Output-only methods for damage identification in structural health monitoring
In the structural health monitoring (SHM) field, vibration-based damage identification has become a crucial research area due to its potential to be applied in real-world engineering structures. Assuming that the vibration signals can be measured by employing different types of monitoring systems, w...
| Autor principal: | SANTOS, Adam Dreyton Ferreira dos |
|---|---|
| Grau: | Tese |
| Idioma: | eng |
| Publicado em: |
Universidade Federal do Pará
2017
|
| Assuntos: | |
| Acesso em linha: |
http://repositorio.ufpa.br/jspui/handle/2011/9076 |
| id |
ir-2011-9076 |
|---|---|
| recordtype |
dspace |
| spelling |
ir-2011-90762021-10-22T13:57:53Z Output-only methods for damage identification in structural health monitoring SANTOS, Adam Dreyton Ferreira dos COSTA, João Crisóstomo Weyl Albuquerque http://lattes.cnpq.br/9622051867672434 FIGUEIREDO, Elói João Faria http://lattes.cnpq.br/2315380423001185 Aprendizado de máquina Monitoramento de integridade estrutural Identificação de danos Monitoramento de integridade estrutural Condições ambientais Machine learning Structural health monitoring Damage identification Environmental conditions CNPQ::ENGENHARIAS::ENGENHARIA ELETRICA CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO In the structural health monitoring (SHM) field, vibration-based damage identification has become a crucial research area due to its potential to be applied in real-world engineering structures. Assuming that the vibration signals can be measured by employing different types of monitoring systems, when one applies appropriate data treatment, damage-sensitive features can be extracted and used to assess early and progressive structural damage. However, real-world structures are subjected to regular changes in operational and environmental conditions (e.g., temperature, relative humidity, traffic loading and so on) which impose difficulties to identify structural damage as these changes influence different features in a distinguish manner. In this thesis by papers, to overcome this drawback, novel output-only methods are proposed for detecting and quantifying damage on structures under unmeasured operational and environmental influences. The methods are based on the machine learning and artificial intelligence fields and can be classified as kernel- and cluster-based techniques. When the novel methods are compared to the state-of-the-art ones, the results demonstrated that the former ones have better damage detection performance in terms of false-positive (ranging between 3.65.4%) and false-negative (ranging between 0-2.6%) indications of damage, suggesting their applicability for real-world SHM solutions. If the proposed methods are compared to each other, the cluster-based ones, namely the global expectation-maximization approaches based on memetic algorithms, proved to be the best techniques to learn the normal structural condition, without loss of information or sensitivity to the initial parameters, and to detect damage (total errors equal to 4.4%). CNPq - Conselho Nacional de Desenvolvimento Científico e Tecnológico No campo da monitorização de integridade estrutural (SHM), a identificação de dano baseada em vibração tem se tornado uma área de pesquisa crucial devido a sua potencial aplicação em estruturas de engenharia do mundo real. Assumindo que os sinais de vibração podem ser medidos pelo emprego de diferentes tipos de sistemas de monitorização, quando aplica-se o tratamento de dados adequado, as características sensíveis a dano podem ser extraídas e usadas para avaliar dano estrutural incipiente ou progressivo. Entretanto, as estruturas do mundo real estão sujeitas às mudanças regulares nas condições operacionais e ambientais (e.g., temperatura, umidade relativa, massa de tráfego e outros), as quais impõem dificuldades na identificação do dano estrutural uma vez que essas mudanças influenciam diferentes características de forma distinta. Nesta tese por agregação de artigos, a fim de superar essa limitação, novos métodos output-only são propostos para detectar e quantificar dano em estruturas sob influências operacionais e ambientais não medidas. Os métodos são baseados nos campos de aprendizagem de máquina e inteligência artificial e podem ser classificados como técnicas baseadas em kernel e clusterização. Quando os novos métodos são comparados àqueles do estado da arte, os resultados demonstraram que os primeiros possuem melhor performance de detecção de dano em termos de indicações de dano falso-positivas (variando entre 3,6Ű5,4%) e falso-negativas (variando entre 0Ű2,6%), sugerindo potencial aplicabilidade em soluções práticas de SHM. Se os métodos propostos são comparados entre si, aqueles baseados em clusterização, nomeadamente as abordagens de expectância-maximização global via algoritmos meméticos, provaram ser as melhores técnicas para aprender a condição estrutural normal, sem perda de informação ou sensibilidade aos parâmetros iniciais, e para detectar dano (erros totais iguais a 4,4%). 