Investigating the Thermo-Mechanical Properties of Aluminum/Graphene Nano-Platelets Composites Developed by Friction Stir Processing

Gamil, Mohammed; Ahmed, Mohamed M. Z.

doi:10.1007/s12541-020-00355-3

Cited by 18 publications

(5 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to verify the accuracy and reliability of the machine learning model developed in this article, we compared the machine learning prediction results with some random experimental data in the dataset with the prediction results, as shown in Supplementary Figures S1 and S2. In addition, in order to judge the generalisation ability of the model, we compare the machine learning prediction results with the experimental results outside the dataset [32][33][34][35], as shown in Figure 6. From the above three figures, it can be seen that the machine learning prediction results have small differences with all the similar data, and the MAPE are all within 10%, regardless of whether these data are included In order to verify the accuracy and reliability of the machine learning model developed in this article, we compared the machine learning prediction results with some random experimental data in the dataset with the prediction results, as shown in Supplementary Figures S1 and S2.…”

Section: Interpretable Machine Learning and Validationmentioning

confidence: 99%

“…From the above three figures, it can be seen that the machine learning prediction results have small differences with all the similar data, and the MAPE are all within 10%, regardless of whether these data are included In order to verify the accuracy and reliability of the machine learning model developed in this article, we compared the machine learning prediction results with some random experimental data in the dataset with the prediction results, as shown in Supplementary Figures S1 and S2. In addition, in order to judge the generalisation ability of the model, we compare the ma-chine learning prediction results with the experimental results outside the dataset [32][33][34][35], as shown in Figure 6. From the above three figures, it can be seen that the machine learning prediction results have small differences with all the similar data, and the MAPE are all within 10%, regardless of whether these data are included in the dataset or not.…”

Section: Interpretable Machine Learning and Validationmentioning

confidence: 99%

See 1 more Smart Citation

Explanatory Machine Learning Accelerates the Design of Graphene-Reinforced Aluminium Matrix Composites with Superior Performance

Xue,

Huang,

et al. 2023

Metals

View full text Add to dashboard Cite

Addressing the exceptional properties of aluminium alloy composites reinforced with graphene, this study presents an interpretable machine learning approach to aid in the rapid and efficient design of such materials. Initially, data on these composites were gathered and optimised in order to create a dataset of composition/process-property. Several machine learning algorithms were used to train various models. The SHAP method was used to interpret and select the best performing model, which happened to be the CatBoost model. The model achieved accurate predictions of hardness and tensile strength, with coefficients of determination of 0.9597 and 0.9882, respectively, and average relative errors of 6.02% and 5.01%, respectively. The results obtained from the SHAP method unveiled the correlation between the composition, process and properties of aluminium alloy composites reinforced with graphene. By comparing the predicted and experimental data in this study, all machine learning models exhibited prediction errors within 10%, confirming their ability to generalise. This study offers valuable insights and support for designing high-performance aluminium matrix composites reinforced with graphene and showcases the implementation of machine learning in materials science.

show abstract

Section: Interpretable Machine Learning and Validationmentioning

confidence: 99%

Section: Interpretable Machine Learning and Validationmentioning

confidence: 99%

Explanatory Machine Learning Accelerates the Design of Graphene-Reinforced Aluminium Matrix Composites with Superior Performance

Xue,

Huang,

et al. 2023

Metals

View full text Add to dashboard Cite

show abstract

“…The hard precipitates hinder the movement of dislocations to grow further as cracks and improved the fatigue strength. The climb dissociation movement in the tensile-tensile repeated load gets hampered due to the presence of hard ceramic based precipitates [41]. However, adding more SiO 2 particle in to the weld pool reduced the fatigue strength.…”

Section: Fatigue Behaviourmentioning

confidence: 99%

Friction stir processing of nanofiller assisted AISI 1010 steel-CDA 101 copper dissimilar welds: a strength factor approach

Giridharan¹,

Sevvel²,

Ramadoss³

et al. 2022

Metall. Res. Technol.

