Yazarlar
- Gul, Muhammet(16)
- Kahraman, Gökhan(13)
- Onat, Onur(13)
- Yucesan, Melih(12)
- Etli, Serkan(11)
- Mete, Suleyman(11)
- Akkurt, Nevzat(10)
- Karataş, Mehmet(10)
- Utku, Anıl(10)
- Yön, Burak(10)
- Akmaz, Düzgün(8)
- Cemalgil, Selim(8)
- Demir, Yakup(8)
- Ergen, Burhan(8)
- Çil, Zeynel Abidin(8)
- Akgül, Melek(7)
- Doğan, Gürkan(7)
- Gülmez, Nihan(7)
- Xu, Qian(7)
- Yildirim, Ozal(7)
- Yilmaz, Mehmet(7)
- Özceylan, Eren(7)
- Celik, Erkan(6)
- Göçmen, Elifcan(6)
- Orhan, Ahmet(6)
- Ertarğın, Merve(5)
- Serin, Faruk(5)
- Yilmazer, Merve(5)
- Zheng, Qiang(5)
- Akpolat, Mustafa(4)
- Atangana, A(4)
- Baskonus, HM(4)
- Bulut, H(4)
- Ding, Yulong(4)
- Dogan, Akar(4)
- Eristi, Huseyin(4)
- Hammouch, Z(4)
- Işık, Erdem(4)
- Karakose, Mehmet(4)
- Kaya, Sema Kayapinar(4)
Yayınlar
- BildiriAçık Erişim2025Health Status Classification of Electric Motors Using CNN-Based Models and SDP Images Under Varying Noise Conditions
Ertarğın, Merve; Yordanov, Nikolay; Zhilevski, Marin; Benedicenti, L.; Liu, Z.
The increasing application of electric motors across various industrial sectors requires effective monitoring and early diagnostics to prevent potential failures. This study explores the use of Convolutional Neural Network (CNN)-based models together with Symmetrized Dot Pattern (SDP) sound representations for classifying the health status of electric motors under different noise conditions. Acoustic data from a brushless DC motor were transformed into SDP images, which were then used to train CNN models. The dataset included recordings of motors in “Good”, “Broken” and “Heavy Load” conditions, captured under various noise environments such as pure, talking, white noise, atmospheric, and stress test conditions. The classification tasks were conducted under three conditions: assessing motor health status, evaluating both motor health status and noise types, and excluding the stress test noise type for a balanced dataset. The results demonstrated that the CNN models achieved high accuracy rates in classifying motor health status, with the Custom CNN model performing best in simpler tasks and MobileNet excelling in more complex scenarios. The study highlights the feasibility of using SDP images with CNN-based models for fault classification in motors and suggests future research directions for improving classification accuracy through advanced feature extraction techniques and multimodal data representations.
AtıfScopus1
İncele - BildiriAçık Erişim2025Investigation of Fatigue Performance of Hot Mix Asphalt Mixtures Modified with Elvaloy and Phosphoric Acid (PPA) as an Alternative to SBS Polymer
Furtana-Yalcin, Beyza; Ozaslan, M.
In this study, the combined use of Elvaloy and phosphoric acid (PPA) was investigated to enhance the performance of asphalt concrete (Hot Mix Asphalt - HMA) layers used in flexible pavement structures under increasing traffic loads and environmental conditions. These additives, considered as alternatives to Styrene-Butadiene-Styrene (SBS) polymer, were evaluated solely for their effects on the mechanical performance of HMA mixtures. Binders modified with Elvaloy/PPA at specified proportions were used to produce HMA specimens, and indirect tensile fatigue tests were conducted on these samples. The experimental results indicated that the addition of Elvaloy and PPA improved the mechanical properties of mixtures prepared with bituminous binders, extended fatigue life, and enhanced the strength and deformation resistance of asphalt mixtures at the selected proportions. The findings suggest that the Elvaloy/PPA additive combination could be a viable alternative to SBS polymer and has the potential to extend the service life of hot mix asphalt. Thus, it was concluded that the use of these additives contributes to improving HMA performance and supports sustainable pavement design.
