An Automated Non–Parametric Healthy Subspace Method for Unsupervised Robust Vibration–Based Damage Detection Under Uncertainty

2019 ◽  
Author(s):  
KYRIAKOS VAMVOUDAKIS-STEFANOU ◽  
SPILIOS FASSOIS ◽  
JOHN SAKELLARIOU
Keyword(s):  
Damage Detection ◽  
Subspace Method ◽  
Non Parametric

scholarly journals Vibration Tests in CFRP Plates for Damage Detection via Non-Parametric Signal Analysis

2012 ◽  
Vol 19 (5) ◽  
pp. 857-865 ◽  
Author(s):  
P. Moreno-García ◽  
E. Castro ◽  
L. Romo-Melo ◽  
A. Gallego ◽  
A. Roldán
Keyword(s):  
Damage Detection ◽  
Signal Analysis ◽  
Vibration Tests ◽  
Non Parametric

A method for non-parametric damage detection through the use of neural networks

1998 ◽  
Vol 27 (9) ◽  
pp. 997-1010 ◽  
Author(s):  
Mitsuru Nakamura ◽  
Sami F. Masri ◽  
Anastassios G. Chassiakos ◽  
Thomas K. Caughey
Keyword(s):  
Neural Networks ◽  
Damage Detection ◽  
Non Parametric

An automated hypersphere-based healthy subspace method for robust and unsupervised damage detection via random vibration response signals

2021 ◽  
pp. 147592172110044
Author(s):  
Vamvoudakis-Stefanou Kyriakos ◽  
Fassois Spilios ◽  
Sakellariou John
Keyword(s):  
Damage Detection ◽  
High Performance ◽  
Random Vibration ◽  
Feature Space ◽  
Vibration Response ◽  
Alternative Methods ◽  
Detection Methods ◽  
Subspace Method ◽  
Uncertainty Sources ◽  
Automated Algorithm

A novel, unsupervised, hypersphere-based healthy subspace method for robust damage detection under non-quantifiable uncertainty via a limited number of random vibration response sensors is postulated. The method is based on the approximate construction, within a proper feature space, of a healthy subspace representing the healthy structural dynamics under uncertainty as the union of properly selected hyperspheres. This is achieved via a fully automated algorithm eliminating user intervention, and thus subjective selections, or complex optimization procedures. The main asset of the proposed method lies in combining simplicity and full automation with high performance. Its performance is systematically assessed via two experimental case studies featuring various uncertainty sources and distinct healthy subspace geometries, while interesting comparisons with three well-known robust damage detection methods are also performed. The results indicate excellent detection performance, which also compares favorably to that of alternative methods.

scholarly journals Non-parametric Inference Applied to Damage Detection in the Electromechanical Impedance-based Health Monitoring

2020 ◽  
Vol 7 (9) ◽  
pp. 73-79
Author(s):  
Quintiliano Siqueira Schroden Nomelini ◽  
Jose Waldemar da Silva ◽  
Carlos Alberto Gallo ◽  
Roberto Mendes Finzi Neto ◽  
Karina Mayumi Tsuruta ◽  
...  
Keyword(s):  
Damage Detection ◽  
Health Monitoring ◽  
Parametric Inference ◽  
Electromechanical Impedance ◽  
Non Parametric

Error vector choice in direct inversion in the iterative subspace method

10.1002/jcc.4 ◽  
1996 ◽  
Vol 17 (16) ◽  
pp. 1836-1847 ◽  
Author(s):  
Irina V. Ionova ◽  
Emily A. Carter
Keyword(s):  
Subspace Method ◽  
Error Vector ◽  
Direct Inversion

ESTIMATION OF PRESSURE DROP FOR NON-NEWTONIAN LIQUID FLOW THROUGH BENDS USING ADAPTIVE NON-PARAMETRIC MODEL

2020 ◽  
Vol 47 (1) ◽  
pp. 59-69
Author(s):  
Suman Debnath ◽  
Anirban Banik ◽  
Tarun Kanti Bandyopadhyay ◽  
Mrinmoy Majumder ◽  
Apu Kumar Saha
Keyword(s):  
Pressure Drop ◽  
Liquid Flow ◽  
Parametric Model ◽  
Newtonian Liquid ◽  
Flow Through ◽  
Non Parametric
Sign in / Sign up

Export Citation Format

Share Document