Uncertainty evaluation for a three dimensional rotary measuring system by Markov chain Monte Carlo method

Uncertainty evaluation, which is an effort to set reasonable bounds for the measurement results, is important for assessing the performances of precision measuring systems. The three dimensional measurement is affected by a large number of error sources. The distributions of the primary error sources are analyzed in this paper. The multiple-try Metropolis (MTM) algorithm is applied for sampling and propagation of uncertainty for these error sources due to its advantage in dealing with large dimensional problems. The uncertainties of the three coordinates of a measured point on the workpiece r, z, and θ are evaluated before and after error separation, respectively. The differences between the two types of uncertainties are compared to find out the influence of the error separation to the uncertainty. Finally, numerical experiments are implemented to demonstrate the uncertainty assessment process.

[1]  David J. Whitehouse,et al.  Some theoretical aspects of error separation techniques in surface metrology , 1976 .

[2]  Gary C. Lin,et al.  Design and analysis of experiments in CMM measurement uncertainty study , 2007 .

[3]  Ruedi Thalmann.  BASICS OF HIGHEST ACCURACY ROUNDNESS MEASUREMENT , 2006 .

[4]  Nando de Freitas,et al.  An Introduction to MCMC for Machine Learning , 2004, Machine Learning.

[5]  Xiaoying He,et al.  Investigation of error separation for three dimensional profile rotary measuring system , 2014 .

[6]  Francesco Bartolucci,et al.  A generalization of the Multiple-try Metropolis algorithm for Bayesian estimation and model selection , 2010, AISTATS.

[7]  S. Duane,et al.  Hybrid Monte Carlo , 1987 .

[8]  Ted Doiron,et al.  Uncertainty and Dimensional Calibrations , 1997, Journal of research of the National Institute of Standards and Technology.

[9]  Yin Zhang,et al.  Solving a low-rank factorization model for matrix completion by a nonlinear successive over-relaxation algorithm , 2012, Mathematical Programming Computation.

[10]  Ruedi Thalmann,et al.  A primary roundness measuring machine , 2005, SPIE Optics + Photonics.

[11]  Jun S. Liu,et al.  The Multiple-Try Method and Local Optimization in Metropolis Sampling , 2000 .

[12]  S. Chib,et al.  Marginal Likelihood From the Metropolis–Hastings Output , 2001 .

[13]  Christiane Lemieux,et al.  Acceleration of the Multiple-Try Metropolis algorithm using antithetic and stratified sampling , 2007, Stat. Comput..

[14]  Robert G. Wilhelm,et al.  Task Specific Uncertainty in Coordinate Measurement , 2001 .

[15]  H. Kozumi,et al.  Gibbs sampling methods for Bayesian quantile regression , 2011 .

[16]  Roberto Casarin,et al.  Interacting multiple try algorithms with different proposal distributions , 2010, Statistics and Computing.

[17]  Michael Neugebauer,et al.  Uncertainty analysis for roundness measurements by the example of measurements on a glass hemisphere , 2001 .

[18]  Jean-Pierre Kruth,et al.  Uncertainty determination for CMMs by Monte Carlo simulation integrating feature form deviations , 2009 .