Development of an edge computing-based cyber-physical machine tool

Abstract Digital twin is a virtual model that represents physical entities in a digital manner. By leveraging means of data to simulate the behavior of physical entities in the real environment, the functions of physical entities can be optimized and expanded, through virtual and real interaction feedback, data fusion, decision making, and optimization. Despite numerous researches on digital twin concept and its applications, scarcely any discusses about the computation efficiency of the twin established. In order to shorten the latency of mapping and reduce the high computation workload in the cloud, this paper develops a cyber-physical machine tool based on edge computing techniques, to realize remote sensing, real-time monitoring and scalable high-performance digital twin application. Furthermore, a novel edge computing algorithm is proposed to detect the abnormality of the edge data from two aspects: the unary outliers of the edge data itself and the multivariate parameter correlation among edge devices. The effectiveness of the application platform of the cyber-physical machine tool developed is verified by the prototype system and edge algorithm experiment.