Developing an AI-Based Model for Optimizing Concrete Work Cycle in Building Construction
Angga Trisna Yudhistira, Prof. Ir. Iman Satyarno, ME, Ph.D.
2025 | Disertasi | S3 Teknik Sipil
Sebuah kerangka berbasis AI untuk mengoptimasi penggunaan CAA dan
schedule pengecoran telah dikembangkan pada penelitian ini. Optimasi campuran
beton dengan CAA dilakukan dengan Particle Swarm Optimization (PSO) menggunakan
parameter kuat tekan umur 3 hari, biaya produksi, dan embodied carbon. Hasil
campuran optimal dari PSO digunakan untuk simulasi siklus pengecoran pada kasus
proyek sesungguhnya.
Hasil simulasi menunjukkan bahwa, optimasi siklus pengecoran
dengan memanfaatkan CAA dapat menurunkan biaya hingga 21-24?ri biaya semula dan
mempercepat durasi pelaksanaan hingga 30-40?ri durasi awal. Selain itu,
optimasi siklus pengecoran juga berkontribusi dalam penurunan total emisi
karbon sebesar 10-11?ngan kontributor utama adalah pengurangan embodied
carbon dalam beton.
Reinforced concrete structures are critical
components of high-rise buildings. The duration of their construction is
primarily determined by the concreting cycle, which includes activities such as
formwork preparation, rebar installation, shoring installation, concrete
pouring, and formwork and shoring dismantling. The effects of shortening the concreting
cycle by using a concrete accelerator admixture (CAA) to increase the early
strength of the concrete has been studied. This study aims to develop an AI-based framework
for optimizing CAA usage and concreting schedules to mitigate delays, reduce
costs, and minimize carbon emissions in building construction.
An AI-based model for optimizing CAA usage and
concreting schedules has been developed in this research. Concrete mix
optimization with CAA was carried out using Particle Swarm Optimization (PSO)
using 3-day compressive strength, production costs, and embodied carbon
parameters. The optimal mix results from PSO were used to simulate the concreting
cycle in real project cases.
The simulation results showed that optimization
of the casting cycle by utilizing CAA can reduce costs by 21-24% of the
original cost and accelerate the implementation duration by 30-40% of the
initial duration. In addition, optimization of the casting cycle also
contributed to a reduction in total carbon emissions by 10-11%, with the main
contributor being the reduction of embodied carbon in concrete.
Kata Kunci : AI-based optimization, reinforced concrete, concreting cycle, acceleration, schedule, cost, concrete admixture, carbon emission