Abstract
Accurate identification of the tool wear state during the machining process is of great significance to improve product quality and benefit. The wear states of the same tool type and machining material have similarities during the machining process. By mining the data value of the historical machining process and analyzing the similarity of the procedure, the subsequent machining process can be predicted with the help of transfer learning. Therefore, this study proposes a tool wear prediction scheme based on feature-based transfer learning to realize the accurate prediction of the tool wear state. The genetic algorithm (GA) is used to select a subset of sensor features that are highly correlated with tool wear. Then, the source domain and target domain are constructed on the basis of the selected sensor features of the historical tool and the new tool during the machining process, respectively. In addition, features in the life cycle of the new tool are completed by feature-based transfer learning. After feature transfer, the maximum mean square discrepancy (MMD) method is used to evaluate the similarity of features, and the optimal feature subset is selected according to the evaluation result. Finally, the particle swarm-optimized support vector machine (PSO-SVM) model is applied to predict the tool wear states during the new tool machining. The effectiveness of the proposed tool wear scheme is verified by the cutting force and wear data of the tool life cycle under three different milling parameter combinations. Results with high accuracy show the advantages of the feature-based transfer learning method for tool wear state prediction.
Similar content being viewed by others
References
Zhu DH, Zhang XM, Ding H (2013) Tool wear characteristics in machining of nickel-based superalloys. Int J Mach Tools Manuf 64:60–77. https://doi.org/10.1016/j.ijmachtools.2012.08.001
Pu CL, Zhu G, Yang SB, Yue EB, Subramanian SV (2016) Effect of dynamic recrystallization at tool-chip interface on accelerating tool wear during high-speed cutting of AISI1045 steel. Int J Mach Tools Manuf 100:72–80. https://doi.org/10.1016/j.ijmachtools.2015.10.006
Duro JA, Padget JA, Bowen CR, Kim HA, Nassehi A (2016) Multi-sensor data fusion framework for CNC machining monitoring. Mech Syst Signal Process 66-67:505–520. https://doi.org/10.1016/j.ymssp.2015.04.019
García-Ordás MT, Alegre-Gutiérrez E, Alaiz-Rodríguez R, González-Castro R (2018) Tool wear monitoring using an online, automatic and low cost system based on local texture. Mech Syst Signal Process 112:167–182. https://doi.org/10.1016/j.ymssp.2018.04.035
Niaki FA, Mears L (2017) A comprehensive study on the effects of tool wear on surface roughness, dimensional integrity and residual stress in turning IN718 hard-to-machine alloy. J Manuf Process 30:268–280. https://doi.org/10.1016/j.jmapro.2017.09.016
Kong DD, Chen CJ, Li N, Tan SL (2017) Tool wear monitoring based on kernel principal component analysis and v-support vector regression. Int J Adv Manuf Technol 89:175–190. https://doi.org/10.1007/s00170-016-9070-x
Kong DD, Chen YJ, Li N (2017) Hidden semi-Markov model-based method for tool wear estimation in milling process. Int J Adv Manuf Technol 92:3647–3657. https://doi.org/10.1007/s00170-017-0404-0
Liu T, Jolley B (2015) Tool condition monitoring (TCM) using neural networks. Int J Adv Manuf Technol 78:1999–2007. https://doi.org/10.1007/s00170-014-6738-y
Segreto T, D’Addona D, Teti R (2020) Tool wear estimation in turning of Inconel 718 based on wavelet sensor signal analysis and machine learning paradigms. Prod Eng 14:693–705. https://doi.org/10.1007/s11740-020-00989-2
Maia LHA, Abram AM, Vasconcelos WL, Sales WF, Machado AR (2015) A New Approach for detection of wear mechanisms and determination of tool life in turning using acoustic emission. Tribol Int 92:519–532. https://doi.org/10.1016/j.triboint.2015.07.024
Drouillet C, Karandikar J, Nath C, Journeaux AC, El Mansori M, Kurfess T (2016) Tool life predictions in milling using spindle power with the neural network technique. J Manuf Process 22:161–168. https://doi.org/10.1016/j.jmapro.2016.03.010
Özçifta A, Gültenb A (2013) Genetic algorithm wrapped Bayesian network feature selection applied to differential diagnosis of erythemato-squamous diseases. Digit Signal Process 23(1):230–237. https://doi.org/10.1016/j.dsp.2012.07.008
