This study introduces a data‑driven method for multi‑objective optimization in fused filament fabrication (FFF), targeting both geometric accuracy and filament bond quality. Experiments supply part‑quality data, which feed Bayesian neural network models that predict the two objectives while accounting for epistemic and aleatory uncertainties. Using these stochastic predictions, robustness‑based optimization explores nozzle temperature, speed, and layer thickness, producing Pareto surfaces that reveal trade‑offs and are validated through actual part manufacturing.
By Berkcan Kapusuzoglu, Paromita Nath, Matthew Sato, Sankaran Mahadevan, Paul Witherell
The article explores physics-informed and hybrid machine learning approaches for predicting bond quality and porosity in fused filament fabrication (FFF) parts. It examines three strategies—embedding physics constraints in the loss function, adding physics model outputs as inputs, and pre‑training with physics data—to enforce consistency with physical laws. Eight combinations of these strategies are tested, showing that integrating multiple approaches yields accurate predictions even with limited experimental data.
By Berkcan Kapusuzoglu, Sankaran Mahadevan
The paper presents a geometry‑informed modeling framework that couples a deep‑learning filament shape predictor (ShapeGen3DCP) with a layer‑activation finite element method to assess buildability in 3D concrete printing. By generating realistic filament geometries directly from material and process parameters, the approach eliminates the need for experimental filament characterization or fluid‑flow simulations. Validation and parametric studies show that extrusion parameters and filament shape significantly affect buildability predictions, especially for free‑flow deposition, and that an elliptical approximation balances fidelity and simplicity while volume‑conserving rectangular representations improve prediction reliability.
By Giacomo Rizzieri, Saif-Ur-Rehman, J\"org F. Unger, Annika Robens-Radermacher
arXiv:2606. 19375v1 Announce Type: new Abstract: Identifying anisotropic yield functions remains challenging since yielding is not directly observed in full-field mechanical measurements, directional calibration can require many loading directions, and selecting an appropriate analytical form is nontrivial.
By Hyeonbin Moon, Donghyuk Cho, Jecheon Yu, Jeong Whan Yoon, Seunghwa Ryu
arXiv:2602. 09120v2 Announce Type: replace Abstract: Electrospinning is a powerful technique for producing micro to nanoscale fibers with application specific architectures.
By Elisa Roldan, Tasneem Sabir
arXiv:2604. 14562v2 Announce Type: replace Abstract: Accurate temperature field prediction in metal additive manufacturing (AM) is essential for understanding the process-structure-performance relationship.
By Hyeonsu Lee, Jihoon Jeong
arXiv:2608. 05006v1 Announce Type: new Abstract: Metamodels are instrumental in reducing the computational burden associated with nested reliability analyses and optimization loops in Performance-Based Risk Optimization (PBRO) of structures under stochastic loads.
By Isabela D. Rodrigues, Seymour M. J. Spence, Henrique M. Kroetz, Andr\'e T. Beck
This study introduces a two‑stage physics‑based model to predict the build‑direction crystallographic texture intensity of Inconel 718 produced by laser powder bed fusion. Stage 1 maps process parameters to melting mode and melt‑pool geometry, while Stage 2 combines an empirical physics model with a random‑forest residual correction, attenuated by k‑nearest‑neighbor weighting and a beam‑power‑density gate. The physics‑anchored approach achieves substantially higher predictive accuracy (R² ≈ 0.78) than black‑box models and provides calibrated uncertainty estimates that allow selective withholding of predictions outside the model’s valid domain.
By Yisheng Lu, John Riris, Jie Song, Yao Fu, Jie Chen
HiPoly is a polymer-native AI framework that uses a three-level hierarchical graph architecture built on the G2RINS representation to process complete polymer descriptions. It encodes stochastic inter-monomer connectivity, composition, and molecular weight directly within its architecture, enabling end-to-end workflows from experimental data to property prediction, generative design, and physics-based validation. The framework achieves state-of-the-art accuracy for thermophysical properties of multi-component polymer systems and demonstrates generative design by discovering sustainable, PFAS-free alternatives with target surface-energy properties.
By Ge Sun, Gervasio Zaldivar, Yuan Tian, Gustavo Perez Lemus, Juhae Park, Dasha Safarian, Ming Han, Juan J. de Pablo
arXiv:2607. 29256v1 Announce Type: new Abstract: Designing polyimide structures with specific glass transition temperatures (Tg) is highly challenging.
By Junquan Hu, Zhihui Wang, Peng Xu, Xinru Guo, Xintong Li, Kun Lu, Ben Fei
arXiv:2510. 16023v2 Announce Type: replace Abstract: Linear polymers, macromolecules formed from monomers covalently bonded into continuous chains, underpin countless technologies and are indispensable to modern life.
By Fanmeng Wang, Ruochao Wang, Shan Mei, Wentao Guo, Hongshuai Wang, Qi Ou, Zhifeng Gao, Hongteng Xu
arXiv:2608. 10549v1 Announce Type: new Abstract: Achieving high accuracy in laser-based cutting of optical films requires careful tuning of parameters such as focal length and laser power beam, adjusted according to the specific properties of each film type.
By Khanh Quan Pham, Majid Kundroo, Geunwoo Ban, Seongho Bae, Taehong Kim