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

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.

[1]  Julian Padget,et al.  Multi-sensor data fusion framework for CNC machining monitoring , 2016 .

[2]  Qian Chen,et al.  A novel method for feature extraction using crossover characteristics of nonlinear data and its application to fault diagnosis of rotary machinery , 2014 .

[3]  L. C. Lee,et al.  A study of noise emission for tool failure prediction , 1986 .

[4]  Jean-François Rigal,et al.  Tool wear detection in milling—An original approach with a non-dedicated sensor , 2010 .

[5]  Lin Li,et al.  Study on machinability of a stellite alloy with uncoated and coated carbide tools in turning , 2013 .

[6]  Rui Silva,et al.  TOOL WEAR MONITORING OF TURNING OPERATIONS BY NEURAL NETWORK AND EXPERT SYSTEM CLASSIFICATION OF A FEATURE SET GENERATED FROM MULTIPLE SENSORS , 1998 .

[7]  Anselmo Cardoso de Paiva,et al.  Detection of masses based on asymmetric regions of digital bilateral mammograms using spatial description with variogram and cross-variogram functions , 2013, Comput. Biol. Medicine.

[8]  Geok Soon Hong,et al.  Wavelet analysis of sensor signals for tool condition monitoring: A review and some new results , 2009 .

[9]  Tak-Chung Fu,et al.  A review on time series data mining , 2011, Eng. Appl. Artif. Intell..

[10]  D. E. Dimla,et al.  On-line metal cutting tool condition monitoring.: I: force and vibration analyses , 2000 .

[11]  Glenn Platt,et al.  Unsupervised feature selection using swarm intelligence and consensus clustering for automatic fault detection and diagnosis in Heating Ventilation and Air Conditioning systems , 2015, Appl. Soft Comput..

[12]  Li Yupeng,et al.  A flexible lag definition for experimental variogram calculation , 2011 .

[13]  I. Choudhury,et al.  Monitoring the tool wear, surface roughness and chip formation occurrences using multiple sensors in turning , 2014 .

[14]  Sameer Singh,et al.  Novelty detection: a review - part 2: : neural network based approaches , 2003, Signal Process..

[15]  Xiaoli Li,et al.  A brief review: acoustic emission method for tool wear monitoring during turning , 2002 .

[16]  Tae-Hyung Kim,et al.  Feature selection for manufacturing process monitoring using cross-validation , 2013 .

[17]  Rui Silva,et al.  THE ADAPTABILITY OF A TOOL WEAR MONITORING SYSTEM UNDER CHANGING CUTTING CONDITIONS , 2000 .

[18]  Mimoun Zelmat,et al.  Variogram-based fault diagnosis in an interconnected tank system. , 2012, ISA transactions.

[19]  D. E. Dimla,et al.  On-line metal cutting tool condition monitoring.: II: tool-state classification using multi-layer perceptron neural networks , 2000 .

[20]  R. Kerry,et al.  Determining the effect of asymmetric data on the variogram. I. Underlying asymmetry , 2007, Comput. Geosci..

[21]  Roberto Teti,et al.  Advanced IT Methods of Signal Processing and Decision Making for Zero Defect Manufacturing in Machining , 2015 .

[22]  Fritz Klocke,et al.  Tool wear simulation of complex shaped coated cutting tools , 2015 .

[23]  Rui G. Silva,et al.  Condition monitoring of the cutting process using a self-organizing spiking neural network map , 2010, J. Intell. Manuf..

[24]  C. W. de Silva,et al.  Tool wear detection and fault diagnosis based on cutting force monitoring , 2007 .

[25]  Toshimichi Moriwaki,et al.  Intelligent monitoring and identification of cutting states of chips and chatter on CNC turning machine , 2008 .

[26]  Krzysztof Jemielniak,et al.  Tool condition monitoring using artificial intelligence methods , 2002 .

[27]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[28]  Barry K. Fussell,et al.  Real-time tool wear monitoring in milling using a cutting condition independent method , 2015 .

[29]  Carlos Henrique Lauro,et al.  Monitoring and processing signal applied in machining processes – A review , 2014 .

[30]  D. E. Dimla,et al.  Sensor signals for tool-wear monitoring in metal cutting operations—a review of methods , 2000 .

[31]  Bjorn Weichbrodt,et al.  What Sound Can Be Expected From a Worn Tool , 1969 .

[32]  Theodoros Loutas,et al.  The combined use of vibration, acoustic emission and oil debris on-line monitoring towards a more effective condition monitoring of rotating machinery , 2011 .

[33]  Teuvo Kohonen,et al.  Essentials of the self-organizing map , 2013, Neural Networks.

[34]  T. Warren Liao,et al.  Feature extraction and selection from acoustic emission signals with an application in grinding wheel condition monitoring , 2010, Eng. Appl. Artif. Intell..

[35]  Robert X. Gao,et al.  Wavelets for fault diagnosis of rotary machines: A review with applications , 2014, Signal Process..