Scopus İndeksli Yayınlar Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/8651

Browse

Filters

2021 - 20233

Settings

Scopus Q: search.filters.scopusQuartile.Q1Subject: search.filters.subject.Ann

Search Results

Now showing 1 - 3 of 3
  • Article
    Citation - WoS: 12
    Citation - Scopus: 16
    A Metaheuristic-Guided Machine Learning Approach for Concrete Strength Prediction With High Mix Design Variability Using Ultrasonic Pulse Velocity Data
    (Elsevier, 2023) Selcuk, S.; Tang, P.
    Assessment of concrete strength in existing structures is a common engineering problem. Several attempts in the literature showed the potential of ML methods for predicting concrete strength using concrete properties and NDT values as inputs. However, almost all such ML efforts based on NDT data trained models to predict concrete strength for a specific concrete mix design. We trained a global ML-based model that can predict concrete strength for a wide range of concrete types. This study uses data with high variability for training a metaheuristic-guided ANN model that can cover most concrete mixes used in practice. We put together a dataset that has large variations of mix design components. Training an ANN model using this dataset introduced significant test errors as expected. We optimized hyperparameters, architecture of the ANN model and performed feature selection using genetic algorithm. The proposed model reduces test errors from 9.3 MPa to 4.8 MPa.
  • Article
    Citation - WoS: 5
    Citation - Scopus: 6
    The Effects of Using Corrugated Booster Reflectors To Improve the Performance of a Novel Solar Collector To Apply in Cooling Pv Cells-Navigating Performance Using Ann
    (Springer, 2021) Oztop, Hakan F.; Alnefaie, Khalid A.; Ahmadian, Ali; Baleanu, Dumitru; Abu-Hamdeh, Nidal H.
    In this study, turbulent flow and heat transfer of water in a solar collector equipped with corrugated booster reflectors to apply in cooling photovoltaic cells (PV) are investigated. 3D simulation is done using by the control volume method and SIMPLEC algorithm. The optimization was carried out by comparison of different parameters to reach the optimal situation with the maximum efficiencies of energy and exergy. It is established that in the case of corrugated booster reflectors, the temperature of outlet fluid and efficiencies of energy and exergy are more. In general, while the trend of variation of exergy efficacy with impressive parameters is increasing, using the mixers precipitate the efficacy increment. Furthermore, for the case that the trend of variation of exergy efficacy with altering these parameters is reducing, the reducing trend gets slow. Finally, it is realized that using corrugated booster reflectors have a significant effect on collector efficacy, and the highest exergy efficacy was obtained for the 50 degrees corrugations. At Re = 6800, the maximum Nusselt number achieves and it is about 6.03. Finally, using an artificial neural network, the output parameters were navigated with acceptable accuracy. For 76.6% of the data points, the margin of deviation (MOD) was < 1%, and for the rest, the maximum MOD was 2%.
  • Article
    Citation - WoS: 5
    Citation - Scopus: 7
    Hydrodynamic Analysis of a Heat Exchanger With Crosscut Twisted Tapes and Filled With Thermal Oil-Based Swcnt Nanofluid: Applying Ann for Prediction of Objective Parameters
    (Springer, 2021) Almitani, Khalid H.; Gari, Abdullatif A.; Alimoradi, Ashkan; Ahmadian, Ali; Baleanu, Dumitru; Abu-Hamdeh, Nidal H.
    Present study investigates hydrodynamic analysis of heat exchanger with crosscut twisted tapes and filled with thermal oil-based SWCNT nanofluid (NF). SIMPLE algorithm and FVM method are used. The heat transfer fluid enters the test section at T-in = 300 K in different flow velocities, which are related with Reynolds numbers 5000, 10,000, 15,000 and 20,000. For ensuring that the input flow to test section is always fully developed, the input part to length 2L is considered. It is also intended to ensure that the flow does not return to test section of the exit section of length L. Also, the test section has the constant temperature of T-s = 400 K. Different geometrical parameters of twisted tapes in heat exchanger are studied. The optimization is carried out due to fulfill the highest performance evaluation criterion (PEC index). Based on results, usage of twisted tapes has a sharp impact on thermal and hydraulic characteristics of heat exchanger and leading to swirling motion, which improve the heat transfer coefficient and augment the pressure drop (Delta P). Besides, usage of simple model is more efficient than crosscut model. Also, it is understood that the PEC index values always are more than 1.11, which means that employment of these turbulators is effective and positive with thermal-hydraulic viewpoint. The simple model (Case K and N = 8) is introduced as the most optimum model in this paper, and its PEC values for system filled with NF in phi = 0.8% at Re = 5000, 10,000, 15,000 and 20,000 are 1.37, 1.59, 1.78 and 1.93, respectively. The application of machine learning methods showed that the output parameters in the simulation of heat exchangers are well predicted. The accuracy of the developed neural network was such that the maximum error was below 1%.