Abstract
Machining processes are most accurately described using complex dynamical systems that include nonlinearities, time delays and stochastic effects. Due to the nature of these models as well as the practical challenges which include time-varying parameters, the transition from numerical/analytical modeling of machining to the analysis of real cutting signals remains challenging. Some studies have focused on studying the signals of cutting processes using machine learning algorithms with the goal of identifying and predicting undesirable vibrations during machining referred to as chatter. These tools typically decompose the signal using Wavelet Packet Transforms (WPT) or Ensemble Empirical Mode Decomposition (EEMD). However, these methods require a significant overhead in identifying the feature vectors before a classifier can be trained. In this study, we present an alternative approach based on featurizing the time series of the cutting process using its topological features. We first embed the time series as a point cloud using Takens embedding. We then utilize Support Vector Machine, Logistic Regression, Random Forest and Gradient Boosting classifier combined with feature vectors derived from persistence diagrams, a tool from persistent homology, to encode chatter’s distinguishing characteristics. We present the results for several choices of the topological feature vectors, and we compare our results to the WPT and EEMD methods using experimental turning data. Our results show that in two out of four cutting configurations the Topological Data Analysis (TDA)-based features yield accuracies as high as 97%. We also show that combining Bézier curve approximation method and parallel computing can reduce runtime for persistence diagram computation of a single time series to less than a second thus making our approach suitable for online chatter detection.
Similar content being viewed by others
Availability of data and material
Experimental data set is available in a Mendeley repository [51].
Code availability
Source codes for TDA-based approach is available in machine learning module of a Python package called teaspoon.
References
Thaler T, Potočnik P, Bric I, Govekar E (2014) Chatter detection in band sawing based on discriminant analysis of sound features. Appl Acoust 77:114–121
Yesilli MC, Khasawneh F (2020) On transfer learning of traditional frequency and time domain features in turning, arXiv:preprint:2008.12691, cs.LG, pp 1–12
Chen GS, Zheng QZ (2017) Online chatter detection of the end milling based on wavelet packet transform and support vector machine recursive feature elimination. Int J Adv Manuf Technol 95(1-4):775–784
Ji Y, Wang X, Liu Z, Wang H, Jiao L, Wang D, Leng S (2018) Early milling chatter identification by improved empirical mode decomposition and multi-indicator synthetic evaluation. J Sound Vib 433:138–159
Li X, Ouyang G, Liang Z (2080) Complexity measure of motor current signals for tool flute breakage detection in end milling. Int J Mach Tools Manuf 48(3-4):371–379
Liu H, Chen Q, Li B, Mao X, Mao K, Peng F (2011) On-line chatter detection using servo motor current signal in turning. Sci China Technol Sci 54(12):3119–3129
Ding L, Sun Y, Xiong Z (2017) Early chatter detection based on logistic regression with time and frequency domain features. In: 2017 IEEE International conference on advanced intelligent mechatronics (AIM). IEEE
Fu Y, Zhang Y, Qiao H, Li D, Zhou H, Leopold J (2015) Analysis of feature extracting ability for cutting state monitoring using deep belief networks. Procedia CIRP 31:29–34
Lamraoui M, Barakat M, Thomas M, Badaoui ME (2013) Chatter detection in milling machines by neural network classification and feature selection. J Vib Control 21(7):1251–1266
Cheng C, Li J, Liu Y, Nie M, Wang W (2019) Deep convolutional neural network-based in-process tool condition monitoring in abrasive belt grinding. Comput Ind 106:1–13
