Feedforward Analysis for Shield-Ground System

Abstract

Ground surface settlement is an important measurement in identifying potential damages for shield tunneling. Identifying the relationship between shield parameters and the resulting settlement is of vital importance to the reasonable adjustment of the shield parameters so as to control settlement development. However, many other factors, besides the shield parameters, affect settlement, which makes shield-ground interaction complicated. Therefore, a better method is necessary for extracting the shield-ground relationship for the purpose of steering shield tunneling. This paper proposes a method that incorporates smooth relevance vector machine (sRVM) and particle swarm optimization (PSO) for shield steering with concern for settlement control. First, smooth relevance vector machine with adaptive Gaussian kernel function is used to establish the relationship between the identified factors and the settlement. Particle swarm optimization is then applied to identify the appropriate kernel parameters. Then, optimal shield parameters are searched based on the established relationships. A slurry shield-driven tunnel (the Jiyuqiao-Jianghan Road tunnel) is used to validate the method. The results evaluate the potential as well as some limitations of the proposed method, which attempts to offer an alternative means for feedforward control of shield steering.