AI-assisted prediction of St14 steel sheets formability: Neural-fuzzy systems and crystal plasticity assessments
Journal
Structures
ISSN
2352-0124
Date Issued
2024-07
Author(s)
Zhao Zisong
Mostafa Habibi
Abstract
We've introduced a new technique leveraging artificial intelligence to determine in-plane forming limit strains in St14 sheet metals.
A neural-fuzzy AI system was devised to predict safe points on forming limit diagrams, considering aspects like crystal texture, metal sheet thickness, and spherical punch diameter. Neural-fuzzy systems could be utilized in prediction of forming limit curves using linguistic data description.
To obtain the data required for training the AI network, in-depth tests, including XRD, metallography, tensile testing, and Nakazima's hemisphere evaluations, were carried out to detail the metallurgical and mechanical properties of St14 sheet metal.
Data on texture, the tensile curves, and grain morphology were then incorporated in crystal plasticity models to find hardening constants for St14's single crystals. Using these determined values, Nakazima's tests were replicated through multi-crystal aggregate configurations.
We then undertook a comprehensive parameter investigation via 324 crystal plasticity simulations to shed light on the effects of texture, sheet depth, and punch dimensions on St14's formability.
This rich dataset paved the way for training an adaptive neural fuzzy inference system (ANFIS), leading to substantial reductions in time and computational needs. The results validate that the ANFIS model offers accurate and reliable predictions, highlighting its viability for wider use in determining forming limit diagrams.
A neural-fuzzy AI system was devised to predict safe points on forming limit diagrams, considering aspects like crystal texture, metal sheet thickness, and spherical punch diameter. Neural-fuzzy systems could be utilized in prediction of forming limit curves using linguistic data description.
To obtain the data required for training the AI network, in-depth tests, including XRD, metallography, tensile testing, and Nakazima's hemisphere evaluations, were carried out to detail the metallurgical and mechanical properties of St14 sheet metal.
Data on texture, the tensile curves, and grain morphology were then incorporated in crystal plasticity models to find hardening constants for St14's single crystals. Using these determined values, Nakazima's tests were replicated through multi-crystal aggregate configurations.
We then undertook a comprehensive parameter investigation via 324 crystal plasticity simulations to shed light on the effects of texture, sheet depth, and punch dimensions on St14's formability.
This rich dataset paved the way for training an adaptive neural fuzzy inference system (ANFIS), leading to substantial reductions in time and computational needs. The results validate that the ANFIS model offers accurate and reliable predictions, highlighting its viability for wider use in determining forming limit diagrams.