Abstract
Machined surface quality and dimensional accuracy are significantly affected by tool wear in machining process. Tool wear state (TWS) recognition is highly desirable to realize automated machining process. In order to improve the accuracy of TWS recognition, this research develops a TWS recognition scheme using an indirect measurement method which selects signal features that are strongly correlated with tool wear to recognize TWS. Firstly, three time domain features are proposed, including dynamic time warping feature and two entropy features. The time, frequency, and time-frequency domain features of the vibration and force signals are extracted to form a feature set. Secondly, gradient boosting decision tree (GBDT) is adopted to select the optimal feature subset. Lastly, contrastive divergence (CD) and RMSspectral are used to train hybrid classification RBM (H-ClassRBM). The trained H-ClassRBM is used for TWS recognition. The PHM challenge 2010 data set is used to validate the proposed scheme. Experimental results show that the proposed features have better monotonicity and correlation than the classical features. Compared with CD and Adadelta, CD and Adagrad, and CD and stochastic gradient descent with momentum, the H-ClassRBM trained by CD and RMSspectral improves recognition accuracy by 1%, 2%, and 2%, respectively. Compared with feedforward neural network, probabilistic neural network, Gaussian kernel support vector machine, and H-ClassRBM, the proposed TWS recognition scheme improves recognition accuracy by 37%, 51%, 9%, and 8%, respectively. Therefore, the proposed TWS recognition scheme is beneficial in improving the recognition accuracy of TWS, and provides an effective guide for decision-making in the machining process.
Similar content being viewed by others
References
Zhu KP, Zhang Y (2019) A generic tool wear model and its application to force modeling and wear monitoring in high speed milling. Mech Syst Signal Process 115:147–161. https://doi.org/10.1016/j.ymssp.2018.05.045
Cao XC, Chen BQ, Yao B, Zhuang SQ (2019) An intelligent milling tool wear monitoring methodology based on convolutional neural network with derived wavelet frames coefficient. Appl Sci-Basel 9(18):26. https://doi.org/10.3390/app9183912
Chi YJ, Dai W, Lu ZY, Wang MQ, Zhao Y (2018) Real-time estimation for cutting tool wear based on modal analysis of monitored signals. Appl Sci-Basel 8(5):13. https://doi.org/10.3390/app8050708
Martinez-Arellano G, Terrazas G, Ratchev S (2019) Tool wear classification using time series imaging and deep learning. Int J Adv Manuf Technol 104(9-12):3647–3662. https://doi.org/10.1007/s00170-019-04090-6
Xie ZY, Li JG, Lu Y (2019) Feature selection and a method to improve the performance of tool condition monitoring. Int J Adv Manuf Technol 100(9-12):3197–3206. https://doi.org/10.1007/s00170-018-2926-5
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(1-4):1051–1063. https://doi.org/10.1007/s00170-019-03906-9
Wang GF, Xie QL, Zhang YC (2017) Tool condition monitoring system based on support vector machine and differential evolution optimization. Proc Inst Mech Eng B J Eng Manuf 231(5):805–813. https://doi.org/10.1177/0954405415619871
Benkedjouh T, Medjaher K, Zerhouni N, Rechak S (2015) Health assessment and life prediction of cutting tools based on support vector regression. J Intell Manuf 26(2):213–223. https://doi.org/10.1007/s10845-013-0774-6
Kong DD, Chen YJ, Li N (2018) Gaussian process regression for tool wear prediction. Mech Syst Signal Process 104:556–574. https://doi.org/10.1016/j.ymssp.2017.11.021
Hui-bin S, Wei-long N, Jun-yang W (2015) Tool wear feature extraction based on Hilbert-Huang transformation. J Vibr Shock 34(4):158–164. https://doi.org/10.13465/j.cnki.jvs.2015.04.027
Liu TI, Jolley B (2015) Tool condition monitoring (TCM) using neural networks. Int J Adv Manuf Technol 78(9-12):1999–2007. https://doi.org/10.1007/s00170-014-6738-y
Guo L, Li NP, Jia F, Lei YG, Lin J (2017) A recurrent neural network based health indicator for remaining useful life prediction of bearings. Neurocomputing 240:98–109. https://doi.org/10.1016/j.neucom.2017.02.045
Que ZJ, Xu ZG (2019) A data-driven health prognostics approach for steam turbines based on XGBoost and DTW. IEEE Access 7:93131–93138. https://doi.org/10.1109/access.2019.2927488
He ZY, Cheng WD, Wen WG (2020) A similarity comparison method of homologous fault response fragments under variable rotational speed. Shock Vib 2020:12–12. https://doi.org/10.1155/2020/8973678
Javed K, Gouriveau R, Zerhouni N, Nectoux P (2015) Enabling health monitoring approach based on vibration data for accurate prognostics. IEEE Trans Ind Electron 62(1):647–656. https://doi.org/10.1109/tie.2014.2327917
Zhang B, Zhang LJ, Xu JW (2016) Degradation feature selection for remaining useful life prediction of rolling element bearings. Qual Reliab Eng Int 32(2):547–554. https://doi.org/10.1002/qre.1771
Kong DD, Chen YJ, Li N (2017) Force-based tool wear estimation for milling process using Gaussian mixture hidden Markov models. Int J Adv Manuf Technol 92(5-8):2853–2865. https://doi.org/10.1007/s00170-017-0367-1
