Next Article in Journal
Development of the RF-MEAM Interatomic Potential for the Fe-C System to Study the Temperature-Dependent Elastic Properties
Next Article in Special Issue
Effect of Annular Laser Metal Deposition (ALMD) Process Parameters on Track Geometry and Thermal History on Ti6Al4V Alloy Clad
Previous Article in Journal
Pulsed Laser Spot Welding Thermal-Shock-Induced Microcracking of Inconel 718 Thin Sheet Alloy
Previous Article in Special Issue
A Multilevel Physically Based Model of Recrystallization: Analysis of the Influence of Subgrain Coalescence at Grain Boundaries on the Formation of Recrystallization Nuclei in Metals
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Materials
Volume 16
Issue 10
10.3390/ma16103777
materials-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles thumb_up
...
Endorse textsms
...
Comment
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Prediction of Tool Eccentricity Effects on the Mechanical Properties of Friction Stir Welded AA5754-H24 Aluminum Alloy Using ANN Model

by
Ahmed R. S. Essa
1,2,
Mohamed M. Z. Ahmed
3,*,
Aboud R. K. Aboud
2,
Rakan Alyamani
4,* and
Tamer A. Sebaey
4,5
1
Faculty of Engineering, King Salman International University, El-Tor 45615, Egypt
2
Mechanical Department, Faculty of Technology and Education, Suez University, Suez 43512, Egypt
3
Mechanical Engineering Department, College of Engineering at Al Kharj, Prince Sattam bin Abdulaziz University, Al Kharj 11942, Saudi Arabia
4
Engineering Management Department, College of Engineering, Prince Sultan University, Riyadh 12435, Saudi Arabia
5
Mechanical Design and Production Department, Faculty of Engineering, Zagazig University, Zagazig 44519, Egypt
*
Authors to whom correspondence should be addressed.
Materials 2023, 16(10), 3777; https://doi.org/10.3390/ma16103777
Submission received: 23 March 2023 / Revised: 12 May 2023 / Accepted: 15 May 2023 / Published: 17 May 2023
(This article belongs to the Special Issue Multiscale Characterization and Computational Modeling/Simulation of Metallic Materials)
Browse Figures
Versions Notes

Abstract

:
The current study uses three different pin eccentricities (e) and six different welding speeds to investigate the impact of pin eccentricity on friction stir welding (FSW) of AA5754-H24. To simulate and forecast the impact of (e) and welding speed on the mechanical properties of friction stir welded joints for (FSWed) AA5754-H24, an artificial neural network (ANN) model was developed. The input parameters for the model in this work are welding speed (WS) and tool pin eccentricity (e). The outputs of the developed ANN model include the mechanical properties of FSW AA5754-H24 (ultimate tensile strength, elongation, hardness of the thermomechanically affected zone (TMAZ), and hardness of the weld nugget zone (NG)). The ANN model yielded a satisfactory performance. The model has been used to predict the mechanical properties of the FSW AA5754 aluminum alloy as a function of TPE and WS with excellent reliability. Experimentally, the tensile strength is increased by increasing both the (e) and the speed, which was already captured from the ANN predictions. The R2 values are higher than 0.97 for all the predictions, reflecting the output quality.

