Nonparametric approach to improvement of qualitt of modal parameters estimation
暂无分享,去创建一个
In the paper, issues concerning curve smoothing methods such as the locally weighted scatter plot smooth method (LOESS), moving average method (MA), Savitzky-Golay filter method (SG) are discussed. Results of the ERA analysis for measured noisy frequency response functions smoothed by curve smoothing methods as well as frequency response functions with no additional noise introduced and smoothed by the curve smoothing methods are presented. As reference values, natural frequencies and modal damping factors corresponding with poles estimated by the use of the ERA method for the frequency response functions measured in a harmonic test are assumed.
[1] Thomas C.M. Lee. Improved smoothing spline regression by combining estimates of different smoothness , 2004 .
[2] R. Hunt,et al. Regression Smoothers for Estimating Parameters of Growth Analyses , 1996 .
[3] J. Marron,et al. SCALE SPACE VIEW OF CURVE ESTIMATION , 2000 .