A Novel Unsupervised Machine Learning-Based Method for Chatter Detection in the Milling of Thin-Walled Parts

Data-driven chatter detection techniques avoid complex physical modeling and provide the basis for industrial applications of cutting process monitoring. Among them, feature extraction is the key step of chatter detection, which can compensate for the accuracy disadvantage of machine learning algorithms to some extent if the extracted features are highly correlated with the milling condition. However, the classification accuracy of the current feature extraction methods is not satisfactory, and a combination of multiple features is required to identify the chatter. This limits the development of unsupervised machine learning algorithms for chattering detection, which further affects the application in practical processing. In this paper, the fractal feature of the signal is extracted by structure function method (SFM) for the first time, which solves the problem that the features are easily affected by process parameters. Milling chatter is identified based on k-means algorithm, which avoids the complex process of training model, and the judgment method of milling chatter is also discussed. The proposed method can achieve 94.4% identification accuracy by using only one single signal feature, which is better than other feature extraction methods, and even better than some supervised machine learning algorithms. Moreover, experiments show that chatter will affect the distribution of cutting bending moment, and it is not reliable to monitor tool wear through the polar plot of the bending moment. This provides a theoretical basis for the application of unsupervised machine learning algorithms in chatter detection.

Cutting Force and Nonlinear Chatter Stability of Ball-end Milling Cutter

Ball-end milling cutters are one of the most widely used cutters in the automotive, aerospace, die and machine parts industries. In addition, milling chatter will reduce the surface quality and production efficiency, resulting in noise. It is particularly important to model the cutting force and analyze the flutter stability of ball-end milling cutters. In this paper, a simplified milling force model of ball-end milling cutter with three degrees of freedom was established based on Merchant bevel cutting theory. The model simplified the milling force coefficient. The expressions of instantaneous milling area considering the vibration displacements in X, Y and Z directions were derived. The nonlinear dynamic cutting force model of ball-end milling cutter with three degrees of freedom was established. The nonlinear chatter vibration mechanical model of ball-end milling cutter with three degrees of freedom was established by introducing the time delay term, the stability analysis is carried out by time domain simulation. The proposed models were experimentally verified.

Stability Analysis of Milling Process with Variable Spindle Speed and Pitch Angle considering Helix Angle and Process Phase Difference

Suppression of milling chatter by disrupting regenerative effect is a well-known method to obtain higher cutting stability domain. In this paper, a dynamic model of the milling process with variable spindle speed and pitch angle considering helix angle and process phase difference is presented. Then, an updated semidiscretization method is applied to obtain the stability chart. After the effectiveness of the proposed method is confirmed by comparisons with the previously published works and the time-domain simulations, lots of analyses are conducted to deeply evaluate the influence of the helix angle, the process phase difference, and feed per tooth on milling stability. Results show that the change of helix angle can result in significant stability discrepancies for both high-speed and low-speed regions. Though the process phase difference has the randomness and immeasurability in the practical application, it has an important influence on the stability and will result in a periodic evolution of the stability with a period π. Also, its recommended values are given for the practical milling process.