1. Introduction

As experimentally proven by Thomas et al. [1] in 1991, friction stir welding (FSW) is a solid-state welding process that joins two plates using a non-consumable rotating tool to heat and stir the material plates at the interface of the joint. FSW generates frictional heat through mechanical stirring between the rotating tool and materials to produce strong joints. This process can be utilized for various materials, including aluminum, titanium, steel, and copper alloys, and is known for its ability to produce high-quality defect-free weldments [1]. Friction stir welding (FSW) provides high-integrity joints for welding metal alloys in a solid state. FSW is used in various applications, including shipbuilding, aerospace, automotive, and railways [2,3,4,5,6,7]. For low, medium, and high deformation resistance alloys, investigations have been conducted on how the welding parameters and tool shape affect the quality of the weld [8,9,10,11]. When compared to conventional arc welding methods, FSW offers a number of benefits [12,13,14]. FSW does not experience issues such as thermal distortion, gas porosity brought on by hydrogen absorption during welding, softening of the heat-affected zone, or difficulties in linking sensitivity to solidification cracking, which are particularly frequent in fusion welding processes [15,16,17].
Artificial neural network (ANN) is a technology used in the field of Artificial Intelligence that represents an interconnected network consisting of multi-layered nodes (neurons), including input and output nodes and weighted connections that are meant to simulate a biological neural network [18,19]. Through years of experiments and research, ANN techniques have demonstrated robust learning capabilities and high prediction accuracy through its ability to identify complex mathematical relationships between input and output variables [20]. Accordingly, ANN models have been widely used in the literature as predictive techniques in a range of different fields, including healthcare [21,22], sustainable development [18,19,23], agriculture [23,24], and material science [25,26,27,28].
More specifically, in the field of material science, various ANN models have been used to study friction stir welding. For example, Jamalian et al. [29] used an ANN model to study the joint parameters, mechanical properties, and microstructures of multi-pass FSW of AA5086-H34 joints. Darzi Naghibi et al. [30] also employed an ANN based model to predict the optimal parameters of FSW, including rotary speed, welding speed, and tool offset on maximizing the tensile strength for AA 5052 and AISI 304 joints. Similarly, Buffa et al. [31] developed an ANN model to predict the microhardness values and the microstructure of the FSW of Ti–6Al–4V titanium alloy joints using different process parameters. Another example is presented by D’Orazio et al. [32] where they developed a multi-variable ANN prediction model to predict the vertical force that occurs during the FSW of an AZ31 magnesium alloy sheet. Several other examples exist in the literature of the use of ANN in studying FSW [33,34,35].
In order to predict the impact of pin eccentricity on the mechanical properties of AA 5754-H24 FSW aluminium alloys and to identify the ideal conditions for input parameters to produce FSW joints with good mechanical properties, computer-aided ANN modelling has recently become widely used in the field of friction stir welding [4,31,36,37,38]. Many publications are found in the literature on FSW of aluminum alloys, focusing on the correlation between the friction stir welding parameters and the mechanical properties [31,39]. More recently, research on modern trends involves the effects of tool eccentricity [40,41], tool pin eccentricity [42], and tool pin or shoulder eccentricity in friction stir welding [43,44,45].
Tool eccentricity or tool runout occurs due to the tool offset with respect to the spindle centre. In general, two types of eccentricity can be defined, namely, pin profile eccentricity and tool eccentricity derived from concentric oscillations [43]. Tool pin eccentricity and welding speeds can significantly affect the quality of the friction stir welded joints. Tool pin eccentricity can affect the string action and material flow during the FSW process. Additionally, the material flow behavior around the rotating tool will help achieve high-quality and defect-free joints. Furthermore, the welding speed of the FSW process significantly affects the welded joints’ quality and properties. Due to the selected low welding speed, the heat generated during FSW can accumulate, thereby producing defected joints. On the other hand, when the welding speed is high, the material may not be sufficiently softened, and the material in the stir zone may have insufficient stirring, leading to the production of defected joints. Thus, detecting a suitable welding speed is crucial for conducting defect-free and high-quality weldments using the FSW process [43].
However, there seems to be a lack of research in the literature on the correlation between the tool pin eccentricity and the mechanical properties of FSW of aluminum alloys. Although a few numerical models for the FSW of aluminum alloys can be found in the literature [31,43,46,47], none of them deal with tool pin eccentricity in the process input parameters. This study aims to determine the correlation between welding speed (WS), tool pin eccentricity, and mechanical characteristics of the aluminum alloy FSW AA5754-H24. Neural networks were designed and properly trained based on the experimental data obtained at a tool rotational speed of 600 rpm, different welding speeds, and different values of tool pin eccentricity.
The remainder of this article is structured as follows. Section 2 discusses the data collection methodology for the experimental data used to train the ANN. Section 3 outlines the development and training of the ANN model, as well as the produced results. Section 4 presents a discussion of the produced results from the ANN model. Finally, an overall conclusion of this article is presented in Section 5.

2. Collecting the Experimental Data

At Suez University, the friction stir welding of AA5754-H24 aluminum alloy butt joint was carried out using a locally produced FSW machine [48,49,50,51]. The welding samples are produced on two plates that are 5 mm thick, 100 mm broad, and 120 mm long. Table 1 provides the chemical breakdown of the AA5754-H24 aluminium alloys. Table 2 is a list of the measured mechanical characteristics of the employed Al alloys.
The welding tool is made of an HRC62 heat-treated cold-worked tool steel rod W302 (0.1% Si, 0.39% C, 5.2% Cr, 0.40% Mn, 1.4% Mo, 0.95% V, and 90.6 wt%). Three tool designs are prepared, as shown in Figure 1. The first is the tool without eccentricity (T0), in which the pin and shoulder axes are aligned. The second tool contains a pin eccentricity of 0.2 mm (T2), i.e., the pin axis is shifted by 0.2 mm from the tool axis. The third tool contains a pin eccentricity of 0.8 mm (T8), i.e., the axis of the designed pin has been shifted 0.8 mm from the axis of the tool. In every instance, a pin that is 4.6 mm long and 6 mm in diameter with 19 mm shoulder diameter and a 2° concavity is employed.
The welding speeds used in FSW are 50, 100, 150, 200, 300, and 500 mm/min. In each case, a rotation speed of 600 rpm is used along with a 0.2 mm tool plunge depth and a 3° tilt angle.
By evaluating the joint tensile characteristics and calculating the Vickers hardness in the heat-affected zone (HAZ) and weld nugget zone (WNZ), the FSW joints are evaluated. A “Instron” tensile testing machine with a 300 KN capability is used for tensile testing. Flat tensile specimens with the dimensions specified in Figure 2 are cut perpendicular to the welding direction. The moving head of the machine moves at a velocity of 0.1 mm/s in accordance with ASTM: E8/E8M-16a standard. With a 1 kg load close to the section centerline, the Vickers hardness of the weld nuggets and the thermomechanically affected zone (TMAZ) of the cross sections perpendicular to the welding line direction are measured. To evaluate the mechanical performance of the welding, measurements were made of the ultimate tensile strength, elongation, and hardness of FSWed nugget zone (WNZ) and thermomechanically affected zone (TMAZ). The measured data are shown in Table 3.
For FSW joints made with T0 and T2 tools, it has been found that the tensile strength increases as the welding speed rises. The highest possible tensile strength is reached at 500 mm/min welding speed, and it lowers for the FSW joints made with tool T8 (highest speed). This may be caused by the rate at which heat is applied, which regulates the amount of plastic deformation that occurs. Moreover, a tool pin that is eccentric by more than 0.3 mm produces more heat input [42,52]. This causes a stress concentration, which greatly worsens the mechanical characteristics of the weld joint. Additionally, lowering the rotational speed and increasing the welding speed (by increasing the revolutionary pitch) reduces the heat input. This increases the tensile strength as the welding speed is increased. However, decreasing the welding speed causes more heat input and a low tensile strength [36].
The FSWed nugget zone and the TMAZ are used to measure the hardness values of the FSW welded joints. The junction with the maximum hardness is one that has been welded using a T2 tool with an eccentricity of (e 0.2) at a welding speed of 500 mm/min. The TMAZ is found to have less hardness than the weld nugget zone.
Figure 3 shows the top surface view of the AA5754-H24 FSW joints at rotating speeds of 600 rpm and various welding speeds of 50, 100, 150, 200, 300, and 500 mm/min using the FSW tools T0, T2, and T8 previously discussed. All joints appear nearly identical on the top surface, which is mostly affected by the shoulder, with the exception that the top surfaces of joints fused at low welding speeds are smoother and have less flash on both the advancing side (AS) and the retreating side (RS). On the other hand, it can be observed that the welding speed has a noticeable impact on the way the surface of welded joints looks. At these high welding speeds, beginning at 300 mm/min, the semicircular banding features visibly grow broader. The measured semicircular banding features spacing agrees with the calculated ones, claims Krishnan [53]. For the welding speeds of 50, 100, 150, 200, 300, and 500 mm/min, the measured semicircular spacing (revolutionary pitch) in this study is 0.083, 0.167, 0.25, 0.333, 0.5, and 0.83 mm, respectively. This spacing appears to be almost identical to the spacing in Figure 3.

