Digital twin-driven carbon emission prediction and low-carbon control of intelligent manufacturing job-shop

Abstract

Along with the development of sensing and data processing technology, intelligence manufacturing based on cyber physical system (CPS) is a development tendency of manufacturing industry. And digital twin has been regarded as an implement method of CPS. Considering the complexity and uncertainty of discrete manufacturing job-shop, the carbon emission data integration and low-carbon control of the manufacturing systems automatically are two significant challenges. In order to realize the carbon emission reduction in intelligent manufacturing workshop, a digital twin-driven carbon emission prediction and low-carbon control of intelligent manufacturing job-shop is proposed, which includes digital twin model of low-carbon manufacturing job-shop, digital twin data interaction and fusion for low-carbon manufacturing, digital twin-driven carbon emission prediction and low-carbon control. And three key enabling technologies are also studied, i.e., digital twin data processing of low-carbon manufacturing job-shop, carbon emission evaluation and prediction service based on digital twin, digital twin data-driven low-carbon control methods of manufacturing job-shop. This method can integrate the latest information and computing technology with low-carbon manufacturing, and verify and optimize the control schemes through virtual workshop. Meanwhile, the carbon emission evaluation and prediction can be encapsulated into a service of a machine tool for customers.