A preliminary data fusion study to assess the feasibility of Foundation Process-Property Models in Laser Powder Bed Fusion
🤖 AI Summary
This work addresses the challenge of data-scarce process–property modeling across materials (17-4 PH/316L) and properties (porosity/hardness) in laser powder bed fusion (LPBF). It presents the first systematic validation of data-driven transfer learning for constructing LPBF foundational models. Methodologically, the study integrates Gaussian process modeling, multi-configuration transfer learning, and interpretable hyperparameter analysis. Results reveal that naïve data-fusion transfer exhibits poor robustness, and uncover a coupled influence of dataset size, noise level, physical relationship complexity, and model architecture on transfer efficacy. The work innovatively proposes a domain-knowledge-embedded, structured learning paradigm—grounded in empirical evidence—to guide the design of foundational models for additive manufacturing, thereby establishing methodological principles and practical guidelines for cross-material, cross-property generalization in LPBF.
Application Category
📝 Abstract
Foundation models are at the forefront of an increasing number of critical applications. In regards to technologies such as additive manufacturing (AM), these models have the potential to dramatically accelerate process optimization and, in turn, design of next generation materials. A major challenge that impedes the construction of foundation process-property models is data scarcity. To understand the impact of this challenge, and since foundation models rely on data fusion, in this work we conduct controlled experiments where we focus on the transferability of information across different material systems and properties. More specifically, we generate experimental datasets from 17-4 PH and 316L stainless steels (SSs) in Laser Powder Bed Fusion (LPBF) where we measure the effect of five process parameters on porosity and hardness. We then leverage Gaussian processes (GPs) for process-property modeling in various configurations to test if knowledge about one material system or property can be leveraged to build more accurate machine learning models for other material systems or properties. Through extensive cross-validation studies and probing the GPs' interpretable hyperparameters, we study the intricate relation among data size and dimensionality, complexity of the process-property relations, noise, and characteristics of machine learning models. Our findings highlight the need for structured learning approaches that incorporate domain knowledge in building foundation process-property models rather than relying on uninformed data fusion in data-limited applications.
Problem
Research questions and friction points this paper is trying to address.
Assessing feasibility of Foundation Process-Property Models in LPBF
Overcoming data scarcity for process-property model construction
Testing transferability of knowledge across material systems and properties
Innovation
Methods, ideas, or system contributions that make the work stand out.
Uses Gaussian processes for process-property modeling
Tests transferability across material systems and properties
Incorporates domain knowledge in structured learning approaches
🔎 Similar Papers
No similar papers found.