3. Methodology of the ANN Model

Most manufacturing processes are complex in nature, highly non-linear, and have a large number of input parameters. Currently, no mathematical models can describe the behavior of these processes. Due to the cost-effective and relatively easily understandable nature of ANN models and their ability to be trained using data collected from these complex manufacturing processes, they have been extensively used as predictive techniques [54,55].
The input layer, the hidden layer, and the output layer are the three layers that constitute an ANN. All of the input parameters are contained in the input layer. The hidden layer processes data from the input layer, after which the final (output) layer computes the next output vector. In Figure 4, the three layers of the ANN model utilized in this study are shown schematically.
An ANN consists of simple synchronous processing elements that are inspired by the biological nervous system. The basic unit in the ANN is the neuron. Neurons are connected by links known as synapses, and associated with each synapse is a weight factor. In this work, two training algorithms (gradient descent with momentum algorithm, and Levenberg–Marquardt Algorithm) were used with a single hidden layer (eight neurons). The inputs and outputs were normalized in the range of 0:1. Thus, the network architecture consisted of two input neurons, eight hidden neurons with a nonlinear activation function, a logistic sigmoid (logsig), and four output neurons with a linear activation function. Table 4 shows the trained network weights and biases.
The ANN is trained and tested using MATLAB. After training the ANN successfully, it is tested using measured data that are different from what was used in the training processes. The number of neurons is increased through the training process from five to nine to define the output accurately.
To train and test an ANN neural network, we need ANN training (patterns), input data, and corresponding target values (measured data). A total of 18 patterns have been obtained in this work from the experiments. The welding speed and tool pin eccentricity are inputs to the network, while the outputs include tensile strength, elongation, TMAZ hardness, and weld nugget zone hardness. As a result, the architecture of the ANN changes to 2-8-4, where 2 represents the input values, 8 represents the number of hidden layer neurons, and 4 represents the outputs. Four measured results have been utilized as test data, and fourteen out of a total of eighteen measured results have been used as data sets to train the network (75% training data against 25% test data). The measured results are used to develop and test the ANN model.

4. Results and Discussion

Figure 5 shows the variation in the mechanical properties of AA5754-H24 FSW joints with tool pin eccentricity and welding speed, and the predicted new data obtained from the network after the training process. As can be seen from the figure, the predicted values match very well with the measured data.
The results of the training and testing of the ANN model for the measured and predicted data are given in Figure 6a,b. The results show that both the measured and predicted data sets are highly similar, with variance values (R) of 0.9986 and 0.9889 for training and testing, respectively. Figure 6c–f compare the measured and predicted results of the test data. From these figures, it can be observed that the measured and predicted values are also highly similar. The ability of a neural network to reliably anticipate the results of the test data that have not yet been seen is, nevertheless, its main criterion for quality.
The arithmetical mean of the number of inputs and outputs is typically used to determine how many neurons should be employed in the hidden layer. As a result, it is advised to employ a scaled conjugate gradient (SCG) with eight hidden layer neurons in the current application. Five to nine hidden layers are used in this application’s testing. Based on these outcomes, the model performed well. The network with nine hidden layer neurons has produced the same accuracy of results for the eight hidden layer neurons. Accordingly, only eight hidden layer neurons have been used in the present application.
The prediction accuracy for the results produced by the network is based on statistical methods. Errors occurring during the training and testing processes are called the root-mean-squared (RMS), an absolute fraction of variance (R2), and mean error percentage values. These are calculated as follows [14]:
R M S = ( ( 1 / p ) ∑ | t j − o j | 2 ) 1 / 2 ,   R 2 = 1 − ( ∑ j ( t j − o j ) 2 ∑ j ( o j ) 2 ) ,
m e a n   %   e r r o r = 1 p ∑ j ( t j − o j t j × 100 )
The results are shown in Table 5.
As can be seen in Table 5, the absolute fraction of variance (R2) values for the outputs of the tensile strength, elongation, hardness of TMAZ and weld metal for the training data are all greater than 0.99 and for the test data are all greater than 0.98, except for the hardness of the TMAZ, which is 0.97, respectively. Based on these results, it can be concluded that the proposed model is highly accurate.

