@article{JIN2023, 
author = {Chunling JIN and Yang SU and Li GONG and Jingjing LIU and Jianzhou WEI},
title = {Configuration optimization of construction machine group for hydraulic tunnel under carbon emission constraint},
year = {2023},
journal = {Journal of Hohai University (Natural Sciences)},
volume = {51},
number = {3},
pages = {84-90},
keywords = {hydraulic tunnel, carbon emission, particle swarm optimization, multi-objective optimization, construction machine group configurations},
url = {https://www.sciopen.com/article/10.3876/j.issn.1000-1980.2023.03.011},
doi = {10.3876/j.issn.1000-1980.2023.03.011},
abstract = {A multi-objective optimization function based on the schedule-cost-quality-carbon emission is constructed according to the improvement path of optimization of hydraulic tunnel construction machine fleet and carbon emission reduction under the constraint of carbon emission. A particle swarm optimization (PSO) after the improvement of simulated annealing (SA) is selected and the carbon emission per working unit of construction machines is calculated with the reference to the construction machine-working cost quota and IPCC guidelines. By incorporating the new mechanical configuration into carbon emission factors, an evaluation system with duration, cost, quality and carbon emission as the primary indicators and 14 secondary indicators is established and the optimization model of fleet configuration considering carbon emissions is built. The optimization of construction machine fleet configuration under multi-objective constraints was carried out in the No. 3 branch of Wanjia tunnel of the Dianzhong water diversion project. The results show that the established target preference weight evaluation system of hydraulic tunnel construction fleet configuration can comprehensively consider the impact of construction fleets on the environment. The main carbon emission sources of the construction machine fleet are tunnel multifunctional work cart and concrete mixing plant, and the carbon emission(CO2) reaches 1000kg/machine working unit. The improved particle algorithm can effectively enhance the search capability of global optimization and identify the key risk sources of carbon emission in the construction machinery. Finally, the model optimization results are consistent with the on-site construction situation, which verifies the feasibility of the model.}
}