Ex Situ Upgrading of Extra Heavy Oil: The Effect of Pore Shape of Co-Mo/γ-Al2O3 Catalysts

Kirgizov, A. Yu.; Ding, Bin; Spiridonov, Artur A.; Liu, Lei; Laskin, Artem; Cao, Changyong; Il’yasov, Il’dar R.; Al‐Muntaser, Ameen A.; Zhou, Xiaodong; Zinnatov, Radik A.; Ламберов, А. А.; Yuan, Chengdong; Varfolomeev, Mikhail A.

doi:10.3390/catal12101271

Cited by 3 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The shape of adsorption isotherm is indicative of adsorption mechanism include microporous filling, capillary condensation, monolayer-multilayer adsorption, competitive adsorption and catalytic reaction [1][2][3][4][5]. The classification of adsorption isotherm is a summary of different types of isotherms based on their known shapes and characteristics.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An adsorption isotherm identification method based on CNN-LSTM neural network

Liu,

Xie,

Yan

et al. 2023

J Mol Model

View full text Add to dashboard Cite

Context：Adsorption isotherm is integral to comprehending the adsorption mechanism and catalytic processes.Despite the well-established research on isotherm classification methods, existing techniques for isotherm identification are hampered by inefficiency, human interference, insufficient feature information extracting and the fact that specific types isotherm of identification can be achieved. To overcome these limitations, an end-to-end isotherm identification method based on a CNN-LSTM neural network is proposed, which employs a combination of Convolutional Neural Network (CNN) and Long Short-Term Memory network (LSTM) to extract the features of adsorption isotherm. Additionally, dataset is constructed for training and validating the neural network using various theoretical adsorption isotherm equations, thereby eliminating the need for time-consuming and expensive repetitive experiments. The results indicate that the model achieves identification accuracy of 100% on both the training and validation sets constructed using theoretical adsorption equations. The model's F1-score on the test set, which consists of five categories actual adsorption isotherms, is 88.85%, and there has been a 20% enhancement in the mean precision of isotherm identification compared to the traditional method. All these results demonstrate that the proposed method can accurately identify adsorption isotherm.Method: Pycharm was used as the experimental and testing platform, python 3.9 was used as the programming language, Tensorflow 2.11.0 and Keras 2.10.0 were used to train and test the CNN-LSTM model, numpy 1.21.5 and scipy 1.81 were used to generate the train and validation dataset.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Here, N denotes the data number of adsorption loading. The CNN layer then performs convolutional operations on the vector x, as demonstrated in equation(5).…”

mentioning

confidence: 99%

An adsorption isotherm identification method based on CNN-LSTM neural network

Liu,

Xie,

Yan

et al. 2023

J Mol Model

View full text Add to dashboard Cite

show abstract

Towards improvement of hydroprocessing catalysts - understanding the role of advanced mineral materials in hydroprocessing catalysts

Majodina,

Poswayo,

Dembaremba

et al. 2023

Miner Miner Mater

View full text Add to dashboard Cite

Mineral materials play a pivotal in heterogeneous catalysts as active, support, or promoter components, with the oil refinery industry being one of the biggest beneficiaries. While conventional hydroprocessing catalysts have historically met the industry’s needs, the growing need to accommodate unique feedstocks, meet the increasing demand for environmentally acceptable products, obtain better product specifications, enhance selectivity for reactions to increase ratios for certain product cuts, and use more cost-effective and abundant mineral materials, has recently motivated for fresh considerations in the development of hydroprocessing catalysts. Based on periodic trends, noble metals possess the most desirable qualities, but their relative abundance in the Earth’s crust is too low to meet industry needs. They are costly and highly sensitive to sulfur poisoning. Mo and W lie in the sweet spot, but it is anticipated that they cannot meet the increasing demand. Investigations of electronic interactions of more economical and abundant metals, such as Nb, V, and Fe, with other elements and support materials have yielded a better understanding of synergistic effects that help to access noble metal-like qualities. This work contrasts conventional hydroprocessing catalysts and recently improved catalysts, detailing the chemistry considerations behind the selection of mineral materials used in the catalysts. It also explores how further manipulation of these mineral materials and synthesis approaches is driving toward more desirable properties. The work brings to the attention of the readers the challenges and opportunities for the further improvement of hydroprocessing catalysts to ensure environmental sustainability while meeting the industry’s growing needs.

show abstract

An adsorption isotherm identification method based on CNN-LSTM neural network

Liu

Xie

Yan

et al. 2023

Preprint

View full text Add to dashboard Cite

Context: Adsorption isotherm is integral to comprehending the adsorption mechanism and catalytic processes. Despite the well-established research on isotherm classification methods, existing techniques for isotherm identification are hampered by inefficiency, human interference, insufficient feature information extracting and the fact that specific types isotherm of identification can be achieved. To overcome these limitations, an end-to-end isotherm identification method based on a CNN-LSTM neural network is proposed, which employs a combination of Convolutional Neural Network (CNN) and Long Short-Term Memory network (LSTM) to extract the features of adsorption isotherm. Additionally, dataset is constructed for training and validating the neural network using various theoretical adsorption isotherm equations, thereby eliminating the need for time-consuming and expensive repetitive experiments. The results indicate that the model achieves identification accuracy of 100% on both the training and validation sets constructed using theoretical adsorption equations. The model's F1-score on the test set, which consists of five categories actual adsorption isotherms, is 88.85%, and there has been a 20% enhancement in the mean precision of isotherm identification compared to the traditional method. All these results demonstrate that the proposed method can accurately identify adsorption isotherm. Method: Pycharm was used as the experimental and testing platform, python 3.9 was used as the programming language, Tensorflow 2.11.0 and Keras 2.10.0 were used to train and test the CNN-LSTM model, numpy 1.21.5 and scipy 1.81 were used to generate the train and validation dataset.

show abstract

Ex Situ Upgrading of Extra Heavy Oil: The Effect of Pore Shape of Co-Mo/γ-Al2O3 Catalysts

Cited by 3 publications

References 36 publications

An adsorption isotherm identification method based on CNN-LSTM neural network

An adsorption isotherm identification method based on CNN-LSTM neural network

Towards improvement of hydroprocessing catalysts - understanding the role of advanced mineral materials in hydroprocessing catalysts

An adsorption isotherm identification method based on CNN-LSTM neural network

Contact Info

Product

Resources

About