An intelligent approach for the modeling and experimental optimization of molecular hydrodesulfurization over AlMoCoBi catalyst

Al-Jamimi, Hamdi A.; Bagudu, Aliyu; Saleh, Tawfik A.

doi:10.1016/j.molliq.2018.12.144

Cited by 35 publications

(13 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning Approach for prediction: The future of HDS catalysts can be improved by employing machine learning (ML) to predict and formulate the right composite support(s) at the very best conditions for maximum catalytic conversion and stability. [166][167][168][169] ML is a predictive tool in solving and understanding complex process, especially for heterogeneous catalysis where some understandings are lacking. For example, support-metal interaction is the main point of discussion with respect to performance and activity of HDS supported catalysts, and mostly the differential catalytic performance is not comprehensively understood.…”

Section: Machine Learning Application In Hdsmentioning

confidence: 99%

Section: Machine Learning Application In Hdsmentioning

confidence: 99%

“…ML is aimed at reducing number of experimental runs and designs through simple, fast and reliable optimization, whilst the extent of desulfurization is accurately modelled and predicted at most 5% experimental errors. Specifically, a smart and precise model was reported by, [167] to predict the sulfur concentration in the fuel taken into consideration the operating conditions (temperature and pressure) in the presence of critical properties. In the same vein, the relationship between input variables such as catalyst dosage, sulfur initial concentration, nature of the fuel, temperature and pressure etc.…”

Section: Machine Learning Application In Hdsmentioning

confidence: 99%

See 2 more Smart Citations

Hierarchical Hybrid Supports and Synthesis Strategies for Hydrodesulfurization of Recalcitrance Organosulfur Compounds

Ganiyu

2021

Chemistry An Asian Journal

View full text Add to dashboard Cite

It is undisputed that there is a paradigm shift in the global trend of crude oil towards being more sour and heavier than usual light sources. Consequently, the hydrotreating activity becomes a bottleneck with high content of S, N, metals and other impurities than expected. On the other hand, the price of petroleum products lately witnessed instability and fell to the lowest average price (<USD 20) in recent times. In the same vein, the regulation to control the emission of toxic compounds in the atmosphere become stricter as promulgated by various policymakers. In this sense, robust hydrotreating catalysts with characteristics efficient catalytic activity, selectivity and stability are highly desirable. Recently, different approaches have been used to improve and cushion the unprecedented effect emanated from economic, social and environmental challenges posed by heavy and sour crude sources, price instability of the refined products and regulation to lower the sulfur to minimum level or zero parts per millions (ppm). Importantly, the role of support in catalysis cannot be over emphasized, whilst the surface area and porosity, mechanical and thermal stability, dispersion of active metals, acidity/basicity have been greatly improved, the increased activity, stability and selectivity has been observed significantly. In this review, hybrid supports based on aluminosilicates (zeolitic types) and other notable supports from recent literatures were explored and discussed for Ni(Co)Mo(W) supported catalysts for hydrodesulfurization (HDS) activity of heavy organosulfur molecules. The emphasis on the hybrid supports’ varied characteristics for HDS of organosulfur molecules, where there are necessities for fast diffusion of reactants and products, better dispersion of MoS2 crystallites, high surface area and pore volume, and increased acidity of the catalysts are greatly emphasized. Furthermore, the progress made so far on different HDS active phases viz. noble metals, metal phosphides, intermetallic silicides, carbides and iron‐zinc are highlighted in this write‐up, irrespective of the support composition in the supported catalysts formulations. The need for application of predictive tools, like machine learning (ML) in the design and development of HDS catalysts, and performance evaluation of HDS activity towards achieving better catalytic operation was briefly highlighted. Finally, the review will serve as a summary of scientific efforts in this regards and bridge a gap for the newcomers to investigate the topic in a better way through proper selection and efficient catalysts design.

show abstract

Section: Machine Learning Application In Hdsmentioning

confidence: 99%

Section: Machine Learning Application In Hdsmentioning

confidence: 99%

Section: Machine Learning Application In Hdsmentioning

confidence: 99%

See 1 more Smart Citation

Hierarchical Hybrid Supports and Synthesis Strategies for Hydrodesulfurization of Recalcitrance Organosulfur Compounds