5. Conclusions

In this study, AA5754-H24 has been friction-welded using a wide range of welding speeds at three different tool pin eccentricities, and an ANN model has been developed to predict mechanical properties. The experimental results have been used to train the ANN model used afterward for prediction. Based on the obtained results, the following conclusions can be outlined:
  • The ANN model has been developed based on the FSW experimental work data of AA5754-H24, in which FS was welded using 0, 0.2, and 0.8 mm TPE and welding speeds of 50, 100, 150, 200, 300, and 500 mm/min.
  • The ANN model was successfully used to predict the effect of tool pin eccentricity on the mechanical properties of FSW AA 5547-H24, and the networks can be used as an alternative.
  • The RMS error values for the ultimate tensile strength, elongation, hardness of the TMAZ, and weld metal for the test data were 1.1346, 0.3515, 1.2759, and 0.3743, respectively; the R2 values are all greater than 0.98, except for the hardness of the TMAZ, which is 0.97.
  • It is found that the correlations between the measured and predicted values of the ultimate tensile strength, elongation, and hardness of the weld metal are better than those of the hardness of the TMAZ.

Author Contributions

Conceptualization, A.R.S.E. and A.R.K.A.; data curation, A.R.S.E. and A.R.K.A.; formal analysis, M.M.Z.A., A.R.S.E. and T.A.S.; funding acquisition, M.M.Z.A., R.A. and T.A.S.; investigation, A.R.S.E.; methodology, M.M.Z.A. and A.R.S.E. project administration, M.M.Z.A.; resources, R.A.; software, A.R.S.E.; supervision, M.M.Z.A.; validation, R.A.; visualization, T.A.S.; writing—original draft; A.R.S.E.; writing—review and editing, M.M.Z.A., T.A.S. and R.A. All authors have read and agreed to the published version of the manuscript.

Funding

This study was supported by funding from Prince Sattam bin Abdulaziz University, project number (PSAU/2023/R/1444). The authors would like to acknowledge the support of Prince Sultan University for paying the Article Processing Charges (APC) of this publication.

Institutional Review Board Statement

Not applicable.

Informed Consent Statement

Not applicable.

Data Availability Statement

Data will be available upon request from the corresponding authors.

Acknowledgments

The authors would like to acknowledge the support of Prince Sultan University for paying the Article Processing Charges (APC) of this publication.

Conflicts of Interest

The authors declare no conflict of interest.

Nomenclature

biBiases of layer one, i = 1, 2, 3, …, 8
bjBiases of layer two, j = 1, 2, 3, 4
ojOutput (prediction data), where j = 1, 2, 3, …, 14 for training and j = 1, 2, 3, 4 for testing.
pSamples (p = 14 for training, p = 4 for testing).
R2Absolute fraction of variance
RMSRoot-mean squared
tjTarget (measured data), where j = 1, 2, 3, …, 14 for training and j = 1, 2, 3, 4 for testing.
TMAZThermo mechanical affected zone
WiWeights of layer one, i = 1, 2, 3, …, 8
WjWeights of layer two, j = 1, 2, 3, 4
WNZWeld nugget zone

