← Back to all news
arXiv Machine Learning

Multi-Objective Optimization Under Uncertainty of Part Quality in Fused Filament Fabrication

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.

Related stories

arXiv Machine Learning
Aug 20

Process Optimization Under Uncertainty for Improving the Bond Quality of Polymer Filaments in Fused Filament Fabrication

This paper presents a computational framework that optimizes process parameters to maximize bond quality between polymer filaments in fused filament fabrication (FFF). It couples transient heat‑transfer analysis with a sintering neck growth model, quantifies uncertainty from both aleatory and epistemic sources, and incorporates model discrepancy via a Gaussian process surrogate. Sensitivity analysis using Sobol indices and physical experiments for calibration validate that the optimized parameters yield high bond quality.

By Berkcan Kapusuzoglu, Matthew Sato, Sankaran Mahadevan, Paul Witherell
More like this →
arXiv Machine Learning
Aug 19

Physics-Informed and Hybrid Machine Learning in Additive Manufacturing: Application to Fused Filament Fabrication

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
More like this →
arXiv AI
Jun 4

Uncertainty-Aware End-to-End Co-Design of Neural Network Processors: From Training and Mapping to Fabrication

arXiv:2606. 04850v1 Announce Type: cross Abstract: Designing a neural network processor is an end-to-end co-design problem: network architecture and training budget determine the inference workload; hardware mapping decisions determine chip area, latency, and energy; and these characteristics govern fabrication yield and manufacturing cost.

By Yuyang Du, Yujun Huang, Gioele Zardini
More like this →
Hugging Face Trending Papers
Jul 8

Bayesian Optimization of Genetic Algorithm Hyperparameters in a Multi-Fidelity Framework for Efficient Lattice Material Design

This study presents a multi-fidelity framework for the systematic optimization of genetic algorithm (GA) hyperparameters. The framework integrates three fidelity levels: high-fidelity Fast Fourier Transform (FFT) homogenization for validation, a medium-fidelity 3D convolutional neural network surrogate for rapid property evaluation, and a low-fidelity Gaussian process (GP) surrogate within a Bayesian optimization (BO) framework to guide the hyperparameter search.

More like this →
Hugging Face Trending Papers
Jun 17

A Human-in-the-Loop Bayesian Optimization Framework for Constraint-Aware Bioprocess Development

This work presents an extension to Pareto Front Guided Sampling (PFGS), a Human-in-the-Loop (HitL) Bayesian Optimization (BO) framework in which Gaussian process (GP) surrogate-derived quantities are reformulated as objectives of a multi-objective optimization problem, and the resulting Pareto front is exposed to a domain expert for interactive candidate selection rather than returning a single automated recommendation. The framework is extended in two directions: constrained optimization is addressed by incorporating the posterior probability of satisfying output specification limits as an explicit Pareto objective, computed analytically from the GP posterior distribution; robust optimization is addressed by a Monte Carlo sampling strategy that estimates expected lower-confidence performance over a user-defined variability of input perturbations, capturing performance degradation under likely implementation deviations.

More like this →