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
- MakaleAçık Erişim2024Effect of Ground Diatomite on Early Strength of Self-Compacting Mortars
Karabulut, Büşra; Yon, Merve Sahin; Karataş, Mehmet
Portland cement fabrication is a significant factor that increases the amount of carbon dioxide released into nature. For this reason, it is very important to use natural and waste materials with pozzolanic properties instead of portland cement. In this article, the usability of diatomite rock, a natural pozzolanic material that can be substituted with portland cement, in the manufacture of self-compacting mortar was studied. In the experimental study, prismatic specimens with dimensions of 40 × 40 × 160 mm were used to examine the impact of ground diatomite on the early age mechanical properties of self-compacting mortar; it was produced by replacing 0%, 5%, 10%, 15%, 20% of diatomite with portland cement, respectively. The slump-flow test to obtain self-compacting mortar was conducted according to the European Federation of Specialized Construction Chemicals and Concrete Systems guidance. Specimens prepared using 0%, 5%, 10%, 15% and 20% diatomite were cured in water at 23±2 ̊C temperature for 3 days. 3-day (early age) flexural and compressive strength worths were gained for the samples whose curing period was completed. As a result of this experimental study, it was specified that the highest strengths were in the series containing 5% diatomite, exceeding the reference samples. Additionally, it has been determined that mechanical strength decreases when the diatomite ratio in mixtures is more than 5%.
AtıfOpenAlex1
İncele - MakaleAçık Erişim2024Hindistan'daki Turistik Şehirlerin İklim Değişkenlerinin Tahminine Yönelik Hibrit ConvGRU Modeli
Utku, Anıl
Hava durumu tahmini tarım, sağlık, ulaşım, turizm, hava kalitesi ve endüstriyel üretim gibi alanlarda etkinliğin ve verimliliğin sağlanabilmesi açısından oldukça önemlidir. Geleneksel hava durumu tahmin modelleri uzun vadeli tahminlerde yetersiz kalmaktadır. Yapay zekâ yöntemleri, sıcaklık, nem, rüzgâr hızı ve hava basıncını gibi hava durumu verileri arasındaki karmaşık ilişkileri öğrenerek geleceğe dönük başarılı tahminler üretebilmektedir. Bu çalışmada, Hindistan'ın önemli turizm şehirlerinden olan Agra, Jaipur, Jodhpur, New Delhi ve Rishikesh'in sıcaklık, nem ve çiğ noktası gibi uzun vadeli iklim değişkenlerinin tahmin edilmesi amaçlanmıştır. Bu amaçla, geliştirilen ConvGRU hibrit modeli, RF, SVM, CNN, LSTM ve GRU modelleriyle kapsamlı bir şekilde karşılaştırılmıştır. 2010-2024 yılları arasına ait gerçek zamanlı ve güncel bir veriseti kullanılmıştır. Deneysel sonuçlar, ConvGRU’nun tüm şehirler ve iklim değişkenleri için 0,9’un üzerinde R2 değeriyle karşılaştırılan modellerden daha başarılı olduğunu göstermiştir.
AtıfOpenAlex3TR Dizin3İncele - MakaleAçık Erişim2024An Exploratory Study on the Application of Blockchain Technology to the Chinese Ship Auction Market
Peng, Chen; Alatas, Bilal
The Chinese ship trading market has undergone remarkable development, transitioning into a global exemplar of ship transactions. Nevertheless, this market continues to confront a series of challenges, encompassing low transaction rates, delayed transaction values, and market instability. Blockchain, with its secure, transparent, and tamper-resistant technological features, presents a potential solution for the ship trading market. Through its decentralized architecture, blockchain technology can reduce platform operational costs, enhancing market competitiveness. Concurrently, the utilization of asymmetric encryption technology can enhance the security of platform data, effectively addressing privacy concerns. Furthermore, through a sharing mechanism, blockchain can aid in establishing a unified credit evaluation system, thereby increasing market trust to address the absence of a credit evaluation system. Moreover, blockchain technology can be employed to construct a risk identification mechanism, fortifying the platform's regulatory model to address regulatory deficiencies.
