Kernel density maximum entropy method with generalized moments for evaluating probability distributions, including tails, from a small sample of data

2017 ◽  
Vol 113 (13) ◽  
pp. 1904-1928 ◽  
Author(s):  
Umberto Alibrandi ◽  
Khalid M. Mosalam
Author(s):  
S. M. Nielsen ◽  
H. A. Hougaard ◽  
O. Balling

Abstract Use of high-fidelity fatigue models that incorporate not only material uncertainty but also part variability and operational uncertainties can improve the accuracy of predictive maintenance and thus decrease operational cost. However, due to the large number of computationally expensive cost function evaluations necessary, little work has been done to explore this field. In this research, the expected life probability distributions with low computational cost is estimated through a general statistical framework that applies Maximum Entropy Method (MEM), fractional statistical moments and Multiplicative Dimensional Reduction (M-DRM). The framework is tested on advanced models of a 6204 SKF ball bearing. The influence of critical part tolerances and load conditions on fatigue life with a probability density function with only 80 function evaluations is quantified in both a finite element analysis and a non-linear analytical model. The number of function evaluations is one order of magnitude lower than necessary for a comparable accuracy achieved by Monte Carlo simulation.


1996 ◽  
Vol 51 (5-6) ◽  
pp. 337-347 ◽  
Author(s):  
Mariusz Maćkowiak ◽  
Piotr Kątowski

Abstract Two-dimensional zero-field nutation NQR spectroscopy has been used to determine the full quadrupolar tensor of spin - 3/2 nuclei in serveral molecular crystals containing the 3 5 Cl and 7 5 As nuclei. The problems of reconstructing 2D-nutation NQR spectra using conventional methods and the advantages of using implementation of the maximum entropy method (MEM) are analyzed. It is shown that the replacement of conventional Fourier transform by an alternative data processing by MEM in 2D NQR spectroscopy leads to sensitivity improvement, reduction of instrumental artefacts and truncation errors, shortened data acquisition times and suppression of noise, while at the same time increasing the resolution. The effects of off-resonance irradiation in nutation experiments are demonstrated both experimentally and theoretically. It is shown that off-resonance nutation spectroscopy is a useful extension of the conventional on-resonance experiments, thus facilitating the determination of asymmetry parameters in multiple spectrum. The theoretical description of the off-resonance effects in 2D nutation NQR spectroscopy is given, and general exact formulas for the asymmetry parameter are obtained. In off-resonance conditions, the resolution of the nutation NQR spectrum decreases with the spectrometer offset. However, an enhanced resolution can be achieved by using the maximum entropy method in 2D-data reconstruction.


Geophysics ◽  
2003 ◽  
Vol 68 (4) ◽  
pp. 1417-1422 ◽  
Author(s):  
Danilo R. Velis

The distribution of primary reflection coefficients can be estimated by means of the maximum entropy method, giving rise to smooth nonparametric functions which are consistent with the data. Instead of using classical moments (e.g. skewness and kurtosis) to constraint the maximization, nonconventional sample statistics help to improve the quality of the estimates. Results using real log data from various wells located in the Neuquen Basin (Argentina) show the effectiveness of the method to estimate both robust and consistent distributions that may be used to simulate realistic sequences.


1987 ◽  
Vol 4 (1) ◽  
pp. 78-82 ◽  
Author(s):  
B. C. De Simone ◽  
F. De Luca ◽  
B. Maraviglia

Sign in / Sign up

Export Citation Format

Share Document