AtıfOpenAlex1İncele - MakaleAçık Erişim2025Scopus SJRQ1Automated fault classification of asynchronous motor using mobile phone accelerometer and Parallel Residual CNN-GRU
Ertargin, Merve; Orhan, Ahmet; Yildirim, Ozal; Gurgenc, Turan
In this study, a fault detection system that classifies motor faults using deep learning without requiring any sensor connections inside or on the motor setup is proposed. The focus is on the electrical and mechanical faults of asynchronous motors, which are widely used in the industry. A mobile application developed using Flutter can collect vibration data using the three-axis accelerometer sensor in smartphones. By placing a smartphone with the application installed on the motor for which fault detection is desired, vibration data on three axes (x, y, z) is collected to train deep models. Subsequently, test data is used to identify the fault status and class of the electric motor. Different conditions and scenarios were created to test the adequacy of smartphone accelerometer sensors in detecting motor faults. Fault classification with vibration data obtained under different motor operating speeds in loaded and unloaded conditions achieved accuracy rates of over 99%.
AtıfScopus18OpenAlex15İncele - MakaleYalnız künye2025Scopus SJRQ2Investigation of Mechanical Properties of Jute and Tea Waste-Reinforced Epoxy Composite Material Produced by Vacuum Assisted Resin Infusion Molding
Dogan, Akar; Mahmat, Aybars; Agar, Salih
Recently, the production of materials obtained from plant sources has been increasing due to their environmentally friendly and sustainable sources. Natural fibers and waste materials offer a remarkable alternative in composite production due to their biodegradability, low cost and renewability. In this study, composite materials were produced using hybrid Jute and industrial tea waste-reinforced epoxy materials by vacuum assisted resin infusion molding. In this context, the reason for using natural and industrial resources such as jute fiber and tea waste is to contribute to both the improvement of mechanical properties and the reduction of environmental impacts. It was observed that tensile and flexural strength decreased as the amount of tea waste increased. Conversely, the energy absorbed during the quasi-static punch shear and Charpy impact tests increased, unlike the tensile and flexural strength. Approximately 50% decrease was observed in the tensile strength of the 60% tea waste reinforced material compared to the pure jute composite material. In Charpy impact and quasi-static punch shear tests, a 5% increase in the energy absorbed in the 60% tea waste reinforced composite materials was obtained.
AtıfScopus2WoS1OpenAlex1
İncele - MakaleAçık Erişim2025Scopus SJRQ1Spring-Based Soil–Structure Interaction Modeling of Pile–Abutment Joints in Short-Span Integral Abutment Bridges with LR and RSM
Polat, Erkan; Göçmen Polat, Elifcan
Integral abutment bridges (IABs) are increasingly adopted in transportation infrastructure due to their durability, reduced maintenance needs, and cost-effectiveness compared to conventional bridges. However, their reliable performance under live loads is strongly influenced by the nonlinear soil–structure interaction (SSI) at the pile–abutment joint, which remains challenging to quantify using conventional analysis methods. This study develops simplified spring-based models to capture the SSI behavior of pile–abutment joints in short-span IABs. Predictive equations for joint rotation, deflection, moment, and shear are formulated using Linear Regression (LR) and Response Surface Methodology (RSM). Unlike prior studies relying solely on FEM or traditional p–y curves, the novelty of this work lies in deriving regression-based spring constants calibrated against FEM analyses, which can be directly implemented in standard structural software. This approach significantly reduces computational demands while maintaining predictive accuracy, enabling efficient assessment of pile contributions and global bridge response. Validation against finite element method (FEM) results confirms the reliability of the simplified models, with RSM outperforming LR in representing nonlinear parameter interactions.
