universidade lusófona

News

Student Mobility

Thiago Carreta Moro will be part of the team under the UNESP/ULHT research proposal “Deteção de danos estruturais através do sistema de monitoramento de integridade estrutural fisico cibernético baseado na inteligência artificial”, approved by the Brazilian entity FAPESP (2020/13690-9).

Special Issue on Integration of numerical modeling, monitoring and machine learning for SHM in Civil Structures

Call for papers

Guest Editors: Eloi Figueiredo, Ionut Moldovan and Yun Lai Zhou Cornal of Civil Structural Health Monitoring

Reconhecer Project

8 June 2020

This afternoon, two students from the MSc program of civil engineering hit the road again in order to perform the inventory of the bridges under the Barcelos Municipality responsability.

Submit your paper

22 May 2020

Structural health monitoring (SHM) has developed into an important area of research over recent decades in mechanical and civil engineering. SHM includes various sensing techniques, field testing, signal processing, transmission, and data management. Early damage identification can anticipate and warn against structural failures, preventing significant economic loss. Stronger and more in-depth understanding of structures can also benefit evaluation of current conditions and potential in-service life. This Special Collection aims to explore recent advances of SHM and damage identification, especially those for engineering applications. We encourage the submission of multidisciplinary studies, including investigations related to SHM from mechanical and civil engineering, numerical simulation, and signal processing. High quality original research and comprehensive review articles are both welcomed.

PhD Student mobility

17 October 2019

Mihai Bud, PhD student from the Technical University of Cluj-Napoca will spend one year at ULHT, in order to carry out research activities on SHM. Mihai’s PhD programme is aimed at developing an efficient hybrid strategy for the structural health monitoring of bridges. Finite element models of the structure are used as proxies for environmental and operational variability and damage, to generate data for the training of the MLAs. The models are computationally simple and generated probabilistically. The MLAs are casted using the Gaussian Mixture Model and the Mahalanobis Squared Distance algorithm.