View full text Add to dashboard Cite

In this research study the effects of adding nano fillers such as SiO2, graphene nanoplatelets (Gnps) and biochar on to the weld pool of dissimilar AISI-SAE 1010 Steel- CDA 101 copper were investigated. The main aim of this research study was to investigate the effect of adding ceramic and carbon rich secondary reinforcements on to the friction stir weld (FSW) pool of dissimilar metals and its relative outcomes. The mechanical properties such as tensile strength, yield strength, % of elongation, hardness and fatigue strength were investigated in the form of the strength factor approach. According to the results, the highest strength factor of 98 was obtained for welds made using Gnps of about 1.0 wt.% with constant axial load of 5 kN, traverse speed of 30 mm/min, rotational speed of 900 rpm, dwell time of 5 s and plunging depth of 0.2 mm. The highest tensile strength of 225 MPa and a fatigue strength of 168 MPa was noted for the weld using 2 wt.% Gnps in the weld pool. However, the biochar addition of 2.0 wt.% on to the weld bead positioned the second highest strength factor of 88 due to its solid lubricity. In all the welding processes, large doses of fillers produced undesirable strength factor values. The microstructure of both the weld and tool shows desirable effects for nanoparticle assisted welds. The HAZ and TMAZ grains were refined due to the inclusion of the nanoparticles. The result shows that naturally acquired biochar nanoparticles have the potential of replacing high cost nanofillers in joining metals with more than 85% close to the high cost fillers for the same output. These properties improved dissimilar copper-steel welded plate joints that could be used in automotive, defence, aerospace and structural applications.

show abstract

“…132,133 Poor thermal conductivity and mismatched coefficient of thermal expansion of component materials such as Cu = ∼17ppm K −1 and Si = ∼4ppm K −1 induces high thermo-mechanical stresses and adversely effects the life span and reliability of the smart electronic devices. 134 The focus of modern technical development is on smaller and more efficient technologies which display better thermal management systems. As a result, their greater application in components needing effective thermal control is likely to happen soon.…”

Section: Potential Of Graphene-reinforced Cu and Al Nanocomposites Fo...mentioning

confidence: 99%

Engineering Electrical and Thermal Attributes of Two-Dimensional Graphene Reinforced Copper/Aluminium Metal Matrix Composites for Smart Electronics

Khanna

Singh²,

Kumar³

et al. 2022

ECS J. Solid State Sci. Technol.

View full text Add to dashboard Cite

Rising demand for reliable thermally and electrically conductive and stable, light weight, and mechanically enduring materials in architecting smart electronics has accelerated the research in engineering metal-matrix composites (MMCs). Among these, copper (Cu) and aluminium (Al) based MMCs are popular owing to high electrical conductivity, but large heat dissipation in compact electronic gadgets is still challenging. The reinforcement of Cu/Al with graphene caters to the problem of heat dissipation, strengthens mechanical endurance, and optimizes electronic and thermal conductivities as per device architecture and application. Here we systematically review the state-of-the-art Cu/Al MMCs using graphene reinforcement with enhanced electrical, thermal, and mechanical attributes for smart electronics manufacturing and discuss the fundamentals for optimising the electrical and thermal charge transport in Cu/Al MMCs through graphene reinforcement. In addition, we discuss challenges, alternate solutions, and advanced prospects of graphene reinforced Cu/Al MMCs for smart electronics manufacturing.

show abstract

Investigating the Thermo-Mechanical Properties of Aluminum/Graphene Nano-Platelets Composites Developed by Friction Stir Processing

Cited by 18 publications

References 37 publications

Explanatory Machine Learning Accelerates the Design of Graphene-Reinforced Aluminium Matrix Composites with Superior Performance

Explanatory Machine Learning Accelerates the Design of Graphene-Reinforced Aluminium Matrix Composites with Superior Performance

Friction stir processing of nanofiller assisted AISI 1010 steel-CDA 101 copper dissimilar welds: a strength factor approach

Engineering Electrical and Thermal Attributes of Two-Dimensional Graphene Reinforced Copper/Aluminium Metal Matrix Composites for Smart Electronics

Contact Info

Product

Resources

About