Yayınlar
Koleksiyondaki öğeler
- MakaleYalnız künye2024Scopus SJRQ1A stratified Bayesian decision-making model for occupational risk assessment of production facilities
Gul, Muhammet; Yucesan, Melih; Karci, Coskun
In the production industry, harmony and good management of the workplace environment, production machinery/vehicles, and workers are necessary to carry out production by occupational health and safety (OHS) principles. Therefore, occupational risk assessment (ORA) is crucial for manufacturing-based industries. When deciding on the prioritization of risks in ORA, adding to the analysis “how the parameters defining the risk changes in possible different states in the future” positively affects the soundness of decision-making. Therefore, this study aims to develop a unique ORA model handling future changes in the importance levels of risk parameters in the risk assessment process. To this aim, the concept of stratification and the best-worst method (BWM) are used together to determine the importance weights of the risk parameters in the ORA. In addition, the Bayesian version of BWM considers more than one expert's evaluations without losing information. In a nutshell, an approach called stratified Bayesian BWM (SBBWM) that can be used for further studies has been introduced to the literature. The technique determines the priority scores of each hazard by technique for order preference by similarity to the ideal solution sorting (TOPSIS-Sort) method. Thus, while determining each hazard's priority score and order, the class of this risk has also been determined. The proposed approach evaluated thirty-six risks encountered in manufacturing, storage, handling, and laboratory processes of a flour production facility. Control measures to be taken for each risk were also determined. Methodologically, various scenario analyses and sensitivity studies were conducted to reveal how the results changed in different conditions. The proposed approach provides a more comprehensive procedure for production facilities than traditional methods and avoids the deficiencies of traditional methods.
AtıfScopus18WoS16OpenAlex18
İncele - MakaleYalnız künye2024Scopus SJRQ1A closer-look on W and Pb alloys: In-depth evaluation in elastic modulus, gamma-ray, and neutron attenuation for critical applications
ALMisned, Ghada; Susoy, Gulfem; Sen Baykal, Duygu; Alkarrani, Hessa; Güler, Ömer; Tekin, H.O.
This investigation assesses the gamma-ray and neutron attenuation properties of various alloys, including Pb90Cu10, A5, Manganin-R, Cu0.2Ag0.8, SA4, and W-based, to uncover efficient and cost-effective radiation shielding materials. Our study centers on alloys featuring elements such as lead, molybdenum, silver, and tungsten, selected for their unique protective qualities against radiation. Employing computational methods to evaluate critical parameters like mass attenuation coefficients, half-value layers, linear attenuation coefficients, and effective atomic numbers, transmission factor, we found the W-based alloy to exhibit exceptional shielding properties, primarily due to its tungsten content. Interestingly, this alloy also demonstrated the highest elastic modulus among the samples studied, indicating a potential synergy between an alloy's mechanical strength and its radiation shielding effectiveness. It can be concluded that alloys with higher elastic moduli not only offer better resistance to radiation-induced deformations, enhancing shielding, but also underscore the need for further research on alloys that balance performance, affordability, and environmental impact. The findings underscore the dual importance of composition and mechanical properties in advancing radiological safety and suggest continued investigation into the sustainability and practicality of effective shielding materials.
AtıfScopus28OpenAlex31İncele - MakaleAçık Erişim2024Scopus SJRQ1The Mediating Effect of Experiential Avoidance on the relationship between psychological resilience and psychological needs in the COVID-19 pandemic
Dursun, Asiye; Kaplan, Yılmaz; Altunbaş, Tuğçe; Bahtiyar, Muhammed
The COVID-19 pandemic that has impinged upon the world affects individuals not only physically but also psychologically. Considering the effects of the pandemic that can be called a challenging life event, the concept of psychological resilience comes to mind. In this study, the effect of multidimensional avoidance on the relationship between psychological resilience and psychological need satisfaction-frustration of adults is discussed through structural equation modeling. The study data were collected online from 506 adults who participated voluntarily from 7 different geographical regions of Turkey. The study findings were obtained by using correlation analysis, structural equation modeling, and path analysis. As a result of the study, it is seen that all the variables of multidimensional avoidance except distraction/suppression and frustration directly affect psychological resilience in satisfaction and frustration of basic psychological needs. In addition, it shows that psychological resilience has a significant effect on satisfaction and frustration of basic psychological needs, both directly and indirectly through multidimensional avoidance.