AtıfWoS1OpenAlex2
İncele - MakaleAçık Erişim2024Scopus SJRQ1Ensemble Learning Framework for DDoS Detection in SDN-Based SCADA Systems
Oyucu, Saadin; Polat, Onur; Türkoğlu, Muammer; Polat, Hüseyin; Aksöz, Ahmet; Ağdaş, Mehmet Tevfik
Supervisory Control and Data Acquisition (SCADA) systems play a crucial role in overseeing and controlling renewable energy sources like solar, wind, hydro, and geothermal resources. Nevertheless, with the expansion of conventional SCADA network infrastructures, there arise significant challenges in managing and scaling due to increased size, complexity, and device diversity. Using Software Defined Networking (SDN) technology in traditional SCADA network infrastructure offers management, scaling and flexibility benefits. However, as the integration of SDN-based SCADA systems with modern technologies such as the Internet of Things, cloud computing, and big data analytics increases, cybersecurity becomes a major concern for these systems. Therefore, cyber-physical energy systems (CPES) should be considered together with all energy systems. One of the most dangerous types of cyber-attacks against SDN-based SCADA systems is Distributed Denial of Service (DDoS) attacks. DDoS attacks disrupt the management of energy resources, causing service interruptions and increasing operational costs. Therefore, the first step to protect against DDoS attacks in SDN-based SCADA systems is to develop an effective intrusion detection system. This paper proposes a Decision Tree-based Ensemble Learning technique to detect DDoS attacks in SDN-based SCADA systems by accurately distinguishing between normal and DDoS attack traffic. For training and testing the ensemble learning models, normal and DDoS attack traffic data are obtained over a specific simulated experimental network topology. Techniques based on feature selection and hyperparameter tuning are used to optimize the performance of the decision tree ensemble models. Experimental results show that feature selection, combination of different decision tree ensemble models, and hyperparameter tuning can lead to a more accurate machine learning model with better performance detecting DDoS attacks against SDN-based SCADA systems.
AtıfScopus36OpenAlex27
İncele - MakaleYalnız künye2024Scopus SJRQ2Stress–strength reliability for electricity systems based on the Bernstein copula approximation
Susam, Selim Orhun; Hudaverdi, Burcu
Electricity is a critical resource for modern society, and its availability is essential for various aspects of daily life, from powering homes to supporting industrial processes and infrastructure. Ensuring a reliable supply of electricity is vital for economic stability and the well-being of a population. As the world moves toward more sustainable and renewable energy sources, understanding the reliability of these sources compared to traditional fossil fuels is crucial. In this study, we develop a methodology that enables the measurement of stress–strength reliability when electricity consumption is considered as the strength variable, positioned between electricity generation from renewable energy sources and fossil fuels as stress variables. We achieve this using the copula-based reliability with Bernstein copula approximation. The methodology is applied to the U.S. monthly electricity data. The result shows that the current rates of electricity output from fossil fuels and renewables will not be sufficient to meet the demand for electricity.
AtıfScopus2WoS3OpenAlex3İncele - MakaleAçık Erişim2024Scopus SJRQ1A new hybrid mobile CNN approach for crosswalk recognition in autonomous vehicles
Doğan, Gürkan; Ergen, Burhan
While automobile transportation is increasing worldwide, it also negatively affects the safety of road users. Along with the neglect of traffic rules, pedestrians account for 22% of all highway traffic deaths. Millions of pedestrians suffer non-fatal injuries from these accidents. Most of these injuries and deaths occur at crosswalks, where the highway and pedestrians intersect. In this study, deep learning-based a new hybrid mobile CNN approaches are proposed to reduce injuries and deaths by automatically recognizing of crosswalks in autonomous vehicles. The first of these proposed approaches is the HMCNet approach, which is a hybrid model in which the MobileNetv3 and MNasNet CNN models are used together. This model achieves approximately 2% more accuracy than the peak performance of the lean used MobileNetv3 and MNasNet models. Another proposed approach is the FHMCNet approach, which increases the success of the HMCNet approach. In the FHMCNet approach, LSVC feature selection method and SVM classification method are used in addition to HMCNet. This approach increased the classification success of HMCNet by more than approximately 2%. Finally, the proposed FHMCNet offered approximately 3% more classification accuracy than state-of-the-art methods in the literature.
