In-situ Porosity Detection in Additive Manufacturing
Paper in proceeding, 2025
Additive Manufacturing (AM) is a rapidly growing technology with applications in aerospace, automotive, and medical industries. Scalable AM requires in-situ quality monitoring to detect defects promptly. However, in-situ monitoring introduces scalability challenges due to high data volumes, rapid acquisition rates, and strict latency requirements. We introduce Hephaestus, a continuous in-situ monitoring system for data streams from optical monitoring sensors, able to detect porosity risks promptly and to balance accuracy and timeliness by adjusting the window of data used for porosity detection. Using data from two builds, we study this trade-off and the method's cost-benefit towards early cancellation decisions.
In-situ Monitoring; Stream Processing; Machine learning
Author
Erik Sievers
Chalmers, Computer Science and Engineering (Chalmers), Computer and Network Systems
Marina Papatriantafilou
Chalmers, Computer Science and Engineering (Chalmers), Computer and Network Systems
Vincenzo Massimiliano Gulisano
Chalmers, Computer Science and Engineering (Chalmers), Computer and Network Systems
Eduard Hryha
Chalmers, Industrial and Materials Science, Materials and manufacture
Lars Nyborg
Chalmers, Industrial and Materials Science, Materials and manufacture
Zhuoer Chen
Chalmers, Industrial and Materials Science, Materials and manufacture
Debs 2025 Proceedings of the 19th ACM International Conference on Distributed and Event Based Systems
211-222
9798400713323 (ISBN)
19th ACM International Conference on Distributed and Event-Based Systems, DEBS 2025
Gothenburg, Sweden,
Gothenburg, Sweden,
WASP-WISE STRATIFIER
Wallenberg Initiative Materials Science for Sustainability, 2024-01-01 -- 2025-01-01.
Wallenberg AI, Autonomous Systems and Software Program, 2024-01-01 -- 2025-01-01.
Relaxed Semantics Across the Data Analytics Stack (RELAX-DN)
European Commission (EC) (EC/HE/101072456), 2023-03-01 -- 2027-03-01.
Demonstration of Infrastructure for Digitalization enabling industrialization of Additive Manufacturing (DiDAM)
VINNOVA (2019-05591), 2020-02-20 -- 2023-02-20.
VINNOVA, 2020-02-20 -- 2023-02-20.
Scalability and quality control in AM - Big Data and ML in Production
Chalmers, 2020-01-01 -- .
Additive Manufacturing using Metal Pilot Line (MANUELA)
European Commission (EC) (EC/H2020/820774), 2018-10-01 -- 2022-09-30.
VR EPITOME - Summarization and structuring of continuous data in concurrent processing pipelines
Swedish Research Council (VR) (2021-05424), 2022-01-01 -- 2025-12-31.
Areas of Advance
Information and Communication Technology
Production
Energy
Subject Categories (SSIF 2025)
Computer Sciences
Computer Engineering
Computer Systems
Other Computer and Information Science
DOI
10.1145/3701717.3734463