The proposed paper introduces a practical and expandable digital twin (DT)-based tool condition monitoring (TCM) system in CNC turning, which is tailored for the Industry 4.0 laboratory environment in engineering teaching.
A systematic search of the recent developments in DT was done, including data-driven, physics-based and hybrid methods. The knowledge is packaged into a five-layer DT framework comprising of virtual modeling, sensor systems, real-time data connectivity, analytical tools and operator interfaces. The paper further identifies the way in which this framework can be applied in an academic CNC lab with low-cost sensors, Internet of Things (IoT) platforms and simulation tools.
The Hybrid DT Model’s wear estimation was validated by way of simulation-based validation showing rating A, average accuracy rating of 89%–92% and also having a mean absolute error of only between 0.015 and 0.020 mm. In comparison to purely data-driven approaches, Hybrid DT’s greater robustness allowed it to function better under different machining environments (i.e. variable cutting conditions). The lab prototype has demonstrated that low-cost sensors along with IoT integration enable real-time monitoring capabilities.
The study is mainly conceptual; the validation of experiment using simulation or prototype implementation is cited as future research.
The framework promotes practical learning in intelligent manufacturing, where students will have the opportunity to interact with real-time monitoring and data analytics, as well as a virtual machining environment.
To the best of the authors’ knowledge, this paper is the first one to fill the gap between industrial DT-based TCM methods and educational use, providing a conceptual framework about how to apply Industry 4.0 technologies to engineering laboratories.
