Abstract
The fundamental purpose of milling process detection is to precisely predict chatter, which is the principal factor affecting the cutting process stability. This study proposes a cutting process detection approach for curved parts based on cutting force signals, splitting the cutting process into four states: no cutting, stable cutting, transition cutting, and chatter cutting. First, multichannel cutting force signals were employed to compensate for the fact that unidirectional cutting force signals cannot accurately describe the cutting condition of curved components. Then, cutting force components (intrinsic mode functions) were obtained through the simultaneous decomposition of multi-channel cutting force signals using multivariate variational mode decomposition (MVMD), and the time-domain characteristics of cutting force components were calculated using the improved waveform factor and margin factor calculation methods. The long short-term memory (LSTM) neural network was trained to create a milling process detection model based on labeled features identified by FFT and cutting surface. Comparing the obtained detection results with the training results of the original signal features without MVMD decomposition and the training results of the single-channel signal features with MVMD reveals that the method can accurately recognize the cutting process of curved parts with a superior recognition effect.
Similar content being viewed by others
Availability of data and material
All data generated or analyzed during this study are included in this article.
References
Quintana G, Ciurana J (2011) Chatter in machining processes: a review. Int J Mach Tool Manuf 51(5):363–376
Wiercigroch M, Budak E (2001) Sources of nonlinearities, chatter generation and suppression in metal cutting. Philos Trans Royal Soc London Ser A Math Phys Eng Sci 359(1781):663–693
Altintaş Y, Budak E (1995) Analytical prediction of stability lobes in milling. CIRP Ann 44(1):357–362
Insperger T, Stepan G (2002) Semi-discretization method for delayed systems. Int J Numer Meth Eng 55(5):503–518
Li M, Zhang G, Huang Y (2013) Complete discretization scheme for milling stability prediction. Nonlinear Dyn 71(1):187–199
Zhang Z, Li H, Meng G, Liu C (2015) A novel approach for the prediction of the milling stability based on the Simpson method. Int J Mach Tool Manuf 99:43–47
Pérez-Canales D, Álvarez-Ramírez J, Jáuregui-Correa JC, Vela-Martínez L, Herrera-Ruiz G (2011) Identification of dynamic instabilities in machining process using the approximate entropy method. Int J Mach Tool Manuf 51(6):556–564
Toh C (2004) Vibration analysis in high speed rough and finish milling hardened steel. J Sound Vib 278(1–2):101–115
Cao H, Lei Y, He Z (2013) Chatter identification in end milling process using wavelet packets and Hilbert-Huang transform. Int J Mach Tool Manuf 69:11–19
Liu C, Zhu L, Ni C (2017) The chatter identification in end milling based on combining EMD and WPD. Int J Adv Manuf Technol 91(9):3339–3348
Shrivastava Y, Singh B (2019) A comparative study of EMD and EEMD approaches for identifying chatter frequency in CNC turning. Eur J Mech A Solids 73:381–393
Zhang Q, Tu X, Li F, Hu Y (2019) An effective chatter detection method in milling process using morphological empirical wavelet transform. IEEE Trans Instrum Meas 69(8):5546–5555
Cao H, Zhou K, Chen X (2015) Chatter identification in end milling process based on EEMD and nonlinear dimensionless indicators. Int J Mach Tool Manuf 92:52–59
Zhang Z, Li H, Meng G, Tu X, Cheng C (2016) Chatter detection in milling process based on the energy entropy of VMD and WPD. Int J Mach Tool Manuf 108:106–112
Liu C, Zhu L, Ni C (2018) Chatter detection in milling process based on VMD and energy entropy. Mech Syst Signal Process 105:169–182
Shrivastava Y, Singh B (2018) Possible way to diminish the effect of chatter in CNC turning based on EMD and ANN approaches. Arab J Sci Eng 43(9):4571–4591
Sener B, Serin G, Gudelek MU, Ozbayoglu AM, Unver HO (2020) Intelligent chatter detection in milling using vibration data features and deep multi-layer perceptron. In: 2020 IEEE International Conference on Big Data (Big Data), IEEE, pp 4759–4768
Zhu W, Zhuang J, Guo B, Teng W, Wu F (2020) An optimized convolutional neural network for chatter detection in the milling of thin-walled parts. Int J Adv Manuf Technol 106(9):3881–3895
Dun Y, Zhus L, Yan B, Wang S (2021) A chatter detection method in milling of thin-walled TC4 alloy workpiece based on auto-encoding and hybrid clustering. Mech Syst Signal Process 158
Unver HO, Sener B (2021) A novel transfer learning framework for chatter detection using convolutional neural networks. J Intell Manuf 1–20
Wan S, Li X, Yin Y, Hong J (2021) Milling chatter detection by multi-feature fusion and Adaboost-SVM. Mech Syst Signal Process 156
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Vashisht RK, Peng Q (2021) Online chatter detection for milling operations using LSTM neural networks assisted by motor current signals of ball screw drives. J Manuf Sci Eng 143(1)
Vaishnav S, Desai K (2022) Long short-term memory-based cutting depth monitoring system for end milling operation. J Comput Inf Sci Eng 22(5)
Chiu MC, Tsai CD, Li TL (2020) An integrative machine learning method to improve fault detection and productivity performance in a cyber-physical system. J Comput Inf Sci Eng 20(2)
Maturana D, Scherer S (2015) VoxNet: a 3D convolutional neural network for real-time object recognition. In: 2015 IEEE/RSJ international conference on intelligent robots and systems (IROS), IEEE, pp 922–928
Ur Rehman N, Aftab H (2019) Multivariate variational mode decomposition. IEEE Trans Signal Process 67(23):6039–6052
Funding
This study is supported by the National Natural Science Foundation of China (51805116).
Author information
Authors and Affiliations
Contributions
Hongyu Jin and Zhenyu Han conceived and designed the study. Haiyong Sun, Hongya Fu, and Hongyu Jin performed the experiments. Hongyu Jin and Hongya Fu analyzed the data. All authors read and approved the manuscript.
Corresponding author
Ethics declarations
Ethics approval
Not applicable.
Consent to participate
Not applicable.
Consent for publication
Not applicable.
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Jin, H., Sun, H., Fu, H. et al. Milling process stability detection for curved workpiece based on MVMD and LSTM. Int J Adv Manuf Technol 123, 1025–1036 (2022). https://doi.org/10.1007/s00170-022-10030-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-022-10030-8