AtıfScopus10WoS7OpenAlex8İncele - MakaleYalnız künye2024Scopus SJRQ1Modeling of Optimal Power Generation in Small Hydropower Plants
Kahraman, Gokhan
Small hydropower plants (SHPs) have gained international attention as a reliable and versatile renewable energy source. Unfortunately, this energy source is not used efficiently. This is because these systems utilize headwaters with lower water capacity called forebays instead of large water reservoirs like dams. Since this hinders the control of electricity generation, the headwater is either wasted before it can be converted into electricity or it is exhausted very quickly and electricity generation stops after a short time. The aim of this study is to prevent the loss of electricity generation through the efficient use of SHP headwater. For this purpose, a mathematical model was created based on two SHPs operating in tandem. The mathematical model obtained was analyzed, and forebay water level simulation graphs for electricity generation at water flowrates of 2000, 4000, 6000, and 8000 kg/h were obtained. With the help of the obtained graphs, critical wicket gate openings for maximum electricity generation at flowrates of 2000, 4000, 6000, and 8000 kg/h were calculated. The results of this study are applicable to all SHPs. These results are also promising in terms of optimizing the use of a renewable energy source.
AtıfScopus7WoS6OpenAlex6İncele - MakaleYalnız künye2024Scopus SJRQ2A fuzzy Bayesian network risk assessment model for analyzing the causes of slow-down processes in two-stroke ship main engines
Başhan, Veysi; Yucesan, Melih; Gul, Muhammet; Demirel, Hakan
This paper presents a risk assessment approach for analyzing the causes of malfunction-related main engine slowdowns. A fuzzy Bayesian Network-based methodology is used to assess the factors contributing to the engine’s slow-down processes. The model addresses the complexity and uncertainty inherent in maritime operations with fuzzy sets where numerous interrelated factors can affect engine performance, and the Bayesian network to capture probabilistic dependencies. It considers various potential causes of the slow-down of ship engines that the manufacturer provides. Results demonstrate the model's ability to identify the influential factors leading to engine slow-down events and quantify the overall risk. Integrating fuzzy logic and Bayesian Networks comprehensively assesses relevant risk factors. It enables maritime stakeholders to manage engine performance and improves operational safety proactively. Findings can inform decision-makers, enabling the implementation of targeted maintenance strategies, fuel quality control measures, and crew training programs in the maritime industry.
AtıfScopus19WoS17OpenAlex18İncele - MakaleYalnız künye2024Scopus SJRQ1Assessment of short and long-term pozzolanic activity of natural pozzolans using machine learning approaches
Khatti, Jitendra; Polat, Berivan Yılmazer
This investigation introduces the optimal performance models for predicting the compressive strength (CS) and pozzolanic activity index (PAI) by comparing the machine learning models. The machine learning models, i.e., multilinear regression (MLR), support vector machine (SVM), gaussian process regression (GPR), decision tree (DT), random forest (RF), and gene expression programming (GEP) have been trained (TRN) and tested (TST) by 28 and 7 data points. For the first time, the SiO2, Al2O3, Fe2O3, SiO2 +Al2O3 +Fe2O3, reactive SiO2, Blaine specific surface area, and specific gravity have been used as input variables to compute the CS, and 28 days PAI (28PAI), and 90 days PAI (90PAI) of the natural pozzolans. The multicollinearity analysis showed the SiO2, Al2O3, Fe2O3, SiO2 +Al2O3 +Fe2O3, reactive SiO2, and specific gravity have problematic multicollinearity (variance inflation factor – VIF > 10). Therefore, the root mean square error (RMSE), mean absolute error (MAE), correlation coefficient (R), performance index (PI), and variance accounted for (VAF) metrics have been implemented to evaluate the model's performance and multicollinearity impact. From the comparison of models, it has been recorded that model GPR outperformed the MLR, SVM, DT, RF, and GEP models in predicting CS (PI = 1.29, VAF = 71.31, R = 0.8473, MAE = 0.9390 MPa), 28PAI (PI = 1.87, VAF = 94.88, R = 0.9744, MAE = 0.7295 %), and 90PAI (PI = 1.72, VAF = 88.11, R = 0.9393, MAE = 1.2444 %) in the TST phase, close to ideal values. The score, generalizability. Wilcoxon test, uncertainty analysis, Anderson-daring test, and accuracy metrics have confirmed the superiority of GPR models in predicting CS, 28PAI, and 90PAI of natural pozzolans.