AtıfScopus13WoS15OpenAlex13
İncele - MakaleYalnız künye2024Scopus SJRQ2Combating with COPD by QiGong Physical and Mental Exercise
Kaplan Serin, Emine
Physical activity levels of patients with chronic obstructive pulmonary disease (COPD) are low due to the symptoms of COPD. The patients diagnosed with COPD are headed for complementary and alternative treatments to reduce the COPD symptoms, facilitate the treatment, and increase their physical activity. One of these treatments is QiGong, which is not yet common in our country. QiGong is a type of exercise based on ancient Chinese medicine, and mainly consists of active and passive exercises. These exercises open energy channels in the body, and thus prevent and/or heal diseases by establishing energy balance in the body through meditation, breath control, and bodily exercises. According to a literature review abroad, there are a small number of scientific studies related the therapeutic effect of QiGong exercises on symptom control, anxiety, reduction of stress and depression, increase in physical activity and quality of life, and the development of lung function of patients with COPD. By considering the educative role of nurses, it is important that the nurse has adequate knowledge of the treatment and care of patients with COPD. Therefore, this review is compiled to be informative about the effects of QiGong in the treatment of COPD, and assistance to subsequent studies.
AtıfScopus4WoS4İncele - MakaleYalnız künye2024Scopus SJRQ3On the Construction of a Semiparametric Family of Bivariate Copulas Using the Opposite Diagonal Section of Copulas
Susam, Selim Orhun; Chesneau, Christophe
In this article, a new semiparametric family of bivariate copulas is proposed and studied. The copulas of this family innovate in their construction; they are based on an original univariate generating function involving the opposite diagonal section of intermediary copulas. Several of their crucial properties are examined. In the practical part, we use them to estimate the reliability parameter in a stress-strength-dependent setting, including an estimation approach based on the Bernstein copula. Finally, their applicability and good performance are confirmed using a data set related to the logarithmic concentrations of two chemical elements in water samples.
AtıfScopus1WoS1OpenAlex1İncele - MakaleAçık Erişim2023Scopus SJRQ2Shape Memory Polymer-Based Nanocomposites Magnetically Enhanced with Fe3O4 Nanoparticles
Pekdemir, Mustafa Ersin; Aydin, Derya; Selçuk Pekdemir, Sibel; Erecevit Sönmez, Pınar; Aksoy, Edanur
This work aimed to investigate the effect of magnetic Fe3O4 nanoparticles (MNP), which are known to have a wide range of applications in recent years, on nanocomposite films prepared with shape memory polymers. Herein, PLA–PEG blend nanocomposite films were prepared by solution casting method using MNP at different ratios. PLA–PEG Blend/MNP nanocomposite films were characterized with Attenuated total reflection infrared spectroscopy (ATR-IR) to determine the –C=O stretching of PLA and Fe–O stretching signals of Fe3O4. The thermal stability, morphology, and magnetic behavior were studied by comparing the results among PLA–PEG blend, PLA–PEG blend/MNP nanocomposite with thermogravimetric analyses (TGA), differential scanning calorimetry (DSC), scanning electron microscopy (SEM), and a vibrating sample magnetometer (VSM), respectively. The effect of MNP on the shape memory properties of PLA/PEG blend was investigated. Moreover, the comparison of antimicrobial activity between PLA/PEG blend and PLA–PEG blend/MNP nanocomposite films were conducted by the disk diffusion method. The results showed that MNP increased the thermal stability of the PLA/PEG blend and the nanocomposites inhibited the growth of C.albicans microorganism. Graphical Abstract: [Figure not available: see fulltext.].
