Abstract
As a kind of self-excited vibrations, chatter vibration is extremely common in end milling, especially in high-speed cutting processes. It affects the machining accuracy of products and decreases the processing efficiency of machine tools. Thus it is very crucial to develop an effective condition monitoring system to extract the chatter feature before chatter vibration grows. In this paper, a hybrid chatter detection method (HCDM) is proposed for chatter feature extraction and classification in end milling. Firstly, wavelet packet decomposition is employed to decompose cutting vibration signals into a series of wavelet coefficients, and the signals of each frequency band are reconstructed. Secondly, fast Fourier transform and singular spectrum analysis are chosen to obtain the chatter features. Furthermore, the support vector machine model is optimized by particle swarm optimization to recognize the cutting states in end milling. At last, cutting experiments of 300 M steel under different machining conditions are conducted, and the results indicate that the proposed HCDM can distinguish the stable, transition, and chatter states accurately and rapidly in end milling.
Highlights
A hybrid chatter detection method based on wavelet packet decomposition (WPD), Singular spectrum analysis (SSA), and support vector machine (SVM)-PSO in end milling is proposed
Based on the in-depth analysis of the chatter-emerging frequency band of vibration signals, the coefficients of the energy ratio and the singular spectrum entropy are extracted as two chatter features
To improve the precision and efficiency of the proposed hybrid chatter detection method (HCDM), PSO is chosen to optimize the input parameters of SVM. e effectiveness is primarily verified by a set of cutting experiments of 300 M steel under different working conditions. e proposed approach can recognize the stable, transition, and chatter states more accurately than the other traditional approaches
Summary
Wavelet packet decomposition (WPD) and SSA are employed to acquire the dimensionless chatter features of the acceleration signals in end milling. After the chatter features are extracted, some classification methods are employed to recognize the cutting states, such as the hidden Markov model [31, 32], artificial neural network [33, 34], and support vector machine (SVM) [23, 35, 36]. A hybrid chatter detection method (HCDM) based on the WPD, SSA, and SVM-PSO model is proposed to recognize the stable, transition, and chatter states in end milling. The WPD and SSA decompose the vibration signals under different cutting conditions and overcome the calculation precision problem of STFT and the mode mixing problem of EMD. The SVM-PSO model is used for feature classification to obtain the final recognition results
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