AtıfScopus2WoS2OpenAlex3İncele - MakaleYalnız künye2025Scopus SJRQ2Experimental comparison of conventional and ultrasonic-assisted high-speed drilling of glass fiber reinforced epoxy composites
Ağar, Salih; Mahmat, Aybars; Doğan, Akar
Glass fiber reinforced epoxy composites are favored in several industries, including automotive and aerospace, owing to their superior strength-to-weight ratio. Drilling is a prevalent machining procedure employed to add fasteners for laminate assembly. Nonetheless, drilling these composites presents significant challenges due to the abrasive characteristics of the reinforcement, necessitating an examination of machining performance. During the drilling of composites, cutting temperature, thrust force, and delamination damage are primary concerns. In recent years, high-speed ultrasonic drilling, an innovative machining technique designed to address these challenges, has garnered significant interest. This investigation involved high-speed ultrasonic drilling and conventional drilling of glass fiber reinforced epoxy material. In the studies, optimal conditions were studied by evaluating thrust force, cutting temperature, and delamination damage by varying speeds, feed rates, and frequencies. The thrust force was 11 N in the traditional approach at 40,000 rpm, but it was recorded at 9 N with the ultrasonic method. Moreover, with ultrasonic drilling, cutting temperatures decreased by over 25% relative to traditional drilling, attributable to the harmonic motion that dissipates heat in the drilling zone. Analysis of the drilling region revealed a notable enhancement in damage, particularly in delamination, with the application of ultrasonic drilling. The experimental results indicate that ultrasonic machining enhances machining performance.
- MakaleYalnız künye2025Scopus SJRQ1Multivariable assessment of ınfill strategies for enhanced mechanical properties in 3D-printed curved beams
Arıkan, Volkan; Dogan, Akar
Purpose – This study specifically focuses on low-to-medium infill densities where the influence of internal geometry on structural performance becomes most dominant. This study aims to explore how different infill patterns and densities affect the mechanical response of curved-axis beams produced by fused filament fabrication-based additive manufacturing (AM), providing insights for optimizing lightweight and material-efficient components subjected to bending loads. Design/methodology/approach – Twenty-seven PLA-based specimens with varying curvature radii (500, 750 and 1000 mm), infill patterns (grid, triangular and trihexagonal) and densities (20%, 30% and 40%) were manufactured. Each was subjected to three-point bending tests following ASTM standards. The experimental approach focused on analyzing force-displacement behavior to evaluate stiffness, load capacity and deformation characteristics under static loading conditions. Findings – Increasing infill density enhanced the maximum force capacity of curved beams but reduced their displacement tolerance, reflecting greater rigidity. The trihexagonal (TH) pattern exhibited the highest displacement values, confirming its energy absorption capability, while the triangular (TA) pattern provided the greatest rigidity with lower deformation. The grid (GR) pattern showed intermediate behavior, with displacement capacity strongly influenced by curvature radius. Straighter beams generally displayed reduced displacement and higher stability, while more curved beams exhibited greater deformation. These results highlight the critical role of infill geometry and curvature in balancing strength, stiffness and energy absorption in three-dimensional (3D)-printed curved beams. Originality/value – Unlike prior studies that focus on high or near-solid infill levels, this work uniquely highlights the mechanical response of additively manufactured curved beams within the low-to-medium infill density range, where infill geometry plays a critical role. The study presents the first detailed comparison of how infill strategies interact with curvature in 3D-printed beams. It delivers practical design guidance for engineers working with curved structures in mechanical, aerospace and civil applications. Its novelty lies in demonstrating how trihexagonal patterns can optimize performance across various geometries, supporting enhanced structural resilience in AM.
