Abstract
In this study, the vibration transmitted solely from a spindle to the worktable is proposed to be a crucial feature of wear prediction models for machine tools. To validate the effectiveness of the proposed feature, a feature ranking and screening methodology was also used for developing a tool wear prediction model. First, the features extracted from vibration signals were ranked according to their contributions to tool wear prediction. The features were then filtered through a screening process based on singular value decomposition to eliminate redundant features, which exhibited collinearity with features of higher rankings. The aim of the aforementioned steps was to use a relatively small number of highly appropriate features to create an accurate real-time tool wear prediction model. The results indicated that the accuracy of the tool wear prediction model based on the proposed feature ranking and screening methodology is higher than that of models without feature ranking or screening. Moreover, the proposed feature was proven to be more important and effective than other features.
Similar content being viewed by others
References
Beganovic N, Söffker D (2017) Remaining lifetime modeling using state-of-health estimation. Mech Syst Signal Process 92:107–123. https://doi.org/10.1016/j.ymssp.2017.01.031
Zhang C, Yao X, Zhang J, Jin H (2016) Tool condition monitoring and remaining useful life prognostic based on a wireless sensor in dry milling operations. Sensors 16(6):795. https://doi.org/10.3390/s16060795
Xie Z, Li J, Lu Y (2018) An integrated wireless vibration sensing tool holder for milling tool condition monitoring. Int J Adv Manuf Technol 95:2885–2896. https://doi.org/10.1007/s00170-017-1391-x
Vetrichelvan G, Sundaram S, Kumaran Sand Velmurugan P (2014) An investigation of tool wear using acoustic emission and genetic algorithm. J Vibration Control 21:1–6. https://doi.org/10.1177/1077546314520835
Kong D, Chen Y, Li N (2017) Force-based tool wear estimation for milling process using Gaussian mixture hidden Markov models. Int J Adv Manuf Technol 92:2853–2865. https://doi.org/10.1007/s00170-017-0367-1
Zhou Y, Xue W (2018) Review of tool condition monitoring methods in milling processes. Int J Adv Manuf Technol 96:2509–2523. https://doi.org/10.1007/s00170-018-1768-5
Gao H, Xu M, Su Y, Fu P, Liu Q (2008) Experimental study of tool wear monitoring based on neural networks. In 2008 7th World Congress on Intelligent Control and Automation, IEEE. https://ieeexplore.ieee.org/document/4593985
Wu D, Jennings C, Terpenny J, Kumara S (2016) Cloud-based machine learning for predictive analytics: tool wear prediction in milling. In 2016 IEEE international conference on big data (big data), IEEE. https://doi.org/10.1109/BigData.2016.7840831
Jegorowa A, Górski J, Kurek J, Kruk M (2019) Initial study on the use of support vector machine (SVM) in tool condition monitoring in chipboard drilling. Eur J Wood Wood Products 77:957–959. https://doi.org/10.1007/s00107-019-01428-5
Hesser DF, Markert B (2019) Tool wear monitoring of a retrofitted CNC milling machine using artificial neural networks. Manufacturing Letters 19:1–4. https://doi.org/10.1016/j.mfglet.2018.11.001
Li YG, Liu CQ, Hua J, Gao J, Maropoulos P (2019) A novel method for accurately monitoring and predicting tool wear under varying cutting conditions based on meta-learning. CIRP Ann 68(1):487–490. https://doi.org/10.1016/j.cirp.2019.03.010
Kothuru A, Nooka SP, Liu R (2018) Application of audible sound signals for tool wear monitoring using machine learning techniques in end milling. Int J Adv Manuf Technol 95:3797–3808. https://doi.org/10.1007/s00170-017-1460-1
Jurkovic J, Korosec M, Kopac J (2005) New approach in tool wear measuring technique using CCD vision system. Int J Machine Tools Manuf 45(9):1023–1030. https://doi.org/10.1016/j.ijmachtools.2004.11.030
Thakre AA, Lad AV, Mala K (2019) Measurements of tool wear parameters using machine vision system. Model Simul Eng 4:1–9. https://doi.org/10.1155/2019/1876489
Zhu K, Vogel-Heuser B (2014) Sparse representation and its applications in micro-milling condition monitoring: noise separation and tool condition monitoring. Int J Adv Manuf Technol 70:185–199. https://doi.org/10.1007/s00170-013-5258-5
Ghosh N, Ravi YB, Patra A, Mukhopadhyay S, Paul S, Mohanty AR, Chattopadhyay AB (2007) Estimation of tool wear during CNC milling using neural network-based sensor fusion. Mech Syst Signal Process 21(1):466–479. https://doi.org/10.1016/j.ymssp.2005.10.010
Lee BY, Tarng YS (1999) Application of the discrete wavelet transform to the monitoring of tool failure in end milling using the spindle motor current. Int J Adv Manuf Technol 15(4):238–243. https://doi.org/10.1007/s001700050062
