Performance, cost, and risk
What are the performance, cost, and risk impacts of implementing this product?
- Performance: Improves upon existing anomaly detection models for powder bed fusion. Enables detecting manufacturing defects before parts are complete, saving time and resources.
- Cost: The product involves certain data collection capabilities which, if not available, need to be invested in.
- Risk: The product deals exclusively with recoater streaking errors – detection for other common errors in powder bed fusion should be implemented in parallel.
Implementation requirements
What capabilities would a business/organization/institution need to have to implement this product?
- Processes: Validation and evaluation processes of anomaly detection procedures for asset management.
- Resources: Computational infrastructure, manufacturing data, data analysts.
- Competences: Machine learning expertise and substantial knowledge of manufacturing assets’ characteristics to enable appropriate decision-making.
- Technologies: Ultimately, data (pre)processing, statistics, and visualization tools for anomaly detection (e.g., PowerBI).
Related works
- Stribos et al. (2023). A Comparison of Anomaly Detection Algorithms with applications on Recoater Streaking in an Additive Manufacturing Process (Factsheet).
- Stribos et al. (2024). A comparison of anomaly detection algorithms with applications on recoater streaking in an additive manufacturing process (Thesis).
Contact information
For further inquiries regarding this product, feel free to get in touch with:
- Roel Bouman, Radboud Universiteit. roel [dot] bouman [at] ru [dot] nl
- Reinier Stribos, University of Twente. r [dot] h [dot] stribos [at] utwente [dot] nl
