Probability embedded failure prediction of unidirectional composites under biaxial loadings combining machine learning and micromechanical modelling

نویسندگان

چکیده

This study presents a data-driven, probability embedded approach for the failure prediction of IM7/8552 unidirectional carbon fibre reinforced polymer (CFRP) composite materials under biaxial stress states based on micromechanical modelling and artificial neural networks (ANNs). High-fidelity 3D representative volume element (RVE) finite models were used generation points. Fibre friction between fibres matrix after fibre/matrix debonding taken into consideration implemented as VUMAT subroutines, respectively. Uncertainty quantification was conducted coupled experimental–numerical probabilities inserted points to generate database training ANNs. A total 15 combinations considered datasets. Two strategies construction form-free criteria ANNs regression classification problems. It is found that problems, an ANN model with 2 hidden layers 64 neurons can achieve mean square error (MSE) 0.027% absolute (MAE) 0.78%. For 3 32 neurons, excellent performance in 98.1%. good agreement observed strength composites transverse in-plane shear predicted by these envelopes theoretically Tsai–Wu Hashin criteria.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Transverse compression failure of unidirectional composites

Y. Hu*, N.K. Kar andS.R. Nutt Gill Composites Center, Department of Chemical Engineering and Materials Science, University of Southern California, Los Angeles, California Abstract: The mechanical response of unidirectional composites subject to uniaxial transverse compressive loads was measured and analyzed by finite element simulation. Consistency in failure plane orientation was observed when...

متن کامل

Distinct failure modes in bio-inspired 3D-printed staggered composites under non-aligned loadings

The superior mechanical properties of biological materials originate in their complex hierarchical microstructures, combining stiff and soft constituents at different length scales. In this work, we employ a three-dimensional multi-materials printing to fabricate the bio-inspired staggered composites, and study their mechanical properties and failure mechanisms. We observe that bioinspired stag...

متن کامل

Compressive response and failure of fiber reinforced unidirectional composites

The compressive response of polymer matrix fiber reinforced unidirectional composites (PMC’s) is investigated via a combination of experiment and analysis. The study accounts for the nonlinear constitutive response of the polymer matrix material and examines the effect of fiber geometric imperfections, fiber mechanical properties and fiber volume fraction on the measured compressive strength an...

متن کامل

Failure Behavior of Unidirectional Composites under Compression Loading: Effect of Fiber Waviness

The key objective of this work is to highlight the effect of manufacturing-induced fiber waviness defects on the compressive failure of glass fiber-reinforced unidirectional specimens. For this purpose, in-plane, through-thickness waviness defects (with different waviness severities) are induced during the manufacturing of the laminate. Numerical and experimental results show that the compressi...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Composite Structures

سال: 2023

ISSN: ['0263-8223', '1879-1085']

DOI: https://doi.org/10.1016/j.compstruct.2023.116837