Digital Twin of Micro-Milling Process for Micro-Tool Wear Monitoring

Abstract

This paper presents a novel digital twin of the micro-milling process that can indirectly monitor the micro-tool wear progression by making inferences from the real-time and simulated variables of the micro-milling process. With its wear monitoring service, the digital twin is regarded as the new approach in the field of tool wear monitoring (TWM) systems. The dynamics of the micro-milling process are simulated by using physics-based models, such as spindle motor, spindle controller, and cutting torque models with real-time data from the actual micro-milling machine. The advantage of the proposed digital twin is that the wear monitoring can adaptively adjust to the main machining parameters, such as feed rate and spindle speed. Therefore, exhaustive training of the models is not needed whenever the machining parameters change. The performance of the digital twin in monitoring the wear progression has been evaluated through several slot micro-milling experiments of the stainless steel workpiece. The evaluation and analysis of the experiment result concluded that the proposed digital twin could detect wear progression abnormality by using the estimate discrepancy. Furthermore, the wear severity could be recognized using the final wear estimation value.

Tool Wear Monitoring in Micro-Milling Based on Digital Twin Technology with an Extended Kalman Filter

“…φ = 1 for an on-state spindle 0 for an off-state spindle ( 16) ψ = 1 for on-state feeding 0 for off-state feeding ( 17) The physical contact detector generates the contact signal κ by monitoring the collision between the 3D virtual models of the tool and workpiece inside an open-source CAD system called FreeCAD [43]. The position of the virtual model inside the FreeCAD virtual environment is updated regularly following the real-time position from the feeddrive controller [19]. The collision volume V c reported by the collision detection module of FreeCAD becomes information for judging whether tool-workpiece contact occurs; see Equation (18) and Figure 4a.…”

“…The collision volume V c reported by the collision detection module of FreeCAD becomes information for judging whether tool-workpiece contact occurs; see Equation (18) and Figure 4a. For machining with simple workpiece geometry (see Figure 4b), the physical contact detector may use the information of machined surface vertexes (cyan dots) together with the feeding motion direction ⃗ f. A contact event can be detected by checking whether the tool perimeter (red circle) is inside or outside the machined surface; see Equations (19) and (20). The contact signal κ is generated by evaluating the six cases in Equation (21).…”

“…The works contain a formulation of a DT model based on the mechanistic law of micromilling [18]. The proposed system also used open-source CAD software to visualize the micro-tool motion and compute the material removal rate based on the tool-workpiece immersion volume [19]. More research is required to demonstrate the benefits of DT technology for the TWM issue, particularly in the micro-milling domain.…”