| Abstrakt: |
In this study, the authors utilize the wavelet transform technique within the intelligent turning process. This technique is applied to the machining of hardened steel SKD 61. The main focus is on monitoring the condition of the cutting tool, and this is done during the machining process, regardless of the conditions related to chip formation. Wavelet transforms serve the purpose of distinguishing indications of tool wear from received signals. These signals emerge from the analysis of components such as cutting force and acoustic emission (AE) signals. The authors investigate this analysis alongside the relationships between various cutting parameters, including depth of cut, feed rate, and cutting speed. The fifth-order wavelet transform is used to determine the ratio between the primary cutting force and the components obtained from the AE signal decomposition. This ratio is evaluated using mean–variance calculations. The intention is to mitigate the influence of different factors that relate to cutting conditions. Building upon the factors associated with cutting parameters (feed rate, depth of cut, and cutting speed), a model for predicting tool wear is established. This model takes into account the decomposition analysis ratio of the main cutting force and the AE signal component. This ratio is developed based on exponential analysis. The reliability of the proposed model for monitoring cutting tool wear is validated through a series of experiments. The results of these experiments indicate that changes in cutting parameters significantly impact the amount of tool wear. Specifically, increasing the depth of cut, feed rate, and cutting speed leads to higher cutting forces and subsequently increased tool wear. The experimental analysis for turning hardened steel SKD 61 reveals that the tool wear monitoring system introduced through wavelet analysis demonstrates impressive predictive capabilities. This system not only accurately predicts tool wear but also effectively separates noise signals from chip formation signals, even when faced with varying cutting conditions. [ABSTRACT FROM AUTHOR] |
Full text from SpringerLink