Design for Assembly in Series Production by Using Data Mining Methods

Abstract

Decision making in early production planning phases is often based on vague expert knowledge due to lack of a reliable knowledge base. Virtual planning has been prevailed as a method used to evaluate risks and costs before the concrete realization of production processes. This paper introduces a new concept and the corresponding data model for Design for Assembly by using Data Mining (DM) methods in the field of series production. The approach adopts the usage of existing planning data in order to extrapolate assembly processes. Especially linked product and process data allow the innovative usage of Data Mining methods. The concept presents assistance potentials for development of new products variants along the product emergence process (PEP). With this approach an early cost estimation of assembly processes in series production can be achieved using innovative Data Mining methods as shown in an industrial use case. Furthermore, design and planning processes can be supported effectively.