References

  1. Thomas, W.M.; Nicholas, E.D.; Needham, J.C.; Murch, M.G.; Templesmith, P.; Dawes, C.J. Friction Welding. G.B. Patent No. 9125978.8, December 1991. [Google Scholar]
  2. Luan, G.; Ji, Y.; Jian, B. Primary Study on Friction Stir Welding of the Lightweight Aircraft Structures. In Proceedings of the 6th International Symposium on Friction Stir Welding, Saint Sauveur, QC, Canada, 10–13 October 2006; TWI: Montreal, QC, Canada, 2006. [Google Scholar]
  3. Ahmed, M.M.Z.; Ahmed, E.; Hamada, A.S.; Khodir, S.A.; El-Sayed Seleman, M.M.; Wynne, B.P. Microstructure and Mechanical Properties Evolution of Friction Stir Spot Welded High-Mn Twinning-Induced Plasticity Steel. Mater. Des. 2016, 91, 378–387. [Google Scholar] [CrossRef]
  4. Ahmed, M.M.Z.; El-Sayed Seleman, M.M.; Zidan, Z.A.; Ramadan, R.M.; Ataya, S.; Alsaleh, N.A. Microstructure and Mechanical Properties of Dissimilar Friction Stir Welded AA2024-T4/AA7075-T6 T-Butt Joints. Metals 2021, 11, 128. [Google Scholar] [CrossRef]
  5. Ahmed, M.M.Z.; Jouini, N.; Alzahrani, B.; Seleman, M.M.E.-S.; Jhaheen, M. Dissimilar Friction Stir Welding of AA2024 and AISI 1018: Microstructure and Mechanical Properties. Metals 2021, 11, 330. [Google Scholar] [CrossRef]
  6. Ahmed, M.M.Z.; Seleman, M.M.E.S.; Ahmed, E.; Reyad, H.A.; Touileb, K.; Albaijan, I. Friction Stir Spot Welding of Different Thickness Sheets of Aluminum Alloy AA6082-T6. Materials 2022, 15, 2971. [Google Scholar] [CrossRef]
  7. Ahmed, M.M.Z.; Hajlaoui, K.; El-Sayed Seleman, M.M.; Ataya, S.; Latief, F.H.; Habba, M.I.A. Microstructure and Mechanical Properties of Friction Stir Welded 2205 Duplex Stainless Steel Butt Joints. Materials 2021, 14, 6640. [Google Scholar] [CrossRef]
  8. Ahmed, M.M.Z.Z.; Wynne, B.P.; Rainforth, W.M.; Addison, A.; Martin, J.P.; Threadgill, P.L. Effect of Tool Geometry and Heat Input on the Hardness, Grain Structure, and Crystallographic Texture of Thick-Section Friction Stir-Welded Aluminium. Met. Mater. Trans. A 2018, 50, 271–284. [Google Scholar] [CrossRef]
  9. Fujii, H.; Cui, L.; Maeda, M.; Nogi, K. Effect of Tool Shape on Mechanical Properties and Microstructure of Friction Stir Welded Aluminum Alloys. Mater. Sci. Eng. A 2006, 419, 25–31. [Google Scholar] [CrossRef]
  10. Hamada, A.S.; Järvenpää, A.; Ahmed, M.M.Z.; Jaskari, M.; Wynne, B.P.; Porter, D.A.; Karjalainen, L.P. The Microstructural Evolution of Friction Stir Welded AA6082-T6 Aluminum Alloy during Cyclic Deformation. Mater. Sci. Eng. A 2015, 642, 366–376. [Google Scholar] [CrossRef]
  11. Ahmed, M.M.Z.; Abdelazem, K.A.; El-Sayed Seleman, M.M.; Alzahrani, B.; Touileb, K.; Jouini, N.; El-Batanony, I.G.; Abd El-Aziz, H.M. Friction Stir Welding of 2205 Duplex Stainless Steel: Feasibility of Butt Joint Groove Filling in Comparison to Gas Tungsten Arc Welding. Materials 2021, 14, 4597. [Google Scholar] [CrossRef]
  12. Colligan, K. Material Flow Behavior during Friction Stir Welding of Aluminum. Weld. J. 1999, 78, 229s–237s. [Google Scholar]
  13. Sutton, M.; Yang, B.; Reynolds, A.; Taylor, R. 31-Microstructural Studies of Friction Stir Welds in 2024-T3 Aluminum. Mater. Sci. Eng. A 2002, 323, 160–166. [Google Scholar] [CrossRef]
  14. Çam, G.; İpekoğlu, G. Recent Developments in Joining of Aluminum Alloys. Int. J. Adv. Manuf. Technol. 2017, 91, 1851–1866. [Google Scholar] [CrossRef]
  15. Ahmed, M.M.Z.; Ataya, S.; El-Sayed Seleman, M.M.; Ammar, H.R.; Ahmed, E. Friction Stir Welding of Similar and Dissimilar AA7075 and AA5083. J. Mater. Process. Technol. 2017, 242, 77–91. [Google Scholar] [CrossRef]
  16. Heidarzadeh, A.; Mironov, S.; Kaibyshev, R.; Çam, G.; Simar, A.; Gerlich, A.; Khodabakhshi, F.; Mostafaei, A.; Field, D.P.; Robson, J.D.; et al. Friction Stir Welding/Processing of Metals and Alloys: A Comprehensive Review on Microstructural Evolution. Prog. Mater. Sci. 2021, 117, 100752. [Google Scholar] [CrossRef]
  17. Çam, G.; Javaheri, V.; Heidarzadeh, A. Advances in FSW and FSSW of Dissimilar Al-Alloy Plates. J. Adhes. Sci. Technol. 2023, 37, 162–194. [Google Scholar] [CrossRef]
  18. Dhibi, K.; Mansouri, M.; Bouzrara, K.; Nounou, H.; Nounou, M. Reduced Neural Network Based Ensemble Approach for Fault Detection and Diagnosis of Wind Energy Converter Systems. Renew. Energy 2022, 194, 778–787. [Google Scholar] [CrossRef]
  19. Jamii, J.; Mansouri, M.; Trabelsi, M.; Mimouni, M.F.; Shatanawi, W. Effective Artificial Neural Network-Based Wind Power Generation and Load Demand Forecasting for Optimum Energy Management. Front. Energy Res. 2022, 10, 1–13. [Google Scholar] [CrossRef]
