Intrinsic feature extraction using discriminant diffusion mapping analysis for automated tool wear evaluation

  • Yi-xiang HuangEmail author
  • Xiao Liu
  • Cheng-liang Liu
  • Yan-ming Li


We present a method of discriminant diffusion maps analysis (DDMA) for evaluating tool wear during milling processes. As a dimensionality reduction technique, the DDMA method is used to fuse and reduce the original features extracted from both the time and frequency domains, by preserving the diffusion distances within the intrinsic feature space and coupling the features to a discriminant kernel to refine the information from the high-dimensional feature space. The proposed DDMA method consists of three main steps: (1) signal processing and feature extraction; (2) intrinsic dimensionality estimation; (3) feature fusion implementation through feature space mapping with diffusion distance preservation. DDMA has been applied to current signals measured from the spindle in a machine center during a milling experiment to evaluate the tool wear status. Compared with the popular principle component analysis method, DDMA can better preserve the useful intrinsic information related to tool wear status. Thus, two important aspects are highlighted in this study: the benefits of the significantly lower dimension of the intrinsic features that are sensitive to tool wear, and the convenient availability of current signals in most industrial machine centers.

Key words

Tool condition monitoring Manifold learning Dimensionality reduction Diffusion mapping analysis Intrinsic feature extraction 

