Digital Twin Enabled Asset Management of Machine Tools

Abstract

Machine tools (MT) are essential equipment in modern manufacturing. They are a large investment which yields great returns to productivity and profitability. MTs enable the high throughput manufacturing of high precision components. Given their great importance, and their large cost, it is beneficial to implement asset management (AM) strategies such as condition monitoring, fault detection and predictive maintenance. Implementing these processes and methods can improve reliability and performance of MTs, while extending their lifetime and reducing operating expenses. Digital twins (DT) are an emerging technology within the Industry 4.0 landscape. They represent a connection between a physical system, object, or process and it's virtual representation. DTs can be leveraged for AM implementation in MTs. This work examines the potential benefits of applying DTs to AM, examples in the literature of applying AM methods to MTs using DT, and how advanced AM strategies can be deployed using DT. From examining the literature it was clear that DTs are well suited for AM in MTs. DTs enable improved data collection and processing, modeling and model retention, and historical analysis and trend prediction. DTs have been applied to a variety of application scenarios for MTs such as in cutting tools, spindles, and feed drives. DTs can additionally enable more advanced modeling solutions such as physics informed machine learning which can overcome some issues with traditional data-driven and physics-based modeling strategies. These advanced methods can improve overall AM across the MT's life-cycle and enable effective prognostic health management.