Ant lion optimisation algorithm for structural damage detection using vibration data

2018 ◽  
Vol 9 (1) ◽  
pp. 117-136 ◽  
Author(s):  
Mayank Mishra ◽  
Swarup Kumar Barman ◽  
Damodar Maity ◽  
Dipak Kumar Maiti
Keyword(s):  
Damage Detection ◽  
Structural Damage ◽  
Structural Damage Detection ◽  
Vibration Data ◽  
Optimisation Algorithm ◽  
Ant Lion

VIBRATION-BASED STRUCTURAL DAMAGE DETECTION UNDER VARYING TEMPERATURE CONDITIONS

2013 ◽  
Vol 13 (05) ◽  
pp. 1250082 ◽  
Author(s):  
XIAO-QING ZHOU ◽  
WEN HUANG
Keyword(s):  
Damage Detection ◽  
Structural Damage ◽  
Natural Frequencies ◽  
Environmental Changes ◽  
Model Updating ◽  
Modal Testing ◽  
Structural Damage Detection ◽  
Vibration Data ◽  
Temperature Conditions ◽  
Vibration Properties

In vibration-based structural damage detection, it is necessary to discriminate the variation of structural properties due to environmental changes from those caused by structural damages. The present paper aims to investigate the temperature effect on vibration-based structural damage detection in which the vibration data are measured under varying temperature conditions. A simply-supported slab was tested in laboratory to extract the vibration properties with modal testing. The slab was then damaged and the modal testing was conducted again, in which the temperature varied. The modal data measured under different temperature conditions were used to detect the damage with a two-stage model updating technique. Some damage was falsely detected if the temperature variation was not considered. Natural frequencies were then corrected to those under the same temperature conditions according to the relation between the temperature and material modulus. It is shown that all of the damaged elements can be accurately identified.

Vibration-based damage detection for bridges by deep convolutional denoising autoencoder

2020 ◽  
pp. 147592172094283 ◽  
Author(s):  
Zhiqiang Shang ◽  
Limin Sun ◽  
Ye Xia ◽  
Wei Zhang
Keyword(s):  
Neural Networks ◽  
Damage Detection ◽  
Correlation Functions ◽  
Structural Damage ◽  
Cross Correlation ◽  
Deep Neural Networks ◽  
Beam Model ◽  
Structural Damage Detection ◽  
Denoising Autoencoder ◽  
Vibration Data

One of the main challenges for structural damage detection using monitoring data is to acquire features that are sensitive to damages but insensitive to noise (e.g. sensor measurement noise) as well as environmental and operational effects (e.g. temperature effect). Inspired by the capabilities of deep learning methods in representation learning, various deep neural networks have been developed to obtain effective damage features from raw vibration data. However, most of the available deep neural networks are supervised, resulting in practical difficulties owing to the lack of damage labels. This article proposes a damage detection strategy based on an unsupervised deep neural network, referred to as deep convolutional denoising autoencoder, which accepts multi-dimensional cross-correlation functions as input. The strategy aims to extract damage features from field measurements of undamaged structures under the influence of noise and temperature uncertainties. In the proposed strategy, cross-correlation functions of vibration data are first calculated as basic features; then deep convolutional denoising autoencoder is developed to reconstruct cross-correlation functions from their noise-corrupted versions to extract desired features; exponentially weighted moving average control charts are finally established for these features to identify minor structural damages. The strategy is evaluated through a numerical simply supported beam model and an experimental continuous beam model. The mechanism of deep convolutional denoising autoencoder to extract damage features is interpreted by visualizing feature maps of convolutional layers in the encoder. It is found that these layers perform rough estimations of modal properties and preserve the damage information as the general trend of these properties in multiple extra frequency bands. The results show that the proposed strategy is competent for structural damage detection under the exposed environment and worth further exploring its capabilities in applications of real bridges.

A hybrid ant lion optimizer with improved Nelder–Mead algorithm for structural damage detection by improving weighted trace lasso regularization

2019 ◽  
Vol 23 (3) ◽  
pp. 468-484 ◽  
Author(s):  
Chengbin Chen ◽  
Ling Yu
Keyword(s):  
Damage Detection ◽  
Objective Function ◽  
Hybrid Algorithm ◽  
Structural Damage ◽  
Heuristic Algorithms ◽  
Structural Damage Detection ◽  
Ant Lion Optimizer ◽  
Computing Performance ◽  
Ant Lion ◽  
Nelder Mead Algorithm

Structural damage detection is the kernel technique in deploying structural health monitoring. The structural damage–detection technique using heuristic algorithms has been developed at an astounding pace over the past years. However, some existing structural damage–detection methods are prone to easily fall into the local optimum and to be unstable when they are applied to complex structures. In order to make full use of advantages of heuristic algorithms and overcome abovementioned shortcomings, a hybrid algorithm, which combines the ant lion optimizer with an improved Nelder–Mead algorithm, is proposed to solve the constrained optimization problem of complex structural damage detection. First, an objective function is established for damage identification using structural modal parameters, that is, frequencies and mode shapes. The solution to the objective function is accurately attained by a newly improved weighted trace lasso which can improve the computing performance and stability of procedure and reduce randomness of weighted coefficients. After assessing the computing performance of the proposed hybrid algorithm using three classical mathematical benchmark functions, two structural damage–detection numerical simulations and a laboratory verification are then conducted to fully assess the structural damage–detection capability of the proposed method. Meanwhile, the equivalent element stiffness-reduction model is introduced to estimate the real damage severities of cracks which are created in laboratory structures and to compare with the structural damage–detection results by the proposed method. The illustrated results show that the proposed hybrid algorithm can locate damage and quantify damage severity more accurately and stably with a good robustness to noise.

Sign in / Sign up

Export Citation Format

Share Document