Modeling and Optimization of Copper Tube Drawing Process Parameters Based on Neuro-Regression and Stochastic Search Techniques
Abstract views: 0
/ 
PDF downloads: 2
Keywords:
Tube drawing process, neuro-regression modeling, stochastic optimization, copper tubeAbstract
This study is dedicated to optimizing two critical responses within the tube drawing process:
drawing force and linear thickness distribution. The process is influenced by four design factors: die
angle, bearing length, friction coefficient, and drawing velocity.
To mathematically define the tube drawing process, 13 functional forms were utilized, encompassing
linear, quadratic, trigonometric, and logarithmic expressions and their rational and hybrid combinations.
The dataset for model development was taken from the literature. The candidate models were assessed
using multiple performance metrics, including R2 training, R2 testing, and R2 validation, along with
boundedness checks and adherence to predefined constraints.
After identifying a suitable model, modified version of stochastic search optimization methods;
Differential Evolution and Simulated Annealing were applied to minimize drawing force while
maximizing thickness distribution. The results revealed a minimum drawing force of 2107.75 kN and a
maximum linear thickness distribution of 0.911 mm.
These findings underscore the robustness and versatility of the neuro-regression modeling and stochastic
optimization processes proposed in this study. In comparison to previous methodologies—such as
response surface and artificial bee optimization techniques referenced in the literature—this approach has
yielded an improvement of 3.5 % in drawing force and an enhancement of 18% in thickness distribution.
Downloads
References
S. Kalpakjian and S. R. Schmid, Manufacturing Engineering and Technology. Pearson Education, 2014.
Z. Pater, J. Kazanecki, and J. Bartnicki, Analysis of drawing force and energy efficiency in the tube drawing process, International Journal of Mechanical Sciences, vol. 122, pp. 304–315, 2017.
N. Tiesler, P. Franke, and G. Hirt, Application of finite element modeling in the optimization of tube forming processes, Materials Today Communications, vol. 24, pp. 101–113, 2020.
T. Altan and A. E. Tekkaya, Sheet Metal Forming: Processes and Applications. ASM International, 2012.
R. Kumar and S. R. Chauhan, Optimization of tube drawing parameters using Response Surface Methodology, Materials Today: Proceedings, vol. 26, pp. 1527–1532, 2020.
S. S. Rajput and P. Nimbalkar, Application of Artificial Neural Networks for modeling and optimizing tube drawing, Journal of Intelligent Manufacturing, vol. 30, no. 3, pp. 793–805, 2019.
R. Patel, V. Sharma, and P. Kumar, Taguchi-based optimization of the tube drawing process with emphasis on die design, Journal of Manufacturing Processes, vol. 62, pp. 45–55, 2021.
R. Yadav, R. K. Singh, and V. Mishra, Central Composite Design for optimization of tube drawing parameters, International Journal of Advanced Manufacturing Technology, vol. 97, no. 1, pp. 1023–1034, 2018.
W. Sun, Y. Zhang, and H. Li, Optimization of tube drawing parameters using Genetic Algorithms for multi-objective solutions, Journal of Materials Processing Technology, vol. 249, pp. 290–298, 2017.
M. Salehi, M. Hosseinzadeh, and M. Elyasi, A study on optimal design of process parameters in tube drawing process of rectangular parts by combining box–behnken design of experiment, response surface methodology and artificial bee colony algorithm, Transactions of the Indian Institute of Metals, vol. 69, pp. 1223–1235, 2016.
İ. Polatoğlu, L. Aydın, B. Ç. Nevruz, and S. Özer, A novel approach for the optimal design of a biosensor, Analytical Letters, vol. 53, no. 9, pp. 1428–1445, 2020.
M. Savran, L. Aydin, A. Ayaz, and T. Uslu, A new strategy for manufacturing, modeling, and optimization of 3D printed polylactide based on multiple nonlinear neuro regression analysis and stochastic optimization methods, Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering, vol. 09544089241272909, 2024.
M. Savran and L. Aydin, An Integrated Approach to Modeling and Optimization in Engineering and Science, CRC Press, 2024.
