Data mining methods for macro level process planning

Procedia CIRP, vol. 88, pp. 48–53

Abstract

Due to increasing availability of feedback data from the shop floor and prevalence of feature technology for CAD data, relevant information for process planning is available in data of completed production orders. Data mining can be used to extract the relevant information, however the identification of suitable methods for the specific domain of macro level process planning is challenging. In this paper, we analyze data types and distributions of process planning problems as well as the suitability of data mining methods. The methods are matched to planning problems and successfully applied to case study data to obtain process planning information.

Authors 3

1. Günther Schuh Aachen Laboratory for Machine Tools and Production Engineering (WZL)

   RWTH Aachen University

   Affiliation as printed

   Laboratory for Machine Tools and Production Engineering (WZL), RWTH Aachen University, Steinbachstraße 19, D-52074 Aachen, Germany

2. Jan-Philipp Prote Aachen Laboratory for Machine Tools and Production Engineering (WZL)

   RWTH Aachen University

   Affiliation as printed

   Laboratory for Machine Tools and Production Engineering (WZL), RWTH Aachen University, Steinbachstraße 19, D-52074 Aachen, Germany

3. Philipp Hünnekes corresponding Aachen Laboratory for Machine Tools and Production Engineering (WZL)

   RWTH Aachen University

   Affiliation as printed

   Laboratory for Machine Tools and Production Engineering (WZL), RWTH Aachen University, Steinbachstraße 19, D-52074 Aachen, Germany