Refine
Document Type
- Article (13)
- Part of a Book (10)
- Contribution to a Periodical (1)
Institute
Is part of the Bibliography
- yes (24)
Production companies are required to implement efficient, flexible manufacturing processes to face the competitive global market. The ongoing digital transformation leads many companies to store production process data, which offers optimization potential using Artificial Intelligence (AI). However, production planning and control is often still performed manually with a significant amount of human expert knowledge. To enhance the decision-makers’ knowledge and hereby the decisions’ quality, the available database can be analyzed with AI methods. This paper aims at improving the human decision-making process by providing a methodology to evaluate and apply AI-generated knowledge w.r.t. its quality and long-term usefulness for decision-makers.
Die Automobilproduktion steht aktuell vor der Herausforderung, einen sich weiter diversifizierenden Antriebsmix effizient zu produzieren. Der vorliegende Beitrag erläutert die grundsätzlichen Einflüsse alternativer Antriebsarten auf die Fahrzeugproduktion, welche mithilfe umfangreicher Experteninterviews ermittelt wurden. Diese Erkenntnisse können genutzt werden, um langfristig die richtigen Produktionsstrategien für die Gestaltung effizienter Produktionsnetzwerke abzuleiten.
The automotive industry is currently facing significant uncertainties and challenges. At the same time, efforts to achieve emission-free mobility are leading to power train diversity. In this complex environment, it is essential for car producers to define an efficient and resilient production strategy of future car production networks. This article provides a universal approach and simulation model to evaluate production strategies considering power train diversity. A case study, mirroring possible scenarios for automotive manufacturers, shows that a certain proportion of mix production can have an advantage in terms of resilience compared to a highly efficient pure-variant network, especially by marked uncertainties.