Han Z, Jin H, Han D, Fu H (2016) ESPRIT- And HMM-based real-time monitoring and suppression of machining chatter in smart CNC milling system. Int J Adv Manuf Technol 89(9-12):2731–2746
Xie F-Y, Hu Y-M, Wu B, Wang Y (2016) A generalized hidden markov model and its applications in recognition of cutting states. Int J Precis Eng Manuf 17(11):1471–1482
Zuo L, Zhang L, Zhang Z. -H., Luo X. -L., Liu Y (2020) A spiking neural network-based approach to bearing fault diagnosis. Journal of Manufacturing Systems
Yesilli MC, Khasawneh F, Otto A (2020) On transfer learning for chatter detection in turning using wavelet packet transform and ensemble empirical mode decomposition. CIRP J Manuf Sci Technol 28:118–135
Ghrist R (2008) Barcodes: The persistent topology of data. Builletin Amer Math Soc 45:61–75 survey
Carlsson G (2009) Topology and data. Bullet Amer Math Soc 46(2):255–308, survey. [Online]. Available: http://www.ams.org/journal-getitem?pii=S0273-0979-09-01249-X
Edelsbrunner H, Harer J (2009) Computational topology: an introduction. American Mathematical Society
Oudot S (2015) Persistence theory: from quiver representations to data analysis. ser. AMS Mathematical Surveys and Monographs, American Mathematical Society, pp 209
Robinson M (2014) Topological Signal Processing, 1st ed. Springer, Berlin
Khasawneh F, Munch E (2014) Stability of a stochastic turning model using persistent homology. in submission
Khasawneh F (2016) Chatter detection in turning using persistent homology. Mech Syst Signal Process 70-71:527–541. [Online] Available: http://www.sciencedirect.com/science/article/pii/S0888327015004598
Khasawneh F, Munch E, Perea JA (2018) Chatter classification in turning using machine learning and topological data analysis. IFAC-PapersOnLine 51(14):195–200
Khasawneh F, Munch E (2014) Stability determination in turning using persistent homology and time series analysis. In: Proceedings of the ASME 2014 International Mechanical Engineering Congress & Exposition, Montreal, paper no. IMECE2014-40221
Adcock A, Carlsson E, Carlsson G (2016) The ring of algebraic functions on persistence bar codes. Homol Homotopy Appl 18(1):381–402
Perea JA, Munch E, Khasawneh F (2019) Approximating continuous functions on persistence diagrams using template functions, arXiv:1902.07190v1, cs.CG, pp 1–51
Yesilli MC, Tymochko S, Khasawneh F, Munch E (2019) Chatter diagnosis in milling using supervised learning and topological features vector. In: 2019 18Th IEEE international conference on machine learning and applications (ICMLA). IEEE
Bubenik P Statistical topological data analysis using persistence landscapes. J Mach Learn Res 16:77–102 (2015). [Online]. Available: http://jmlr.org/papers/v16/bubenik15a.html
Adams H, Emerson T, Kirby M, Neville R, Peterson C, Shipman P, Chepushtanova S, Hanson E, Motta F, Ziegelmeier L (2017) Persistence images: A stable vector representation of persistent homology. J Mach Learn Res 18(1):218–252. [Online]. Available: http://dl.acm.org/citation.cfm?id=3122009.3122017
Reininghaus J, Huber S, Bauer U, Kwitt R (2015) A stable multi-scale kernel for topological machine learning. In: The IEEE conference on computer vision and pattern recognition (CVPR)
Chevyrev I, Nanda V, Oberhauser H (2018) Persistence paths and signature features in topological data analysis. IEEE Trans Pattern Anal Mach Intell 42:1–1
Tsuji S, Aihara K (2019) A fast method of computing persistent homology of time series data. In: ICASSP 2019 - 2019 IEEE International conference on acoustics, speech and signal processing (ICASSP). IEEE
Cavanna NJ, Jahanseir M, Sheehy DR (2015) A geometric perspective on sparse filtrations, arXiv:1506.03797v1, cs.CG, pp 1–18
Li C, Ovsjanikov M, Chazal F (2014) Persistence-based structural recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1995–2002
