This study focuses on the settlement of buildings around the foundation pit caused by foundation pit dewatering. Within the study context, a test is conducted on the control of ground settlement during double-layered foundation pit dewatering based on the seepage control-recharge coupling effect. Moreover, a large indoor seepage test device is developed to accurately simulate in-situ three-dimensional seepage conditions of double-layer foundations. The study results showed that compared to the antiseepage conditions, upon the additional recharge, the head of the upper row of the pressure measuring tubes outside the foundation pit is raised by nearly 10.7%, and the water level of the lower row of pressure measuring tubes is raised by about 3.1%. Additionally, the head of the outer side of each pressure measuring tube is higher than that of the inner side by about 2.75% on average, indicating that the recharge outside the pit can effectively increase the head height in the area above the soil layer at the bottom of the recharging well outside the foundation pit and reduce the settlement of the building outside the foundation pit. The numerical calculation of the settlement outside the pit using FLAC3D software further confirms the effect of the seepage control-recharge coupling model on the ground settlement during foundation pit dewatering. The research results are important for the infiltration deformation and foundation settlement control in composite foundations precipitation.

NOx is a harmful by-product of coal-fired boilers, and accurate prediction of NOx emissions in the outlet of a boiler is essential for environmental protection. In recent years, data-driven models have been widely studied and applied in this area. However, dynamic characteristics are ignored by many existing models, leading to sub-optimal performance. Besides, outliers that occur in the operation data have adverse effects on the efficacy of these prediction models.To address these issues, this paper presents a novel method for predicting NOx concentration via integrating a robust dynamic probabilistic approach and the long short-term memory (LSTM). First, mutual information (MI) is applied to determine the input variables. Subsequently, a robust probabilistic method is proposed to extract dynamic latent features considering outliers. On this basis, the generated latent variables are further utilized to train the LSTM-based model, with which the intrinsic relation between inputs and NOx values are obtained. Based on the application to a 660 MW thermal power plant, the superiority of the proposed method is demonstrated in terms of high prediction accuracy.