AtıfScopus41WoS39OpenAlex42İncele - MakaleAçık Erişim2025Scopus SJRQ2Forecasting daily natural gas consumption with regression, time series and machine learning based methods
Yucesan, Melih; Pekel, Engin; Celik, Erkan; Gul, Muhammet; Serin, Faruk
An effective short-term natural gas forecasting method contributes to social contributions and allows industrial chain elements to function effectively and minimize economic losses. We dealt with a comparative framework on the applicability of different methods in daily natural gas service (NGS) consumption forecasting. In this context, time series, machine learning, evolutionary and population-based approaches, and their hybrid versions are applied to the NGS data. Hybridized approaches are tested in the scope of NGS consumption forecasting for the first time in the literature in this study. The case of Turkey is handled, and its NGS data is used to demonstrate the comparative framework’s applicability. The comparative study is assessed in the lights of common forecasting accuracy measures of mean absolute percentage error (MAPE), R-squared (R2), and mean squared error (MSE). According to each method’s results, the seasonal autoregressive integrated moving average with exogenous regressors (SARIMAX) and artificial neural network (ANN) hybrid model provides the most dominant performance with respect to MAPE. The lowest error was obtained with a MAPE value of 0.357 in this hybrid model constructed under seven neurons in its ANN structure. This model is followed by another hybrid model, autoregressive integrated moving average (ARIMA)-ANN, with a MAPE value of 0.5 under nine neurons in terms of accuracy performance. The worst performance value belongs to the Genetic algorithm-ANN hybrid model with a MAPE value of approximately 26%.
AtıfScopus16WoS19OpenAlex22İncele - Kitap BölümüYalnız künye2024Digital marketing and customer experience strategy: Leveraging digital channels for marketing and customer engagement
Cevher, Muhammed Fatih
This study examines the importance of using digital channels in increasing marketing and customer loyalty by addressing digital marketing and customer experience strategies. The rapid development of the digital age obliges businesses to focus on digital marketing methods and develop strategies to improve customer experience. In the introduction part of the study, digital marketing and customer experience issues are briefly mentioned, and the current situation analysis is made. After the introduction, the previous studies on the subject are examined under the title of a literature review. Then, it explains the concept of digital marketing and explains some digital marketing strategies. In the next stage, the customer journey and customer experience were examined and then focused on the digital customer experience. In the last part of the study, the digital marketing and customer experience strategy has been summarized, and the importance of digital channels in customer loyalty has been pointed out.
AtıfScopus7İncele - MakaleAçık Erişim2024Scopus SJRQ1Determination of oxidative stress responses caused by aluminum oxide (γ-Al2O3 and α-Al2O3) nanoparticles in Gammarus pulex
Serdar, Osman; Aydin, Ayşe Nur; Çimen, Isıl Canan Çiçek
The rapid growth in the use of aluminum oxide nanoparticles (Al2O3 NPs) in various fields such as medicine, pharmacy, cosmetics industries and engineering, and the fact that these NPs and their wastes mix with the aquatic environment and damage the aquatic ecosystem, affect the organisms in the water, enter the food chain and reach humans is a major problem is cause for concern. The aim of this study is to investigate the oxidative stress caused by two separate forms of aluminum oxide, γ-Al2O3 and α-Al2O3, in Gammarus pulex, which is a good indicator species, with biochemical parameters. For this purpose, G. pulex was exposed to different concentrations (0, 10, 20, 40 ppm) of γ-Al2O3 and α-Al2O3 separately. The experiments were carried out for 24 and 96 h by creating 3 repeated experimental groups consisting of 4 groups. For biomarker analysis, superoxide dismutase (SOD), catalase (CAT) activities and glutathione (GSH) and thiobarbituric acid (TBARS) levels were performed using an ELISA kit. As a result of the in experimental study, it was observed that both nanoparticles affected oxidative stress and antioxidant parameters after 96 h compared to the control group. Increases in SOD activity were observed, γ-Al2O3 caused a decrease in CAT activity at 24 h, and α- Al2O3 caused increases in CAT activity at 96 h. Decreases in GSH levels and increases in TBARS levels have been observed.
