Prioritization of Texas prestressed concrete bridges for future truck platoon loading

Autonomous truck platoons shall soon be traveling our highway system with greater frequency. The objective of the presented study is to conduct a high-level evaluation of the Texas concrete bridge inventory when subjected to potential truck platoon loading. The National Bridge Inventory (NBI) database is utilized to the greatest extent possible. In addition, a significant literature review is performed to make assumptions allowing estimated load rating calculations for the prestressed concrete bridges likely to support future platoons (nearly 3,000 bridges). The truck platoon load ratings, combined with the NBI structural evaluation condition ratings, are utilized to prioritize each bridge. As a result, bridges are identified for more detailed evaluation prior to future truck platoon implementation. Data analysis was also performed to further understand the impact of various parameters on the load rating and prioritization results. Conclusions were drawn regarding the sensitivity of the (1) original design methodology, (2) bridge span length, (3) truck type, (4) truck spacing and (5) number of trucks within a platoon. In addition, a secondary benefit of the study is a presented framework for other bridge owners to prioritize their bridges that may be subjected to truck platoon or other heavy vehicle loading.

Construction cost estimation of reinforced and prestressed concrete bridges using machine learning

Seven state-of-the-art machine learning techniques for estimation of construction costs of reinforced-concrete and prestressed concrete bridges are investigated in this paper, including artificial neural networks (ANN) and ensembles of ANNs, regression tree ensembles (random forests, boosted and bagged regression trees), support vector regression (SVR) method, and Gaussian process regression (GPR). A database of construction costs and design characteristics for 181 reinforced-concrete and prestressed-concrete bridges is created for model training and evaluation.