AtıfScopus28WoS25OpenAlex28İncele - MakaleYalnız künye2024Scopus SJRQ3Powder coating waste filler in high-density polyethylene – Variations in morphology, mechanical and thermal performance; [Variationen in Morphologie, mechanischer und thermischer Leistung von Pulverlackrecyclaten als Füllstoff in Polyethylen mit hoher Dichte]
Kısmet, Y.
In the present study, electrostatic powder coating waste was recycled and employed to reinforce high-density polyethylene. The hydrolysis method was preferred to modify the powder coating waste of various systems, and they were mixed with high-density polyethylene at various weight ratios. The mixtures were prepared in a mechanical mixer and then in an extruder to obtain a homogeneous mixture. This homogeneous structure was pressed into molds with a plastic injection device to obtain standard tensile samples. Mechanical and thermal tests were conducted on the samples. It was determined that the tensile stress of the sample decreased with the increase in filler content. The changes in sample tensile strength were investigated after the samples were aged. Three-point bending strength of the samples was also investigated and it was observed that they became more resistant to vertical loads as the filler content increased. The Izod impact strength of the samples differed based on the filler type and weight ratio. Furthermore, mass loss in the produced mixtures was determined with thermogravimetric analysis. The matrix and filler bonding mechanisms were observed under an electron microscope.
AtıfScopus1WoS1OpenAlex1İncele - MakaleYalnız künye2024Scopus SJRQ1A comprehensive risk assessment framework for mooring risks at hydrocarbon berths using fuzzy rule-based Bayesian network and multi-attribute decision-making
Demirel, Hakan; Başhan, Veysi; Yucesan, Melih; Gul, Muhammet
Mooring operations -especially at hydrocarbon berths- are critical components of the marine and offshore industry. They usually involve securing the berths of ships carrying valuable cargo and ensuring the safety of personnel, assets, and the environment. For this purpose, a comprehensive risk assessment framework for mooring operations at hydrocarbon berths is proposed in this study. This framework helps evaluate risks using a rule-based Bayesian network. In the assessment of mooring risks, four risk parameters of severity, occurrence, detection, and maintenance are considered to construct the BN structure of each mooring risk. These parameters are weighted with the aid of the fuzzy Best Worst Method. Hereafter, a fuzzy rule-based system is constructed by incorporating BN to determine a risk priority score. The framework also develops mitigation strategies to maintain effective risk management for safe and secure maritime transportation. Sensitivity analyzes and comparison studies were conducted to test the validity of the proposed comprehensive risk management framework. The study reveals that the most critical risk is associated with Technical Failures (Q1) in the cluster pertaining to the automation of Quick Release Hooks. This risk stems from technical malfunctions in automation systems, encompassing sensors and control mechanisms, potentially resulting in the unintended release of mooring lines. The second highest priority risk is linked to Human Error (M1) in the mooring risks cluster, attributed to human errors such as inadequate training, miscommunication, and procedural mistakes during mooring operations, posing risks of accidents and damage to ships and infrastructure. Conversely, the least significant risk, Redundancy (Q5), focuses on redundancy. This risk is associated with automation and underscores the importance of implementing redundancy mechanisms to ensure the safe continuation of mooring operations in the face of system failures. In conclusion, the proposed comprehensive risk assessment framework offers a systematic approach to evaluate and prioritize mooring risks at hydrocarbon berths. The study’s findings emphasize the critical importance of addressing technical malfunctions in the automation of Quick Release Hooks and human errors during mooring operations. By identifying the most significant risks and developing mitigation strategies, this framework contributes to enhancing the safety and security of maritime transportation, particularly in the context of hydrocarbon berths.
