Tool Wear Condition Monitoring by Combining Variational Mode Decomposition and Ensemble Learning

Most online tool condition monitoring (TCM) methods easily cause machining interference. To solve this problem, we propose a method based on the analysis of the spindle motor current signal of a machine tool. Firstly, cutting experiments under multi-conditions were carried out at a Fanuc vertical machining center, using the Fanuc Servo Guide software to obtain the spindle motor current data of the built-in current sensor of the machine tool, which can not only apply to the actual processing conditions but, also, save costs. Secondly, we propose the variational mode decomposition (VMD) algorithm for feature extraction, which can describe the tool conditions under different cutting conditions due to its excellent performance in processing the nonstationary current signal. In contrast with the popular wavelet packet decomposition (WPD) method, the VMD method was verified as a more effective signal-processing technique according to the experimental results. Thirdly, the most indicative features that relate to the tool condition were fed into the ensemble learning (EL) classifier to establish a nonlinear mapping relationship between the features and the tool wear level. Compared with existing TCM methods based on current sensor signals, the operation process and experimental results show that using the proposed method for the monitoring signal acquisition is suitable for the actual processing conditions, and the established tool wear prediction model has better performance in both accuracy and robustness due to its good generalization capability.

Investigations on force generation and joint properties of dissimilar thickness friction stir corner welded AA 5086 alloy

The force generation, joint mechanical and metallurgical properties of friction stir corner welded non-heat treatable AA 5086 aluminum alloy are investigated in this paper. The friction stir welding process is carried out with the plate thicknesses of 6 mm and 4 mm. The welding speed, tool rotational speed and tool plunge depth were considered as the process parameters to conduct the welding experiments. The machine spindle motor current consumption and tool down force generation during friction stir welding were analyzed. The microstructures of various joint regions were observed. The tensile samples revealed the tensile strength of 197 MPa with tool rotational and welding speeds of 1,000 rev/min and 150 mm/min respectively, which is 78 % of parent material tensile strength. A maximum micro hardness of 98 HV was observed at thermomechanically joint affected zone, which was welded with tool rotation of 1,000 rev/min and welding speed of 190 mm/min.

Process monitoring of friction stir welding via the frequency of the spindle motor current

Friction stir welding is a solid-state process that is gaining preference for the joining of metals with low melting points. Despite the clear advantages of friction stir welding over traditional fusion welding, voids within the weld seam arise when improper conditions are present. The work presented in this article examines the development of an automated process monitoring system for friction stir welding. The system indirectly monitors the welding torque through the supplied current to the spindle motor. To measure the current, a clamp-on current meter was used. Our results have shown that using a simple and inexpensive clamp-on current meter provides good insight into the welding torque. Examination focused on the frequency spectrum of the current. A Fourier transform decomposed the signal into various frequencies present. The results consistently showed that when no void was present, there was a component of the current’s frequency at 14 Hz. However, when the tool encountered a void, the frequency spectrum changed. The component at 14 Hz went away while content in the range of 1–4 Hz increased.