Adaptive Optimization of Shield Tunnel Segment Assembly Points by Integrating DBSCAN and Genetic Algorithm

In shield tunnel construction, segment assembly is a critical process, and its quality directly affects the overall performance and safety of the tunnel. Although the technology for shield tunnel segment assembly has developed, it still has limitations. Traditional methods for selecting assembly points often rely on experience or simple rules, making it difficult to adapt to the complex and dynamic construction environment.Genetic algorithms are widely used in optimization problems, and some studies have applied them to weight optimization for segment assembly point selection. However, existing methods often use fixed interval classification, which lacks flexibility and cannot dynamically adjust based on the actual data distribution. This leads to classification errors, particularly when dealing with unevenly distributed data.To address these issues, this paper proposes an innovative method that integrates DBSCAN (Density-Based Spatial Clustering of Applications with Noise) and genetic algorithms, aiming to achieve adaptive optimization of shield tunnel segment assembly points. The goal is to improve the accuracy and adaptability of assembly point selection, thereby enhancing tunnel construction quality.