In this study, we aimed to optimize the cutting parameters that affect the minimum temperature and power consumption in the turning of AISI 52100 bearing steel. For this, the Box-Behnken experimental design method, which was used for the lowest number of experiments in the experimental systems created using the response surface method (RSM), was used. The cutting parameters affecting the turning of the AISI 52100 bearing steel were determined as the cutting speed, depth of cut, and feed rate based on a literature research. The temperature and power consumption values were obtained via analyses according to the experimental design method determined by the finite element analysis (FEM) method. The results obtained were analyzed in Design Expert 13 software. According to the analysis results, the parameter values were determined for the minimum temperature and power consumption. The temperature and power consumption variables were affected by all three parameters, namely the cutting speed, depth of cut, and feed rate. For the minimum temperature and power consumption, a cutting speed of 162.427 m/min, depth of cut of 1.395 mm, and feed rate of 0.247 mm/rev, as well as the feed rate parameters, affected both the temperature and power consumption the most. In addition, it was determined that the cutting speed parameter had the least effect on both the temperature and power consumption variables. In addition, validation experiments were carried out in a real experimental environment with optimum values for the cutting parameters. The results showed that the output values obtained within the limits of the study with the obtained equation were quite close (3.3% error for temperature, 6.6% error for power consumption) to the real experimental outputs.

Recent breakthroughs in artificial intelligence have accelerated the adoption of learning algorithms, visual data categorization, and defect identification methods within quality control workflows across manufacturing industries. This review thoroughly explores the incorporation of AI-based solutions within industrial workflows, emphasizing the improved performance of neural network-driven techniques as opposed to classical inspection strategies. Specifically, CNN architectures (convolutional neural networks) and advanced YOLO models (YOLOv5, YOLOv7, YOLOv8) have exhibited outstanding precision and speed in detecting structural anomalies and identifying faults as they occur. By utilizing attention mechanisms, architectural refinements, knowledge transfer techniques and synthetic data expansion, these models have demonstrated enhanced capabilities—particularly in cases where training data is scarce. Transformer-based and hybrid neural network designs have shown great potential as effective alternatives, ensuring a balance between accuracy and computational demand. Research findings suggest that AI-based quality control frameworks play an essential role in minimizing manufacturing defects, elevating product quality, and improving overall customer satisfaction. These advancements span multiple industries, including automotive, steel, textiles, electronics, and more. They strongly align with Industry 4.0 goals, enabling the shift towards digitalized manufacturing systems, thereby fostering intelligent and automated production environments.

Kurumsal hediyeleşme süreçleri sonrasında, özellikle çalışanlara yan hak olarak sunulan Ramazan, yılbaşı gibi hediye paketlerinin dağıtımının ardından gelen şikayet e-postalarının manuel yönetimi, satın alma departmanları için ciddi bir operasyonel yük oluşturmaktadır. Bu çalışma, bu spesifik probleme odaklanarak, şikayet e-postalarının otomatik sınıflandırılması ve yönetimi için yapay zekâ (YZ) destekli, çok etiketli bir sistem geliştirmeyi amaçlamaktadır. Sistem, şikayetleri; ürün türü, paket türü, şikâyet türü ve sorumlu kişi olmak üzere dört ana kategoride sınıflandırmaktadır. Çalışmada, gerçek şirket verilerinin gizlilik kısıtları nedeniyle, büyük dil modelleri kullanılarak ve gerçek operasyonel senaryolar temel alınarak 1.870 adet sentetik şikâyet e-postası içeren özgün bir veri seti oluşturulmuş ve TF-IDF yöntemiyle metinler vektörleştirilmiştir. CatBoost, XGBoost ve Destek Vektör Makineleri (SVM) dâhil olmak üzere on farklı makine öğrenmesi algoritmasının performansı karşılaştırmalı olarak değerlendirilmiştir. Elde edilen bulgular, geliştirilen sistemin %87.75 ortalama F1-skoru başarısı gösterdiğini ortaya koymuştur. Literatürdeki spam ve oltalama odaklı çalışmaların aksine, bu çalışmanın özgün katkısı; çok etiketli kurumsal şikayet yönetimi problemine SHAP (SHapley Additive exPlanations) yöntemini uygulayarak model kararlarını şeffaf hale getirmesidir. Bu sayede, model tahminlerinin hangi kelimelere dayandığı açıklanarak sisteme duyulan güven artırılmıştır. Geliştirilen bu açıklanabilir YZ destekli sistem, kurumsal hediye paketleriyle ilgili şikayet yönetimi süreçlerinde otomasyon ve verimlilik artışı için etkin ve yorumlanabilir bir çözüm sunmaktadır.