Bridge Type Classification: Supervised Learning on a Modified NBI Data Set

Abstract

A key phase in the bridge design process is the selection of the structural system. Due to budget and time constraints, engineers typically rely on engineering judgment and prior experience when selecting a structural system, often considering a limited range of design alternatives. The objective of this study was to explore the suitability of supervised machine learning as a preliminary design aid that provides guidance to engineers with regards to the statistically optimal bridge type to choose, ultimately improving the likelihood of optimized design, design standardization, and reduced maintenance costs. In order to devise this supervised learning system, data for over 600,000 bridges from the National Bridge Inventory database were analyzed. Key attributes for determining the bridge structure type were identified through three feature selection techniques. Potentially useful attributes like seismic intensity and historic data on the cost of materials (steel and concrete) were then added from the US Geological Survey (USGS) database and Engineering News Record. Decision tree, Bayes network and Support Vector Machines were used for predicting the bridge design type. Due to state-to-state variations Published link: https://ascelibrary.org/doi/full/10.1061/(ASCE) CP.1943-5487.0000712 in material availability, material costs, and design codes, supervised learning models based on the complete data set did not yield favorable results. Supervised learning models were then trained and tested using 10-fold cross validation on data for each state. Inclusion of seismic data improved the model performance noticeably. The data was then resampled to reduce the bias of the models towards more common design types, and the supervised learning models thus constructed showed further improvements in performance. The average recall and precision for the state models was 88.6% and 88.0% using Decision Trees, 84.0% and 83.7% using Bayesian Networks, and 80.8% and 75.6% using SVM.The design and construction of a structure has several stages (Figure 1). In the first stage, the initial design requirements such as site constraints and usage demands are defined. In the next stage, preliminary design, the structural system and design materials are chosen (e.g.: steel trusses or concrete box beams). Because project budgets and time are limited at this phase, initial prototyping is generally reliant on the engineering judgment and prior experiences of the design engineer. This often means that engineers only consider a limited set of structural systems that seem most feasible, and explicit design optimization is not considered. The preliminary design forms the basis for a cost estimate and final design of the structure, and so choosing a suboptimal structural system can lead to unnecessarily high project costs and other inefficiencies.A computer-based decision support system could help guide preliminary design teams towards optimal structural designs by using initial design criteria as program input and rapidly Published link: https://asc...

Machine learning and image processing approaches for estimating concrete surface roughness using basic cameras

“…For bridge applications, Jootoo and Lattanzi (2017) proposed a supervised machine learning to assess bridge designers on choosing suitable bridge systems based on the national bridge inventory (NBI) database.…”