Structural Engineering and Mechanics

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Milling tool wear forecast based on the partial least-squares regression analysis

  • Xu, Chuangwen (School of Mechanical Engineering, Xi'an Jiaotong University, Department of Mechanical Engineering, Lanzhou Polytechnic College) ;
  • Chen, Hualing (School of Mechanical Engineering, Xi'an Jiaotong University)
  • Received : 2006.10.25
  • Accepted : 2008.12.02
  • Published : 2009.01.10
⟨ Previous Next ⟩

Abstract

Power signals resulting from spindle and feed motor, present a rich content of physical information, the appropriate analysis of which can lead to the clear identification of the nature of the tool wear. The partial least-squares regression (PLSR) method has been established as the tool wear analysis method for this purpose. Firstly, the results of the application of widely used techniques are given and their limitations of prior methods are delineated. Secondly, the application of PLSR is proposed. The singular value theory is used to noise reduction. According to grey relational degree analysis, sample variable is filtered as part sample variable and all sample variables as independent variables for modelling, and the tool wear is taken as dependent variable, thus PLSR model is built up through adapting to several experimental data of tool wear in different milling process. Finally, the prediction value of tool wear is compare with actual value, in order to test whether the model of the tool wear can adopt to new measuring data on the independent variable. In the new different cutting process, milling tool wear was predicted by the methods of PLSR and MLR (Multivariate Linear Regression) as well as BPNN (BP Neural Network) at the same time. Experimental results show that the methods can meet the needs of the engineering and PLSR is more suitable for monitoring tool wear.

Keywords

Acknowledgement

Supported by : Natural Science Foundation of Gansu Province

References

  1. Chen, J.C. (2004), 'A multiple-regression model for monitoring tool wear with a dynamometer in milling operations', Int. J. Technol. Studies, 30(4), 71-77
  2. Dimla, D.E. (2002), 'The correlation of vibration signal features to cutting tool wear in a metal turning operation', J. Mater. Process. Tech., 19(10), 705-713 https://doi.org/10.1007/s001700200080
  3. Dragos, A. (2003), 'Tool condition monitoring in broaching', Int. J. Wear, 254(3), 370-382 https://doi.org/10.1016/S0043-1648(03)00003-6
  4. Erdogmus, D. (2004), 'Minimax mutual information approach for independent component analysis', Neural Comput., 16(6), 1235-1252 https://doi.org/10.1162/089976604773717595
  5. Ertunc, M.H. and Loparo, A.K. (2001), 'Tool wear condition monitoring in drilling operations using hidden Markov models (HMPs)', Int. J. Mach. Tool Manu., 41, 1363-1384 https://doi.org/10.1016/S0890-6955(00)00112-7
  6. Kamarthi, S.V. and Kumara, S.R.T. (2000), 'Flank wear estimation in turning through wavelet representation of acoustic emission signals', J. Manuf. Sci. E. - T. ASME., 122(1), 12-19 https://doi.org/10.1115/1.538886
  7. Kopac, J. and Sali, S. (2001), 'Tool wear monitoring during the turning process', J. Mater. Process. Tech., 113(1), 312-316 https://doi.org/10.1016/S0924-0136(01)00621-5
  8. Liangyue Cao. (1997), 'Practical method for determining the minimum embedding dimension of a scalar time series', Int. J. Phys. D, 110(1), 43-50 https://doi.org/10.1016/S0167-2789(97)00118-8
  9. Mannan, M.A. and Kassim, A. (2000), 'Application of image and sound analysis techniques to monitor the condition of cutting tools', Pattern. Recogn. Lett., 21(11), 969-979 https://doi.org/10.1016/S0167-8655(00)00050-7
  10. Packard, N.H. (1980), 'Geometry from a time series', Int. J. Phys. Rev., 45, 712-716 https://doi.org/10.1103/PhysRevLett.45.712
  11. Palanisamy, P. and Rajendran, I. (2007), 'Prediction of tool wear using regression and ANN models in endmilling operation', Int. J. Adv. Manuf. Tech., 1433-3015 https://doi.org/10.1007/s00170-007-0948-5
  12. Shao, H. and Wang, H.L. (2004), “A cutting power model for tool wear monitoring in milling”, Int. J. Mach. Tool. Manu., 44(14), 1503-1509 https://doi.org/10.1016/j.ijmachtools.2004.05.003
  13. Srinivasa, P. (2002), 'Acoustic emission analysis for tool wear monitoring in face milling', Int. J. Prod. Res., 40(5), 1081-1093 https://doi.org/10.1080/00207540110107534
  14. Tang, Q.Y. (2002), 'Practical statistic analysis and DPS data processing system', Science Press, Beijing
  15. Wang, H.L. and Shao, H. (2003), 'On-line tool breakage monitoring in turning', J. Mater. Process. Tech., 139(1), 237-242 https://doi.org/10.1016/S0924-0136(03)00227-9
  16. Wang, H.W. (2005), 'The partial least-squares regression method and application', National Industry Press, Beijing
  17. Wang, S.B. and Cao, Y.D. (2005), 'Deformation measurements using mutual information : Principle and applications', Int. J. Optic. Laser. Eng., 43(7), 895-903 https://doi.org/10.1016/j.optlaseng.2004.09.007
  18. Xu, C.G. and Wang, X.Y. (2006), 'New approach on monitoring cutting tool states by motor current', J. Instrum. Technique Sensor, 32(4), 34-40
  19. Xu, C.W. (2003), 'Design and research for tool wear monitoring', Harbin Inst. Tech., 35(1), 76-80
  20. Xu, C.W. and Chen, H.L. (2007), 'A research of tool wear recognizing based on wavelet packet pretreated and neural network', The International Journal of System Design and Dynamics, JPN Soc. Mech. Eng., 1(4), 760-770 https://doi.org/10.1299/jsdd.1.760

Cited by

  1. The concept and progress of intelligent spindles: A review vol.112, 2017, https://doi.org/10.1016/j.ijmachtools.2016.10.005
  2. Milling Tool Wear Identification Using Information Fusion vol.496-500, pp.1662-7482, 2014, https://doi.org/10.4028/www.scientific.net/AMM.496-500.1681