2017-09-13T12:17:43Z 2017-09-13T12:17:43Z 2017-04-27 Tese SANTOS, Adam Dreyton Ferreira dos. Output-only methods for damage identification in structural health monitoring. Orientador: João Crisóstomo Weyl Albuquerque Costa; Elói João Faria Figueiredo. 2017. 149 f. Tese (Doutorado em Engenharia Elétrica.) - Instituto de Tecnologia, Universidade Federal do Pará, Belém, 2017. Disponível em: http://repositorio.ufpa.br/jspui/handle/2011/9076. Acesso em:. http://repositorio.ufpa.br/jspui/handle/2011/9076 eng Acesso Aberto application/pdf Universidade Federal do Pará Brasil Instituto de Tecnologia UFPA Programa de Pós-Graduação em Engenharia Elétrica |
| institution |
Repositório Institucional - Universidade Federal do Pará |
| collection |
RI-UFPA |
| language |
eng |
| topic |
Aprendizado de máquina Monitoramento de integridade estrutural Identificação de danos Monitoramento de integridade estrutural Condições ambientais Machine learning Structural health monitoring Damage identification Environmental conditions CNPQ::ENGENHARIAS::ENGENHARIA ELETRICA CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO |
| spellingShingle |
Aprendizado de máquina Monitoramento de integridade estrutural Identificação de danos Monitoramento de integridade estrutural Condições ambientais Machine learning Structural health monitoring Damage identification Environmental conditions CNPQ::ENGENHARIAS::ENGENHARIA ELETRICA CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO SANTOS, Adam Dreyton Ferreira dos Output-only methods for damage identification in structural health monitoring |
| topic_facet |
Aprendizado de máquina Monitoramento de integridade estrutural Identificação de danos Monitoramento de integridade estrutural Condições ambientais Machine learning Structural health monitoring Damage identification Environmental conditions CNPQ::ENGENHARIAS::ENGENHARIA ELETRICA CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO |
| description |
In the structural health monitoring (SHM) field, vibration-based damage identification has become a crucial research area due to its potential to be applied in real-world engineering structures. Assuming that the vibration signals can be measured by employing different types of monitoring systems, when one applies
appropriate data treatment, damage-sensitive features can be extracted and used to assess early and progressive structural damage. However, real-world structures are subjected to regular changes in operational and environmental conditions (e.g., temperature, relative humidity, traffic loading and so on) which impose difficulties to identify structural damage as these changes influence different features in a distinguish manner. In this thesis by papers, to overcome this drawback, novel output-only methods are proposed for detecting and quantifying damage on structures under unmeasured operational and environmental influences. The methods are based on the machine learning and artificial intelligence fields and can be classified as kernel- and cluster-based techniques. When the novel methods are compared to the state-of-the-art ones, the results demonstrated that the former ones have better damage detection performance in terms of false-positive (ranging between 3.65.4%) and false-negative (ranging between 0-2.6%) indications of damage, suggesting their applicability for real-world SHM solutions. If the proposed methods are compared to each other, the cluster-based ones, namely the global expectation-maximization approaches based on memetic algorithms, proved to be the best techniques to learn the normal structural condition, without loss of information or sensitivity to the initial parameters, and to detect damage (total errors equal to 4.4%). |
| author_additional |
COSTA, João Crisóstomo Weyl Albuquerque |
| author_additionalStr |
COSTA, João Crisóstomo Weyl Albuquerque |
| format |
Tese |
| author |
SANTOS, Adam Dreyton Ferreira dos |
| title |
Output-only methods for damage identification in structural health monitoring |
| title_short |
Output-only methods for damage identification in structural health monitoring |
| title_full |
Output-only methods for damage identification in structural health monitoring |
| title_fullStr |
Output-only methods for damage identification in structural health monitoring |
| title_full_unstemmed |
Output-only methods for damage identification in structural health monitoring |
| title_sort |
output-only methods for damage identification in structural health monitoring |
| publisher |
Universidade Federal do Pará |
| publishDate |
2017 |
| url |
http://repositorio.ufpa.br/jspui/handle/2011/9076 |
| _version_ |
1832603296667271168 |
| score |
11.755432 |