Prediction of crack depth and position in vibrating beams using artificial neural networks

Q3 Engineering

Diagnostyka Pub Date : 2022-09-20 DOI:10.29354/diag/154758

A. Bouboulas, P. Nikolakopoulos, Nikolaos Anifantis

引用次数: 0

Abstract

The aim of this paper is to develop a finite element procedure for crack prediction in vibrating beams. Based on this procedure, full frictional contact conditions are introduced between the crack surfaces in order to consider the breathing of crack. The region surrounding the crack is simulated by two-dimensional finite elements. An incremental-iterative procedure is employed to solve the nonlinear dynamic equations governing this problem. The obtained time response is processed with Fast Fourier Transform to extract its frequency components. The first three natural frequencies are input to a trained Artificial Neural Network for depth and position prediction of the crack. This study is validated for a dynamic loading cantilever beam. It is found that the proposed procedure is capable of predicting the crack depth and position with high accuracy.

查看原文本刊更多论文

用人工神经网络预测振动梁裂纹深度和位置

本文的目的是开发一种振动梁裂纹预测的有限元程序。在此基础上，为了考虑裂纹的呼吸，在裂纹表面之间引入了完全摩擦接触条件。采用二维有限元法对裂纹周围区域进行了模拟。采用增量迭代法求解了控制该问题的非线性动力学方程。对得到的时间响应进行快速傅里叶变换，提取其频率分量。将前三个固有频率输入到训练好的人工神经网络中，用于裂缝的深度和位置预测。该研究在动载荷悬臂梁上得到了验证。结果表明，该方法能够较准确地预测裂纹的深度和位置。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Diagnostyka Engineering-Mechanical Engineering

CiteScore

2.20

自引率

0.00%

发文量

期刊介绍： Diagnostyka – is a quarterly published by the Polish Society of Technical Diagnostics (PSTD). The journal “Diagnostyka” was established by the decision of the Presidium of Main Board of the Polish Society of Technical Diagnostics on August, 21st 2000 and replaced published since 1990 reference book of the PSTD named “Diagnosta”. In the years 2000-2003 there were issued annually two numbers of the journal, since 2004 “Diagnostyka” is issued as a quarterly. Research areas covered include: -theory of the technical diagnostics, -experimental diagnostic research of processes, objects and systems, -analytical, symptom and simulation models of technical objects, -algorithms, methods and devices for diagnosing, prognosis and genesis of condition of technical objects, -methods for detection, localization and identification of damages of technical objects, -artificial intelligence in diagnostics, neural nets, fuzzy systems, genetic algorithms, expert systems, -application of technical diagnostics, -diagnostic issues in mechanical and civil engineering, -medical and biological diagnostics with signal processing application, -structural health monitoring, -machines, -noise and vibration, -analysis of technical and civil systems.