Abstract
Tool condition monitoring (TCM) system serves as the link between the cutting tool condition and the maintenance decision. The recent prognostic system employs highly complex models, which might need long calculation time. This long calculation time is acceptable for machine health prognostics, as machines’ maintenance interval is in the unit of month. However, a cutting tool’s life varies between minutes to hours. The calculation time might be critical to achieve a valid prognosis. In this paper, a novel prognostic system is proposed for TCM prognostics. This system consists of two parts: (1) online cutting force prediction part and (2) tool wear estimation part. The first part predicts the future cutting force segmentation by projecting the embedded historical cutting force with function approximation methods. Three function approximation methods are compared in the aspect of prediction error and calculation time. It is found that the Saucer’s local linear model could achieve the lowest prediction error (4.71 %) and calculation time (2.717 s) compared with global linear model and nonlinear model. The second part estimates the tool wear by inputting the predicted cutting force to a Bayesian-multilayer perceptron. It is found that this system can trace the progress of tool wear accurately (95 % successful rate has been achieved). Moreover, good generalization for different cutting conditions is also achieved.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Qu J, Zuo MJ (2012) An LSSVR-based algorithm for online system condition prognostics. Expert Syst Appl 39(5):6089–6102. doi:10.1016/j.eswa.2011.12.002
Caesarendra W, Widodo A, Yang B-S (2011) Combination of probability approach and support vector machine towards machine health prognostics. Probabilistic Eng Mech 26(2):165–173. doi:10.1016/j.probengmech.2010.09.008
Liao W, Wang Y, Pan E (2012) Single-machine-based predictive maintenance model considering intelligent machinery prognostics. Int J Adv Manuf Technol 63(1–4):51–63. doi:10.1007/s00170-011-3884-3
Lin D, Makis V (2003) Recursive filters for a partially observable system subject to random failure. Adv Appl Probab 35:207–227, Copyright 2003, IEE
Wang WQ, Golnaraghi MF, Ismail F (2004) Prognosis of machine health condition using neuro-fuzzy systems. Mech Syst Signal Process 18:813–831, Compendex
Yam RCM, Tse PW, Li L, Tu P (2001) Intelligent predictive decision support system for condition-based maintenance. Int J Adv Manuf Technol 17:383–391, Copyright 2001, IEE
Baruah P, Chinnam RB (2005) HMMs for diagnostics and prognostics in machining processes. Int J Prod Res 43(6):1275–1293
Kunpeng Z (2007) Multi-categories tool wear classification in micro-milling. NUS, Singapore
Packard NH, Crutchfield JP, Farmer JD, Shaw RS (1980) Geometry from a time series. Phys Rev Lett 45:712–716, Copyright 1980, IEE
Zhang J, Shu-Hung Chung H, Wai-Lun L (2008) Chaotic time series prediction using a neuro-fuzzy system with time-delay coordinates. IEEE Trans Knowl Data Eng 20:956–964, Copyright 2008, The Institution of Engineering and Technology
Sauer T (1994) Time series prediction by using delay coordinate embedding (data set A). (Compendex):175-175
Kennel MB, Brown R, Abarbanel HDI (1992) Determining embedding dimension for phase-space reconstruction using a geometrical construction. Phys Rev A Stat Phys Plasmas Fluids Relat Interdiscip Top 45:3403–3411, Copyright 1992, IEE
Casdagli M, Weigend AS (1994) Exploring the continuum between deterministic and stochastic modeling (data sets A,B,D). (Compendex):347-347
Shao Y, Nezu K (2000) Prognosis of remaining bearing life using neural networks. Proc Inst Mech Eng I-J Syst 214(13):217–230
Wang P, Vachtsevanos G (2001) Fault prognostics using dynamic wavelet neural networks. AI EDAM Artif Intell Eng Des Anal Manuf 15:383–391
Chinnam RB, Baruah P (2004) A neuro-fuzzy approach for estimating mean residual life in condition-based maintenance systems. Int J Mater Prod Technol 20:166–179
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wu, Y., Hong, G.S. & Wong, W.S. Prognosis of the probability of failure in tool condition monitoring application-a time series based approach. Int J Adv Manuf Technol 76, 513–521 (2015). https://doi.org/10.1007/s00170-014-6299-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-014-6299-0