Novelty detection based on elastic wave signals measured by different techniques
Journal Title: Computer Assisted Methods in Engineering and Science - Year 2012, Vol 19, Issue 4
Abstract
The paper discusses the results of laboratory experiments in which three independent measurement techniques were compared: a digital oscilloscope, phased array acquisition system, a laser vibrometer 3D. These techniques take advantage of elastic wave signals actuated and sensed by a surface-mounted piezoelectric transducers as well as non-contact measurements. In these experiments two samples of aluminum strips were investigated while the damage was modeled by drilling a hole. The structure responses recorded were then subjected to a procedure of signal processing, and features' extraction was done by Principal Components Analysis. A pattern database defined was used to train artificial neural networks for the purpose of damage detection.
Authors and Affiliations
Piotr Nazarko, Leonard Ziemiański
Keywords
Related Articles
- EP ID EP73950
- DOI -
- Views 178
- Downloads 0
Neural networks for the analysis of mine-induced building vibrations
A study of the capabilities of artificial neural networks in respect of selected problems of the analysis of mine-induced building vibrations is presented. Neural network technique was used for the prediction of building...
The efficiency of the application of the heap lists to the algorithm of mesh generation
The paper presents an analysis of the efficiency of the application of heap lists data structures to the 2D triangular mesh generation algorithms. Such efficiency is especially important for the frontal methods for which...
Neural network prediction of load capacity for eccentrically loaded reinforced concrete columns
This paper presents neural networks prediction of load capacity for eccentrically loaded reinforced concrete (RC) columns. The direct modelling of the load capacity of RC columns by means of the finite element method pre...
Computational mechanics of multiphase materials-modeling strategies at different scales
The paper addresses various scale-bridging modeling and discretization strategies for multiphase porous materials, starting with a micromechanics model for ion transport within the pore space to generate homogenized diff...
An improved Neural Kalman Filtering Algorithm in the analysis of cyclic behaviour of concrete specimens
The article is related to the results of research on Node Decoupled Extended Kalman Filtering (NDEKF) as a learning method for the training of Multilayer Perceptron (MPL). Developments of this method made by the author a...