Experimental and Machine Learning Study on Friction Stir Surface Alloying in Al1050-Cu Alloy
Abstract
:1. Introduction
2. Materials and Methods
- Initial temperature: 2
- Cooling rate: 1—Controls the acceptance of worse solutions initially, avoiding local optima and gradually reducing acceptance to promote convergence.
- Subpopulation size: 30—Enhances diversity within the overall population, leading to more varied and potentially better solutions through different evolutionary paths.
- Tolerance level: 0.05—Ensures the algorithm halts when improvements in the models become minimal, saving computational resources while maintaining solution quality.
3. Results and Discussions
3.1. Experimental Results
3.2. Machine Learning Results
4. Conclusions
- Increasing the tool rotation speed leads to higher hardness.
- A greater number of passes results in lower hardness.
- Increasing the feed rate leads to a decrease in hardness.
- The strength increases with an increase in the number of passes.
- Decreasing the feed rate results in higher strength.
- Increasing the tool rotation speed leads to higher strength.
- The base metal has a strength of 115 MPa, but it can be increased to 192 MPa through the surface alloying process.
- The system’s real-time capabilities ensure the effective identification of material defects during live production processes.
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Gan, Y.; Solomon, D.; Reinbolt, M. Friction Stir Processing Of Particle Reinforced Composite Materials. Materials 2010, 1, 329–350. [Google Scholar] [CrossRef]
- Hasan, M.; Tolba, S.; Allam, N. In Situ Formation Of Graphene Stabilizes Zero-valent Copper Nanoparticles and Significantly Enhances The Efficiency Of Photocatalytic Water Splitting. ACS Sustain. Chem. Eng. 2018, 12, 16876–16885. [Google Scholar] [CrossRef]
- Sajed, M.; Seyedkashi, S.H. Solid-state local micro-alloying of thick ST37 steel plates with SiC powder using a modified friction hydro-pillar process. J. Mater. Res. Technol. 2020, 9, 7158–7171. [Google Scholar] [CrossRef]
- Adetunji, O.R.; Olukuade, M.L.; Simka, W.; Sowa, M.; Adesusi, O.M.; Okediran, I.K. Production and Characterization of Amorphous Aluminum-Copper Alloy for Aerospace Applications. Eur. J. Eng. Technol. Res. 2017, 2, 1–5. [Google Scholar]
- Stojanovic, B.; Bukvic, M.; Epler, I. Application of Aluminum and Aluminum Alloys in Engineering. Appl. Eng. Lett. J. Eng. Appl. Sci. 2018, 3, 52–62. [Google Scholar] [CrossRef]
- Lequeu, P.; Smith, K.P.; Daniélou, A. Aluminum-Copper-Lithium Alloy 2050 Developed for Medium to Thick Plate. J. Mater. Eng. Perform. 2010, 19, 841–847. [Google Scholar] [CrossRef]
- Chainarong, S.; Muangjunburee, P.; Suthummanon, S. Friction Stir Processing Of SSM356 Aluminium Alloy. Procedia Eng. 2014, 97, 732–740. [Google Scholar] [CrossRef]
- Liu, L.; Nakayama, H.; Fukumoto, S.; Yamamoto, A.; Tsubakino, H. Microscopic Observations of Friction Stir Welded 6061 Aluminum Alloy. Mater. Trans. 2004, 2, 288–291. [Google Scholar] [CrossRef]
- Eslami, N.; Harms, A.; Deringer, J.; Fricke, A.; Böhm, S. Dissimilar Friction Stir Butt Welding Of Aluminum and Copper With Cross-section Adjustment For Current-carrying Components. Metals 2018, 9, 661. [Google Scholar] [CrossRef]
- Uematsu, Y.; Tozaki, Y.; Tokaji, K.; Nakamura, M. Fatigue Behavior Of Dissimilar Friction Stir Welds Between Cast and Wrought Aluminum Alloys. Strength Mater. 2008, 1, 138–141. [Google Scholar] [CrossRef]