AtıfScopus11WoS11OpenAlex13İncele - MakaleAçık Erişim2024Scopus SJRQ4Comparative And Dynamic Analysis of Türkiye's Competitiveness in Unmanned Aerial Vehicles; [İnsansız Hava Araçlarında Türkiye’nin Rekabet Gücünün Karşılaştırmalı ve Dinamik Analizi]
Aydin, Üzeyir; Ateş, Erdem; Öztürk, Hasan
The study aims to determine the competitiveness of Türkiye’s UAV exports in a dynamic framework. The analysis used data from the first 20 countries with the largest share in the production and trade of products designated as UAVs by the Harmonic System six-digit and by the European Commission for 2012-2021. Within the scope of the study, it is determined that some countries have high competitiveness in 4 product groups examined with five different foreign trade indexes. It is concluded that Türkiye has strategic and dynamic superiority in two of the four product groups.
AtıfOpenAlex2TR Dizin1İncele - MakaleYalnız künye2024Scopus SJRQ2Dynamic Analysis and Metallographic Examination of Linings with Different Composite Contents used in the Brakes of a Hydraulic Turbine
Işık, Erdem; Kahraman, Gökhan
The main aim of this study was to find ways to increase the performance and life of generator brake linings, which can lead to cost reduction and adequate downtime periods for hydroelectric power plants. First, the dynamic analysis of the linings used in hydraulic turbines was realized and their reactions were examined under different operating conditions. Second, two types of brake linings with different composite components produced in the market were examined metallographically and tested to determine both the stopping performance and durability time of the turbine-generator unit for a sufficient period of time in the vertical 150-megawatt Francis turbine with approximately 500 tons of rotary weight. As a result of these experiments, the lining with the boron component led to much better results than the other brake linings. It has been determined that the boron-containing lining makes 100 stops more than the other lining and stops 20 s earlier in one stop. Therefore, the use of a composite lining with boron content in the braking systems of hydroelectric power plants significantly reduces maintenance incidents and operation costs as it prolongs brake replacement periods in these plants. Graphical Abstract: (Figure presented.)
AtıfScopus1WoS1OpenAlex1İncele - Kitap BölümüYalnız künye2024Assessment of critical raw materials by addressing sustainable development goals using fuzzy MCDM approach
Göçmen-Polat, Elifcan
Critical raw materials (CRMs), constituting the first step of the industry, are vital to meet sustainable development. With increasing digital technology and green transition efforts under the scope of twin transformation, demand for CRMs has increased, and supply interruption is expected in the future. All countries should plan the supply chain of CRMs in the context of the green and digital transition. The sustainable development goals (SDGs) have presented a reference based on sustainability metrics. In the chapter, hesitant-fuzzy analytical hierarchy process-based order preference technique based on similarity to ideal solutions (HF-AHP based TOPSIS) has been developed to evaluate the critical raw materials in the context of sustainability. Most relevant goals with the CRMs are obtained as SDG 1, SDG 3, SDG 5, SDG 6, SDG 7, SDG 8, SDG 9, SDG 11, SDG 17. The findings show how raw materials have important strengths and weaknesses in sustainable development. Policies recommended for the most important CRMs are effective road maps in the context of twin transformation.
