Improving Manufacturing Quality by Re-sequencing Assembly Operations: a Data-mining Approach

An assemble-to-order policy delays the final assembly operations of a product until a customer order is received. The quality of the final product is determined by the quality of the assembly operations. The datamining approach presented in this paper uses information extracted from production history to determine the sequence of assemblies that minimize the risk of producing faulty products. The extracted knowledge plays important role in sequencing modules and forming product families that minimize the cost of non-quality. The concepts introduced in the paper are illustrated with numerical results.