Data mining based damage identification using imperialist competitive algorithm and artificial neural network
Autor(a) principal: | |
---|---|
Data de Publicação: | 2018 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Latin American journal of solids and structures (Online) |
Texto Completo: | http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1679-78252018000800507 |
Resumo: | Abstract Currently, visual inspections for damage identification of structures are broadly used. However, they have two main drawbacks; time limitation and qualified manpower accessibility. Therefore, more precise and quicker technique is required to monitor the condition of structures. To aid the aim, a data mining based damage identification approach can be utilized to solve these drawbacks. In this study, to predict the damage severity of single-point damage scenarios of I-beam structures a data mining based damage identification framework and a hybrid algorithm combining Artificial Neural Network (ANN) and Imperial Competitive Algorithm (ICA), called ICA-ANN method, is proposed. ICA is employed to determine the initial weights of ANN. The efficiency coefficient and mean square error (MSE) are used to evaluate the performance of the ICA-ANN model. Moreover, the proposed model is compared with a pre-developed ANN approach in order to verify the efficiency of the proposed methodology. Based on the obtained results, it is concluded that the ICA-ANN indicates a better performance in detection of damage severity over the ANN method used only. |
id |
ABCM-1_ef2a3beee29c3c9e6b1d3327fb8ec4b9 |
---|---|
oai_identifier_str |
oai:scielo:S1679-78252018000800507 |
network_acronym_str |
ABCM-1 |
network_name_str |
Latin American journal of solids and structures (Online) |
repository_id_str |
|
spelling |
Data mining based damage identification using imperialist competitive algorithm and artificial neural networkStructural health monitoringdamage detectiondata miningartificial neural networkimperial competitive algorithmhybrid algorithmAbstract Currently, visual inspections for damage identification of structures are broadly used. However, they have two main drawbacks; time limitation and qualified manpower accessibility. Therefore, more precise and quicker technique is required to monitor the condition of structures. To aid the aim, a data mining based damage identification approach can be utilized to solve these drawbacks. In this study, to predict the damage severity of single-point damage scenarios of I-beam structures a data mining based damage identification framework and a hybrid algorithm combining Artificial Neural Network (ANN) and Imperial Competitive Algorithm (ICA), called ICA-ANN method, is proposed. ICA is employed to determine the initial weights of ANN. The efficiency coefficient and mean square error (MSE) are used to evaluate the performance of the ICA-ANN model. Moreover, the proposed model is compared with a pre-developed ANN approach in order to verify the efficiency of the proposed methodology. Based on the obtained results, it is concluded that the ICA-ANN indicates a better performance in detection of damage severity over the ANN method used only.Associação Brasileira de Ciências Mecânicas2018-01-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S1679-78252018000800507Latin American Journal of Solids and Structures v.15 n.8 2018reponame:Latin American journal of solids and structures (Online)instname:Associação Brasileira de Engenharia e Ciências Mecânicas (ABCM)instacron:ABCM10.1590/1679-78254546info:eu-repo/semantics/openAccessGordan,MeisamRazak,Hashim AbdulIsmail,ZubaidahGhaedi,Khaledeng2018-08-20T00:00:00Zoai:scielo:S1679-78252018000800507Revistahttp://www.scielo.br/scielo.php?script=sci_serial&pid=1679-7825&lng=pt&nrm=isohttps://old.scielo.br/oai/scielo-oai.phpabcm@abcm.org.br||maralves@usp.br1679-78251679-7817opendoar:2018-08-20T00:00Latin American journal of solids and structures (Online) - Associação Brasileira de Engenharia e Ciências Mecânicas (ABCM)false |
dc.title.none.fl_str_mv |
Data mining based damage identification using imperialist competitive algorithm and artificial neural network |
title |
Data mining based damage identification using imperialist competitive algorithm and artificial neural network |
spellingShingle |
Data mining based damage identification using imperialist competitive algorithm and artificial neural network Gordan,Meisam Structural health monitoring damage detection data mining artificial neural network imperial competitive algorithm hybrid algorithm |
title_short |
Data mining based damage identification using imperialist competitive algorithm and artificial neural network |
title_full |
Data mining based damage identification using imperialist competitive algorithm and artificial neural network |
title_fullStr |
Data mining based damage identification using imperialist competitive algorithm and artificial neural network |
title_full_unstemmed |
Data mining based damage identification using imperialist competitive algorithm and artificial neural network |
title_sort |
Data mining based damage identification using imperialist competitive algorithm and artificial neural network |
author |
Gordan,Meisam |
author_facet |
Gordan,Meisam Razak,Hashim Abdul Ismail,Zubaidah Ghaedi,Khaled |
author_role |
author |
author2 |
Razak,Hashim Abdul Ismail,Zubaidah Ghaedi,Khaled |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Gordan,Meisam Razak,Hashim Abdul Ismail,Zubaidah Ghaedi,Khaled |
dc.subject.por.fl_str_mv |
Structural health monitoring damage detection data mining artificial neural network imperial competitive algorithm hybrid algorithm |
topic |
Structural health monitoring damage detection data mining artificial neural network imperial competitive algorithm hybrid algorithm |
description |
Abstract Currently, visual inspections for damage identification of structures are broadly used. However, they have two main drawbacks; time limitation and qualified manpower accessibility. Therefore, more precise and quicker technique is required to monitor the condition of structures. To aid the aim, a data mining based damage identification approach can be utilized to solve these drawbacks. In this study, to predict the damage severity of single-point damage scenarios of I-beam structures a data mining based damage identification framework and a hybrid algorithm combining Artificial Neural Network (ANN) and Imperial Competitive Algorithm (ICA), called ICA-ANN method, is proposed. ICA is employed to determine the initial weights of ANN. The efficiency coefficient and mean square error (MSE) are used to evaluate the performance of the ICA-ANN model. Moreover, the proposed model is compared with a pre-developed ANN approach in order to verify the efficiency of the proposed methodology. Based on the obtained results, it is concluded that the ICA-ANN indicates a better performance in detection of damage severity over the ANN method used only. |
publishDate |
2018 |
dc.date.none.fl_str_mv |
2018-01-01 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1679-78252018000800507 |
url |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1679-78252018000800507 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1590/1679-78254546 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
text/html |
dc.publisher.none.fl_str_mv |
Associação Brasileira de Ciências Mecânicas |
publisher.none.fl_str_mv |
Associação Brasileira de Ciências Mecânicas |
dc.source.none.fl_str_mv |
Latin American Journal of Solids and Structures v.15 n.8 2018 reponame:Latin American journal of solids and structures (Online) instname:Associação Brasileira de Engenharia e Ciências Mecânicas (ABCM) instacron:ABCM |
instname_str |
Associação Brasileira de Engenharia e Ciências Mecânicas (ABCM) |
instacron_str |
ABCM |
institution |
ABCM |
reponame_str |
Latin American journal of solids and structures (Online) |
collection |
Latin American journal of solids and structures (Online) |
repository.name.fl_str_mv |
Latin American journal of solids and structures (Online) - Associação Brasileira de Engenharia e Ciências Mecânicas (ABCM) |
repository.mail.fl_str_mv |
abcm@abcm.org.br||maralves@usp.br |
_version_ |
1754302889643212800 |