Effective power estimation is key in streamlining continuous extrusion processes by reducing computational intensity and maximizing operational efficiency. In this paper, Naïve Bayes algorithm application in predicting commercially pure (CP) Titanium Grade 2 continuous extrusion power consumption is investigated. The model is trained using a theoretical, numerical, and experimental calculation dataset, enabling a probabilistic forecasting model. The model takes into account influential processing parameters such as feedstock temperature and extrusion wheel velocity in assessing their contribution towards powering requirements. Naïve Bayes model returns an RMSE of 0.46, demonstrating competitive performance in power consumption estimation. By leveraging probabilistic classification, this study recognizes Naïve Bayes’ potential in providing a lightweight and interpretable predictive model for metal forming processes. Contributions towards the development of data-driven methodologies in manufacturing by a real-life alternative to computationally intensive approaches render its application a viable and valuable tool in metal forming processes.
2 April 2026 in Computer Methods in Applied Mechanics and Engineering
Multiscale homogenization of woven composites requires detailed micromechanical evaluations, leading to high computational costs. Data-driven surrogate models based on neural networks address this challenge but often suffer from big data requirements, limited interpretability, and poor extrapolation capabilities. This study introduces a Hierarchical Physically Recurrent Neural Network (HPRNN) employing two levels of surrogate modeling. First, Physically Recurrent Neural Networks (PRNNs) are trained to capture the nonlinear elasto-plastic behavior of warp and weft yarns using micromechanical data. In a second scale transition, a physics-encoded meso-to-macroscale model integrates these yarn surrogates with the matrix constitutive model, embedding physical properties directly into the latent space. Adopting HPRNNs for both scale transitions can avoid nonphysical behavior often observed in predictions from pure data-driven recurrent neural networks and transformer networks. This results in better generalization under complex cyclic loading conditions. The framework offers a computationally efficient and explainable solution for multiscale modeling of woven composites.