Optimizations of friction stir welding of aluminum alloy by using genetically optimized neural network

Tansel, İbrahim N.; Demetgül, Mustafa; Okuyucu, H.; Yapıcı, Ahmet

doi:10.1007/s00170-009-2266-6

Cited by 73 publications

(47 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regression analysis (Jayaraman et al 2009;Mohanty et al 2012;Rajakumar et al 2011a), response surface methodology Elatharasan and Kumar 2012;Palanivel and Mathews 2012;Rajakumar et al 2011b), and ANN (Ocuyucu et al 2007;Boldsaikhan et al 2011;Ghetiya and Patel 2014;Chiteka 2014;Fahd 2014;Shojaeefard et al 2013;Tansel et al 2010;Rezgui et al 2013) are different tools used for the modeling of weld strength. Among these, ANN was mostly used because of its robustness and flexibility in modeling complex processes where precise mathematical formulation is not available as FSW process.…”

Section: Modeling Of Weld Qualitymentioning

confidence: 99%

Monitoring of Weld Quality in Friction Stir Welding Based on Spindle Speed and Motor Current Signals

Das

Pal

Bag

2015

Advances in Material Forming and Joining

View full text Add to dashboard Cite

The process of friction stir welding passed more than two decades since its invention in the year 1991 in TWI, UK. It involves complex physics and has not been explored fully to understand its physical behavior. Due to the lack of precise mathematical modeling and too many influencing factors that govern the welding process, difficulty arises in direct monitoring of the process based on the process parameters only. Moreover, the influencing parameters are so correlated that the effect of one on the weld quality cannot be isolated from the others for effective monitoring of the process. Thus, a need is realized to develop different methods for the efficacious monitoring of the process with the acquired signals during welding for better control over the outcome of the process. In this study, effectiveness of spindle speed and main motor current signals is investigated for the development of tools which will lead to real-time weld quality prediction.

show abstract

Section: Modeling Of Weld Qualitymentioning

confidence: 99%

Monitoring of Weld Quality in Friction Stir Welding Based on Spindle Speed and Motor Current Signals

Das

Pal

Bag

2015

Advances in Material Forming and Joining

View full text Add to dashboard Cite

show abstract

“…For example, optimization of manufacturing processes, [21][22][23][24][25] vibro-acoustic optimization of mechanical structures 29 and optimization of trusses design. 30 To the knowledge of authors, any analytical formulation describing the relationship between the inputs and the outputs of FSP is not available in the literature.…”

Section: Multilayer Neural Network Function Approximationmentioning

confidence: 99%

Trade-off among mechanical properties and energy consumption in multi-pass friction stir processing of Al7075 alloy employing neural network–based genetic optimization

Hussain

Ranjbar

Hassanzadeh

2016

Proceedings of the Institution of Mechanical Engineers, Part B:

View full text Add to dashboard Cite

Friction stir processing is a novel material processing technique. In this study, neural network-based genetic optimization is applied to optimize the process performance in terms of post-friction stir processing mechanical properties of Al7075 alloy and the energy cost. At first, the experimental data regarding the properties (i.e. elongation, tensile strength and hardness) and the consumed electrical energy are obtained by conducting tests varying two process parameters, namely, feed rate and spindle speed. Then, a numerical model making use of empirical data and artificial neural networks is developed, and multiobjective multivariable genetic optimization is applied to find a trade-off among the performance measures of friction stir processing. For this purpose, the properties like elongation, tensile strength and hardness are maximized and the cost of consumed electrical energy is minimized. Finally, the optimization results are verified by conducting experiments. It is concluded that artificial neural network together with genetic algorithm can be successfully employed to optimize the performance of friction stir processing.

show abstract

“…In recent decades, various meta-heuristics approaches such as the genetic algorithm (GA), the particle swarm optimization (PSO) algorithm, the simulated annealing (SA) algorithm, and the non-dominated sorting genetic algorithm (NSGA) have been proposed for use in various welding techniques. Tansel et al (2009) used a genetically optimized neural network to optimize the process parameters of friction stir welding on Al-1080 aluminum alloys. DebRoy et al (2013)proposed a genetic algorithm for the FSW process to model effective heat transfer and plastic flow.…”

Section: Introductionmentioning

confidence: 99%

Tensile Properties Improvement on Friction Stir Welded Age-Hardenable Aluminum Alloys: An Evolutionary Approach using RSM based GA and SA

2016

Rev. Téc. Ing. Univ. Zulia.

View full text Add to dashboard Cite

AA2024 and AA6061 aluminum alloys were fabricated using the friction stir welding technique to improve the tensile properties such as ultimate tensile strength (UTS) and tensile elongation (TE). The BoxBehnken design matrix with four significant factors-rotational speed (X(1)), welding speed (X(2)), axial load (X(3)), and pin shape (X(4)), each having three levels-was used with response surface methodology to develop a mathematical model. The experiments yielded ultimate tensile strength of 141 MPa at 12% tensile elongation. The obtained tensile properties of fabricated weld joints were low when compared to those of base materials. Several voids and pinholes were found, these being the consequence of poor tensile properties on the fabricated weld joints. Therefore, to maximize the tensile properties, two computational approaches were employed: a genetic algorithm and a simulated annealing algorithm. The main objectives of applying these computational approaches were: (1) to maximize the UTS and TE compared to the welding performance value of the experimental data and regression modeling; (2) to estimate the optimal process parameter values that must be within the obtained range of the minimum and maximum values; and (3) to evaluate the number of iterations generated by the computational approaches. The results show that use of the computational approaches resulted in significant improvement in the tensile properties. Comparing the genetic algorithm with the simulated annealing algorithm, the latter maximizes the tensile properties of fabricated AA2024 and AA6061 aluminum alloy weld joints; however, a considerable number of iterations and substantial amount of time was required to achieve a global optimal solution.

show abstract

Optimizations of friction stir welding of aluminum alloy by using genetically optimized neural network

Cited by 73 publications

References 27 publications

Monitoring of Weld Quality in Friction Stir Welding Based on Spindle Speed and Motor Current Signals

Monitoring of Weld Quality in Friction Stir Welding Based on Spindle Speed and Motor Current Signals

Trade-off among mechanical properties and energy consumption in multi-pass friction stir processing of Al7075 alloy employing neural network–based genetic optimization

Tensile Properties Improvement on Friction Stir Welded Age-Hardenable Aluminum Alloys: An Evolutionary Approach using RSM based GA and SA

Contact Info

Product

Resources

About