- MakaleYalnız künye2025Scopus SJRQ1Mechanical, durability and microstructure properties of eco-friendly self-compacting mortars with addition of volcanic scoria, silica fume and boron waste as cement replacement
Şahin Yön, Merve
The objective of this experimental study is to investigate the mechanical and durability performances of self-compacting mortars containing industrial waste and natural stone to develop an environmentally friendly mortar. Binary series of boron waste (B), silica fume (S) and volcanic scoria (V) were formed by substituting up to 95 % by weight with Portland cement, and ternary series were formed by substituting up to 80 % by weight with Portland cement. A total of 14 mixtures and one reference mixture (R) were improved for the purpose of investigating the workability, mechanical strength and durability properties of self-compacting mortar with different binder compositions. Samples of 40x40x160 mm were produced to evaluate mechanical properties and freeze-thaw effect, 100x100x100 mm for abrasion testing and 50x50x50 mm to determine physical properties. Additionally, SEM/EDS and XRD analyses were performed to determine the microstructural characteristics of the mixtures formed. The test results demonstrated that the sole replacement of boron waste with Portland cement resulted in enhanced fluidity. Nonetheless, the 90-day compressive strengths of the S10V20 and B5S10V5 mixtures exhibited increases of 7.47 % and 5.57 %, respectively, relative to the reference, whilst the B15 series saw a 52.5 % reduction, marking the lowest 90-day compressive strength compared to the reference sample. When the freeze-thaw effect was assessed after 136 cycles, the compressive strength diminished by 8.57 %, 13.1 %, 4.13 %, 7.28 %, 6.22 %, 24.77 %, and 48.1 % in the R, B5, V5, V10, V15, B5S10V5, B5S10V10, and B5S10V15 samples, respectively. Among the samples subjected to abrasion tests, a loss of 6.5 per thousand occurred in the mass of the reference sample at the end of 6 minutes, while a loss of 11 per thousand occurred in the binary mixture containing 5 % B, which had the highest abrasion.
AtıfScopus16WoS14OpenAlex16İncele - MakaleYalnız künye2025Scopus SJRQ2The impact of global value chains on climate change
Ateş, Erdem; Şanlısoy, Selim
Climate change can be defined as the increase in average temperatures due to rising greenhouse gas (GHG) emissions, predominantly due to human activities. Carbon emissions have increased at an alarming rate with the emergence of globalization, with its accompanying global value chain, and the consequent increase in global production volume with its polluting sectors. To combat this alarming situation, production with environmentally friendly technologies has emerged recently, and developing countries are embracing more and more costly environmentally friendly production techniques, although they are disadvantaged when it comes to covering the costs. However, it has been observed that they stay behind in this race to adopt environmentally friendly techniques compared to developed countries. The aim of the study, which is a novel contribution to the existing literature, is to examine the relationship between the global value chain and climate change by considering the distinction between developed and developing countries. The study used the data of 156 countries from the years 2000–2018. The results obtained from the generalized method of moments (GMM) show that participation in global value chains has different effects in developed and developing countries regarding carbon emissions. When the level of participation in GVC (global value chain) and FVA (foreign value added) increases, countries’ carbon emissions decrease, and it increases when the DVA (domestic value added) level increases. As a result, in particular, developing countries should green their production methods, and for this purpose, financial support mechanisms should be established.
AtıfScopus8WoS4OpenAlex7İncele - MakaleYalnız künye2025Scopus SJRQ3Development of alternative carbon fibre powder and rare earth element-based filler for high density polyethylene; [Entwicklung von alternativen Kohlenstofffaserpulvern und Seltene Erden-basierten Füllstoffen für Polyethylen hoher Dichte]
Ayikurt, P.; Kısmet, Y.; Dogan, A.; Höchstötter, K.H.; Fiedler, B.
This study developed alternative fillers to enhance the flowability of high-density polyethylene (HDPE). Lanthanum and cerium oxide with over 90 % purity were used as binder interfacial elements in fillers developed using both carbon fiber powder wastes and powder coating wastes. Polyethylene gel was used to make the fillers thermoplastic and homogenous. A total of six different fillers were developed and melt flow index analyses were performed. As a result of these analyses, it was found that the fluidity of high-density polyethylene improved significantly, especially with fillers containing carbon fiber powder. As a result, high-density polyethylene mixtures containing 10 %, 20 %, 30 %, 40 %, and 50% by weight of carbon fiber powder-based fillers were pressed into molds by a plastic injection molding machine, and samples were produced. According to the mechanical analysis results of these specimens, tensile and flexural strengths decreased slightly depending on the filling ratio, while the impact strengths remained constant. Differential scanning calorimetry analysis was performed to determine the glass transition temperature and melting/crystallization temperatures of the obtained mixtures, while thermogravimetric analysis was performed to determine the mass losses. At the same time, electron microscope analysis of the cross sections of the samples were performed.
