Design and Development of a Semi-Automatic Steel Pipe Bending Machine with a Polynomial Regression Model for Optimal Bending Angle Prediction

Authors

  • Thanapat Maneesaeng Faculty of Industrial Technology, Muban Chombueng Rajabhat University
  • Nattapon Phurahong Faculty of Agricultural Technology and Industrial Technology Phetchabun Rajabhat University
  • Surachat Bunsing Faculty of Agricultural Technology and Industrial Technology Phetchabun Rajabhat University
  • Kittapon Lasing Faculty of Agricultural Technology and Industrial Technology Phetchabun Rajabhat University

Keywords:

Semi-automatic steel-pipe bending machine, Polynomial regression, Bendangle prediction, Optimization

Abstract

This study aims to develop a compact semi- automatic steel- pipe bending machine integrated with a polynomial regression model for predicting the optimal bend angle. Experiments were conducted using steel pipes with diameters ranging from 3/8 to 3/4 inch and lengths of 5, 6, and 7 meters. The investigation focused on the quantitative relationships among motor rotation counts, the resulting bend angles, and changes in end- to- end pipe width after bending. The results show strong correlations among all variables, with average correlation coefficients exceeding 0.90. Motor rotations exhibited a positive correlation with bend angle, while bend angle and end-to-end width displayed a negative relationship. These empirical findings were used to construct a polynomial regression model for predicting bend angles from motor rotations. The model achieved an average R2 value above 98% and a confidence interval of approximately ±5 degrees. The findings confirm that the developed bending machine and regression model can accurately predict and control bend angles, making the system suitable for practical small-scale steel-pipe bending applications.

References

T. Ahmed, M. Faheem, and M. A. Murtaza, “Case study & stress analysis of a 3-roller bar bending machine,” International Journal of Mechanical and Production Engineering Research and Development, vol. 3, no. 8, pp. 57–67, 2013.

M. C. Baraiya, N. N. Jadeja, A. B. Jasoliya, R. U. Jagad, and V. R. Makwana, “Research paper of manually operated pipe bending machine,” Paripex – Indian Journal of Research, vol. 3, no. 5, pp. 66–67, 2014.

S. B. Deshmukh, J. A. Patil, D. S. Gurame, and D. S. Patil, “Design analysis and fabrication of hydraulic bar bending machine,” International Research Journal of Engineering and Technology (IRJET), vol. 4, no. 5, pp. 2658–2666, 2017.

M. Krishna S. A., “Experimental design and fabrication of a portable hydraulic pipe bending machine,” International Journal of Development Research, vol. 4, no. 12, pp. 2681–2684, Dec. 2014.

V. Görüş, M. Bahşı, and M. Çevik, “Machine learning for the prediction of problems in steel tube bending process,” Engineering Applications of Artificial Intelligence, vol. 133, no. 1, p. 108584, 2024.

D. S. Kim, J. W. Lee, and H. S. Kim, “Tube geometry prediction in rotary draw bending process using random forest regression,” International Journal of Advanced Manufacturing Technology, vol. 116, pp. 2543–2555, 2021.

S. Mazdak, M. R. Sheykholeslami, M. Gholami, H. Parvaz, M. M. Najafizadeh, S. Mahmoudi, and A. Vanaki, “A statistical model for estimation of bending angle in laser bending of two-layer steel– aluminum sheets,” Optics & Laser Technology, vol. 157, p. 108575, 2023.

E. Gao, D. Xue, and Y. Li, “Springback angle prediction for high-strength aluminum alloy bending via multistage regression,” Metals, vol. 15, no. 4, p. 358, 2025.

R. G. Budynas and J. K. Nisbett, Shigley’s Mechanical Engineering Design, 11th ed. New York, NY, USA: McGraw-Hill Education, 2019.

R. L. Norton, Machine Design: An Integrated Approach, 6th ed. Boston, MA, USA: Pearson, 2019.

American Gear Manufacturers Association, ANSI/AGMA 2001-D04: Fundamental Rating Factors and Calculation Methods for Involute Spur and Helical Gear Teeth, Alexandria, VA, USA: AGMA, 2004.

F. P. Beer, E. R. Johnston Jr., J. T. DeWolf, and D. F. Mazurek, Mechanics of Materials, 7th ed. New York, NY, USA: McGraw-Hill, 2015.

J. M. Gere and B. J. Goodno, Mechanics of Materials, 9th ed. Stamford, CT, USA: Cengage Learning, 2018.

Downloads

Published

2026-06-30

How to Cite

Maneesaeng, T., Phurahong, N., Bunsing, S., & Lasing, K. (2026). Design and Development of a Semi-Automatic Steel Pipe Bending Machine with a Polynomial Regression Model for Optimal Bending Angle Prediction. Journal of Industrial Technology : Suan Sunandha Rajabhat University, 14(1), 16–29. retrieved from https://ph01.tci-thaijo.org/index.php/fit-ssru/article/view/264702

Issue

Section

Research Articles