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.Conference Object Application of Artificial Neural Network for Predicting Peak Discharge From Breached Embankment Dam(International Association for Hydro-Environment Engineering and Research (IAHR), 2024) Okan, M.; Bor, A.; Tayfur, G.Estimation of peak discharge is a key parameter for risk assessment in case of dam failure, and has attracted great attention from researchers in recent years. Many formulas are available in the literature, but these cannot cover all experimental scenarios. Existing models are typically inadequate to address the complexities of dam breaches. This research attempted to predict the peak discharge in the breached embankments with an artificial neural network (ANN) model, which is effective in nonlinear problems, using datasets obtained from various dam breaches cited in the literature. The ANN model is useful in the preparation of emergency action plans since it enables prediction of peak discharge. Multilayer Perceptron (MLP) with Levenberg-Marquardt (LM) and Bayesian Regularization (BR) algorithms was used to predict peak discharges from breached embankments. The dataset was divided into three: 56% for training, 20% for validation and 24% for testing. Different scenarios were created using different input combinations. Performance evaluation was based on the root-mean squared error (RMSE), percent bias (PBIAS), determination of coefficient (R2), Nash-Sutcliffe efficiency (NSE) and RMSE-observations standard deviation ratio (RSR). A comparison of training algorithms revealed that LM showed the best performance when the best ANN was selected from 1000 networks. Volume of water above the breach bottom (Vw) had a greater effect on model performance than the depth of water above the breach bottom (Hw). The best performance was obtained when both Vw and Hw were used as input. © 2024 ISHS. All Rights Reserved.Article Comprehensive 4E Analysis, Multi-Objective Optimization, and Feasibility Study of Five Natural Gas Liquefaction Processes With a Case Study for Iran(Elsevier Sci Ltd, 2026) Basmenj, Farhad Rahmdel; Tabriz, Zahra Hajimohammadi; Aghdasinia, Hassan; Mohammadpourfard, MousaNatural gas (NG) is increasingly vital as a cleaner energy source due to its lower carbon emissions compared to other fossil fuels. Liquefaction facilitates efficient long-distance transportation. While numerous studies address NG liquefaction's technical aspects, holistic research remains limited. This study presents a comprehensive evaluation of five conventional natural gas (NG) liquefaction processes (including SMR-Linde, SMR-APCI, C3MRLinde, DMR-APCI, and MFC-Linde) through a 4E framework: energy, exergy, exergoeconomic, and exergoenvironmental analyses. Addressing limitations in prior research, it incorporates environmental considerations and introduces production volume-independent metrics to ensure equitable comparisons. Multi-objective optimization, based on exergoeconomic and exergoenvironmental criteria, is employed to identify Pareto-optimal operating conditions. To accelerate this complex process, neural networks are utilized. The study concludes with a feasibility assessment of large-scale LNG production in Iran, offering practical insights for optimizing process selection and enhancing the economic and environmental viability of LNG technologies. Simulations show that the MFC-Linde cycle as the most efficient regarding specific energy consumption (0.2563 kWh/kgLNG), coefficient of performance (3.184), and exergy efficiency (52.32 %). It also demonstrates the lowest unit exergy cost (3.67$/GJ) and exergy unit environmental impact (5271.86mPts/GJ). Multi-objective optimization, considering both exergetic-economic and exergetic-environmental criteria, using neural networks and genetic algorithms in MATLAB identifies Pareto-optimal conditions for all processes. For the MFCLinde, as the most efficient process, optimal operating conditions in the exergetic-economic trade off scenario are: Exergy efficiency of process = 51.45% and Exergy cost rate of LNG = 82, 162.15$/h; at Pressure of NG feed = 5, 925.32kPa, Pressure drop in valve = 5, 831.99kPa, and NG side temperature in heat exchanger = -168.34 degrees C. Finally, a feasibility study for large-scale LNG (Liquefied Natural Gas) production in Iran shows promising results, with a return on investment of 32.24 %/year and a payback period of 2.34 years, indicating the project's potential success in regions with abundant NG reserves.Article Citation - WoS: 2Citation - Scopus: 2Image Processing and Artificial Neural Network Based Determination of Surface Mean Texture Depth on Lab-Controlled Chip Seal Pavement Samples(Nature Portfolio, 2024) Gokalp, Islam; Uz, Volkan Emre; Barstugan, Mucahid; Balci, Mehmet CanBecause surface texture is nearly the sole indicator of pavement functional properties and highly correlated with critical operational characteristics of roadways like traffic noise and safety, the change in pavement surface texture because of traffic loadings and environment has to be evaluated routinely. There are numerous direct or indirect evaluation techniques in the market. However, most of these methods have some limitations like requiring lane closure or being expensive. In this study, a 2D image processing method was established to estimate the surface mean texture depth (MTD) of chip sealed pavements. We produced chip sealed pavement samples in the laboratory with different aggregate type, shape, and size ranging between 2 and 19 mm to cover wide range of live conditions. Two well-known conventional test methods, Sand Patch (SP) and Hydrotimer (HT), were used to determine MTDs of chip seal samples. Subsequently numerous photos were taken on surface of the samples with a camera for 2-D image processing that was done based on surface void ratio (SVR) approach. With the image processing, SVR of all samples were determined. At the point of whether there is a relationship or not, correlation analysis was made between the MTDs obtained with SP and HT and the data obtained by SVR approach with the artificial neural network method. The results show that the proposed SVR approach construed on 2D image processing method can be a reliable alternative to evaluate the surface texture of pavements.