Damage Detection in Flat Panels by Guided Waves Based Artificial Neural Network Trained through Finite Element Method

Artificial Neural Networks (ANNs) have rapidly emerged as a promising tool to solve damage identification and localization problem, according to a Structural Health Monitoring approach. Finite Element (FE) Analysis can be extremely helpful, especially for reducing the laborious experimental campaign costs for the ANN development and training phases. The aim of the present work is to propose a guided wave-based ANN, developed through the use of the Finite Element Method, to determine the position of damages. The paper first addresses the development and assessment of the modeling technique. The FE model accuracy was proven through the comparison of the predicted results with experimental and analytical data. Then, the ANN was developed and trained on an aluminum plate and subsequently verified in a composite plate, as well as under different damage configurations. According to the results herein proposed, the ANN allowed to detect and localize damages with a high level of accuracy in all cases of study.

Download Full-text

CALCULATION OF DISPERSION CURVES FOR ARBITRARY WAVEGUIDES USING FINITE ELEMENT METHOD

International Journal of Applied Mechanics ◽

10.1142/s1758825114500598 ◽

2014 ◽

Vol 06 (05) ◽

pp. 1450059 ◽

Cited By ~ 5

Author(s):

KAIGE ZHU ◽

DAINING FANG

Keyword(s):

Finite Element Method ◽

Finite Element ◽

Guided Waves ◽

Dispersion Curves ◽

Guided Wave ◽

Sandwich Plates ◽

Multilayered Structures ◽

Finite Element Software ◽

Honeycomb Sandwich ◽

Element Method

Dispersion curves for waveguide structures are an important prerequisite for the implementation of guided wave-based nondestructive evaluation (NDE) approach. Although many methods exist, each method is only applicable to a certain type of structures, and also requires complex programming. A Bloch theorem-based finite element method (FEM) is proposed to obtain dispersion curves for arbitrary waveguides using commercial finite element software in this paper Dispersion curves can be obtained for a variety of structures, such as homogeneous plates, multilayered structures, finite cross section rods and honeycomb sandwiches. The propagation of guided waves in honeycomb sandwich plates and beams are discussed in detail. Then, dispersion curves for honeycomb sandwich beams are verified by experiments.

Download Full-text

Aspects of a Hybrid Analytical Finite Element Method Approach for Ultrasonic Guided Wave Inspection Design

Journal of Nondestructive Evaluation Diagnostics and Prognostics of Engineering Systems ◽

10.1115/1.4037573 ◽

2017 ◽

Vol 1 (1) ◽

Cited By ~ 2

Author(s):

Joseph L. Rose

Keyword(s):

Finite Element Method ◽

Finite Element ◽

Guided Waves ◽

Wave Structure ◽

Guided Wave ◽

Ultrasonic Guided Wave ◽

Inspection Systems ◽

Actuator Design ◽

Wave Problems ◽

Element Method

A strategy is presented here to develop guided wave inspection systems using short-range ultrasonic guided waves. A hybrid analytical finite element method (FEM) is presented. The importance of dispersion curve computation, wave structure analysis in the test part, actuator design, the establishment of appropriate boundary conditions from the actuator design to be used in any FEM computations leading to key experiments, and aspects of system design are discussed. Several interesting problems reported by the author in previous publications are used here to stress the importance of mode and frequency choice when solving guided wave problems.

Download Full-text

Acoustic emission propagation characteristics in plate structure with various materials, cracks and coating metal

Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science ◽

10.1177/0954406215627822 ◽

2016 ◽

Vol 231 (11) ◽

pp. 2080-2088

Author(s):

Kuanfang He ◽

Zhi Tan ◽

Yong Cheng ◽

Xuejun Li

Keyword(s):

Finite Element Method ◽

Finite Element ◽

Acoustic Emission ◽

Guided Waves ◽

Propagation Characteristic ◽

Guided Wave ◽

Propagation Characteristics ◽

The Finite Element Method ◽

Plate Structure ◽

Element Method

The propagation characteristic of guided waves is important to acoustic emission nondestructive detection for the structural integrity of engineering components. The finite element method is introduced to study the propagation of guided waves in plate structure with different materials, cracks and coating metal. The displacement contours and wave curve at different receiving positions are examined first for the propagation characteristics of guided waves in plate structure with different homogeneous material of steel 45 and GCr15. Next, the interface reflection, refraction and diffraction characteristics of guided waves in plate structure with cracks and steel 45 with coating metal of aluminium 2024 are investigated. Finally, these FE results are compared with the mechanical pencil lead fracture experiment results. The results of this study clearly illustrate the accuracy and reasonableness of the finite element method to predict propagation characteristic of guided wave.

