Abstract
The manufacturing industry is highly affected by trends of mass customization and increasing dynamics of product life-cycles which result in a large set of part variants. Thus, the required effort for logistics planning and, in particular, for packaging planning is increasing. This paper proposes an approach to automate the assignment of packaging for an individual part based on its characteristics using machine learning. We use the historical data of product parts and their packaging specifications to train our two-step machine learning model. Consequently, the model is able to propose a packaging with an accuracy of 84% in comparison with real-world data.
Original language | English |
---|---|
Pages (from-to) | 576-581 |
Number of pages | 6 |
Journal | Procedia CIRP |
Volume | 81 |
DOIs | |
State | Published - 2019 |
Event | 52nd CIRP Conference on Manufacturing Systems, CMS 2019 - Ljubljana, Slovenia Duration: 12 Jun 2019 → 14 Jun 2019 |
Keywords
- Case study
- Machine learning
- Model building
- Packaging planning
- Production planning