AtıfScopus14OpenAlex14İncele - MakaleAçık Erişim2024Scopus SJRQ1Assessment of toxicity and oxidative stress induced by rare earth oxide nanoparticles in brine shrimp (Artemia salina)
Unal, Ilkay; Erturk Gurkan, Selin; Aydogdu, Burcu
This study meticulously explored the oxidative stress effects induced by lanthanum (III) oxide (La2O3), erbium (III) oxide (Er2O3), and yttrium (III) oxide (Y2O3) nanoparticles on Artemia salina, with the objective of evaluating the environmental toxicity of rare earth oxide nanoparticles. The characterization of the nanoparticles was conducted using a suite of advanced techniques, including X-ray diffraction (XRD), Fourier transform infrared spectroscopy (FTIR), transmission electron microscopy (TEM), dynamic light scattering (DLS), and zeta potential analysis. Artemia salina, a widely recognized model organism in ecotoxicological research, was exposed to these nanoparticles under meticulously controlled laboratory conditions. The investigation focused on quantifying oxidative stress markers, such as reduced glutathione (GSH), malondialdehyde (MDA), and antioxidant enzymes including catalase (CAT), superoxide dismutase (SOD), and glutathione-S-transferase (GST). The findings revealed significant alterations in these biomarkers, indicating nanoparticle-induced oxidative stress, which varied according to the type of nanoparticle and the duration of exposure.
AtıfScopus9OpenAlex9İncele - MakaleAçık Erişim2024Scopus SJRQ4Effect of Sperm Extender and Dilution Ratio on the Sperm Motility, Fertility, and Hatching Rates of Depik Fish Rasbora Tawarensis (Pisces: Cyprinidae) Eggs
Muchlisin, Zainal Abidin; Aldila, Dhea Febby; Sarah, Putri Inten; Eriani, Kartini; Hasri, Iwan; Fadli, Nur; Muhammadar, Abdullah Abbas; Handayani, Luvi Syafrida; Maulida, Siti; Siti-Azizah, Mohd Nor
There is no known artificial breeding method for depik fish Rasbora tawarensis. Sperm extender and the dilution ratio are crucial factors in the artificial breeding of fish. The current study aimed to assess the effect of several common fish sperm extenders and its dilution ratio on sperm characteristics and fertilization of depik fish eggs. Two series of experiments were performed to find the best extender and its dilution ratio. In the first experiment, five types of extenders were tested: Ringer's solution, physiological solution, coconut water, sugarcane water, and roomie water. The second experiment studied four dilution levels of sperm and extender (v/v): 1:20, 1:30, 1:40, and 1:50. Every treatment was conducted in four replicates and the experiments were conducted consequently so that the findings in the first experiment were applied in the second. The first experiment showed that Ringer's is the best extender for depik sperm with sperm motility, fertilization and hatching rates of 71.00%, 69.30%, and 53.66%, respectively; and the second experiment revealed that Ringer's at dilution ratio 1:40 gave higher sperm motility, fertilization, and hatching rates of 74.66, 70.33, and 59.00%, respectively. In conclusion, Ringer's solution was the most favorable extender for sperm which yielded best fertilization results at 1:40 dilution ratio (sperm:extender, v/v) in depik fish.
AtıfScopus1WoS1OpenAlex1İncele - MakaleAçık Erişim2023Scopus SJRQ1DEEP LEARNING BASED AN EFFICIENT HYBRID PREDICTION MODEL FOR COVID-19 CROSS-COUNTRY SPREAD AMONG E7 AND G7 COUNTRIES
Utku, Anil
The COVID-19 pandemic has caused the death of many people around the world and has also caused economic problems for all countries in the world. In the literature, there are many studies to analyze and predict the spread of COVID-19 in cities and countries. However, there is no study to predict and analyze the cross-country spread in the world. In this study, a deep learning based hybrid model was developed to predict and analysis of COVID-19 cross-country spread and a case study was carried out for Emerging Seven (E7) and Group of Seven (G7) countries. It is aimed to reduce the workload of healthcare professionals and to make health plans by predicting the daily number of COVID-19 cases and deaths. Developed model was tested extensively using Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE) and R Squared (R2). The experimental results showed that the developed model was more successful to predict and analysis of COVID-19 cross-country spread in E7 and G7 countries than Linear Regression (LR), Random Forest (RF), Support Vector Machine (SVM), Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM). The developed model has R2 value close to 0.9 in predicting the number of daily cases and deaths in the majority of E7 and G7 countries.
