TY - GEN
T1 - Advanced framework for degradation modeling of operating structures
AU - Ben Seghier, Mohamed El Amine
AU - Jiménez Rios, Alejandro
AU - Plevris, Vagelis
AU - Dai, Jian
PY - 2024/7/12
Y1 - 2024/7/12
N2 - The safe operation of steel structures, such as bridges, is of paramount importance to mitigate potential issues. Consequently, the continuous and thorough monitoring of their operational conditions is imperative to uphold their safety and reliability. However, the inexorable process of corrosion, catalyzed by environmental conditions, leads to the inevitable deterioration of structural integrity over time. This research endeavors to predict the extent of corrosion in the primary cables of bridges through the application of advanced methodologies based on machine learning techniques. The execution of the proposed model necessitates the utilization of an extensive database encompassing diverse characteristics pertaining to the environmental properties of the surrounding region. The performance of the proposed models is rigorously assessed using a comprehensive suite of statistical and graphical metrics. The findings of this investigation underscore the effectiveness of the recommended solutions, surpassing previously established methodologies in addressing this pressing issue. The demonstrated success of the proposed model augurs favorably for its potential utility in furthering research into the dependability assessment of suspension bridge main cables.
AB - The safe operation of steel structures, such as bridges, is of paramount importance to mitigate potential issues. Consequently, the continuous and thorough monitoring of their operational conditions is imperative to uphold their safety and reliability. However, the inexorable process of corrosion, catalyzed by environmental conditions, leads to the inevitable deterioration of structural integrity over time. This research endeavors to predict the extent of corrosion in the primary cables of bridges through the application of advanced methodologies based on machine learning techniques. The execution of the proposed model necessitates the utilization of an extensive database encompassing diverse characteristics pertaining to the environmental properties of the surrounding region. The performance of the proposed models is rigorously assessed using a comprehensive suite of statistical and graphical metrics. The findings of this investigation underscore the effectiveness of the recommended solutions, surpassing previously established methodologies in addressing this pressing issue. The demonstrated success of the proposed model augurs favorably for its potential utility in furthering research into the dependability assessment of suspension bridge main cables.
KW - Suspension Bridges
KW - Corrosion
KW - Machine Learning
UR - https://library.oapen.org/handle/20.500.12657/91144
UR - http://www.scopus.com/inward/record.url?scp=85200356032&partnerID=8YFLogxK
U2 - 10.1201/9781003483755-57
DO - 10.1201/9781003483755-57
M3 - Chapter in a published conference proceeding
SN - 9781032770406
T3 - Bridge Maintenance, Safety, Management, Digitalization and Sustainability - Proceedings of the 12th International Conference on Bridge Maintenance, Safety and Management, IABMAS 2024
SP - 510
EP - 517
BT - Bridge Maintenance, Safety, Management, Digitalization and Sustainability - Proceedings of the 12th International Conference on Bridge Maintenance, Safety and Management, IABMAS 2024
A2 - Jensen, Jens Sandager
A2 - Frangopol, Dan M.
A2 - Schmidt, Jacob Wittrup
PB - Taylor and Francis
T2 - 12th International Conference on Bridge Maintenance, Safety and Management, IABMAS 2024
Y2 - 24 June 2024 through 28 June 2024
ER -