Atwakyire Moses
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Atwakyire Moses has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
Ding Chen
7 shared publications- Ding Chen
College of Mechanical and Vehicle Engineering, Hunan University, Changsha, CHINA
5 shared publications Qiao Huang
4 shared publicationsYing Gui
State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, College of Mechanical and Vehicle Engineering Hunan University Changsha 410082 China
4 shared publicationsPeng Wan
State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, College of Mechanical and Vehicle Engineering Hunan University Changsha 410082 China
3 shared publicationsSiyuan Wang
Henan Province Engineering Research Center of Additive Manufacturing Aeronautical Materials Nanyang Institute of Technology Nanyang Henan 473004 China
3 shared publications
Latest Publications
- 5 February 2026
- Published by Elsevier in Next Research
- Vol. 6
A two-stage predicting approach of magnesium alloys based on a single target regression strategy
- 5 February 2026
- Published by Elsevier in Next Research
- Vol. 6
A two-stage predicting approach of magnesium alloys based on a single target regression strategy
- Open Access
- 17 November 2025
- Published by Elsevier in Next Materials
- Vol. 10
Accelerating age hardening behavior of Mg alloy using a data-driven screening strategy guided by machine learning
- 17 November 2025
- Published by Elsevier in Next Materials
- Vol. 10
Open AccessAccelerating age hardening behavior of Mg alloy using a data-driven screening strategy guided by machine learning
- 24 September 2025
- Published by Wiley in Advanced Engineering Materials
- Vol. 27 (22)
Octadecylamine‐Functionalized Graphene Oxide as a Lubricant Additive Fabricated by Microwave‐Assisted Ball Milling for Castor Oil
Enhancing plant‐derived lubricant additives to reduce friction and improve wear resistance has been a critical focus in advancing sustainable technologies. This study introduces a catalyst‐free method for synthesizing ODA@GO by functionalizing graphene oxide (GO) with octadecylamine (ODA) through microwave‐assisted ball milling. Experimental results demonstrate that ODA@GO, at a concentration of 0.05 wt%, exhibits excellent dispersion stability in castor oil for over 40 days. Tribological tests reveal that, under mixed lubrication conditions, the addition of ODA@GO to castor oil reduces the coefficient of friction by 45.36%, significantly outperforming the 34.05% reduction achieved by GO alone. The lubrication mechanism analysis suggests that ODA@GO enhances the thickness of the fluid lubrication film through simultaneous physical and chemical adsorption on the friction surfaces, thereby forming a robust protective barrier. This leads to significantly improved tribological properties and enhanced lubrication stability, achieving a coefficient of friction as low as 0.05 with the addition of ODA@GO. Furthermore, a consistent decreasing trend in the coefficient of friction is observed. This methodology offers a practical pathway for friction and wear mitigation in plant‐derived lubricants, with observed effects suggesting applicability in industrial environments. The findings may inform ongoing efforts toward sustainable tribology solutions.
- 24 September 2025
- Published by Wiley in Advanced Engineering Materials
- Vol. 27 (22)
Octadecylamine‐Functionalized Graphene Oxide as a Lubricant Additive Fabricated by Microwave‐Assisted Ball Milling for Castor Oil
Enhancing plant‐derived lubricant additives to reduce friction and improve wear resistance has been a critical focus in advancing sustainable technologies. This study introduces a catalyst‐free method for synthesizing ODA@GO by functionalizing graphene oxide (GO) with octadecylamine (ODA) through microwave‐assisted ball milling. Experimental results demonstrate that ODA@GO, at a concentration of 0.05 wt%, exhibits excellent dispersion stability in castor oil for over 40 days. Tribological tests reveal that, under mixed lubrication conditions, the addition of ODA@GO to castor oil reduces the coefficient of friction by 45.36%, significantly outperforming the 34.05% reduction achieved by GO alone. The lubrication mechanism analysis suggests that ODA@GO enhances the thickness of the fluid lubrication film through simultaneous physical and chemical adsorption on the friction surfaces, thereby forming a robust protective barrier. This leads to significantly improved tribological properties and enhanced lubrication stability, achieving a coefficient of friction as low as 0.05 with the addition of ODA@GO. Furthermore, a consistent decreasing trend in the coefficient of friction is observed. This methodology offers a practical pathway for friction and wear mitigation in plant‐derived lubricants, with observed effects suggesting applicability in industrial environments. The findings may inform ongoing efforts toward sustainable tribology solutions.
