership functions (MF) per input. The proposed systems were trained to make wind speed estimates after 3 hours and the data obtained were obtained and the successes of the systems were revealed by comparing the obtained values with real measurements. Mean Squarred Error (MSE) and the regression between the predictions and expected values (R) were used to evaluate the success of the estimation values obtained from the systems. According to estimation results, ANN achieved 2.19 MSE and 0.897 R values in training, 2.88 MSE and 0.866 R values in validation, and 2.93 MSE and 0.857 R values in testing. ANFIS method has obtained 0.31634 MSE and 0.99 R values. © 2020 IEEE.
2020-01-01T00:00:00Z
Development of a deep wavelet pyramid scene parsing semantic segmentation network for scene perception in indoor environments
Aslan, Simge Nur
Uçar, Ayşegül
Güzeliş, Cüneyt
https://hdl.handle.net/20.500.12294/3219
2023-01-31T15:32:07Z
2022-01-01T00:00:00Z
Development of a deep wavelet pyramid scene parsing semantic segmentation network for scene perception in indoor environments
Aslan, Simge Nur; Uçar, Ayşegül; Güzeliş, Cüneyt
In this paper, a new Deep Wavelet Pyramid Scene Parsing Network (DW-PSPNet) is proposed as an effective combination of Discrete Wavelet Transform (DWT), inception module, the channel and spatial attention modules, and PSPNet. Improved semantic segmentation via the combination, to our best knowledge, is not yet reported in the literature. The paper has two main contributions: (1) a new backbone network into PSPNET introduced by a combination of DWT, inspection modules, and attention mechanisms; (2) a new and improved version of PSPNet base structure. Further, three new modifications are introduced. First, the drop activation function is used to increase validation and test accuracy of the segmentation. Second, a skip connection from the backbone is applied to increase validation and test accuracies by restoring the resolution of feature maps via full utilization of multilevel semantic features. Third, Inverse Wavelet Transform (IWT) and convolution layer are applied to obtain the segmented images without information loss. DW-PSPNet was implemented via our own data generated by using a Robotis-Op3 humanoid robot to detect objects in indoor environments and and benchmark data set. Simulation results show higher performance of the proposed network compared with that of previous successful networks in handling semantic segmentation tasks in indoor environments. Moreover, extensive experiments on the benchmark Ade20K data set were also conducted. DW-PSPNET achieved an mIoU score of 45.97% on the ADE20K validation set, which are new state-of-the-art results. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.
2022-01-01T00:00:00Z
Toward Class AAA LED Large Scale Solar Simulator with Active Cooling System for PV Module Tests
Esen, Vedat
Saglam, Şafak
Oral, Bülent
Ceylan Esen, Özge
https://hdl.handle.net/20.500.12294/2982
2022-10-03T19:03:28Z
2022-01-01T00:00:00Z
Toward Class AAA LED Large Scale Solar Simulator with Active Cooling System for PV Module Tests
Esen, Vedat; Saglam, Şafak; Oral, Bülent; Ceylan Esen, Özge
Solar simulators are significant in testing solar cells and photovoltaic (PV) modules since they provide spectrum and optic characteristics close to natural sunlight. This research introduces two fundamental novelties to the literature on light-emitting diode (LED) light source solar simulators. One of these innovations is designing and developing a solar simulator to achieve I-V characterization on a PV module basis instead of cell-based contrary to the previous studies. For this purpose, a unique board with a modular structure is designed on which the LEDs are positioned. In the research, LEDs of at six different wavelengths are used. Spectral match, spatial nonuniformity, and temporal instability performance criteria tests conducted on the illuminated area is performed based on IEC 60904-9 and ASTM 927E-10 standards. Class AAA was obtained according to the large-scale solar simulator standard specified in ASTM 927E-10. The second novelty the study introduces is developing an active cooling system that can prevent an increase in LED junction temperature when the number of LEDs increases in an LED solar simulator with a wide illuminated area. In addition to the fans, this solution is suggested to prevent any damage to the LEDs during the test, as well as high temperatures from affecting the wavelengths and at the same time achieve 25 °C, one of the standard test conditions. Also, the device dimensions are optimized ergonomically for ease of use. With this system designed and devised, it becomes possible to test commercially available PV modules successfully. The active cooling system minimizes the heating problem and the impact of wavelengths that might invalidate performance criteria classes.
2022-01-01T00:00:00Z
Gemi çarpışmalarının önlenmesi için melez algoritma tabanlı bir karar destek sisteminin oluşturulması
İnan, Timur
Baba, Ahmet Fevzi
https://hdl.handle.net/20.500.12294/2480
2022-10-03T19:03:41Z
2020-01-01T00:00:00Z
Gemi çarpışmalarının önlenmesi için melez algoritma tabanlı bir karar destek sisteminin oluşturulması
İnan, Timur; Baba, Ahmet Fevzi
Decision support systems constitute the focus of many studies in the maritime industry as vessel accidents are often caused by human errors. In this study, an anti-collision decision support system is proposed. The system consists of three main parts. An artificial neural network system capable of predicting the forward position of ships, a fuzzy logic system that calculates which of the surrounding ships is at greater risk of collision, and a collision avoidance route using the CSGA (Cuckoo Search-Genetic Algorithm) algorithm. In this study, scenarios have been created in order to measure the success of collision prevention system. The CSGA algorithm used in the calculation of collision prevention routes and the ACO (Ant Colony Optimization), PSO (Particle Swarm Optimization), and GA (Genetic Algorithm) algorithms previously used in the literature were also used for calculation and the results compared in terms of efficiency. While measuring the efficiency of algorithms; the time spent on the calculation and the efficiency of the recommended collision avoidance routes are considered. In the collision avoidance system with the CSGA algorithm, on average, the calculation times were 29.47 times faster than ACO, 5.78 times faster than PSO, and 2.72 times faster than GA. Considering the appropriateness of the paths calculated by the algorithms, the CSGA algorithm has found an average of %7. 85 in comparison to PSO, %2.62 in comparison to PSA, and %1.18 in comparison to GA.
2020-01-01T00:00:00Z