Home
Scholarly Works
Digital Twin Enabled Performance Optimization of...
Conference

Digital Twin Enabled Performance Optimization of Machine Tools: A Survey

Abstract

Digital twin (DT) is an emerging technology within the Industry 4.0 landscape. They represent a connection between a physical system, object, or process and its virtual representation, and are ideal candidates to augment control and decision-making capabilities in systems. They allow for real-time model, parameter, and state identification and updates, which can enable and enhance various control and performance improvement schemes. An ideal application case for this technology would be a machine tool (MT) which are critical manufacturing systems. MTs have various subsystems which work together to accomplish various tasks, they are often electro-mechanical and can include: the spindle, feed drives, tool changer, and cooling system. Precise control is essential for these subsystems, as work pieces produced using MTs are often required to adhere to the most rigorous standards of geometric tolerance. This work examines the potential performance and control improvements when implementing a DT by examining the literature on current applications of DT for improving control and performance in MTs. It was shown that DT has been successfully applied to improve performance and outcomes by implementing real-time performance monitoring, improving control scheme optimization, and enabling dynamic machining parameter adjustments. With these improvements, benefits were seen in surface finish, geometric conformance, cycle time, tracking errors, and disturbance rejection. While still in the early stages of development, DTs have been shown to be a promising paradigm for MT performance optimization.

Authors

Sicard B; Wu Y; Gadsden SA; McCafferty-Leroux A

Volume

00

Pagination

pp. 1-8

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Publication Date

August 9, 2025

DOI

10.1109/acdsa65407.2025.11166550

Name of conference

2025 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)
View published work (Non-McMaster Users)

Contact the Experts team