Process mapping and anomaly detection in laser wire directed energy deposition additive manufacturing using in-situ imaging and process-aware machine learning
- PAR ID:
- 10575370
- Publisher / Repository:
- Elseiver
- Date Published:
- Journal Name:
- Materials & Design
- Volume:
- 245
- Issue:
- C
- ISSN:
- 0264-1275
- Page Range / eLocation ID:
- 113281
- Subject(s) / Keyword(s):
- LW-DED process mapping, process stability, meltpool imaging, process-aware machine learning, deep learning.
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
Regulatory authorities place stringent guidelines on the removal of contaminants during the manufacture of biopharmaceutical products. Monoclonal antibodies, Fc-fusion proteins, and other mammalian cell-derived biotherapeutics are heterogeneous molecules that are validated based on the production process and not on molecular homogeneity. Validation of clearance of potential contamination by viruses is a major challenge during the downstream purification of these therapeutics. Virus filtration is a single-use, size-based separation process in which the contaminating virus particles are retained while the therapeutic molecules pass through the membrane pores. Virus filtration is routinely used as part of the overall virus clearance strategy. Compromised performance of virus filters due to membrane fouling, low throughput and reduced viral clearance, is of considerable industrial significance and is frequently a major challenge. This review shows how components generated during cell culture, contaminants, and product variants can affect virus filtration of mammalian cell-derived biologics. Cell culture-derived foulants include host cell proteins, proteases, and endotoxins. We also provide mitigation measures for each potential foulant.more » « less
An official website of the United States government