AtıfScopus9OpenAlex11İncele - MakaleYalnız künye2024Scopus SJRQ2New national and regional bryophyte records, 79
Ellis, L.T.; Alataş, M.; Ali, Sk. N.; Alvarez, D.J.; Aponte Rojas, A.M.; Atwood, J.J.; Batan, N.; Bednarek-Ochyra, H.; Cano, M.J.; Cimerman, Ž. L.
AtıfScopus6OpenAlex6İncele - MakaleAçık Erişim2024Scopus SJRQ1Evaluation of antioxidant, antimicrobial, and bioactive properties and peptide sequence composition of Malatya apricot kernels
Aydın, Çağlar Mert; Çelikbıçak, Ömür; Hayaloğlu, Ali Adnan
BACKGROUND: This study used four different apricot (Prunus armeniaca) kernels cultivated in Malatya during two consecutive years. The varieties were Hacihaliloglu, Hasanbey, Kabaasi, and Zerdali. The physicochemical properties of the kernels were determined, and the bioactive content of the kernels was evaluated using kernel hydrolysates prepared using trypsin. RESULTS: With regard to the physicochemical properties of the kernels, the dry matter ratio and protein content were the highest in the Hacihaliloglu variety; the ash ratio was the highest in the Kabaasi variety, and the free oil ratio was the highest in the Hasanbey variety. The bioactive compound content changed according to kernel variety. Angiotensin-converting enzyme inhibitors activity was found to be the highest in the Hacihaliloglu and Hasanbey varieties, which had the lowest amygdalin content, and Zerdali had the highest amygdalin content. The antioxidant and antimicrobial effects of the kernels varied, with Hasanbey and Kabaasi generally having the highest content in both analyses. Moreover, a concentration of 20 mg mL−1 of the hydrolysate was determined to have a destructive effect for the microorganisms used in this study. The storage protein of the kernels, except Hacihaliloglu, was found to be Prunin 1, with the longest matching protein chain in the kernels being R.QQQGGQLMANGLEETFCSLRLK.E. CONCLUSION: The results suggest that the peptide sequences identified in the kernels could have antihypertensive, antioxidative, and Dipeptidyl peptidase IV (DPP-IV) inhibitory effects. Consequently, apricot kernels show potential for use in the production of functional food products. Of the kernels evaluated in this study, Hacihaliloglu and Hasanbey were deemed the most suitable varieties due to their higher bioactive content and lower amygdalin content.
AtıfScopus13WoS11OpenAlex12İncele - MakaleYalnız künye2025Scopus SJRQ4Bioaccumulation of copper by Gammarus pulex (L., 1758): monitoring through a statistical modelling approach
Pala, Aysegul; Ince, Muharrem; Serdar, Osman
The aim of this study is to test freshwater gammarids as ecotoxicological biomarkers. Gammarids were collected from fresh water and adapted to the laboratory environment. Then, the influence of various variables was investigated. For monitoring and detecting the bioaccumulation level in Gammarus pulex exposed to controlled copper ions and to evaluate potential human and ecological risks, the use of G. pulex as sentinel indicators of water quality is one rational approach. Copper bioaccumulation rate and fate are currently not sufficiently studied. For optimization, the experimental conditions to ensure bioaccumulation level and to find the effects of various variables on proses, a Box–Behnken experimental design was performed. Used mentioned model with statistical underpinnings for Cu2+ ions bioaccumulation have been analyzed, tested and verified and the viability of G. pulex as a biomonitor. The variables’ optimum levels (temperature; 18.1, pH; 4.3, initial concentration of Cu2+ ions, mg L−1; 11.2 and exposure time, h; 42.2) were achieved by employing the quadratic regression model. Critical role of G. pulex in freshwater biomonitoring and their potential to be evaluated as biomarkers for Cu2+ ions was confirmed. It was also explored to see if G. pulex may serve as a potential tool for estimating aquatic quality.