  20. Zhang, M.; Tang, Y.; Zhang, H.; Lan, H.; Niu, H. Parameter Optimization of Spiral Fertilizer Applicator Based on Artificial Neural Network. Sustainability 2023, 15, 1744. [Google Scholar] [CrossRef]
  21. Seetha, J.; Raja, S.S. Brain Tumor Classification Using Convolutional Neural Networks. Biomed. Pharmacol. J. 2018, 11, 1457–1461. [Google Scholar] [CrossRef]
  22. Alyami, J.; Rehman, A.; Almutairi, F.; Fayyaz, A.M.; Roy, S.; Saba, T.; Alkhurim, A. Tumor Localization and Classification from MRI of Brain Using Deep Convolution Neural Network and Salp Swarm Algorithm. Cognit. Comput. 2023. [Google Scholar] [CrossRef]
  23. Hichri, A.; Hajji, M.; Mansouri, M.; Abodayeh, K.; Bouzrara, K.; Nounou, H.; Nounou, M. Genetic-Algorithm-Based Neural Network for Fault Detection and Diagnosis: Application to Grid-Connected Photovoltaic Systems. Sustainability 2022, 14, 10518. [Google Scholar] [CrossRef]
  24. Kujawa, S.; Niedbała, G. Artificial Neural Networks in Agriculture. Agriculture 2021, 11, 497. [Google Scholar] [CrossRef]
  25. Adamu, M.; Çolak, A.B.; Ibrahim, Y.E.; Haruna, S.I.; Hamza, M.F. Prediction of Mechanical Properties of Rubberized Concrete Incorporating Fly Ash and Nano Silica by Artificial Neural Network Technique. Axioms 2023, 12, 81. [Google Scholar] [CrossRef]
  26. Ficko, M.; Begic-Hajdarevic, D.; Cohodar Husic, M.; Berus, L.; Cekic, A.; Klancnik, S. Prediction of Surface Roughness of an Abrasive Water Jet Cut Using an Artificial Neural Network. Materials 2021, 14, 3108. [Google Scholar] [CrossRef] [PubMed]
  27. Quadros, J.D.; Nagpal, C.; Khan, S.A.; Aabid, A.; Baig, M. Investigation of Suddenly Expanded Flows at Subsonic Mach Numbers Using an Artificial Neural Networks Approach. PLoS ONE 2022, 17, e0276074. [Google Scholar] [CrossRef] [PubMed]
  28. Sharath, B.N.; Venkatesh, C.V.; Afzal, A.; Aslfattahi, N.; Aabid, A.; Baig, M.; Saleh, B. Multi Ceramic Particles Inclusion in the Aluminium Matrix and Wear Characterization through Experimental and Response Surface-Artificial Neural Networks. Materials 2021, 14, 2895. [Google Scholar] [CrossRef] [PubMed]
  29. Mohammadzadeh Jamalian, H.; Tamjidi Eskandar, M.; Chamanara, A.; Karimzadeh, R.; Yousefian, R. An Artificial Neural Network Model for Multi-Pass Tool Pin Varying FSW of AA5086-H34 Plates Reinforced with Al2O3 Nanoparticles and Optimization for Tool Design Insight. CIRP J. Manuf. Sci. Technol. 2021, 35, 69–79. [Google Scholar] [CrossRef]
  30. Darzi Naghibi, H.; Shakeri, M.; Hosseinzadeh, M. Neural Network and Genetic Algorithm Based Modeling and Optimization of Tensile Properties in FSW of AA 5052 to AISI 304 Dissimilar Joints. Trans. Indian Inst. Met. 2016, 69, 891–900. [Google Scholar] [CrossRef]
  31. Buffa, G.; Fratini, L.; Micari, F. Mechanical and Microstructural Properties Prediction by Artificial Neural Networks in FSW Processes of Dual Phase Titanium Alloys. J. Manuf. Process. 2012, 14, 289–296. [Google Scholar] [CrossRef]
  32. D’Orazio, A.; Forcellese, A.; Simoncini, M. Prediction of the Vertical Force during FSW of AZ31 Magnesium Alloy Sheets Using an Artificial Neural Network-Based Model. Neural Comput. Appl. 2019, 31, 7211–7226. [Google Scholar] [CrossRef]
  33. Ghetiya, N.D.; Patel, K.M. Prediction of Tensile Strength in Friction Stir Welded Aluminium Alloy Using Artificial Neural Network. Procedia Technol. 2014, 14, 274–281. [Google Scholar] [CrossRef]
  34. Tansel, I.N.; Demetgul, M.; Okuyucu, H.; Yapici, A. Optimizations of Friction Stir Welding of Aluminum Alloy by Using Genetically Optimized Neural Network. Int. J. Adv. Manuf. Technol. 2010, 48, 95–101. [Google Scholar] [CrossRef]
  35. Yousif, Y.K.; Daws, K.M.; Kazem, B.I. Prediction of Friction Stir Welding Characteristic Using Neural Network. Jordan J. Mech. Ind. Eng. 2008, 2, 151–155. [Google Scholar]
  36. Okuyucu, H.; Kurt, A. Artificial Neural Network Application to the Friction Stir Welding of Aluminum Plates. Mater. Des. 2007, 28, 78–84. [Google Scholar] [CrossRef]
  37. Ahmed, M.M.Z.; Seleman, M.M.E.-S.; Fydrych, D.; Çam, G. Friction Stir Welding of Aluminum in the Aerospace Industry: The Current Progress and State-of-the-Art Review. Materials 2023, 16, 2971. [Google Scholar] [CrossRef] [PubMed]
  38. Venkateswarlu, D.; Mandal, N.R.; Mahapatra, M.M.; Harsh, S.P. Tool Design Effects for FSW of AA7039. Weld. J. 2013, 92, 41–47. [Google Scholar]
  39. Zhang, Y.; Sato, Y.S.; Kokawa, H.; Hwan, S.; Park, C.; Hirano, S. Microstructural Characteristics and Mechanical Properties of Ti–6Al–4V Friction Stir Welds. Mater. Sci. Eng. A 2008, 485, 448–455. [Google Scholar] [CrossRef]
