Abstract
In this paper, an Artificial Neural Network (ANN) is used to predict the stress-strain behavior of PET at conditions relevant to Stretch Blow Moulding i.e. Large equibiaxial deformation at elevated temperature and high strain rate. The input vectors considered are temperature, strain, and strain rate with a corresponding output parameter of stress. In the present work, a feed-forward back backpropagation algorithm was used to train the ANN. The ANN is able to approximate the relationship between stress and strain at various strain rates & temperatures to a high degree of accuracy for all conditions tested.
Highlights
Predicting the deformation behavior of amorphous polyethylene terephthalate (PET) at elevated temperature is one of the most important problems in order to achieve accurate Stretch Moulding simulations (SBM)
Several material constitutive models have been proposed by researchers to describe the mechanical behavior of PET, just above the glass transition temperature region which is the most critical temperature region for industry production, such as Boyce’s 3D model[1][2], ‘Glass-Rubber’ model from Buckley and Jones[3][4], augmented Buckley’s model proposed by Yan[5] and visco-hyperelastic model proposed by Chevalier et al[6]
This paper aims to build up a model by Artificial Neural Network (ANN) to predict the behavior of amorphous PET at conditions relevant to Stretch Blow Monlding i.e. Equibiaxial deformation in the temperature range 85°C to 110°C and strain rate range 1 s-1 to 32 s-1
Summary
Predicting the deformation behavior of amorphous PET at elevated temperature is one of the most important problems in order to achieve accurate Stretch Moulding simulations (SBM). Constitutive laws need to consider the effects of all these parameters, which makes modelling PET behavior become a very complex task. This task is suitable for ANNs which are able to overcome these problems that are difficult to be modeled by conventional mathematics and analytical methods[8]. Once an ANN is trained perfectly, the neurons’ weights and biases will be extracted into a matrix which will be implemented into the user-defined material subroutine (VUMAT) as part of a constitutive model used during FEA forming simulation.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