AtıfScopus4OpenAlex6İncele - BildiriYalnız künye2024An Analysis of Dependence Relationships Between Covid-19 Pandemic and Environmental Conditions Cases Study in Indonesia, England, and Türkiye
Handhayani, Teny; Caglar, Durdane Kocacoban; Wibowo, F.W.
This study explores the causal relationships between environmental conditions and Coronavirus disease 2019 (COVID-19) using Bayesian networks in three geographically distinct cities: Jakarta (Indonesia), London (England), and Istanbul (Türkiye). The datasets collected from these cities span from January 2020 to October 2022, encompassing a variety of environmental variables (Particulate Matter (PM2.5), temperature, humidity, precipitation, wind speed, and Ultraviolet (UV) index) and COVID-19 variables (new cases, deaths, and population density). By using the PC algorithm and Greedy Equivalence Search (GES) to generate causal graphs, and applying the Intersection-Validation (InterVal) method to derive agreement graphs, this research reveals significant geographical differences in how environmental factors influence COVID-19 dynamics. The Peter-Clark (PC) algorithm identifies conditional dependencies, while GES optimizes the structure of the causal graph. The study highlights the significant impact of temperature, UV index, and humidity on COVID-19 dynamics, emphasizing the importance of localized public health strategies tailored to specific environmental conditions. These findings contribute to the understanding of environmental influences on COVID-19 and offer valuable insights for future research and policy-making aimed at mitigating the impact of pandemics in diverse geographical settings.
AtıfScopus3OpenAlex2İncele - MakaleYayıncıda açık erişim2024Scopus SJRQ3Fastener and rail surface defects detection with deep learning techniques
Yilmazer, Merve; Karakose, Mehmet
The railways, which are frequently used by countries for both passenger and freight transportation, should be checked periodically. Controls made with classical methods are slow and there are often overlooked faults. This work suggests a novel deep learning-based technique for identifying fastener and railway track surface defects. Within the scope of the proposed method, firstly, the railroad track was observed using an autonomous drone. Shaky images in the recorded video were removed with a video stabilization algorithm. Frames were created and labeled from the video, and rail and fastener regions were detected using the Faster R-CNN deep neural network. Fault detection was performed through ResNet101v2-based classification using different datasets for identifying surface detects in rails and different datasets for the detection of fasteners. The proposed method was experimentally shown to have a 98% accuracy rate for detecting rail surface flaws and a 95% accuracy rate for detecting fastener flaws. A user interface was developed to display the identified faulty images on computers, tablets, and mobile phones via a mobile application. The system, which was previously proposed in a different study, was retrained by going through the video stabilization step, thus improving the fault detection rate, and the method was also included in the user interface module. This study contributes to the processing of ever-increasing video data with deep learning-based methods. It is also anticipated that it will benefit researchers working in the field of railway non-contact fault detection.
AtıfScopus6OpenAlex6İncele - MakaleAçık Erişim2024Scopus SJRQ1Effect of White-Portland cement containing micro and nano silica on the mechanical and freeze-thaw properties of self compacting mortars
Etli, Serkan; Yılmaz, Tekin; Hansu, Osman
This study concentrated to investigate the influences of white-Portland cement (W-PC) containing silica fume (SF: micro-silica (µSi) and nano-silica (nSi)) as replacement (2–4 wt%) on mechanical (strength and durability), physical and microstructural behaviors of self-compacting mortars (SCMs) fabricated at 0.48–0.63 w/b ratios. In keeping with these purposes, besides of carrying out the workability (mini-slump flow: M−SF and V-funnel: V-F) experiments of SCMs, the mechanical and microstructural tests implemented were: unconfined compressive strength (UCS), flexural strength (FS), freeze–thaw (F-T) and scanning electron microscope (SEM) analysis. The outcomes displayed that, in comparison with the control, replacing W-PC by SF (particularly nSi) enhanced the UCS and FS, resisted against F-T durability by lowering the strength losses in UCS and FS. The ameliorated microstructure resulting in a reduction in the number and/or a narrowing in the size of micro-cracks and pores contributed to generate a more compact and consolidated SCM structure for the improving of strength and durability due of pore-filling effect and superior pozzolanic characteristics of µSi and especially nSi, this in turn reduced the permeability of SCM, which has a significant effect on the strength and durability behaviors of the SCM.