Ganiyu

2021

Chemistry An Asian Journal

View full text Add to dashboard Cite

show abstract

“…Therefore, they have been constantly evolving and have now included artificial intelligence techniques. Examples of this are the models to find new catalysts (Günay and Yıldırım, 2021;Goldsmith et al, 2018;Lamoureux et al, 2019;Yang et al, 2020), the models to control oil exploitation (Davtyan et al, 2020;Liu et al, 2020;Tsvaki et al, 2020), and the models to analyze oil transformation (Al-Jamimi et al, 2019;Sircar et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Learning the Use of Artificial Intelligence in Heterogeneous Catalysis

Bokhimi

2021

Front. Chem. Eng.

View full text Add to dashboard Cite

We describe the use of artificial intelligence techniques in heterogeneous catalysis. This description is intended to give readers some clues for the use of these techniques in their research or industrial processes related to hydrodesulfurization. Since the description corresponds to supervised learning, first of all, we give a brief introduction to this type of learning, emphasizing the variables X and Y that define it. For each description, there is a particular emphasis on highlighting these variables. This emphasis will help define them when one works on a new application. The descriptions that we present relate to the construction of learning machines that infer adsorption energies, surface areas, adsorption isotherms of nanoporous materials, novel catalysts, and the sulfur content after hydrodesulfurization. These learning machines can predict adsorption energies with mean absolute errors of 0.15 eV for a diverse chemical space. They predict more precise surface areas of porous materials than the BET technique and can calculate their isotherms much faster than the Monte Carlo method. These machines can also predict new catalysts by learning from the catalytic behavior of materials generated through atomic substitutions. When the machines learn from the variables associated with a hydrodesulfurization process, they can predict the sulfur content in the final product.

show abstract

“…Recent studies have proven that machine learning can also help scientists identify patterns that are difficult to detect by traditional methods and provide accurate simulations replacing complicated experimental works. [24] In fact, in addition to commonly reported works focused on experiments,studies have attempted to build generalized models on PEMFCs by numerical modeling and computer simulations. [25] As early as the 2000 s, machine learning methods were introduced to help reduce expensive computational costs and analyze data.…”

Section: Introductionmentioning

confidence: 99%

Designing AI‐Aided Analysis and Prediction Models for Nonprecious Metal Electrocatalyst‐Based Proton‐Exchange Membrane Fuel Cells

et al. 2020

View full text Add to dashboard Cite

Traditionally,alarger number of experiments are needed to optimize the performance of the membrane electrode assembly (MEA) in proton-exchange membrane fuel cells (PEMFCs) since it involves complex electrochemical, thermodynamic,a nd hydrodynamic processes.H erein, we introduce artificial intelligence (AI)-aided models for the first time to determine key parameters for nonprecious metal electrocatalyst-based PEMFCs,t hus avoiding unnecessary experiments during MEA development. Among 16 competing algorithms widely applied in the AI field, decision tree and XGBoost showed good accuracy (86.7 %and 91.4 %) in determining key factors for high-performance MEA. Artificial neural network (ANN) shows the best accuracy (R2 = 0.9621) in terms of predictions of the maximum power density and ad ecent reproducibility (R2 > 0.99) on uncharted I-V polarization curves with 26 input features.H ence,m achine learning is shown to be an excellent method for improving the efficiency of MEA design and experiments.

show abstract

An intelligent approach for the modeling and experimental optimization of molecular hydrodesulfurization over AlMoCoBi catalyst

Cited by 35 publications

References 26 publications

Hierarchical Hybrid Supports and Synthesis Strategies for Hydrodesulfurization of Recalcitrance Organosulfur Compounds

Hierarchical Hybrid Supports and Synthesis Strategies for Hydrodesulfurization of Recalcitrance Organosulfur Compounds

Learning the Use of Artificial Intelligence in Heterogeneous Catalysis

Designing AI‐Aided Analysis and Prediction Models for Nonprecious Metal Electrocatalyst‐Based Proton‐Exchange Membrane Fuel Cells

Contact Info

Product

Resources

About