We propose a novel systematic approach for the deployment optimization of unmanned aerial vehicles (UAVs). In this context, this study focuses on enhancing the coverage of UAV-mounted 6G mobile base stations. The number and placement optimization of UAV-mounted 6G mobile base stations, deployed to support terrestrial base stations during periods of increased population density in a given area, are addressed using a symbolic limited optimal discrete controller synthesis technique. Within the scope of this study, the UAVs’ altitude and attitude behaviors are optimized to ensure the most efficient trajectory toward the designated base station coordinates. Additionally, at their new locations, these behaviors are adjusted to facilitate accurate coverage estimation from the base stations they serve. In the deployment optimization of UAVs, the placement of base stations is determined using received signal strength data obtained through the ray-tracing-based channel modeling technique. The channel model considered critical parameters such as path loss, received power, weather loss, and foliage loss. Final average path loss values of 102.3 dB, 111.7 dB, and 127.4 dB were obtained at the carrier frequencies of 7 GHz, 26 GHz, and 140 GHz, respectively. These findings were confirmed with MATLAB-based ray tracing simulations. Our proposed approach is validated through experimental evaluations, demonstrating superior performance compared to existing methods reported in the literature.

In this study, we propose an architectural model for path optimization in cluster order picking within warehouse robotics, utilizing a hybrid approach that combines symbolic control and metaheuristic techniques. Among the optimization strategies, we incorporate bio-inspired metaheuristic algorithms such as the Walrus Optimization Algorithm (WOA), Puma Optimization Algorithm (POA), and Flying Foxes Algorithm (FFA), which are grounded in behavioral models observed in nature. We consider large-scale warehouse robotic systems, partitioned into clusters. To manage shared resources between clusters, the set of clusters is first formulated as a symbolic control design task within a discrete synthesis framework. Subsequently, the desired control goals are integrated into the model, encoded using parallel synchronous dataflow languages; the resulting controller, derived using our safety-focused and optimization-based synthesis approach, serves as the manager for the cluster. Safety objectives address the rigid system behaviors, while optimization objectives focus on minimizing the traveled path of the warehouse robots through the constructed cost function. The metaheuristic algorithms contribute at this stage, drawing inspiration from real-world animal behaviors, such as walruses’ cooperative movement and foraging, pumas’ territorial hunting strategies, and flying foxes’ echolocation-based navigation. These nature-inspired processes allow for effective solution space exploration and contribute to improving the quality of cluster-level path optimization. Our hybrid approach, integrating symbolic control and metaheuristic techniques, demonstrates significantly higher performance advantage over existing solutions, with experimental data verifying the practical effectiveness of our approach. Our proposed algorithm achieves up to 3.01% shorter intra-cluster paths compared to the metaheuristic algorithms, with an average improvement of 1.2%. For the entire warehouse, it provides up to 2.05% shorter paths on average, and even in the worst case, outperforms competing metaheuristic methods by 0.28%, demonstrating its consistent effectiveness in path optimization.

Hydrometallurgical leaching processes contain complex and nonlinear parameter interactions that are difficult to capture with conventional empirical models. In this study, a multiple hybrid machine learning approach was developed to predict manganese (Mn) and iron (Fe) dissolution efficiency in leaching systems and performed using sulfuric acid (H₂SO₄), hydrochloric acid (HCl), and nitric acid (HNO₃). A large-format dataset consisting of 204 independent leaching experiments was generated in which acid type, acid concentration (0.5–5 M), temperature (25–90 °C), solid/liquid ratio (100–200 g/L), leaching time (1–4 h), and eight different reducing agent types were systematically varied. XGBoost, LightGBM, CatBoost, and Random Forest algorithms were individually trained and subsequently combined with a Soft Voting Ensemble architecture. Hyperparameters were optimized using the RandomizedSearchCV method with 3-fold cross-validation. The XGBoost model achieved the highest prediction accuracy for Mn dissolution (R² = 0.8993, RMSE = 8.06%), while CatBoost demonstrated the best performance in Fe dissolution (R² = 0.8415, RMSE = 4.43%). SHAP analysis suggested that the dosage and type of reducing agents are the most influential predictive features for Mn dissolution, while acid molarity and temperature were identified as the dominant predictors for Fe leaching. Friedman test confirmed that performance differences among both Mn and Fe models were statistically significant (Mn: χ² = 32.76, p < 0.001; Fe: χ² = 25.96, p < 0.001). The developed models contribute significantly to hydrometallurgical process optimization by predicting the nonlinear effects of leaching parameters on metal dissolution with high accuracy. This study presents a comprehensive and interpretable machine learning framework supported by an extensive experimental dataset, a substantial portion of which has not been previously utilized or comparatively analyzed within a unified multi-acid framework, enabling systematic modeling of selective Mn–Fe dissolution across multiple acid systems and reducing agents.

Kalıcı mıknatıslı senkron motorlarda (KMSM) rotor üzerindeki kalıcı mıknatısların sıcaklığı, güç yoğunluğunu ve çalışma güvenliğini doğrudan belirleyen kritik bir büyüklüktür; ancak bu sıcaklık dönen rotor üzerinde doğrudan ve ekonomik biçimde ölçülememektedir. Bu çalışmada, açık erişimli bir test düzeneği veri seti (yaklaşık 1,33 milyon örnek, 2 Hz örnekleme) kullanılarak mıknatıs sıcaklığının dolaylı tahmini iki ayrı senaryo altında karşılaştırmalı olarak incelenmiştir. Sensörsüz senaryoda yalnızca ölçülebilen elektriksel ve termal büyüklükler ile bunlardan türetilen üstel ağırlıklı hareketli ortalama (EWMA) ve gecikme öznitelikleri kullanılmış. Tek adım ileri senaryoda ise mıknatıs sıcaklığının yakın geçmiş değerleri de eklenmiştir. Her iki senaryoda Ridge regresyonu, Random Forest, LightGBM ve XGBoost modelleri eğitilmiştir. Sensörsüz senaryoda en iyi başarımı XGBoost sağlamış (R² = 0,729; RMSE = 6,72 °C), tek adım ileri senaryoda ise tüm modeller neredeyse kusursuz doğruluğa ulaşmıştır (R² ≈ 0,9997). Modeller arasındaki farklar Friedman testi ve Kendall'ın uyum katsayısı (W) ile değerlendirilmiştir. İstatistiksel anlamlılığa karşın etki büyüklüğünün küçük olduğu (W < 0,04) belirlenmiştir. SHAP analizi, sensörsüz senaryoda baskın sürücünün soğutucu sıcaklığının uzun vadeli hareketli ortalaması olduğunu; tek adım ileri senaryoda ise bir önceki sıcaklık değerinin belirleyici rol oynadığını ortaya koymuştur. Bulgular, ağaç tabanlı modellerin yorumlanabilir bir sıcaklık kestirim aracı olarak kullanılabileceğini, ancak sensörsüz kestirim doğruluğunun termal dinamiklerin karmaşıklığıyla sınırlandığını göstermektedir.