The classification of workpiece surface patterns is an essential element in trying to understand how functional performance is influenced by the surface geometry. Filter banks have been investigated in literature for capturing the multiscale characterization of the engineering surfaces. Conventionally, parametric representations of the filter outputs were used for classification. In this paper, the histogram estimators of the filter bank outputs from engineering surfaces in combination with the nearest neighbor method for classification are investigated to improve the classification accuracy, which are accomplished by utilizing distribution dissimilarity measures to compare histograms. Furthermore, for large and complex surfaces, the histogram estimators of local surface flatness parameters are also proposed for the purpose of simple computation. Two case studies have been conducted to demonstrate the proposed methods. Influence of the histogram bins for histograms and the dissimilarity measures on classification performance is studied in detail. Results from the first case study show that the proposed method is less effective in classifying small surfaces with clear surface patterns, because the filtering is influenced by the quality of the surface data collected from the measurement sensor. In comparison, results from the second case study show that the proposed method performs better in classifying large surfaces with mild surface pattern differences. The classification accuracy using the conventional method drops from 100% to around 50% in the second case study. In general, one can achieve misclassification errors below 5% in both case studies with the histogram representations of surface parameters and the appropriate selection of the number of bins for histogram construction.
Skip Nav Destination
e-mail: mzhangz@umich.edu
e-mail: ddjurdja@umich.edu
e-mail: junni@umich.edu
Article navigation
June 2008
Research Papers
Estimating Distributions of Surface Parameters for Classification Purposes
Min Zhang,
Min Zhang
Department of Mechanical Engineering,
e-mail: mzhangz@umich.edu
The University of Michigan
, Ann Arbor, MI 48109
Search for other works by this author on:
Dragan Djurdjanovic,
Dragan Djurdjanovic
Department of Mechanical Engineering,
e-mail: ddjurdja@umich.edu
The University of Michigan
, Ann Arbor, MI 48109
Search for other works by this author on:
Jun Ni
Jun Ni
Department of Mechanical Engineering,
e-mail: junni@umich.edu
The University of Michigan
, Ann Arbor, MI 48109
Search for other works by this author on:
Min Zhang
Department of Mechanical Engineering,
The University of Michigan
, Ann Arbor, MI 48109e-mail: mzhangz@umich.edu
Elizaveta Levina
Dragan Djurdjanovic
Department of Mechanical Engineering,
The University of Michigan
, Ann Arbor, MI 48109e-mail: ddjurdja@umich.edu
Jun Ni
Department of Mechanical Engineering,
The University of Michigan
, Ann Arbor, MI 48109e-mail: junni@umich.edu
J. Manuf. Sci. Eng. Jun 2008, 130(3): 031010 (9 pages)
Published Online: May 12, 2008
Article history
Received:
April 27, 2006
Revised:
December 28, 2007
Published:
May 12, 2008
Citation
Zhang, M., Levina, E., Djurdjanovic, D., and Ni, J. (May 12, 2008). "Estimating Distributions of Surface Parameters for Classification Purposes." ASME. J. Manuf. Sci. Eng. June 2008; 130(3): 031010. https://doi.org/10.1115/1.2844588
Download citation file:
Get Email Alerts
Cited By
2024 Reviewers
J. Manuf. Sci. Eng
NoodlePrint: Cooperative Multi-Robot Additive Manufacturing With Helically Interlocked Tiles
J. Manuf. Sci. Eng (June 2025)
Related Articles
A Study on Fluidized Bed-Type Particulate Filter for Diesel Engines
J. Eng. Gas Turbines Power (October,2007)
An Adaptive State Filtering Algorithm for Systems With Partially Known Dynamics
J. Dyn. Sys., Meas., Control (September,2002)
Simplified Federated Filtering Algorithm With Different States in Local Filters
J. Dyn. Sys., Meas., Control (January,2011)
On Optimal Filtering for Polynomial System States
J. Dyn. Sys., Meas., Control (March,2003)
Related Proceedings Papers
Related Chapters
Based on Hybrid Recommendation Personalized of the E-Learning System Study
Proceedings of the 2010 International Conference on Mechanical, Industrial, and Manufacturing Technologies (MIMT 2010)
Application Analysis and Experimental Study on Performance of Energy-Saving Electret Fiber
Inaugural US-EU-China Thermophysics Conference-Renewable Energy 2009 (UECTC 2009 Proceedings)
A Novel Approach for LFC and AVR of an Autonomous Power Generating System
International Conference on Mechanical Engineering and Technology (ICMET-London 2011)