Liao TW (2010) Feature extraction and selection from acoustic emission signals with an application in grinding wheel condition monitoring. Eng Appl Artif Intell 23:74–84. https://doi.org/10.1016/j.engappai.2009.09.004
Alonso FJ, Salgado DR (2008) Analysis of the structure of vibration signals for tool wear detection. Mech Syst Signal Process 22:735–748. https://doi.org/10.1016/j.ymssp.2007.09.012
Niaki FA, Feng LJ, Ulutan D, Mears L (2016) A wavelet-based data-driven modelling for tool wear assessment of difficult to machine materials. Int J Mech Manuf Syst 9:97–121. https://doi.org/10.1504/IJMMS.2016.076168
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 N, Chen YJ, Kong DD, Tan SL (2017) Force-Based tool condition monitoring for turning process using v-support vector regression. Int J Adv Manuf Technol 91:351–361. https://doi.org/10.1007/s00170-016-9735-5
Kong DD, Chen YJ, Li N, Duan CQ, Lu LX, Chen DX (2019) Tool wear estimation in end-milling of titanium alloy using NPE and a novel WOA-SVM model. IEEE Trans Instrum Meas 99:1. https://doi.org/10.1109/TIM.2019.2952476
Wu DZ, Jennings C, Terpenny J, Gao R, Kumara S (2017) A comparative study on machine learning algorithms for smart manufacturing: tool wear prediction using random forests. J Manuf Sci Eng 139:071018. https://doi.org/10.1115/1.4036350
Li JL, Zhang L, Wu ZC, Ling ZC, Cao XQ, Guo KC, Yan FB (2020) Autonomous Martian rock image classification based on transfer deep learning methods. Earth Sci Inf 13:951–963. https://doi.org/10.1007/s12145-019-00433-9
Ozcan T, Basturk A (2020) Static facial expression recognition using convolutional neural networks based on transfer learning and hyperparameter optimization. Multimed Tools Appl 79:26587–26604. https://doi.org/10.1007/s11042-020-09268-9
Howard D, Maslej M, Lee J, Ritchie J, Woollard G, French L (2019) transfer learning for risk classification of social media posts: model evaluation Study. J Med Int Res 22. https://doi.org/10.2196/15371
Pramanik R, Bag S (2020) Segmentation-based recognition system for handwritten Bangla and Devanagari words using conventional classification and transfer learning. IET Image Process 14:959–972. https://doi.org/10.1049/iet-ipr.2019.0208
Ali S, Hassan M, Saleem S, Tahir SF (2020) Deep transfer learning based hepatitis B virus diagnosis using spectroscopic images. Int J Imaging Syst Technol 31:94–105. https://doi.org/10.1002/ima.22462
Jaiswal A, Gianchandani N, Singh D, Kumar V, Kaur M (2020) Classification of the COVID-19 infected patients using DenseNet201 based deep transfer learning. J Biomol Struct Dyn:1–8. https://doi.org/10.1080/07391102.2020.1788642
Kurek J, Wieczorek G, Swiderski B, Kruk M, Jegorowa A, Osowski S (2017) Transfer learning in recognition of drill wear using convolutional neural network. Proceedings of 2017 18th International Conference Computational Problems of Electrical Engineering (CPEE). https://doi.org/10.1109/CPEE.2017.8093087
Zhang AS, Wang HL, Li SB, Cui YX, Liu ZH, Yang GC, Hu JJ (2018) Transfer learning with deep recurrent neural networks for remaining useful life estimation. Appl Sci 8. https://doi.org/10.3390/app8122416
Mao W, He J, Zuo MJ (2020) Predicting remaining useful life of rolling bearings based on deep feature representation and transfer learning. IEEE Trans Instrum Meas 69:1594–1608. https://doi.org/10.1109/TIM.2019.2917735
Sun C, Ma M, Zhao ZB, Tian SH, Yan RQ, Chen XF (2018) Deep transfer learning based on sparse auto-encoder for remaining useful life prediction of tool in manufacturing. IEEE Trans Ind Inf 99:1. https://doi.org/10.1109/TII.2018.2881543
Weiss K, Khoshgoftaar TM, Wang DD (2016) A survey of transfer learning. J Big Data 3:9. https://doi.org/10.1186/s40537-016-0043-6
Bidi N, Elberrichi Z (2017) Feature selection for text classification using genetic algorithm. 2016 8th International Conference on Modelling, identification and control (ICMIC). https://doi.org/10.1109/ICMIC.2016.7804223
Long MS, Wang JM, Ding GG, Pan SJ, Yu PS (2013) Adaptation regularization: a general framework for transfer learning. IEEE Trans Knowl Data Eng 26:1076–1089. https://doi.org/10.1109/TKDE.2013.111
Pan SJ, Tsang IW, Kwok JT, Yang Q (2011) Domain adaptation via transfer component analysis. IEEE Trans Neural Netw 22:199–210. https://doi.org/10.1109/Tnn.2010.2091281
