The article “Fuel Consumption Prediction for Construction Trucks: A Noninvasive Approach Using Dedicated Sensors and Machine Learning” of the co-authorship of Gonçalo Pereira, Manuel Parente and João Moutinho, of BUILT CoLAB, and of Manuel Sampaio, MSc student of ISEP, has been published.
This paper is now part of the special issue “Artificial Intelligence in Geotechnical Infrastructure” of the journal Infrastructures, an international, open access, peer-reviewed scientific journal on infrastructures and that is published monthly by MDPI.
Article Summary: “Decision support and optimisation tools to be used in construction often require accurate estimation of cost variables to maximise their benefits. Heavy machinery is traditionally one of the biggest costs to consider, mainly due to fuel consumption. These typically diesel-powered machines have a large variability in fuel consumption depending on the usage scenario. This paper describes the creation of a framework designed to estimate the fuel consumption of construction trucks as a function of load carried, slope, distance, and pavement type. Having a more accurate estimate will increase the benefit of these optimisation tools. The fuel consumption estimation model was developed using Machine Learning (ML) algorithms supported by data, which was collected through various sensors, in a specially designed datalogger with wireless communication and opportunistic synchronization, in a real context experiment. The results demonstrated the feasibility of the method, providing important insight into the advantages associated with combining sensing and machine learning models in a real-world building scenario. Ultimately, this study comprises a significant step towards realising the implementation of IoT from a Construction 4.0 perspective, especially when considering its potential for twin real-time and digital applications.”
See the full article here.