- MakaleYalnız künye2025Scopus SJRQ1Dunite powder as a green precursor in one-part alkali-activated composites: Effects on mechanical and durability properties
Benli, Ahmet; Bayraktar, Oğuzhan Yavuz; Karataş, Mehmet; Bodur, Burak; Yılmazoğlu, Mehmet Uğur; Kaplan, Gökhan
Natural pozzolans are a sustainable alternative to Portland cement, offering abundant alumina and reactive silica for geopolymer production. Due to their simple extraction methods, they are cost-effective and environmentally friendly. This study explores the utilization of dunite powder (DP) as a sustainable precursor in one-part alkali-activated slag-based composites (AAC), aiming to evaluate its potential to partially replace granulated blast furnace slag (GBFS). The mechanical, fresh, and durability properties of the composites were investigated by varying DP replacement levels (0%, 15%, 30%, and 60%) under an activator dosage of sodium metasilicate, with the mixtures cured at 80 °C for 24 h and subsequently exposed to ambient conditions. The compressive and flexural strengths were evaluated at 7, 28, and 91 days, while the fresh properties (flowability and setting time), durability under sulfate attack, high-temperature resistance, freeze-thaw resistance, dry shrinkage, sorptivity and microstructural characteristics (SEM, XRD, and FT-IR) were also examined. The compressive strength decreased with higher DP content, with the 60% DP mixture showing a 43% strength reduction at 28 days compared to the reference mixture. However, the 30% DP mixture achieved a favorable balance between strength and sustainability, demonstrating a compressive strength decrease of only 11% at 91 days. The mixture containing 15% DP demonstrated the best performance under high-temperature conditions and freeze-thaw cycles. The 60% DP mixture exhibited the highest mass and strength loss when exposed to temperatures above 400 °C and a 15% compressive strength reduction after 120 days of immersion in a 10% MgSO4 solution.
AtıfScopus29OpenAlex22İncele - MakaleAçık Erişim2025Scopus SJRQ1A new lightweight convolutional neural network model for detecting drivable road regions
Doğan, Gürkan; Uyanık, Hakan; Ergen, Burhan
Nowadays, due to the rapid increase in the number of autonomous vehicles on the market, the safe navigation of these vehicles in drivable road areas has become extremely important. One of the most crucial factors in ensuring safe navigation is addressing the detection of drivable road areas as a task of semantic segmentation. Considering that autonomous vehicles are modular, the algorithm to perform this task must have the optimum trade-off in terms of lightweight, computational complexity, and segmentation accuracy. In this study, RoNet, a new model based on convolutional neural networks that provides an optimum trade-off for the detection of drivable road regions, was designed and proposed. The standard convolution types for the encoder and decoder bottleneck module of the RoNet model, as well as the spatial edge attention mechanism, have been optimized by developing asymmetric convolution types using asymmetric atrous convolution, asymmetric convolution types using Prewitt and Sobel kernels. Spatial edge attention mechanism is designed to reduce the loss of detailed information in small-resolution feature maps. In experimental tests performed with CamVid and FUVid datasets, RoNet achieved a better trade-off in terms of segmentation accuracy, number of parameters, and computational complexity compared to other state-of-the-art methods.
