Hostname: page-component-8448b6f56d-qsmjn Total loading time: 0 Render date: 2024-04-20T06:18:59.476Z Has data issue: false hasContentIssue false
  • English
  • Français

Feature evaluation and selection for condition monitoring using a self-organizing map and spatial statistics

Published online by Cambridge University Press:  28 May 2018

Rui G. Silva  and
Steven J. Wilcox
Rui G. Silva*
Affiliation:
Universidade Lusíada de VN Famalicão, Largo Tinoco de Sousa, 4760-108 Vila Nova de Famalicão, Portugal
Steven J. Wilcox
Affiliation:
University of South Wales, Pontypridd, CF37 1DL, UK
*
Author for correspondence: Rui G. Silva, E-mail: rsilva@fam.ulusiada.pt
Get access Rights & Permissions [Opens in a new window]

Abstract

This paper presents a novel approach to sensor-based feature evaluation and selection using a self-organizing map and spatial statistics as a combined technique applied to tool condition monitoring of the turning process. This approach takes advantage of the unique features of unsupervised neural networks combined with spatial statistics to perform analyses into the contributions of the different sensor-based features, carrying large quantities of noise, to achieve a classification of tool wear and a quantitative measure of each feature's suitability. This method does not assume a prior direct correlation between features avoiding misconstructions inherent to common approaches that assume that only obviously correlated features should be considered for condition monitoring. Instead, and taking advantage of neural networks ability to perform non-linear modeling, it has allowed a prior modeling of the process and then analyzed each feature's contribution toward classification. It was found that some of the commonly used features have proven to have a significant contribution to the classification of cutting tool wear, whereas others adversely affect classification performance. Further, it is demonstrated that the proposed combined technique can be used extensively to quantitatively evaluate the contribution of different features toward system monitoring in the presence of noisy data.

