Governing void growth, stress triaxiality (η) is a crucial parameter in ductile damage prediction. η is defined as the ratio of mean stress to equivalent stress and represents loading conditions. Attempts at introducing material anisotropy in ductile damage models have started only recently, rendering necessary in-depth investigation into the role of η here. η is commonly derived via finite elemnt (FE) simulation. An alternative is presented here: based on analytical expressions, η is obtained directly from the strains in the critical zone. For anisotropic materials, η associated with a specimen varies with yield criterion and material (anisotropy). To investigate the meaning of triaxiality for anisotropic materials, metal sheets made of dual phase steel DP780, and zirconium alloy Zirlo are chosen. Analytical expressions for η are derived for three popular yield criteria: von Mises, Hill48 and Barlat89. Tensile tests are performed with uniaxial tension, notch, and shear specimens, and the local principal strains, measured via digital image correlation (DIC), are converted to h. The uniaxial tension case reveals that only the anisotropic yield criteria can predict the expected η = 1/3. The ramifications associated with anisotropy become apparent for notched specimens, where η differences are highest; for shear specimens, the yield criterion and material-dependence is relatively moderate. This necessitates η and, consequently, the triaxiality failure diagram (TFD) being accompanied by the underlying yield criterion and anisotropy parameters. As the TFD becomes difficult to interpret, it seems more advantageous to provide pairs of principal strain ratio β and failure strain. Suggestions for deriving representative β and η are made.

In the automotive industry, extensive research has been conducted to eliminate factors negatively impacting product quality, such as wrinkles, cracks, and thickness distribution in components. The application of drawbeads often relies on the experience of field workers, leading to considerable trial and error before stabilizing the production process. Therefore, to efficiently transform these inefficiencies related to time and cost, there is a need for real-time predictive technology for forming quality based on the position of drawbeads and the bead force. This study proposes a method for predicting formability in real-time, based on a digital twin framework that considers the position of drawbeads and holder force. A digital twin was developed to predict the sheet metal forming process using Support Vector Machine, Random Forest, Gradient Boosting Machine, and Artificial Neural Networks. The machine learning models were trained using finite element analysis data corresponding to the position and bead force of drawbeads, enabling the real-time prediction of wrinkles and crack occurrences. The accuracy of the machine learning models was demonstrated, achieving 100% accuracy in determining crack occurrence, with a mean squared error (MSE) of 0.141 for wrinkle prediction and 0.038 for crack prediction, thereby ensuring the accuracy of the forming prediction model based on drawbead applications. Based on these predictive models, a user-friendly GUI has been developed, which is expected to reduce design time and costs while facilitating real-time predictions of forming quality, such as wrinkles and cracks, on-site.