  40. Gratecap, F.; Girard, M.; Marya, S.; Racineux, G. Exploring Material Flow in Friction Stir Welding: Tool Eccentricity and Formation of Banded Structures. Int. J. Mater. Form. 2012, 5, 99–107. [Google Scholar] [CrossRef]
  41. Tingey, C.; Galloway, A.; Toumpis, A.; Cater, S. Effect of Tool Centreline Deviation on the Mechanical Properties of Friction Stir Welded DH36 Steel. Mater. Des. 2015, 65, 896–906. [Google Scholar] [CrossRef]
  42. Mao, Y.; Ke, L.; Liu, F.; Liu, Q.; Huang, C.; Xing, L. Effect of Tool Pin Eccentricity on Microstructure and Mechanical Properties in Friction Stir Welded 7075 Aluminum Alloy Thick Plate. Mater. Des. 2014, 62, 334–343. [Google Scholar] [CrossRef]
  43. Shah, L.H.; Walbridge, S.; Gerlich, A. Tool Eccentricity in Friction Stir Welding: A Comprehensive Review. Sci. Technol. Weld. Join. 2019, 24, 566–578. [Google Scholar] [CrossRef]
  44. Essa, A.R.S.; Ahmed, M.M.Z.; Mohamed, A.K.Y.A.; El-Nikhaily, A.E. An Analytical Model of Heat Generation for Eccentric Cylindrical Pin in Friction Stir Welding. J. Mater. Res. Technol. 2016, 5, 234–240. [Google Scholar] [CrossRef]
  45. Ahmed, M.M.Z.; Essa, A.R.S.; Ataya, S.; Seleman, M.M.E.; El-aty, A.A.; Alzahrani, B.; Touileb, K.; Bakkar, A.; Ponnore, J.J.; Mohamed, A.Y.A. Friction Stir Welding of AA5754-H24: Impact of Tool Pin Eccentricity and Welding Speed on Grain Structure, Crystallographic Texture, and Mechanical Properties. Materials 2023, 16, 2031. [Google Scholar] [CrossRef]
  46. Ragab, M.; Liu, H.; Yang, G.J.; Ahmed, M.M.Z. Friction Stir Welding of 1Cr11Ni2W2MoV Martensitic Stainless Steel: Numerical Simulation Based on Coupled Eulerian Lagrangian Approach Supported with Experimental work. Appl. Sci. 2021, 11, 3049. [Google Scholar] [CrossRef]
  47. Ragab, M.; Liu, H.; Ahmed, M.M.Z.; Yang, G.-J.; Lou, Z.-J.; Mehboob, G. Microstructure Evolution during Friction Stir Welding of 1Cr11Ni2W2MoV Martensitic Stainless Steel at Different Tool Rotation Rates. Mater. Charact. 2021, 182, 111561. [Google Scholar] [CrossRef]
  48. Elfishawy, E.; Ahmed, M.M.Z.; El-Sayed Seleman, M.M. Additive Manufacturing of Aluminum Using Friction Stir Deposition. In Proceedings of the TMS 2020 149th Annual Meeting & Exhibition Supplemental Proceedings; Springer International Publishing: Cham, Switzerland; San Diego, CA, USA, 2020; pp. 227–238. [Google Scholar]
  49. Hammad, A.S.; Ahmed, M.M.Z.; Lu, H.; El-Shabasy, A.B.; Alzahrani, B.; El-Sayed Seleman, M.M.; Zhang, Y.; El Megharbel, A. An Investigation on Mechanical and Microstructural Evolution of Stationary Shoulder Friction Stir Welded Aluminum Alloy AA7075-T651. Proc. Inst. Mech. Eng. Part C J. Mech. Eng. Sci. 2022, 236, 6665–6676. [Google Scholar] [CrossRef]
  50. Ahmed, M.M.Z.; Seleman, M.M.E.S.; Eid, R.G.; Albaijan, I.; Touileb, K. The Influence of Tool Pin Geometry and Speed on the Mechanical Properties of the Bobbin Tool Friction Stir Processed AA1050. Materials 2022, 15, 4684. [Google Scholar] [CrossRef]
  51. Zayed, E.M.; El-Tayeb, N.S.M.; Ahmed, M.M.Z.; Rashad, R.M. Development and Characterization of AA5083 Reinforced with SiC and Al2O3 Particles by Friction Stir Processing; Springer: Berlin/Heidelberg, Germany, 2019; Volume 92. [Google Scholar]
  52. Elangovan, K.; Balasubramanian, V. Influences of Pin Profile and Rotational Speed of the Tool on the Formation of Friction Stir Processing Zone in AA2219 Aluminium Alloy. Mater. Sci. Eng. A 2007, 459, 7–18. [Google Scholar] [CrossRef]
  53. Krishnan, K.N. On the Formation of Onion Rings in Friction Stir Welds. Mater. Sci. Eng. A 2002, 327, 246–251. [Google Scholar] [CrossRef]
  54. Xu, G.; Chen, J.; Zhou, H. A Tool Breakage Monitoring Method for End Milling Based on the Indirect Electric Data of CNC System. Int. J. Adv. Manuf. Technol. 2019, 101, 419–434. [Google Scholar] [CrossRef]
  55. Hamdia, K.M.; Lahmer, T.; Nguyen-Thoi, T.; Rabczuk, T. Predicting the fracture toughness of PNCs: A stochastic approach based on ANN and ANFIS. Comput. Mater. Sci. 2015, 102, 304–313. [Google Scholar] [CrossRef]
Materials 16 03777 g001 550
Figure 1. 3D CAD drawings of the FSW tool (a) e = 0 mm, (b) e = 0.2 mm, and (c) e = 0.8 mm. Note that e is the value of eccentricity (dimensions in mm).
Figure 1. 3D CAD drawings of the FSW tool (a) e = 0 mm, (b) e = 0.2 mm, and (c) e = 0.8 mm. Note that e is the value of eccentricity (dimensions in mm).
Materials 16 03777 g001
Materials 16 03777 g002 550
Figure 2. Tensile test specimen. All dimensins are in mm.
Figure 2. Tensile test specimen. All dimensins are in mm.
Materials 16 03777 g002
Materials 16 03777 g003 550