AtıfScopus3WoS3OpenAlex6İncele - MakaleAçık Erişim2024Harç atığı ikameli mikro betonlarda sertleşmiş hal ve mikroyapı değerlendirilmesi
Akgül, Melek; Hansu, Osman
İnşaat yıkıntı atığının sürdürülebilirlik ve geri dönüşüm süreçlerine dahil edilme çalışmaları özellikle yıkım gücü büyük depremler ve kentsel dönüşüm stratejileri sonrası hız kazanmıştır. Bu deneysel çalışmada, İnşaat Harç Atığı (HA)’nın CEM-I 42,5R çimentoya hacimce değişken oranlarda ikame edilmesi ile tasarlanan Mikro Beton (MB)’ların fiziksel, mekanik, durabilite ve mikroyapı özellikleri incelenmiştir. HA çimentoya hacimce %0, %5, 10, 15, 20, 25, 30 oranlarında ikame edilmiştir. Referans setinde kullanılan bağlayıcı miktarı 830 kg/m3’tür. Tüm MB karışımlarında su ve Silis Dumanı (SD) miktarı sabittir ve sırasıyla 400 kg/m3 ve 150 kg/m3 olarak tasarımda kullanılmıştır. 20 ± 2 °C sıcaklıkta kirece doygun su kürü 7 ve 28 gün olmak üzere iki farklı periyotta uygulanmıştır. Ayrıca birer takım numune 28 gün su kürü sonrası 56. ve 90. güne kadar laboratuvar ortamında bekletilmiştir. İlgili deney günlerinde sertleşmiş numuneler ile bir dizi fiziksel, mekanik ve durabilite deneyleri gerçekleştirilmiştir. Mikroyapı analizi değerlendirmeleri 28 günlük su kürü sonrası %0, %15 ve %30 HA ikameli numuneler ve karışımda kullanılan HA’nın X-ışını Difraktometresi (XRD) verilerden sağlanmıştır. Tüm veriler karşılaştırmalı grafikler ile sunulmuştur. Sonuç olarak, %10 HA’nın ikame edildiği 7 ve 28 günlük numunelerde mekanik özellikleri iyileşmesine rağmen, bu oran dahil tüm ikame oranlarında ve sonraki yaşlarda mukavemet kayıpları gözlenmiştir.
AtıfOpenAlex2TR Dizin1
İncele - MakaleAçık Erişim2024Automatic Classification of Defective Photovoltaic Module Cells Based on a Novel CNN-PCA-SVM Deep Hybrid Model in Electroluminescence Images
Imak, Andac
In today’s world, the rapid development of photovoltaic (PV) power plants has facilitated sustainable energy production. Maintenance and defect detection play crucial roles in ensuring the continuity of energy production. The manual inspection of electroluminescence (EL) images of PV modules requires significant human power and time investment. This study presents a method for the automatic fault detection of PV cells in EL images using hybrid deep features optimized with a principal component analysis (PCA) feature selection algorithm. A lightweight and high-performance model that combines the strengths of convolutional neural network (CNN) architectures was proposed. First, data augmentation techniques were employed owing to the imbalance between the defective and functional classes in the dataset containing EL images. In experimental studies conducted by integrating the PCA algorithm into MobileNetV2, DenseNet201, and InceptionV3 CNN models, accuracy, precision, recall, and F1-score values of 92.19%, 92%, 90%, and 91%, respectively, were achieved. When the results were analyzed, it was observed that the proposed method was effective in detecting faults in PV panel cells.
AtıfOpenAlex8TR Dizin2İncele - MakaleAçık Erişim2024Tiyatronun Rönesansı: Pandemi Döneminde Dijitalleşme ve Britanya Tiyatrosu
Şentürk, Gamze
2019 yılında ortaya çıkıp dünyayı etkisi altına alan ve insanları evlerine hapseden pandemi süreci, tiyatro başta olmak üzere sahne sanatları üzerinde benzersiz bir etki yaratarak sahneyi bir dönüşüme uğratmıştır. Bu süreçte sahne sanatları alanında gelişen yeni duruma uygun olarak önlemler alınmaya çalışılmış ve sahne adeta yeniden şekillenmeye başlamıştır. Tiyatroda köklü değişikliklerin olduğu bu dönemde Britanya tiyatrosu da önerdiği yenilikçi ve deneysel uygulamalarla pandemi sürecini yönetmeye çalışmıştır. Kuşkusuz bu noktada teknolojinin sunduğu katkı göz ardı edilemez. Pandemi sürecinde dijitalleşen tiyatro, seyircisine yeni deneyimler yaşatmıştır. Sanatın evrensel gücünün bir kez daha anlaşıldığı bu süreçte teknoloji, biçim, içerik ve uygulama açısından tiyatroyu destekleyici bir unsur olarak ortaya çıkmıştır. Seyircisini oyunla buluşturan ve yenilikçi biçimlerin kullanılmasına büyük olanaklar tanıyan teknolojinin tiyatroda bir dönüşüm yaratması söz konusu olmuştur ve adeta tiyatroda bir rönesans yaşanmıştır. Bu çalışma, Britanya tiyatrosunun pandemi sürecini teknolojinin verdiği imkânlarla nasıl aştığını ortaya koymayı ve pandemi sürecinde tiyatro-teknoloji etkileşimini açığa çıkararak teknoloji çağında tiyatro endüstrisinin geleceğini tartışmayı amaçlamaktadır.