Keywords

Condition monitoringfeature selectionself-organizing maptool wear
Type
Research Article
Information
AI EDAM , Volume 33 , Issue 1 , February 2019 , pp. 1 - 10
Copyright
Copyright © Cambridge University Press 2018 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Balazinski, M and Czogala, E (2002) Tool condition monitoring using artificial intelligence methods. Journal of Artificial Intelligence 15, 73–80. Retrieved from http://www.sciencedirect.com/science/article/pii/S0952197602000040Google Scholar
Bhuiyan, MSH, Choudhury, IA and Dahari, M (2014) Monitoring the tool wear, surface roughness and chip formation occurrences using multiple sensors in turning. Journal of Manufacturing Systems 33(4), 476–487. http://doi.org/10.1016/j.jmsy.2014.04.005Google Scholar
Binder, M, Klocke, F and Lung, D (2015) Tool wear simulation of complex shaped coated cutting tools. Wear 330–331, 600–607. http://doi.org/10.1016/j.wear.2015.01.015Google Scholar
Dimla, D and Lister, P (2000) On-line metal cutting tool condition monitoring. International Journal of Machine Tools and Manufacture 40(5), 769–781. http://doi.org/10.1016/S0890-6955(99)00085-1Google Scholar
Dimla, DE (2000) Sensor signals for tool-wear monitoring in metal cutting operations – a review of methods. International Journal of Machine Tools and Manufacture 40(8), 1073–1098. http://doi.org/10.1016/S0890-6955(99)00122-4Google Scholar
Duro, JA, Padget, JA, Bowen, CR, Kim, HA and Nassehi, A (2016) Multi-sensor data fusion framework for CNC machining monitoring. Mechanical Systems and Signal Processing 66–67, 505–520. http://doi.org/10.1016/j.ymssp.2015.04.019Google Scholar
Ericeira, D, Silva, A, Paiva, A and Gattass, M (2013) Detection of masses based on asymmetric regions of digital bilateral mammograms using spatial description with variogram and cross-variogram functions. Computers in Biology and Medicine 43, 987–999.Google Scholar
Fu, TC (2011) A review on time series data mining. Engineering Applications of Artificial Intelligence 24(1), 164–181. http://doi.org/10.1016/j.engappai.2010.09.007Google Scholar
Girardin, F, Rémond, D and Rigal, JF (2010) Tool wear detection in milling – an original approach with a non-dedicated sensor. Mechanical Systems and Signal Processing 24(6), 1907–1920. http://doi.org/10.1016/j.ymssp.2010.02.008Google Scholar
Huang, SN, Tan, KK, Wong, YS, de Silva, CW, Goh, HL and Tan, WW (2007) Tool wear detection and fault diagnosis based on cutting force monitoring. International Journal of Machine Tools and Manufacture 47(3–4), 444–451. http://doi.org/10.1016/j.ijmachtools.2006.06.011Google Scholar
Kerry, R and Oliver, MA (2007) Determining the effect of asymmetric data on the variogram. I. Underlying asymmetry. Computers and Geosciences 33(10), 1212–1232. http://doi.org/10.1016/j.cageo.2007.05.008Google Scholar
Kohonen, T (1990) The self organizing map. Proceedings of IEEE 78, 1464–1480.Google Scholar
Kohonen, T (2013) Essentials of the self-organizing map. Neural Networks 37, 52–65. http://doi.org/10.1016/j.neunet.2012.09.018Google Scholar
Kouadri, A, Aitouche, MA and Zelmat, M (2012) Variogram-based fault diagnosis in an interconnected tank system. ISA Transactions 51(3), 471–476. http://doi.org/10.1016/j.isatra.2012.01.003Google Scholar
Lauro, CH, Brandão, LC, Baldo, D, Reis, RA and Davim, JP (2014) Monitoring and processing signal applied in machining processes – a review. Measurement 58, 73–86. http://doi.org/10.1016/j.measurement.2014.08.035Google Scholar
Li, X (2002) A brief review: acoustic emission method for tool wear monitoring during turning. International Journal of Machine Tools and Manufacture 42(2), 157–165. http://doi.org/10.1016/S0890-6955(01)00108-0Google Scholar
Lin, J and Chen, Q (2014) A novel method for feature extraction using crossover characteristics of nonlinear data and its application to fault diagnosis of rotary machinery. Mechanical Systems and Signal Processing 48(1–2), 174–187. http://doi.org/10.1016/j.ymssp.2014.04.007Google Scholar
Lee, LC (1986) A study of noise emission for tool failure prediction. International Journal of Machine Tool Design and Research 26(2), 205–215.Google Scholar
Loutas, TH, Roulias, D, Pauly, E and Kostopoulos, V (2011) The combined use of vibration, acoustic emission and oil debris on-line monitoring towards a more effective condition monitoring of rotating machinery. Mechanical Systems and Signal Processing 25(4), 1339–1352. http://doi.org/10.1016/j.ymssp.2010.11.007Google Scholar
Markou, M and Singh, S (2003) Novelty detection: a review – Part 2: neural network based approaches. Signal Processing 83(12), 2499–2521. http://doi.org/10.1016/j.sigpro.2003.07.019Google Scholar
McNulty, GJ and Popplewell, N (1997) Health Monitoring of Cutting Tools Through Noise Spectra. In 1st Joint Polytechnic Symposium on Manufacturing Engineering.Google Scholar
Nouri, M, Fussell, BK, Ziniti, BL and Linder, E (2015) Real-time tool wear monitoring in milling using a cutting condition independent method. International Journal of Machine Tools and Manufacture 89, 1–13. http://doi.org/10.1016/j.ijmachtools.2014.10.011Google Scholar
Shao, C, Paynabar, K, Kim, TH, Jin, J, Hu, SJ, Spicer, JP, Abell, JA (2013a) Feature selection for manufacturing process monitoring using cross-validation. Journal of Manufacturing Systems 32(4), 550–555. http://doi.org/10.1016/j.jmsy.2013.05.006Google Scholar
Shao, H, Li, L, Liu, LJJ and Zhang, SZZ (2013b) Study on machinability of a stellite alloy with uncoated and coated carbide tools in turning. Journal of Manufacturing Processes 15(4), 673–681. http://doi.org/10.1016/j.jmapro.2013.10.001Google Scholar
Silva, RG (2009) Condition monitoring of the cutting process using a self-organizing spiking neural network map. Journal of Intelligent Manufacturing 21(6), 823–829. http://doi.org/10.1007/s10845-009-0258-xGoogle Scholar
Silva, RG, Baker, KJ, Wilcox, SJ and Reuben, RL (2000) The adaptability of a tool wear monitoring system under changing cutting conditions. Mechanical Systems and Signal Processing 14(2), 287–298. http://doi.org/10.1006/mssp.1999.1286Google Scholar
Silva, RG, Reuben, RL, Baker, KJ and Wilcox, SJ (1998) Tool wear monitoring of turning operations by neural network and expert system classification of a feature set generated from multiple sensors. Mechanical Systems and Signal Processing 12(2), 319–332. http://doi.org/10.1006/mssp.1997.0123Google Scholar
Tangjitsitcharoen, S and Moriwaki, T (2008) Intelligent monitoring and identification of cutting states of chips and chatter on CNC turning machine. Journal of Manufacturing Processes 10(1), 40–46. http://doi.org/10.1016/j.manpro.2008.01.001Google Scholar
Teti, R (2015) Advanced IT methods of signal processing and decision making for zero defect manufacturing in machining. Procedia CIRP 28, 3–15. http://doi.org/10.1016/j.procir.2015.04.003Google Scholar
Warren Liao, T (2010) Feature extraction and selection from acoustic emission signals with an application in grinding wheel condition monitoring. Engineering Applications of Artificial Intelligence 23(1), 74–84. http://doi.org/10.1016/j.engappai.2009.09.004Google Scholar
Weller, EJ, Scrier, HM and Weichbrodt, B (1969) What sound can be expected from a worn tool? ASME Paper, 68-wa/prod, 1–10.Google Scholar
Yan, R, Gao, RX and Chen, X (2014) Wavelets for fault diagnosis of rotary machines: a review with applications. Signal Processing 96(PART A), 1–15. http://doi.org/10.1016/j.sigpro.2013.04.015Google Scholar
Yupeng, L and Miguel, C (2011) A flexible lag definition for experimental variogram calculation. Mining Science and Technology 21(2), 207–211. http://doi.org/10.1016/j.mstc.2011.02.017Google Scholar
Yuwono, M, Guo, Y, Wall, J, Li, J, West, S, Platt, G and Su, SW (2015) Unsupervised feature selection using swarm intelligence and consensus clustering for automatic fault detection and diagnosis in heating ventilation and air conditioning systems. Applied Soft Computing Journal 34, 402–425. http://doi.org/10.1016/j.asoc.2015.05.030Google Scholar
Zhu, KP, Wong, YS and Hong, GS (2009) Wavelet analysis of sensor signals for tool condition monitoring: a review and some new results. International Journal of Machine Tools and Manufacture 49(7–8), 537–553. http://doi.org/10.1016/j.ijmachtools.2009.02.003.Google Scholar