Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
4 results
Search Results
Article Citation - WoS: 38Citation - Scopus: 50Multi-Zone Optimisation of High-Rise Buildings Using Artificial Intelligence for Sustainable Metropolises. Part 1: Background, Methodology, Setup, and Machine Learning Results(Elsevier Ltd., 2021) Ekici, Berk; Kazanasmaz, Zehra Tuğçe; Turrin, Michela; Taşgetiren, M. Fatih; Sarıyıldız, I. SevilDesigning high-rise buildings is one of the complex tasks of architecture because it involves interdisciplinary performance aspects in the conceptual phase. The necessity for sustainable high-rise buildings has increased owing to the demand for metropolises based on population growth and urbanisation trends. Although artificial intelligence (AI) techniques support swift decision-making when addressing multiple performance aspects related to sustainable buildings, previous studies only examined single floors because modelling and optimising the entire building requires extensive computational time. However, different floor levels require various design decisions because of the performance variances between the ground and sky levels of high-rises in dense urban districts. This paper presents a multi-zone optimisation (MUZO) methodology to support decision-making for an entire high-rise building considering multiple floor levels and performance aspects. The proposed methodology includes parametric modelling and simulations of high-rise buildings, as well as machine learning and optimisation as AI methods. The specific setup focuses on the quad-grid and diagrid shading devices using two daylight metrics of LEED: spatial daylight autonomy and annual sunlight exposure. The parametric model generated samples to develop surrogate models using an artificial neural network. The results of 40 surrogate models indicated that the machine learning part of the MUZO methodology can report very high prediction accuracies for 31 models and high accuracies for six quad-grid and three diagrid models. The findings indicate that the MUZO can be an important part of designing high-rises in metropolises while predicting multiple performance aspects related to sustainable buildings during the conceptual design phase. © 2021 The Author(s)Article Citation - WoS: 16Citation - Scopus: 22Optimum Design of Fatigue-Resistant Composite Laminates Using Hybrid Algorithm(Elsevier Ltd., 2017) Deveci, Hamza Arda; Artem, Hatice SeçilIn this study, a fatigue life prediction model termed as Failure Tensor Polynomial in Fatigue (FTPF) is applied to the optimum stacking sequence design of laminated composites under various in-plane cyclic loadings to obtain maximum fatigue life. The validity of the model is investigated with an experimental correlation using the data available in the literature. The correlation study indicates the reliability of FTPF, and its applicability to different composite materials and multidirectional laminates. In the optimization, a hybrid algorithm combining genetic algorithm and generalized pattern search algorithm is used. It is found by test problems that the hybrid algorithm shows superior performance in finding global optima compared to the so far best results in the literature. After the verifications, a number of problems including different design cases are solved, and the optimum designs constituted of discrete fiber angles which give the maximum possible fatigue lives are proposed to discuss. A comparison study is also performed with selected design cases to demonstrate potential advantages of using non-conventional fiber angles in design.Article Citation - WoS: 126Citation - Scopus: 138Thermal Performance Optimization of Hollow Clay Bricks Made Up of Paper Waste(Elsevier Ltd., 2014) Sütçü, Mücahit; Del Coz Diaz, Juan Jose; Alvarez Rabanal, Felipe Pedro; Gençel, Osman; Akkurt, SedatIn this paper, the thermal behavior of hollow clay bricks made up of paper waste has been studied and their thermal performance has been optimized. On the one hand, both strength and thermal properties of different paper waste concentrations have been obtained by means of laboratory tests. Thermal conductivity of the microporous brick materials with additives produced in this study reduced from 0.68 W/m K to 0.39 W/m K compared with that of the sample without additives. On the other hand, the finite element method (FEM) has been applied to the nonlinear numerical thermal analysis of three different hollow bricks, including radiation and convection phenomena inside holes. Next, using the design of experiments (DOE) over the FEM models, several parameters such as the material conductivity, the convection and radiation properties and the mean brick temperature have been studied. In general, the thermal resistance is a nonlinear function that depends on the geometry of the recesses, the material properties and the temperature distribution. In all analyzed cases, minimizing the material thermal conductivity of bricks and decreasing the recesses surface radiation emissivity caused a lower thermal transmittance in the brick. Finally, the most important conclusions and the main findings of this research are exposed.Article Citation - WoS: 103Citation - Scopus: 132Break-Even Analysis and Size Optimization of a Pv/Wind Hybrid Energy Conversion System With Battery Storage - a Case Study(Elsevier Ltd., 2009) Ekren, Orhan; Yetkin Ekren, Banu; Özerdem, BarışThis paper aims to show an optimum sizing procedure of autonomous PV/wind hybrid energy system with battery storage and a break-even analysis of this system and extension of transmission line. We use net present value (NPV) method for the comparison of autonomous hybrid energy system and extension of transmission line cases. The case study is completed for the satisfaction of the electricity consumption of global system for mobile communication base station (GSM) at Izmir Institute of Technology Campus Area, Urla, Izmir, Turkey. First, we optimize the PV/wind energy system using response surface methodology (RSM) which is a collection of statistical and mathematical methods relying on optimization of response surface with design parameters. As a result of RSM, the optimum PV area, wind turbine rotor swept area, and battery capacity are obtained as 3.95 m2, 29.4 m2, 31.92 kW h, respectively. These results led to $37,033.9 hybrid energy system cost. Second, break-even analysis is done to be able to decide the optimum distance where the hybrid energy system is more economical than the extension of the transmission line. The result shows that, if the distance between national electricity network and the GSM base station location where the hybrid energy system is assumed to be installed is at a distance more than 4817 m, the installation of hybrid energy system is more economical than the electricity network.