A Digital Twin Model for Dynamic Optimization of Metal Cutting Process Parameters

Metal cutting process optimization problem has been extensively studied in the past few decades, researchers either conduct experimental design, develop heuristic algorithms or design expert system to optimize process parameters. The main idea of the past research is to optimize a set of process parameters before executing the entire process steps, which fails to effectively respond to the needs of dynamic manufacture environment. However, very little research has focused on the dynamic optimization of process parameters during the process. Digital twin is commonly known as the enabling technology to solve the dynamic problem in the industrial sector. This paper proposes a novel digital twin framework for metal cutting process dynamic optimization during the metal cutting process. Five characteristics of digital twin model of the proposed framework are analyzed. In this framework, a metal cutting process digital twin model is proposed to dynamically infer the optimal process parameters while interacting with its physical counterpart during the process. An information model for the metal cutting process digital twin is put forward to formalize the representation of the comprehensive information between the digital twin and its physical counterpart. The effectiveness and feasibility of the proposed digital twin model are tested in a case study on a milling process.