- MakaleAçık Erişim2024İkiz dönüşüm kapsamında kritik hammadde ve teknolojilerinin zaman serileri analizi
Göçmen, Elifcan; Say, Halise Miray; Öner, Mahir
Kritik hammaddeler, sürdürülebilir ekonomi için oldukça önemli ve tedarikleriyle bağlantılı olarak yüksek risk taşıyan hammaddelerdir. Yeşil dönüşüm ve teknolojinin dönüşümünü birleştiren ikiz dönüşümde kullanılan teknolojilerde kritik hammaddelerin kullanımı, bu hammaddelerin önemini ve arz riskini arttırmaktadır. Bu kapsamda, ülkede bu dönüşüme zemin hazırlayan teknolojilerin, uygulamaların ve politikaların incelenmesi ve zaman serileri analiziyle incelenmesi amaçlanmaktadır. Yeşil dönüşüm için ülkemizde önemli potansiyeli bulunan ve kritik hammaddelerin kullanıldığı çoğu teknolojinin de kaynağı olan güneş, rüzgâr, hidrolik, jeotermal, termik enerjinin geçmiş verilerinin analizi ve gelecek projeksiyonu sunulmaktadır. Çalışmada kullanılan zaman serileri analizi yöntemleri, basit hareketli ortalama, ağırlıklı hareketli ortalama ve üstel hareketli ortalama yöntemleridir. Üstel hareketli ortalama, güncel verilere daha fazla ağırlık verdiği için, tahmin başarısı ve hata düzeyleri konusunda daha olumlu sonuçlar vermektedir. Böylelikle, her enerji kaynağının gelecek trendleri, bu enerji kaynaklarıyla bağlantılı teknolojilerde kullanılan hammaddelerin talep düzeyi ve bu hammaddelerin kritikliğini de ortaya koyacaktır.
- MakaleAçık Erişim2024Sentetik Atık Takviyeli Poliolefinlerin Mekanik Özelliklerinin GA-LSTM Hibrit Modeli ile Tahmini
Utku, Anıl; Kismet, Yilmaz; Can, Umit
Bu çalışmada, parçacık takviyeli termoplastiklerin enjeksiyon kalıplamasında kullanılan üretim parametrelerinin ürün kalitesi ve üretilen parçanın mekanik özellikleri üzerindeki etkileri optimize edilmiş bir Genetik Algoritma-Uzun Kısa Süreli Bellek (GA-LSTM) hibrit derin öğrenme yöntemi kullanılarak modellenmiştir. Burada termoplastik olarak poliolefinler grubunun en önemli üyesi olan AYPE, YYPE ve PP kullanılırken takviye elemanı olarak ise toz halde sentetik boya atıkları kullanılmıştır. Farklı parametreler kullanılarak enjeksiyon kalıplama yoluyla 819 numune üretilmiş ve her numune üzerinde mekanik çekme, üç nokta eğme ve izod darbe testleri gerçekleştirilmiştir. GA-LSTM modeli, kullanılan parametreler ve deneysel süreç boyunca elde edilen sonuçlarla eğitilmiş ve tahmin edilen değerlerin gerçek değerlere karşılık geldiği belirlenmiştir. Hibrit GA-LSTM modelinin başarısını ölçmek için iyi bilinen yöntemler kullanılmıştır. Elde edilen sonuçlara göre tasarlanan GA-LSTM modeli en iyi sonuçları üretmiştir.
