Prediction of Friction Stir Processed AZ31 Magnesium Alloy Micro-Hardness Using Artificial Neural Networks

Darras, Basil M.; Deiab, Ibrahim

doi:10.4028/www.scientific.net/amr.1043.91

Cited by 7 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The bottom surface is further away from the heat source, which means that lower temperature and more grain refinement are expected away from the top edge. These results are supported by the literature (Darras, Khraisheh, Abu-Farha and Omar, 2007; Darras, Omar and Khraisheh, 2007; Darras, 2012; Darras and Kishta, 2013; Darras et al , 2014; Afrin et al , 2008).…”

Section: Experimental Worksupporting

confidence: 91%

Micro-hardness prediction of friction stir processed magnesium alloy via response surface methodology

Darras

2017

MMMS

Self Cite

View full text Add to dashboard Cite

Purpose The purpose of this paper is to present a model to predict the micro-hardness of friction stir processed (FSPed) AZ31B magnesium alloy using response surface methodology (RSM). Another objective is to identify process parameters and through-thickness position which will give higher micro-hardness values. Moreover, the study aims at defining the factor that exhibits the most effect on the micro-hardness. Friction stir processing (FSP) machine can then be fed with the optimized parameters to achieve desirable properties. Design/methodology/approach An experimental setup was designed to conduct FSP. Several AZ31B magnesium samples were FSPed at different combinations of rotational and translational speeds. The micro-hardness of all the combinations of process parameters was measured at different through-thickness positions. This was followed by an investigation of the three factors on the resulting micro-hardness. RSM was then used to develop a model with three factors and three levels to predict the micro-hardness of FSPed AZ31 magnesium alloy within the covered range. The analyses of variance in addition to experimental verification were both used to validate the model. This was followed by an optimization of the response. Findings The model showed excellent capability of predicting the micro-hardness values as well as the optimum values of the three factors that would result in better micro-hardness. The model was able to capture the effects of rotational speed, translational speed, and through-thickness position. Results suggest that micro-hardness values were mostly sensitive to changes in tool rotational speed. Originality/value FSP is considered to be one of the advanced microstructural modification techniques which is capable of enhancing the mechanical properties of light-weight alloys. However, the lack of accurate models which are capable of predicting the resulted properties from process parameters hinders the widespread utilization of this technique. At the same time, RSM is considered as a vital branch of experimental design due to its ability to develop new processes and optimize their performance. Hence, the developed model is very beneficial and is meant to save time and experimental effort toward effective use of FSP to get the desired/optimum micro-hardness distribution.

show abstract

Section: Experimental Worksupporting

confidence: 91%

Micro-hardness prediction of friction stir processed magnesium alloy via response surface methodology

Darras

2017

MMMS

Self Cite

View full text Add to dashboard Cite

show abstract

“…The further from the top surface, the lower the temperature and the more grain refinement attained. Similar observations were reported in literature [26][27][28][29]. Figure 5 introduces a comparison of the micro-hardness values between as-received, FSPed and FSPed Mg AZ31B/SiC composite at 1200 rpm and 100 mm/min.…”

Section: Resultssupporting

confidence: 83%

Mechanical Behaviour of Mg/SiC Composite Processed by Friction Stir Processing

Darras¹,

Nazzal²

2021

World Congress on Mechanical, Chemical, and Material Engineering

Self Cite

View full text Add to dashboard Cite

Due to their good mechanical and physical properties as well as their low densities, Magnesium Matrix Composites are considered as an attractive option for different aerospace and other commercial applications. Lately, Friction Stir Processing (FSP) which is considered as an effective modification to Friction Stir Welding (FSW) has shown a great protentional as successful alternative for fabricating Metal Matrix Composite (MMC). One major difference between conventional engineering materials and MMC is the addition of reinforcing elements that results in an overall enhancement of the composite's stiffness and strength. This paper discusses the effect of using Silicon Carbide (SiC) reinforcement particles in AZ 31B magnesium alloy base composite using FSP. Effect of reinforcement particles on the thermal profile, microstructure, micro-hardness, tensile properties and impact toughness are discussed. In addition, the effects of tool rotational and translational speeds on the microstructure and micro-hardness of the Mg/SiC surface composite have been examined. Mg/SiC surface composite was successfully fabricated using FSP. Results suggest that Mg/SiC surface composite can be used to significantly enhance the micro-hardness and the ultimate tensile strength within the stir zone.

show abstract

“…Artificial intelligence (AI) is a broad field of computer science that focuses on creating intelligent machines or programs that can accomplish activities that would generally necessitate human intelligence and is widely applicable in materials science. Moreover, AI has known an increasing interest in the Friction Stir Welding applications; it has been used to detect defects in materials degradation [11], to forecast the mechanical properties of materials [12], and tensile strength prediction [13].…”

Section: Introductionmentioning

confidence: 99%

A Tree-Driven Ensemble Learning Approach to Predict FS Welded Al-6061-T6 Material Behavior

Dorbane

Harrou

Sun

2022

2022 7th International Conference on Frontiers of Signal Processing (ICFSP)

View full text Add to dashboard Cite

This paper proposes a machine learning approach to forecast the mechanical behavior of an aluminum alloy, Al6061-T6, in the case of friction stir welding. Essentially, we investigate the performance of the bagged trees regression (BT) in forecasting the stress-strain curve of an aluminum alloy. This choice's motivation is due to BT's ability to improve the performance of machine learning models by combining multiple learners versus single regressors. Actual data was gathered by performing uniaxial tensile testing on both base material and joined using FSW at a deformation speed of 10 -3 s-1 . Then, the performance of the BT model is compared to that of the Support Vector regression, and it proved to be more accurate.

show abstract

Prediction of Friction Stir Processed AZ31 Magnesium Alloy Micro-Hardness Using Artificial Neural Networks

Cited by 7 publications

References 14 publications

Micro-hardness prediction of friction stir processed magnesium alloy via response surface methodology

Micro-hardness prediction of friction stir processed magnesium alloy via response surface methodology

Mechanical Behaviour of Mg/SiC Composite Processed by Friction Stir Processing

A Tree-Driven Ensemble Learning Approach to Predict FS Welded Al-6061-T6 Material Behavior

Contact Info

Product

Resources

About