Automated classification of wear particles based on their surface texture and shape features

In this study, the automated classification system, developed previously by the authors, was used to classify wear particles. Three kinds of wear particles, fatigue, abrasive and adhesive, were classified. The fatigue wear particles were generated using an FZG back-to-back gear test rig. A pin-on-disk tribometer was used to generate the abrasive and adhesive wear particles. Scanning electron microscope (SEM) images of wear particles were acquired, forming a database for further analysis. The particle images were divided into three groups or classes, each class representing a different wear mechanism. Each particle class was first examined visually. Next, area, perimeter, convexity and elongation parameters were determined for each class using image analysis software and the parameters were statistically analysed. Each particle class was then assessed using the automated classification system, based on particle surface texture. The results of the automated particle classification were compared to both the visual assessment of particle morphology and the numerical parameter values. The results showed that the texture-based classification system was a more efficient and accurate way of distinguishing between various wear particles than classification based on size and shape of wear particles. It seems that the texture-based classification method developed has great potential to become a very useful tool in the machine condition monitoring industry.

[1]  Luciano Afferrante,et al.  A re-examination of rolling contact fatigue experiments by Clayton and Su with suggestions for surface durability calculations , 2004 .

[2]  G. Stachowiak,et al.  A Comparison of Texture Feature Extraction Methods for Machine Condition Monitoring and Failure Analysis , 2005 .

[3]  G. Stachowiak,et al.  Evaluation of methods for reduction of surface texture features , 2006 .

[4]  C. James Li,et al.  Gear fatigue crack prognosis using embedded model, gear dynamic model and fracture mechanics , 2005 .

[5]  J. Flašker,et al.  Computational approach to contact fatigue damage initiation analysis of gear teeth flanks , 2007 .

[6]  Srečko Glodež,et al.  Surface fatigue of gear teeth flanks , 1999 .

[7]  B. J. Roylance,et al.  Wear studies through particle size distribution II: Multiple field analysis in Ferrography , 1983 .

[8]  Akira Yoshida,et al.  A Study on Diagnosis of Tooth Surface Failure by Wavelet Transform of Dynamic Characteristics , 2000 .

[9]  E. Rabinowicz,et al.  Friction and Wear of Materials , 1966 .

[10]  D DePellegrin,et al.  「シャープネス解析」を用いたアブレシブ摩耗における粒子形状とスケールの役割の評価 (その2) 技法の評価 , 2002 .

[11]  David K. Aspinwall,et al.  The surface integrity of turned and ground hardened bearing steel , 1996 .

[12]  Abdollah A. Afjeh,et al.  Investigation of spur gear fatigue damage using wear debris , 2002 .

[13]  Hugh Spikes,et al.  Wear in rolling contacts , 1986 .

[14]  Tony Lindeberg,et al.  An automatic assessment scheme for steel quality inspection , 2000, Machine Vision and Applications.

[15]  G. Stachowiak,et al.  Shape and texture features in the automated classification of adhesive and abrasive wear particles , 2006 .

[16]  John C. Russ,et al.  The Image Processing Handbook , 2016, Microscopy and Microanalysis.

[17]  T. Davies,et al.  Computer image analysis for identification of wear particles , 1989 .

[18]  E. D. Doyle,et al.  Wear damage to spur gears , 1974 .

[19]  Gwidon Stachowiak,et al.  A multi-scale measure of particle abrasivity, and its relation to two-body abrasive wear , 1995 .

[20]  Keiji Nakayama,et al.  Wear particle distribution and its relation to the wear transition under boundary lubrication , 1981 .

[21]  Robert P. W. Duin,et al.  Multi-class linear feature extraction by nonlinear PCA , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[22]  Christopher J. Taylor,et al.  The use of kernel principal component analysis to model data distributions , 2003, Pattern Recognit..

[23]  G. Pocock,et al.  Wear studies through particle size distribution I: Application of the Weibull distribution to ferrography , 1983 .

[24]  A. Hambaba,et al.  Multiresolution error detection on early fatigue cracks in gears , 2000, 2000 IEEE Aerospace Conference. Proceedings (Cat. No.00TH8484).

[25]  M. A. Satter,et al.  Wear of gears: A case study at Shiraz Cement Plant , 1993 .

[26]  D.-M. Tsa,et al.  Automated Surface Inspection Using Gabor Filters , 1900 .

[27]  Zhuguo Li,et al.  Grey target theory based equipment condition monitoring and wear mode recognition , 2006 .

[28]  Issam Abu-Mahfouz,et al.  A comparative study of three artificial neural networks for the detection and classification of gear faults , 2005, Int. J. Gen. Syst..

[29]  S. Chandrasekar,et al.  Paper VI (iv) Sliding Microindentation Wear Particles: Spheres in Grinding Swarf , 1992 .

