A framework for big data driven process analysis and optimization for additive manufacturing

Abstract

Purpose This paper aims to present an overall framework of big data-based analytics to optimize the production performance of additive manufacturing (AM) process. Design/methodology/approach Four components, namely, big data application, big data sensing and acquisition, big data processing and storage, model establishing, data mining and process optimization were presented to comprise the framework. Key technologies including the big data acquisition and integration, big data mining and knowledge sharing mechanism were developed for the big data analytics for AM. Findings The presented framework was demonstrated by an application scenario from a company of three-dimensional printing solutions. The results show that the proposed framework benefited customers, manufacturers, environment and even all aspects of manufacturing phase. Research limitations/implications This study only proposed a framework, and did not include the realization of the algorithm for data analysis, such as association, classification and clustering. Practical implications The proposed framework can be used to optimize the quality, energy consumption and production efficiency of the AM process. Originality/value This paper introduces the concept of big data in the field of AM. The proposed framework can be used to make better decisions based on the big data during manufacturing process.