Mileyko Y, Mukherjee S, Harer J (2011) Probability measures on the space of persistence diagrams. Inverse Probl 27(12):124007. [Online]. Available: http://stacks.iop.org/0266-5611/27/i=12/a=124007
Turner K, Mileyko Y, Mukherjee S, Harer J (2014) Fréchet means for distributions of persistence diagrams. Discret Comput Geom 52(1):44–70. [Online]. Available: https://doi.org/10.1007/s00454-014-9604-7https://doi.org/10.1007/s00454-014-9604-7
Munch E, Turner K, Bendich P, Mukherjee S, Mattingly J, Harer J (2015) Probabilistic fréchet means for time varying persistence diagrams. Electron J Statist 9:1173–1204. [Online]. Available: https://doi.org/10.1214/15-EJS1030
Berry E, Chen Y-C, Cisewski-Kehe J, Fasy BT (2018) Functional summaries of persistence diagrams. J Appl Comput Topol 4:211–262
Chazal F, Fasy BT, Lecci F, Rinaldo A, Wasserman L (2014) Stochastic convergence of persistence landscapes and silhouettes. In: Proceedings of the Thirtieth Annual Symposium on Computational Geometry, ser. SOCG’14. ACM, New York, pp 474:474–474:483. [Online]. Available: https://doi.org/10.1145/2582112.2582128https://doi.org/10.1145/2582112.2582128
Chepushtanova S, Emerson T, Hanson E, Kirby M, Motta F, Neville R, Peterson C, Shipman P, Ziegelmeier L (2015) Persistence images: An alternative persistent homology representation, arXiv:1507.06217, cs.CG, pp 1–10
Chen Y-C, Wang D, Rinaldo A, Wasserman L (2015) Statistical analysis of persistence intensity functions, arXiv:1510.02502, stat.ME, pp 1–10
Donatini P, Frosini P, Lovato A (1998) Size functions for signature recognition. In: Vision geometry VII. In: Melter RA, Wu AY, Latecki LG (eds) SPIE
Ferri M, Frosini P, Lovato A, Zambelli C (1998) Point selection: a new comparison scheme for size functions (with an application to monogram recognition). In: ACCV
Chevyrev I, Kormilitzin A (2016) A primer on the signature method in machine learning, arXiv:1603.03788v1, stat.ML, pp 1–45
Fox L, Parker IB (1968) CHebyshev Polynomials in Numerical Analysis. Oxford Univ Press, London
Kwitt R, Huber S, Niethammer M, Lin W, Bauer U (2015) Statistical topological data analysis - a kernel perspective. In: Advances in neural information processing systems. In: Cortes C, Lawrence N, Lee D, Sugiyama M, Garnett R, Garnett R (eds) Curran Associates, Inc., vol 28, pp 3052–3060
Zhao Q, Wang Y (2019) Learning metrics for persistence-based summaries and applications for graph classification, arXiv:1904.12189v1, cs.CG, pp 1–21
Kusano G, Hiraoka Y, Fukumizu K (2016) Persistence weighted gaussian kernel for topological data analysis. In: International conference on machine learning, pp 2004–2013
Kusano G, Fukumizu K, Hiraoka Y (2017) Kernel method for persistence diagrams via kernel embedding and weight factor. J Mach Learn Res 18(1):6947–6987
Carrière M, Cuturi M, Oudot S (2017) Sliced wasserstein kernel for persistence diagrams, arXiv:1706.03358 cs.CG
Kusano G (2018) Persistence weighted gaussian kernel for probability distributions on the space of persistence diagrams, arXiv:1803.08269v1 math.AT
Khasawneh F, Otto A, Yesilli M (2019) Turning dataset for chatter diagnosis using machine learning
Insperger T, Mann BP, Surmann T, Stėpȧn G (2008) On the chatter frequencies of milling processes with runout. Int J Mach Tools Manuf 48(10):1081–1089
Takens F (1981) Detecting strange attractors in turbulence. In: Dynamical Systems and Turbulence. In: Rand D, Young L-S (eds) Warwick 1980, ser. Lecture Notes in Mathematics. [Online]. Available: https://doi.org/10.1007/BFb0091924https://doi.org/10.1007/BFb0091924, vol 898. Springer, Berlin, pp 366–381
Munkres JR (2018) Elements of algebraic topology. CRC press
Munch E (2017) A user’s guide to topological data analysis. J Learn Anal 4(2):47–61
Theodoridis S, Koutroumbas K (2009) Feature selection. In: Pattern recognition. Elsevier, pp 261–322
Rousseeuw PJ (1984) Least median of squares regression. J Am Stat Assoc 79(388):871–880
