• 국제학술발표논문집
• /
• The 10th International Conference on Construction Engineering and Project Management
• /
• pp.558-565
• /
• 2024

This paper presents the development of an optimization framework for road slope design. Recognizing the limitations of current manual stability analysis methods, which are time-consuming, are error-prone, and suffer from data mismatches, this study proposes a systematic approach to improve efficiency, reduce costs, and ensure the safety of infrastructure projects. The framework addresses the subjectivity inherent in engineers' decision-making process by formalizing decision variables, constraints, and objective functions to minimize costs while ensuring safety and environmental considerations. The necessity of this framework is embodied by the review of existing literature, which reveals a trend toward specialization within sub-disciplines of road design; however, a gap remains in addressing the complexities of road slope design through an integrated optimization approach. A genetic algorithm (GA) is employed as a fundamental optimization tool due to its well-established mechanisms of selection, crossover, and mutation, which are suitable for evolving road slope designs toward optimal solutions. An automated batch analysis process supports the GA, demonstrating the potential of the proposed framework. Although the framework focuses on the design optimization of single cross-section road slopes, the implications extend to broader applications in civil engineering practices. Future research directions include refining the GA, expanding the decision variables, and empirically validating the framework in real-world scenarios. Ultimately, this research lays the groundwork for more comprehensive optimization models that could consider multiple cross-sections and contribute to safer and more cost-effective road slope designs.

• 국제학술발표논문집
• /
• The 10th International Conference on Construction Engineering and Project Management
• /
• pp.1322-1322
• /
• 2024

Reinforced concrete (RC) , a major contributor to resource depletion and harmful emissions, fuels research on optimizing its design. Optimizing RC structures is challenging due to the mix of discrete and continuous variables, hindering traditional differentiation-based methods. Thus, this study aims to optimize RC structures cost-effectively using deep reinforcement learning. When the Agent selects design variables, Environment checks design criteria based on KDS 14-20 code (South Korea) and calculates reward. The Agent updates its Neural Network with this reward. Target for optimization is a simply supported doubly RC beam, with design variables including cross-section dimensions, sizes and quantities of tension and compression reinforcement, and size of stirrups. We used 200,000 training sets and 336 test sets, each with live load, dead load, beam length variables. To exclude labeled data, multiple training iterations were conducted. In the initial training, the reward was the ratio of maximum possible cost at beam length to the designed structure's cost. Next iterations used the ratio of optimal values by the previous Agent to the current Agent as the reward. Training ended when the difference between optimal values from the previous and current Agent was within 1% for test data. Brute Force Algorithm was applied to the test set to calculate the actual cost-optimal design for validation. Results showed within 10% difference from actual optimal cost, indicating successful deep reinforcement learning application without labeled data. This study benefits the rapid and accurate calculation of optimized designs and construction processes in Building Information Modeling (BIM) applications.