- Shafiei-Zarghani, A.; Kashani-Bozorg, S.F.; Zarei-Hanzaki, A. Microstructures and mechanical properties of Al/Al2O3 surface nano-composite layer produced by friction stir processing. Mater. Sci. Eng. A 2009, 500, 84–91. [Google Scholar] [CrossRef]
- Huang, C.; Aoh, J. Friction Stir Processing Of Copper-coated SiC Particulate-reinforced Aluminum Matrix Composite. Materials 2018, 4, 599. [Google Scholar] [CrossRef]
- Sharma, D.; Patel, V.; Badheka, V.; Mehta, K.; Upadhyay, G. Different Reinforcement Strategies of Hybrid Surface Composite AA6061/(B4C+MoS2) Produced By Friction Stir Processing. Materwiss. Werksttech. 2020, 11, 1493–1506. [Google Scholar] [CrossRef]
- Wang, T.; Shukla, S.; Gwalani, B.; Sinha, S.; Thapliyal, S.; Frank, M.; Mishra, R.S. Co-introduction of precipitate hardening and TRIP in a TWIP high-entropy alloy using friction stir alloying. Sci. Rep. 2021, 11, 1579. [Google Scholar] [CrossRef] [PubMed]
- Rubtsov, V.; Chumaevskii, A.; Gusarova, A.; Knyazhev, E.; Gurianov, D.; Zykova, A.; Tarasov, S. Macro-and Microstructure of In Situ Composites Prepared by Friction Stir Processing of AA5056 Admixed with Copper Powders. Materials 2023, 16, 1070. [Google Scholar] [CrossRef]
- Verma, S.; Msomi, V.; Mabuwa, S.; Merdji, A.; Misra, J.P.; Batra, U.; Sharma, S. Machine learning application for evaluating the friction stir processing behavior of dissimilar aluminium alloys joint. Proc. Inst. Mech. Eng. Part L J. Mater. Des. Appl. 2022, 236, 633–646. [Google Scholar] [CrossRef]
- Verma, S.; Misra, J.P.; Popli, D. Modeling of friction stir welding of aviation grade aluminium alloy using machine learning approaches. Int. J. Model. Simul. 2022, 42, 1–8. [Google Scholar] [CrossRef]
- Chadha, U.; Selvaraj, S.K.; Gunreddy, N.; Sanjay Babu, S.; Mishra, S.; Padala, D.; Shashank, M.; Mathew, R.M.; Kishore, S.R.; Panigrahi, S.; et al. A survey of machine learning in friction stir welding, including unresolved issues and future research directions. Mater. Des. Process. Commun. 2022, 2022, 2568347. [Google Scholar] [CrossRef]
- Anandan, B.; Manikandan, M. Machine learning approach with various regression models for predicting the ultimate tensile strength of the friction stir welded AA 2050-T8 joints by the K-Fold cross-validation method. Mater. Today Commun. 2023, 34, 105286. [Google Scholar] [CrossRef]
- Acharya, M.; Mandal, A. Microstructure Study of Friction Stir Processed Hypereutectic Al-20Si Alloy and Analysis of the Wear Behaviour using Machine Learning Algorithms. Silicon 2024, 16, 3539–3551. [Google Scholar] [CrossRef]
- Elsheikh, A.H. Applications of machine learning in friction stir welding: Prediction of joint properties, real-time control and tool failure diagnosis. Eng. Appl. Artif. Intell. 2023, 121, 105961. [Google Scholar] [CrossRef]
- Iwazesko, J.; Sajed, M. Technological Aspects of Producing Surface Composites by Friction Stir Processing—A Review. J. Compos. Sci. 2021, 5, 323. [Google Scholar] [CrossRef]
- ASTM International. ASTM E08: Standard Test Methods for Tension Testing of Metallic Materials; ASTM International: West Conshohocken, PA, USA, 2023. [Google Scholar]
- Khan, N.Z.; Mir, M.A.; Maqbool, A.; Khan, H.A. Evolution of Strengthening Precipitates During Friction Stir Welding of Al-Zn and Al-Cu Alloys. Trans. Indian Inst. Met. 2024. [Google Scholar] [CrossRef]
- Jamshidi Aval, H.; Galvão, I. Effect of Tool Rotational Speed on Microstructure and Mechanical Properties of Friction Stir Welded Al–16Si–4Cu–10SiC Composite/Al–4Cu–Mg Alloy Joints. Metallogr. Microstruct. Anal. 2024, 1–15. [Google Scholar] [CrossRef]