Wang GF, Yang YW, Zhang YC, Xie QL (2014) Vibration sensor based tool condition monitoring using ν, support vector machine and locality preserving projection. Sensors Actuators A Phys 209:24–32. https://doi.org/10.1016/j.sna.2014.01.004
Zhou Y, Liu X, Li F, Sun B, Xue W (2015) An online damage identification approach for numerical control machine tools based on data fusion using vibration signals. J Vib Control 21(15):2925–2936. https://doi.org/10.1177/1077546314545097
Chen B, Chen X, Li B, He Z, Cao H, Cai G (2011) Reliability estimation for cutting tools based on logistic regression model using vibration signals. Mech Syst Signal Process 25(7):2526–2537. https://doi.org/10.1016/j.ymssp.2011.03.001
Rowland JJ (2003) Generalisation and model selection in supervised learning with evolutionary computation. In: Workshops on Applications of Evolutionary Computation. Springer. https://doi.org/10.1007/3-540-36605-9_12
Zhang B, Katinas C, Shin YC (2018) Robust tool wear monitoring using systematic feature selection in turning processes with consideration of uncertainties. ASME J Manuf Sci Eng 140(8):081010. https://doi.org/10.1115/1.4040267
Wu D, Jennings C, Terpenny J, Gao RX, Kumara S (2017) A comparative study on machine learning algorithms for smart manufacturing: tool wear prediction using random forests. ASME J Manuf Sci Eng 139(7):071018. https://doi.org/10.1115/1.4036350
Sick B (2002) On-line and indirect tool wear monitoring in turning with artificial neural networks: a review of more than a decade of research. Mech Syst Signal Process 16(4):487–546. https://doi.org/10.1006/mssp.2001.1460
Shekar AK, Bocklisch T, Sánchez PI, Straehle CN, Müller E (2017) Including multi-feature interactions and redundancy for feature ranking in mixed datasets. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer. https://doi.org/10.1007/978-3-319-71249-9_15
Kumar V, Minz S (2014) Feature selection: a literature review. Smart CR 4(3):211–229. https://doi.org/10.6029/smartcr.2014.03.007
Song WQ (2011) Tool state detection by harmonic wavelet and sample entropy. Chin J Mech Eng 24(6):1068. https://doi.org/10.3901/CJME.2011.06.1068
Verleysen M, François D (2005) The curse of dimensionality in data mining and time series prediction. In International Work-Conference on Artificial Neural Networks, IWANN 2005. LNCS 3512:758–770. https://doi.org/10.1007/11494669_93
Liao XP, Zhou G, Zhang ZK, Lu J, Ma JY (2019) Tool wear state recognition based on GWO–SVM with feature selection of genetic algorithm. Int J Adv Manuf Technol 104:1051–1063. https://doi.org/10.1007/s00170-019-03906-9
Li X, Lim BS, Zhou JH, Huang S, Phua SJ, Shaw KC, Er MJ (2009) Fuzzy neural network modelling for tool wear estimation in dry milling operation. In Annual conference of the prognostics and health management society: 1–11. http://www.phmsociety.org/sites/phmsociety.org/files/phm_submission/2009/phmc_09_68.pdf
Lin X, Yang F, Zhou L, Yin P, Kong H, Xing W, Lu X, Jia L, Wang Q, Xu G (2012) A support vector machine-recursive feature elimination feature selection method based on artificial contrast variables and mutual information. J Chromatogr B 910:149–155. https://doi.org/10.1016/j.jchromb.2012.05.020
Sanz H, Valim C, Vegas E, Oller JM, Reverter F (2018) SVM-RFE: selection and visualization of the most relevant features through non-linear kernels. BMC bioinformatics 19(1):1–18. https://doi.org/10.1186/s12859-018-2451-4
Rasmussen CE, Ghahramani Z (2001) Occam’s razor. In advances in neural information processing systems 13, MIT Press. http://papers.nips.cc/paper/1925-occams-razor.pdf
Shi D, Gindy NN (2007) Tool wear predictive model based on least squares support vector machines. Mech Syst Signal Process 21(4):1799–1814. https://doi.org/10.1016/j.ymssp.2006.07.016
Zahoor S, Mufti NA, Saleem MQ, Mughal MP, Qureshi MAM (2017) Effect of machine tool’s spindle forced vibrations on surface roughness, dimensional accuracy, and tool wear in vertical milling of AISI P20. Int J Adv Manuf Technol 89(9–12):3671–3679. https://doi.org/10.1007/s00170-016-9346-1
Kiew CL, Brahmananda A, Islam KHT, Lee HN, Venier SA, Saraar A, Namazi H (2020) Complexity-based analysis of the relation between tool wear and machine vibration in turning operation. Fract 28(1):2050018–2052545. https://doi.org/10.1142/S0218348X20500188
Orhan S, Er AO, Camuşcu N, Aslan E (2007) Tool wear evaluation by vibration analysis during end milling of AISI D3 cold work tool steel with 35 HRC hardness. NDT & E Int 40(2):121–126. https://doi.org/10.1016/j.ndteint.2006.09.006
Huang Z, Zhu J, Lei J, Li X, Tian F (2019) Tool wear predicting based on multi-domain feature fusion by deep convolutional neural network in milling operations. J Intell Manuf 31:953–966. https://doi.org/10.1007/s10845-019-01488-7
Vaseghi SV (2006) Advanced digital signal processing and noise cancellation, 3rd edn. John Wiley & Sons, Ltd, West Sussex England
