Researchers have developed new methodologies for optimizing the fused filament fabrication (FFF) process, focusing on improving part quality under uncertainty. One approach uses Bayesian neural networks to predict geometric inaccuracy and filament bond quality, incorporating both model and input uncertainties to optimize parameters like nozzle temperature and speed. Another paper presents a computational framework that couples heat transfer analysis with a sintering model to maximize filament bond quality, using Sobol indices for sensitivity analysis and Gaussian processes to manage model discrepancy. A third study explores physics-informed and hybrid machine learning strategies, integrating physics knowledge into deep neural networks to predict bond quality and porosity, even with limited experimental data. AI
IMPACT These advancements in AI-driven optimization could lead to more consistent and higher-quality 3D printed parts in industrial applications.
RANK_REASON Multiple arXiv papers detailing novel research methodologies in additive manufacturing.
- arXiv
- Berkcan Kapusuzoğlu
- deep neural network
- fused filament fabrication
- Bayesian neural networks
- Gaussian process
AI-generated summary · Google Gemini · from 3 sources. How we write summaries →
