ARTÍCULO
TITULO

A Novel Integrated Optimization System for Earthwork Tasks

Manuel Parente    
António Gomes Correia    
Paulo Cortez    

Resumen

Earthworks are part of the construction of any type of ground transport infrastructure. In many road and railway infrastructures earthworks represent up to 30 to 50% of total cost of the construction. Moreover, earthworks involve the use of heavy mechanical equipment (e.g., excavators, dumper trucks, bulldozers and rollers) and repetitive activities that are responsible for large amounts of carbon emissions with negative impact to the environment. In this context, the optimization of earthworks construction activities is becoming increasingly important in recent years, while effective and practical integrated solutions have not been established so far. As such, this work introduces a novel optimization integrated system for earthwork tasks. In this integrated system, the optimization is carried out on various fronts, namely minimization of execution cost and duration, while attempting to reduce environmental impacts, such as carbon emissions. In order to achieve this, the integration of a wide array of technologies is required, so as to allow for a proper adjustment to reality. These range from evolutionary computation and data mining (i.e., soft computing), to geographic information systems and linear programming. The former are used firstly to provide realistic estimates of the productivity of available resources (i.e., equipment), and secondly to perform their optimal allocation throughout the construction site. Concurrently, the latter are employed for supporting the optimization of resource and material management, as well as of the trajectories associated with transportation of material from excavation to embankment fronts. The system has been validated using real-world data stemming from a Portuguese road construction site. Results show that the proposed system is very competitive when compared with the manual allocation methodologies currently used for the design and construction of earthworks. In fact, the system can output several different resource distribution solutions, which comprehend a trade-off between the referred optimization objectives, enhancing the flexibility of design by allowing the user to select the solution that best fits the project restrictions (e.g., deadline, budget). As such, the system is capable of allocating the available equipment in a way that maximizes its potential and productivity, while indirectly guaranteeing minimum carbon emissions in each possible solution. These results emphasize the importance of using this kind of decision support/optimization tools in the design and construction of earthworks.

 Artículos similares

       
 
Gleice Kelly Barbosa Souza, Samara Oliveira Silva Santos, André Luiz Carvalho Ottoni, Marcos Santos Oliveira, Daniela Carine Ramires Oliveira and Erivelton Geraldo Nepomuceno    
Reinforcement learning is an important technique in various fields, particularly in automated machine learning for reinforcement learning (AutoRL). The integration of transfer learning (TL) with AutoRL in combinatorial optimization is an area that requir... ver más
Revista: Algorithms

 
Pin-Hung Juan and Ja-Ling Wu    
In this study, we present a federated learning approach that combines a multi-branch network and the Oort client selection algorithm to improve the performance of federated learning systems. This method successfully addresses the significant issue of non... ver más
Revista: Algorithms

 
Roberto Scigliano, Valeria De Simone, Roberta Fusaro, Davide Ferretto and Nicole Viola    
The design of integrated and highly efficient solutions for thermal management is a key capability for different aerospace products, ranging from civil aircraft using hydrogen on board to miniaturized satellites. In particular, this paper discloses a nov... ver más
Revista: Aerospace

 
Shubin Zhang, Peifang Dai, Ning Li and Yanbo Chen    
Integrated circuits suffer severe deterioration due to single-event upsets (SEUs) in irradiated environments. Spin-transfer torque magnetic random-access memory (STT-MRAM) appears to be a promising candidate for next-generation memory as it shows promisi... ver más
Revista: Applied Sciences

 
Tianyi Yang, Marcus White, Ruby Lipson-Smith, Michelle M. Shannon and Mehrnoush Latifi    
Changing the physical environment of healthcare facilities can positively impact patient outcomes. Virtual reality (VR) offers the potential to understand how healthcare environment design impacts users? perception, particularly among those with brain in... ver más
Revista: Buildings