CLC number



Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Abu-Mahfouz I, 2003. Drilling wear detection and classification using vibration signals and artificial neural network. Int J Mach Tools Manuf, 43(7):707–720. CrossRefGoogle Scholar
  2. Bingham E, Hyvärinen A, 2000. A fast fixed-point algorithm for independent component analysis of complex valued signals. Int J Neur Syst, 10(1):1–8. CrossRefGoogle Scholar
  3. Borovkova S, Burton R, Dehling H, 1999. Consistency of the Takens estimator for the correlation dimension. Ann Appl Prob, 9(2):376–390. MathSciNetCrossRefzbMATHGoogle Scholar
  4. Camastra F, 2003. Data dimensionality estimation methods: a survey. Patt Recogn, 36(12):2945–2954. CrossRefzbMATHGoogle Scholar
  5. Camastra F, Vinciarelli A, 2002. Estimating the intrinsic dimension of data with a fractal-based method. IEEE Trans Patt Anal Mach Intell, 24(10):1404–1407. CrossRefGoogle Scholar
  6. Coifman RR, Lafon S, 2006. Diffusion maps. Appl Comput Harmon Anal, 21(1):5–30. MathSciNetCrossRefzbMATHGoogle Scholar
  7. D’Addona DM, Teti R, 2013. Image data processing via neural networks for tool wear prediction. Proc CIRP, 12:252–257. CrossRefGoogle Scholar
  8. D’Addona DM, Matarazzo D, Ullah AMMS, et al., 2015. Tool wear control through cognitive paradigms. Proc CIRP, 33: 221–226. CrossRefGoogle Scholar
  9. D’Addona DM, Ullah AMMS, Matarazzo D, 2017. Tool-wear prediction and pattern-recognition using artificial neural network and DNA-based computing. J Intell Manuf, 28(6):1285–1301. CrossRefGoogle Scholar
  10. Dimla EDS, 2000. Sensor signals for tool-wear monitoring in metal cutting operations—a review of methods. Int J Mach Tools Manuf, 40(8):1073–1098. CrossRefGoogle Scholar
  11. Franco-Gasca LA, Herrera-Ruiz G, Peniche-Vera R, et al., 2006. Sensorless tool failure monitoring system for drilling machines. Int J Mach Tools Manuf, 46(3-4):381–386. CrossRefGoogle Scholar
  12. Goebel K, Yan W, 2000. Feature selection for tool wear diagnosis using soft computing techniques. ASME Int Mechanical Engineering Congress and Exposition, p.157–163.Google Scholar
  13. Harmouche J, Delpha C, Diallo D, 2014. Linear discriminant analysis for the discrimination of faults in bearing balls by using spectral features. Int Conf on Green Energy, p.182–187. Google Scholar
  14. Hein M, Audibert JY, 2005. Intrinsic dimensionality estimation of submanifolds in Rd. Int Conf on Machine Learning, p.289–296. Google Scholar
  15. Huang SN, Tan KK, Wong YS, et al., 2007. Tool wear detection and fault diagnosis based on cutting force monitoring. Int J Mach Tools Manuf, 47(3-4):444–451. CrossRefGoogle Scholar
  16. Huang YX, Zha XF, Lee J, et al., 2013. Discriminant diffusion maps analysis: a robust manifold learner for dimensionality reduction and its applications in machine condition monitoring and fault diagnosis. Mech Syst Signal Process, 34(1-2):277–297. CrossRefGoogle Scholar
  17. ISO, 1989. Tool life testing in milling—part 1: face milling, ISO 8688-1:1989. International Organization for Standardization, Geneva.Google Scholar
  18. Jiang QS, Jia MP, Hu JZ, et al., 2009. Machinery fault diagnosis using supervised manifold learning. Mech Syst Signal Process, 23(7):2301–2311. CrossRefGoogle Scholar
  19. Karam S, Centobelli P, D’Addona DM, et al., 2016. Online prediction of cutting tool life in turning via cognitive decision making. Proc CIRP, 41:927–932. CrossRefGoogle Scholar
  20. Korn F, Pagel BU, Faloutsos C, 2001. On the “dimensionality curse” and the “self-similarity blessing”. IEEE Trans Knowl Data Eng, 13(1):96–111. CrossRefGoogle Scholar
  21. Kunze H, Torre DL, Mendivil F, et al., 2012. Fractal-Based Methods in Analysis. Springer, New York, USA, p.1–16. CrossRefzbMATHGoogle Scholar
  22. Lee DE, Hwang I, Valente CMO, et al., 2006. Precision manufacturing process monitoring with acoustic emission. Int J Mach Tools Manuf, 46(2):176–188. CrossRefGoogle Scholar
  23. Li XL, Tso SK, 1999. Drill wear monitoring based on current signals. Wear, 231(2):172–178. CrossRefGoogle Scholar
  24. Nadler B, Lafon S, Coifman RR, et al., 2006. Diffusion maps, spectral clustering and reaction coordinates of dynamical systems. Appl Comput Harmon Anal, 21(1):113–127. MathSciNetCrossRefzbMATHGoogle Scholar
  25. Oh YT, Kwon WT, Chu CN, 2004. Drilling torque control using spindle motor current and its effect on tool wear. Int J Adv Manuf Technol, 24(5-6):327–334. CrossRefGoogle Scholar
  26. Scheffer C, Heyns PS, 2001. Wear monitoring in turning operations using vibration and strain measurements. Mech Syst Signal Process, 15(6):1185–1202. CrossRefGoogle Scholar
  27. Sipola T, Ristaniemi T, Averbuch A, 2014. Gear classification and fault detection using a diffusion map framework. Patt Recogn Lett, 53:53–61. CrossRefGoogle Scholar
  28. Sortino M, 2003. Application of statistical filtering for optical detection of tool wear. Int J Mach Tools Manuf, 43(5): 493–497. CrossRefGoogle Scholar
  29. Su JC, Huang CK, Tarng YS, 2006. An automated flank wear measurement of microdrills using machine vision. J Mater Process Technol, 180(1-3):328–335. CrossRefGoogle Scholar
  30. Sweldens W, 1998. The lifting scheme: a construction of second generation wavelets. SIAM J Math Anal, 29(2): 511–546. MathSciNetCrossRefzbMATHGoogle Scholar
  31. Yao CW, Chien YX, 2014. A diagnosis method of wear and tool life for an endmill by ultrasonic detection. J Manuf Syst, 33(1):129–138. CrossRefGoogle Scholar
  32. Young HT, 1996. Cutting temperature responses to flank wear. Wear, 201(1-2):117–120. CrossRefGoogle Scholar
  33. Zhou JH, Pang CK, Lewis FL, et al., 2009. Intelligent diagnosis and prognosis of tool wear using dominant feature identification. IEEE Trans Ind Inform, 5(4):454–464. CrossRefGoogle Scholar

Copyright information

© Editorial Office of Journal of Zhejiang University Science and Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.State Key Laboratory of Mechanical System and VibrationShanghai Jiao Tong UniversityShanghaiChina
  2. 2.Shanghai Aerospace Equipment ManufacturerShanghaiChina

Personalised recommendations