Yazar "Sener, Ramazan" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • [ X ]
    Öğe
    Machinability of different Cu-Gr composites in milling: Performance parameters prediction via machine learning models
    (Pergamon-Elsevier Science Ltd, 2025) Sap, Serhat; Acar, Erdi; Degirmenci, Uenal; Usca, uesame Ali; Memis, Samet; Sener, Ramazan
    The machinability of copper-graphite (Cu-Gr) composites has gained significant attention due to their unique thermal, electrical, and mechanical properties. This study experimentally investigates the machinability performances (such as surface roughness, flank wear, cutting temperature, and energy consumption) of Cu-Gr hybrid composite materials during milling. It predicts these parameters with machine learning models. The study aims to contribute to sustainable and optimized manufacturing processes by analyzing the effects of different cutting parameters and cooling/lubrication conditions on this performance. Furthermore, advanced artificial intelligence-based models predict machining outcomes, providing a robust framework for process enhancement and industrial implementation. Although there are comprehensive studies on the machining performances of metal matrix composites in the literature, there is limited information on Cu-Gr composites' mechanical and thermal behaviors in milling processes. To address this deficiency, a full factorial experimental plan was applied on six different Cu-Gr composites and the effects of different cutting speeds, feed rates and cooling/ lubrication environments (Dry, MQL, cryogenic LN2) on flank wear, surface roughness, cutting temperature and energy consumption were analyzed. The materials used in the study were prepared by mixing graphite and hard phases (Al2O3 and Cr3C2) in specific proportions, and these composites were compared in terms of machinability. Afterward, the output parameters of the experimental results are predicted by employing the well-known machine learning models and the experimental results. The results manifested that Gradient-Boosted Decision Tree Regression performs better than the other ten machine learning models in predicting machinability parameters. Finally, this study highlights potential areas for future research and provides a practical guide for optimizing CuGr composites in manufacturing processes and achieving sustainability goals. It has engineering value in efficiency, cost reduction, and developing environmentally friendly applications, especially for the automotive, aerospace, and energy sectors.
  • [ X ]
    Öğe
    Prediction of newly synthesized heparin mimic's effects as heparanase inhibitor in cancer treatments via variational quantum neural networks
    (Elsevier Sci Ltd, 2025) Kocabay, Samet; Acar, Erdi; Memis, Samet; Taskin, Irmak Icen; Sever, Meryem Ruveyda; Sener, Ramazan
    Cancer remains a leading global cause of death, primarily driven by the uncontrolled proliferation of abnormal cells. Malignant tumors, such as carcinomas, originate from unchecked epithelial cell growth and produce growth factors like FGF and VEGF, which promote angiogenesis and tumor progression through heparanasemediated degradation of heparan-sulfate proteoglycans. Chitosan and its derivatives have shown promise in inhibiting tumor growth and metastasis. This study aims to investigate newly synthesized sulfated chitosan oligomers as heparin mimics to inhibit heparanase, evaluating their cytotoxic effects on SH-SY5Y, HCT116, A549, and MDA-MB-231 cancer cell lines. Moreover, it seeks to leverage a variational quantum neural network (VQNN) to predict and validate cytotoxicity outcomes, integrating quantum computing methods into evaluating novel anticancer compounds. The VQNN algorithm was applied to analyze the anticancer effects of sulfated chitosan oligomers. Cytotoxicity data from wet lab experiments validated the model's predictive performance. The VQNN model demonstrated strong predictive capabilities in evaluating anticancer compounds. Specifically, it achieved a mean absolute error (MAE) of 6.5844, indicating a similar trend to the experimental results. Additionally, the model obtained an R2 value of 0.6020, reflecting a moderate level of correlation between predicted and observed outcomes. The results underscore the potential of integrating quantum-based machine learning models into cancer research. The VQNN effectively predicted experimental outcomes, showcasing its utility in assessing novel anticancer compounds. This approach could speed up drug discovery by streamlining the identification and optimization of therapeutic candidates. Furthermore, the findings support the ongoing development of quantum computing techniques for tackling complex biological challenges, contributing to innovative cancer treatment strategies that target tumor growth and angiogenesis.