- Elangovan, K.; Balasubramanian, V. Influences of tool pin profile and welding speed on the formation of friction stir processing zone in AA2219 aluminium alloy. J. Mater. Process. Technol. 2008, 200, 163–175. [Google Scholar] [CrossRef]
- Mishra, R.S.; Ma, Z.Y. Friction stir welding and processing. Mat. Sci. Eng. R. 2005, 50, 1–78. [Google Scholar] [CrossRef]
- Abonyi, J. Genetic Programming MATLAB Toolbox; MathWorks: Natick, MA, USA, 2023. [Google Scholar]
Si | Fe | Mn | P | V | Ti | Al |
---|---|---|---|---|---|---|
0.071 | 0.175 | 0.008 | 0.004 | 0.019 | 0.004 | >99.7 |
Tensile Strength | Hardness (Brinell) | Elongation A | Density | Modulus of Elasticity |
---|---|---|---|---|
105–145 MPa | 34 HB | 12 Min % | 2.71 kg/m3 | 71 GPa |
No. | Tool Rotation Speed (rpm) | Feed Rate (mm/min) | Number of Passes | Hardness | Strength (MPa) |
---|---|---|---|---|---|
1 | 1250 | 80 | 1 | 77 | 94 |
2 | 1250 | 80 | 3 | 64 | 103 |
3 | 1250 | 80 | 6 | 51 | 120 |
4 | 1250 | 50 | 1 | 92 | 111 |
5 | 1250 | 50 | 3 | 55 | 134 |
6 | 1250 | 50 | 6 | 46 | 166 |
7 | 1250 | 20 | 1 | 115 | 98 |
8 | 1250 | 20 | 3 | 95 | 181 |
9 | 1250 | 20 | 6 | 95 | 192 |
10 | 630 | 80 | 1 | 103 | 87 |
11 | 630 | 80 | 3 | 56 | 98 |
12 | 630 | 80 | 6 | 64 | 110 |
13 | 630 | 50 | 1 | 68 | 130 |
14 | 630 | 50 | 3 | 88 | 112 |
15 | 630 | 50 | 6 | 59 | 123 |
16 | 630 | 20 | 1 | 85 | 87 |
17 | 630 | 20 | 3 | 69 | 149 |
18 | 630 | 20 | 6 | 63 | 160 |
Parameter | Value | Description |
---|---|---|
Functions | {‘+’, ‘*’, ‘/’} | Basic arithmetic operations used to build the GP model equations |
Terminals | {‘x1′, ‘x2′, ‘x3′} | Input variables representing features of the dataset |
Population size | 40 | Number of individual programs (models) in the population |
Maximum tree depth | 50 | Maximum depth of the tree structures representing the GP models |
Crossover probability | 0.8 | Probability of combining two parent models to create offspring |
Mutation probability | 0.7 | Probability of randomly altering parts of a model |
Selection pressure | 0.3 | Controls the likelihood of selecting fitter individuals for reproduction |
Maximum generations | 20 | Number of generations (iterations) the GP algorithm runs |
Initial temperature | 2 | Used in simulated annealing processes (if applicable) |
Cooling rate | 1 | Parameter for simulated annealing to reduce the temperature over time (if applicable) |
Subpopulation size | 30 | Size of subpopulations in the algorithm |
Tolerance | 0.05 | Tolerance level for the stopping criterion |
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. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Pedrammehr, S.; Sajed, M.; Al-Abdullah, K.I.A.-L.; Pakzad, S.; Zare Jond, A.; Chalak Qazani, M.R.; Ettefagh, M.M. Experimental and Machine Learning Study on Friction Stir Surface Alloying in Al1050-Cu Alloy. J. Manuf. Mater. Process. 2024, 8, 163. https://doi.org/10.3390/jmmp8040163
Pedrammehr S, Sajed M, Al-Abdullah KIA-L, Pakzad S, Zare Jond A, Chalak Qazani MR, Ettefagh MM. Experimental and Machine Learning Study on Friction Stir Surface Alloying in Al1050-Cu Alloy. Journal of Manufacturing and Materials Processing. 2024; 8(4):163. https://doi.org/10.3390/jmmp8040163
Chicago/Turabian StylePedrammehr, Siamak, Moosa Sajed, Kais I. Abdul-Lateef Al-Abdullah, Sajjad Pakzad, Ahad Zare Jond, Mohammad Reza Chalak Qazani, and Mir Mohammad Ettefagh. 2024. "Experimental and Machine Learning Study on Friction Stir Surface Alloying in Al1050-Cu Alloy" Journal of Manufacturing and Materials Processing 8, no. 4: 163. https://doi.org/10.3390/jmmp8040163