Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
2 results
Search Results
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.Review Citation - WoS: 16Citation - Scopus: 17Green Biohydrogen Production From Renewable Plant-Based Resources: a Comparative Evaluation(Institution of Chemical Engineers, 2024) Goren,A.Y.; Gören, Ayşegül Yağmur; Dincer,I.; Khalvati,A.Increasing energy demand drives the need for environmentally sustainable and economically viable renewable resources to eliminate problems related to greenhouse gas emissions. In recent years, research on biohydrogen (bio-H2) production as a renewable energy source has been recognized as a potential subject. It aims to reduce the pressures set by carbon dioxide emissions and the depletion of fossil fuel supplies. The field of bio-H2 science is considered potentially important; there have been increasing efforts to develop feasible systems for viable applications. This review further presents an updated and comprehensive review of bio-H2 production by dark fermentation (DF), photofermentation (PF), microbial electrolysis cells (MEC), and hybrid processes using plant-based materials. Among these processes, the highest H2 production yield of 680.8 mLH2/g-biomass was obtained using the DF-PF hybrid process. A comparison of bio-H2 production yields, the environmental impact, and the costs of DF, PF, MEC, and hybrid systems is considered, and superior performance was obtained for integrated biological processes. The comparative evaluation results showed that the MEC process is the most economical technology, followed by integrated systems. The PF is the most environmentally friendly H2 production process, presenting the lowest global warming potential (GWP) value of 1.88 kgCO2eq./kgH2 and acidification potential (AP) of 3,61 gSO2/kgH2 ; it is followed by DF and MEC processes. On the other hand, the highest GWP of 14.8 kgCO2eq./kgH2 and AP 103 gSO2/kg H2 were obtained for the DF-MEC process related to electrical and heat requirements during the production process. Furthermore, the WCP and WSF values were 84.5 and 3632.9 m3 for the DF-MEC integrated process due to the water utilization in anode and cathode solutions, while WCP was 2.91 m3 for the DF process. Overall, the results of this study further revealed that substantial effort, in the current and future, should be performed on bio-H2 production from plant-based biomass using integrated biological processes. Moreover, the bibliometric analysis presented that bio-H2 production from plant-based materials, MEC systems utilization, and nano-additives are growing areas in the bio-H2 research that provide zero-carbon energy in the future. © 2024 The Institution of Chemical Engineers