AtıfScopus16WoS16OpenAlex19İncele - MakaleAçık Erişim2024Scopus SJRQ2Development of rare earth element and carbon fiber-based filler for polyethylene—Mechanical and thermal performance
Kısmet, Yılmaz; Ayikurt, Pamuk
In the present study, three fillers produced with carbon fiber powder (CFP) and rare earth elements were developed for low-density polyethylene production. These fillers included CFP with a grain size of less than 400 microns and over 90% pure lanthanum and cerium oxides. Polyethylene was employed to ensure the thermoplasticity and homogeneity of the fillers. The fillers were mixed with the matrix material separately, first mechanically and then homogenously in the extruder, then the test bars were produced with an injection machine. In the mechanical tests, it was determined that the tensile strength of the test bars improved by ~20% and the elastic region increased due to the increasing amount of filler. Similarly, an improvement of about 40% in bending stress was realized. In addition, as the fluidity of the mixtures has improved, it has been possible to produce at lower temperatures and save energy in the production. Thermogravimetric analysis was conducted to determine the melting/crystallization temperatures and material losses in the compounds. The scanning electron microscope analysis showed that the fillers were irregularly distributed on the surface in parallel and perpendicular directions. In addition, x-ray diffraction and energy dispersive spectroscopy analyses were performed on the surfaces.
AtıfScopus1WoS1OpenAlex1İncele - BildiriAçık Erişim2024Classifying induction motor faults using spectrogram images with deep transfer learning
Ertargin, Merve; Yildirim, Ozal; Orhan, Ahmet; Benedicenti, L.
For industrial systems to be reliable and efficient, motor faults detection is important. Conventional methods of fault detection are typically expensive and time-consuming. The ability to detection motor faults has advanced significantly in recent years thanks to the application of deep learning techniques. Deep learning algorithms have the ability to automatically extract complicated features from big data sets, which can speed up and improve the accuracy of motor faults detection. Since collecting motor acoustic data is cost-effective and easy, it is advantageous to use it in fault detection. In this study, motor acoustic signals were converted into spectrograms and faults in induction motors were detected using a transfer learning approach with pre-trained models. Totally 8-class fault detection was performed with an accuracy rate of 91.52% using VGG16 and 92.11% using VGG19.
AtıfScopus4OpenAlex4İncele - MakaleYalnız künye2024Scopus SJRQ1Investigation of the variation of mechanical and durability properties of elements manufactured with rubber substituted SCMs with element height
Akgül, Melek; Etli, Serkan
Controlling the homogeneous distribution of granulated rubber materials added to self-compacting concrete/mortars along the height is of great importance in terms of preserving and defining the holistic behavior of structural elements. In this study, the effect of EPDMGR (ethylene propylene diene monomer granulated rubber) ratio (0 %, 5 %, 10 %, 15 %, 20 % and 25 %), test age, L/D (slenderness ratio) and element test zone (bottom, middle and top) on the mechanical properties (flexural and compressive), durability properties (porosity and sorptivity) of the elements produced with SCM were evaluated. The results obtained were statistically evaluated by GLM-ANOVA. It was observed that flexural tensile strength was strengthened up to 5 % substitution rate due to the hydrophobic properties and elasticity properties of EPDMGR used, while porosity values increased with height in the upper regions compared to the lower regions due to the placement properties of SCM. Differences in compressive strength appeared in the upper and lower sections after 5 % EPDMGR substitution. This indicates that for the mixture properties used, the properties examined in terms of mechanical and durability test results may have different properties with limited variability in terms of L/D ratio depending on the EPDMGR ratio used and the region where the element was taken.
AtıfScopus7WoS7OpenAlex10İncele