Long MS, Wang JM, Ding GG, Sun JG, Yu PS (2013) Transfer feature learning with joint distribution adaptation. Proceedings of the 2013 International Conference on Computer Vision. https://doi.org/10.1109/ICCV.2013.274
Wei YY, Zhang JY, Wang J (2018) Research on building fire risk fast assessment method based on fuzzy comprehensive evaluation and SVM. Procedia Eng 211:1141–1150. https://doi.org/10.1016/j.proeng.2017.12.121
Liu P, Xie MC, Bian J, Li HS, Song LL (2020) A hybrid PSO-SVM model based on safety risk prediction for the design process in metro station construction. Int J Environ Res Public Health 17:1714. https://doi.org/10.3390/ijerph17051714
Liu CQ, Li YG, Zhou GY, Shen WM (2018) A sensor fusion and support vector machine based approach for recognition of complex machining conditions. J Intell Manuf 29:1739–1752. https://doi.org/10.1007/s10845-016-1209-y
Shi DF, Gindy NN (2007) Tool wear predictive model based on least squares support vector machines. Mech Syst Signal Process 21:1799–1814. https://doi.org/10.1016/j.ymssp.2006.07.016
Muller KR, Mika S, Ratsch G, Tsuda K, Scholkopf B (2001) An introduction to kernel-based learning algorithms. IEEE Trans Neural Netw 12:181–201. https://doi.org/10.1109/72.914517
Barakat N, Baradley AP (2010) Rule extraction from support vector machines: a review. Neurocomputing 74:178–190. https://doi.org/10.1016/j.neucom.2010.02.016
Xue TCQ, Shi Y, Deng HZ (2020) Rope tension fault diagnosis in hoisting systems based on vibration signals using EEMD, improved permutation entropy, and PSO-SVM. Entropy 22:209. https://doi.org/10.3390/e22020209
Availability of data and materials
The data and materials used to support the findings of this study are available from the corresponding author upon request.
Funding
This work was supported by a grant from the National Nature Science Foundation of China (No.51665005), Guangxi Natural Science Foundation (No.2020JJD160004 and No.2019JJB160048), the project of improving the basic scientific research ability of young and middle-aged teachers of colleges and universities in Guangxi (No.2020KY10014).
Author information
Authors and Affiliations
Contributions
Xiaoping Liao contributed to the conception of the study.
Chaoyi Chen performed the experiment.
Juan Lu contributed significantly to analysis and manuscript preparation.
Jianbo Li performed the data analyses and wrote the manuscript.
Junyan Ma helped perform the analysis with constructive discussions.
Corresponding author
Ethics declarations
Ethical approval
The author promises that the research results are true and effective. Meanwhile, the author promised to abide by the following rules during the research process:
(1) We promise that the manuscript will not be submitted to multiple journals for simultaneous consideration.
(2) We promise that the submitted manuscript is original works and should not be published elsewhere in any form or language (partially or fully).
(3) We promise not to divide a research into multiple parts to increase the number of submissions, and submit it to various journals or one journal over time.
(4) We promise to present the results clearly and honestly, without false, forged, or inappropriate data processing (including image-based processing). Moreover, we follow the rules of a specific discipline to obtain, select and process data.
(5) We promise not to plagiarize any data, words, or theories.
Consent to participate
We ensure the objectivity and transparency of research, and ensure that recognized principles of ethical and professional conduct are followed. Our research does not involve humans and animals, so there is no need to provide information on potential conflict of interest declarations and informed consent.
Consent to publish
If the manuscript is accepted by the journal, our authors will consent to publish.
Competing interests
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.
Jianbo Li and Juan Lu are co-first authors and contributted equally to this work.
Rights and permissions
About this article
Cite this article
Li, J., Lu, J., Chen, C. et al. Tool wear state prediction based on feature-based transfer learning. Int J Adv Manuf Technol 113, 3283–3301 (2021). https://doi.org/10.1007/s00170-021-06780-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-021-06780-6