Application of artificial neural networks in the damage identification of structural elements

Journal Title: Computer Assisted Methods in Engineering and Science - Year 2011, Vol 18, Issue 3

Abstract

The paper presents a structure test system developed for monitoring structural health, and discusses the results of laboratory experiments conducted on notched strip specimens made of various materials (aluminium, steel, Plexiglas). The system takes advantage of elastic wave signals actuated and sensed by a surface-mounted piezoelectric transducers. The structure responses recorded are then subjected to a procedure of signal processing and feature's extraction, which includes digital filters, wavelets decomposition, Principal Components Analysis (PCA), Fast Fourier Transformation (FFT), etc. A pattern database defined was used to train artificial neural networks and to establish a structure diagnosis system. As a consequence, two levels of damage identification problem were performed: novelty detection and damage evaluation. The system"s accuracy and reliability were verified on the basis of experimental data. The results obtained have proved that the system can be used for the analysis of simple as well as complex signals of elastic waves and it can operate as an automatic Structure Health Monitoring system.

Authors and Affiliations

Piotr Nazarko, Leonard Ziemiański

Keywords

Related Articles

The quality of numerical modelling of the flow around two buildings with different heights. (Received in the final form February 9, 2010)

The paper is devoted to the problems with quality of numerical modeling for two-dimensional incompressible flow around two models of buildings with different heights. The calculations have been made with use of the turbu...

Numerical analysis of tissue heating using the bioheat transfer porous model

The paper concerns the modelling of artificial hyperthermia. The 3D domain including healthy tissue and tumor region is considered. Heat transfer processes proceeding in this domain are described by the Pennes model and...

Stress analysis of linear elastic structures by the fast multipole boundary element method. (Received in the final form January 15, 2010)

In this paper a fast multipole boundary element method (FMBEM) analysis of internal stress in twodimensional linear elastic structures is presented. The expansions of the potentials occurring in the stress integral equat...

Root finding method for problems of elastodynamics. (Received in the final form February 24, 2010)

This paper presents a simple and efficient method for finding complex roots of dispersion equations occurring in many problems of elastodynamics. The method is characterized by high accuracy in root finding and absence o...

Effective thermal conductivity of porous materials and composites as a function of fundamental structural parameters

We conducted thermal conductivity investigations by homogenization. This method can effectively model structural features such as pores within dispersed particle architectures via a finite element mesh. We investigated t...

Download PDF file
  • EP ID EP73977
  • DOI -
  • Views 144
  • Downloads 0

How To Cite

Piotr Nazarko, Leonard Ziemiański (2011). Application of artificial neural networks in the damage identification of structural elements. Computer Assisted Methods in Engineering and Science, 18(3), 175-189. https://europub.co.uk/articles/-A-73977