Figure 3. Top surface view of AA5754-H24 FSW joints made using several FSW tools (T0, T2, and T8) and at a rotational speed of 600 rpm.
Figure 3. Top surface view of AA5754-H24 FSW joints made using several FSW tools (T0, T2, and T8) and at a rotational speed of 600 rpm.
Materials 16 03777 g003
Materials 16 03777 g004 550
Figure 4. The structure of the ANN model used in this work.
Figure 4. The structure of the ANN model used in this work.
Materials 16 03777 g004
Materials 16 03777 g005 550
Figure 5. Variation in predicted and measured data. (a) tensile strength; (b) elongation; (c) hardness of TMAZ; (d) hardness of weld nugget.
Figure 5. Variation in predicted and measured data. (a) tensile strength; (b) elongation; (c) hardness of TMAZ; (d) hardness of weld nugget.
Materials 16 03777 g005
Materials 16 03777 g006 550
Figure 6. Comparison of measured and predicted data for (a,b) training data, (c) test data of tensile strength, (d) test data of elongation, (e) test data of hardness of TMAZ, and (f) test data of hardness of weld nugget.
Figure 6. Comparison of measured and predicted data for (a,b) training data, (c) test data of tensile strength, (d) test data of elongation, (e) test data of hardness of TMAZ, and (f) test data of hardness of weld nugget.
Materials 16 03777 g006
Table
Table 1. Chemical composition of aluminium alloy AA5754.
Table 1. Chemical composition of aluminium alloy AA5754.
wt.%
FeSiMnCuMgZnTiCrAl
0.40 ± 0.030.40 ± 0.020.50 ± 0.040.10 ± 0.012.6–3.2 ± 0.030.20 ± 0.010.15 ± 0.010.30 ± 0.02rest
-
Table
Table 2. Measured mechanical characteristics of AA5754.
Table 2. Measured mechanical characteristics of AA5754.
Proof Stress 0.2% (MPa)Tensile Strength (MPa)Elongation (%)
205 ± 5260.57 ± 4.6012.93 ± 1.80
Table
Table 3. Measured data used to train the ANN.
Table 3. Measured data used to train the ANN.
No.e (mm)Welding Speed (mm/min)Tensile Strength (Mpa)Elongation (%)Average Hardness (HV)
HAZWNZ
1050231.009.6659.9 ± 0.359.5 ± 0.6
20100235.3811.3663.0 ± 0.168.1 ± 0.9
30150234.0611.6063.4 ± 0.168.1 ± 0.3
40200237.4311.5860.2 ± 0.266.9 ± 0.7
50300238.5810.2161.6 ± 0.467.3 ± 0.3
60500244.957.9266.9 ± 0.564.05 ± 0.5
70.250238.8011.3260.6 ± 0.762.0 ± 0.6
80.2100240.3111.3559.9 ± 0.362.7 ± 0.4
90.2150240.0211.3963.4 ± 0.464.9 ± 0.8
100.2200243.2212.3960.9 ± 0.865.3 ± 0.3
110.2300243.6911.2565.7 ± 0.464.82 ± 0.7
120.2500249.879.2167.5 ± 0.673.1 ± 0.6
130.850242.2611.7468.9 ± 0.961.1 ± 0.9
140.8100239.7610.9960.9 ± 0.665.7 ± 0.4
150.8150238.9710.5464.2 ± 0.867.2 ± 0.7
160.8200238.8710.5066.9 ± 0.568.1 ± 0.8
170.8300238.7411.1058.9 ± 0.362.3 ± 0.3
180.8500237.156.1464.2 ± 0.471.9 ± 0.5
Table
Table 4. Weights and biases for the ANN after the training stage.
Table 4. Weights and biases for the ANN after the training stage.
LayerNeurons per Layer Weights Biases
iWi1Wi2 bi
1812.70094.5649 −1.7555
2−2.0315−3.4643 1.3986
3−3.197218.3450 22.1916
43.9171−3.6640 1.4856
5−15.2546−39.2993 −7.1898
63.8393−3.3341 1.5511
77.40151.4190 6.2523
80.6582−1.6493 1.0211
jWj1Wj2Wj3Wj4Wj5Wj6Wj7Wj8bj
2410.60980.6742−0.51324.80890.0594−5.35040.7177−0.05210.2423
23.06413.2349−0.18425.04390.0677−5.77140.50531.1842−0.2822
3−2.0024−2.1078−4.17309.0617−0.4064−9.60110.40180.13663.8853
4−17.6851−19.45170.833215.46430.4267−16.95100.87470.9753−0.3709
Table
Table 5. Statistical values of predication data.
Table 5. Statistical values of predication data.
RMS of TrainR2 of TrainMean Error of TrainRMS of TestR2 of TestMean Error of Test
Tensile strength0.39930.99930.06081.13460.99460.2512
Elongation0.09040.99920.05360.35150.98940.2865
Hardness of TMAZ0.51670.99580.31591.27590.97353.3267
Hardness of WNZ0.07550.99990.00360.37430.99790.0101
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Essa, A.R.S.; Ahmed, M.M.Z.; Aboud, A.R.K.; Alyamani, R.; Sebaey, T.A. Prediction of Tool Eccentricity Effects on the Mechanical Properties of Friction Stir Welded AA5754-H24 Aluminum Alloy Using ANN Model. Materials 2023, 16, 3777. https://doi.org/10.3390/ma16103777

AMA Style

Essa ARS, Ahmed MMZ, Aboud ARK, Alyamani R, Sebaey TA. Prediction of Tool Eccentricity Effects on the Mechanical Properties of Friction Stir Welded AA5754-H24 Aluminum Alloy Using ANN Model. Materials. 2023; 16(10):3777. https://doi.org/10.3390/ma16103777

Chicago/Turabian Style

Essa, Ahmed R. S., Mohamed M. Z. Ahmed, Aboud R. K. Aboud, Rakan Alyamani, and Tamer A. Sebaey. 2023. "Prediction of Tool Eccentricity Effects on the Mechanical Properties of Friction Stir Welded AA5754-H24 Aluminum Alloy Using ANN Model" Materials 16, no. 10: 3777. https://doi.org/10.3390/ma16103777

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop