Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection

Permanent URI for this collectionhttps://hdl.handle.net/11147/7148

Browse

Filters

2015 - 201912020 - 20233

Settings

COAR Access Rights: search.filters.coarAccessRights.metadata only accessSubject: search.filters.subject.Artificial neural network

Search Results

Now showing 1 - 4 of 4
  • Book Part
    Citation - Scopus: 3
    Real-Time Flood Hydrograph Predictions Using Rating Curve and Soft Computing Methods (ga, Ann)
    (Elsevier, 2022) Tayfur, Gökmen
    This chapter introduces hydraulic and hydrologic flood routing methods in natural channels. It details hydrological flood routing methods of the Rating Curve and Muskingum. Based on the rating curve method (RCM), it presents real-time flood hydrograph predictions using the genetic algorithm (GA-based RCM) model. In addition, it presents how to make real-time flood hydrograph predictions using the artificial neural network (ANN). The chapter briefly introduces the basics of GA and details how to calibrate and validate the GA-based RCM model using measured real-time flood hydrographs. Similarly, after giving the basics of ANN, it shows how to train and test the ANN model using measured hydrographs. Real hydrograph simulations by the RCM, GA-based RCM, and ANN are presented, and merits of each model are discussed. © 2023 Elsevier Inc. All rights reserved.
  • Article
    Citation - Scopus: 1
    Relationship Between Abrasion, Fragmentation and Thermal Weathering Resistance of Aggregates: Regression and Artificial Neural Network Analyses
    (Springer, 2023) Gökalp, İslam; Kaya, Orhan; Uz, Volkan Emre
    For being used in pavement construction, properties of aggregates must satisfy the minimum requirements specified by highway agencies or institutions. The properties of the aggregates are determined by many tests lasting anywhere between a couple of hours to a few weeks depending on the type of the test. If good correlations can be established between the tests taking longer time and the ones taking comparably shorter time, there might be no need to conduct these longer time-taking tests for the sake of time. The aim of this study is to investigate the relationships between abrasion, fragmentation, and thermal weathering resistances of different aggregate types. To accomplish this aim, aggregates with different origins (natural and slags) were tested and correlative analyses utilizing regression analysis and artificial neural network (ANN) models were performed to establish relationships between the results of these test methods. It was found that good correlations can be established especially with ANN models and significant amount of time and effort can be saved with these developed models. © 2023, The Author(s), under exclusive licence to Chinese Society of Pavement Engineering.
  • Article
    Citation - WoS: 39
    Citation - Scopus: 42
    Prediction of Char Production From Slow Pyrolysis of Lignocellulosic Biomass Using Multiple Nonlinear Regression and Artificial Neural Network
    (Elsevier, 2021) Li, Ting Yan; Xiang, Huan; Yang, Yang; Wang, Jiawei; Yıldız, Güray
    Char produced from lignocellulosic biomass via slow pyrolysis have become one of the most feasible alternatives that can partially replace the utilisation of fossil fuels for energy production. In this study, the relationship between compositions of lignocellulosic biomass, operating conditions of slow pyrolysis, and characteristics of produced char have been analysed by using multiple nonlinear regression (MnLR) and artificial neural networks (ANN). Six input variables (temperature, solid residence time, production capacity, particle size, and fixed carbon and ash content) and five responses (char yield, and fixed carbon, volatile matter, ash content, HHV of produced char) were selected. A total of 57 literature references with 393-422 datasets were used to determine the correlation and coefficient of determination (R-2) between the input variables and responses. High correlation results (>0.5) existed between pyrolysis temperature and char yield (-0.502) and volatile matter of produced char (-0.619), ash content of feedstock and fixed carbon (-0.685), ash content (0.871) and HHV (-0.571) of produced char. Whilst the quadratic model was selected for the regression model, then the model was further optimised by eliminating any terms with p-values greater than 0.05. The optimised MnLR model results showed a reasonable prediction ability of char yield (R-2 = 0.5579), fixed carbon (R-2 = 0.7763), volatile matter (R-2 = 0.5709), ash (R-2 = 0.8613), and HHV (R-2 = 0.5728). ANN model optimisation was carried out as the results showed trainbr training algorithm, 10 neurons in the hidden layer, and tansig and purelin transfer function in hidden and output layers, respectively. The optimised ANN models had higher accuracy than MnLR models with the R-2 greater than 0.75, including 0.785 for char yield, 0.855 for fixed carbon, 0.752 for volatile matter, 0.951 for ash and 0.784 for HHV, respectively. The trained models can be used to predict and optimise the char production from slow pyrolysis of biomass without expensive experiments.
  • Conference Object
    Citation - Scopus: 1
    Modelling Twin Rotor System With Artificial Neural Networks
    (Institute of Electrical and Electronics Engineers Inc., 2015) Deniz, Meryem; Bıdıklı, Barış; Bayrak, Alper; Özdemirel, Barbaros; Tatlıcıoğlu, Enver
    In this study, the input output relation of the twin rotor system which was constructed in our laboratory is obtained by using ANNs. When compared with the existing literature, main advantage of this modelling approach is that multi input multi output ANN structure is used preferred. As a result of this approach, the cross coupling effects, between the rotors and also between the outputs, are taken into consideration. Thus, we sincerely believe that the obtained input output model demonstrates a close behavior to the real system.