☆ 4.6 Article

Data-driven prediction of product yields and control framework of hydrocracking unit

CHEMICAL ENGINEERING SCIENCE (2024)

Related references

Note: Only part of the references are listed.

Article Engineering, Geological

Explainable machine learning model for liquefaction potential assessment of soils using XGBoost-SHAP

Kaushik Jas et al.

Summary: Most existing machine learning models for liquefaction assessment of soils are black-box in nature, and the database used for model development is imbalanced. In this study, the coefficient of permeability and thickness of the critical layer are added to the existing database. The eXtreme Gradient Boosting (XGBoost) algorithm is used for probabilistic model development, and the imbalanced dataset is improved using the k-means synthetic minority oversampling technique (SMOTE) and hyperparameter tuning.

SOIL DYNAMICS AND EARTHQUAKE ENGINEERING (2023)

Add to Collection

Article Electrochemistry

Remaining useful life prediction of – Lithium batteries based on principal component analysis and improved Gaussian process regression

Jiang Xing et al.

International Journal of Electrochemical Science (2023)

Add to Collection

Article Engineering, Chemical

Modeling industrial hydrocyclone operational variables by SHAP-CatBoost - A conscious lab approach

S. Chehreh Chelgani et al.

Summary: Undoubtedly, hydrocyclones are crucial in powder technology and have a significant impact on process efficiency in plants. However, there is a lack of industrial-scale modeling of hydrocyclones, which can be used to train operators and reduce scale-up errors and lab costs. This study proposes a novel approach using conscious lab (CL) and explainable artificial intelligence (XAI) to fill this gap. The interactions between hydrocyclone variables were explored using the SHapley Additive exPlanations (SHAP) method and a new machine-learning model, CatBoost. The SHAP-CatBoost model successfully captured all the relationships and achieved higher accuracy in predicting O-80 and K-80 compared to other conventional AI methods.

POWDER TECHNOLOGY (2023)

Add to Collection

Article Environmental Sciences

Modelling and investigating the impacts of climatic variables on ozone concentration in Malaysia using correlation analysis with random forest, decision tree regression, linear regression, and support vector regression

Abdul-Lateef Balogun et al.

Summary: This study investigates the impact of climatic variables on ozone concentration in Malaysia and finds a strong positive correlation between temperature and ozone concentration. Wind speed also shows a moderate to strong correlation, while relative humidity exhibits a negative correlation. Machine learning algorithms, particularly random forest, demonstrate high predictive performances in assessing ozone concentration.

CHEMOSPHERE (2022)

Add to Collection

Article Biotechnology & Applied Microbiology

Modeling and optimization of vegetable oil biodiesel production with heterogeneous nano catalytic process: Multi-layer perceptron, decision regression tree, and K-Nearest Neighbor methods

Xuejin Sun et al.

Summary: In this study, Machine Learning (ML) approaches were used to simulate and optimize the biodiesel production process and predict the yield. Comparing the performance of different models, the MLP model showed the highest accuracy. Optimization using the MLP approach resulted in a high yield.

ENVIRONMENTAL TECHNOLOGY & INNOVATION (2022)

Add to Collection

Article Engineering, Mechanical

Comparative analysis of BPNN, SVR, LSTM, Random Forest, and LSTM-SVR for conditional simulation of non-Gaussian measured fluctuating wind pressures

Jinhua Li et al.

Summary: This study focuses on the research of non-Gaussian fluctuating wind pressure by utilizing multivariate conditional simulation to solve the problem of data missing caused by sensor failure. Different algorithms are compared based on prediction measures, and the combined algorithm (LSTM-SVR) is found to have the best accuracy. Furthermore, the simulated results of the combined algorithm (LSTM-SVR) are consistent with the statistical properties of the actual measured wind pressure data.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2022)

Add to Collection

Article Energy & Fuels

Base Oil Process Modelling Using Machine Learning

Muhamad Amir Mohd Fadzil et al.

Summary: The quality of feedstock for base oil production varies due to receiving different blends of crude oil, leading to reactive operations based on limited lab characterizations. Utilizing machine learning algorithms proactively can minimize production loss and optimize product recovery during transition, with the XGBoost model showing optimal performance in predicting base oil product properties.

ENERGIES (2021)

Add to Collection

Article Chemistry, Multidisciplinary

Machine learning based interpretation of microkinetic data: a Fischer-Tropsch synthesis case study

Anoop Chakkingal et al.

Summary: This study demonstrates the application of machine-learning methods for the data-driven design of chemical reactions using Fischer-Tropsch synthesis as a case study. Through the training of an ANN model, the researchers were able to analyze and reproduce microkinetic data, revealing the strong correlation between methane yield and temperature, space-time, and syngas molar inlet ratio.

