Structural Health Fuzzy Classification of Bridge based on Subjective and Objective Inspections

Alejandrino, Jonnel; Concepcion, Ronnie; Lauguico, Sandy; Almero, Vincent Jan D.; Guia, Justin D. de; Flores, Ramón; Dadios, Elmer P.

doi:10.1109/hnicem51456.2020.9400054

Cited by 5 publications

(1 citation statement)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gordan et al used a hybrid artificial neural network-based imperial competitive algorithm to predict the severity and location of multiple damages [15]. Alejandrino et al proposed a fuzzy inference-based structural health condition assessment using subjective and objective inspection data [16]. Abdelkader et al developed a model using a hybrid artificial neural network-particle swarm optimization model to predict spalling areas accurately [17].…”

Section: Literaturementioning

confidence: 99%

Application of Soft Computing Techniques in Bridge Health Assessment: A Review

Khan¹,

Topdar²,

Datta³

2023

Data Science and Intelligent Computing Techniques

View full text Add to dashboard Cite

Bridges are complex structures of highway networks. Regular inspection and maintenance are required to keep these structures safe and functional. Decision-makers often face challenges in selecting maintenance and repair plans for the massive backlog of deteriorated bridge structures within limited budget. Several approaches are available for the health evaluation of bridges, such as visual inspection, non-destructive tests, and sensors. However, the information is somewhat uncertain no matter what the inspection procedure used to gather the health information of bridges. Further, uncertainty in the collected data hampers the reliability of the evaluation process. Therefore, there is a lack of reliable procedures for prioritizing bridges using present health conditions. So, computational techniques are required to tackle the imprecision and uncertainty of bridge inspection data and provide reliable bridge maintenance and management information. In this context, soft computing is a useful technique for extracting meaningful information from a dataset inherent uncertainty. Hence, this study attempted to review the current state of the application of soft computing techniques in bridge health assessment. The articles between 2019 to 2022 were reviewed. Different soft computing techniques were found to be compatible with different inspection data types (visual inspection data, NDT data, or sensor data). The current review found that applying a specific soft computing technique to a particular data type is helpful for reliable health assessment.

show abstract

Section: Literaturementioning

confidence: 99%