[30]  B. J. Roylance,et al.  An assessment of quantimet as an aid in the analysis of wear debris in ferrography , 1976 .

[31]  Gwidon Stachowiak,et al.  Assessing the role of particle shape and scale in abrasion using ‘sharpness analysis’: Part II. Technique evaluation , 2002 .

[32]  H. Hamdi,et al.  Characterization of abrasive grain’s behavior and wear mechanisms , 2003 .

[33]  Abdollah A. Afjeh,et al.  Integrating Oil Debris and Vibration Gear Damage Detection Technologies Using Fuzzy Logic , 2004 .

[34]  Hyunsoo Kim,et al.  Dimension Reduction in Text Classification with Support Vector Machines , 2005, J. Mach. Learn. Res..

[35]  M. R. Phillips,et al.  A magnetic method for detecting the onset of surface contact fatigue , 1978 .

[36]  Thomas Brett Kirk,et al.  Computer image analysis of wear debris for machine condition monitoring and fault diagnosis , 1995 .

[37]  Dennis P. Townsend.  Surface Pitting Fatigue Life of Noninvolute, Low-Contact-Ratio Gears , 1990 .

[38]  Fred K. Choy,et al.  Damage Identification of a Gear Transmission Using Vibration Signatures , 2003 .

[39]  K. Hiratsuka,et al.  Role of wear particles in severe–mild wear transition , 2005 .

[40]  K. Johnson.  The Strength of Surfaces in Rolling Contact , 1989 .

[41]  Ilya I. Kudish,et al.  Modern State of Experimentation and Modeling in Contact Fatigue Phenomenon: Part II—Analysis of the Existing Statistical Mathematical Models of Bearing and Gear Fatigue Life. New Statistical Model of Contact Fatigue , 2000 .

[42]  M. H. Jones.  Advances in ferrographic analysis of wear debris (techniques evolved to enhance the use of ferrography) , 1983 .

[43]  K. Aslantaş,et al.  A study of spur gear pitting formation and life prediction , 2004 .

[44]  A. Ya. Grigoriev,et al.  The use of color in wear debris analysis , 2001 .

[45]  Haesun Park,et al.  Nonlinear feature extraction based on centroids and kernel functions , 2004, Pattern Recognit..

[46]  R. Gnanamoorthy,et al.  Rolling/sliding contact fatigue life prediction of sintered and hardened steels , 2007 .

[47]  Brian A. Shaw,et al.  Scanning electron acoustic microscopy imaging of sub-surface microcracks produced in gear fatigue , 1994 .

[48]  G. Stachowiak.  Numerical characterization of wear particles morphology and angularity of particles and surfaces , 1997 .

[49]  C.James Li,et al.  Model-based condition index for tracking gear wear and fatigue damage , 2000 .

[50]  Charles R. Farrar,et al.  Structural Health Monitoring Using Statistical Pattern Recognition Techniques , 2001 .

[51]  J. J. Nunnari,et al.  An overview of ferrography and its use in maintenance , 1991 .

[52]  E. D. Doyle,et al.  The condition monitoring of heavily loaded spur gears , 1983 .

[53]  Paula J. Dempsey.  Gear Damage Detection Using Oil Debris Analysis , 2001 .

[54]  J. K. Maslach.  Ferrographic analysis of grease-lubricated systems : An analysis of greases in roller bearings , 1996 .

[55]  S. Raadnui,et al.  Wear particle analysis—utilization of quantitative computer image analysis: A review , 2005 .

[56]  Arivazhagan Selvaraj,et al.  Texture classification using wavelet transform , 2003, Pattern Recognit. Lett..

[57]  Jiawen He,et al.  A criterion for contact fatigue of ion-nitrided gear , 1989 .

[58]  Srečko Glodež,et al.  A fracture mechanics model for the wear of gear flanks by pitting , 1997 .

[59]  B. J. Roylance,et al.  Ferrography—then and now , 2005 .

[60]  John A. Williams,et al.  Wear and wear particles—some fundamentals , 2005 .

[61]  S. Bahadur,et al.  Erodent particle characterization and the effect of particle size and shape on erosion , 1990 .

[62]  Kenneth P. Maynard,et al.  RESIDUAL AND DIFFERENCE FEATURE ANALYSIS WITH TRANSITIONAL GEARBOX DATA , 2001 .

[63]  K. Mao,et al.  Gear tooth contact analysis and its application in the reduction of fatigue wear , 2007 .

[64]  Wieslaw J. Staszewski,et al.  Advanced data pre-processing for damage identification based on pattern recognition , 2000, Int. J. Syst. Sci..

[65]  T. B. Kirk,et al.  Computer image analysis of wear particles in three-dimensions for machine condition monitoring , 1998 .