Algorithm for estimating the construction year of Brazilian bridges between 1950 and 1980

Abstract The year of construction is an essential factor in assessing the condition of bridges, as it directly influences the prediction of their deterioration and the analysis of their load-bearing capacity over time. In addition, this data is fundamental for algorithms that deal with missing information, such as that related to design standards. This study proposes and validates an algorithm to estimate the year of construction of Brazilian bridges based on three main characteristics: design vehicle, barrier type and width. The aim of the algorithm is to fill this information gap and provide managers with information to manage these infrastructures. An analysis of 5,000 bridges in the Bridge Management System revealed that 41.7% of them had no record of the year of construction. During validation, the algorithm showed robust performance, achieving a hit rate of 87.82 percent and a mean absolute error (MAE) of 5.20 years. After adjustments, the MAE was reduced to 4.45 years, with accuracy rates of 99.46% (±10 years) and 79.62% (±5 years). In practice, the algorithm successfully estimated the year of construction in 81.87% of cases, with the majority of bridges built in the 1970s (64.16%). These results provide a solid basis for more accurate deterioration predictions and more reliable load capacity assessments, contributing to more efficient and safer bridge management.

Authors

Institutions

Publication Details

Journal
REM - International Engineering Journal
Published
2025-01-01
DOI
https://doi.org/10.1590/0370-44672024780062
Primary Topic
Infrastructure Maintenance and Monitoring
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Algorithm for estimating the construction year of Brazilian bridges between 1950 and 1980

José Maria Franco de Carvalho, José Carlos Lopes Ribeiro, Matheus Sant’Anna Andrade, Ana Carolina Pereira Martins et al.
REM - International Engineering Journal
Infrastructure Maintenance and Monitoring
article

Algorithm for estimating the construction year of Brazilian bridges between 1950 and 1980

José Maria Franco de Carvalho, José Carlos Lopes Ribeiro, Matheus Sant’Anna Andrade, Ana Carolina Pereira Martins, Jose Campos Matos, Fernando Gussão Bellon, Kléos Magalhães Lenz César Júnior, Christian Alexandre Feitosa de Souza, Diôgo Silva de Oliveira, Marcos H. F. Ribeiro
article en

Abstract

Abstract The year of construction is an essential factor in assessing the condition of bridges, as it directly influences the prediction of their deterioration and the analysis of their load-bearing capacity over time. In addition, this data is fundamental for algorithms that deal with missing information, such as that related to design standards. This study proposes and validates an algorithm to estimate the year of construction of Brazilian bridges based on three main characteristics: design vehicle, barrier type and width. The aim of the algorithm is to fill this information gap and provide managers with information to manage these infrastructures. An analysis of 5,000 bridges in the Bridge Management System revealed that 41.7% of them had no record of the year of construction. During validation, the algorithm showed robust performance, achieving a hit rate of 87.82 percent and a mean absolute error (MAE) of 5.20 years. After adjustments, the MAE was reduced to 4.45 years, with accuracy rates of 99.46% (±10 years) and 79.62% (±5 years). In practice, the algorithm successfully estimated the year of construction in 81.87% of cases, with the majority of bridges built in the 1970s (64.16%). These results provide a solid basis for more accurate deterioration predictions and more reliable load capacity assessments, contributing to more efficient and safer bridge management.

REM - International Engineering JournalVol. 78(2)
Universidade Federal de Viçosa (BR), University of Minho (PT)
Openalex Percentile: Top 94%
Infrastructure Maintenance and Monitoring
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.