Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395
Browse
2 results
Search Results
Article Surface Integrity and Tool Wear in S2-GFRP Milling: Experimental and Statistical Evaluation of Cutting Parameters and DLC and TiAlN Tool Coatings(Springer London Ltd, 2026) Danisman, Sengul; Yilmaz, Cagatay; Ersoy, Emin; Kesriklioglu, SinanIn this study, the surface integrity of S2-glass fiber-reinforced polymer (S2-GFRP) composites during milling with carbide cutters was investigated using a two-phase experimental design, focusing on surface roughness (Ra), burr area, and tool wear (VB). In the first phase, using a Taguchi L9 design, the effects of coating type (uncoated, TiAlN, DLC), spindle speed (2000-6000 rpm), and feed rate (0,15-0,25 mm/rev) on Ra and burr area were evaluated. In this short machining range where tool wear was negligible, the optimal combination yielding the lowest Ra (approximate to 0.97 mu m) and the minimum burr area (approximate to 231 mm & sup2;) was determined to be 4000 rpm, 0,15 mm/rev, and the DLC-coated tool. Regarding the effect of tool material on Ra, the DLC-coated tool provided approximately 4 and 2 times better results than the uncoated and TiAlN-coated tools, respectively. In the second phase, experiments extended up to 130 passes with this optimal parameter set showed that Ra increased significantly with increasing VB, and the burr area exhibited threshold-like behavior. In particular, a sudden increase in Ra and the burr area was observed when the VB approximate to threshold of approximately 100 mu m was exceeded; partial regression analyses confirmed different burr-formation tendencies in the low- and high-wear regimes. The results reveal that DLC coating initially provides superior performance in S2-GFRP milling, but surface degradation accelerates after the critical VB threshold.Article Citation - WoS: 20Citation - Scopus: 32Classification of Apple Images Using Support Vector Machines and Deep Residual Networks(Springer London Ltd, 2023-02-21) Adige, Sevim; Kurban, Rifat; Durmus, Ali; Karakose, ErcanOne of the most important problems for farmers who produce large amounts of apples is the classification of the apples according to their types in a short time without handling them. Support vector machines (SVM) and deep residual networks (ResNet-50) are machine learning methods that are able to solve general classification situations. In this study, the classification of apple varieties according to their genus is made using machine learning algorithms. A database is created by capturing 120 images from six different apple species. Bag of visual words (BoVW) treat image features as words representing a sparse vector of occurrences over the vocabulary. BoVW features are classified using SVM. On the other hand, ResNet-50 is a convolutional neural network that is 50 layers deep with embedded feature extraction layers. The pre-trained ResNet-50 architecture is retrained for apple classification using transfer learning. In the experiments, our dataset is divided into three cases: Case 1: 40% train, 60% test; Case 2: 60% train, 40% test; and Case 3: 80% train, 20% test. As a result, the linear, Gaussian, and polynomial kernel functions used in the BoVW + SVM algorithm achieved 88%, 92%, and 96% accuracy in Case 3, respectively. In the ResNet-50 classification, the root-mean-square propagation (rmsprop), adaptive moment estimation (adam), and stochastic gradient descent with momentum (sgdm) training algorithms achieved 86%, 89%, and 90% accuracy, respectively, in the set of Case 3.