Melosik M, Marszalek W (2016) On the 0/1 test for chaos in continuous systems. Bullet Polish Acad Sci Tech Sci 64(3):521–528
Fraser AM, Swinney HL (1986) Independent coordinates for strange attractors from mutual information. Phys Rev A 33:1134–1140. [Online]. Available: https://doi.org/10.1103/PhysRevA.33.1134https://doi.org/10.1103/PhysRevA.33.1134
Kennel MB, Brown R, Abarbanel HDI (1992) Determining embedding dimension for phase-space reconstruction using a geometrical construction. Phys Rev A 45(6)3403–3411
Abarbanel HDI, Carroll TA, Pecora LM, Sidorowich JJ, Tsimring LS (1994) Predicting physical variables in time-delay embedding. Phys Rev E 49(3)1840–1853 mar
Tharwat A, Elhoseny M, Hassanien AE, Gabel T, Kumar A (2018) Intelligent bėzier curve-based path planning model using chaotic particle swarm optimization algorithm. Cluster Comput 22(S2)4745–4766
Elhoseny M, Tharwat A, Hassanien AE (2018) Bėzier curve based path planning in a dynamic field using modified genetic algorithm. J Comput Sci 25:339–350
wung Choi J, Curry R, Elkaim G (2008) Path planning based on bėzier curve for autonomous ground vehicles. In: Advances in electrical and electronics engineering - IAENG special edition of the world congress on engineering and computer science. IEEE
Hwang J-H, Arkin R, Kwon D-S (2003) Mobile robots at your fingertip: bėzier curve on-line trajectory generation for supervisory control. In: Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453). IEEE
Endres SC, Sandrock C, Focke WW (2018) A simplicial homology algorithm for lipschitz optimisation. J Glob Optim 72(2):181–217
Kerber M, Morozov D, Nigmetov A (2016) Geometry helps to compare persistence diagrams, arXiv:1606.03357v1, cs.CG, pp 1–20
Bubenik P, Dłotko P (2017) A persistence landscapes toolbox for topological statistics. J Symb Comput 78:91–114
Zeppelzauer M, Zieliṅski B, Juda M, Seidl M (2018) A study on topological descriptors for the analysis of 3d surface texture. Comput Vis Image Underst 167:74–88
Chang C-C, Lin C-J (2011) LIBSVM: A library for support vector machines. ACM Trans Intell Syst Technol 2:27:1–27:27, software available at http://www.csie.ntu.edu.tw/cjlin/libsvm
Funding
This material is based upon work supported by the National Science Foundation under Grant Nos. CMMI-1759823 and DMS-1759824 with PI FAK.
Author information
Authors and Affiliations
Contributions
Melih C. Yesilli: methodology, software, validation, formal analysis, data curation, writing—original draft, visualization
Firas A. Khasawneh: conceptualization, methodology, investigation, resources, writing—review and editing, supervision, project administration, funding acquisition
Andreas Otto: investigation, resources, writing—review and editing, supervision
Corresponding author
Ethics declarations
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.
Appendices
Appendix A. Expressions for persistence paths’ signatures
Let the k th landscape functions be λk(x) = y where x and y represent coordinates along the birth time and the persistence axes. Since the persistence landscapes are piecewise linear functions, we can write them in closed form in terms of the nodes \(\{x_{i}, y_{i}\}_{i=1}^{n}\) that define the boundaries of each of their linear pieces according to
The corresponding path is given by
and its differential is
Using the above definitions, we can derive general expressions for the first and second level signatures, respectively, according to
The equations for the second level signatures are provided in Table 9.
Appendix B. Classification results
Rights and permissions
About this article
Cite this article
Yesilli, M.C., Khasawneh, F.A. & Otto, A. Topological feature vectors for chatter detection in turning processes. Int J Adv Manuf Technol 119, 5687–5713 (2022). https://doi.org/10.1007/s00170-021-08242-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-021-08242-5