- MakaleAçık Erişim2024Hybrid ConvLSTM Model for Wind Speed Prediction: A Case Study for India's Highest Wind Speed Cities
Utku, Anıl; Akyol, Sinem
Wind speed prediction is very important for logistics, energy production and renewable energy sources, aviation and maritime, agriculture, disaster management, environmental monitoring, construction, life planning and economic activities. In this study, it was aimed to predict the wind speeds of Jaisalmer, Kochi, Mangalore, Puri and Rameswaram, which are among the cities with the highest wind speeds in India. ConvLSTM hybrid model was developed by taking advantage of the effective features of CNN and LSTM models for wind speed prediction. With ConvLSTM, it is aimed to better determine the dynamics of wind speed by processing spatial and temporal data simultaneously. ConvLSTM has been extensively tested using an approximately 15-year hourly dataset consisting of RF, SVM, ANFIS, CNN and LSTM and wind speed measurements at 10 meters and 100 meters’ altitudes. Experimental results show that ConvLSTM has R2 values above 0.9 for almost all of the city and wind speed parameters, and outperforms the compared models with the lowest error values in terms of RMSE and MAE error metrics.
AtıfOpenAlex1TR Dizin1İncele - MakaleAçık Erişim2024Birleşik Deprem Etkilerinin ve Ek Dışmerkezliğin Betonarme Binaların Davranışına Etkisi
Yön, Burak; Tam, Gürkan
Bu çalışmada birleşik deprem etkilerinin ve ek dışmerkezliğin betonarme binaların davranışına etkisi incelenmiştir. Çalışma kapsamında modellenen betonarme yapının beş zemin sınıfına (ZA, ZB, ZC, ZD ve ZE) göre X ve Y yönlerinde olmak üzere toplam 30 adet doğrusal olmayan statik itme analizleri yapılmıştır. Kolon ve kirişlerin doğrusal olmayan davranışları toplanmış plastik mafsal kabulüne göre, perde duvarların doğrusal olmayan davranışları ise yayılı plastik mafsal kabulüne göre yapılmıştır. Analizler sonucunda birleşik deprem etkileri ve ek dışmerkezlik dikkate alınarak her zemin sınıfı için kapasite eğrileri, her zemin sınıfı için X ve Y yönlerinde en düşük yük faktöründe oluşan plastik mafsal dağılımları, X ve Y yönlerinde ilk mafsalın oluştuğu yük faktörü ve maksimum yük faktörü değerleri elde edilmiştir. Analizler sonucunda zemin sınıfı ZA’dan ZE’ye doğru gidildikçe hem kapasite değerlerinde hem de yük faktörü değerlerinde azalmanın olduğu belirlenmiştir. Bununla birlikte, ek dışmerkezlik ve birleşik deprem etkileri dikkate alındığı zemin sınıfındaki değişime bağlı olarak plastik mafsal dağılımlarının yoğunlaştığı tespit edilmiştir. Sonuç olarak betonarme yapıların tasarımlarında ve performans değerlendirmelerinde zemin sınıflarına ilave olarak birleşik deprem etkilerinin ve ek dışmerkezliğin dikkate alınması gereken önemli parametreler olduğu tespit edilmiştir.
AtıfTR Dizin1İncele - MakaleAçık Erişim2024Evaluating the impact of firm size, firm age, international opportunity recognition, and business network on internationalisation performance
Ataman, Göksel; Platin, Nida
This study examines the cumulative impact of firm size, firm age, business network participation, and international opportunity recognition on the internationalisation performance of small and medium- sized enterprises (SMEs). The study population consists of 160 SMEs in the Kayseri, Inegöl, and Istanbul Organized Furniture Industry area, specifically focusing on those involved in business networks. The data was collected through a survey methodology, and the research objective was assessed using a quantitative approach in SPSS 21. The study aims to examine the gradual impact of variables on internationalisation performance. The stepwise regression in the analysis underscores the crucial impact of firm size and various aspects of international opportunity recognition on internationalisation performance. Notably, the business network's structure positively influences performance, providing optimism for firms seeking to enhance their internationalisation efforts. However, the strength of the tie subdimension of the business network does not impact performance significantly. These findings offer valuable insights for firms aiming to improve their internationalisation efforts.
AtıfOpenAlex1TR Dizin1İncele
