An effective damage identification approach in thick steel beams based on guided ultrasonic waves for structural health monitoring applications

Abstract

An inverse analysis using artificial intelligence based on the guided ultrasonic waves is proposed for effective identification of damage in thick steel beams for the purpose of structural health monitoring applications. Parameterized modeling for finite element analysis is applied to constitute the damage parameter database cost-effectively. For signal processing and feature extraction, wavelet transform is employed. A novel feature extraction technique, damage characteristic points, is applied to constitute the database for pattern recognition procedures. Using the extracted metrics, a multilayer feedforward artificial neural network under supervision of an error-backpropagation algorithm is developed and trained. The generalization performance of the artificial neural network has been examined experimentally. Results illustrate that the proposed metrics together with artificial neural network technique are powerful tools for effective identification of damage in the case of thick structures.

A semi-baseline damage identification approach for complex structures using energy ratio correction technique

“…In this article, instantaneous damage detection algorithm, which uses the CWT approach for measuring the differences between the recorded signals along every two equal actuator–sensor paths, is incorporated. Continuous wavelet transform, as a powerful time–frequency analysis technique, is one of the most popular signal processing tools used for identifying the varying characteristics of dispersive guided wave signals . The CWT of a guided wave signal is a transformation that decomposes every such waves into a superposition of both scale and translation of a mother wavelet function ψ ( t ) given by…”

An Efficient and Reliable Structural Health Monitoring System for Buildings after Earthquake

“…Recently Ou and Li [3] reviewed the application of SHM for building in China. Atashipour et al [4] investigated the use of guided wave to detect the presence of damage in thick steel beams.…”

Defect Recognition in Concrete Ultrasonic Detection Based on Wavelet Packet Transform and Stochastic Configuration Networks

“…In the study of hyperspectral images, the methods of extracting discriminative feature information based on local geometric structure Fisher analysis (LGSFA) [4] and local neighborhood structure preserving embedding (LNSPE) [5] effectively reduce the data dimension and improve the classification performance of the model. Mostavi et al used wavelet transform to analyze ultrasonic signals [6], thus establishing an effective method, and machine learning identifies the processed ultrasonic signals and achieves high recognition accuracy.Traditional machine learning algorithms such as neural network and support vector machine have been used in concrete ultrasonic detection signal recognition cases [7]- [9]. However, these algorithms are not of sufficient accuracy for identifying complex concrete defect signals.…”