Download Full-text

Localization of a harmonic excitation load in a bi-clamped beam using finite element method and artificial neural network

10.26678/abcm.cobem2019.cob2019-0629 ◽

2019 ◽

Author(s):

Otavio Duarte Zotelli Boaventura ◽

Daniel Henrique de Sousa Obata ◽

Matheus Proença ◽

Amarildo Tabone Paschoalini

Keyword(s):

Neural Network ◽

Finite Element Method ◽

Artificial Neural Network ◽

Finite Element ◽

Harmonic Excitation ◽

Artificial Neural ◽

Element Method

Download Full-text

Structural Damage Identification Based on Integrated Utilization of Inverse Finite Element Method and Pseudo-Excitation Approach

Sensors ◽

10.3390/s21020606 ◽

2021 ◽

Vol 21 (2) ◽

pp. 606

Author(s):

Tengteng Li ◽

Maosen Cao ◽

Jianle Li ◽

Lei Yang ◽

Hao Xu ◽

...

Keyword(s):

Finite Element Method ◽

Finite Element ◽

Structural Damage ◽

Damage Identification ◽

Displacement Measurement ◽

Engineering Practice ◽

Position Measurement ◽

Inverse Finite Element Method ◽

Pseudo Excitation ◽

Element Method

The attempt to integrate the applications of conventional structural deformation reconstruction strategies and vibration-based damage identification methods is made in this study, where, more specifically, the inverse finite element method (iFEM) and pseudo-excitation approach (PE) are combined for the first time, to give rise to a novel structural health monitoring (SHM) framework showing various advantages, particularly in aspects of enhanced adaptability and robustness. As the key component of the method, the inverse finite element method (iFEM) enables precise reconstruction of vibration displacements based on measured dynamic strains, which, as compared to displacement measurement, is much more adaptable to existing on-board SHM systems in engineering practice. The PE, on the other hand, is applied subsequently, relying on the reconstructed displacements for the identification of structural damage. Delamination zones in a carbon fibre reinforced plastic (CFRP) laminate are identified using the developed method. As demonstrated by the damage detection results, the iFEM-PE method possesses apparently improved accuracy and significantly enhanced noise immunity compared to the original PE approach depending on displacement measurement. Extensive parametric study is conducted to discuss the influence of a variety of factors on the effectiveness and accuracy of damage identification, including the influence of damage size and position, measurement density, sensor layout, vibration frequency and noise level. It is found that different factors are highly correlated and thus should be considered comprehensively to achieve optimal detection results. The application of the iFEM-PE method is extended to better adapt to the structural operational state, where multiple groups of vibration responses within a wide frequency band are used. Hybrid data fusion is applied to process the damage index (DI) constructed based on the multiple responses, leading to detection results capable of indicating delamination positions precisely.

Download Full-text

Guided Wave Focusing Mechanics in Pipe

Ultrasonic Nondestructive Evaluation for Material Science and Industries ◽

10.1115/pvp2003-1850 ◽

2003 ◽

Author(s):

Takahiro Hayashi ◽

Koichiro Kawashima ◽

Zongqi Sun ◽

Joseph L. Rose

Keyword(s):

Finite Element Method ◽

Finite Element ◽

Guided Waves ◽

Wave Structure ◽

Guided Wave ◽

Pipe Inspection ◽

Specific Point ◽

Wave Focusing ◽

Beam Focusing ◽

Subsequent Time

Guided waves can be used in pipe inspection over long distances. Presented in this paper is a beam focusing technique to improve the S/N ratio of the reflection from a tiny defect. Focusing is accomplished by using non-axisymmetric waveforms and subsequent time delayed superposition at a specific point in a pipe. A semi-analytical finite element method is used to present wave structure in the pipe. Focusing potential is also studied with various modes and frequencies.

Download Full-text

Optimization of a thin-walled element geometry using a system integrating neural networks and finite element method

Archives of Metallurgy and Materials ◽

10.1515/amm-2017-0067 ◽

2017 ◽

Vol 62 (1) ◽

pp. 435-442 ◽

Cited By ~ 4

Author(s):

P. Golewski ◽

J. Gajewski ◽

T. Sadowski

Keyword(s):

Neural Networks ◽

Finite Element Method ◽

Finite Element ◽

Artificial Neural Networks ◽

Integrated System ◽

Multilayer Perceptrons ◽

Optimization Of Geometry ◽

Thin Walled ◽

Artificial Neural ◽

Element Method

Abstract Artificial neural networks [ANNs] are an effective method for predicting and classifying variables. This article presents the application of an integrated system based on artificial neural networks and calculations by the finite element method [FEM] for the optimization of geometry of a thin-walled element of an air structure. To ensure optimal structure, the structure’s geometry was modified by creating side holes and ribs, also with holes. The main criterion of optimization was to reduce the structure’s weight at the lowest possible deformation of the tested object. The numerical tests concerned a fragment of an elevator used in the “Bryza” aircraft. The tests were conducted for networks with radial basis functions [RBF] and multilayer perceptrons [MLP]. The calculations described in the paper are an attempt at testing the FEM - ANN system with respect to design optimization.

Download Full-text