Comparison of Deterministic and Probabilistic Machine Learning Algorithms for Precise Dimensional Control and Uncertainty Quantification in Additive Manufacturing

2025-09-15

AI Summary

This study addresses the challenges of low dimensional accuracy and difficulty in quantifying uncertainty in additive manufacturing (AM). We propose a machine learning framework that integrates design features with process-induced variations, and— for the first time—systematically distinguishes and quantifies epistemic and aleatoric uncertainties. Methodologically, the framework unifies support vector regression (SVR), Gaussian process regression (GPR), and Bayesian neural networks (BNN) to jointly model continuous and categorical variables. It is trained and validated on experimental data from 405 parts fabricated across multiple AM systems and materials. Results show: (i) SVR achieves point prediction accuracy approaching the fundamental limit of process repeatability; (ii) GPR balances predictive accuracy with interpretability; and (iii) BNN explicitly disentangles epistemic and aleatoric uncertainties. The framework significantly enhances reliability of dimensional prediction and enables risk-informed design, establishing a new paradigm for data-driven robust manufacturing.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

We present a probabilistic framework to accurately estimate dimensions of additively manufactured components. Using a dataset of 405 parts from nine production runs involving two machines, three polymer materials, and two-part configurations, we examine five key design features. To capture both design information and manufacturing variability, we employ models integrating continuous and categorical factors. For predicting Difference from Target (DFT) values, we test deterministic and probabilistic machine learning methods. Deterministic models, trained on 80% of the dataset, provide precise point estimates, with Support Vector Regression (SVR) achieving accuracy close to process repeatability. To address systematic deviations, we adopt Gaussian Process Regression (GPR) and Bayesian Neural Networks (BNNs). GPR delivers strong predictive performance and interpretability, while BNNs capture both aleatoric and epistemic uncertainties. We investigate two BNN approaches: one balancing accuracy and uncertainty capture, and another offering richer uncertainty decomposition but with lower dimensional accuracy. Our results underscore the importance of quantifying epistemic uncertainty for robust decision-making, risk assessment, and model improvement. We discuss trade-offs between GPR and BNNs in terms of predictive power, interpretability, and computational efficiency, noting that model choice depends on analytical needs. By combining deterministic precision with probabilistic uncertainty quantification, our study provides a rigorous foundation for uncertainty-aware predictive modeling in AM. This approach not only enhances dimensional accuracy but also supports reliable, risk-informed design strategies, thereby advancing data-driven manufacturing methodologies.

Problem

• Accurately estimating dimensions of additively manufactured components
• Quantifying uncertainty in additive manufacturing dimensional control
• Comparing deterministic and probabilistic ML methods for manufacturing

Innovation

• Probabilistic framework for dimensional estimation
• Gaussian Process Regression for interpretable predictions
• Bayesian Neural Networks capturing dual uncertainties