Identifying generic routings for product families based on text mining and tree matching

Product customization leads to an exponentially increased number of product and process variants, which exaggerates the difficulties in building up customization capabilities for make-to-order production systems. It is imperative for companies to configure existing operations routings by exploiting similarities among product and process families so as to take advantage of repetitions. Corresponding to a product family, a process family comprises a set of similar production processes that share certain common operations routings (namely, generic routings). In addition to leveraging the costs of delivering variety, exploiting process families around generic routings can reduce development risks by reusing existing facilities and proven process elements. This paper applies data mining techniques to identify generic routings from large amount of production information and process data available in a firm's legacy systems. Generic routing identification encompasses three consecutive stages, including routing similarity measure, routing clustering and routing unification. Text mining and tree matching techniques are applied to cope with the textual and structural types of data underlying generic routings. A case study of mass customization production of vibration motors for mobile phones is reported to illustrate the feasibility and potential of generic routing identification.