Page 17 - eBook_Proceedings of the International Conference on Digital Manufacturing V2

COLLABORATIVE STUDY ON
WEIGHT OPTIMISATION OF

LUBRICANT BOTTLES UNDER
STACKING CONDITION USING
FINITE ELEMENT ANALYSIS AND
MACHINE LEARNING

Muhammad Hateem Arif (NED University of Engineering and
Technology), Muhammad Wasif
(NED University of Engineering and Technology) and Tariq Jamil
(NED University of Engineering
and Technology)*

ABSTRACT

Plastic bottles are of great importance in packaging industries as
their lightweight structural design helps to maintain the filled
product’s quality from the stage of packaging until delivery to
end-users. However, issues like bottle neck and handle
deformation, as well as fluid leakages, have often been reported
under stacked and logistics modes. The present study aims to
addresses some of these problems by establishing a Standard
Operating Procedure for weight optimisation of HDPE lubricant
bottles under stacking condition. The study combines Finite
Element Analysis and Machine Learning to predict mechanical
properties, particularly on maximum deformation and stress and
evaluate the effect of body thickness on bottle weight. To establish
SOP, two optimisation methods are proposed. Firstly, structural
reinforcement feature is applied to critical region of maximum
mass bottle with uniform thickness reduction, while in second
case, structural shape is retained and thickness is varied across 100
points via parison controller. To streamline a bottle design,
Machine Learning is also integrated by conducting a parametric
analysis.

1