Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
4 results
Search Results
Article Robust Scheduling of Crude Oil Farming and Processing Under Uncertainty(Elsevier, 2026) Yalcin, Damla; Sildir, HasanThe sulphur content in crude oil has a significant impact on refinery operations, influencing the feasibility of crude blending, the distribution of product yields, and overall economic performance. Variations in sulphur content introduce uncertainty in the short-term scheduling of crude oil loading, blending, and distillation processes. This study introduces a scenario-based stochastic optimization framework in which sulphur uncertainty is treated as a central modeling element, represented through a regression-based relationship with specific gravity (SG). The approach systematically propagates uncertainty through blending decisions, crude distillation unit (CDU) feed composition, and product yields. The problem is modeled as a mixed-integer quadratically constrained programming (MIQCP) formulation within a continuous-time scheduling framework, enabling the simultaneous optimization of timing, blending, and processing strategies. The results indicate that increased sulphur uncertainty adversely affects the distribution of yields for nine end-products, resulting in profit losses. These findings underscore the importance of explicitly managing compositional uncertainty and provide insights into cost-performance trade-offs in refinery scheduling.Article Towards Facile Deep Learning Architectures for Chemical Processes: Simultaneous Pseudo-Global Training and Economic Synthesis(Institution of Chemical Engineers, 2025) Sildir, Hasan; Yalcin, Damla; Tuncer, Basak; Deliismail, Ozgun; Leblebici, Mumin EnisChemical process data is usually not directly valorized in pure machine learning predictive models due to limited data availability. This limitation often caused from high sensor costs, data variety, and veracity issues. In response, this study proposes a novel formulation based on mixed-integer linear programming (MILP), called Approximated Deep Learning (ADL), to overcome these limitations and enable accurate modeling under data scarcity. The ADL simultaneously performs input selection, outlier filtering, and training of deep learning architectures within a single-level optimization problem. The method approximates the nonlinear and nonconvex components of traditional deep learning models in the mixed-integer domain through sophisticated reformulations, achieving a pseudo-global solution. A key feature of ADL is the integration of sensor pricing as a regularization mechanism, which promotes cost-efficient soft sensor design without compromising predictive performance. The proposed framework is validated on a publicly available bubble column dataset and benchmarked against four conventional deep learning methods. Results show that ADL achieves superior test accuracy with more than 50% reduction in input space, drastically reducing sensor cost. Furthermore, the optimized architecture is a high-quality initial guess for transfer learning on larger datasets. Overall, the method offers a practical and economically viable solution for data-driven chemical process modeling.Article Citation - WoS: 1Citation - Scopus: 1Storage Tank Farming Planning Under Equipment and Port Operational Costs Through Mixed Integer Quadratically Constrained Programming(Elsevier, 2025) Yalcin, Damla; Deliismail, Ozgun; Tuncer, Basak; Sildir, HasanThe study contributes a new method for managing crude oil tank farms, focusing on scheduling and optimizing storage tanks using mathematical modeling. The short-term continuous-time scheduling model reduces tank requirements and performs selection with convenient capacities. The nonconvex mixed-integer quadratically constrained programming (MIQCP) model is used to account for tank farm scheduling dynamics. It focuses on the integration of ships, storage tanks, charging tanks, and crude oil distillation units. The study examines 8 cases focusing on oil supply, arrival times, prices, and maximum flow rate constraints to show the impact of real-world volatility. By incorporating process intensification principles, the mathematical model emphasizes the importance of optimizing storage tank usage to minimize port operational costs of crude oils.Article Evaluation of Partially Reduced Keratins Extracted From Wool Fibers as a Hydrogel Forming Biomaterial(inst Tecnologia Parana, 2024) Yalcin, Damla; Top, AybenIn this study, it was aimed to prepare low-cost hydrogel from reduced keratin. Keratin proteins were obtained from Merino wool via three extraction methods. In the first method, keratins were reduced using sodium sulfide. In the second method, keratins extracted with the first method were precipitated with HCl. Urea, EDTA, and sodium sulfide were used in the third method. Extraction yields of method 1, method 2, and method 3 were determined as 44 +/- 2, 27 +/- 1, and 42 +/- 2 %, respectively. For all extraction methods, the average value of the free thiol amounts was obtained as 0.06 +/- 0.02 mmol SH/g keratin. A considerable portion of the highly polydisperse keratins was separated between similar to 40 kDa and similar to 60 kDa in the SDS-PAGE gel, and this fraction corresponds to alpha-keratin proteins with low sulfur content. A strong band at similar to 1654 +/- 1 cm(-1) detected in the FTIR spectra of the keratins confirms mainly alpha-helical secondary structure. The self- standing hydrogel was obtained upon incubating 15 wt. % keratin solution at 37 degrees C. Storage modulus and loss modulus of the hydrogel were determined as 1.3 +/- 0.08 kPa and 0.1 +/- 0.015 kPa, respectively. The keratin hydrogel is not cytotoxic to L929 mouse fibroblast cells, suggesting that this affordable hydrogel can be applied as a drug delivery/encapsulation system and in wound healing.