Page 38 - eBook_Proceedings of the International Conference on Digital Manufacturing V2

Proceedings of the International Conference on Digital Manufacturing –
Volume 2

Regressor outperforms the other models by accurately predicting
maximum stress and deformation. Finally, the ML-based
predictions have been validated against FEA simulations by
comparing the outputs of both methodologies, demonstrating the
potential of ML in augmenting conventional FEA techniques.

This study can also be expended by investigating the effect of
varying the top load applied to the bottle stack at the lowest layer
to develop generalized multi-objective solutions. Additionally,
although this study is on static loading conditions, future work can
also be implemented through dynamic loading conditions.

REFERENCES

Anush, C., Yashwanth, K., Shashank, S., Reddy, M. V., & Kumar,
A. (2021). Bottle line detection using digital image
processing with machine learning. In Journal of Physics:
Conference Series (Vol. 1998, No. 1, p. 012033). IOP
Publishing.
ASTM. (2000). Digital packaging tool installation and
maintenance.
ASTM. (2014). Test method for tensile properties of plastics.
ASTM. (2015). Test method for compressive properties of rigid
plastics.
Badarinath, P. V., Chierichetti, M., & Kakhki, F. D. (2021). A
machine learning approach as a surrogate for a finite element
analysis: Status of research and application to one
dimensional systems. Sensors, 21, 1–18.
Béreaux, Y., Charmeau, J. Y., & Balcaen, J. (2010). Optical
measurement and numerical simulation of parison formation
in blow moulding. International Journal of Material Forming,
3, 595–598.
Charlton, D. J., Yang, J., & Teh, K. K. (1994). A review of
methods to characterize rubber elastic behaviour for use in
finite element analysis. Rubber Chemistry and Technology,
67, 481–503.

22