Given the complex mechanism of surface settlement induced by shield tunneling, accurate prediction of surface settlement and rational design of tunneling parameters are critical for ensuring safe and efficient tunneling operations. To address the limitations of the Informer algorithm in predicting surface settlement during shield tunneling, the standard convolution was replaced with dilated causal convolution, and three measures were employed: soil layer classification and characterization, a moving prediction window, and special factor handling. An improved Informer algorithm was developed. The prediction time of the improved Informer algorithm was reduced by up to 30.64% compared to the original algorithm. The improved Informer algorithm exhibited significant enhancements in prediction accuracy, perception range across different timescales, and computational efficiency. Compared with random forest and long short-term memory algorithms, the improved Informer algorithm achieved superior performance, making it more suitable for predicting surface settlement induced by shield tunneling. By integrating the improved Informer algorithm with Shapley additive explanations theory, the contributions of shield tunneling parameters to surface settlement were analyzed. A multi-objective optimization algorithm was constructed for the shield tunneling parameters. Key parameters, including the shield thrust, cutterhead torque, and tunneling speed, were selected for optimization. The surface settlement after parameter optimization was reduced by 16.79%.

Clogging in earth pressure balance (EPB) shield tunnelling through highly cohesive strata critically undermines construction efficiency. Conventional foam agents exhibit limited conditioning effectiveness, even with increased dosage. This study developed a dispersed foam agent by combining anionic surfactant (AES) with nonionic dispersant (HDT). The effects of air pressure (0–2 bar) and HDT content (0–10%) on macro-meso characteristics of foam and adhesion characteristics of conditioned soil were quantified through an evolutionary mechanism investigation of the bubble size distribution of foam, half-life measurements, and mechanical tests on conditioned soils. Results demonstrated that the influence of HDT content on foam exhibited pressure-dependent behavior. Under 0 bar within 0–10 min, HDT increased the proportion of small bubbles while marginally reducing the mean radii. Although HDT accelerated the degradation of small bubbles, it extended the foam half-life. Conversely, under 1 or 2 bar, HDT demonstrated opposite effects on these parameters. The cohesion of conditioned clays was reduced to 1.8–4.3 kPa, and adhesion amounts decreased to 10–15 g, significantly mitigating clogging risks. The optimal injection ratio of dispersed foam was determined for different pressures and clays. Engineering application in an EPB shield tunnelling section of Jinan Metro successfully resolved clogging issues, demonstrating the effectiveness of dispersed foam agent.