Genuer R, Poggi JM, Tuleau-Malot C (2010) Variable selection using random forests. Pattern Recogn Lett 31(14):2225–2236. https://doi.org/10.1016/j.patrec.2010.03.014
Tsai PC, Cheng CC, Chen WJ, Su SJ (2020) Sensor placement methodology for spindle thermal compensation of machine tools. Int J Adv Manuf Technol 106:5429–5440. https://doi.org/10.1007/s00170-020-04932-8
Funding
This study was supported by the Ministry of Science and Technology, Taiwan, ROC (under Contract No. MOST 107-2634-F-194-001)
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
1.1 Formulations of PCA and PCR
The original feature data set X is expressed in matrix form as follows:
where Xn is the nth feature with M samples and N is the total number of features. Each feature must be normalized by its z-score to obtain a new matrix Xnor because each feature has various scale ranges. Subsequently, the eigenvalue λj and eigenvector pj of the covariance matrix of Xnor are calculated, and the following formula is obtained:
where \( {\mathbf{S}}_{\mathrm{xx}}={\mathbf{X}}_{\mathrm{nor}}^T{\mathbf{X}}_{\mathrm{nor}} \) is the covariance matrix of Xnor, λj is the eigenvalue, and pj is the corresponding eigenvector or principal component (PC) loading vector. The degree of importance or weight of the PC loading vector can be determined by calculating the contribution rate fj of each eigenvalue as follows:
The dimensions of the original feature set can be reduced because of the partial mutual linear dependence among features when eigenvalues with small contributions are discarded and an r number of eigenvalues with large contributions (fj) are retained.
Next, Xnor is projected onto each eigenvector (pj) to obtain the corresponding weight tj, which is known as the PC score vector. This vector represents the weights of Xnor on the PC loading vectors.
or
where T = {t1, t2, …, tr} is an m × r matrix representing the projection of Xnor on the eigenspace and P = [p1 p2 … pr] is the eigenmatrix formed by the PC loading vector pj. If r < n, then the feature set Xnor is reduced to \( {\hat{\mathbf{X}}}_{\mathrm{nor}}={\mathbf{TP}}^{\mathrm{T}}={\mathbf{X}}_{\mathrm{nor}}{\mathbf{PP}}^{\mathrm{T}} \) with low dimensionality. In this study, a cumulative contribution of at least 90% was selected as the threshold to determine the r value. Moreover, the summation of f1–fr was greater than 90% of the summation of f1–fn. The contribution of each feature in the original data set cannot be determined through PCA because P is a linear combination of the original features. Consequently, regression must be performed to determine the contribution of each feature according to the PCs. This process is known as PCR, which facilitates subsequent feature ranking, as described in the following text.
The relationship between the feature set and the corresponding true tool wear measured using the CCD camera can be expressed as a regression equation as follows:
where Y is the true tool wear, β is the n × 1 weight vector expressed as β = [β1 β2 … βn]T, and ε is the error vector of the regression equation. The features are not linearly independent; therefore, they must be transformed using PCA in an eigenspace in which the PC loading vectors are orthogonal to each other. Because PPT = I, Eq. (13) can be rewritten as follows:
where \( \mathbf{F}={\hat{\mathbf{X}}}_{\mathrm{nor}}\mathbf{P} \) is the orthogonal transformation and \( {\mathrm{T}}_{\mathrm{m}\times \mathrm{r}}={\mathbf{X}}_{{\mathrm{n}\mathrm{or}}_{\mathrm{m}\times \mathrm{n}}}{\mathbf{P}}_{\mathrm{n}\times \mathrm{r}} \)θ = PTβ represents the regression coefficients in the eigenspace. The optimal regression coefficient \( \hat{\boldsymbol{\uptheta}} \) can be obtained directly by using the least squares method as follows:
After the optimal regression coefficient \( \hat{\boldsymbol{\uptheta}} \) in the eigenspace is obtained, the contribution of each feature to tool wear, which is represented by the regression coefficient β, is determined by transforming \( \hat{\boldsymbol{\uptheta}} \) back into the original feature space. Consequently, the following equation is obtained: β = P\( \hat{\boldsymbol{\uptheta}} \). Moreover, the approximate tool wear \( \hat{\mathbf{Y}} \) can be obtained as a linear combination of the feature set Xnor as follows:
where the contribution of each feature to tool wear is ranked by \( \mathbf{P}\hat{\boldsymbol{\uptheta}} \) in descending order.
Rights and permissions
About this article
Cite this article
Cheng, WN., Cheng, CC., Lei, YH. et al. Feature selection for predicting tool wear of machine tools. Int J Adv Manuf Technol 111, 1483–1501 (2020). https://doi.org/10.1007/s00170-020-06129-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-020-06129-5