Optimized Design of Low-Carbon Mix Ratio for Non-Dominated Sorting Genetic Algorithm II Concrete Based on Genetic...

Area of Science:

• Civil Engineering
• Materials Science
• Environmental Science

Background:

• Intelligent mix ratio design is crucial for low-carbon concrete.
• Existing methods require optimization for accuracy and environmental impact.

Purpose of the Study:

• To develop and validate a low-carbon concrete mix design methodology.
• To improve the accuracy of concrete mix ratio prediction and optimization.
• To reduce the cost and carbon footprint of concrete production.

Main Methods:

• Constructed a concrete mix ratio database and performed statistical analysis.
• Employed standard back propagation (BP) and genetic algorithm-improved BP (GA-BP) for prediction.
• Utilized the Fast Non-Dominated Sorting Genetic Algorithm II (NSGA-II) for mix ratio optimization.

Main Results:

• GA-BP showed improved fitting accuracies over standard BP (4.9% to 16.7%).
• Optimized mix ratio for C50 concrete: cement 331.3, sand 639.4, stone 1039, fly ash 56, water 153, water-reducing agent 0.632 kg/m³.
• Achieved low relative errors (2.1% for strength, 0.6% for cost, 2.9% for carbon emissions).
• Reduced costs by 7.2% and carbon emissions by 15.9% compared to commercial concrete.

Conclusions:

• The integrated methodology enhances concrete design accuracy and reduces environmental impact.
• The optimized mix design offers significant economic and environmental benefits.
• Further research integrating material selection and structural optimization for low-carbon construction is encouraged.