Reasonable tunnelling parameters for underwater shield tunnels play an important role in maintaining driving efficiency and safety. In this paper, a neural network method was developed to predict tunnelling parameters. Soil properties and geometric parameters were taken as inputs for the neural network, which output the tunnelling parameters, such as advancing thrust, rotation, penetration, torque of the cutter head, and support pressure. In order to improve the stability of the neural network, a genetic algorithm (GA) with a global searching ability was used to optimize the initial weight of the neural network (GA-BPNN). The accuracy of the algorithm, based on GA-BPNN, was studied through an underwater shield tunnel project. The results showed that the integration of GA into the neural network significantly improves the prediction ability for shield tunnelling parameters, especially for adjustable parameters. Later, the developed GA-BPNN model was further utilized to predict and set the range of shield tunnelling parameters in fine sand stratum of high risk. Through a comparative analysis of tunnelling parameters, the reasons leading to ground instability have been found out, and the effectiveness of ground pre-reinforcement has been verified.

The application of polymer flocculants plays a pivotal role in the slurry separation process of shields, and the dispersant used for treating cutter mud cakes can significantly impact the effectiveness of polymer flocculants, potentially leading to reduced efficiency in slurry separation. Experiments were conducted to select appropriate flocculants and investigate the influence of dispersants on flocculant effectiveness, aiming to assess the effect of flocculants and explore the relationships and mechanisms governing their influence. Changes in the patterns of slurry flocculation were revealed in terms of flocculation-driven precipitation and vacuum-filtration effects. The purpose of this article is to provide a reference for the field application of polymer flocculants in the shield field. The conclusions are as follows. Inorganic flocculants containing 0.5% polyaluminum chloride (PAC) exhibit the most effective flocculation, demonstrating strong charge neutralization action. Organic flocculants containing 0.1% cationic polyacrylamides (CPAM) exhibit the most effective flocculation, demonstrating strong bridging and net capture effects. The dispersant sodium hexametaphosphate (SHMP) can significantly weaken the charge-neutralizing action of flocculants and slightly enhance bridging and net capture effects. SHMP can impede the flocculation of slurry with PAC. For CPAM, SHMP can enhance the flocculation of slurry at a low mass fraction (0.1% and 0.3%), while SHMP can significantly hinder flocculation at a high mass fraction (0.5% and 1%). A low mass fraction of SHMP reduced slurry viscosity to 246.3 mPa.s and enhanced vacuum filtration, while a high mass fraction of SHMP increased slurry viscosity to 667.2 mPa.s and hindered vacuum filtration. In conclusion, while dispersants reduce the effectiveness of inorganic flocculants at any mass fraction, a small number of dispersants enhances the performance of organic flocculants; thus, the organic flocculant CPAM is recommended for slurry separation.