Notícias

Banca de DEFESA: MOISES FELIPE MELLO DA SILVA

Uma banca de DEFESA de MESTRADO foi cadastrada pelo programa.
DISCENTE: MOISES FELIPE MELLO DA SILVA
DATA: 31/01/2017
HORA: 09:30
LOCAL: Auditório ITEC
TÍTULO:

MACHINE LEARNING ALGORITHMS FOR DAMAGE DETECTION IN STRUCTURES UNDER CHANGING NORMAL CONDITIONS


PALAVRAS-CHAVES:

Structural health monitoring, Damage detection, Deep learning, Clustering, Operational conditions, Environmental conditions


PÁGINAS: 74
GRANDE ÁREA: Engenharias
ÁREA: Engenharia Elétrica
RESUMO:

Engineering structures have played an important role into societies across the years. Manage and maintenance of such structures demand regular inspections, evaluations and controlling activities to derive the actual condition. However, these visual-based approaches still rely heavily dependent of qualitative evaluations, compromising the structural management and decision-making process. To avoid these problems, automated structural health monitoring systems appears as a natural research field, which aims to provide more reliable and quantitative information to the structural manager. Unfortunately, normal variations in structure dynamics, caused by operational and environmental conditions, can mask the existence of damage. In SHM, data normalization is referred as the process of filtering normal effects to provide a proper evaluation of structural health condition. In this context, many research efforts have been carried out to the development of machine learning algorithms to deal with normal variations and expose structural anomalies from time response data. Particularly, the approaches based on principal component analysis and clustering have been successfully employed to model the normal conditions of structures, even when severe effects of varying normal conditions impose difficulties to the damage detection. However, these traditional approaches imposes serious limitations to deployment in real-world monitoring campaigns, mainly due to the constraints related to data distribution and model parameters, as well as data normalization problems. This work aims to apply deep neural networks and propose a novel agglomerative cluster-based approach for data normalization in an effort to overcome the limitations imposed by traditional methods. Regarding deep networks, the employment of new training algorithms provide models with high generalization capabilities, able to learn, at same time, linear/nonlinear influences. On the other hand, the novel cluster-based approach does not require any input parameter, as well as none data distribution assumptions are made, allowing its enforcement on a wide range of applications. These novel algorithms are implemented in an outlier detection strategy to perform data normalization and damage detection using only measurements from baseline conditions. The superiority of the proposed approaches over state-of-the-art ones is attested on standard data sets from monitoring systems installed on two bridges: the Z-24 Bridge and the Tamar Bridge. Both techniques revealed to have better data normalization and classification performance than the alternative ones in terms of false-positive and false-negative indications of damage, suggesting their applicability for real-world structural health monitoring scenarios.


MEMBROS DA BANCA:
Presidente - 2153181 - JOAO CRISOSTOMO WEYL ALBUQUERQUE COSTA
Interno - 3439716 - DIEGO LISBOA CARDOSO
Externo ao Programa - 1809092 - CLAUDOMIRO DE SOUZA DE SALES JUNIOR
Externo à Instituição - ELÓI JOÃO FARIA FIGUEIREDO
Notícia cadastrada em: 20/01/2017 10:16
SIGAA | Centro de Tecnologia da Informação e Comunicação (CTIC) - (91)3201-7793 | Copyright © 2006-2024 - UFPA - jatoba.ufpa.br.jatoba2