Carbon emission analysis of precast concrete building Construction: A study on component transportation phase using Artificial Neural Network

Abstract

Off-site construction has been widely adopted for its carbon reduction potential. However, the emissions from its transportation stage are not fully explored. Given the rising prominence of Battery Electric Vehicles (BEVs), this study explores their potential carbon reduction benefits during the transportation of prefabricated components by comparing emissions from Fossil Vehicles (FVs) and BEVs. An Artificial-Neural-Network-based emission model is developed to estimate the carbon emissions of both vehicle types. Specifically, the model collects the real-time carbon emission dynamics across varying external conditions, encompassing diverse transportation constraints, vehicle operational statuses, and road conditions. By employing a supervised learning framework, the transportation carbon emission coefficient of prefabricated components is determined. Comparative analysis reveals that BEVs consistently outperforms FVs, achieving a peak reduction rate of 47.76%. The negative correlation between the reduction rate of BEVs and factors like average speed and load rate underscores BEVs' advantage in urban transportation scenarios, where these factors tend to be low. Hence, the integration of BEVs in the transportation of prefabricated components is advocated. This study provides robust carbon emissions coefficients for BEVs in the transportation of prefabricated components, filling the gap in current estimation methods. These coefficients present a valuable tool for researchers, aiding in the accurate estimation of transportation carbon emissions and fostering the conceptualization of innovative carbon reduction tactics through BEV adoption.