Rao H, Shi XZ, Rodrigue AK, Feng JJ, Xia YC, Elhoseny M, Yuan XH, Gu LC (2019) Feature selection based on artificial bee colony and gradient boosting decision tree. Appl Soft Comput 74:634–642. https://doi.org/10.1016/j.asoc.2018.10.036
Zhang Z, Li YB, Jin SS, Zhang ZY, Wang H, Qi L, Zhou RL (2018) Modulation signal recognition based on information entropy and ensemble learning. Entropy 20(3):18. https://doi.org/10.3390/e20030198
Twardowski P, Wiciak-Pikula M (2019) Prediction of tool wear using artificial neural networks during turning of hardened steel. Materials 12(19):15. https://doi.org/10.3390/ma12193091
Khajavi MN, Nasernia E, Rostaghi M (2016) Milling tool wear diagnosis by feed motor current signal using an artificial neural network. J Mech Sci Technol 30(11):4869–4875. https://doi.org/10.1007/s12206-016-1005-9
Jegorowa A, Gorski 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 Prod 77(5):957–959. https://doi.org/10.1007/s00107-019-01428-5
Ma M, Sun C, Chen XF, Zhang XW, Yan RQ (2019) A deep coupled network for health state assessment of cutting tools based on fusion of multisensory signals. IEEE Trans Ind Inform 15(12):6415–6424. https://doi.org/10.1109/tii.2019.2912428
Larochelle H, Mandel M, Pascanu R, Bengio Y (2012) Learning algorithms for the classification restricted Boltzmann machine. J Mach Learn Res 13:643–669
Luo LK, Zhang SF, Wang YD, Peng H (2018) An alternate method between generative objective and discriminative objective in training classification restricted Boltzmann machine. Knowl Based Syst 144:144–152. https://doi.org/10.1016/j.knosys.2017.12.032
Yin J, Lv JC, Sang YS, Guo JX (2018) Classification model of restricted Boltzmann machine based on reconstruction error. Neural Comput Applic 29(11):1171–1186. https://doi.org/10.1007/s00521-016-2628-6
Niu QM, Liu F, Tong QB, Cao JC, Zhang YH (2018) Health condition assessment of ball bearings using TOSELM. J Vibroeng 20(1):272–282. https://doi.org/10.21595/jve.2017.18978
Upadhya V, Sastry PS (2019) An overview of restricted Boltzmann machines. J Indian Inst Sci 99(2):225–236. https://doi.org/10.1007/s41745-019-0102-z
Chaudhuri A (2019) The minimization of empirical risk through stochastic gradient descent with momentum algorithms. In: Silhavy R (ed) Artificial intelligence methods in intelligent algorithms, Advances in Intelligent Systems and Computing, vol 985. Springer International Publishing Ag, Cham, pp 168–181. https://doi.org/10.1007/978-3-030-19810-7_17
Ruder S (2016) An overview of gradient descent optimization algorithms. arXiv
Zeiler MD (2012) ADADELTA: an adaptive learning rate method. Comput Sci
Dauphin YN, de Vries H, Bengio Y (2015) Equilibrated adaptive learning rates for non-convex optimization. In: Cortes C, Lawrence ND, Lee DD, Sugiyama M, Garnett R (eds) Advances in neural information processing systems 28, vol 28. Advances in Neural Information Processing Systems. Neural Information Processing Systems (Nips), La Jolla,
Carlson DE, Collins E, Hsieh YP, Carin L, Cevher V (2015) Preconditioned spectral descent for deep learning. In: Cortes C, Lawrence ND, Lee DD, Sugiyama M, Garnett R (eds) Advances in neural information processing systems 28, vol 28. Advances in Neural Information Processing Systems. Neural Information Processing Systems (Nips), La Jolla,
Carlson D, Hsieh YP, Collins E, Carin L, Cevher V (2016) Stochastic spectral descent for discrete graphical models. IEEE J Sel Top Signal Process 10(2):296–311. https://doi.org/10.1109/jstsp.2015.2505684
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, PHM 2009, September 27, 2009 - October 1, 2009, San Diego, CA, United States. Annual Conference of the Prognostics and Health Management Society, PHM 2009. Prognostics and Health Management Society, p et al.; General Atomics; IMPACT; Palo Alto Research Center (PARC); Ridgetop Group Inc.; Xerox
Zhu KP, Mei T, Ye DS (2015) Online condition monitoring in micromilling: a force waveform shape analysis approach. IEEE Trans Ind Electron 62(6):3806–3813. https://doi.org/10.1109/tie.2015.2392713
Lei Z, Zhou YQ, Sun BT, Sun WF (2020) An intrinsic timescale decomposition-based kernel extreme learning machine method to detect tool wear conditions in the milling process. Int J Adv Manuf Technol 106(3-4):1203–1212. https://doi.org/10.1007/s00170-019-04689-9
Funding
This work is supported by the State Key Science & Technology Program of China (Grant No. 2019ZX04012-001); National Natural Science Foundation of China (51905209); Industrial Technology Research and Development Project of Jilin Province Development and Reform Commission, China (2019C040-2); Young and Middle-aged Scientific and Technological Innovation leaders and Team Projects in Jilin Province, China (20190101015JH); and Program for JLU Science and Technology Innovative Research Team (JLUSTIRT).
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.
Rights and permissions
About this article
Cite this article
Li, G., Wang, Y., He, J. et al. Tool wear state recognition based on gradient boosting decision tree and hybrid classification RBM. Int J Adv Manuf Technol 110, 511–522 (2020). https://doi.org/10.1007/s00170-020-05890-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-020-05890-x