An improved multi-objective genetic algorithm and data fusion in structural damage identification

Yu, Along; Ji, ajia; Sun, Shiyu

doi:10.1504/ijsn.2019.100087

Cited by 5 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e interest of the scientific community in damage identification is highlighted by the great variety of presented computational procedures such as genetic algorithms [32][33][34], metaheuristic algorithms [35], particle swarm optimization [36], fuzzy cognitive maps [37], digital image correlation [38], vision-based measurements [39], neural networks [40], and wavelet analysis [41].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On Damage Identification in Planar Frames of Arbitrary Size

Fiore

Greco

Pluchino

2022

Shock and Vibration

View full text Add to dashboard Cite

Framed structures are deeply studied in civil engineering since they provide a numerical model for the analysis of the static and dynamic response of multi-storey buildings. In order to evaluate the vibrational properties of these structures, an eigen-problem, which involves the stiffness and mass matrices of the frame, must be solved. Both matrices can be assembled by means of standard methods, which take into account the numbers of degrees of freedom of the frame. The occurrence of concentrated damage in some vulnerable sections modifies the degrees of freedom and therefore both the stiffness and mass matrices. Very often, the critical sections are located in the joints between the structural elements of the frame where the bending moment reaches its maximum value. Assuming that the joints are rigid in the undamaged configuration of the frame, it is possible to take into account their loss of stiffness due to the presence of eventual damage by means of hinges with rotational springs of variable rigidity. In this paper, an original algorithm that allows us to evaluate the stiffness and mass matrices and therefore the natural frequencies of vibration of undamaged and damaged planar frames with an arbitrary number of beams and columns is presented. The proposed algorithm for the stiffness and mass matrices determination requires a few input data which can be provided in a text file and therefore allows us to speed up the procedure with respect to the application of an FEM approach which requires the construction of single models for each considered frame. The results obtained by means of the proposed algorithm have been validated through a comparison with those provided by an FEM model implemented in SAP2000. The natural frequencies obtained by means of the proposed approach are used for the solution of two different inverse problems, which concern the identification of, respectively, the mechanical characteristics of the constitutive material and the location and intensity of the damage. Both the proposed identification procedures deal with optimization algorithms that are based on opportune fitness functions. Applications to frames of different size confirm the validity of the presented identification algorithms. Furthermore, an iterative procedure, able to reduce the required computational burden related to the identification of the location and intensity of damage, is presented and applied in a parametric study concerning frames with increasing size.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Some contributions on crack modeling approaches and their effects on the response of beams can be found in [45,46]. Several papers consider the joints between beams and columns as possible damage locations [33,[47][48][49].…”

Section: Introductionmentioning

confidence: 99%

On Damage Identification in Planar Frames of Arbitrary Size

Fiore

Greco

Pluchino

2022

Shock and Vibration

View full text Add to dashboard Cite

show abstract

“…Other machine learning techniques such as support vector machine (SVM) [11][12][13], fuzzy neural network (FNN) [14,15], optimization algorithms such as genetic algorithm (GA) [16][17][18][19], multiverse optimizer (MVO) algorithm [20], and grey wolf optimization (GWO) algorithm [21] have also been used in SHM and damage detection of civil structures.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Structural Damage Detection Technique Based on a Deep Convolutional Autoencoder

Rastin

Amiri

Darvishan

2021

Shock and Vibration

View full text Add to dashboard Cite

Structural health monitoring (SHM) is a hot research topic with the main purpose of damage detection in a structure and assessing its health state. The major focus of SHM studies in recent years has been on developing vibration-based damage detection algorithms and using machine learning, especially deep learning-based approaches. Most of the deep learning-based methods proposed for damage detection in civil structures are based on supervised algorithms that require data from the healthy state and different damaged states of the structure in the training phase. As it is not usually possible to collect data from damaged states of a large civil structure, using such algorithms for these structures may be impractical. This paper proposes a new unsupervised deep learning-based method for structural damage detection based on convolutional autoencoders (CAEs). The main objective of the proposed method is to identify and quantify structural damage using a CAE network that employs raw vibration signals from the structure and is trained by the signals solely acquired from the healthy state of the structure. The CAE is chosen to take advantage of high feature extraction capability of convolution layers and at the same time use the advantages of an autoencoder as an unsupervised algorithm that does not need data from damaged states in the training phase. Applications on the two numerical models of IASC-ASCE benchmark structure and a grid structure located at the University of Central Florida, as well as the full-scale Tianjin Yonghe Bridge, prove the efficiency of the proposed algorithm in assessing the global health state of the structures and quantifying the damage.

show abstract

“…3) Multi-data fusion methods. By combining data from diverse sources, such as SAR, LiDAR, optical cameras, and geographical information system (GIS) data, some complex and detailed information on building damage can be accurately extracted [18]. Although these fusion methods have brought some improvements to the extraction of building damage information, several issues need to be resolved.…”

Section: Introductionmentioning

confidence: 99%