Year: 2016
Type: article
Abstract: Manufacturing industry is highly affected by trends of globalization and increasing dynamics of product life-cycles which results in global supply chain networks. For inbound logistics, a high variance of parts from different suppliers and locations needs to be delivered to the assembly line. Planning these inbound logistics processes depends on frequently changing information of product development, assembly line planning and purchasing. Currently, a high amount of time is spent for gathering information during planning and existing knowledge from previous planning processes is scarcely used for future planning. Therefore, this paper presents an approach for predictive inbound logistics planning. Using machine learning, generic knowledge of logistics processes can be extracted and used to predict future scenarios.
Source: Procedia CIRP
Authors: Dino Knoll, Marco Prüglmeier, Gunther Reinhart
Institutions: Technical University of Munich, BMW (Germany)
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: diamond
OpenAlex ID: W2511589402
