Abstract
Tool remaining useful life prediction is important to guarantee processing quality and efficient continuous production. Tool wear is directly related to the working conditions, showing a complex correlation and timing correlation, which makes it difficult to predict the tool remaining useful life under variable conditions. In this paper, we seek to overcome this challenge. First, we establish the unified representation of the working condition, then extract the wear characteristics from the processing signal. The extracted wear features and corresponding working conditions are combined into an input matrix for predicting tool wear. Based on this, the complex spatio-temporal relationship under variable working conditions is captured. Finally, using the unique advantages of the long short-term memory (LSTM) model to solve complex correlation and memory accumulation effects, the tool remaining useful life prediction model under variable working conditions is established. An experiment illustrates the effectiveness of the proposed method.
Similar content being viewed by others
References
Attanasio A, Ceretti E, Giardini C (2013) Analytical models for tool wear prediction during AISI 1045 turning operations. Procedia Cirp 8(11):218–223
Ji W, Shi J, Liu X, Wang L, Liang SY (2017) A novel approach of tool wear evaluation. J Manuf Sci Eng 139(9):091015
Kothuru A, Nooka SP, Victoria PI & Liu R. 2017 “Application of audible sound signals for tool wear monitoring and workpiece hardness identification in gear milling using machine learning techniques.” ASME 2017 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, Volume 10.
Mikolajczyk T, Nowicki K, Klodowski A, Pimenov YD (2017) Neural network approach for automatic image analysis of cutting edge wear. Mech Syst Signal Process 88:100–110
Kurada S, Bradley C (1997) A review of machine vision sensors for tool condition monitoring. Comput Ind 34(1):55–72
Zhang C, Zhang J (2013) On-line tool wear measurement for ball-end milling cutter based on machine vision. Comput Ind 64(6):708–719
Nan X, Duan M, Gao Y, Zheng P (2017) Tool wear prediction approach based on power sensor. J Tongji Univ 453:420–426
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Graves A (2013). “Generating sequences with recurrent neural networks.” Computer Science
Munozescalona P, Diaz N, Cassier Z (2011) Prediction of tool wear mechanisms in face milling AISI 1045 steel. J Mater Eng Perform 21(6):797–808
Chinchanikar S, Choudhury SK (2015) Predictive modeling for flank wear progression of coated carbide tool in turning hardened steel under practical machining conditions. Int J Adv Manuf Technol 76:1185–1201
Yang S, Zhu G, Xu J, Fu Y (2013) Tool wear prediction of machining hydrogenated titanium alloy Ti6Al4V with uncoated carbide tools. Int J Adv Manuf Technol 68(1):673–682
Cheon S, Kim N (2016) Prediction of tool wear in the blanking process using updated geometry. Wear 352-353:160–170
Braglia M, Castellano D (2014) Diffusion theory applied to tool-life stochastic modeling under a progressive wear process. J Manuf Sci Eng-Trans Asme 136(3):031010
Braglia M, Castellano D (2015) Improving tool-life stochastic control through a tool-life model based on diffusion theory. J Manuf Sci Eng-Trans Asme 137:4
Karuppusamy NS, Pal Pandian P, Lee H-S and Kang B-Y. (2015) “Tool wear and tool life estimation based on linear regression learning.” international conference on mechatronics and automation 17-21.
Daddona D, Ullah AM, Matarazzo D (2017) Tool-wear prediction and pattern-recognition using artificial neural network and DNA-based computing. J Intell Manuf 28(6):1285–1301
Rangwala S, Dornfeld D (1990) Sensor integration using neural networks for intelligent tool condition monitoring. J Eng Indu 112(3):219
Byrne G, Dornfeld D, Inasaki I, Ketteler G, König W, Trti R (1995) Tool Condition Monitoring (TCM) — The Status of Research and Industrial Application. CIRP Ann 44(2):541–567
Wilcox SJ, Reuben RL, Souquet P (1997) The use of cutting force and acoustic emission signals for the monitoring of tool insert geometry during rough face milling. Int J Mach Tool Manu 37(4):481–494
Wang G, Qian L, Guo Z (2013) Continuous tool wear prediction based on Gaussian mixture regression model. Int J Adv Manuf Technol 66(9):1921–1929
Zhang, Peipei, and Y. Guo. (2016) Mapping time-variant modelling of tool wears and cutting parameters on difficult-to-machine materials. Proceedings of the 10th World Congress on Engineering Asset Management (WCEAM 2015). Springer International Publishing.
Qinglu X, and Guofeng W. (2016) “Changed parameters of milling tool wearing condition monitoring research.” J Mech Sci Technol (12):1842-1847.
Wei F. (2008)“Research on tool state identification based on infrared temperature measurement.” Shanghai jiaotong University.
Yu J, Liang S, Tang D, Liu H (2016) A weighted hidden Markov model approach for continuous-state tool wear monitoring and tool life prediction. Int J Adv Manuf Technol 91(1-4):1–11
Xiaoqiang W, Zhang Yun, Huamin Z, and Yang F. (2016)“Tool wear continuous monitoring based on hidden Markov model.” Mod Mach Tool Autom Proc Technol, (10):87-90.
Alonso FJ, Salgado DR (2005) Application of singularspectrum analysis to tool wear detection using sound signals. Proc Instit Mech Eng Part B: J Eng Manuf 219(9):703–710
Emerson Raja J, Kiong LC, and Soong LW (2011)“Emitted sound amplitude analysis using Hilbert Huang Transformation for cutting tool flank wear prediction.” International Conference on Computing & Communication Systems Springer, Berlin, Heidelberg.
Xin W, Ji W, Chao L, Haiyan Y, Yanli D, and Wensheng N. (2018) “Fault time series prediction based on LSTM recurrent neural network.” J Beijing Univ Aeronaut Astronaut, (4):772-784.
Zhihui R, Haoyu X, Songlin F, Han Z, Jun S (2017) Sequence marking Chinese word segmentation based on LSTM network. Comp Appl Res 34(5):1321–1324
Qiang W, Yingguang L, Xiaozhong H, Changqing L, Haiji C (2019) Dynamic prediction method of nc machining tool life based on online learning. Aerospace Manuf Technol 62(07):49–53
Ma XL, Tao ZM, Wang YH, Yu HY, Wang YP (2015) Long short-term memory neural network for traffic speed prediction using remote microwave sensor data. Trans Res Part C: Emerg Technol 54:187–197
Adlen K, Abderrezak M, Ridha K, Batouche M (2018) Real-time safety monitoring in the induction motor using deep hierarchic long short-term memory. Int J Adv Manuf Technol 99(9–12):2245–2255
Huibin S, Weilong N, Junyang W (2015) Tool wear feature extraction based on Hilbert-Huang Transform. J Vib Shock 34(4):158–164
Funding
The work is financially supported by the National Defense Basic Scientific Research program of China through approval no. JSCG2016205B006 and the National Science and Technology Major Project of China through approval no. 2012ZX04011041.
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
Zhou, JT., Zhao, X. & Gao, J. Tool remaining useful life prediction method based on LSTM under variable working conditions. Int J Adv Manuf Technol 104, 4715–4726 (2019). https://doi.org/10.1007/s00170-019-04349-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-019-04349-y