Accès libre

Dynamic Cost Estimation and Optimization Strategy in Engineering Cost Combining Reinforcement Learning

Xi Zhang

Xi Zhang

School of Civil Engineering, Chang’an UniversityChina
Recherchez cet auteur sur
Sciendo|Google Scholar
Zhang, Xi
  
11 avr. 2025
Dynamic Cost Estimation and Optimization Strategy in Engineering Cost Combining Reinforcement Learning's Cover Image
À propos de cet article
Article précédent
Article suivant
Citez
Télécharger la couverture
Publié en ligne: 11 avr. 2025
Reçu: 05 déc. 2024
Accepté: 05 mars 2025
DOI: https://doi.org/10.2478/amns-2025-0844
Mots clés
© 2025 Xi Zhang, published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1

A neural network-based cost estimation model.
A neural network-based cost estimation model.

Figure 2

Reinforcement learning framework for cost optimization.
Reinforcement learning framework for cost optimization.

Figure 3.

Pareto front representation for multi-objective cost optimization.
Pareto front representation for multi-objective cost optimization.

Figure 4.

Predicted vs. actual costs for different models.
Predicted vs. actual costs for different models.

Figure 5

Cost allocation before and after optimization.
Cost allocation before and after optimization.

Figure 6

Pareto front for multi-objective cost optimization.
Pareto front for multi-objective cost optimization.

Performance comparison of different cost estimation models_

Model MAE RMSE R2
Linear Regression 12.4% 18.2% 0.72
Support Vector Regression 9.8% 14.6% 0.81
Deep Neural Networks 6.2% 10.4% 0.89
Proposed Model 4.3% 7.6% 0.94

Cost savings achieved through rl-based optimization_

Project Type Initial Cost Estimate Optimized Cost Cost Savings (%)
Infrastructure Development $5.6M $5.2M 7.1%
Residential Construction $2.8M $2.6M 7.5%
Commercial Projects $4.2M $3.9M 7.1%
Langue:
Anglais
Périodicité:
1 fois par an
Sujets de la revue:
Sciences de la vie, Sciences de la vie, autres, Mathématiques, Mathématiques appliquées, Mathématiques générales, Physique, Physique, autres
RSS Feed de la revue