University of Twente Student Theses
Improving the defect detection performance of Incoming Quality Control
Vent, J.M.H. de (2024) Improving the defect detection performance of Incoming Quality Control.
|
PDF
4MB |
| Abstract: | This thesis at VDL ETGA, a high-tech industry supplier, focuses on improving Incoming Quality Control (IQC) for semiconductor machine modules. In 2023, 740 quality complaints were registered, with only 9% detected at incoming goods. Most defects (82%) are found during assembly, costing €3,000 additionally per complaint. The study aims to enhance IQC detection by refining item selection and inspection instructions. A predictive model using Logistic Regression, Decision Tree, SVM, XGBoost, and CatBoost was developed, with CatBoost achieving the highest F1 score. The model predicts defects with key features like item code, price, and supplier. Implementing the model improved the inspection performance, reducing the annual quality costs by 10%. The optimal inspection frequency (16 per day) could save a total of 16% annually but requires doubling IQC staff. The model, now in use, selects purchase order lines and provides inspection instructions, achieving a 15% precision rate. |
| Item Type: | Essay (Master) |
| Clients: | VDL ETG Almelo, Almelo, The Netherlands |
| Faculty: | BMS: Behavioural, Management and Social Sciences |
| Subject: | 50 technical science in general |
| Programme: | Industrial Engineering and Management MSc (60029) |
| Link to this item: | https://purl.utwente.nl/essays/103384 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page