Marwah Ghazi Kareem
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Marwah Ghazi Kareem has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Hadi Hasan Mussttaf
Electrical Engineering Technical College , Middle Technical University , Baghdad , Iraq
1 shared publication - Kawther K. Younus
Electrical Engineering Technical College Middle Technical University Baghdad Iraq
1 shared publication - Luay Sadeq Al-Ansari
Mechanical Engineering Department, Faculty of Engineering, University of Kufa, Iraq
1 shared publication - Mujtaba A. Flayyih
Biomedical Engineering Department, College of Engineering and Technologies, Al-Mustaqbal University, Hillah, Iraq
1 shared publication - Orhan Sabah Abdullah
University of Technology
1 shared publication - Sadiq Emad Sadiq
Al-Furat Al-Awsat Technical University
1 shared publication
Latest Publications
- 25 April 2025
- Published by Taylor & Francis in Australian Journal of Mechanical Engineering
- Vol. 24 (1) , 14-27
Innovative fabrication and static analysis of porous functionally graded beams: experimental and finite element investigations
- 25 April 2025
- Published by Taylor & Francis in Australian Journal of Mechanical Engineering
- Vol. 24 (1) , 14-27
Innovative fabrication and static analysis of porous functionally graded beams: experimental and finite element investigations
- Open Access
- 1 January 2025
- Published by Walter de Gruyter GmbH in Open Engineering
- Vol. 15 (1)
Hybrid mechanics-informed machine learning models for predicting mechanical failure in graphene sponge: a low-data strategy for mechanical engineering applications
Graphene sponge – a structure derivative of graphene that is porous and light-weight – exhibits properties including mechanical and structurally features that are exciting for advanced utilization in a wide variety of engineered applications. As such, the challenging aspect of graphene sponge is accurately inferring its failure strength since it possesses complex hierarchical morphology with limited experimental data. In this study we propose a hybrid approach to predict 3D graphene sponge mechanical failure of products using a new method of taking experimental physical measurements, complemented with machine learning models – Gaussian Process Regression (GPR) and Bayesian Ridge Regression (BRR). To formulate mechanical failure predictions we have characterized our fabricated samples using Raman, X-ray diffraction (XRD), BET surface analysis, nanoindentation and tensile testing methods. For GPR and BRR models, we created and engineered features to enrich the mechanical failure model predictions. GPR performed better than BRR with R 2 = 0.967 and MAE = 0.192 MPa (versus 0.953 and 0.220 MPa) based on R 2 and MAE results. The results provided evidence that AI-based models informed with physics can be productive in low-data mechanical predictions, which supports intelligent design of nanostructured materials.
- 1 January 2025
- Published by Walter de Gruyter GmbH in Open Engineering
- Vol. 15 (1)
Open AccessHybrid mechanics-informed machine learning models for predicting mechanical failure in graphene sponge: a low-data strategy for mechanical engineering applications
Graphene sponge – a structure derivative of graphene that is porous and light-weight – exhibits properties including mechanical and structurally features that are exciting for advanced utilization in a wide variety of engineered applications. As such, the challenging aspect of graphene sponge is accurately inferring its failure strength since it possesses complex hierarchical morphology with limited experimental data. In this study we propose a hybrid approach to predict 3D graphene sponge mechanical failure of products using a new method of taking experimental physical measurements, complemented with machine learning models – Gaussian Process Regression (GPR) and Bayesian Ridge Regression (BRR). To formulate mechanical failure predictions we have characterized our fabricated samples using Raman, X-ray diffraction (XRD), BET surface analysis, nanoindentation and tensile testing methods. For GPR and BRR models, we created and engineered features to enrich the mechanical failure model predictions. GPR performed better than BRR with R 2 = 0.967 and MAE = 0.192 MPa (versus 0.953 and 0.220 MPa) based on R 2 and MAE results. The results provided evidence that AI-based models informed with physics can be productive in low-data mechanical predictions, which supports intelligent design of nanostructured materials.