Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

A MULTIMODAL DATA-DRIVEN DECISION FUSION METHOD FOR PROCESS MONITORING IN METAL POWDER BED FUSION ADDITIVE MANUFACTURING

Published

Author(s)

Zhuo Yang, Jaehyuk Kim, Yan Lu, Ho Yeung, Brandon Lane, Albert T. Jones, Yande Ndiaye

Abstract

Data fusion techniques aim to improve inference results or decision making by combining multiple data sources. Additive manufacturing (AM) in-situ monitoring systems measure various physical phenomena and generate data at different scales and sampling rates during a build process. Data analysis based on an individual data source may not be accurate enough to monitor the process state, or be limited by the relevancy of the observations, signal-to-noise ratio, or other measurement uncertainties. This work proposes a decision-level, multimodal data fusion method that combines multiple in-situ AM monitoring data sources to improve overall process monitoring performance. A powder bed fusion experiment that was conducted to create overhang surfaces throughout a 3D part is used to illustrate and validate the proposed method. The overhang features are designed with different shapes and angles, and at various build locations. They are formed using constant laser power and scan speed. A high-frequency coaxial melt pool imaging system and a low-frequency layerwise staring camera are the two in-situ monitoring data sources used in the case study. The Naïve Bayes and k-nearest neighbors algorithms are first applied to each data set for overhang feature detection. Then both hard voting and soft voting are adopted in fusing the classification outcomes. The results show that while none of the individual classifiers are perfect in detecting overhang features, the fused decision of the 324 test samples achieved 100 % detection accuracy.
Proceedings Title
A MULTIMODAL DATA-DRIVEN DECISION FUSION METHOD FOR PROCESS MONITORING IN METAL POWDER BED FUSION ADDITIVE MANUFACTURING
Conference Dates
October 19-20, 2022
Conference Location
Lisbon, PT
Conference Title
ASME International Additive Manufacturing Conference

Keywords

Powder Bed Fusion, Additive Manufacturing, Decision Fusion, Data Fusion, Bayesian Network, Classification

Citation

Yang, Z. , Kim, J. , Lu, Y. , Yeung, H. , Lane, B. , Jones, A. and Ndiaye, Y. (2022), A MULTIMODAL DATA-DRIVEN DECISION FUSION METHOD FOR PROCESS MONITORING IN METAL POWDER BED FUSION ADDITIVE MANUFACTURING, A MULTIMODAL DATA-DRIVEN DECISION FUSION METHOD FOR PROCESS MONITORING IN METAL POWDER BED FUSION ADDITIVE MANUFACTURING, Lisbon, PT, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=935090 (Accessed April 19, 2024)
Created October 20, 2022, Updated February 26, 2024