Anwendung von Support Vector Regression zur vorausschauenden Identifikation von Störungswirkungen in der Produktionslogistik

Abstract

On time delivery performance is one of the most important logistic indicators. In particular, for producing companies the on-time delivery performance depends to a high degree on the fulfillment of planned completion dates. Unexpected disruptions cause significant deviations from planned processes and thus impair the compliance with the completion dates. The use of early warning systems in the context of operational disruption management can help to identify potential disruptive effects at an early stage in order to extend the action period for adequate reactions to disruptions. Therefore, in this paper the study of support vector regression (SVR) with regard to applicability and operational capability for the identification of disruptive effects in production logistics is presented.