| Bibtype |
Inproceedings |
| Bibkey |
Schulte/etal/2020a |
| Author |
Schulte, Lukas and Schmitt, Jacqueline and Meierhofer, Florian and Deuse, Jochen |
| Editor |
Nunes, Isabel L. |
| Title |
Optimizing Inspection Process Severity by Machine Learning Under Label Uncertainty |
| Booktitle |
Advances in Human Factors and Systems Interaction |
| Pages |
3--9 |
| Address |
Cham |
| Publisher |
Springer International Publishing |
| Abstract |
The increasing competition forces manufacturing companies striving for Zero Defect Manufacturing to constantly improve their products and processes. This vision cannot be realized completely however, so cost-efficient inspection of quality is of high importance: While no defects should remain undetected, this always comes at the expense of pseudo defects. As this effect is common knowledge, the automatically generated inspection results have to be verified by human process experts. As this manual verification leads to tremendous inspection costs, reducing pseudo defects is a major business case nowadays. This paper presents an approach to reduce pseudo defects by applying Machine Learning (ML). A decision support system based on recorded inspection data and ML techniques has been developed to reduce manual verification efforts.
|
| Year |
2020 |
| Projekt |
SFB876-B3 |
| Isbn |
978-3-030-51369-6 |