AtıfScopus1WoS1OpenAlex1İncele - MakaleAçık Erişim2023Scopus SJRQ3Statistical Analysis and EEG Signal Filtering Using Design of Window Function Based on Optimization Methods
Serbet, Fatmanur; Kaya, Turgay
The window functions, which are widely used in Finite Impulse Response (FIR) digital filter design with the Fourier Series Methods, aim to eliminate the oscillations adversely affecting the filter performance that occur during the filter design. Window functions, which were developed with different methods in the literature, were designed with three different optimization techniques in this study. By using Particle Swarm Optimization (PSO), Grey Wolf Colony Optimization (GWCO), Cuckoo Search Optimization (CSO) algorithms, which are among current metaheuristic optimization methods, new window functions are designed for FIR digital filter design such that the designed new window functions have different window coefficients and design parameters. The difference of the designed window functions was analyzed with the Friedman and Wilcoxon tests, which are statistical data analysis methods, and the originality of the designed window functions was proven. FIR digital filters that can perform the same operation as the designed window functions have been produced and the results obtained by performing the filtering application of the EEG signal with the produced filters are presented in the study.
AtıfScopus9WoS6OpenAlex7İncele - 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 - MakaleYalnız künye2024Scopus SJRQ3Green synthesis of cobalt-oxide nanoparticles with an endemic species Allium tuncelianum and anticancer activity
Aslan Korkmaz, Şengül
The green synthesis method used to synthesize Co3O4-NPs has attracted numerous advantages due to its low cost, less time and energy consume, no need of special instruments for experimental and more eco-friendly with environment. In this study, the Co3O4-NPs were synthesized by green synthesis method to overcome the toxicity of chemical synthesis. And Allium tuncelianum plant which is an endemic species in Tunceli was used as a reducing agent and Co(NO3)2.6H2O as a source of cobalt. The synthesized Co3O4-NPs were characterized by using FTIR, XRD, SEM and HR-TEM techniques. The XRD pattern was shown that the Co-NPs were face-centered cubic (fcc) of crystalline nature and the average crystallite size was found nearly 23 nm with a value of COD(R^2): 0.982. The Co3O4-NPs generally had a spherical shape in the SEM images taken at 200 nm. The Co3O4-NPs showed low IC50 value against HeLa cells compare with RPE normal cells.
AtıfScopus7WoS10OpenAlex8İncele - MakaleYalnız künye2024Scopus SJRQ1Predicting and optimizing maximum flexural strength of planar composite plate shear walls – concrete filled with the application of LR and RSM
Polat, Erkan; Polat, Elifcan Göçmen
Traditional theoretical models, while conservative, overlook the complex, nonlinear interactions between material and geometric parameters that influence wall flexural strength. Additionally, the extent to which these models maintain their conservative assumptions across varying parameters remains uncertain. This study aims to develop advanced predictive models for the flexural strength of planar composite plate shear walls—concrete filled (C-PSW/CF) by employing Linear Regression (LR) and Response Surface Methodology (RSM). Central Composite Design (CCD) was utilized to design numerical experiments to analyze the effects of varying parameters, including steel plate yield strength, concrete compressive strength, wall depth, depth-to-thickness ratio, and reinforcement ratio. A validated complex finite element modeling (FEM) procedure was used to analyze numerical experiments involving varying parameters of the selected variables. Both LR and RSM were applied to the generated dataset to formulate predictive equations for the maximum moment capacity of walls. Interaction plots were developed to reveal the nonlinear relationships between the variables and identify the most effective parameters influencing the wall strength. Comparisons between theoretical predictions, RSM, and LR models revealed that RSM provided the most accurate predictions, closely aligning with FEM results and effectively capturing the nonlinear interactions between wall parameters. The findings of this paper contribute to the development of more practical, accurate and optimized design methods for C-PSW/CF, ultimately improving both structural safety and efficiency.
AtıfScopus10WoS8OpenAlex10İncele - BildiriAçık Erişim2025Health Status Classification of Electric Motors Using CNN-Based Models and SDP Images Under Varying Noise Conditions
Ertarğın, Merve; Yordanov, Nikolay; Zhilevski, Marin
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.
AtıfScopus1İncele