- 5 June 2024
- Published by Springer Nature in JOM
- Vol. 76 (8) , 4388-4403
Unraveling Magnesium Alloy Corrosion Patterns Through Unsupervised Machine Learning: Exploring Clustering Techniques for Enhanced Insight
- 5 June 2024
- Published by Springer Nature in JOM
- Vol. 76 (8) , 4388-4403
Unraveling Magnesium Alloy Corrosion Patterns Through Unsupervised Machine Learning: Exploring Clustering Techniques for Enhanced Insight
- Open Access
- 27 December 2023
- Published by Elsevier in SSRN Electronic Journal
Intelligent Prediction and Analysis of Mechanical Properties of Magnesium Alloys Using Interpretable Machine Learning
The Magnesium-rare earth alloy dataset was compiled by collecting data from the experiment and utilizing machine learning (ML) models to predict the mechanical properties of 348 sample tests. The proportion between the predicted and experimental results produced by different ML models demands more advanced regression methods to obtain better results. Utilizing magnesium chemical compositions at elevated temperatures as input variables and mechanical properties as output variables, four different machine learning (ML) models were employed namely (i.e.) Random Forest (RF), Extra Tree (ET), Gradient Boost (GB), and XG Boost (XGB) to resolve this difficult problem. Each single algorithm aimed to predict the mechanical properties of Mg-rare earth alloy i.e. ultimate tensile strength (UTS), yield strength (YS), and elongation (EL). Subsequently, the data-driven intelligent prediction modeling technique called Super learner (SL) was employed to integrate the single models into the stacked model approach to enhance prediction accuracy. The results obtained using SL models demonstrated enhanced prediction accuracy for UTS, YS, and EL. The findings further demonstrate enhanced prediction ability by outperforming other approaches as demonstrated by lower RMSE and higher R2 compared to previous studies. The reason to choose SL is because of its robustness, less prone to overfitting, and is also widely known for its better scalability, simplicity, and ability to handle noisy. The SL model is an optimal approach for predicting the properties of Mg-rare earth alloys. The proposed SL approach can serve as a tool for predicting the properties of Mg alloys.
- 27 December 2023
- Published by Elsevier in SSRN Electronic Journal
Open AccessIntelligent Prediction and Analysis of Mechanical Properties of Magnesium Alloys Using Interpretable Machine Learning
The Magnesium-rare earth alloy dataset was compiled by collecting data from the experiment and utilizing machine learning (ML) models to predict the mechanical properties of 348 sample tests. The proportion between the predicted and experimental results produced by different ML models demands more advanced regression methods to obtain better results. Utilizing magnesium chemical compositions at elevated temperatures as input variables and mechanical properties as output variables, four different machine learning (ML) models were employed namely (i.e.) Random Forest (RF), Extra Tree (ET), Gradient Boost (GB), and XG Boost (XGB) to resolve this difficult problem. Each single algorithm aimed to predict the mechanical properties of Mg-rare earth alloy i.e. ultimate tensile strength (UTS), yield strength (YS), and elongation (EL). Subsequently, the data-driven intelligent prediction modeling technique called Super learner (SL) was employed to integrate the single models into the stacked model approach to enhance prediction accuracy. The results obtained using SL models demonstrated enhanced prediction accuracy for UTS, YS, and EL. The findings further demonstrate enhanced prediction ability by outperforming other approaches as demonstrated by lower RMSE and higher R2 compared to previous studies. The reason to choose SL is because of its robustness, less prone to overfitting, and is also widely known for its better scalability, simplicity, and ability to handle noisy. The SL model is an optimal approach for predicting the properties of Mg-rare earth alloys. The proposed SL approach can serve as a tool for predicting the properties of Mg alloys.