REACTION CHEMISTRY & ENGINEERING (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Explaining individual predictions when features are dependent: More accurate approximations to Shapley values

Kjersti Aas et al.

Summary: Explaining complex or seemingly simple machine learning models is an important practical problem. The Shapley value framework is a game theoretic concept that can be used to explain individual predictions from such models. However, current methods like Kernel SHAP may produce misleading explanations when features are correlated.

ARTIFICIAL INTELLIGENCE (2021)

Add to Collection

Review Chemistry, Multidisciplinary

Gaussian Process Regression for Materials and Molecules

Volker L. Deringer et al.

Summary: This paper introduces the application of Gaussian process regression machine learning in computational materials science and chemistry, focusing on the regression of atomistic properties, including the construction of interatomic potentials, force fields, and fitting of various quantities. Methodological aspects of reference data generation, representation, regression, and model validation are reviewed, along with a survey of applications in chemistry and materials science and an outline of future development vision.

CHEMICAL REVIEWS (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Adding interpretability to predictive maintenance by machine learning on sensor data

Bram Steurtewagen et al.

Summary: This study utilizes a supervised machine learning approach, combining sensor and report data, to achieve prediction and diagnosis of equipment failures, highlighting the importance of diagnosis. The combination of statistical methods with proper data treatment can greatly enhance the diagnostic value of machine learning approaches.

COMPUTERS & CHEMICAL ENGINEERING (2021)

Add to Collection

Article Statistics & Probability

Reducing the number of experiments required for modelling the hydrocracking process with kriging through Bayesian transfer learning

Loic Iapteff et al.

Summary: In this study, a transfer learning approach is used to improve the regression model of the hydrocracking process for a new catalyst by leveraging data from an old catalyst. The results show significant improvement when applying a Bayesian approach to transfer linear and kriging models.

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES C-APPLIED STATISTICS (2021)

Add to Collection

Article Engineering, Chemical

Modeling the Hydrocracking Process with Deep Neural Networks

Wenjiang Song et al.

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH (2020)

Add to Collection

Review Green & Sustainable Science & Technology

Hydrocracking: A Perspective towards Digitalization

Esin Iplik et al.

SUSTAINABILITY (2020)

Add to Collection

Article Chemistry, Organic

Development of a SVM model for Prediction of Hydrocracking Product Yields

K. Sharifi et al.

PETROLEUM CHEMISTRY (2019)

Add to Collection

Article Energy & Fuels

A continuous lumping model for hydrocracking on a zeolite catalysts: model development and parameter identification

Per Julian Becker et al.

FUEL (2016)

Add to Collection

Article Energy & Fuels

Comparing hydrocracking models: Continuous lumping vs. single events

P. J. Becker et al.

FUEL (2016)

Add to Collection

Article Engineering, Chemical

Development of Vacuum Residue Hydrodesulphurization-Hydrocracking Models and Their Integration with Refinery Hydrogen Networks

Blessing Umana et al.

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH (2016)

Add to Collection

Proceedings Paper Computer Science, Interdisciplinary Applications

A study on C.5 Decision Tree Classification Algorithm for Risk Predictions during Pregnancy

B. N. Lakshmi et al.

INTERNATIONAL CONFERENCE ON EMERGING TRENDS IN ENGINEERING, SCIENCE AND TECHNOLOGY (ICETEST - 2015) (2016)

Add to Collection

Article Energy & Fuels

Modeling the Hydrocracking Kinetics of Atmospheric Residue in Hydrotreating Processes by the Continuous Lumping Approach

Haitham M. S. Lababidi et al.

ENERGY & FUELS (2011)

Add to Collection

Article Energy & Fuels

On the detailed solution and application of the continuous kinetic lumping modeling to hydrocracking of heavy oils

Ignacio Elizalde et al.

FUEL (2011)

Add to Collection

Article Statistics & Probability

Principal component analysis

Herve Abdi et al.

WILEY INTERDISCIPLINARY REVIEWS-COMPUTATIONAL STATISTICS (2010)

Add to Collection

Article Chemistry, Physical

Application of continuous kinetic lumping modeling to moderate hydrocracking of heavy oil

Ignacio Elizalde et al.

APPLIED CATALYSIS A-GENERAL (2009)

Add to Collection

Article Computer Science, Artificial Intelligence

Top 10 algorithms in data mining

Xindong Wu et al.

KNOWLEDGE AND INFORMATION SYSTEMS (2008)

Add to Collection

Review Chemistry, Applied

Kinetic modeling of hydrocracking of heavy oil fractions:: A review

J Ancheyta et al.

CATALYSIS TODAY (2005)

Add to Collection

Article Chemistry, Applied

Industrial hydrocracker model based on novel continuum lumping approach for optimization in petroleum refinery

K Basak et al.

CATALYSIS TODAY (2004)

Add to Collection

© Peeref 2019-2024. All rights reserved.