msamDB: Towards addressing data-scarcity challenges in L-PBF additive manufacturing

Jigar Patel, Chris Vuong, Mihaela Vlasea, M. Tamer ÖzsuProceedings of the Holistic Innovation in Additive Manufacturing (HI-AM) Conference 2025 · DOI

TL;DR

This paper introduces msamDB, a novel database platform designed to combat data scarcity in Laser Powder Bed Fusion (L-PBF) additive manufacturing research. By aggregating and validating heterogeneous data from various stages of the L-PBF lifecycle, msamDB aims to foster data sharing and enable more robust, data-driven machine learning models.

What Problem Does This Paper Address?

Additive Manufacturing (AM), particularly Laser Powder Bed Fusion (L-PBF), involves a vast parameter space that makes traditional experimental or simulation-based exploration time-consuming and costly. Machine learning (ML) offers a promising avenue for rapid exploration and optimization of these parameters. However, the effectiveness of ML models is heavily reliant on the availability of large, diverse, and informative datasets. Currently, such datasets for L-PBF research are scarce, fragmented, and often lack standardization, hindering the development and widespread adoption of ML-driven solutions in the field. This paper addresses this critical data gap by proposing a centralized, scalable, and extensible database solution.

Methods

The core of this work is the development of msamDB, a relational database built on PostgreSQL. The framework is designed to ingest data from various stages of the L-PBF lifecycle, including powder characterization, build planning, process parameter selection, and surface characterization. A key aspect of msamDB is its multi-scale modeling approach, conceptualized through an Entity-Relationship (ER) diagram that captures relationships between entities like "parts," "surfaces," and "measurements."

Crucially, msamDB incorporates a comprehensive data validation layer. This layer performs rigorous rule-based and statistical testing on incoming data points to ensure a high level of trust and reduce data cleaning burdens for downstream analytics. The paper illustrates this with examples of validation scenarios, such as checking for anomalies, ensuring correct units, and verifying data integrity through linked entities.

Datasets

The paper describes the population of msamDB with data from approximately 30 L-PBF builds. This data originates from multiple research and industry studies, utilizes three different powder materials, and covers a broad range of process parameters. Specifically, the initial focus is on surface roughness data, with over 1000 data points collected across various surface orientations. The data was extracted from builds not specifically created for this work, simulating real-world conditions with heterogeneous data structures and quality.

Key Insights and Ideas

  • Data Scarcity is a Major Bottleneck: The paper clearly illustrates the challenge of data scarcity in L-PBF research, showing that most existing datasets are high-dimensional but lack sufficient size and variety for robust ML model development.
  • A Centralized, Shared Database is Crucial: msamDB proposes a solution to this by creating a platform that not only stores data but also actively promotes data sharing among researchers.
  • Data Quality is Paramount: The inclusion of a robust validation layer is a critical design choice. It ensures that the data entering msamDB meets a baseline quality standard, making it more reliable for ML applications.
  • Multi-Scale Modeling is Necessary: Recognizing the complex, multi-stage nature of L-PBF, the ER model effectively captures the intricate relationships between different data entities, enabling a more holistic understanding of the process.

Key Results

The paper demonstrates the efficacy of msamDB by extracting surface roughness data from 10 L-PBF builds across two different machines and various alloys and surface orientations. Baseline data retrieval metrics for simple and joined queries are provided, showing efficient execution times (e.g., ~0.058 ms for a simple query fetching 528 rows, and ~0.336 ms for a joined query fetching 1043 rows). The data validation layer was also demonstrated, showing how incoming data points can be assessed against existing distributions to identify potential outliers, with the system providing warnings or rejecting erroneous data.

Limitations and Future Work

The authors acknowledge several limitations:

  • Currently, only surface roughness data is ingested as a process outcome.
  • The preliminary architecture for ingesting high-volume temporal sensor data (e.g., photodiode streams) is still under development.
  • A user interface (UI) for facilitating smoother data sharing is yet to be developed.

Future work will focus on addressing these limitations, particularly the development of a user-friendly UI for data interaction. While the current scope is limited to surface roughness, the relational model is designed to be adaptable for other process outputs like density. The authors also hope to scale data ingestion to hundreds of builds by collaborating with other researchers.

Summary updated

Abstract

Data science techniques, particularly machine learning (ML), have proven to be valuable tools in PBF-LM research. While ML can rapidly model the large process parameter space of PBF-LM, their efficacy is dependent on large, informative and diverse training datasets. However, scarcity in the development and availability of such datasets is an on-going challenge. This work outlines the on-going progress to address this challenge through the development of a database platform, tentatively named msamDB (multi-scale additive manufacturing database). This platform, specifically created to manage PBF-LM academic research data, is a modular, extensible and scalable database that can promote data-sharing among researchers. The initial architecture of msamDB focuses on surface roughness data generated throughout the PBF-LM lifecycle. This work highlights the findings and challenges encountered in the design, implementation and pilot data population stages of msamDB. In its current stage, msamDB data spans data from approximately 30 builds, multiple research and industry studies, 3 different powder materials and a broad range of process parameters. Data has been collected from various stages such as powder characterization, build planning, process parameter selection, surface characterization, etc. In reference to surface roughness measurements, the database currently has more than 1000 data points across various surface orientations. This work represents first known effort to curate research PBF-LM data at scale for PBF-LM. The potential impact of such a database is to promote federated data for PBF-LM researchers, which allows for data-driven model development to have increased usability.
BibTeX
@inproceedings{patel2025msamdb,
  author = {Jigar Patel and Chris Vuong and Mihaela Vlasea and M. TAMER ÖZSU},
  title = {{msamDB: Towards addressing data-scarcity challenges in L-PBF additive manufacturing}},
  booktitle = {Proceedings of the Holistic Innovation in Additive Manufacturing (HI-AM) Conference},
  year = {2025},
  doi = {10.15353/hi-am.v1i1.6832},
}
Figure