Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
4 results
Search Results
Conference Object Developing Machine Learning Models to Predict Outdoor Thermal Comfort of Kinetic Shading Devices: An Approach for Global Optimization(Education and Research in Computer Aided Architectural Design in Europe, 2025) Dağlier, Y.; Ekici, B.; Korkmaz, K.Utilizing artificial intelligence (AI) methods in the design process supports the achievement of sustainable alternatives during the conceptual design. In various AI methods, optimization and machine learning (ML) algorithms are the most common methods to develop predictive models and discover favorable design alternatives with significantly reduced computational time. Recent works focused on limited datasets, as well as the evaluation of the developed prediction models based on collected data. During the optimization process of complex design problems, the number of design parameters becomes enormous; thus, search areas contain many design alternatives that might lead the search outside of the collected data. Therefore, evaluating the accuracy of prediction models only based on the collected samples may result in scenarios where the predicted outcome during the optimization process aligns with an unrealistic solution. This study investigates how accurately prediction models developed using different ML algorithms can perform in optimization processes. The proposed framework is used to cope with outdoor thermal performance, considering kinetic shading devices with rigid origami techniques. A parametric shading device model with kinematic principles and 10 design parameters is created in Grasshopper 3d. LadyBug is used to analyze the performance of the universal thermal climate index (UTCI). To minimize the UTCI, the radial basis function optimization (RBFOpt) algorithm in the Opossum plugin is used. To compare the optimization results with the prediction results, multiple linear regression, support vector machines, random forest, polynomial regression algorithms, and artificial neural networks (ANN) are developed to predict outdoor thermal comfort performance targets on each collected data set with 2000 samples. Results showed that ANN models can provide more accurate predictions during the optimization process. The paper aims to discuss the way ML algorithms are applied and evaluated for ML-based optimization domains in design problems. © 2025, Education and research in Computer Aided Architectural Design in Europe. All rights reserved.Article Citation - WoS: 1Citation - Scopus: 1Approaches To Optimization for Movable Shading Systems: a Review of Optimization Methods and Tools(Znack Publishing House, 2021) Keskinel, Yeşim; İlal, Mustafa EmreStudies show that movable shading systems have lots of benefits for building performance. Minimizing energy consumption and maximizing daylight usage are natural expectations when using these systems. To find optimal solutions for these systems, different methods have been used. Today, optimization methods are used to solve this problem. In the literature, there are few studies about optimization of movable shading systems. This paper aims to identify different movable shading systems, optimization types, and computational optimization tools that are used. Research findings and future projections based on the reviewed papers are summarized.Article Citation - Scopus: 1Sizing of Autonomous Wind/Solar Hybrid Energy Conversion Systems for Urla, Turkey(ACTA Press, 2009) Özerdem, Barış; Ekren, OrhanIn this paper, an optimum sizing procedure of autonomous hybrid (wind + solar) energy system is presented which can be used to satisfy the requirements of given load distribution. The main purpose of this study is to find out an appropriate wind-photovoltaic hybrid energy system to satisfy electricity consumption of GSM (Global System for Mobile communication) base station at Izmir Institute of Technology Campus Area, Urla, Izmir, Turkey. To do this, monthly average daily solar radiation and wind speed data are collected. The monthly average wind speeds are measured at 10 m height during 3 years period on Izmir Institute of Technology Campus Area. The monthly average wind speed values are obtained between 5.7 and 7.7 m/s, on the other hand, the monthly average daily value of solar radiations on horizontal surfaces are ranged from 1.4 to 6.9kWh/m2 at Izmir Institute of Technology Campus Area. The hybrid system considered in the present analysis consists of one 5kW nominal power wind energy conversion systems (WECS), 21.82 m2 of photovoltaic (PV) panels (18 mono crystal PV panels each having 75 W power output) together with a battery storage system.Conference Object Citation - Scopus: 1Effects of Processing on the Properties and Permeability of Pure Gases Through Sol-Gel Silica Membranes(Trans Tech Publications, 2004) Topuz, Berna; Çiftçioğlu, Muhsin; Özkan, FehimeN2, O2 and CO2 pure gas permeation through sol-gel derived silica membranes were determined and the effects of processing parameters on the microstructure of the membrane was investigated. Silica sols were prepared in an alcoholic solution by hydrolysis and condensation of TEOS as a function of acid content. The thickness of the silica membranes was determined to be about 2μm and significant infiltration into the support was observed from the SEM pictures. The supported membranes were heat treated in the 50-400°C. The N2 permeabilities of silica membranes varied in the 2.2*10-10-2.7*10-8 mol/m2.s.Pa range for single layer membranes dipped for 10s. in the sol. The CO2 permeability of these membranes varied in the 1.2*10-9-6.95 *10-8 mol/m2.s.Pa range. The sols became viscous and gelled at 50°C in 16 hours. The O2 permeability increased with aging time. The optimum dipping time during processing was determined to be 10 seconds. The increase in the acid content of the sols were observed to increase permeabilities of the membranes significantly.