

Porsche combines bayesian networks with modern approaches to optimize production planning
Aug 16, 2023
Simon Dürr from Porsche and Prof. Dr. Marco Huber discuss the optimization of production planning using Bayesian networks. They delve into incorporating customer behavior and market variations, the creation and reinforcement learning of network structures, and the challenges of implementation in a large organization. They also highlight the importance of plant orders and the potential application in other industries.
AI Snips
Chapters
Transcript
Episode notes
Porsche's Legacy System
- Porsche's planning and ordering process was implemented 24 years ago by a small team.
- This monolithic system, based on SAP, is now facing a redesign due to the end of support for some modules.
Service-Oriented Approach
- Porsche aims to shift from a monolithic system to a service-oriented approach for planning and ordering.
- This involves combining a greenfield and brownfield approach to address increasing product variations and customer configurations.
Global Challenges
- Porsche's global presence requires adapting to diverse customer behaviors in different markets.
- The established planning process struggles to accommodate these varying demands and supply chain uncertainties.